diff --git a/ChangeLog.md b/ChangeLog.md new file mode 100644 --- /dev/null +++ b/ChangeLog.md @@ -0,0 +1,4 @@ +# 6.2 + + - This release has removed `wordout_dropkey` because the corresponding + constant in Bibutils has also been removed. diff --git a/README b/README deleted file mode 100644 --- a/README +++ /dev/null @@ -1,125 +0,0 @@ -% Haskell Bindings to Bibutils, the Bibliography Conversion Utilities -% Andrea Rossato - -About ------ - -[hs-bibutils] is library with Haskell bindings to Chris Putnam's -[bibutils], a library that interconverts between various bibliography -formats using a common MODS-format XML intermediate. - -[hs-bibutils] can be used with [citeproc-hs] and [pandoc] to read and -use various bibliographic database formats for processing and -automatically formatting citations and references according to a [CSL] -style. - -[citeproc-hs] adds to [pandoc], the famous [Haskell] text processing -tool, a Bibtex like citation and bibliographic formatting and -generation facility. - -[CSL] is an XML language for specifying citation and bibliographic -formatting, similar in principle to BibTeX `.bst` files or the binary -style files in commercial products like Endnote or Reference Manager. - -Download --------- - -[hs-bibutils] can be downloaded from [Hackage]: - - - -To get the darcs source run: - - darcs get http://code.haskell.org/hs-bibutils/ - -Installation ------------- - -[hs-bibutils] does not require [bibutils] to be installed, since it -ships with its one version of the library. To build and install -[hs-bibutils] unpack the tar archive, in the source directory run: - - runhaskell Setup.lhs configure - runhaskell Setup.lhs build - runhaskell Setup.lhs install - -This last step requires `root` privileges. - -If you don't have `root` privileges you can install [hs-bibutils] -locally with these commands: - - runhaskell Setup.lhs configure --user --prefix=$HOME - runhaskell Setup.lhs build - runhaskell Setup.lhs install --user - -[hs-bibutils] should be compatible with cabal-install. - -Documentation -------------- - -The [Haddock] generated documentation is available here: - - - -The original API documentation is available here: - - - -Bug Reports ------------ - -To submit bug reports you can use the [citeproc-hs] bug tracking -system available at the following address: - - - -Credits -------- - -Thanks to [Chris Putnam] for his help. - -Author ------- - -Andrea Rossato - -`andrea.rossato at unitn.it` - -Links to Related Projects ----------------- - -Bibutils -: - -Pandoc -: - -Citeproc-hs: -: - -CSL -: - -Legal ------ - -This software is released under the GNU GPL. See LICENSE for more -details. - -This is an early, "alpha" release. It carries no warranties of any kind. - -Copyright © 2008 - 2010 Andrea Rossato - -[hs-bibutils]: http://code.haskell.org/hs-bibutils -[bibutils]: http://www.scripps.edu/~cdputnam/software/bibutils/ -[Hackage]: http://hackage.haskell.org/cgi-bin/hackage-scripts/package/hs-bibutils -[citeproc-hs]: http://code.haskell.org/citeproc-hs -[CSL]: http://citationstyles.org/ -[pandoc]: http://johnmacfarlane.net/pandoc/ -[Zotero]: http://www.zotero.org -[MODS]: http://www.loc.gov/mods/ -[Bruce D'Arcus]: http://community.muohio.edu/blogs/darcusb/ -[John MacFarlane]: http://johnmacfarlane.net/ -[Chris Putnam]: http://www.scripps.edu/~cdputnam/ -[Haskell]: http://www.haskell.org/ -[Haddock]: http://www.haskell.org/haddock/ diff --git a/README.md b/README.md new file mode 100644 --- /dev/null +++ b/README.md @@ -0,0 +1,95 @@ +About +----- + +[hs-bibutils] is library with Haskell bindings to Chris Putnam's +[bibutils], a library that interconverts between various bibliography +formats using a common MODS-format XML intermediate. + +[hs-bibutils] can be used with [pandoc-citeproc] to read and use various +bibliographic database formats for processing and automatically formatting +citations and references according to a [CSL] style. + +[pandoc-citeproc] adds to [pandoc], the famous [Haskell] text processing +tool, a Bibtex like citation and bibliographic formatting and generation +facility. + +[CSL] is an XML language for specifying citation and bibliographic +formatting, similar in principle to BibTeX `.bst` files or the binary +style files in commercial products like Endnote or Reference Manager. + +Documentation +------------- + +The [Haddock] generated documentation is available here: + + + +Bug Reports +----------- + +To submit bug reports you can use the [hs-bibutils] bug tracking +system available at the following address: + + + +Credits +------- + +Thanks to [Chris Putnam] for his help. + +Author +------ + +Andrea Rossato + +`andrea.rossato at unitn dot it` + +Maintainer +---------- + +Václav Haisman + +`vhaisman at gmail dot com` + +Links to Related Projects +---------------- + +Bibutils +: + +Pandoc +: + +Pandoc-Citeproc +: + +Citeproc-hs: +: + +CSL +: + +Legal +----- + +This software is released under the GNU GPL. See LICENSE for more +details. + +This is an early, "alpha" release. It carries no warranties of any kind. + +Copyright © 2008 – 2010 Andrea Rossato + +[hs-bibutils]: https://github.com/wilx/hs-bibutils +[bibutils]: https://sourceforge.net/p/bibutils/home/Bibutils/ +[Hackage]: http://hackage.haskell.org/cgi-bin/hackage-scripts/package/hs-bibutils +[citeproc-hs]: http://istitutocolli.org/repos/citeproc-hs/ +[CSL]: http://citationstyles.org/ +[pandoc]: http://pandoc.org/ +[pandoc-citeproc]: https://github.com/jgm/pandoc-citeproc +[Zotero]: http://www.zotero.org +[MODS]: http://www.loc.gov/mods/ +[Bruce D'Arcus]: http://community.muohio.edu/blogs/darcusb/ +[John MacFarlane]: http://johnmacfarlane.net/ +[Chris Putnam]: http://www.scripps.edu/~cdputnam/ +[Haskell]: http://www.haskell.org/ +[Haddock]: http://www.haskell.org/haddock/ diff --git a/bibutils/adsout.c b/bibutils/adsout.c --- a/bibutils/adsout.c +++ b/bibutils/adsout.c @@ -1,8 +1,8 @@ /* * adsout.c * - * Copyright (c) Richard Mathar 2007-2014 - * Copyright (c) Chris Putnam 2007-2014 + * Copyright (c) Richard Mathar 2007-2017 + * Copyright (c) Chris Putnam 2007-2017 * * Program and source code released under the GPL version 2 * @@ -13,12 +13,17 @@ #include #include #include "utf8.h" -#include "newstr.h" +#include "str.h" #include "strsearch.h" #include "fields.h" #include "name.h" -#include "adsout.h" +#include "title.h" +#include "url.h" +#include "bibformats.h" +static int adsout_write( fields *in, FILE *fp, param *p, unsigned long refnum ); +static void adsout_writeheader( FILE *outptr, param *p ); + void adsout_initparams( param *p, const char *progname ) { @@ -76,7 +81,7 @@ } match_type; static int -get_type( fields *info ) +get_type( fields *in ) { match_type match_genres[] = { { "academic journal", TYPE_ARTICLE }, @@ -101,15 +106,15 @@ char *tag, *data; int i, j, type = TYPE_UNKNOWN; - for ( i=0; in; ++i ) { - tag = info->tag[i].data; + for ( i=0; in; ++i ) { + tag = in->tag[i].data; if ( strcasecmp( tag, "GENRE" )!=0 && strcasecmp( tag, "NGENRE" )!=0 ) continue; - data = info->data[i].data; + data = in->data[i].data; for ( j=0; jlevel[i]==0 ) type = TYPE_BOOK; + if ( in->level[i]==0 ) type = TYPE_BOOK; else type = TYPE_INBOOK; } else if ( !strcasecmp( data, "collection" ) ) { - if ( info->level[i]==0 ) type = TYPE_BOOK; + if ( in->level[i]==0 ) type = TYPE_BOOK; else type = TYPE_INBOOK; } - if ( type!=TYPE_UNKNOWN ) fields_setused( info, i ); + if ( type!=TYPE_UNKNOWN ) fields_setused( in, i ); } } if ( type==TYPE_UNKNOWN ) { - for ( i=0; in; ++i ) { - if ( strcasecmp( info->tag[i].data, "RESOURCE" ) ) + for ( i=0; in; ++i ) { + if ( strcasecmp( in->tag[i].data, "RESOURCE" ) ) continue; - data = info->data[i].data; + data = in->data[i].data; if ( !strcasecmp( data, "moving image" ) ) type = TYPE_BROADCAST; else if ( !strcasecmp( data, "software, multimedia" ) ) type = TYPE_PROGRAM; - if ( type!=TYPE_UNKNOWN ) fields_setused( info, i ); + if ( type!=TYPE_UNKNOWN ) fields_setused( in, i ); } } @@ -147,81 +152,144 @@ return type; } -static void -output_title( FILE *fp, fields *f, char *full, char *sub, char *adstag, int level ) +static int +append_title( fields *in, char *ttl, char *sub, char *adstag, int level, fields *out, int *status ) { - newstr *fulltitle, *subtitle, *vol, *iss, *sn, *en, *ar; + str fulltitle, *title, *subtitle, *vol, *iss, *sn, *en, *ar; + int fstatus, output = 0; - fulltitle = fields_findv( f, level, FIELDS_STRP, full ); - subtitle = fields_findv( f, level, FIELDS_STRP, sub ); + str_init( &fulltitle ); - if ( fulltitle && fulltitle->len ) { + title = fields_findv( in, level, FIELDS_STRP, ttl ); + subtitle = fields_findv( in, level, FIELDS_STRP, sub ); - fprintf( fp, "%s %s", adstag, fulltitle->data ); - if ( subtitle && subtitle->len ) { - if ( fulltitle->data[ fulltitle->len - 1 ] != '?' ) - fprintf( fp, ": " ); - else fprintf( fp, " " ); - fprintf( fp, "%s", subtitle->data ); - } + if ( str_has_value( title ) ) { - vol = fields_findv( f, LEVEL_ANY, FIELDS_STRP, "VOLUME" ); - if ( vol && vol->len ) fprintf( fp, ", vol. %s", vol->data ); + output = 1; - iss = fields_findv_firstof( f, LEVEL_ANY, FIELDS_STRP, "ISSUE", + title_combine( &fulltitle, title, subtitle ); + + vol = fields_findv( in, LEVEL_ANY, FIELDS_STRP, "VOLUME" ); + if ( str_has_value( vol ) ) { + str_strcatc( &fulltitle, ", vol. " ); + str_strcat( &fulltitle, vol ); + } + + iss = fields_findv_firstof( in, LEVEL_ANY, FIELDS_STRP, "ISSUE", "NUMBER", NULL ); - if ( iss && iss->len ) fprintf( fp, ", no. %s", iss->data ); + if ( str_has_value( iss ) ) { + str_strcatc( &fulltitle, ", no. " ); + str_strcat( &fulltitle, iss ); + } - sn = fields_findv( f, LEVEL_ANY, FIELDS_STRP, "PAGESTART" ); - en = fields_findv( f, LEVEL_ANY, FIELDS_STRP, "PAGEEND" ); - ar = fields_findv( f, LEVEL_ANY, FIELDS_STRP, "ARTICLENUMBER" ); - if ( sn && sn->len ) { - if ( en && en->len ) - fprintf( fp, ", pp." ); - else - fprintf( fp, ", p." ); - fprintf( fp, " %s", sn->data ); - } else if ( ar && ar->len ) { - fprintf( fp, ", p. %s", ar->data ); + sn = fields_findv( in, LEVEL_ANY, FIELDS_STRP, "PAGES:START" ); + en = fields_findv( in, LEVEL_ANY, FIELDS_STRP, "PAGES:STOP" ); + ar = fields_findv( in, LEVEL_ANY, FIELDS_STRP, "ARTICLENUMBER" ); + + if ( str_has_value( sn ) ) { + if ( str_has_value( en ) ) { + str_strcatc( &fulltitle, ", pp. " ); + } else { + str_strcatc( &fulltitle, ", p. " ); + } + str_strcat( &fulltitle, sn ); + } else if ( str_has_value( ar ) ) { + str_strcatc( &fulltitle, ", p. " ); + str_strcat( &fulltitle, ar ); } - if ( en && en->len ) { - fprintf( fp, "-%s", en->data ); + if ( str_has_value( en ) ) { + str_addchar( &fulltitle, '-' ); + str_strcat( &fulltitle, en ); } - fprintf( fp, "\n" ); + if ( str_memerr( &fulltitle ) ) { + *status = BIBL_ERR_MEMERR; + goto out; + } + + fstatus = fields_add( out, adstag, str_cstr( &fulltitle ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + +out: + str_free( &fulltitle ); + + return output; } static void -output_people( FILE *fp, fields *f, char *tag1, char *tag2, char *tag3, char *adstag, int level ) +append_titles( fields *in, int type, fields *out, int *status ) { - newstr oneperson; + int added; + if ( type==TYPE_ARTICLE || type==TYPE_MAGARTICLE ) { + added = append_title( in, "TITLE", "SUBTITLE", "%J", LEVEL_HOST, out, status ); + if ( added==0 ) + (void) append_title( in, "SHORTTITLE", "SHORTSUBTITLE", "%J", LEVEL_HOST, out, status ); + } +} + +static void +append_people( fields *in, char *tag1, char *tag2, char *tag3, char *adstag, int level, fields *out, int *status ) +{ + str oneperson, allpeople; + vplist_index i; + int fstatus; vplist a; - int i; - newstr_init( &oneperson ); + + str_init( &oneperson ); + str_init( &allpeople ); vplist_init( &a ); - fields_findv_eachof( f, level, FIELDS_CHRP, &a, tag1, tag2, tag3, NULL ); - extern void fields_findv_eachof( fields *f, int level, int mode, vplist *a, ... ); - for ( i=0; ilen!=0 ) fprintf( fp, "%%P %s\n", sn->data ); - else if ( ar && ar->len!=0 ) fprintf( fp, "%%P %s\n", ar->data ); - if ( en && en->len!=0 ) fprintf( fp, "%%L %s\n", en->data ); + str *sn, *en, *ar; + int fstatus; + + sn = fields_findv( in, LEVEL_ANY, FIELDS_STRP, "PAGES:START" ); + en = fields_findv( in, LEVEL_ANY, FIELDS_STRP, "PAGES:STOP" ); + ar = fields_findv( in, LEVEL_ANY, FIELDS_STRP, "ARTICLENUMBER" ); + + if ( str_has_value( sn ) ) { + fstatus = fields_add( out, "%P", str_cstr( sn ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + return; + } + } + + else if ( str_has_value( ar ) ) { + fstatus = fields_add( out, "%P", str_cstr( ar ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + return; + } + } + + if ( str_has_value( en ) ) { + fstatus = fields_add( out, "%L", str_cstr( en ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + return; + } + } } static int @@ -240,23 +308,28 @@ } static int -get_month( fields *f, int level ) +get_month( fields *in, int level ) { - newstr *month = fields_findv_firstof( f, level, FIELDS_STRP, - "MONTH", "PARTMONTH", NULL ); - if ( month && month->len ) return mont2mont( month->data ); + str *month; + + month = fields_findv_firstof( in, level, FIELDS_STRP, "DATE:MONTH", "PARTDATE:MONTH", NULL ); + if ( str_has_value( month ) ) return mont2mont( month->data ); else return 0; } static void -output_date( FILE *fp, fields *f, char *adstag, int level ) +append_date( fields *in, char *adstag, int level, fields *out, int *status ) { - newstr *year = fields_findv_firstof( f, level, FIELDS_STRP, - "YEAR", "PARTYEAR", NULL ); - int month; - if ( year && year->len ) { - month = get_month( f, level ); - fprintf( fp, "%s %02d/%s\n", adstag, month, year->data ); + int month, fstatus; + char outstr[1000]; + str *year; + + year = fields_findv_firstof( in, level, FIELDS_STRP, "DATE:YEAR", "PARTDATE:YEAR", NULL ); + if ( str_has_value( year ) ) { + month = get_month( in, level ); + sprintf( outstr, "%02d/%s", month, str_cstr( year ) ); + fstatus = fields_add( out, adstag, outstr, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } } @@ -279,29 +352,29 @@ } static char -get_firstinitial( fields *f ) +get_firstinitial( fields *in ) { char *name; int n; - n = fields_find( f, "AUTHOR", LEVEL_MAIN ); - if ( n==-1 ) n = fields_find( f, "AUTHOR", LEVEL_ANY ); + n = fields_find( in, "AUTHOR", LEVEL_MAIN ); + if ( n==-1 ) n = fields_find( in, "AUTHOR", LEVEL_ANY ); if ( n!=-1 ) { - name = fields_value( f, n, FIELDS_CHRP ); + name = fields_value( in, n, FIELDS_CHRP ); return name[0]; } else return '\0'; } static int -get_journalabbr( fields *f ) +get_journalabbr( fields *in ) { char *jrnl; int n, j; - n = fields_find( f, "TITLE", LEVEL_HOST ); + n = fields_find( in, "TITLE", LEVEL_HOST ); if ( n!=-1 ) { - jrnl = fields_value( f, n, FIELDS_CHRP ); + jrnl = fields_value( in, n, FIELDS_CHRP ); for ( j=0; j=10000 ) { ch = 'a' + (page/10000); - out[13] = ch; + outstr[13] = ch; } } /** A */ - ch = toupper( (unsigned char) get_firstinitial( f ) ); - if ( ch!='\0' ) out[18] = ch; + ch = toupper( (unsigned char) get_firstinitial( in ) ); + if ( ch!='\0' ) outstr[18] = ch; - fprintf( fp, "%s %s\n", adstag, out ); + fstatus = fields_add( out, adstag, outstr, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } static void -output_easyall( FILE *fp, fields *f, char *tag, char *adstag, int level ) +append_easyall( fields *in, char *tag, char *adstag, int level, fields *out, int *status ) { + vplist_index i; + int fstatus; vplist a; - int i; + vplist_init( &a ); - fields_findv_each( f, level, FIELDS_CHRP, &a, tag ); - for ( i=0; i0 ) str_strcatc( &allkeys, ", " ); + str_strcatc( &allkeys, (char *) vplist_get( &a, i ) ); + } + fstatus = fields_add( out, adstag, str_cstr( &allkeys ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } - if ( a.n ) fprintf( fp, "\n" ); + + str_free( &allkeys ); vplist_free( &a ); } -void -adsout_write( fields *f, FILE *fp, param *p, unsigned long refnum ) +static void +append_urls( fields *in, fields *out, int *status ) { - int type; - fields_clearused( f ); - type = get_type( f ); + int lstatus; + slist types; - output_people( fp, f, "AUTHOR", "AUTHOR:ASIS", "AUTHOR:CORP", "%A", LEVEL_MAIN ); - output_people( fp, f, "EDITOR", "EDITOR:ASIS", "EDITOR:CORP", "%E", LEVEL_ANY ); - output_easy( fp, f, "TITLE", "%T", LEVEL_ANY ); + lstatus = slist_init_valuesc( &types, "URL", "DOI", "PMID", "PMC", "ARXIV", "JSTOR", "MRNUMBER", "FILEATTACH", "FIGATTACH", NULL ); + if ( lstatus!=SLIST_OK ) { + *status = BIBL_ERR_MEMERR; + return; + } - if ( type==TYPE_ARTICLE || type==TYPE_MAGARTICLE ) - output_title( fp, f, "TITLE", "SUBTITLE", "%J", LEVEL_HOST ); + *status = urls_merge_and_add( in, LEVEL_ANY, out, "%U", LEVEL_MAIN, &types ); - output_date( fp, f, "%D", LEVEL_ANY ); - output_easy( fp, f, "VOLUME", "%V", LEVEL_ANY ); - output_easy( fp, f, "ISSUE", "%N", LEVEL_ANY ); - output_easy( fp, f, "NUMBER", "%N", LEVEL_ANY ); - output_easy( fp, f, "LANGUAGE", "%M", LEVEL_ANY ); - output_easyall( fp, f, "NOTES", "%X", LEVEL_ANY ); - output_easy( fp, f, "ABSTRACT", "%B", LEVEL_ANY ); - output_keys( fp, f, "KEYWORD", "%K", LEVEL_ANY ); - output_easyall( fp, f, "URL", "%U", LEVEL_ANY ); - output_easyall( fp, f, "FILEATTACH", "%U", LEVEL_ANY ); - output_easyall( fp, f, "FIGATTACH", "%U", LEVEL_ANY ); - output_pages( fp, f ); - output_easyall( fp, f, "DOI", "%Y", LEVEL_ANY ); - fprintf( fp, "%%W PHY\n%%G AUTHOR\n" ); - output_Rtag( fp, f, "%R", type ); + slist_free( &types ); +} + +static void +append_trailer( fields *out, int *status ) +{ + int fstatus; + + fstatus = fields_add( out, "%W", "PHY", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + return; + } + + fstatus = fields_add( out, "%G", "AUTHOR", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + return; + } +} + +static void +output( FILE *fp, fields *out ) +{ + char *tag, *value; + int i; + + for ( i=0; in; ++i ) { + tag = fields_tag( out, i, FIELDS_CHRP ); + value = fields_value( out, i, FIELDS_CHRP ); + fprintf( fp, "%s %s\n", tag, value ); + } + fprintf( fp, "\n" ); fflush( fp ); } -void +static int +append_data( fields *in, fields *out ) +{ + int type, status = BIBL_OK; + + fields_clearused( in ); + type = get_type( in ); + + append_people ( in, "AUTHOR", "AUTHOR:ASIS", "AUTHOR:CORP", "%A", LEVEL_MAIN, out, &status ); + append_people ( in, "EDITOR", "EDITOR:ASIS", "EDITOR:CORP", "%E", LEVEL_ANY, out, &status ); + append_easy ( in, "TITLE", "%T", LEVEL_ANY, out, &status ); + append_titles ( in, type, out, &status ); + append_date ( in, "%D", LEVEL_ANY, out, &status ); + append_easy ( in, "VOLUME", "%V", LEVEL_ANY, out, &status ); + append_easy ( in, "ISSUE", "%N", LEVEL_ANY, out, &status ); + append_easy ( in, "NUMBER", "%N", LEVEL_ANY, out, &status ); + append_easy ( in, "LANGUAGE", "%M", LEVEL_ANY, out, &status ); + append_easyall( in, "NOTES", "%X", LEVEL_ANY, out, &status ); + append_easy ( in, "ABSTRACT", "%B", LEVEL_ANY, out, &status ); + append_keys ( in, "KEYWORD", "%K", LEVEL_ANY, out, &status ); + append_urls ( in, out, &status ); + append_pages ( in, out, &status ); + append_easyall( in, "DOI", "%Y", LEVEL_ANY, out, &status ); + append_trailer( out, &status ); + append_Rtag ( in, "%R", type, out, &status ); + + return status; +} + +static int +adsout_write( fields *in, FILE *fp, param *p, unsigned long refnum ) +{ + int status; + fields out; + + fields_init( &out ); + + status = append_data( in, &out ); + if ( status==BIBL_OK ) output( fp, &out ); + + fields_free( &out ); + + return status; +} + +static void adsout_writeheader( FILE *outptr, param *p ) { if ( p->utf8bom ) utf8_writebom( outptr ); diff --git a/bibutils/adsout.h b/bibutils/adsout.h deleted file mode 100644 --- a/bibutils/adsout.h +++ /dev/null @@ -1,22 +0,0 @@ -/* - * adsout.h - * - * Copyright (c) Richard Mathar 2007-2013 - * Copyright (c) Chris Putnam 2007-2013 - * - * Source code released under the GPL version 2 - * - */ -#ifndef ADSOUT_H -#define ADSOUT_H - -#include -#include "bibutils.h" - -extern void adsout_write( fields *info, FILE *fp, param *p, - unsigned long refnum ); -extern void adsout_writeheader( FILE *outptr, param *p ); - -extern void adsout_initparams( param *p, const char *progname ); - -#endif diff --git a/bibutils/bibcore.c b/bibutils/bibcore.c --- a/bibutils/bibcore.c +++ b/bibutils/bibcore.c @@ -1,7 +1,7 @@ /* * bibcore.c * - * Copyright (c) Chris Putnam 2005-2014 + * Copyright (c) Chris Putnam 2005-2017 * * Source code released under the GPL version 2 * @@ -13,7 +13,7 @@ /* internal includes */ #include "reftypes.h" #include "charsets.h" -#include "newstr_conv.h" +#include "str_conv.h" #include "is_ws.h" /* illegal modes to pass in, but use internally for consistency */ @@ -95,13 +95,13 @@ static int bibl_duplicateparams( param *np, param *op ) { - int ok; - list_init( &(np->asis) ); - list_init( &(np->corps) ); - ok = list_copy( &(np->asis), &(op->asis ) ); - if ( !ok ) return BIBL_ERR_MEMERR; - ok = list_copy( &(np->corps), &(op->corps ) ); - if ( !ok ) return BIBL_ERR_MEMERR; + int status; + slist_init( &(np->asis) ); + slist_init( &(np->corps) ); + status = slist_copy( &(np->asis), &(op->asis ) ); + if ( status!=SLIST_OK ) return BIBL_ERR_MEMERR; + status = slist_copy( &(np->corps), &(op->corps ) ); + if ( status!=SLIST_OK ) return BIBL_ERR_MEMERR; if ( !op->progname ) np->progname = NULL; else { @@ -190,8 +190,8 @@ bibl_freeparams( param *p ) { if ( p ) { - list_free( &(p->asis) ); - list_free( &(p->corps) ); + slist_free( &(p->asis) ); + slist_free( &(p->corps) ); if ( p->progname ) free( p->progname ); } } @@ -204,10 +204,10 @@ if ( !p ) return BIBL_ERR_BADINPUT; if ( !f ) return BIBL_ERR_BADINPUT; - status = list_fill( &(p->asis), f, 1 ); + status = slist_fill( &(p->asis), f, 1 ); - if ( status == LIST_ERR_CANNOTOPEN ) return BIBL_ERR_CANTOPEN; - else if ( status == 0 ) return BIBL_ERR_MEMERR; + if ( status == SLIST_ERR_CANTOPEN ) return BIBL_ERR_CANTOPEN; + else if ( status == SLIST_ERR_MEMERR ) return BIBL_ERR_MEMERR; return BIBL_OK; } @@ -219,9 +219,9 @@ if ( !p ) return BIBL_ERR_BADINPUT; if ( !f ) return BIBL_ERR_BADINPUT; - status = list_fill( &(p->corps), f, 1 ); + status = slist_fill( &(p->corps), f, 1 ); - if ( status == LIST_ERR_CANNOTOPEN ) return BIBL_ERR_CANTOPEN; + if ( status == SLIST_ERR_CANTOPEN ) return BIBL_ERR_CANTOPEN; else if ( status == 0 ) return BIBL_ERR_MEMERR; return BIBL_OK; } @@ -233,12 +233,12 @@ int bibl_addtoasis( param *p, char *d ) { - newstr *s; + str *s; if ( !p ) return BIBL_ERR_BADINPUT; if ( !d ) return BIBL_ERR_BADINPUT; - s = list_addc( &(p->asis), d ); + s = slist_addc( &(p->asis), d ); return ( s==NULL )? BIBL_ERR_MEMERR : BIBL_OK; } @@ -250,12 +250,12 @@ int bibl_addtocorps( param *p, char *d ) { - newstr *s; + str *s; if ( !p ) return BIBL_ERR_BADINPUT; if ( !d ) return BIBL_ERR_BADINPUT; - s = list_addc( &(p->corps), d ); + s = slist_addc( &(p->corps), d ); return ( s==NULL )? BIBL_ERR_MEMERR : BIBL_OK; } @@ -343,23 +343,23 @@ * value = "Masters thesis" */ static int -extract_tag_value( newstr *tag, newstr *value, char *p ) +extract_tag_value( str *tag, str *value, char *p ) { - newstr_empty( tag ); + str_empty( tag ); while ( p && *p && *p!='|' ) { - newstr_addchar( tag, *p ); + str_addchar( tag, *p ); p++; } - if ( newstr_memerr( tag ) ) return BIBL_ERR_MEMERR; + if ( str_memerr( tag ) ) return BIBL_ERR_MEMERR; if ( p && *p=='|' ) p++; - newstr_empty( value ); + str_empty( value ); while ( p && *p ) { - newstr_addchar( value, *p ); + str_addchar( value, *p ); p++; } - if ( newstr_memerr( tag ) ) return BIBL_ERR_MEMERR; + if ( str_memerr( tag ) ) return BIBL_ERR_MEMERR; return BIBL_OK; } @@ -374,10 +374,10 @@ process_defaultadd( fields *f, int reftype, param *r ) { int i, n, process, level, status, ret = BIBL_OK; - newstr tag, value; + str tag, value; char *p; - newstrs_init( &tag, &value, NULL ); + strs_init( &tag, &value, NULL ); for ( i=0; iall[reftype].ntags; ++i ) { @@ -404,7 +404,7 @@ } out: - newstrs_free( &tag, &value, NULL ); + strs_free( &tag, &value, NULL ); return ret; } @@ -419,10 +419,10 @@ process_alwaysadd( fields *f, int reftype, param *r ) { int i, process, level, status, ret = BIBL_OK; - newstr tag, value; + str tag, value; char *p; - newstrs_init( &tag, &value, NULL ); + strs_init( &tag, &value, NULL ); for ( i=0; iall[reftype].ntags; ++i ) { @@ -446,7 +446,7 @@ } out: - newstrs_free( &tag, &value, NULL ); + strs_free( &tag, &value, NULL ); return ret; } @@ -455,11 +455,11 @@ read_ref( FILE *fp, bibl *bin, char *filename, param *p ) { int nrefs = 0, bufpos = 0, ok, ret=BIBL_OK, fcharset;/* = CHARSET_UNKNOWN;*/ - newstr reference, line; + str reference, line; char buf[256]=""; fields *ref; - newstr_init( &reference ); - newstr_init( &line ); + str_init( &reference ); + str_init( &line ); while ( p->readf( fp, buf, sizeof(buf), &bufpos, &line, &reference, &fcharset ) ) { if ( reference.len==0 ) continue; ref = fields_new(); @@ -468,7 +468,7 @@ bibl_free( bin ); goto out; } - if ( p->processf( ref, reference.data, filename, nrefs+1 )){ + if ( p->processf( ref, reference.data, filename, nrefs+1, p )){ ok = bibl_addref( bin, ref ); if ( !ok ) { ret = BIBL_ERR_MEMERR; @@ -481,7 +481,7 @@ fields_free( ref ); free( ref ); } - newstr_empty( &reference ); + str_empty( &reference ); if ( fcharset!=CHARSET_UNKNOWN ) { /* charset from file takes priority over default, but * not user-specified */ @@ -494,8 +494,8 @@ } if ( p->charsetin==CHARSET_UNICODE ) p->utf8in = 1; out: - newstr_free( &line ); - newstr_free( &reference ); + str_free( &line ); + str_free( &reference ); return ret; } @@ -517,7 +517,7 @@ static int bibl_fixcharsetdata( fields *ref, param *p ) { - newstr *data; + str *data; char *tag; long i, n; int ok; @@ -530,11 +530,11 @@ data = fields_value( ref, i, FIELDS_STRP_NOUSE ); if ( bibl_notexify( tag ) ) { - ok = newstr_convert( data, + ok = str_convert( data, p->charsetin, 0, p->utf8in, p->xmlin, p->charsetout, 0, p->utf8out, p->xmlout ); } else { - ok = newstr_convert( data, + ok = str_convert( data, p->charsetin, p->latexin, p->utf8in, p->xmlin, p->charsetout, p->latexout, p->utf8out, p->xmlout ); } @@ -564,16 +564,16 @@ { char *year, *author, *p, num[512]; int status, ret = BIBL_OK; - newstr refnum; + str refnum; *n = -1; - newstr_init( &refnum ); + str_init( &refnum ); - year = fields_findv( f, LEVEL_MAIN, FIELDS_CHRP_NOUSE, "YEAR" ); + year = fields_findv( f, LEVEL_MAIN, FIELDS_CHRP_NOUSE, "DATE:YEAR" ); if ( !year ) year = fields_findv_firstof( f, LEVEL_ANY, FIELDS_CHRP_NOUSE, - "YEAR", "PARTYEAR", NULL ); + "DATE:YEAR", "PARTDATE:YEAR", NULL ); author = fields_findv( f, LEVEL_MAIN, FIELDS_CHRP_NOUSE, "AUTHOR" ); if ( !author ) @@ -583,15 +583,15 @@ if ( year && author ) { p = author; while ( *p && *p!='|' ) - newstr_addchar( &refnum, *p++ ); + str_addchar( &refnum, *p++ ); p = year; while ( *p && *p!=' ' && *p!='\t' ) - newstr_addchar( &refnum, *p++ ); + str_addchar( &refnum, *p++ ); } else { sprintf( num, "%ld", nrefs ); - newstr_mergestrs( &refnum, "ref", num, NULL ); + str_mergestrs( &refnum, "ref", num, NULL ); } - if ( newstr_memerr( &refnum ) ) { + if ( str_memerr( &refnum ) ) { ret = BIBL_ERR_MEMERR; goto out; } @@ -601,7 +601,7 @@ else *n = fields_find( f, "REFNUM", 0 ); out: - newstr_free( &refnum ); + str_free( &refnum ); return ret; } @@ -623,8 +623,8 @@ } if ( p->addcount ) { sprintf( buf, "_%ld", i+1 ); - newstr_strcat( &(ref->data[n]), buf ); - if ( newstr_memerr( &(ref->data[n]) ) ) + str_strcatc( &(ref->data[n]), buf ); + if ( str_memerr( &(ref->data[n]) ) ) return BIBL_ERR_MEMERR; } } @@ -637,28 +637,28 @@ { int n1, n2, status, ret; char *p, buf[100]; - newstr citekey; + str citekey; - newstr_init( &citekey ); + str_init( &citekey ); n1 = fields_find( f, "AUTHOR", 0 ); if ( n1==-1 ) n1 = fields_find( f, "AUTHOR", -1 ); - n2 = fields_find( f, "YEAR", 0 ); - if ( n2==-1 ) n2 = fields_find( f, "YEAR", -1 ); - if ( n2==-1 ) n2 = fields_find( f, "PARTYEAR", 0 ); - if ( n2==-1 ) n2 = fields_find( f, "PARTYEAR", -1 ); + n2 = fields_find( f, "DATE:YEAR", 0 ); + if ( n2==-1 ) n2 = fields_find( f, "DATE:YEAR", -1 ); + if ( n2==-1 ) n2 = fields_find( f, "PARTDATE:YEAR", 0 ); + if ( n2==-1 ) n2 = fields_find( f, "PARTDATE:YEAR", -1 ); if ( n1!=-1 && n2!=-1 ) { p = f->data[n1].data; while ( p && *p && *p!='|' ) { - if ( !is_ws( *p ) ) newstr_addchar( &citekey, *p ); + if ( !is_ws( *p ) ) str_addchar( &citekey, *p ); p++; } p = f->data[n2].data; while ( p && *p ) { - if ( !is_ws( *p ) ) newstr_addchar( &citekey, *p ); + if ( !is_ws( *p ) ) str_addchar( &citekey, *p ); p++; } - if ( newstr_memerr( &citekey ) ) { + if ( str_memerr( &citekey ) ) { ret = -1; goto out; } @@ -669,41 +669,41 @@ } } else { sprintf( buf, "ref%d\n", nref ); - newstr_strcpy( &citekey, buf ); + str_strcpyc( &citekey, buf ); } ret = fields_find( f, "REFNUM", -1 ); out: - newstr_free( &citekey ); + str_free( &citekey ); return ret; } static int -resolve_citekeys( bibl *b, list *citekeys, int *dup ) +resolve_citekeys( bibl *b, slist *citekeys, int *dup ) { const char abc[]="abcdefghijklmnopqrstuvwxyz"; int nsame, ntmp, n, i, j, status = BIBL_OK; - newstr tmp; + str tmp; - newstr_init( &tmp ); + str_init( &tmp ); for ( i=0; in; ++i ) { if ( dup[i]==-1 ) continue; nsame = 0; for ( j=i; jn; ++j ) { if ( dup[j]!=i ) continue; - newstr_newstrcpy( &tmp, &(citekeys->str[j]) ); - if ( newstr_memerr( &tmp ) ) { + str_strcpy( &tmp, slist_str( citekeys, j ) ); + if ( str_memerr( &tmp ) ) { status = BIBL_ERR_MEMERR; goto out; } ntmp = nsame; while ( ntmp >= 26 ) { - newstr_addchar( &tmp, 'a' ); + str_addchar( &tmp, 'a' ); ntmp -= 26; } if ( ntmp<26 && ntmp>=0 ) - newstr_addchar( &tmp, abc[ntmp] ); - if ( newstr_memerr( &tmp ) ) { + str_addchar( &tmp, abc[ntmp] ); + if ( str_memerr( &tmp ) ) { status = BIBL_ERR_MEMERR; goto out; } @@ -711,8 +711,8 @@ dup[j] = -1; n = fields_find( b->ref[j], "REFNUM", -1 ); if ( n!=-1 ) { - newstr_newstrcpy(&((b->ref[j])->data[n]),&tmp); - if ( newstr_memerr( &((b->ref[j])->data[n]) ) ) { + str_strcpy(&((b->ref[j])->data[n]),&tmp); + if ( str_memerr( &((b->ref[j])->data[n]) ) ) { status = BIBL_ERR_MEMERR; goto out; } @@ -720,25 +720,25 @@ } } out: - newstr_free( &tmp ); + str_free( &tmp ); return status; } static int -get_citekeys( bibl *b, list *citekeys ) +get_citekeys( bibl *b, slist *citekeys ) { - newstr *s; fields *f; int i, n; + str *s; for ( i=0; inrefs; ++i ) { f = b->ref[i]; n = fields_find( f, "REFNUM", -1 ); if ( n==-1 ) n = generate_citekey( f, i ); if ( n!=-1 && f->data[n].data ) { - s = list_add( citekeys, &(f->data[n]) ); + s = slist_add( citekeys, &(f->data[n]) ); if ( !s ) return BIBL_ERR_MEMERR; } else { - s = list_addc( citekeys, "" ); + s = slist_addc( citekeys, "" ); if ( !s ) return BIBL_ERR_MEMERR; } } @@ -746,7 +746,7 @@ } static int -dup_citekeys( bibl *b, list *citekeys ) +dup_citekeys( bibl *b, slist *citekeys ) { int i, j, status = BIBL_OK, *dup, ndup=0; @@ -757,8 +757,8 @@ for ( i=0; in-1; ++i ) { if ( dup[i]!=-1 ) continue; for ( j=i+1; jn; ++j ) { - if ( !strcmp( citekeys->str[i].data, - citekeys->str[j].data ) ) { + if ( !strcmp( slist_cstr( citekeys, i ), + slist_cstr( citekeys, j ) ) ) { dup[i] = i; dup[j] = i; ndup++; @@ -773,14 +773,14 @@ static int uniqueify_citekeys( bibl *b ) { - list citekeys; + slist citekeys; int status; - list_init( &citekeys ); + slist_init( &citekeys ); status = get_citekeys( b, &citekeys ); if ( status!=BIBL_OK ) goto out; status = dup_citekeys( b, &citekeys ); out: - list_free( &citekeys ); + slist_free( &citekeys ); return status; } @@ -803,8 +803,8 @@ rout = fields_new(); if ( !rout ) return BIBL_ERR_MEMERR; if ( p->typef ) - reftype = p->typef( rin, fname, i+1, p, p->all, p->nall ); - status = p->convertf( rin, rout, reftype, p, p->all, p->nall ); + reftype = p->typef( rin, fname, i+1, p ); + status = p->convertf( rin, rout, reftype, p ); if ( status!=BIBL_OK ) return status; if ( p->all ) { status = process_alwaysadd( rout, reftype, p ); @@ -815,6 +815,13 @@ ok = bibl_addref( bout, rout ); if ( !ok ) return BIBL_ERR_MEMERR; } + if ( debug_set( p ) ) { + fflush( stdout ); + fprintf( stderr, "-------------------start for convert_ref\n"); + bibl_verbose0( bout ); + fprintf( stderr, "-------------------end for convert_ref\n" ); + fflush( stderr ); + } status = uniqueify_citekeys( bout ); return status; } @@ -838,7 +845,10 @@ bibl_init( &bin ); status = read_ref( fp, &bin, filename, &lp ); - if ( status!=BIBL_OK ) return status; + if ( status!=BIBL_OK ) { + bibl_freeparams( &lp ); + return status; + } if ( debug_set( p ) ) { fflush( stdout ); @@ -884,13 +894,18 @@ fflush( stderr ); } ok = bibl_copy( b, &bin ); - if ( !ok ) return BIBL_ERR_MEMERR; + if ( !ok ) { + bibl_freeparams( &lp ); + return BIBL_ERR_MEMERR; + } } if ( !lp.output_raw || ( lp.output_raw & BIBL_RAW_WITHMAKEREFID ) ) bibl_checkrefid( b, &lp ); bibl_free( &bin ); + bibl_freeparams( &lp ); + return BIBL_OK; } @@ -932,14 +947,16 @@ static int bibl_writeeachfp( FILE *fp, bibl *b, param *p ) { + int status; long i; for ( i=0; inrefs; ++i ) { fp = singlerefname( b->ref[i], i, p->writeformat ); if ( !fp ) return BIBL_ERR_CANTOPEN; if ( p->headerf ) p->headerf( fp, p ); - p->writef( b->ref[i], fp, p, i ); + status = p->writef( b->ref[i], fp, p, i ); if ( p->footerf ) p->footerf( fp ); fclose( fp ); + if ( status!=BIBL_OK ) return status; } return BIBL_OK; } @@ -947,12 +964,15 @@ static int bibl_writefp( FILE *fp, bibl *b, param *p ) { + int status = BIBL_OK; long i; if ( p->headerf ) p->headerf( fp, p ); - for ( i=0; inrefs; ++i ) - p->writef( b->ref[i], fp, p, i ); + for ( i=0; inrefs; ++i ) { + status = p->writef( b->ref[i], fp, p, i ); + if ( status!=BIBL_OK ) break; + } if ( p->footerf ) p->footerf( fp ); - return BIBL_OK; + return status; } int @@ -972,10 +992,19 @@ status = bibl_fixcharsets( b, &lp ); if ( status!=BIBL_OK ) return status; - if ( debug_set( p ) ) report_params( stderr, "bibl_write", &lp ); + if ( debug_set( p ) ) { + report_params( stderr, "bibl_write", &lp ); + fflush( stdout ); + fprintf( stderr, "-------------------start for bibl_write\n"); + bibl_verbose0( b ); + fprintf( stderr, "-------------------end for bibl_write\n" ); + fflush( stderr ); + } if ( p->singlerefperfile ) status = bibl_writeeachfp( fp, b, &lp ); else status = bibl_writefp( fp, b, &lp ); + + bibl_freeparams( &lp ); return status; } diff --git a/bibutils/bibformats.h b/bibutils/bibformats.h new file mode 100644 --- /dev/null +++ b/bibutils/bibformats.h @@ -0,0 +1,35 @@ +/* + * bibformats.h + * + * Copyright (c) Chris Putnam 2007-2017 + * + * Source code released under the GPL version 2 + * + */ +#ifndef BIBFORMATS_H +#define BIBFORMATS_H + +#include "bibutils.h" + +void adsout_initparams( param *p, const char *progname ); +void biblatexin_initparams( param *p, const char *progname ); +void bibtexin_initparams( param *p, const char *progname ); +void bibtexout_initparams( param *p, const char *progname ); +void copacin_initparams( param *p, const char *progname ); +void ebiin_initparams( param *p, const char *progname ); +void endin_initparams( param *p, const char *progname ); +void endout_initparams( param *p, const char *progname ); +void endxmlin_initparams( param *p, const char *progname ); +void isiin_initparams( param *p, const char *progname ); +void isiout_initparams( param *p, const char *progname ); +void medin_initparams( param *p, const char *progname ); +void modsin_initparams( param *p, const char *progname ); +void modsout_initparams( param *p, const char *progname ); +void nbibin_initparams( param *p, const char *progname ); +void risin_initparams( param *p, const char *progname ); +void risout_initparams( param *p, const char *progname ); +void wordin_initparams( param *p, const char *progname ); +void wordout_initparams( param *p, const char *progname ); + +#endif + diff --git a/bibutils/bibl.c b/bibutils/bibl.c --- a/bibutils/bibl.c +++ b/bibutils/bibl.c @@ -1,7 +1,7 @@ /* * bibl.c * - * Copyright (c) Chris Putnam 2005-2014 + * Copyright (c) Chris Putnam 2005-2017 * * Source code released under the GPL version 2 * @@ -92,7 +92,7 @@ value = fields_value( refin, j, FIELDS_CHRP ); level = fields_level( refin, j ); if ( tag && value ) { - status = fields_add( refout, tag, value, level ); + status = fields_add_can_dup( refout, tag, value, level ); if ( status!=FIELDS_OK ) return 0; } } diff --git a/bibutils/bibl.h b/bibutils/bibl.h --- a/bibutils/bibl.h +++ b/bibutils/bibl.h @@ -1,7 +1,7 @@ /* * bibl.h * - * Copyright (c) Chris Putnam 2005-2014 + * Copyright (c) Chris Putnam 2005-2017 * * Source code released under the GPL version 2 * @@ -10,7 +10,7 @@ #define BIBL_H #include -#include "newstr.h" +#include "str.h" #include "fields.h" #include "reftypes.h" diff --git a/bibutils/biblatexin.c b/bibutils/biblatexin.c --- a/bibutils/biblatexin.c +++ b/bibutils/biblatexin.c @@ -1,1412 +1,1300 @@ /* * biblatexin.c * - * Copyright (c) Chris Putnam 2008-2014 - * Copyright (c) Johannes Wilm 2010-2014 - * - * Program and source code released under the GPL version 2 - * - */ -#include -#include -#include -#include -#include "is_ws.h" -#include "strsearch.h" -#include "newstr.h" -#include "newstr_conv.h" -#include "fields.h" -#include "list.h" -#include "name.h" -#include "reftypes.h" -#include "biblatexin.h" - -extern const char progname[]; - -static list find = { 0, 0, NULL, 0 }; -static list replace = { 0, 0, NULL, 0 }; - -/***************************************************** - PUBLIC: void biblatexin_initparams() -*****************************************************/ - -void -biblatexin_initparams( param *p, const char *progname ) -{ - p->readformat = BIBL_BIBLATEXIN; - p->charsetin = BIBL_CHARSET_DEFAULT; - p->charsetin_src = BIBL_SRC_DEFAULT; - p->latexin = 1; - p->xmlin = 0; - p->utf8in = 0; - p->nosplittitle = 0; - p->verbose = 0; - p->addcount = 0; - p->output_raw = 0; - - p->readf = biblatexin_readf; - p->processf = biblatexin_processf; - p->cleanf = biblatexin_cleanf; - p->typef = biblatexin_typef; - p->convertf = biblatexin_convertf; - p->all = biblatex_all; - p->nall = biblatex_nall; - - list_init( &(p->asis) ); - list_init( &(p->corps) ); - - if ( !progname ) p->progname = NULL; - else p->progname = strdup( progname ); -} - -/***************************************************** - PUBLIC: int biblatexin_readf() -*****************************************************/ - -/* - * readf can "read too far", so we store this information in line, thus - * the next new text is in line, either from having read too far or - * from the next chunk obtained via newstr_fget() - * - * return 1 on success, 0 on error/end-of-file - * - */ -static int -readmore( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line ) -{ - if ( line->len ) return 1; - else return newstr_fget( fp, buf, bufsize, bufpos, line ); -} - -/* - * readf() - * - * returns zero if cannot get reference and hit end of-file - * returns 1 if last reference in file, 2 if reference within file - */ -int -biblatexin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ) -{ - int haveref = 0; - char *p; - while ( haveref!=2 && readmore( fp, buf, bufsize, bufpos, line ) ) { - if ( line->len == 0 ) continue; /* blank line */ - p = &(line->data[0]); - p = skip_ws( p ); - if ( *p == '%' ) { /* commented out line */ - newstr_empty( line ); - continue; - } - if ( *p == '@' ) haveref++; - if ( haveref && haveref<2 ) { - newstr_strcat( reference, p ); - newstr_addchar( reference, '\n' ); - newstr_empty( line ); - } else if ( !haveref ) newstr_empty( line ); - - } - *fcharset = CHARSET_UNKNOWN; - return haveref; -} - -/***************************************************** - PUBLIC: int biblatexin_processf() -*****************************************************/ - -static char * -process_biblatextype( char *p, newstr *type ) -{ - newstr tmp; - newstr_init( &tmp ); - - if ( *p=='@' ) p++; - p = newstr_cpytodelim( &tmp, p, "{( \t\r\n", 0 ); - p = skip_ws( p ); - if ( *p=='{' || *p=='(' ) p++; - p = skip_ws( p ); - - if ( tmp.len ) newstr_strcpy( type, tmp.data ); - else newstr_empty( type ); - - newstr_free( &tmp ); - return p; -} - -static char * -process_biblatexid( char *p, newstr *id ) -{ - char *start_p = p; - newstr tmp; - - newstr_init( &tmp ); - p = newstr_cpytodelim( &tmp, p, ",", 1 ); - - if ( tmp.len ) { - if ( strchr( tmp.data, '=' ) ) { - /* Endnote writes biblatex files w/o fields, try to - * distinguish via presence of an equal sign.... if - * it's there, assume that it's a tag/data pair instead - * and roll back. - */ - p = start_p; - newstr_empty( id ); - } else { - newstr_strcpy( id, tmp.data ); - } - } else { - newstr_empty( id ); - } - - newstr_free( &tmp ); - return skip_ws( p ); -} - -static char * -biblatex_tag( char *p, newstr *tag ) -{ - p = newstr_cpytodelim( tag, skip_ws( p ), "= \t\r\n", 0 ); - return skip_ws( p ); -} - -static char * -biblatex_data( char *p, fields *bibin, list *tokens ) -{ - unsigned int nbracket = 0, nquotes = 0; - char *startp = p; - newstr tok, *s; - - newstr_init( &tok ); - while ( p && *p ) { - if ( !nquotes && !nbracket ) { - if ( *p==',' || *p=='=' || *p=='}' || *p==')' ) - goto out; - } - if ( *p=='\"' && nbracket==0 && ( p==startp || *(p-1)!='\\' ) ) { - nquotes = !nquotes; - newstr_addchar( &tok, *p ); - if ( !nquotes ) { - s = list_add( tokens, &tok ); - if ( !s ) { p = NULL; goto outerr; } - newstr_empty( &tok ); - } - } else if ( *p=='#' && !nquotes && !nbracket ) { - if ( tok.len ) { - s = list_add( tokens, &tok ); - if ( !s ) { p = NULL; goto outerr; } - } - newstr_strcpy( &tok, "#" ); - s = list_add( tokens, &tok ); - if ( !s ) { p = NULL; goto outerr; } - newstr_empty( &tok ); - } else if ( *p=='{' && !nquotes && ( p==startp || *(p-1)!='\\' ) ) { - nbracket++; - newstr_addchar( &tok, *p ); - } else if ( *p=='}' && !nquotes && ( p==startp || *(p-1)!='\\' ) ) { - nbracket--; - newstr_addchar( &tok, *p ); - if ( nbracket==0 ) { - s = list_add( tokens, &tok ); - if ( !s ) { p = NULL; goto outerr; } - newstr_empty( &tok ); - } - } else if ( !is_ws( *p ) || nquotes || nbracket ) { - if ( !is_ws( *p ) ) newstr_addchar( &tok, *p ); - else { - if ( tok.len!=0 && *p!='\n' && *p!='\r' ) - newstr_addchar( &tok, *p ); - else if ( tok.len!=0 && (*p=='\n' || *p=='\r')) { - newstr_addchar( &tok, ' ' ); - while ( is_ws( *(p+1) ) ) p++; - } - } - } else if ( is_ws( *p ) ) { - if ( tok.len ) { - s = list_add( tokens, &tok ); - if ( !s ) { p = NULL; goto outerr; } - newstr_empty( &tok ); - } - } - p++; - } -out: - if ( nbracket!=0 ) { - fprintf( stderr, "%s: Mismatch in number of brackets in reference.\n", progname ); - } - if ( nquotes!=0 ) { - fprintf( stderr, "%s: Mismatch in number of quotes in reference.\n", progname ); - } - if ( tok.len ) { - s = list_add( tokens, &tok ); - if ( !s ) p = NULL; - } -outerr: - newstr_free( &tok ); - return p; -} - -/* replace_strings() - * - * do string replacement -- only if unprotected by quotation marks or curly brackets - */ -static void -replace_strings( list *tokens, fields *bibin ) -{ - int i, n, ok; - newstr *s; - char *q; - i = 0; - while ( i < tokens->n ) { - s = list_get( tokens, i ); - if ( !strcmp( s->data, "#" ) ) { - } else if ( s->data[0]!='\"' && s->data[0]!='{' ) { - n = list_find( &find, s->data ); - if ( n!=-1 ) { - newstr_newstrcpy( s, list_get( &replace, n ) ); - } else { - q = s->data; - ok = 1; - while ( *q && ok ) { - if ( !isdigit( *q ) ) ok = 0; - q++; - } - if ( !ok ) { - fprintf( stderr, "%s: Warning: Non-numeric " - "BibTeX elements should be in quotations or " - "curly brackets in reference.\n", progname ); - } - } - } - i++; - } -} - -static int -string_concatenate( list *tokens, fields *bibin ) -{ - int i, status; - newstr *s, *t; - i = 0; - while ( i < tokens->n ) { - s = list_get( tokens, i ); - if ( !strcmp( s->data, "#" ) ) { - if ( i==0 || i==tokens->n-1 ) { - fprintf( stderr, "%s: Warning: Stray string concatenation " - "('#' character) in reference\n", progname ); - status = list_remove( tokens, i ); - if ( status!=LIST_OK ) return BIBL_ERR_MEMERR; - continue; - } - s = list_get( tokens, i-1 ); - if ( s->data[0]!='\"' && s->data[s->len-1]!='\"' ) - fprintf( stderr, "%s: Warning: String concentation should " - "be used in context of quotations marks.\n", progname ); - t = list_get( tokens, i+1 ); - if ( t->data[0]!='\"' && t->data[s->len-1]!='\"' ) - fprintf( stderr, "%s: Warning: String concentation should " - "be used in context of quotations marks.\n", progname ); - if ( ( s->data[s->len-1]=='\"' && t->data[0]=='\"') || (s->data[s->len-1]=='}' && t->data[0]=='{') ) { - newstr_trimend( s, 1 ); - newstr_trimbegin( t, 1 ); - newstr_newstrcat( s, t ); - } else { - newstr_newstrcat( s, t ); - } - status = list_remove( tokens, i ); - if ( status!=LIST_OK ) return BIBL_ERR_MEMERR; - status = list_remove( tokens, i ); - if ( status!=LIST_OK ) return BIBL_ERR_MEMERR; - } else i++; - } - return BIBL_OK; -} - -static char * -process_biblatexline( char *p, newstr *tag, newstr *data, uchar stripquotes ) -{ - int i, status; - list tokens; - newstr *s; - - newstr_empty( data ); - - p = biblatex_tag( p, tag ); - if ( tag->len==0 ) return p; - - list_init( &tokens ); - - if ( *p=='=' ) p = biblatex_data( p+1, NULL, &tokens ); - - replace_strings( &tokens, NULL ); - - status = string_concatenate( &tokens, NULL ); - if ( status!=BIBL_OK ) { - p = NULL; - goto out; - } - - for ( i=0; idata[0]=='\"' && s->data[s->len-1]=='\"' ) || - ( s->data[0]=='{' && s->data[s->len-1]=='}' ) ) { - newstr_trimbegin( s, 1 ); - newstr_trimend( s, 1 ); - } - newstr_newstrcat( data, list_get( &tokens, i ) ); - } -out: - list_free( &tokens ); - return p; -} - -static int -process_cite( fields *bibin, char *p, char *filename, long nref ) -{ - int fstatus, status = BIBL_OK; - newstr tag, data; - newstrs_init( &tag, &data, NULL ); - p = process_biblatextype( p, &data ); - if ( data.len ) { - fstatus = fields_add( bibin, "INTERNAL_TYPE", data.data, 0 ); - if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } - } - p = process_biblatexid ( p, &data ); - if ( data.len ) { - fstatus = fields_add( bibin, "REFNUM", data.data, 0 ); - if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } - } - while ( *p ) { - p = process_biblatexline( p, &tag, &data, 1 ); - if ( !p ) { status = BIBL_ERR_MEMERR; goto out; } - /* no anonymous or empty fields allowed */ - if ( tag.len && data.len ) { - fstatus = fields_add( bibin, tag.data, data.data, 0 ); - if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } - } - newstrs_empty( &tag, &data, NULL ); - } -out: - newstrs_free( &tag, &data, NULL ); - return status; -} - -/* process_string() - * - * Handle lines like: - * - * '@STRING{TL = {Tetrahedron Lett.}}' - * - * p should point to just after '@STRING' - * - * In BibTeX, if a string is defined several times, the last one is kept. - * - */ -static int -process_string( char *p ) -{ - int n, status = BIBL_OK; - newstr s1, s2, *s; - newstrs_init( &s1, &s2, NULL ); - while ( *p && *p!='{' && *p!='(' ) p++; - if ( *p=='{' || *p=='(' ) p++; - p = process_biblatexline( skip_ws( p ), &s1, &s2, 0 ); - if ( s2.data ) { - newstr_findreplace( &s2, "\\ ", " " ); - if ( newstr_memerr( &s2 ) ) { status = BIBL_ERR_MEMERR; goto out; } - } - if ( s1.data ) { - n = list_find( &find, s1.data ); - if ( n==-1 ) { - s = list_add( &find, &s1 ); - if ( s==NULL ) { status = BIBL_ERR_MEMERR; goto out; } - if ( s2.data ) s = list_add( &replace, &s2 ); - else s = list_addc( &replace, "" ); - if ( s==NULL ) { status = BIBL_ERR_MEMERR; goto out; } - } else { - if ( s2.data ) s = list_set( &replace, n, &s2 ); - else s = list_setc( &replace, n, "" ); - if ( s==NULL ) { status = BIBL_ERR_MEMERR; goto out; } - } - } -out: - newstrs_free( &s1, &s2, NULL ); - return status; -} - -int -biblatexin_processf( fields *bibin, char *data, char *filename, long nref ) -{ - if ( !strncasecmp( data, "@STRING", 7 ) ) { - process_string( data+7 ); - return 0; - } else { - process_cite( bibin, data, filename, nref ); - return 1; - } -} - -/***************************************************** - PUBLIC: void biblatexin_cleanf() -*****************************************************/ - -static void -biblatex_process_tilde( newstr *s ) -{ - char *p, *q; - int n = 0; - - p = q = s->data; - if ( !p ) return; - while ( *p ) { - if ( *p=='~' ) { - *q = ' '; - } else if ( *p=='\\' && *(p+1)=='~' ) { - n++; - p++; - *q = '~'; - } else { - *q = *p; - } - p++; - q++; - } - *q = '\0'; - s->len -= n; -} - -static void -biblatex_process_bracket( newstr *s ) -{ - char *p, *q; - int n = 0; - - p = q = s->data; - if ( !p ) return; - while ( *p ) { - if ( *p=='\\' && ( *(p+1)=='{' || *(p+1)=='}' ) ) { - n++; - p++; - *q = *p; - q++; - } else if ( *p=='{' || *p=='}' ) { - n++; - } else { - *q = *p; - q++; - } - p++; - } - *q = '\0'; - s->len -= n; -} - -static int -biblatex_cleantoken( newstr *s ) -{ - /* 'textcomp' annotations */ - newstr_findreplace( s, "\\textit", "" ); - newstr_findreplace( s, "\\textbf", "" ); - newstr_findreplace( s, "\\textsl", "" ); - newstr_findreplace( s, "\\textsc", "" ); - newstr_findreplace( s, "\\textsf", "" ); - newstr_findreplace( s, "\\texttt", "" ); - newstr_findreplace( s, "\\textsubscript", "" ); - newstr_findreplace( s, "\\textsuperscript", "" ); - newstr_findreplace( s, "\\emph", "" ); - newstr_findreplace( s, "\\url", "" ); - - /* Other text annotations */ - newstr_findreplace( s, "\\it ", "" ); - newstr_findreplace( s, "\\em ", "" ); - - newstr_findreplace( s, "\\%", "%" ); - newstr_findreplace( s, "\\$", "$" ); - while ( newstr_findreplace( s, " ", " " ) ) {} - - /* 'textcomp' annotations that we don't want to substitute on output*/ - newstr_findreplace( s, "\\textdollar", "$" ); - newstr_findreplace( s, "\\textunderscore", "_" ); - - biblatex_process_bracket( s ); - biblatex_process_tilde( s ); - - if ( !newstr_memerr( s ) ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} - -static int -biblatex_split( list *tokens, newstr *s ) -{ - int i, n = s->len, nbrackets = 0, status = BIBL_OK; - newstr tok, *t; - - newstr_init( &tok ); - - for ( i=0; idata[i]=='{' && ( i==0 || s->data[i-1]!='\\' ) ) { - nbrackets++; - newstr_addchar( &tok, '{' ); - } else if ( s->data[i]=='}' && ( i==0 || s->data[i-1]!='\\' ) ) { - nbrackets--; - newstr_addchar( &tok, '}' ); - } else if ( !is_ws( s->data[i] ) || nbrackets ) { - newstr_addchar( &tok, s->data[i] ); - } else if ( is_ws( s->data[i] ) ) { - if ( newstr_memerr( &tok ) ) { status = BIBL_ERR_MEMERR; goto out; } - if ( tok.len ) { - t = list_add( tokens, &tok ); - if ( !t ) { status = BIBL_ERR_MEMERR; goto out; } - } - newstr_empty( &tok ); - } - } - if ( tok.len ) { - if ( newstr_memerr( &tok ) ) { status = BIBL_ERR_MEMERR; goto out; } - t = list_add( tokens, &tok ); - if ( !t ) { status = BIBL_ERR_MEMERR; goto out; } - } - - for ( i=0; in; ++i ) { - t = list_get( tokens, i ); - newstr_trimstartingws( t ); - newstr_trimendingws( t ); - if ( newstr_memerr( t ) ) { status = BIBL_ERR_MEMERR; goto out; } - } -out: - newstr_free( &tok ); - return status; -} - -static int -biblatexin_addtitleurl( fields *info, newstr *in ) -{ - int fstatus, status = BIBL_OK; - newstr s; - char *p; - - newstr_init( &s ); - /* skip past "\href{" */ - p = newstr_cpytodelim( &s, in->data + 6, "}", 1 ); - if ( newstr_memerr( &s ) ) { - status = BIBL_ERR_MEMERR; - goto out; - } - fstatus = fields_add( info, "URL", s.data, 0 ); - if ( fstatus!=FIELDS_OK ) { - status = BIBL_ERR_MEMERR; - goto out; - } - - p = newstr_cpytodelim( &s, p, "", 0 ); - if ( newstr_memerr( &s ) ) { - status = BIBL_ERR_MEMERR; - goto out; - } - newstr_swapstrings( &s, in ); -out: - newstr_free( &s ); - return status; -} - -static int -is_name_tag( newstr *tag ) -{ - if ( tag->len ) { - if ( !strcasecmp( tag->data, "author" ) ) return 1; - if ( !strcasecmp( tag->data, "editor" ) ) return 1; - if ( !strcasecmp( tag->data, "editorb" ) ) return 1; - if ( !strcasecmp( tag->data, "editorc" ) ) return 1; - if ( !strcasecmp( tag->data, "director" ) ) return 1; - if ( !strcasecmp( tag->data, "producer" ) ) return 1; - if ( !strcasecmp( tag->data, "execproducer" ) ) return 1; - if ( !strcasecmp( tag->data, "writer" ) ) return 1; - if ( !strcasecmp( tag->data, "redactor" ) ) return 1; - if ( !strcasecmp( tag->data, "annotator" ) ) return 1; - if ( !strcasecmp( tag->data, "commentator" ) ) return 1; - if ( !strcasecmp( tag->data, "translator" ) ) return 1; - if ( !strcasecmp( tag->data, "foreword" ) ) return 1; - if ( !strcasecmp( tag->data, "afterword" ) ) return 1; - if ( !strcasecmp( tag->data, "introduction" ) ) return 1; - } - return 0; -} - -static int -is_url_tag( newstr *tag ) -{ - if ( tag->len ) { - if ( !strcasecmp( tag->data, "url" ) ) return 1; - } - return 0; -} - -static int -biblatexin_cleandata( newstr *tag, newstr *s, fields *info, param *p ) -{ - list tokens; - newstr *tok; - int i, status = BIBL_OK; - if ( !s->len ) return status; - /* protect url from undergoing any parsing */ - if ( is_url_tag( tag ) ) return status; - list_init( &tokens ); - biblatex_split( &tokens, s ); - for ( i=0; ilatexin && !is_name_tag( tag ) ) { - status = biblatex_cleantoken( &(tokens.str[i]) ); - if ( status!=BIBL_OK ) goto out; - } - } - newstr_empty( s ); - for ( i=0; i0 ) newstr_addchar( s, ' ' ); - newstr_newstrcat( s, tok ); - } -out: - list_free( &tokens ); - return status; -} - -static long -biblatexin_findref( bibl *bin, char *citekey ) -{ - int n; - long i; - for ( i=0; inrefs; ++i ) { - n = fields_find( bin->ref[i], "refnum", -1 ); - if ( n==-1 ) continue; - if ( !strcmp( bin->ref[i]->data[n].data, citekey ) ) return i; - } - return -1; -} - -static void -biblatexin_nocrossref( bibl *bin, long i, int n, param *p ) -{ - int n1 = fields_find( bin->ref[i], "REFNUM", -1 ); - if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, "Cannot find cross-reference '%s'", - bin->ref[i]->data[n].data); - if ( n1!=-1 ) - fprintf( stderr, " for reference '%s'\n", - bin->ref[i]->data[n1].data ); - fprintf( stderr, "\n" ); -} - -static int -biblatexin_crossref_oneref( fields *ref, fields *cross ) -{ - int j, nl, ntype, fstatus; - char *type, *nt, *nd; - ntype = fields_find( ref, "INTERNAL_TYPE", -1 ); - type = ( char * ) fields_value( ref, ntype, FIELDS_CHRP_NOUSE ); - for ( j=0; jn; ++j ) { - nt = ( char * ) fields_tag( cross, j, FIELDS_CHRP_NOUSE ); - if ( !strcasecmp( nt, "INTERNAL_TYPE" ) ) continue; - if ( !strcasecmp( nt, "REFNUM" ) ) continue; - if ( !strcasecmp( nt, "TITLE" ) ) { - if ( !strcasecmp( type, "Inproceedings" ) || - !strcasecmp( type, "Incollection" ) ) - nt = "booktitle"; - } - nd = ( char * ) fields_value( cross, j, FIELDS_CHRP_NOUSE ); - nl = fields_level( cross, j ) + 1; - fstatus = fields_add( ref, nt, nd, nl ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } - return BIBL_OK; -} - -static int -biblatexin_crossref( bibl *bin, param *p ) -{ - int n, ncross, status = BIBL_OK; - fields *ref, *cross; - long i; - for ( i=0; inrefs; ++i ) { - ref = bin->ref[i]; - n = fields_find( ref, "CROSSREF", -1 ); - if ( n==-1 ) continue; - fields_setused( ref, n ); - ncross = biblatexin_findref(bin, (char*)fields_value(ref,n, FIELDS_CHRP_NOUSE)); - if ( ncross==-1 ) { - biblatexin_nocrossref( bin, i, n, p ); - continue; - } - cross = bin->ref[ncross]; - status = biblatexin_crossref_oneref( ref, cross ); - if ( status!=BIBL_OK ) return status; - } - return status; -} - -static int -biblatexin_cleanref( fields *bibin, param *p ) -{ - int i, n, status; - newstr *t, *d; - n = fields_num( bibin ); - for ( i=0; idata, "AUTHORS" ) ) { - newstr_findreplace( d, "\n", " " ); - newstr_findreplace( d, "\r", " " ); - } - else if ( !strsearch( t->data, "ABSTRACT" ) || - !strsearch( t->data, "SUMMARY" ) || - !strsearch( t->data, "NOTE" ) ) { - newstr_findreplace( d, "\n", "" ); - newstr_findreplace( d, "\r", "" ); - } - } - return BIBL_OK; -} - -int -biblatexin_cleanf( bibl *bin, param *p ) -{ - int status; - long i; - for ( i=0; inrefs; ++i ) { - status = biblatexin_cleanref( bin->ref[i], p ); - if ( status!=BIBL_OK ) return status; - } - status = biblatexin_crossref( bin, p ); - return status; -} - -/***************************************************** - PUBLIC: void biblatexin_typef() -*****************************************************/ - -int -biblatexin_typef( fields *bibin, char *filename, int nrefs, param *p, - variants *all, int nall ) -{ - char *refnum = ""; - int reftype, n, nrefnum; - n = fields_find( bibin, "INTERNAL_TYPE", 0 ); - nrefnum = fields_find( bibin, "REFNUM", 0 ); - if ( nrefnum!=-1 ) refnum = (bibin->data[nrefnum]).data; - if ( n!=-1 ) - /* figure out type */ - reftype = get_reftype( (bibin->data[n]).data, nrefs, - p->progname, all, nall, refnum ); - else - /* no type info, go for default */ - reftype = get_reftype( "", nrefs, p->progname, all, nall, refnum ); - return reftype; -} - -/***************************************************** - PUBLIC: int biblatexin_convertf(), returns BIBL_OK or BIBL_ERR_MEMERR -*****************************************************/ - -/* is_utf8_emdash() - * - * Internally pages="A---B" will convert --- to a UTF8 - * emdash = 0xE2 (-30) 0x80 (-128) 0x94 (-108) - */ -static int -is_utf8_emdash( char *p ) -{ - static char emdash[3] = { -30, -128, -108 }; - if ( strncmp( p, emdash, 3 ) ) return 0; - return 1; -} -/* is_utf8_endash() - * - * Internally pages="A--B" will convert -- to a UTF8 - * endash = 0xE2 (-30) 0x80 (-128) 0x93 (-109) - */ -static int -is_utf8_endash( char *p ) -{ - static char endash[3] = { -30, -128, -109 }; - if ( strncmp( p, endash, 3 ) ) return 0; - return 1; -} - -static int -process_pages( fields *info, newstr *s, int level ) -{ - int fstatus, status = BIBL_OK; - newstr page; - char *p; - - newstr_findreplace( s, " ", "" ); - if ( s->len==0 ) return status; - - newstr_init( &page ); - p = skip_ws( s->data ); - while ( *p && !is_ws(*p) && *p!='-' && *p!=-30 ) - newstr_addchar( &page, *p++ ); - if ( page.len>0 ) { - fstatus = fields_add( info, "PAGESTART", page.data, level ); - if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } - } - - while ( *p && (is_ws(*p) || *p=='-' ) ) p++; - if ( *p && is_utf8_emdash( p ) ) p+=3; - if ( *p && is_utf8_endash( p ) ) p+=3; - - newstr_empty( &page ); - while ( *p && !is_ws(*p) && *p!='-' && *p!=-30 ) - newstr_addchar( &page, *p++ ); - if ( page.len>0 ) { - fstatus = fields_add( info, "PAGEEND", page.data, level ); - if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } - } -out: - newstr_free( &page ); - return status; -} - -static int -process_url( fields *info, char *p, int level ) -{ - int fstatus; - if ( !strncasecmp( p, "\\urllink", 8 ) ) - fstatus = fields_add( info, "URL", p+8, level ); - else if ( !strncasecmp( p, "\\url", 4 ) ) - fstatus = fields_add( info, "URL", p+4, level ); - else if ( !strncasecmp( p, "arXiv:", 6 ) ) - fstatus = fields_add( info, "ARXIV", p+6, level ); - else if ( !strncasecmp( p, "http://arxiv.org/abs/", 21 ) ) - fstatus = fields_add( info, "ARXIV", p+21, level ); - else if ( !strncasecmp( p, "http:", 5 ) ) - fstatus = fields_add( info, "URL", p, level ); - else - fstatus = fields_add( info, "URL", p, level ); - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} - - -/* process_howpublished() - * - * howpublished={}, - * - * Normally indicates the manner in which something was - * published in lieu of a formal publisher, so typically - * 'howpublished' and 'publisher' will never be in the - * same reference. - * - * Occasionally, people put Diploma thesis information - * into this field, so check for that first. - */ -static int -process_howpublished( fields *info, char *p, int level ) -{ - int fstatus; - if ( !strncasecmp( p, "Diplom", 6 ) ) - fstatus = fields_replace_or_add( info, "NGENRE", "Diploma thesis", level ); - else if ( !strncasecmp( p, "Habilitation", 13 ) ) - fstatus = fields_replace_or_add( info, "NGENRE", "Habilitation thesis", level ); - else - fstatus = fields_add( info, "PUBLISHER", p, level ); - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} - -static int -process_thesistype( fields *info, char *p, int level ) -{ - int fstatus; - /* type in the @thesis is used to distinguish Ph.D. and Master's thesis */ - if ( !strncasecmp( p, "phdthesis", 9 ) ) { - fstatus = fields_replace_or_add( info, "NGENRE", "Ph.D. thesis", level ); - } else if ( !strncasecmp( p, "mastersthesis", 13 ) || !strncasecmp( p, "masterthesis", 12 ) ) { - fstatus = fields_replace_or_add( info, "NGENRE", "Masters thesis", level ); - } else if ( !strncasecmp( p, "mathesis", 8 ) ) { - fstatus = fields_replace_or_add( info, "NGENRE", "Masters thesis", level ); - } else if ( !strncasecmp( p, "diploma", 7 ) ) { - fstatus = fields_replace_or_add( info, "NGENRE", "Diploma thesis", level ); - } else if ( !strncasecmp( p, "habilitation", 12 ) ) { - fstatus = fields_replace_or_add( info, "NGENRE", "Habilitation thesis", level ); - } - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} - -/* biblatex drops school field if institution is present */ -static int -process_school( fields *bibin, fields *info, char *tag, char *value, int level ) -{ - int fstatus; - if ( fields_find( bibin, "institution", LEVEL_ANY ) != -1 ) - return BIBL_OK; - else { - fstatus = fields_add( info, tag, value, level ); - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; - } -} - -/* biblatex drops school field if institution is present */ -static int -process_subtype( fields *bibin, fields *info, char *tag, char *value, int level ) -{ - int fstatus; - if ( !strcasecmp( value, "magazine" ) ) { - fstatus = fields_add( info, "NGENRE", "magazine article", LEVEL_MAIN ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - fstatus = fields_add( info, "NGENRE", "magazine", LEVEL_HOST ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } else if ( !strcasecmp( value, "newspaper" ) ) { - fstatus = fields_add( info, "NGENRE", "newspaper article", LEVEL_MAIN ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - fstatus = fields_add( info, "GENRE", "newspaper", LEVEL_HOST ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } - return BIBL_OK; -} - -static int -process_eprint( fields *bibin, fields *info, int level ) -{ - int neprint, netype, fstatus; - char *eprint = NULL, *etype = NULL; - neprint = fields_find( bibin, "eprint", -1 ); - netype = fields_find( bibin, "eprinttype", -1 ); - if ( neprint!=-1 ) eprint = bibin->data[neprint].data; - if ( netype!=-1 ) etype = bibin->data[netype].data; - if ( eprint && etype ) { - if ( !strncasecmp( etype, "arxiv", 5 ) ) { - fstatus = fields_add( info, "ARXIV", eprint, level ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } else if ( !strncasecmp( etype, "jstor", 5 ) ) { - fstatus = fields_add( info, "JSTOR", eprint, level ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } else if ( !strncasecmp( etype, "pubmed", 6 ) ) { - fstatus = fields_add( info, "PMID", eprint, level ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } else if ( !strncasecmp( etype, "medline", 7 ) ) { - fstatus = fields_add( info, "MEDLINE", eprint, level ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } else { - fstatus = fields_add( info, "EPRINT", eprint, level ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - fstatus = fields_add( info, "EPRINTTYPE", etype, level ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } - fields_setused( bibin, neprint ); - fields_setused( bibin, netype ); - } else if ( eprint ) { - fstatus = fields_add( info, "EPRINT", eprint, level ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - fields_setused( bibin, neprint ); - } else if ( etype ) { - fstatus = fields_add( info, "EPRINTTYPE", etype, level ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - fields_setused( bibin, netype ); - } - return BIBL_OK; -} - -static void -report( fields *f ) -{ - int i, n; - n = fields_num( f ); - for ( i=0; iverbose && strcmp( tag, "INTERNAL_TYPE" ) ) { - if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, " Cannot find tag '%s'\n", tag ); - } -} - -/* get_title_elements() - * - * find all of the biblatex title elements for the current level - * internal "TITLE" -> "title", "booktitle", "maintitle" - * internal "SUBTITLE" -> "subtitle", "booksubtitle", "mainsubtitle" - * internal "TITLEADDON" -> "titleaddon", "booktitleaddon", "maintitleaddon" - * - * place in ttl, subttl, and ttladdon strings - * - * return 1 if an element is found, 0 if not - */ -static int -get_title_elements( fields *bibin, int currlevel, int reftype, variants *all, int nall, - newstr *ttl, newstr *subttl, newstr *ttladdon ) -{ - int nfields, process, level, i, n; - newstr *t, *d; - char *newtag; - - newstrs_empty( ttl, subttl, ttladdon, NULL ); - - nfields = fields_num( bibin ); - - for ( i=0; ilen == 0 ) continue; - - n = translate_oldtag( t->data, reftype, all, nall, &process, &level, &newtag ); - if ( n==-1 ) continue; - if ( process != TITLE ) continue; - if ( level != currlevel ) continue; - - fields_setused( bibin, i ); - - if ( !strcasecmp( newtag, "TITLE" ) ) { - if ( ttl->len ) newstr_addchar( ttl, ' ' ); - newstr_newstrcat( ttl, d ); - } else if ( !strcasecmp( newtag, "SUBTITLE" ) ) { - if ( subttl->len ) newstr_addchar( subttl, ' ' ); - newstr_newstrcat( subttl, d ); - } else if ( !strcasecmp( newtag, "TITLEADDON" ) ) { - if ( ttladdon->len ) newstr_addchar( ttladdon, ' ' ); - newstr_newstrcat( ttladdon, d ); - } - } - - return ( ttl->len>0 || subttl->len > 0 || ttladdon->len > 0 ); -} - -/* attach_addon() - * - * Add titleaddon to the title. - */ -static void -attach_addon( newstr *title, newstr *addon ) -{ - if ( title->len ) { - if ( title->data[title->len-1]!='.' ) - newstr_addchar( title, '.' ); - newstr_addchar( title, ' ' ); - } - newstr_newstrcat( title, addon ); -} - -static int -process_combined_title( fields *info, newstr *ttl, newstr *subttl, newstr *ttladdon, int currlevel ) -{ - int fstatus, status = BIBL_OK; - newstr combined; - - newstr_init( &combined ); - newstr_newstrcpy( &combined, ttl ); - if ( subttl->len ) { - if ( combined.len && combined.data[combined.len-1]!=':' && combined.data[combined.len-1]!='?' ) - newstr_addchar( &combined, ':' ); - newstr_addchar( &combined, ' ' ); - newstr_newstrcat( &combined, subttl ); - } - if ( ttladdon->len ) attach_addon( &combined, ttladdon ); - if ( newstr_memerr( &combined ) ) { status = BIBL_ERR_MEMERR; goto out; } - fstatus = fields_add( info, "TITLE", combined.data, currlevel ); - if ( fstatus==FIELDS_OK ) status = BIBL_ERR_MEMERR; -out: - newstr_free( &combined ); - return status; -} - -static int -process_separated_title( fields *info, newstr *ttl, newstr *subttl, newstr *ttladdon, int currlevel ) -{ - int fstatus; - if ( ttladdon->len ) { - if ( subttl->len ) attach_addon( subttl, ttladdon ); - else attach_addon( ttl, ttladdon ); - } - if ( ttl->len ) { - fstatus = fields_add( info, "TITLE", ttl->data, currlevel ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } - if ( subttl->len ) { - fstatus = fields_add( info, "SUBTITLE", subttl->data, currlevel ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } - return BIBL_OK; -} - -static int -process_title_all( fields *bibin, fields *info, int reftype, param *p, - variants *all, int nall ) -{ - int currlevel, found, status = BIBL_OK; - newstr ttl, subttl, ttladdon; - newstrs_init( &ttl, &subttl, &ttladdon, NULL ); - for ( currlevel = 0; currlevelnosplittitle ) - status = process_combined_title( info, &ttl, &subttl, &ttladdon, currlevel ); - else - status = process_separated_title( info, &ttl, &subttl, &ttladdon, currlevel ); - if ( status!=BIBL_OK ) goto out; - } -out: - newstrs_free( &ttl, &subttl, &ttladdon, NULL ); - return status; -} - - -static int -biblatex_matches_list( fields *info, char *tag, char *suffix, newstr *data, int level, - list *names, int *match ) -{ - int i, fstatus, status = BIBL_OK; - newstr newtag; - - *match = 0; - if ( names->n==0 ) return status; - - newstr_init( &newtag ); - - for ( i=0; in; ++i ) { - if ( strcmp( data->data, list_getc( names, i ) ) ) continue; - newstr_initstr( &newtag, tag ); - newstr_strcat( &newtag, suffix ); - fstatus = fields_add( info, newtag.data, data->data, level ); - if ( fstatus!=FIELDS_OK ) { - status = BIBL_ERR_MEMERR; - goto out; - } - *match = 1; - goto out; - } - -out: - newstr_free( &newtag ); - return status; -} - -static int -biblatex_names( fields *info, char *tag, newstr *data, int level, list *asis, list *corps ) -{ - int begin, end, ok, n, etal, i, match, status = BIBL_OK; - list tokens; - - /* If we match the asis or corps list add and bail. */ - status = biblatex_matches_list( info, tag, ":ASIS", data, level, asis, &match ); - if ( match==1 || status!=BIBL_OK ) return status; - status = biblatex_matches_list( info, tag, ":CORP", data, level, corps, &match ); - if ( match==1 || status!=BIBL_OK ) return status; - - list_init( &tokens ); - - biblatex_split( &tokens, data ); - for ( i=0; idata, editor_fields[i] ) ) n = i; - ntype = fields_find( bibin, editor_types[n], LEVEL_ANY ); - if ( ntype!=-1 ) { - type = fields_value( bibin, ntype, FIELDS_CHRP_NOUSE ); - if ( !strcasecmp( type, "collaborator" ) ) outtag = "COLLABORATOR"; - else if ( !strcasecmp( type, "compiler" ) ) outtag = "COMPILER"; - else if ( !strcasecmp( type, "redactor" ) ) outtag = "REDACTOR"; - else if ( !strcasecmp( type, "director" ) ) outtag = "DIRECTOR"; - else if ( !strcasecmp( type, "producer" ) ) outtag = "PRODUCER"; - else if ( !strcasecmp( type, "none" ) ) outtag = "PERFORMER"; - } - return biblatex_names( info, outtag, value, level, asis, corps ); -} - -static int -biblatexin_simple( fields *f, char *tag, char *value, int level ) -{ - int fstatus = fields_add( f, tag, value, level ); - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} - -int -biblatexin_convertf( fields *bibin, fields *info, int reftype, param *p, - variants *all, int nall ) -{ - int process, level, i, n, nfields, status = BIBL_OK; - newstr *t, *d; - char *newtag; - - nfields = fields_num( bibin ); - for ( i=0; ilen == 0 || d->len == 0 ) continue; - - n = translate_oldtag( t->data, reftype, all, nall, &process, &level, &newtag ); - if ( n==-1 ) { - biblatexin_notag( p, t->data ); - continue; - } - - switch ( process ) { - - case SIMPLE: - status = biblatexin_simple( info, newtag, d->data, level ); - fields_setused( bibin, i ); - break; - - case PERSON: - status = biblatex_names( info, newtag, d, level, &(p->asis), &(p->corps) ); - fields_setused( bibin, i ); - break; - - case BLT_EDITOR: - status = process_editor( bibin, info, t, d, level, &(p->asis), &(p->corps) ); - fields_setused( bibin, i ); - break; - - case PAGES: - status = process_pages( info, d, level); - fields_setused( bibin, i ); - break; - - case HOWPUBLISHED: - status = process_howpublished( info, d->data, level ); - fields_setused( bibin, i ); - break; - - case BT_URL: - status = process_url( info, d->data, level ); - fields_setused( bibin, i ); - break; - - case BT_GENRE: - status = biblatexin_simple( info, "NGENRE", d->data, level ); - fields_setused( bibin, i ); - break; - - case BT_EPRINT: - status = process_eprint( bibin, info, level ); - fields_setused( bibin, i ); - break; - - case BLT_THESIS_TYPE: - status = process_thesistype( info, d->data, level ); - fields_setused( bibin, i ); - break; - - case BLT_SCHOOL: - status = process_school( bibin, info, newtag, d->data, level ); - fields_setused( bibin, i ); - break; - - case BLT_SUBTYPE: - status = process_subtype( bibin, info, newtag, d->data, level ); - fields_setused( bibin, i ); - break; - - case BLT_SKIP: - status = BIBL_OK; - fields_setused( bibin, i ); - break; - - case TITLE: - status = BIBL_OK; /* delay title processing until later */ - break; - - default: - status = BIBL_OK; - break; - - } - if ( status!=BIBL_OK ) return status; - - } - - status = process_title_all( bibin, info, reftype, p, all, nall ); - - if ( status==BIBL_OK && p->verbose ) report( info ); + * Copyright (c) Chris Putnam 2008-2017 + * Copyright (c) Johannes Wilm 2010-2017 + * + * Program and source code released under the GPL version 2 + * + */ +#include +#include +#include +#include +#include "is_ws.h" +#include "strsearch.h" +#include "str.h" +#include "utf8.h" +#include "str_conv.h" +#include "fields.h" +#include "slist.h" +#include "name.h" +#include "reftypes.h" +#include "bibformats.h" +#include "generic.h" + +extern variants biblatex_all[]; +extern int biblatex_nall; + +static slist find = { 0, 0, 0, NULL }; +static slist replace = { 0, 0, 0, NULL }; + +/***************************************************** + PUBLIC: void biblatexin_initparams() +*****************************************************/ + +static int biblatexin_convertf( fields *bibin, fields *info, int reftype, param *p ); +static int biblatexin_processf( fields *bibin, char *data, char *filename, long nref, param *p ); +static int biblatexin_cleanf( bibl *bin, param *p ); +static int biblatexin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int biblatexin_typef( fields *bibin, char *filename, int nrefs, param *p ); + +void +biblatexin_initparams( param *p, const char *progname ) +{ + p->readformat = BIBL_BIBLATEXIN; + p->charsetin = BIBL_CHARSET_DEFAULT; + p->charsetin_src = BIBL_SRC_DEFAULT; + p->latexin = 1; + p->xmlin = 0; + p->utf8in = 0; + p->nosplittitle = 0; + p->verbose = 0; + p->addcount = 0; + p->output_raw = 0; + + p->readf = biblatexin_readf; + p->processf = biblatexin_processf; + p->cleanf = biblatexin_cleanf; + p->typef = biblatexin_typef; + p->convertf = biblatexin_convertf; + p->all = biblatex_all; + p->nall = biblatex_nall; + + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); + + if ( !progname ) p->progname = NULL; + else p->progname = strdup( progname ); +} + +/***************************************************** + PUBLIC: int biblatexin_readf() +*****************************************************/ + +/* + * readf can "read too far", so we store this information in line, thus + * the next new text is in line, either from having read too far or + * from the next chunk obtained via str_fget() + * + * return 1 on success, 0 on error/end-of-file + * + */ +static int +readmore( FILE *fp, char *buf, int bufsize, int *bufpos, str *line ) +{ + if ( line->len ) return 1; + else return str_fget( fp, buf, bufsize, bufpos, line ); +} + +/* + * readf() + * + * returns zero if cannot get reference and hit end of-file + * returns 1 if last reference in file, 2 if reference within file + */ +static int +biblatexin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) +{ + int haveref = 0; + char *p; + while ( haveref!=2 && readmore( fp, buf, bufsize, bufpos, line ) ) { + if ( line->len == 0 ) continue; /* blank line */ + p = &(line->data[0]); + p = skip_ws( p ); + if ( *p == '%' ) { /* commented out line */ + str_empty( line ); + continue; + } + if ( *p == '@' ) haveref++; + if ( haveref && haveref<2 ) { + str_strcatc( reference, p ); + str_addchar( reference, '\n' ); + str_empty( line ); + } else if ( !haveref ) str_empty( line ); + + } + *fcharset = CHARSET_UNKNOWN; + return haveref; +} + +/***************************************************** + PUBLIC: int biblatexin_processf() +*****************************************************/ + +static char * +process_biblatextype( char *p, str *type ) +{ + str tmp; + str_init( &tmp ); + + if ( *p=='@' ) p++; + p = str_cpytodelim( &tmp, p, "{( \t\r\n", 0 ); + p = skip_ws( p ); + if ( *p=='{' || *p=='(' ) p++; + p = skip_ws( p ); + + if ( str_has_value( &tmp ) ) str_strcpy( type, &tmp ); + else str_empty( type ); + + str_free( &tmp ); + return p; +} + +static char * +process_biblatexid( char *p, str *id ) +{ + char *start_p = p; + str tmp; + + str_init( &tmp ); + p = str_cpytodelim( &tmp, p, ",", 1 ); + + if ( str_has_value( &tmp ) ) { + if ( strchr( tmp.data, '=' ) ) { + /* Endnote writes biblatex files w/o fields, try to + * distinguish via presence of an equal sign.... if + * it's there, assume that it's a tag/data pair instead + * and roll back. + */ + p = start_p; + str_empty( id ); + } else { + str_strcpy( id, &tmp ); + } + } else { + str_empty( id ); + } + + str_free( &tmp ); + return skip_ws( p ); +} + +static char * +biblatex_tag( char *p, str *tag ) +{ + p = str_cpytodelim( tag, skip_ws( p ), "= \t\r\n", 0 ); + return skip_ws( p ); +} + +static char * +biblatex_data( char *p, fields *bibin, slist *tokens, long nref, param *pm ) +{ + unsigned int nbracket = 0, nquotes = 0; + char *startp = p; + str tok, *s; + + str_init( &tok ); + while ( p && *p ) { + if ( !nquotes && !nbracket ) { + if ( *p==',' || *p=='=' || *p=='}' || *p==')' ) + goto out; + } + if ( *p=='\"' && nbracket==0 && ( p==startp || *(p-1)!='\\' ) ) { + nquotes = !nquotes; + str_addchar( &tok, *p ); + if ( !nquotes ) { + s = slist_add( tokens, &tok ); + if ( !s ) { p = NULL; goto outerr; } + str_empty( &tok ); + } + } else if ( *p=='#' && !nquotes && !nbracket ) { + if ( str_has_value( &tok ) ) { + s = slist_add( tokens, &tok ); + if ( !s ) { p = NULL; goto outerr; } + } + str_strcpyc( &tok, "#" ); + s = slist_add( tokens, &tok ); + if ( !s ) { p = NULL; goto outerr; } + str_empty( &tok ); + } else if ( *p=='{' && !nquotes && ( p==startp || *(p-1)!='\\' ) ) { + nbracket++; + str_addchar( &tok, *p ); + } else if ( *p=='}' && !nquotes && ( p==startp || *(p-1)!='\\' ) ) { + nbracket--; + str_addchar( &tok, *p ); + if ( nbracket==0 ) { + s = slist_add( tokens, &tok ); + if ( !s ) { p = NULL; goto outerr; } + str_empty( &tok ); + } + } else if ( !is_ws( *p ) || nquotes || nbracket ) { + if ( !is_ws( *p ) ) str_addchar( &tok, *p ); + else { + if ( tok.len!=0 && *p!='\n' && *p!='\r' ) + str_addchar( &tok, *p ); + else if ( tok.len!=0 && (*p=='\n' || *p=='\r')) { + str_addchar( &tok, ' ' ); + while ( is_ws( *(p+1) ) ) p++; + } + } + } else if ( is_ws( *p ) ) { + if ( str_has_value( &tok ) ) { + s = slist_add( tokens, &tok ); + if ( !s ) { p = NULL; goto outerr; } + str_empty( &tok ); + } + } + p++; + } +out: + if ( nbracket!=0 ) { + fprintf( stderr, "%s: Mismatch in number of brackets in reference %ld\n", pm->progname, nref ); + } + if ( nquotes!=0 ) { + fprintf( stderr, "%s: Mismatch in number of quotes in reference %ld\n", pm->progname, nref ); + } + if ( str_has_value( &tok ) ) { + s = slist_add( tokens, &tok ); + if ( !s ) p = NULL; + } +outerr: + str_free( &tok ); + return p; +} + +/* replace_strings() + * + * do string replacement -- only if unprotected by quotation marks or curly brackets + */ +static void +replace_strings( slist *tokens, fields *bibin, long nref, param *pm ) +{ + int i, n, ok; + char *q; + str *s; + i = 0; + while ( i < tokens->n ) { + s = slist_str( tokens, i ); + if ( !strcmp( s->data, "#" ) ) { + } else if ( s->data[0]!='\"' && s->data[0]!='{' ) { + n = slist_find( &find, s ); + if ( n!=-1 ) { + str_strcpy( s, slist_str( &replace, n ) ); + } else { + q = s->data; + ok = 1; + while ( *q && ok ) { + if ( !isdigit( *q ) ) ok = 0; + q++; + } + if ( !ok ) { + fprintf( stderr, "%s: Warning: Non-numeric " + "BibTeX elements should be in quotations or " + "curly brackets in reference %ld\n", pm->progname, nref ); + } + } + } + i++; + } +} + +static int +string_concatenate( slist *tokens, fields *bibin, long nref, param *pm ) +{ + int i, status; + str *s, *t; + i = 0; + while ( i < tokens->n ) { + s = slist_str( tokens, i ); + if ( !strcmp( str_cstr( s ), "#" ) ) { + if ( i==0 || i==tokens->n-1 ) { + fprintf( stderr, "%s: Warning: Stray string concatenation " + "('#' character) in reference %ld\n", pm->progname, nref ); + status = slist_remove( tokens, i ); + if ( status!=SLIST_OK ) return BIBL_ERR_MEMERR; + continue; + } + s = slist_str( tokens, i-1 ); + if ( s->data[0]!='\"' && s->data[s->len-1]!='\"' ) + fprintf( stderr, "%s: Warning: String concentation should " + "be used in context of quotations marks in reference %ld\n", pm->progname, nref ); + t = slist_str( tokens, i+1 ); + if ( t->data[0]!='\"' && t->data[s->len-1]!='\"' ) + fprintf( stderr, "%s: Warning: String concentation should " + "be used in context of quotations marks in reference %ld\n", pm->progname, nref ); + if ( ( s->data[s->len-1]=='\"' && t->data[0]=='\"') || (s->data[s->len-1]=='}' && t->data[0]=='{') ) { + str_trimend( s, 1 ); + str_trimbegin( t, 1 ); + str_strcat( s, t ); + } else { + str_strcat( s, t ); + } + status = slist_remove( tokens, i ); + if ( status!=SLIST_OK ) return BIBL_ERR_MEMERR; + status = slist_remove( tokens, i ); + if ( status!=SLIST_OK ) return BIBL_ERR_MEMERR; + } else i++; + } + return BIBL_OK; +} + +static char * +process_biblatexline( char *p, str *tag, str *data, uchar stripquotes, long nref, param *pm ) +{ + int i, status; + slist tokens; + str *s; + + str_empty( data ); + + p = biblatex_tag( p, tag ); + if ( tag->len==0 ) return p; + + slist_init( &tokens ); + + if ( *p=='=' ) p = biblatex_data( p+1, NULL, &tokens, nref, pm ); + + replace_strings( &tokens, NULL, nref, pm ); + + status = string_concatenate( &tokens, NULL, nref, pm ); + if ( status!=BIBL_OK ) { + p = NULL; + goto out; + } + + for ( i=0; idata[0]=='\"' && s->data[s->len-1]=='\"' ) || + ( s->data[0]=='{' && s->data[s->len-1]=='}' ) ) { + str_trimbegin( s, 1 ); + str_trimend( s, 1 ); + } + str_strcat( data, slist_str( &tokens, i ) ); + } +out: + slist_free( &tokens ); + return p; +} + +static int +process_cite( fields *bibin, char *p, char *filename, long nref, param *pm ) +{ + int fstatus, status = BIBL_OK; + str tag, data; + strs_init( &tag, &data, NULL ); + p = process_biblatextype( p, &data ); + if ( str_has_value( &data ) ) { + fstatus = fields_add( bibin, "INTERNAL_TYPE", str_cstr( &data ), 0 ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + } + p = process_biblatexid ( p, &data ); + if ( str_has_value( &data ) ) { + fstatus = fields_add( bibin, "REFNUM", str_cstr( &data ), 0 ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + } + while ( *p ) { + p = process_biblatexline( p, &tag, &data, 1, nref, pm ); + if ( !p ) { status = BIBL_ERR_MEMERR; goto out; } + /* no anonymous or empty fields allowed */ + if ( str_has_value( &tag ) && str_has_value( &data ) ) { + fstatus = fields_add( bibin, str_cstr( &tag ), str_cstr( &data ), 0 ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + } + strs_empty( &tag, &data, NULL ); + } +out: + strs_free( &tag, &data, NULL ); + return status; +} + +/* process_string() + * + * Handle lines like: + * + * '@STRING{TL = {Tetrahedron Lett.}}' + * + * p should point to just after '@STRING' + * + * In BibTeX, if a string is defined several times, the last one is kept. + * + */ +static int +process_string( char *p, long nref, param *pm ) +{ + int n, status = BIBL_OK; + str s1, s2, *s; + strs_init( &s1, &s2, NULL ); + while ( *p && *p!='{' && *p!='(' ) p++; + if ( *p=='{' || *p=='(' ) p++; + p = process_biblatexline( skip_ws( p ), &s1, &s2, 0, nref, pm ); + if ( str_has_value( &s2 ) ) { + str_findreplace( &s2, "\\ ", " " ); + if ( str_memerr( &s2 ) ) { status = BIBL_ERR_MEMERR; goto out; } + } + if ( str_has_value( &s1 ) ) { + n = slist_find( &find, &s1 ); + if ( n==-1 ) { + s = slist_add( &find, &s1 ); + if ( s==NULL ) { status = BIBL_ERR_MEMERR; goto out; } + if ( str_has_value( &s2 ) ) s = slist_add( &replace, &s2 ); + else s = slist_addc( &replace, "" ); + if ( s==NULL ) { status = BIBL_ERR_MEMERR; goto out; } + } else { + if ( str_has_value( &s2 ) ) s = slist_set( &replace, n, &s2 ); + else s = slist_setc( &replace, n, "" ); + if ( s==NULL ) { status = BIBL_ERR_MEMERR; goto out; } + } + } +out: + strs_free( &s1, &s2, NULL ); + return status; +} + +static int +biblatexin_processf( fields *bibin, char *data, char *filename, long nref, param *p ) +{ + if ( !strncasecmp( data, "@STRING", 7 ) ) { + process_string( data+7, nref, p ); + return 0; + } else { + process_cite( bibin, data, filename, nref, p ); + return 1; + } +} + +/***************************************************** + PUBLIC: void biblatexin_cleanf() +*****************************************************/ + +static void +biblatex_process_tilde( str *s ) +{ + char *p, *q; + int n = 0; + + p = q = s->data; + if ( !p ) return; + while ( *p ) { + if ( *p=='~' ) { + *q = ' '; + } else if ( *p=='\\' && *(p+1)=='~' ) { + n++; + p++; + *q = '~'; + } else { + *q = *p; + } + p++; + q++; + } + *q = '\0'; + s->len -= n; +} + +static void +biblatex_process_bracket( str *s ) +{ + char *p, *q; + int n = 0; + + p = q = s->data; + if ( !p ) return; + while ( *p ) { + if ( *p=='\\' && ( *(p+1)=='{' || *(p+1)=='}' ) ) { + n++; + p++; + *q = *p; + q++; + } else if ( *p=='{' || *p=='}' ) { + n++; + } else { + *q = *p; + q++; + } + p++; + } + *q = '\0'; + s->len -= n; +} + +static int +biblatex_cleantoken( str *s ) +{ + /* 'textcomp' annotations */ + str_findreplace( s, "\\textit", "" ); + str_findreplace( s, "\\textbf", "" ); + str_findreplace( s, "\\textsl", "" ); + str_findreplace( s, "\\textsc", "" ); + str_findreplace( s, "\\textsf", "" ); + str_findreplace( s, "\\texttt", "" ); + str_findreplace( s, "\\textsubscript", "" ); + str_findreplace( s, "\\textsuperscript", "" ); + str_findreplace( s, "\\emph", "" ); + str_findreplace( s, "\\url", "" ); + + /* Other text annotations */ + str_findreplace( s, "\\it ", "" ); + str_findreplace( s, "\\em ", "" ); + + str_findreplace( s, "\\%", "%" ); + str_findreplace( s, "\\$", "$" ); + while ( str_findreplace( s, " ", " " ) ) {} + + /* 'textcomp' annotations that we don't want to substitute on output*/ + str_findreplace( s, "\\textdollar", "$" ); + str_findreplace( s, "\\textunderscore", "_" ); + + biblatex_process_bracket( s ); + biblatex_process_tilde( s ); + + if ( !str_memerr( s ) ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + +static int +biblatex_split( slist *tokens, str *s ) +{ + int i, n = s->len, nbrackets = 0, status = BIBL_OK; + str tok, *t; + + str_init( &tok ); + + for ( i=0; idata[i]=='{' && ( i==0 || s->data[i-1]!='\\' ) ) { + nbrackets++; + str_addchar( &tok, '{' ); + } else if ( s->data[i]=='}' && ( i==0 || s->data[i-1]!='\\' ) ) { + nbrackets--; + str_addchar( &tok, '}' ); + } else if ( !is_ws( s->data[i] ) || nbrackets ) { + str_addchar( &tok, s->data[i] ); + } else if ( is_ws( s->data[i] ) ) { + if ( str_memerr( &tok ) ) { status = BIBL_ERR_MEMERR; goto out; } + if ( str_has_value( &tok ) ) { + t = slist_add( tokens, &tok ); + if ( !t ) { status = BIBL_ERR_MEMERR; goto out; } + } + str_empty( &tok ); + } + } + if ( str_has_value( &tok ) ) { + if ( str_memerr( &tok ) ) { status = BIBL_ERR_MEMERR; goto out; } + t = slist_add( tokens, &tok ); + if ( !t ) { status = BIBL_ERR_MEMERR; goto out; } + } + + for ( i=0; in; ++i ) { + t = slist_str( tokens, i ); + str_trimstartingws( t ); + str_trimendingws( t ); + if ( str_memerr( t ) ) { status = BIBL_ERR_MEMERR; goto out; } + } +out: + str_free( &tok ); + return status; +} + +static int +biblatexin_addtitleurl( fields *info, str *in ) +{ + int fstatus, status = BIBL_OK; + char *p; + str s; + + str_init( &s ); + /* skip past "\href{" */ + p = str_cpytodelim( &s, in->data + 6, "}", 1 ); + if ( str_memerr( &s ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } + fstatus = fields_add( info, "URL", s.data, 0 ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + + p = str_cpytodelim( &s, p, "", 0 ); + if ( str_memerr( &s ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } + str_swapstrings( &s, in ); +out: + str_free( &s ); + return status; +} + +static int +is_name_tag( str *tag ) +{ + if ( str_has_value( tag ) ) { + if ( !strcasecmp( str_cstr( tag ), "author" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "editor" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "editorb" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "editorc" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "director" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "producer" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "execproducer" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "writer" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "redactor" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "annotator" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "commentator" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "translator" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "foreword" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "afterword" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "introduction" ) ) return 1; + } + return 0; +} + +static int +is_url_tag( str *tag ) +{ + if ( str_has_value( tag ) ) { + if ( !strcasecmp( str_cstr( tag ), "url" ) ) return 1; + } + return 0; +} + +static int +biblatexin_cleandata( str *tag, str *s, fields *info, param *p ) +{ + slist tokens; + str *tok; + int i, status = BIBL_OK; + if ( str_is_empty( s ) ) return status; + /* protect url from undergoing any parsing */ + if ( is_url_tag( tag ) ) return status; + slist_init( &tokens ); + biblatex_split( &tokens, s ); + for ( i=0; ilatexin && !is_name_tag( tag ) ) { + status = biblatex_cleantoken( slist_str( &tokens, i ) ); + if ( status!=BIBL_OK ) goto out; + } + } + str_empty( s ); + for ( i=0; i0 ) str_addchar( s, ' ' ); + str_strcat( s, tok ); + } +out: + slist_free( &tokens ); + return status; +} + +static long +biblatexin_findref( bibl *bin, char *citekey ) +{ + int n; + long i; + for ( i=0; inrefs; ++i ) { + n = fields_find( bin->ref[i], "refnum", -1 ); + if ( n==-1 ) continue; + if ( !strcmp( bin->ref[i]->data[n].data, citekey ) ) return i; + } + return -1; +} + +static void +biblatexin_nocrossref( bibl *bin, long i, int n, param *p ) +{ + int n1 = fields_find( bin->ref[i], "REFNUM", -1 ); + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Cannot find cross-reference '%s'", + bin->ref[i]->data[n].data); + if ( n1!=-1 ) + fprintf( stderr, " for reference '%s'\n", + bin->ref[i]->data[n1].data ); + fprintf( stderr, "\n" ); +} + +static int +biblatexin_crossref_oneref( fields *ref, fields *cross ) +{ + int j, nl, ntype, fstatus; + char *type, *nt, *nd; + ntype = fields_find( ref, "INTERNAL_TYPE", -1 ); + type = ( char * ) fields_value( ref, ntype, FIELDS_CHRP_NOUSE ); + for ( j=0; jn; ++j ) { + nt = ( char * ) fields_tag( cross, j, FIELDS_CHRP_NOUSE ); + if ( !strcasecmp( nt, "INTERNAL_TYPE" ) ) continue; + if ( !strcasecmp( nt, "REFNUM" ) ) continue; + if ( !strcasecmp( nt, "TITLE" ) ) { + if ( !strcasecmp( type, "Inproceedings" ) || + !strcasecmp( type, "Incollection" ) ) + nt = "booktitle"; + } + nd = ( char * ) fields_value( cross, j, FIELDS_CHRP_NOUSE ); + nl = fields_level( cross, j ) + 1; + fstatus = fields_add( ref, nt, nd, nl ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + return BIBL_OK; +} + +static int +biblatexin_crossref( bibl *bin, param *p ) +{ + int n, ncross, status = BIBL_OK; + fields *ref, *cross; + long i; + for ( i=0; inrefs; ++i ) { + ref = bin->ref[i]; + n = fields_find( ref, "CROSSREF", -1 ); + if ( n==-1 ) continue; + fields_setused( ref, n ); + ncross = biblatexin_findref(bin, (char*)fields_value(ref,n, FIELDS_CHRP_NOUSE)); + if ( ncross==-1 ) { + biblatexin_nocrossref( bin, i, n, p ); + continue; + } + cross = bin->ref[ncross]; + status = biblatexin_crossref_oneref( ref, cross ); + if ( status!=BIBL_OK ) return status; + } + return status; +} + +static int +biblatexin_cleanref( fields *bibin, param *p ) +{ + int i, n, status; + str *t, *d; + n = fields_num( bibin ); + for ( i=0; inrefs; ++i ) { + status = biblatexin_cleanref( bin->ref[i], p ); + if ( status!=BIBL_OK ) return status; + } + status = biblatexin_crossref( bin, p ); + return status; +} + +/***************************************************** + PUBLIC: void biblatexin_typef() +*****************************************************/ + +static int +biblatexin_typef( fields *bibin, char *filename, int nrefs, param *p ) +{ + int ntypename, nrefname, is_default; + char *refname = "", *typename=""; + + ntypename = fields_find( bibin, "INTERNAL_TYPE", LEVEL_MAIN ); + nrefname = fields_find( bibin, "REFNUM", LEVEL_MAIN ); + if ( nrefname!=-1 ) refname = fields_value( bibin, nrefname, FIELDS_CHRP_NOUSE ); + if ( ntypename!=-1 ) typename = fields_value( bibin, ntypename, FIELDS_CHRP_NOUSE ); + + return get_reftype( typename, nrefs, p->progname, p->all, p->nall, refname, &is_default, REFTYPE_CHATTY ); +} + +/***************************************************** + PUBLIC: int biblatexin_convertf(), returns BIBL_OK or BIBL_ERR_MEMERR +*****************************************************/ + +/* get_title_elements() + * + * find all of the biblatex title elements for the current level + * internal "TITLE" -> "title", "booktitle", "maintitle" + * internal "SUBTITLE" -> "subtitle", "booksubtitle", "mainsubtitle" + * internal "TITLEADDON" -> "titleaddon", "booktitleaddon", "maintitleaddon" + * + * place in ttl, subttl, and ttladdon strings + * + * return 1 if an element is found, 0 if not + */ +static int +get_title_elements( fields *bibin, int currlevel, int reftype, variants *all, int nall, str *ttl, str *subttl, str *ttladdon ) +{ + int nfields, process, level, i; + str *t, *d; + char *newtag; + + strs_empty( ttl, subttl, ttladdon, NULL ); + + nfields = fields_num( bibin ); + + for ( i=0; ilen == 0 ) continue; + + if ( !translate_oldtag( t->data, reftype, all, nall, &process, &level, &newtag ) ) + continue; + if ( process != TITLE ) continue; + if ( level != currlevel ) continue; + + fields_setused( bibin, i ); + + if ( !strcasecmp( newtag, "TITLE" ) ) { + if ( str_has_value( ttl ) ) str_addchar( ttl, ' ' ); + str_strcat( ttl, d ); + } else if ( !strcasecmp( newtag, "SUBTITLE" ) ) { + if ( str_has_value( subttl ) ) str_addchar( subttl, ' ' ); + str_strcat( subttl, d ); + } else if ( !strcasecmp( newtag, "TITLEADDON" ) ) { + if ( str_has_value( ttladdon ) ) str_addchar( ttladdon, ' ' ); + str_strcat( ttladdon, d ); + } + } + + return ( ttl->len>0 || subttl->len > 0 || ttladdon->len > 0 ); +} + +/* attach_subtitle() + * + * Add subtitle (if exists) to the title + */ +static void +attach_subtitle( str *title, str *subtitle ) +{ + if ( str_has_value( subtitle ) ) { + if ( str_has_value( title ) ) { + if ( title->data[title->len-1]!=':' && title->data[title->len-1]!='?' ) + str_addchar( title, ':' ); + str_addchar( title, ' ' ); + } + str_strcat( title, subtitle ); + } +} + +/* attach_addon() + * + * Add titleaddon (if exists) to the title. + */ +static void +attach_addon( str *title, str *addon ) +{ + if ( str_has_value( addon ) ) { + if ( str_has_value( title ) ) { + if ( title->data[title->len-1]!='.' ) + str_addchar( title, '.' ); + str_addchar( title, ' ' ); + } + str_strcat( title, addon ); + } +} + +static int +process_combined_title( fields *info, str *ttl, str *subttl, str *ttladdon, int currlevel ) +{ + int fstatus, status = BIBL_OK; + str combined; + + str_init( &combined ); + + str_strcpy( &combined, ttl ); + attach_subtitle( &combined, subttl ); + attach_addon( &combined, ttladdon ); + + if ( str_memerr( &combined ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } + + fstatus = fields_add( info, "TITLE", combined.data, currlevel ); + if ( fstatus==FIELDS_OK ) status = BIBL_ERR_MEMERR; +out: + str_free( &combined ); + return status; +} + +static int +process_separated_title( fields *info, str *ttl, str *subttl, str *ttladdon, int currlevel ) +{ + int fstatus; + if ( str_has_value( ttladdon ) ) { + if ( subttl->len ) attach_addon( subttl, ttladdon ); + else attach_addon( ttl, ttladdon ); + } + if ( str_has_value( ttl ) ) { + fstatus = fields_add( info, "TITLE", str_cstr( ttl ), currlevel ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + if ( str_has_value( subttl ) ) { + fstatus = fields_add( info, "SUBTITLE", str_cstr( subttl ), currlevel ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + return BIBL_OK; +} + +static int +process_title_all( fields *bibin, fields *info, int reftype, param *p ) +{ + int currlevel, found, status = BIBL_OK; + str ttl, subttl, ttladdon; + strs_init( &ttl, &subttl, &ttladdon, NULL ); + for ( currlevel = 0; currlevelall, p->nall, &ttl, &subttl, &ttladdon ); + if ( !found ) continue; + if ( p->nosplittitle ) + status = process_combined_title( info, &ttl, &subttl, &ttladdon, currlevel ); + else + status = process_separated_title( info, &ttl, &subttl, &ttladdon, currlevel ); + if ( status!=BIBL_OK ) goto out; + } +out: + strs_free( &ttl, &subttl, &ttladdon, NULL ); + return status; +} + + +static int +biblatex_matches_list( fields *info, char *tag, char *suffix, str *data, int level, slist *names, int *match ) +{ + int i, fstatus, status = BIBL_OK; + str newtag; + + *match = 0; + if ( names->n==0 ) return status; + + str_init( &newtag ); + + for ( i=0; in; ++i ) { + if ( strcmp( str_cstr( data ), slist_cstr( names, i ) ) ) continue; + str_initstrc( &newtag, tag ); + str_strcatc( &newtag, suffix ); + fstatus = fields_add( info, str_cstr( &newtag ), str_cstr( data ), level ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + *match = 1; + goto out; + } + +out: + str_free( &newtag ); + return status; +} + +static int +biblatex_names( fields *info, char *tag, str *data, int level, slist *asis, slist *corps ) +{ + int begin, end, ok, n, etal, i, match, status = BIBL_OK; + slist tokens; + + /* If we match the asis or corps list add and bail. */ + status = biblatex_matches_list( info, tag, ":ASIS", data, level, asis, &match ); + if ( match==1 || status!=BIBL_OK ) return status; + status = biblatex_matches_list( info, tag, ":CORP", data, level, corps, &match ); + if ( match==1 || status!=BIBL_OK ) return status; + + slist_init( &tokens ); + + biblatex_split( &tokens, data ); + for ( i=0; idata; + int fstatus = FIELDS_OK; + /* type in the @thesis is used to distinguish Ph.D. and Master's thesis */ + if ( !strncasecmp( p, "phdthesis", 9 ) ) { + fstatus = fields_replace_or_add( bibout, "NGENRE", "Ph.D. thesis", level ); + } else if ( !strncasecmp( p, "mastersthesis", 13 ) || !strncasecmp( p, "masterthesis", 12 ) ) { + fstatus = fields_replace_or_add( bibout, "NGENRE", "Masters thesis", level ); + } else if ( !strncasecmp( p, "mathesis", 8 ) ) { + fstatus = fields_replace_or_add( bibout, "NGENRE", "Masters thesis", level ); + } else if ( !strncasecmp( p, "diploma", 7 ) ) { + fstatus = fields_replace_or_add( bibout, "NGENRE", "Diploma thesis", level ); + } else if ( !strncasecmp( p, "habilitation", 12 ) ) { + fstatus = fields_replace_or_add( bibout, "NGENRE", "Habilitation thesis", level ); + } + if ( fstatus==FIELDS_OK ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + +static int +biblatexin_bteprint( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + int neprint, netype, fstatus; + char *eprint = NULL, *etype = NULL; + + neprint = fields_find( bibin, "eprint", -1 ); + netype = fields_find( bibin, "eprinttype", -1 ); + + if ( neprint!=-1 ) eprint = bibin->data[neprint].data; + if ( netype!=-1 ) etype = bibin->data[netype].data; + + if ( eprint && etype ) { + if ( !strncasecmp( etype, "arxiv", 5 ) ) { + fstatus = fields_add( bibout, "ARXIV", eprint, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } else if ( !strncasecmp( etype, "jstor", 5 ) ) { + fstatus = fields_add( bibout, "JSTOR", eprint, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } else if ( !strncasecmp( etype, "pubmed", 6 ) ) { + fstatus = fields_add( bibout, "PMID", eprint, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } else if ( !strncasecmp( etype, "medline", 7 ) ) { + fstatus = fields_add( bibout, "MEDLINE", eprint, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } else { + fstatus = fields_add( bibout, "EPRINT", eprint, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + fstatus = fields_add( bibout, "EPRINTTYPE", etype, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + fields_setused( bibin, neprint ); + fields_setused( bibin, netype ); + } else if ( eprint ) { + fstatus = fields_add( bibout, "EPRINT", eprint, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + fields_setused( bibin, neprint ); + } else if ( etype ) { + fstatus = fields_add( bibout, "EPRINTTYPE", etype, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + fields_setused( bibin, netype ); + } + return BIBL_OK; +} + +static int +biblatexin_btgenre( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + if ( fields_add( bibout, "NGENRE", str_cstr( invalue ), level ) == FIELDS_OK ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + +/* biblatexin_howpublished() + * + * howpublished={}, + * + * Normally indicates the manner in which something was + * published in lieu of a formal publisher, so typically + * 'howpublished' and 'publisher' will never be in the + * same reference. + * + * Occasionally, people put Diploma thesis information + * into this field, so check for that first. + */ +static int +biblatexin_howpublished( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + int fstatus; + + if ( !strncasecmp( str_cstr( invalue ), "Diplom", 6 ) ) + fstatus = fields_replace_or_add( bibout, "NGENRE", "Diploma thesis", level ); + else if ( !strncasecmp( str_cstr( invalue ), "Habilitation", 13 ) ) + fstatus = fields_replace_or_add( bibout, "NGENRE", "Habilitation thesis", level ); + else + fstatus = fields_add( bibout, "PUBLISHER", str_cstr( invalue ), level ); + + if ( fstatus==FIELDS_OK ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + +/* + * biblatex has multiple editor fields "editor", "editora", "editorb", "editorc", + * each of which can be modified from a type of "EDITOR" via "editortype", + * "editoratype", "editorbtype", "editorctype". + * + * Defined types: + * "editor" + * "collaborator" + * "compiler" + * "redactor" + * + * "reviser" ? + * "founder" ? + * "continuator" ? + * + * bibtex-chicago + * + * "director" + * "producer" + * "conductor" + * "none" (for performer) + */ +static int +biblatexin_blteditor( fields *bibin, int m, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + char *editor_fields[] = { "editor", "editora", "editorb", "editorc" }; + char *editor_types[] = { "editortype", "editoratype", "editorbtype", "editorctype" }; + int i, n = 0, ntype, neditors = sizeof( editor_fields ) / sizeof( editor_fields[0] ); + char *type, *usetag = "EDITOR"; + for ( i=1; idata, editor_fields[i] ) ) n = i; + ntype = fields_find( bibin, editor_types[n], LEVEL_ANY ); + if ( ntype!=-1 ) { + type = fields_value( bibin, ntype, FIELDS_CHRP_NOUSE ); + if ( !strcasecmp( type, "collaborator" ) ) usetag = "COLLABORATOR"; + else if ( !strcasecmp( type, "compiler" ) ) usetag = "COMPILER"; + else if ( !strcasecmp( type, "redactor" ) ) usetag = "REDACTOR"; + else if ( !strcasecmp( type, "director" ) ) usetag = "DIRECTOR"; + else if ( !strcasecmp( type, "producer" ) ) usetag = "PRODUCER"; + else if ( !strcasecmp( type, "none" ) ) usetag = "PERFORMER"; + } + return biblatex_names( bibout, usetag, invalue, level, &(pm->asis), &(pm->corps) ); +} + +static int +biblatexin_person( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + return biblatex_names( bibout, outtag, invalue, level, &(pm->asis), &(pm->corps) ); +} + +static void +biblatexin_notag( param *p, char *tag ) +{ + if ( p->verbose && strcmp( tag, "INTERNAL_TYPE" ) ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, " Cannot find tag '%s'\n", tag ); + } +} + +static int +biblatexin_convertf( fields *bibin, fields *bibout, int reftype, param *p ) +{ + static int (*convertfns[NUM_REFTYPES])(fields *, int, str *, str *, int, param *, char *, fields *) = { + [ 0 ... NUM_REFTYPES-1 ] = generic_null, + [ SIMPLE ] = generic_simple, + [ PAGES ] = generic_pages, + [ NOTES ] = generic_notes, + [ PERSON ] = biblatexin_person, + [ BLT_EDITOR ] = biblatexin_blteditor, + [ HOWPUBLISHED ] = biblatexin_howpublished, + [ URL ] = generic_url, + [ BT_GENRE ] = biblatexin_btgenre, + [ BT_EPRINT ] = biblatexin_bteprint, + [ BLT_THESIS_TYPE ] = biblatexin_bltthesistype, + [ BLT_SCHOOL ] = biblatexin_bltschool, + [ BLT_SUBTYPE ] = biblatexin_bltsubtype, + [ BLT_SKIP ] = generic_skip, + [ TITLE ] = generic_null, /* delay processing until later */ + }; + + int process, level, i, nfields, status = BIBL_OK; + str *intag, *invalue; + char *outtag; + + nfields = fields_num( bibin ); + for ( i=0; idata, reftype, p->all, p->nall, &process, &level, &outtag ) ) { + biblatexin_notag( p, intag->data ); + continue; + } + + status = convertfns[ process ]( bibin, i, intag, invalue, level, p, outtag, bibout ); + if ( status!=BIBL_OK ) return status; + + if ( convertfns[ process ] != generic_null ) + fields_setused( bibin, i ); + + } + + status = process_title_all( bibin, bibout, reftype, p ); + + if ( status==BIBL_OK && p->verbose ) fields_report( bibout, stdout ); return status; } diff --git a/bibutils/biblatexin.h b/bibutils/biblatexin.h deleted file mode 100644 --- a/bibutils/biblatexin.h +++ /dev/null @@ -1,33 +0,0 @@ -/* - * biblatexin.h - * - * Copyright (c) Chris Putnam 2008-2014 - * - * Source code released under the GPL version 2 - * - */ -#ifndef BIBLATEXIN_H -#define BIBLATEXIN_H - -#include "newstr.h" -#include "list.h" -#include "fields.h" -#include "bibl.h" -#include "bibutils.h" -#include "reftypes.h" - -extern int biblatexin_convertf( fields *bibin, fields *info, int reftype, param *p, variants *all, int nall ); -extern int biblatexin_processf( fields *bibin, char *data, char *filename, long nref ); -extern int biblatexin_cleanf( bibl *bin, param *p ); -extern int biblatexin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ); -extern int biblatexin_typef( fields *bibin, char *filename, int nrefs, - param *p, variants *all, int nall ); - -extern void biblatexin_initparams( param *p, const char *progname ); - -extern variants biblatex_all[]; -extern int biblatex_nall; - - -#endif - diff --git a/bibutils/bibtexin.c b/bibutils/bibtexin.c --- a/bibutils/bibtexin.c +++ b/bibutils/bibtexin.c @@ -1,1375 +1,1325 @@ /* * bibtexin.c * - * Copyright (c) Chris Putnam 2003-2014 - * - * Program and source code released under the GPL version 2 - * - */ -#include -#include -#include -#include -#include "is_ws.h" -#include "strsearch.h" -#include "newstr.h" -#include "newstr_conv.h" -#include "fields.h" -#include "list.h" -#include "name.h" -#include "title.h" -#include "reftypes.h" -#include "bibtexin.h" - -static list find = { 0, 0, NULL, 0 }; -static list replace = { 0, 0, NULL, 0 }; - -extern const char progname[]; - -/***************************************************** - PUBLIC: void bibtexin_initparams() -*****************************************************/ -void -bibtexin_initparams( param *p, const char *progname ) -{ - p->readformat = BIBL_BIBTEXIN; - p->charsetin = BIBL_CHARSET_DEFAULT; - p->charsetin_src = BIBL_SRC_DEFAULT; - p->latexin = 1; - p->xmlin = 0; - p->utf8in = 0; - p->nosplittitle = 0; - p->verbose = 0; - p->addcount = 0; - p->output_raw = 0; - - p->readf = bibtexin_readf; - p->processf = bibtexin_processf; - p->cleanf = bibtexin_cleanf; - p->typef = bibtexin_typef; - p->convertf = bibtexin_convertf; - p->all = bibtex_all; - p->nall = bibtex_nall; - - list_init( &(p->asis) ); - list_init( &(p->corps) ); - - if ( !progname ) p->progname = NULL; - else p->progname = strdup( progname ); -} - -/***************************************************** - PUBLIC: int bibtexin_readf() -*****************************************************/ - -/* - * readf can "read too far", so we store this information in line, thus - * the next new text is in line, either from having read too far or - * from the next chunk obtained via newstr_fget() - * - * return 1 on success, 0 on error/end-of-file - * - */ -static int -readmore( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line ) -{ - if ( line->len ) return 1; - else return newstr_fget( fp, buf, bufsize, bufpos, line ); -} - -/* - * readf() - * - * returns zero if cannot get reference and hit end of-file - * returns 1 if last reference in file, 2 if reference within file - */ -int -bibtexin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ) -{ - int haveref = 0; - char *p; - *fcharset = CHARSET_UNKNOWN; - while ( haveref!=2 && readmore( fp, buf, bufsize, bufpos, line ) ) { - if ( line->len == 0 ) continue; /* blank line */ - p = &(line->data[0]); - /* Recognize UTF8 BOM */ - if ( line->len > 2 && - (unsigned char)(p[0])==0xEF && - (unsigned char)(p[1])==0xBB && - (unsigned char)(p[2])==0xBF ) { - *fcharset = CHARSET_UNICODE; - p += 3; - } - p = skip_ws( p ); - if ( *p == '%' ) { /* commented out line */ - newstr_empty( line ); - continue; - } - if ( *p == '@' ) haveref++; - if ( haveref && haveref<2 ) { - newstr_strcat( reference, p ); - newstr_addchar( reference, '\n' ); - newstr_empty( line ); - } else if ( !haveref ) newstr_empty( line ); - - } - return haveref; -} - -/***************************************************** - PUBLIC: int bibtexin_processf() -*****************************************************/ - -static char* -process_bibtextype( char *p, newstr *type ) -{ - newstr tmp; - newstr_init( &tmp ); - - if ( *p=='@' ) p++; - p = newstr_cpytodelim( &tmp, p, "{( \t\r\n", 0 ); - p = skip_ws( p ); - if ( *p=='{' || *p=='(' ) p++; - p = skip_ws( p ); - - if ( tmp.len ) newstr_strcpy( type, tmp.data ); - else newstr_empty( type ); - - newstr_free( &tmp ); - return p; -} - -static char* -process_bibtexid( char *p, newstr *id ) -{ - char *start_p = p; - newstr tmp; - - newstr_init( &tmp ); - p = newstr_cpytodelim( &tmp, p, ",", 1 ); - - if ( tmp.len ) { - if ( strchr( tmp.data, '=' ) ) { - /* Endnote writes bibtex files w/o fields, try to - * distinguish via presence of an equal sign.... if - * it's there, assume that it's a tag/data pair instead - * and roll back. - */ - p = start_p; - newstr_empty( id ); - } else { - newstr_strcpy( id, tmp.data ); - } - } else { - newstr_empty( id ); - } - - newstr_free( &tmp ); - return skip_ws( p ); -} - -static char * -bibtex_tag( char *p, newstr *tag ) -{ - p = newstr_cpytodelim( tag, skip_ws( p ), "= \t\r\n", 0 ); - if ( newstr_memerr( tag ) ) return NULL; - return skip_ws( p ); -} - -static char * -bibtex_data( char *p, fields *bibin, list *tokens ) -{ - unsigned int nbracket = 0, nquotes = 0; - char *startp = p; - newstr tok, *t; - - newstr_init( &tok ); - while ( p && *p ) { - if ( !nquotes && !nbracket ) { - if ( *p==',' || *p=='=' || *p=='}' || *p==')' ) - goto out; - } - if ( *p=='\"' && nbracket==0 && ( p==startp || *(p-1)!='\\' ) ) { - nquotes = !nquotes; - newstr_addchar( &tok, *p ); - if ( !nquotes ) { - if ( newstr_memerr( &tok ) ) { p=NULL; goto out; } - t = list_add( tokens, &tok ); - if ( !t ) { p=NULL; goto out0; } - newstr_empty( &tok ); - } - } else if ( *p=='#' && !nquotes && !nbracket ) { - if ( tok.len ) { - if ( newstr_memerr( &tok ) ) { p=NULL; goto out; } - t = list_add( tokens, &tok ); - if ( !t ) { p=NULL; goto out0; } - } - newstr_strcpy( &tok, "#" ); - t = list_add( tokens, &tok ); - if ( !t ) { p=NULL; goto out0; } - newstr_empty( &tok ); - } else if ( *p=='{' && !nquotes && ( p==startp || *(p-1)!='\\' ) ) { - nbracket++; - newstr_addchar( &tok, *p ); - } else if ( *p=='}' && !nquotes && ( p==startp || *(p-1)!='\\' ) ) { - nbracket--; - newstr_addchar( &tok, *p ); - if ( nbracket==0 ) { - if ( newstr_memerr( &tok ) ) { p=NULL; goto out; } - t = list_add( tokens, &tok ); - if ( !t ) { p=NULL; goto out; } - newstr_empty( &tok ); - } - } else if ( !is_ws( *p ) || nquotes || nbracket ) { - if ( !is_ws( *p ) ) newstr_addchar( &tok, *p ); - else { - if ( tok.len!=0 && *p!='\n' && *p!='\r' ) - newstr_addchar( &tok, *p ); - else if ( tok.len!=0 && (*p=='\n' || *p=='\r')) { - newstr_addchar( &tok, ' ' ); - while ( is_ws( *(p+1) ) ) p++; - } - } - } else if ( is_ws( *p ) ) { - if ( tok.len ) { - if ( newstr_memerr( &tok ) ) { p=NULL; goto out; } - t = list_add( tokens, &tok ); - if ( !t ) { p=NULL; goto out; } - newstr_empty( &tok ); - } - } - p++; - } -out: - if ( nbracket!=0 ) { - fprintf( stderr, "%s: Mismatch in number of brackets in reference.\n", progname ); - } - if ( nquotes!=0 ) { - fprintf( stderr, "%s: Mismatch in number of quotes in reference.\n", progname ); - } - if ( tok.len ) { - if ( newstr_memerr( &tok ) ) { p = NULL; goto out; } - t = list_add( tokens, &tok ); - if ( !t ) p = NULL; - } -out0: - newstr_free( &tok ); - return p; -} - -/* replace_strings() - * - * do string replacement -- only if unprotected by quotation marks or curly brackets - */ -static void -replace_strings( list *tokens, fields *bibin ) -{ - int i, n, ok; - newstr *s; - char *q; - i = 0; - while ( i < tokens->n ) { - s = list_get( tokens, i ); - if ( !strcmp( s->data, "#" ) ) { - } else if ( s->data[0]!='\"' && s->data[0]!='{' ) { - n = list_find( &find, s->data ); - if ( n!=-1 ) { - newstr_newstrcpy( s, list_get( &replace, n ) ); - } else { - q = s->data; - ok = 1; - while ( *q && ok ) { - if ( !isdigit( *q ) ) ok = 0; - q++; - } - if ( !ok ) { - fprintf( stderr, "%s: Warning: Non-numeric " - "BibTeX elements should be in quotations or " - "curly brackets in reference.\n", progname ); - } - } - } - i++; - } -} - -static int -string_concatenate( list *tokens, fields *bibin ) -{ - newstr *s, *t; - int i, status; - i = 0; - while ( i < tokens->n ) { - s = list_get( tokens, i ); - if ( !strcmp( s->data, "#" ) ) { - if ( i==0 || i==tokens->n-1 ) { - fprintf( stderr, "%s: Warning: Stray string concatenation " - "('#' character) in reference\n", progname ); - status = list_remove( tokens, i ); - if ( status!=LIST_OK ) return BIBL_ERR_MEMERR; - continue; - } - s = list_get( tokens, i-1 ); - if ( s->data[0]!='\"' && s->data[s->len-1]!='\"' ) - fprintf( stderr, "%s: Warning: String concentation should " - "be used in context of quotations marks.\n", progname ); - t = list_get( tokens, i+1 ); - if ( t->data[0]!='\"' && t->data[s->len-1]!='\"' ) - fprintf( stderr, "%s: Warning: String concentation should " - "be used in context of quotations marks.\n", progname ); - if ( ( s->data[s->len-1]=='\"' && t->data[0]=='\"') || (s->data[s->len-1]=='}' && t->data[0]=='{') ) { - newstr_trimend( s, 1 ); - newstr_trimbegin( t, 1 ); - newstr_newstrcat( s, t ); - } else { - newstr_newstrcat( s, t ); - } - status = list_remove( tokens, i ); - if ( status!=LIST_OK ) return BIBL_ERR_MEMERR; - status = list_remove( tokens, i ); - if ( status!=LIST_OK ) return BIBL_ERR_MEMERR; - } else i++; - } - return BIBL_OK; -} - -/* return NULL on memory error */ -static char * -process_bibtexline( char *p, newstr *tag, newstr *data, uchar stripquotes, fields *bibin ) -{ - int i, status; - list tokens; - newstr *s; - - newstr_empty( data ); - - p = bibtex_tag( p, tag ); - if ( p==NULL || tag->len==0 ) return p; - - list_init( &tokens ); - - if ( *p=='=' ) { - p = bibtex_data( p+1, bibin, &tokens ); - if ( p==NULL ) goto out; - } - - replace_strings( &tokens, bibin ); - - status = string_concatenate( &tokens, bibin ); - if ( status!=BIBL_OK ) { - p = NULL; - goto out; - } - - for ( i=0; idata[0]=='\"' && s->data[s->len-1]=='\"' ) || - ( s->data[0]=='{' && s->data[s->len-1]=='}' ) ) { - newstr_trimbegin( s, 1 ); - newstr_trimend( s, 1 ); - } - newstr_newstrcat( data, list_get( &tokens, i ) ); - } -out: - list_free( &tokens ); - return p; -} - -/* process_cite() - * - */ -static int -process_cite( fields *bibin, char *p, char *filename, long nref ) -{ - int fstatus, status = BIBL_OK; - newstr tag, data; - - newstrs_init( &tag, &data, NULL ); - - p = process_bibtextype( p, &data ); - if ( data.len ) { - fstatus = fields_add( bibin, "INTERNAL_TYPE", data.data, 0 ); - if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } - } - - p = process_bibtexid( p, &data ); - if ( data.len ) { - fstatus = fields_add( bibin, "REFNUM", data.data, 0 ); - if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } - } - - while ( *p ) { - p = process_bibtexline( p, &tag, &data, 1, bibin ); - if ( p==NULL ) { status = BIBL_ERR_MEMERR; goto out; } - /* no anonymous or empty fields allowed */ - if ( tag.len && data.len ) { - fstatus = fields_add( bibin, tag.data, data.data, 0 ); - if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } - } - newstrs_empty( &tag, &data, NULL ); - } -out: - newstrs_free( &tag, &data, NULL ); - return status; -} - -/* process_string() - * - * Handle lines like: - * - * '@STRING{TL = {Tetrahedron Lett.}}' - * - * p should point to just after '@STRING' - * - * In BibTeX, if a string is defined several times, the last one is kept. - * - */ -static int -process_string( char *p ) -{ - int n, status = BIBL_OK; - newstr s1, s2, *t; - newstrs_init( &s1, &s2, NULL ); - while ( *p && *p!='{' && *p!='(' ) p++; - if ( *p=='{' || *p=='(' ) p++; - p = process_bibtexline( skip_ws( p ), &s1, &s2, 0, NULL ); - if ( p==NULL ) { status = BIBL_ERR_MEMERR; goto out; } - if ( s2.data ) { - newstr_findreplace( &s2, "\\ ", " " ); - } - if ( s1.data ) { - n = list_find( &find, s1.data ); - if ( n==-1 ) { - t = list_add( &find, &s1 ); - if ( t==NULL ) { status = BIBL_ERR_MEMERR; goto out; } - if ( s2.data ) t = list_add( &replace, &s2 ); - else t = list_addc( &replace, "" ); - if ( t==NULL ) { status = BIBL_ERR_MEMERR; goto out; } - } else { - if ( s2.data ) t = list_set( &replace, n, &s2 ); - else t = list_setc( &replace, n, "" ); - if ( t==NULL ) { status = BIBL_ERR_MEMERR; goto out; } - } - } -out: - newstrs_free( &s1, &s2, NULL ); - return status; -} - -/* bibtexin_processf() - * - * Handle '@STRING', '@reftype', and ignore '@COMMENT' - */ -int -bibtexin_processf( fields *bibin, char *data, char *filename, long nref ) -{ - if ( !strncasecmp( data, "@STRING", 7 ) ) { - process_string( data+7 ); - return 0; - } else if ( !strncasecmp( data, "@COMMENT", 8 ) ) { - /* Not sure if these are real Bibtex, but not references */ - return 0; - } else { - process_cite( bibin, data, filename, nref ); - return 1; - } -} - -/***************************************************** - PUBLIC: void bibtexin_cleanf() -*****************************************************/ - -static int -bibtex_protected( newstr *data ) -{ - if ( data->data[0]=='{' && data->data[data->len-1]=='}' ) return 1; - if ( data->data[0]=='\"' && data->data[data->len-1]=='\"' ) return 1; - return 0; -} - -static int -bibtex_split( list *tokens, newstr *s ) -{ - int i, n = s->len, nbrackets = 0, status = BIBL_OK; - newstr tok, *t; - - newstr_init( &tok ); - - for ( i=0; idata[i]=='{' && ( i==0 || s->data[i-1]!='\\' ) ) { - nbrackets++; - newstr_addchar( &tok, '{' ); - } else if ( s->data[i]=='}' && ( i==0 || s->data[i-1]!='\\' ) ) { - nbrackets--; - newstr_addchar( &tok, '}' ); - } else if ( !is_ws( s->data[i] ) || nbrackets ) { - newstr_addchar( &tok, s->data[i] ); - } else if ( is_ws( s->data[i] ) ) { - if ( tok.len ) { - t = list_add( tokens, &tok ); - if ( !t ) { - status = BIBL_ERR_MEMERR; - goto out; - } - } - newstr_empty( &tok ); - } - } - if ( tok.len ) { - t = list_add( tokens, &tok ); - if ( !t ) { - status = BIBL_ERR_MEMERR; - goto out; - } - } - - for ( i=0; in; ++i ) { - newstr_trimstartingws( list_get( tokens, i ) ); - newstr_trimendingws( list_get( tokens, i ) ); - } -out: - newstr_free( &tok ); - return status; -} - -static int -bibtex_addtitleurl( fields *info, newstr *in ) -{ - int fstatus, status = BIBL_OK; - newstr s; - char *p; - - newstr_init( &s ); - - /* ...skip past "\href{" and copy to "}" */ - p = newstr_cpytodelim( &s, in->data + 6, "}", 1 ); - if ( newstr_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } - - /* ...add to URL */ - fstatus = fields_add( info, "URL", s.data, 0 ); - if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } - - /* ...return deleted fragment to newstr in */ - p = newstr_cpytodelim( &s, p, "", 0 ); - if ( newstr_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } - newstr_swapstrings( &s, in ); - -out: - newstr_free( &s ); - return status; -} - -static int -is_url_tag( newstr *tag ) -{ - if ( tag->len ) { - if ( !strcasecmp( tag->data, "url" ) ) return 1; - } - return 0; -} - -static int -is_name_tag( newstr *tag ) -{ - if ( tag->len ) { - if ( !strcasecmp( tag->data, "author" ) ) return 1; - if ( !strcasecmp( tag->data, "editor" ) ) return 1; - } - return 0; -} - -static void -bibtex_process_tilde( newstr *s ) -{ - char *p, *q; - int n = 0; - - p = q = s->data; - if ( !p ) return; - while ( *p ) { - if ( *p=='~' ) { - *q = ' '; - } else if ( *p=='\\' && *(p+1)=='~' ) { - n++; - p++; - *q = '~'; - } else { - *q = *p; - } - p++; - q++; - } - *q = '\0'; - s->len -= n; -} - -static void -bibtex_process_bracket( newstr *s ) -{ - char *p, *q; - int n = 0; - - p = q = s->data; - if ( !p ) return; - while ( *p ) { - if ( *p=='\\' && ( *(p+1)=='{' || *(p+1)=='}' ) ) { - n++; - p++; - *q = *p; - q++; - } else if ( *p=='{' || *p=='}' ) { - n++; - } else { - *q = *p; - q++; - } - p++; - } - *q = '\0'; - s->len -= n; -} - -static void -bibtex_cleantoken( newstr *s ) -{ - /* 'textcomp' annotations */ - newstr_findreplace( s, "\\textit", "" ); - newstr_findreplace( s, "\\textbf", "" ); - newstr_findreplace( s, "\\textsl", "" ); - newstr_findreplace( s, "\\textsc", "" ); - newstr_findreplace( s, "\\textsf", "" ); - newstr_findreplace( s, "\\texttt", "" ); - newstr_findreplace( s, "\\textsubscript", "" ); - newstr_findreplace( s, "\\textsuperscript", "" ); - newstr_findreplace( s, "\\emph", "" ); - newstr_findreplace( s, "\\url", "" ); - newstr_findreplace( s, "\\mbox", "" ); - - /* Other text annotations */ - newstr_findreplace( s, "\\it ", "" ); - newstr_findreplace( s, "\\em ", "" ); - - newstr_findreplace( s, "\\%", "%" ); - newstr_findreplace( s, "\\$", "$" ); - while ( newstr_findreplace( s, " ", " " ) ) {} - - /* 'textcomp' annotations that we don't want to substitute on output*/ - newstr_findreplace( s, "\\textdollar", "$" ); - newstr_findreplace( s, "\\textunderscore", "_" ); - - bibtex_process_bracket( s ); - bibtex_process_tilde( s ); - -} - -static int -bibtex_cleandata( newstr *tag, newstr *s, fields *info, param *p ) -{ - int i, status; - list tokens; - newstr *tok; - if ( !s->len ) return BIBL_OK; - /* protect url from undergoing any parsing */ - if ( is_url_tag( tag ) ) return BIBL_OK; - list_init( &tokens ); - status = bibtex_split( &tokens, s ); - if ( status!=BIBL_OK ) goto out; - for ( i=0; idata,"\\href{", 6)) { - bibtex_addtitleurl( info, tok ); - } - } - if ( p->latexin && !is_name_tag( tag ) && !is_url_tag( tag ) ) - bibtex_cleantoken( tok ); - } - newstr_empty( s ); - for ( i=0; i0 ) newstr_addchar( s, ' ' ); - newstr_newstrcat( s, tok ); - } -out: - list_free( &tokens ); - return status; -} - -static int -bibtexin_cleanref( fields *bibin, param *p ) -{ - int i, n, status; - newstr *t, *d; - n = fields_num( bibin ); - for ( i=0; inrefs; ++i ) { - n = fields_find( bin->ref[i], "refnum", -1 ); - if ( n==-1 ) continue; - if ( !strcmp( bin->ref[i]->data[n].data, citekey ) ) return i; - } - return -1; -} - -static void -bibtexin_nocrossref( bibl *bin, long i, int n, param *p ) -{ - int n1 = fields_find( bin->ref[i], "REFNUM", -1 ); - if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, "Cannot find cross-reference '%s'", - bin->ref[i]->data[n].data ); - if ( n1!=-1 ) fprintf( stderr, " for reference '%s'\n", - bin->ref[i]->data[n1].data ); - fprintf( stderr, "\n" ); -} - -static int -bibtexin_crossref_oneref( fields *bibref, fields *bibcross ) -{ - int j, n, nl, ntype, fstatus, status = BIBL_OK; - char *type, *nt, *nv; - - ntype = fields_find( bibref, "INTERNAL_TYPE", -1 ); - type = ( char * ) fields_value( bibref, ntype, FIELDS_CHRP_NOUSE ); - - n = fields_num( bibcross ); - for ( j=0; jnrefs; ++i ) { - bibref = bin->ref[i]; - n = fields_find( bibref, "CROSSREF", -1 ); - if ( n==-1 ) continue; - fields_setused( bibref, n ); - ncross = bibtexin_findref( bin, (char*) fields_value( bibref, n, FIELDS_CHRP ) ); - if ( ncross==-1 ) { - bibtexin_nocrossref( bin, i, n, p ); - continue; - } - bibcross = bin->ref[ncross]; - status = bibtexin_crossref_oneref( bibref, bibcross ); - if ( status!=BIBL_OK ) goto out; - } -out: - return status; -} - -int -bibtexin_cleanf( bibl *bin, param *p ) -{ - int status = BIBL_OK; - long i; - - for ( i=0; inrefs; ++i ) - status = bibtexin_cleanref( bin->ref[i], p ); - bibtexin_crossref( bin, p ); - return status; -} - -/***************************************************** - PUBLIC: int bibtexin_typef() -*****************************************************/ - -int -bibtexin_typef( fields *bibin, char *filename, int nrefs, param *p, - variants *all, int nall ) -{ - char *refnum = ""; - int reftype, n, nrefnum; - n = fields_find( bibin, "INTERNAL_TYPE", 0 ); - nrefnum = fields_find( bibin, "REFNUM", 0 ); - if ( nrefnum!=-1 ) refnum = (bibin->data[nrefnum]).data; - if ( n!=-1 ) - /* figure out type */ - reftype = get_reftype( (bibin->data[n]).data, nrefs, - p->progname, all, nall, refnum ); - else - /* no type info, go for default */ - reftype = get_reftype( "", nrefs, p->progname, all, nall, refnum ); - return reftype; -} - -/***************************************************** - PUBLIC: int bibtexin_convertf(), returns BIBL_OK or BIBL_ERR_MEMERR -*****************************************************/ - -static int -bibtex_matches_list( fields *info, char *tag, char *suffix, newstr *data, int level, - list *names, int *match ) -{ - int i, fstatus, status = BIBL_OK; - newstr newtag; - - *match = 0; - if ( names->n==0 ) return status; - - newstr_init( &newtag ); - - for ( i=0; in; ++i ) { - if ( strcmp( data->data, list_getc( names, i ) ) ) continue; - newstr_initstr( &newtag, tag ); - newstr_strcat( &newtag, suffix ); - fstatus = fields_add( info, newtag.data, data->data, level ); - if ( fstatus!=FIELDS_OK ) { - status = BIBL_ERR_MEMERR; - goto out; - } - *match = 1; - goto out; - } - -out: - newstr_free( &newtag ); - return status; -} - -/* - * bibtex_names( info, newtag, field, level); - * - * split names in author list separated by and's (use '|' character) - * and add names - * - * returns BIBL_OK on success, BIBL_ERR_MEMERR on memory error - */ -static int -bibtex_names( fields *info, char *tag, newstr *data, int level, list *asis, - list *corps ) -{ - int begin, end, ok, n, etal, i, status, match; - list tokens; - - /* If we match the asis or corps list add and bail. */ - status = bibtex_matches_list( info, tag, ":ASIS", data, level, asis, &match ); - if ( match==1 || status!=BIBL_OK ) return status; - status = bibtex_matches_list( info, tag, ":CORP", data, level, corps, &match ); - if ( match==1 || status!=BIBL_OK ) return status; - - list_init( &tokens ); - - bibtex_split( &tokens, data ); - for ( i=0; ilen==0 ) return 1; - - newstr_init( &page ); - p = skip_ws( s->data ); - while ( *p && !is_ws(*p) && *p!='-' && *p!='\r' && *p!='\n' && *p!=-30 ) - newstr_addchar( &page, *p++ ); - if ( page.len>0 ) { - fstatus = fields_add( info, "PAGESTART", page.data, level ); - if ( fstatus!=FIELDS_OK ) { - status = BIBL_ERR_MEMERR; - goto out; - } - } - - while ( *p && (is_ws(*p) || *p=='-' ) ) p++; - if ( *p && is_utf8_emdash( p ) ) p+=3; - if ( *p && is_utf8_endash( p ) ) p+=3; - - newstr_empty( &page ); - while ( *p && !is_ws(*p) && *p!='-' && *p!='\r' && *p!='\n' ) - newstr_addchar( &page, *p++ ); - if ( page.len>0 ) { - fstatus = fields_add( info, "PAGEEND", page.data, level ); - if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; - } - -out: - newstr_free( &page ); - return status; -} - -static int -process_urlcore( fields *info, newstr *d, int level, char *default_tag ) -{ - char *p = d->data; - int fstatus; - if ( !strncasecmp( p, "\\urllink", 8 ) ) - fstatus = fields_add( info, "URL", p+8, level ); - else if ( !strncasecmp( p, "\\url", 4 ) ) - fstatus = fields_add( info, "URL", p+4, level ); - else if ( !strncasecmp( p, "arXiv:", 6 ) ) - fstatus = fields_add( info, "ARXIV", p+6, level ); - else if ( !strncasecmp( p, "http://arxiv.org/abs/", 21 ) ) - fstatus = fields_add( info, "ARXIV", p+21, level ); - else if ( !strncasecmp( p, "http:", 5 ) ) - fstatus = fields_add( info, "URL", p, level ); - else - fstatus = fields_add( info, default_tag, p, level ); - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} - -static int -process_url( fields *info, newstr *d, int level ) -{ - return process_urlcore( info, d, level, "URL" ); -} - -/* Split keywords="" with semicolons. - * Commas are also frequently used, but will break - * entries like: - * keywords="Microscopy, Confocal" - * Returns BIBL_OK or BIBL_ERR_MEMERR - */ -static int -process_keywords( fields *info, newstr *d, int level ) -{ - int fstatus, status = BIBL_OK; - newstr keyword; - char *p; - - if ( !d || d->len==0 ) return BIBL_OK; - - p = d->data; - newstr_init( &keyword ); - - while ( *p ) { - p = newstr_cpytodelim( &keyword, skip_ws( p ), ";", 1 ); - newstr_trimendingws( &keyword ); - if ( newstr_memerr( &keyword ) ) { - status = BIBL_ERR_MEMERR; - goto out; - } - if ( keyword.len ) { - fstatus = fields_add( info, "KEYWORD", keyword.data, level ); - if ( fstatus!=FIELDS_OK ) { - status = BIBL_ERR_MEMERR; - goto out; - } - } - } -out: - newstr_free( &keyword ); - return status; -} - -/* proces_howpublished() - * - * howpublished={}, - * - * Normally indicates the manner in which something was - * published in lieu of a formal publisher, so typically - * 'howpublished' and 'publisher' will never be in the - * same reference. - * - * Occassionally, people put Diploma thesis information - * into the field, so check that first. - * - * Returns BIBL_OK or BIBL_ERR_MEMERR - */ -static int -process_howpublished( fields *info, newstr *d, int level ) -{ - int fstatus, status = BIBL_OK; - char *p = d->data; - if ( !strncasecmp( p, "Diplom", 6 ) ) { - fstatus = fields_replace_or_add( info, "GENRE", "Diploma thesis", level ); - if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; - } else if ( !strncasecmp( p, "Habilitation", 13 ) ) { - fstatus = fields_replace_or_add( info, "GENRE", "Habilitation thesis", level ); - if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; - } else if ( !strncasecmp( d->data, "http:", 5 ) ) { - status = process_url( info, d, level ); - } else if ( !strncasecmp( d->data, "arXiv:", 6 ) ) { - status = process_url( info, d, level ); - } else { - fstatus = fields_add( info, "PUBLISHER", p, level ); - if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; - } - return status; -} - -/* - * sentelink = {file://localhost/full/path/to/file.pdf,Sente,PDF} - */ -static int -process_sente( fields *info, newstr *d, int level ) -{ - int fstatus, status = BIBL_OK; - newstr link; - - newstr_init( &link ); - newstr_cpytodelim( &link, skip_ws( d->data ), ",", 0 ); - newstr_trimendingws( &link ); - if ( newstr_memerr( &link ) ) status = BIBL_ERR_MEMERR; - - if ( status==BIBL_OK && link.len ) { - fstatus = fields_add( info, "FILEATTACH", link.data, level ); - if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; - } - - newstr_free( &link ); - return status; -} - -/* - * BibTeX uses 'organization' in lieu of publisher if that field is missing. - * Otherwise output as - * - * The organization - * - * organizer of meeting - * - * - */ -static int -process_organization( fields *bibin, fields *info, newstr *d, int level ) -{ - int n, fstatus; - n = fields_find( bibin, "publisher", LEVEL_ANY ); - if ( n==-1 ) - fstatus = fields_add( info, "PUBLISHER", d->data, level ); - else - fstatus = fields_add( info, "ORGANIZER:CORP", d->data, level ); - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} - -static int -count_colons( char *p ) -{ - int n = 0; - while ( *p ) { - if ( *p==':' ) n++; - p++; - } - return n; -} - -static int -first_colon( char *p ) -{ - int n = 0; - while ( p[n] && p[n]!=':' ) n++; - return n; -} - -static int -last_colon( char *p ) -{ - int n = strlen( p ) - 1; - while ( n>0 && p[n]!=':' ) n--; - return n; -} - -/* - * file={Description:/full/path/to/file.pdf:PDF} - */ -static int -process_file( fields *info, newstr *d, int level ) -{ - int fstatus, status = BIBL_OK; - char *p = d->data; - int i, n, n1, n2; - newstr link; - - n = count_colons( p ); - if ( n > 1 ) { - /* A DOS file can contain a colon ":C:/....pdf:PDF" */ - /* Extract after 1st and up to last colons */ - n1 = first_colon( p ) + 1; - n2 = last_colon( p ); - newstr_init( &link ); - for ( i=n1; idata, "http:", 5 ) || - !strncasecmp( d->data, "arXiv:", 6 ) ) { - status = process_url( info, d, level ); - } else { - fstatus = fields_add( info, "NOTES", d->data, level ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } - return status; -} - -static void -bibtexin_notag( param *p, char *tag ) -{ - if ( p->verbose && strcmp( tag, "INTERNAL_TYPE" ) ) { - if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, "Cannot find tag '%s'\n", tag ); - } -} - -/* bibtexin_titleinbook_isbooktitle() - * - * Normally, the title field of inbook refers to the book. The - * section in a @inbook reference is untitled. If it's titled, - * the @incollection should be used. For example, in: - * - * @inbook{ - * title="xxx" - * } - * - * the booktitle is "xxx". - * - * However, @inbook is frequently abused (and treated like - * @incollection) so that title and booktitle are present - * and title is now 'supposed' to refer to the section. For example: - * - * @inbook{ - * title="yyy", - * booktitle="xxx" - * } - * - * Therefore report whether or not booktitle is present as well - * as title in @inbook references. If not, then make 'title' - * correspond to the title of the book, not the section. - * - */ -static int -bibtexin_titleinbook_isbooktitle( char *intag, fields *bibin ) -{ - int n; - - /* ...look only at 'title="xxx"' elements */ - if ( strcasecmp( intag, "TITLE" ) ) return 0; - - /* ...look only at '@inbook' references */ - n = fields_find( bibin, "INTERNAL_TYPE", -1 ); - if ( n==-1 ) return 0; - if ( strcasecmp( fields_value( bibin, n, FIELDS_CHRP ), "INBOOK" ) ) return 0; - - /* ...look to see if 'booktitle="yyy"' exists */ - n = fields_find( bibin, "BOOKTITLE", -1 ); - if ( n==-1 ) return 0; - else return 1; -} -static int -bibtexin_title_process( fields *info, char *outtag, fields *bibin, newstr *t, newstr *d, int level, int nosplittitle ) -{ - char *intag = t->data; - char *indata = d->data; - int ok; - if ( bibtexin_titleinbook_isbooktitle( intag, bibin ) ) level=LEVEL_MAIN; - ok = title_process( info, outtag, indata, level, nosplittitle ); - if ( ok ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} - -static int -bibtex_simple( fields *info, char *outtag, newstr *d, int level ) -{ - int fstatus; - fstatus = fields_add( info, outtag, d->data, level ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - return BIBL_OK; -} - -int -bibtexin_convertf( fields *bibin, fields *info, int reftype, param *p, - variants *all, int nall ) -{ - int process, level, i, n, nfields, status; - newstr *t, *d; - char *outtag; - - nfields = fields_num( bibin ); - for ( i=0; ilen == 0 ) continue; /* Don't consider with null tags */ - n = process_findoldtag( t->data, reftype, all, nall ); - if ( n==-1 ) { - bibtexin_notag( p, t->data ); - continue; - } - - d = fields_value( bibin, i, FIELDS_STRP ); - - process = ((all[reftype]).tags[n]).processingtype; - level = ((all[reftype]).tags[n]).level; - outtag = ((all[reftype]).tags[n]).newstr; - - switch( process ) { - - case SIMPLE: - status = bibtex_simple( info, outtag, d, level ); - break; - - case TITLE: - status = bibtexin_title_process( info, "TITLE", bibin, t, d, level, p->nosplittitle ); - break; - - case PERSON: - status = bibtex_names( info, outtag, d, level, &(p->asis), &(p->corps) ); - break; - - case PAGES: - status = process_pages( info, d, level ); - break; - - case KEYWORD: - status = process_keywords( info, d, level ); - break; - - case HOWPUBLISHED: - status = process_howpublished( info, d, level ); - break; - - case LINKEDFILE: - status = process_file( info, d, level ); - break; - - case BT_NOTE: - status = process_note( info, d, level ); - break; - - case BT_SENTE: - status = process_sente( info, d, level ); - break; - - case BT_URL: - status = process_url( info, d, level ); - break; - - case BT_ORG: - status = process_organization( bibin, info, d, level ); - break; - - default: - status = BIBL_OK; - break; - } - - if ( status!=BIBL_OK ) return status; - } - return status; -} - + * Copyright (c) Chris Putnam 2003-2017 + * + * Program and source code released under the GPL version 2 + * + */ +#include +#include +#include +#include +#include "is_ws.h" +#include "str.h" +#include "utf8.h" +#include "str_conv.h" +#include "fields.h" +#include "slist.h" +#include "name.h" +#include "title.h" +#include "url.h" +#include "reftypes.h" +#include "bibformats.h" +#include "generic.h" + +static slist find = { 0, 0, 0, NULL }; +static slist replace = { 0, 0, 0, NULL }; + +extern variants bibtex_all[]; +extern int bibtex_nall; + +/***************************************************** + PUBLIC: void bibtexin_initparams() +*****************************************************/ + +static int bibtexin_convertf( fields *bibin, fields *info, int reftype, param *p ); +static int bibtexin_processf( fields *bibin, char *data, char *filename, long nref, param *p ); +static int bibtexin_cleanf( bibl *bin, param *p ); +static int bibtexin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int bibtexin_typef( fields *bibin, char *filename, int nrefs, param *p ); + +void +bibtexin_initparams( param *p, const char *progname ) +{ + p->readformat = BIBL_BIBTEXIN; + p->charsetin = BIBL_CHARSET_DEFAULT; + p->charsetin_src = BIBL_SRC_DEFAULT; + p->latexin = 1; + p->xmlin = 0; + p->utf8in = 0; + p->nosplittitle = 0; + p->verbose = 0; + p->addcount = 0; + p->output_raw = 0; + + p->readf = bibtexin_readf; + p->processf = bibtexin_processf; + p->cleanf = bibtexin_cleanf; + p->typef = bibtexin_typef; + p->convertf = bibtexin_convertf; + p->all = bibtex_all; + p->nall = bibtex_nall; + + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); + + if ( !progname ) p->progname = NULL; + else p->progname = strdup( progname ); +} + +/***************************************************** + PUBLIC: int bibtexin_readf() +*****************************************************/ + +/* + * readf can "read too far", so we store this information in line, thus + * the next new text is in line, either from having read too far or + * from the next chunk obtained via str_fget() + * + * return 1 on success, 0 on error/end-of-file + * + */ +static int +readmore( FILE *fp, char *buf, int bufsize, int *bufpos, str *line ) +{ + if ( line->len ) return 1; + else return str_fget( fp, buf, bufsize, bufpos, line ); +} + +/* + * readf() + * + * returns zero if cannot get reference and hit end of-file + * returns 1 if last reference in file, 2 if reference within file + */ +static int +bibtexin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) +{ + int haveref = 0; + char *p; + *fcharset = CHARSET_UNKNOWN; + while ( haveref!=2 && readmore( fp, buf, bufsize, bufpos, line ) ) { + if ( line->len == 0 ) continue; /* blank line */ + p = &(line->data[0]); + /* Recognize UTF8 BOM */ + if ( line->len > 2 && + (unsigned char)(p[0])==0xEF && + (unsigned char)(p[1])==0xBB && + (unsigned char)(p[2])==0xBF ) { + *fcharset = CHARSET_UNICODE; + p += 3; + } + p = skip_ws( p ); + if ( *p == '%' ) { /* commented out line */ + str_empty( line ); + continue; + } + if ( *p == '@' ) haveref++; + if ( haveref && haveref<2 ) { + str_strcatc( reference, p ); + str_addchar( reference, '\n' ); + str_empty( line ); + } else if ( !haveref ) str_empty( line ); + + } + return haveref; +} + +/***************************************************** + PUBLIC: int bibtexin_processf() +*****************************************************/ + +static char* +process_bibtextype( char *p, str *type ) +{ + str tmp; + str_init( &tmp ); + + if ( *p=='@' ) p++; + p = str_cpytodelim( &tmp, p, "{( \t\r\n", 0 ); + p = skip_ws( p ); + if ( *p=='{' || *p=='(' ) p++; + p = skip_ws( p ); + + if ( str_has_value( &tmp ) ) str_strcpy( type, &tmp ); + else str_empty( type ); + + str_free( &tmp ); + return p; +} + +static char* +process_bibtexid( char *p, str *id ) +{ + char *start_p = p; + str tmp; + + str_init( &tmp ); + p = str_cpytodelim( &tmp, p, ",", 1 ); + + if ( str_has_value( &tmp ) ) { + if ( strchr( tmp.data, '=' ) ) { + /* Endnote writes bibtex files w/o fields, try to + * distinguish via presence of an equal sign.... if + * it's there, assume that it's a tag/data pair instead + * and roll back. + */ + p = start_p; + str_empty( id ); + } else { + str_strcpy( id, &tmp ); + } + } else { + str_empty( id ); + } + + str_free( &tmp ); + return skip_ws( p ); +} + +static char * +bibtex_tag( char *p, str *tag ) +{ + p = str_cpytodelim( tag, skip_ws( p ), "= \t\r\n", 0 ); + if ( str_memerr( tag ) ) return NULL; + return skip_ws( p ); +} + +static char * +bibtex_data( char *p, fields *bibin, slist *tokens, long nref, param *pm ) +{ + unsigned int nbracket = 0, nquotes = 0; + char *startp = p; + str tok, *t; + + str_init( &tok ); + while ( p && *p ) { + if ( !nquotes && !nbracket ) { + if ( *p==',' || *p=='=' || *p=='}' || *p==')' ) + goto out; + } + if ( *p=='\"' && nbracket==0 && ( p==startp || *(p-1)!='\\' ) ) { + nquotes = !nquotes; + str_addchar( &tok, *p ); + if ( !nquotes ) { + if ( str_memerr( &tok ) ) { p=NULL; goto out; } + t = slist_add( tokens, &tok ); + if ( !t ) { p=NULL; goto out0; } + str_empty( &tok ); + } + } else if ( *p=='#' && !nquotes && !nbracket ) { + if ( str_has_value( &tok ) ) { + if ( str_memerr( &tok ) ) { p=NULL; goto out; } + t = slist_add( tokens, &tok ); + if ( !t ) { p=NULL; goto out0; } + } + str_strcpyc( &tok, "#" ); + t = slist_add( tokens, &tok ); + if ( !t ) { p=NULL; goto out0; } + str_empty( &tok ); + } else if ( *p=='{' && !nquotes && ( p==startp || *(p-1)!='\\' ) ) { + nbracket++; + str_addchar( &tok, *p ); + } else if ( *p=='}' && !nquotes && ( p==startp || *(p-1)!='\\' ) ) { + nbracket--; + str_addchar( &tok, *p ); + if ( nbracket==0 ) { + if ( str_memerr( &tok ) ) { p=NULL; goto out; } + t = slist_add( tokens, &tok ); + if ( !t ) { p=NULL; goto out; } + str_empty( &tok ); + } + } else if ( !is_ws( *p ) || nquotes || nbracket ) { + if ( !is_ws( *p ) ) str_addchar( &tok, *p ); + else { + if ( tok.len!=0 && *p!='\n' && *p!='\r' ) + str_addchar( &tok, *p ); + else if ( tok.len!=0 && (*p=='\n' || *p=='\r')) { + str_addchar( &tok, ' ' ); + while ( is_ws( *(p+1) ) ) p++; + } + } + } else if ( is_ws( *p ) ) { + if ( tok.len ) { + if ( str_memerr( &tok ) ) { p=NULL; goto out; } + t = slist_add( tokens, &tok ); + if ( !t ) { p=NULL; goto out; } + str_empty( &tok ); + } + } + p++; + } +out: + if ( nbracket!=0 ) { + fprintf( stderr, "%s: Mismatch in number of brackets in reference %ld.\n", pm->progname, nref ); + } + if ( nquotes!=0 ) { + fprintf( stderr, "%s: Mismatch in number of quotes in reference %ld.\n", pm->progname, nref ); + } + if ( str_has_value( &tok ) ) { + if ( str_memerr( &tok ) ) { p = NULL; goto out; } + t = slist_add( tokens, &tok ); + if ( !t ) p = NULL; + } +out0: + str_free( &tok ); + return p; +} + +/* replace_strings() + * + * do string replacement -- only if unprotected by quotation marks or curly brackets + */ +static void +replace_strings( slist *tokens, fields *bibin, param *pm ) +{ + int i, n, ok; + char *q; + str *s; + i = 0; + while ( i < tokens->n ) { + s = slist_str( tokens, i ); + if ( !strcmp( s->data, "#" ) ) { + } else if ( s->data[0]!='\"' && s->data[0]!='{' ) { + n = slist_find( &find, s ); + if ( n!=-1 ) { + str_strcpy( s, slist_str( &replace, n ) ); + } else { + q = s->data; + ok = 1; + while ( *q && ok ) { + if ( !isdigit( *q ) ) ok = 0; + q++; + } + if ( !ok ) { + fprintf( stderr, "%s: Warning: Non-numeric " + "BibTeX elements should be in quotations or " + "curly brackets in reference.\n", pm->progname ); + } + } + } + i++; + } +} + +static int +string_concatenate( slist *tokens, fields *bibin, long nref, param *pm ) +{ + int i, status; + str *s, *t; + i = 0; + while ( i < tokens->n ) { + s = slist_str( tokens, i ); + if ( !strcmp( s->data, "#" ) ) { + if ( i==0 || i==tokens->n-1 ) { + fprintf( stderr, "%s: Warning: Stray string concatenation " + "('#' character) in reference %ld\n", pm->progname, nref ); + status = slist_remove( tokens, i ); + if ( status!=SLIST_OK ) return BIBL_ERR_MEMERR; + continue; + } + s = slist_str( tokens, i-1 ); + if ( s->data[0]!='\"' && s->data[s->len-1]!='\"' ) + fprintf( stderr, "%s: Warning: String concentation should " + "be used in context of quotations marks in reference %ld\n", pm->progname, nref ); + t = slist_str( tokens, i+1 ); + if ( t->data[0]!='\"' && t->data[s->len-1]!='\"' ) + fprintf( stderr, "%s: Warning: String concentation should " + "be used in context of quotations marks in reference %ld\n", pm->progname, nref ); + if ( ( s->data[s->len-1]=='\"' && t->data[0]=='\"') || (s->data[s->len-1]=='}' && t->data[0]=='{') ) { + str_trimend( s, 1 ); + str_trimbegin( t, 1 ); + str_strcat( s, t ); + } else { + str_strcat( s, t ); + } + status = slist_remove( tokens, i ); + if ( status!=SLIST_OK ) return BIBL_ERR_MEMERR; + status = slist_remove( tokens, i ); + if ( status!=SLIST_OK ) return BIBL_ERR_MEMERR; + } else i++; + } + return BIBL_OK; +} + +/* return NULL on memory error */ +static char * +process_bibtexline( char *p, str *tag, str *data, uchar stripquotes, fields *bibin, long nref, param *pm ) +{ + int i, status; + slist tokens; + str *s; + + str_empty( data ); + + p = bibtex_tag( p, tag ); + if ( p==NULL || str_is_empty( tag ) ) return p; + + slist_init( &tokens ); + + if ( *p=='=' ) { + p = bibtex_data( p+1, bibin, &tokens, nref, pm ); + if ( p==NULL ) goto out; + } + + replace_strings( &tokens, bibin, pm ); + + status = string_concatenate( &tokens, bibin, nref, pm ); + if ( status!=BIBL_OK ) { + p = NULL; + goto out; + } + + for ( i=0; idata[0]=='\"' && s->data[s->len-1]=='\"' ) || + ( s->data[0]=='{' && s->data[s->len-1]=='}' ) ) { + str_trimbegin( s, 1 ); + str_trimend( s, 1 ); + } + str_strcat( data, slist_str( &tokens, i ) ); + } +out: + slist_free( &tokens ); + return p; +} + +/* process_cite() + * + */ +static int +process_cite( fields *bibin, char *p, char *filename, long nref, param *pm ) +{ + int fstatus, status = BIBL_OK; + str tag, data; + + strs_init( &tag, &data, NULL ); + + p = process_bibtextype( p, &data ); + if ( str_has_value( &data ) ) { + fstatus = fields_add( bibin, "INTERNAL_TYPE", str_cstr( &data ), 0 ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + } + + p = process_bibtexid( p, &data ); + if ( str_has_value( &data ) ) { + fstatus = fields_add( bibin, "REFNUM", str_cstr( &data ), 0 ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + } + + while ( *p ) { + p = process_bibtexline( p, &tag, &data, 1, bibin, nref, pm ); + if ( p==NULL ) { status = BIBL_ERR_MEMERR; goto out; } + /* no anonymous or empty fields allowed */ + if ( str_has_value( &tag ) && str_has_value( &data ) ) { + fstatus = fields_add( bibin, str_cstr( &tag ), str_cstr( &data ), 0 ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + } + strs_empty( &tag, &data, NULL ); + } +out: + strs_free( &tag, &data, NULL ); + return status; +} + +/* process_string() + * + * Handle lines like: + * + * '@STRING{TL = {Tetrahedron Lett.}}' + * + * p should point to just after '@STRING' + * + * In BibTeX, if a string is defined several times, the last one is kept. + * + */ +static int +process_string( char *p, long nref, param *pm ) +{ + int n, status = BIBL_OK; + str s1, s2, *t; + strs_init( &s1, &s2, NULL ); + while ( *p && *p!='{' && *p!='(' ) p++; + if ( *p=='{' || *p=='(' ) p++; + p = process_bibtexline( skip_ws( p ), &s1, &s2, 0, NULL, nref, pm ); + if ( p==NULL ) { status = BIBL_ERR_MEMERR; goto out; } + if ( str_has_value( &s2 ) ) { + str_findreplace( &s2, "\\ ", " " ); + } + if ( str_has_value( &s1 ) ) { + n = slist_find( &find, &s1 ); + if ( n==-1 ) { + t = slist_add( &find, &s1 ); + if ( t==NULL ) { status = BIBL_ERR_MEMERR; goto out; } + if ( str_has_value( &s2 ) ) t = slist_add( &replace, &s2 ); + else t = slist_addc( &replace, "" ); + if ( t==NULL ) { status = BIBL_ERR_MEMERR; goto out; } + } else { + if ( str_has_value( &s2 ) ) t = slist_set( &replace, n, &s2 ); + else t = slist_setc( &replace, n, "" ); + if ( t==NULL ) { status = BIBL_ERR_MEMERR; goto out; } + } + } +out: + strs_free( &s1, &s2, NULL ); + return status; +} + +/* bibtexin_processf() + * + * Handle '@STRING', '@reftype', and ignore '@COMMENT' + */ +static int +bibtexin_processf( fields *bibin, char *data, char *filename, long nref, param *p ) +{ + if ( !strncasecmp( data, "@STRING", 7 ) ) { + process_string( data+7, nref, p ); + return 0; + } else if ( !strncasecmp( data, "@COMMENT", 8 ) ) { + /* Not sure if these are real Bibtex, but not references */ + return 0; + } else { + process_cite( bibin, data, filename, nref, p ); + return 1; + } +} + +/***************************************************** + PUBLIC: void bibtexin_cleanf() +*****************************************************/ + +static int +bibtex_protected( str *data ) +{ + if ( data->data[0]=='{' && data->data[data->len-1]=='}' ) return 1; + if ( data->data[0]=='\"' && data->data[data->len-1]=='\"' ) return 1; + return 0; +} + +static int +bibtex_split( slist *tokens, str *s ) +{ + int i, n = s->len, nbrackets = 0, status = BIBL_OK; + str tok, *t; + + str_init( &tok ); + + for ( i=0; idata[i]=='{' && ( i==0 || s->data[i-1]!='\\' ) ) { + nbrackets++; + str_addchar( &tok, '{' ); + } else if ( s->data[i]=='}' && ( i==0 || s->data[i-1]!='\\' ) ) { + nbrackets--; + str_addchar( &tok, '}' ); + } else if ( !is_ws( s->data[i] ) || nbrackets ) { + str_addchar( &tok, s->data[i] ); + } else if ( is_ws( s->data[i] ) ) { + if ( str_has_value( &tok ) ) { + t = slist_add( tokens, &tok ); + if ( !t ) { + status = BIBL_ERR_MEMERR; + goto out; + } + } + str_empty( &tok ); + } + } + if ( str_has_value( &tok ) ) { + t = slist_add( tokens, &tok ); + if ( !t ) { + status = BIBL_ERR_MEMERR; + goto out; + } + } + + for ( i=0; in; ++i ) { + str_trimstartingws( slist_str( tokens, i ) ); + str_trimendingws( slist_str( tokens, i ) ); + } +out: + str_free( &tok ); + return status; +} + +static int +bibtex_addtitleurl( fields *info, str *in ) +{ + int fstatus, status = BIBL_OK; + str s; + char *p; + + str_init( &s ); + + /* ...skip past "\href{" and copy to "}" */ + p = str_cpytodelim( &s, in->data + 6, "}", 1 ); + if ( str_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } + + /* ...add to URL */ + fstatus = fields_add( info, "URL", s.data, 0 ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + + /* ...return deleted fragment to str in */ + p = str_cpytodelim( &s, p, "", 0 ); + if ( str_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } + str_swapstrings( &s, in ); + +out: + str_free( &s ); + return status; +} + +static int +is_url_tag( str *tag ) +{ + if ( str_has_value( tag ) ) { + if ( !strcasecmp( str_cstr( tag ), "url" ) ) return 1; + } + return 0; +} + +static int +is_name_tag( str *tag ) +{ + if ( str_has_value( tag ) ) { + if ( !strcasecmp( str_cstr( tag ), "author" ) ) return 1; + if ( !strcasecmp( str_cstr( tag ), "editor" ) ) return 1; + } + return 0; +} + +static void +bibtex_process_tilde( str *s ) +{ + char *p, *q; + int n = 0; + + p = q = s->data; + if ( !p ) return; + while ( *p ) { + if ( *p=='~' ) { + *q = ' '; + } else if ( *p=='\\' && *(p+1)=='~' ) { + n++; + p++; + *q = '~'; + } else { + *q = *p; + } + p++; + q++; + } + *q = '\0'; + s->len -= n; +} + +static void +bibtex_process_bracket( str *s ) +{ + char *p, *q; + int n = 0; + + p = q = s->data; + if ( !p ) return; + while ( *p ) { + if ( *p=='\\' && ( *(p+1)=='{' || *(p+1)=='}' ) ) { + n++; + p++; + *q = *p; + q++; + } else if ( *p=='{' || *p=='}' ) { + n++; + } else { + *q = *p; + q++; + } + p++; + } + *q = '\0'; + s->len -= n; +} + +static void +bibtex_cleantoken( str *s ) +{ + /* 'textcomp' annotations */ + str_findreplace( s, "\\textit", "" ); + str_findreplace( s, "\\textbf", "" ); + str_findreplace( s, "\\textsl", "" ); + str_findreplace( s, "\\textsc", "" ); + str_findreplace( s, "\\textsf", "" ); + str_findreplace( s, "\\texttt", "" ); + str_findreplace( s, "\\textsubscript", "" ); + str_findreplace( s, "\\textsuperscript", "" ); + str_findreplace( s, "\\emph", "" ); + str_findreplace( s, "\\url", "" ); + str_findreplace( s, "\\mbox", "" ); + + /* Other text annotations */ + str_findreplace( s, "\\it ", "" ); + str_findreplace( s, "\\em ", "" ); + + str_findreplace( s, "\\%", "%" ); + str_findreplace( s, "\\$", "$" ); + while ( str_findreplace( s, " ", " " ) ) {} + + /* 'textcomp' annotations that we don't want to substitute on output*/ + str_findreplace( s, "\\textdollar", "$" ); + str_findreplace( s, "\\textunderscore", "_" ); + + bibtex_process_bracket( s ); + bibtex_process_tilde( s ); + +} + +static int +bibtex_cleandata( str *tag, str *s, fields *info, param *p ) +{ + int i, status; + slist tokens; + str *tok; + if ( str_is_empty( s ) ) return BIBL_OK; + /* protect url from undergoing any parsing */ + if ( is_url_tag( tag ) ) return BIBL_OK; + slist_init( &tokens ); + status = bibtex_split( &tokens, s ); + if ( status!=BIBL_OK ) goto out; + for ( i=0; idata,"\\href{", 6)) { + bibtex_addtitleurl( info, tok ); + } + } + if ( p->latexin && !is_name_tag( tag ) && !is_url_tag( tag ) ) + bibtex_cleantoken( tok ); + } + str_empty( s ); + for ( i=0; i0 ) str_addchar( s, ' ' ); + str_strcat( s, tok ); + } +out: + slist_free( &tokens ); + return status; +} + +static int +bibtexin_cleanref( fields *bibin, param *p ) +{ + int i, n, status; + str *t, *d; + n = fields_num( bibin ); + for ( i=0; inrefs; ++i ) { + n = fields_find( bin->ref[i], "refnum", LEVEL_ANY ); + if ( n==-1 ) continue; + if ( !strcmp( bin->ref[i]->data[n].data, citekey ) ) return i; + } + return -1; +} + +static void +bibtexin_nocrossref( bibl *bin, long i, int n, param *p ) +{ + int n1 = fields_find( bin->ref[i], "REFNUM", LEVEL_ANY ); + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Cannot find cross-reference '%s'", + bin->ref[i]->data[n].data ); + if ( n1!=-1 ) fprintf( stderr, " for reference '%s'\n", + bin->ref[i]->data[n1].data ); + fprintf( stderr, "\n" ); +} + +static int +bibtexin_crossref_oneref( fields *bibref, fields *bibcross ) +{ + int j, n, nl, ntype, fstatus, status = BIBL_OK; + char *type, *nt, *nv; + + ntype = fields_find( bibref, "INTERNAL_TYPE", LEVEL_ANY ); + type = ( char * ) fields_value( bibref, ntype, FIELDS_CHRP_NOUSE ); + + n = fields_num( bibcross ); + for ( j=0; jnrefs; ++i ) { + bibref = bin->ref[i]; + n = fields_find( bibref, "CROSSREF", LEVEL_ANY ); + if ( n==-1 ) continue; + fields_setused( bibref, n ); + ncross = bibtexin_findref( bin, (char*) fields_value( bibref, n, FIELDS_CHRP ) ); + if ( ncross==-1 ) { + bibtexin_nocrossref( bin, i, n, p ); + continue; + } + bibcross = bin->ref[ncross]; + status = bibtexin_crossref_oneref( bibref, bibcross ); + if ( status!=BIBL_OK ) goto out; + } +out: + return status; +} + +static int +bibtexin_cleanf( bibl *bin, param *p ) +{ + int status = BIBL_OK; + long i; + + for ( i=0; inrefs; ++i ) + status = bibtexin_cleanref( bin->ref[i], p ); + bibtexin_crossref( bin, p ); + return status; +} + +/***************************************************** + PUBLIC: int bibtexin_typef() +*****************************************************/ + +static int +bibtexin_typef( fields *bibin, char *filename, int nrefs, param *p ) +{ + int ntypename, nrefname, is_default; + char *refname = "", *typename = ""; + + ntypename = fields_find( bibin, "INTERNAL_TYPE", LEVEL_MAIN ); + nrefname = fields_find( bibin, "REFNUM", LEVEL_MAIN ); + if ( nrefname!=-1 ) refname = fields_value( bibin, nrefname, FIELDS_CHRP_NOUSE ); + if ( ntypename!=-1 ) typename = fields_value( bibin, ntypename, FIELDS_CHRP_NOUSE ); + + return get_reftype( typename, nrefs, p->progname, p->all, p->nall, refname, &is_default, REFTYPE_CHATTY ); +} + +/***************************************************** + PUBLIC: int bibtexin_convertf(), returns BIBL_OK or BIBL_ERR_MEMERR +*****************************************************/ + +static int +bibtex_matches_list( fields *bibout, char *tag, char *suffix, str *data, int level, + slist *names, int *match ) +{ + int i, fstatus, status = BIBL_OK; + str newtag; + + *match = 0; + if ( names->n==0 ) return status; + + str_init( &newtag ); + + for ( i=0; in; ++i ) { + if ( strcmp( str_cstr( data ), slist_cstr( names, i ) ) ) continue; + str_initstrc( &newtag, tag ); + str_strcatc( &newtag, suffix ); + fstatus = fields_add( bibout, str_cstr( &newtag ), str_cstr( data ), level ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + *match = 1; + goto out; + } + +out: + str_free( &newtag ); + return status; +} + +/**** bibtexin_btorg ****/ + +/* + * BibTeX uses 'organization' in lieu of publisher if that field is missing. + * Otherwise output as + * + * The organization + * + * organizer of meeting + * + * + */ + +static int +bibtexin_btorg( fields *bibin, int m, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + int n, fstatus; + n = fields_find( bibin, "publisher", LEVEL_ANY ); + if ( n==-1 ) + fstatus = fields_add( bibout, "PUBLISHER", str_cstr( invalue ), level ); + else + fstatus = fields_add( bibout, "ORGANIZER:CORP", str_cstr( invalue ), level ); + if ( fstatus==FIELDS_OK ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + +/**** bibtexin_btsente() ****/ + +/* + * sentelink = {file://localhost/full/path/to/file.pdf,Sente,PDF} + * + * Sente is an academic reference manager for MacOSX and Apple iPad. + */ + +static int +bibtexin_btsente( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + int fstatus, status = BIBL_OK; + str link; + + str_init( &link ); + str_cpytodelim( &link, skip_ws( invalue->data ), ",", 0 ); + str_trimendingws( &link ); + if ( str_memerr( &link ) ) status = BIBL_ERR_MEMERR; + + if ( status==BIBL_OK && link.len ) { + fstatus = fields_add( bibout, "FILEATTACH", str_cstr( &link ), level ); + if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; + } + + str_free( &link ); + return status; +} + +/**** bibtexin_linkedfile() ****/ + +static int +count_colons( char *p ) +{ + int n = 0; + while ( *p ) { + if ( *p==':' ) n++; + p++; + } + return n; +} + +static int +first_colon( char *p ) +{ + int n = 0; + while ( p[n] && p[n]!=':' ) n++; + return n; +} + +static int +last_colon( char *p ) +{ + int n = strlen( p ) - 1; + while ( n>0 && p[n]!=':' ) n--; + return n; +} + +/* + * file={Description:/full/path/to/file.pdf:PDF} + */ +static int +bibtexin_linkedfile( fields *bibin, int m, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + int fstatus, status = BIBL_OK; + char *p = invalue->data; + int i, n, n1, n2; + str link; + + n = count_colons( p ); + if ( n > 1 ) { + /* A DOS file can contain a colon ":C:/....pdf:PDF" */ + /* Extract after 1st and up to last colons */ + n1 = first_colon( p ) + 1; + n2 = last_colon( p ); + str_init( &link ); + for ( i=n1; idata, level ); + if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; + } + + else if ( !strcmp( prefix, "jstor" ) ) { + fstatus = fields_add( bibout, "JSTOR", value->data, level ); + if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; + } + + else if ( !strcmp( prefix, "medline" ) ) { + fstatus = fields_add( bibout, "MEDLINE", value->data, level ); + if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; + } + + else if ( !strcmp( prefix, "pubmed" ) ) { + fstatus = fields_add( bibout, "PMID", value->data, level ); + if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; + } + + /* ...if this is unknown prefix, merge prefix & eprint */ + else { + str_init( &merge ); + str_mergestrs( &merge, prefix, ":", value->data, NULL ); + fstatus = fields_add( bibout, "URL", merge.data, level ); + if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; + str_free( &merge ); + } + + return status; +} +static int +process_eprint_without_prefix( fields *bibout, str *value, int level ) +{ + int fstatus; + + /* ...no archivePrefix, need to handle just 'eprint' tag */ + fstatus = fields_add( bibout, "URL", value->data, level ); + + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + else return BIBL_OK; +} + +static int +bibtexin_eprint( fields *bibin, int m, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + char *prefix; + int n; + + /* ...do we have an archivePrefix too? */ + n = fields_find( bibin, "ARCHIVEPREFIX", level ); + if ( n==-1 ) n = fields_find( bibin, "EPRINTTYPE", level ); + if ( n!=-1 ) { + prefix = fields_value( bibin, n, FIELDS_CHRP ); + return process_eprint_with_prefix( bibout, prefix, invalue, level ); + } + + /* ...no we don't */ + return process_eprint_without_prefix( bibout, invalue, level ); +} + +/**** bibtexin_keyword() ****/ + +/* Split keywords="" with semicolons. + * Commas are also frequently used, but will break + * entries like: + * keywords="Microscopy, Confocal" + * Returns BIBL_OK or BIBL_ERR_MEMERR + */ + +static int +bibtexin_keyword( fields *bibin, int m, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + int fstatus, status = BIBL_OK; + str keyword; + char *p; + + p = invalue->data; + str_init( &keyword ); + + while ( *p ) { + p = str_cpytodelim( &keyword, skip_ws( p ), ";", 1 ); + str_trimendingws( &keyword ); + if ( str_memerr( &keyword ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } + if ( keyword.len ) { + fstatus = fields_add( bibout, "KEYWORD", keyword.data, level ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + } + } +out: + str_free( &keyword ); + return status; +} + +/* + * bibtex_names( bibout, newtag, field, level); + * + * split names in author list separated by and's (use '|' character) + * and add names + * + * returns BIBL_OK on success, BIBL_ERR_MEMERR on memory error + */ + +static int +bibtexin_person( fields *bibin, int m, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + int begin, end, ok, n, etal, i, status, match; + slist tokens; + + /* If we match the asis or corps list add and bail. */ + status = bibtex_matches_list( bibout, outtag, ":ASIS", invalue, level, &(pm->asis), &match ); + if ( match==1 || status!=BIBL_OK ) return status; + status = bibtex_matches_list( bibout, outtag, ":CORP", invalue, level, &(pm->corps), &match ); + if ( match==1 || status!=BIBL_OK ) return status; + + slist_init( &tokens ); + + bibtex_split( &tokens, invalue ); + for ( i=0; idata ) ) level=LEVEL_MAIN; + ok = title_process( bibout, "TITLE", invalue->data, level, pm->nosplittitle ); + if ( ok ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + +static void +bibtexin_notag( param *p, char *tag ) +{ + if ( p->verbose && strcmp( tag, "INTERNAL_TYPE" ) ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Cannot find tag '%s'\n", tag ); + } +} + +static int +bibtexin_convertf( fields *bibin, fields *bibout, int reftype, param *p ) +{ + static int (*convertfns[NUM_REFTYPES])(fields *, int, str *, str *, int, param *, char *, fields *) = { + [ 0 ... NUM_REFTYPES-1 ] = generic_null, + [ SIMPLE ] = generic_simple, + [ TITLE ] = bibtexin_title, + [ PERSON ] = bibtexin_person, + [ PAGES ] = generic_pages, + [ KEYWORD ] = bibtexin_keyword, + [ EPRINT ] = bibtexin_eprint, + [ HOWPUBLISHED ] = bibtexin_howpublished, + [ LINKEDFILE ] = bibtexin_linkedfile, + [ NOTES ] = generic_notes, + [ BT_SENTE ] = bibtexin_btsente, + [ BT_ORG ] = bibtexin_btorg, + [ URL ] = generic_url + }; + + int process, level, i, nfields, status = BIBL_OK; + str *intag, *invalue; + char *outtag; + + nfields = fields_num( bibin ); + for ( i=0; iall, p->nall, &process, &level, &outtag ) ) { + bibtexin_notag( p, str_cstr( intag ) ); + continue; + } + + status = convertfns[ process ] ( bibin, i, intag, invalue, level, p, outtag, bibout ); + if ( status!=BIBL_OK ) return status; + } + + if ( status==BIBL_OK && p->verbose ) fields_report( bibout, stderr ); + + return status; +} diff --git a/bibutils/bibtexin.h b/bibutils/bibtexin.h deleted file mode 100644 --- a/bibutils/bibtexin.h +++ /dev/null @@ -1,33 +0,0 @@ -/* - * bibtexin.h - * - * Copyright (c) Chris Putnam 2003-2014 - * - * Source code released under the GPL version 2 - * - */ -#ifndef BIBTEXIN_H -#define BIBTEXIN_H - -#include "newstr.h" -#include "list.h" -#include "fields.h" -#include "bibl.h" -#include "bibutils.h" -#include "reftypes.h" - -extern int bibtexin_convertf( fields *bibin, fields *info, int reftype, param *p, variants *all, int nall ); -extern int bibtexin_processf( fields *bibin, char *data, char *filename, long nref ); -extern int bibtexin_cleanf( bibl *bin, param *p ); -extern int bibtexin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ); -extern int bibtexin_typef( fields *bibin, char *filename, int nrefs, - param *p, variants *all, int nall ); -extern void bibtexin_initparams( param *p, const char *progname ); - - -extern variants bibtex_all[]; -extern int bibtex_nall; - - -#endif - diff --git a/bibutils/bibtexout.c b/bibutils/bibtexout.c --- a/bibutils/bibtexout.c +++ b/bibutils/bibtexout.c @@ -1,7 +1,7 @@ /* * bibtexout.c * - * Copyright (c) Chris Putnam 2003-2014 + * Copyright (c) Chris Putnam 2003-2017 * * Program and source code released under the GPL version 2 * @@ -10,16 +10,19 @@ #include #include #include -#include "newstr.h" +#include "str.h" #include "strsearch.h" #include "utf8.h" #include "xml.h" #include "fields.h" #include "name.h" -#include "bibl.h" -#include "doi.h" -#include "bibtexout.h" +#include "title.h" +#include "url.h" +#include "bibformats.h" +static int bibtexout_write( fields *in, FILE *fp, param *p, unsigned long refnum ); +static void bibtexout_writeheader( FILE *outptr, param *p ); + void bibtexout_initparams( param *p, const char *progname ) { @@ -59,44 +62,22 @@ TYPE_MANUAL, TYPE_UNPUBLISHED, TYPE_ELECTRONIC, - TYPE_MISC + TYPE_MISC, + NUM_TYPES }; -static void -output_citekey( FILE *fp, fields *info, unsigned long refnum, int format_opts ) -{ - int n = fields_find( info, "REFNUM", -1 ); - char *p; - if ( n!=-1 ) { - p = info->data[n].data; - while ( p && *p && *p!='|' ) { - if ( format_opts & BIBOUT_STRICTKEY ) { - if ( isdigit((unsigned char)*p) || (*p>='A' && *p<='Z') || - (*p>='a' && *p<='z' ) ) - fprintf( fp, "%c", *p ); - } - else { - if ( *p!=' ' && *p!='\t' ) { - fprintf( fp, "%c", *p ); - } - } - p++; - } - } -} - static int -bibtexout_type( fields *info, char *filename, int refnum, param *p ) +bibtexout_type( fields *in, char *filename, int refnum, param *p ) { - char *genre; int type = TYPE_UNKNOWN, i, maxlevel, n, level; + char *tag, *genre; /* determine bibliography type */ - for ( i=0; in; ++i ) { - if ( strcasecmp( info->tag[i].data, "GENRE" ) && - strcasecmp( info->tag[i].data, "NGENRE" ) ) continue; - genre = info->data[i].data; - level = info->level[i]; + for ( i=0; in; ++i ) { + tag = fields_tag( in, i, FIELDS_CHRP ); + if ( strcasecmp( tag, "GENRE" ) && strcasecmp( tag, "NGENRE" ) ) continue; + genre = fields_value( in, i, FIELDS_CHRP ); + level = in->level[i]; if ( !strcasecmp( genre, "periodical" ) || !strcasecmp( genre, "academic journal" ) || !strcasecmp( genre, "magazine" ) || @@ -115,9 +96,11 @@ else type = TYPE_INCOLLECTION; } else if ( !strcasecmp( genre, "report" ) ) type = TYPE_REPORT; + else if ( !strcasecmp( genre, "book chapter" ) ) + type = TYPE_INBOOK; else if ( !strcasecmp( genre, "book" ) ) { - if ( level==0 ) type=TYPE_BOOK; - else type=TYPE_INBOOK; + if ( level==0 ) type = TYPE_BOOK; + else type = TYPE_INBOOK; } else if ( !strcasecmp( genre, "thesis" ) ) { if ( type==TYPE_UNKNOWN ) type=TYPE_PHDTHESIS; } else if ( !strcasecmp( genre, "Ph.D. thesis" ) ) @@ -128,26 +111,27 @@ type = TYPE_ELECTRONIC; } if ( type==TYPE_UNKNOWN ) { - for ( i=0; in; ++i ) { - if ( strcasecmp( info->tag[i].data, "ISSUANCE" ) ) continue; - if ( !strcasecmp( info->data[i].data, "monographic" ) ) { - if ( info->level[i]==0 ) type = TYPE_BOOK; - else if ( info->level[i]==1 ) type=TYPE_INBOOK; + for ( i=0; in; ++i ) { + tag = fields_tag( in, i, FIELDS_CHRP ); + if ( strcasecmp( tag, "ISSUANCE" ) ) continue; + genre = fields_value( in, i, FIELDS_CHRP ); + if ( !strcasecmp( genre, "monographic" ) ) { + if ( in->level[i]==0 ) type = TYPE_BOOK; + else if ( in->level[i]==1 ) type = TYPE_MISC; } } } - /* default to BOOK type */ + /* default to TYPE_MISC */ if ( type==TYPE_UNKNOWN ) { - maxlevel = fields_maxlevel( info ); - if ( maxlevel > 0 ) type = TYPE_INBOOK; + maxlevel = fields_maxlevel( in ); + if ( maxlevel > 0 ) type = TYPE_MISC; else { if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, "Cannot identify TYPE " - "in reference %d ", refnum+1 ); - n = fields_find( info, "REFNUM", -1 ); + fprintf( stderr, "Cannot identify TYPE in reference %d ", refnum+1 ); + n = fields_find( in, "REFNUM", LEVEL_ANY ); if ( n!=-1 ) - fprintf( stderr, " %s", info->data[n].data); + fprintf( stderr, " %s", (char*) fields_value( in, n, FIELDS_CHRP ) ); fprintf( stderr, " (defaulting to @Misc)\n" ); type = TYPE_MISC; } @@ -156,355 +140,592 @@ } static void -output_type( FILE *fp, int type, int format_opts ) +output( FILE *fp, fields *out, int format_opts ) { - typedef struct { - int bib_type; - char *type_name; - } typenames; + int i, j, len, nquotes; + char *tag, *value, ch; - typenames types[] = { - { TYPE_ARTICLE, "Article" }, - { TYPE_INBOOK, "Inbook" }, - { TYPE_PROCEEDINGS, "Proceedings" }, - { TYPE_INPROCEEDINGS, "InProceedings" }, - { TYPE_BOOK, "Book" }, - { TYPE_PHDTHESIS, "PhdThesis" }, - { TYPE_MASTERSTHESIS, "MastersThesis" }, - { TYPE_REPORT, "TechReport" }, - { TYPE_MANUAL, "Manual" }, - { TYPE_COLLECTION, "Collection" }, - { TYPE_INCOLLECTION, "InCollection" }, - { TYPE_UNPUBLISHED, "Unpublished" }, - { TYPE_ELECTRONIC, "Electronic" }, - { TYPE_MISC, "Misc" } }; - int i, len, ntypes = sizeof( types ) / sizeof( types[0] ); - char *s = NULL; - for ( i=0; in; ++j ) { + nquotes = 0; + tag = ( char * ) fields_tag( out, j, FIELDS_CHRP ); + value = ( char * ) fields_value( out, j, FIELDS_CHRP ); + fprintf( fp, ",\n" ); + if ( format_opts & BIBL_FORMAT_BIBOUT_WHITESPACE ) fprintf( fp, " " ); + if ( !(format_opts & BIBL_FORMAT_BIBOUT_UPPERCASE ) ) fprintf( fp, "%s", tag ); else { - if ( format_opts & BIBOUT_BRACKETS || - ( i>0 && data[i-1]=='\\' ) ) - fprintf( fp, "\"" ); + len = strlen( tag ); + for ( i=0; i0 && value[i-1]=='\\' ) ) + fprintf( fp, "\"" ); + else { + if ( nquotes % 2 == 0 ) + fprintf( fp, "``" ); + else fprintf( fp, "\'\'" ); + nquotes++; + } } } + + if ( format_opts & BIBL_FORMAT_BIBOUT_BRACKETS ) fprintf( fp, "}" ); + else fprintf( fp, "\"" ); } - if ( format_opts & BIBOUT_BRACKETS ) fprintf( fp, "}" ); - else fprintf( fp, "\"" ); + /* ...finish reference */ + if ( format_opts & BIBL_FORMAT_BIBOUT_FINALCOMMA ) fprintf( fp, "," ); + fprintf( fp, "\n}\n\n" ); + + fflush( fp ); } static void -output_and_use( FILE *fp, fields *info, int n, char *outtag, int format_opts ) +append_type( int type, fields *out, int *status ) { - output_element( fp, outtag, info->data[n].data, format_opts ); - fields_setused( info, n ); + char *typenames[ NUM_TYPES ] = { + [ TYPE_ARTICLE ] = "Article", + [ TYPE_INBOOK ] = "Inbook", + [ TYPE_PROCEEDINGS ] = "Proceedings", + [ TYPE_INPROCEEDINGS ] = "InProceedings", + [ TYPE_BOOK ] = "Book", + [ TYPE_PHDTHESIS ] = "PhdThesis", + [ TYPE_MASTERSTHESIS ] = "MastersThesis", + [ TYPE_REPORT ] = "TechReport", + [ TYPE_MANUAL ] = "Manual", + [ TYPE_COLLECTION ] = "Collection", + [ TYPE_INCOLLECTION ] = "InCollection", + [ TYPE_UNPUBLISHED ] = "Unpublished", + [ TYPE_ELECTRONIC ] = "Electronic", + [ TYPE_MISC ] = "Misc", + }; + int fstatus; + char *s; + + if ( type < 0 || type >= NUM_TYPES ) type = TYPE_MISC; + s = typenames[ type ]; + + fstatus = fields_add( out, "TYPE", s, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } static void -output_simple( FILE *fp, fields *info, char *intag, char *outtag, - int format_opts ) +append_citekey( fields *in, fields *out, int format_opts, int *status ) { - int n = fields_find( info, intag, -1 ); + int n, fstatus; + str s; + char *p; + + n = fields_find( in, "REFNUM", LEVEL_ANY ); + if ( ( format_opts & BIBL_FORMAT_BIBOUT_DROPKEY ) || n==-1 ) { + fstatus = fields_add( out, "REFNUM", "", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + + else { + str_init( &s ); + p = fields_value( in, n, FIELDS_CHRP ); + while ( p && *p && *p!='|' ) { + if ( format_opts & BIBL_FORMAT_BIBOUT_STRICTKEY ) { + if ( isdigit((unsigned char)*p) || (*p>='A' && *p<='Z') || + (*p>='a' && *p<='z' ) ) { + str_addchar( &s, *p ); + } + } + else { + if ( *p!=' ' && *p!='\t' ) { + str_addchar( &s, *p ); + } + } + p++; + } + if ( str_memerr( &s ) ) { *status = BIBL_ERR_MEMERR; str_free( &s ); return; } + fstatus = fields_add( out, "REFNUM", str_cstr( &s ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + str_free( &s ); + } +} + +static void +append_simple( fields *in, char *intag, char *outtag, fields *out, int *status ) +{ + int n, fstatus; + + n = fields_find( in, intag, LEVEL_ANY ); if ( n!=-1 ) { - output_and_use( fp, info, n, outtag, format_opts ); + fields_setused( in, n ); + fstatus = fields_add( out, outtag, fields_value( in, n, FIELDS_CHRP ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } } static void -output_simpleall( FILE *fp, fields *info, char *intag, char *outtag, - int format_opts ) +append_simpleall( fields *in, char *intag, char *outtag, fields *out, int *status ) { - int i; - for ( i=0; in; ++i ) { - if ( fields_match_tag( info, i, intag ) ) - output_and_use( fp, info, i, outtag, format_opts ); + int i, fstatus; + + for ( i=0; in; ++i ) { + if ( fields_match_tag( in, i, intag ) ) { + fields_setused( in, i ); + fstatus = fields_add( out, outtag, fields_value( in, i, FIELDS_CHRP ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + return; + } + } } } static void -output_keywords( FILE *fp, fields *info, int format_opts ) +append_keywords( fields *in, fields *out, int *status ) { - newstr keywords, *word; + str keywords, *word; + vplist_index i; + int fstatus; vplist a; - int i; - newstr_init( &keywords ); + + str_init( &keywords ); vplist_init( &a ); - fields_findv_each( info, LEVEL_ANY, FIELDS_STRP, &a, "KEYWORD" ); + + fields_findv_each( in, LEVEL_ANY, FIELDS_STRP, &a, "KEYWORD" ); + if ( a.n ) { + for ( i=0; i0 ) newstr_strcat( &keywords, "; " ); - newstr_newstrcat( &keywords, word ); + if ( i>0 ) str_strcatc( &keywords, "; " ); + str_strcat( &keywords, word ); } - output_element( fp, "keywords", keywords.data, format_opts ); + if ( str_memerr( &keywords ) ) { *status = BIBL_ERR_MEMERR; goto out; } + + fstatus = fields_add( out, "keywords", str_cstr( &keywords ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + goto out; + } + + } - newstr_free( &keywords ); + +out: + str_free( &keywords ); vplist_free( &a ); } static void -output_fileattach( FILE *fp, fields *info, int format_opts ) +append_fileattach( fields *in, fields *out, int *status ) { - newstr data; - int i; - newstr_init( &data ); - for ( i=0; in; ++i ) { - if ( strcasecmp( info->tag[i].data, "FILEATTACH" ) ) continue; - newstr_strcpy( &data, ":" ); - newstr_newstrcat( &data, &(info->data[i]) ); - if ( strsearch( info->data[i].data, ".pdf" ) ) - newstr_strcat( &data, ":PDF" ); - else if ( strsearch( info->data[i].data, ".html" ) ) - newstr_strcat( &data, ":HTML" ); - else newstr_strcat( &data, ":TYPE" ); - output_element( fp, "file", data.data, format_opts ); - fields_setused( info, i ); - newstr_empty( &data ); + char *tag, *value; + int i, fstatus; + str data; + + str_init( &data ); + + for ( i=0; in; ++i ) { + + tag = fields_tag( in, i, FIELDS_CHRP ); + if ( strcasecmp( tag, "FILEATTACH" ) ) continue; + + value = fields_value( in, i, FIELDS_CHRP ); + str_strcpyc( &data, ":" ); + str_strcatc( &data, value ); + if ( strsearch( value, ".pdf" ) ) + str_strcatc( &data, ":PDF" ); + else if ( strsearch( value, ".html" ) ) + str_strcatc( &data, ":HTML" ); + else str_strcatc( &data, ":TYPE" ); + + if ( str_memerr( &data ) ) { + *status = BIBL_ERR_MEMERR; + goto out; + } + + fields_setused( in, i ); + fstatus = fields_add( out, "file", str_cstr( &data ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + goto out; + } + + str_empty( &data ); } - newstr_free( &data ); +out: + str_free( &data ); } static void -output_people( FILE *fp, fields *info, unsigned long refnum, char *tag, - char *ctag, char *atag, char *bibtag, int level, - int format_opts ) +append_people( fields *in, char *tag, char *ctag, char *atag, + char *bibtag, int level, fields *out, int format_opts ) { - newstr allpeople, oneperson; + str allpeople, oneperson; int i, npeople, person, corp, asis; - newstrs_init( &allpeople, &oneperson, NULL ); + strs_init( &allpeople, &oneperson, NULL ); /* primary citation authors */ npeople = 0; - for ( i=0; in; ++i ) { - if ( level!=-1 && info->level[i]!=level ) continue; - person = ( strcasecmp( info->tag[i].data, tag ) == 0 ); - corp = ( strcasecmp( info->tag[i].data, ctag ) == 0 ); - asis = ( strcasecmp( info->tag[i].data, atag ) == 0 ); + for ( i=0; in; ++i ) { + if ( level!=LEVEL_ANY && in->level[i]!=level ) continue; + person = ( strcasecmp( in->tag[i].data, tag ) == 0 ); + corp = ( strcasecmp( in->tag[i].data, ctag ) == 0 ); + asis = ( strcasecmp( in->tag[i].data, atag ) == 0 ); if ( person || corp || asis ) { if ( npeople>0 ) { - if ( format_opts & BIBOUT_WHITESPACE ) - newstr_strcat(&allpeople,"\n\t\tand "); - else newstr_strcat( &allpeople, "\nand " ); + if ( format_opts & BIBL_FORMAT_BIBOUT_WHITESPACE ) + str_strcatc( &allpeople, "\n\t\tand " ); + else str_strcatc( &allpeople, "\nand " ); } if ( corp ) { - newstr_addchar( &allpeople, '{' ); - newstr_strcat( &allpeople, fields_value( info, i, FIELDS_CHRP ) ); - newstr_addchar( &allpeople, '}' ); + str_addchar( &allpeople, '{' ); + str_strcat( &allpeople, fields_value( in, i, FIELDS_STRP ) ); + str_addchar( &allpeople, '}' ); } else if ( asis ) { - newstr_addchar( &allpeople, '{' ); - newstr_strcat( &allpeople, fields_value( info, i, FIELDS_CHRP ) ); - newstr_addchar( &allpeople, '}' ); + str_addchar( &allpeople, '{' ); + str_strcat( &allpeople, fields_value( in, i, FIELDS_STRP ) ); + str_addchar( &allpeople, '}' ); } else { - name_build_withcomma( &oneperson, fields_value( info, i, FIELDS_CHRP ) ); - newstr_newstrcat( &allpeople, &oneperson ); + name_build_withcomma( &oneperson, fields_value( in, i, FIELDS_CHRP ) ); + str_strcat( &allpeople, &oneperson ); } npeople++; } } - if ( npeople ) - output_element( fp, bibtag, allpeople.data, format_opts ); + if ( npeople ) { + fields_add( out, bibtag, allpeople.data, LEVEL_MAIN ); + } - newstrs_free( &allpeople, &oneperson, NULL ); + strs_free( &allpeople, &oneperson, NULL ); } -static void -output_title( FILE *fp, fields *info, unsigned long refnum, char *bibtag, int level, int format_opts ) +static int +append_title_chosen( fields *in, char *bibtag, fields *out, int nmainttl, int nsubttl ) { - newstr title, *mainttl, *subttl; - int n1 = -1, n2 = -1; - /* Option is for short titles of journals */ - if ( ( format_opts & BIBOUT_SHORTTITLE ) && level==1 ) { - n1 = fields_find( info, "SHORTTITLE", level ); - n2 = fields_find( info, "SHORTSUBTITLE", level ); + str fulltitle, *mainttl = NULL, *subttl = NULL; + int status, ret = BIBL_OK; + + str_init( &fulltitle ); + + if ( nmainttl!=-1 ) { + mainttl = fields_value( in, nmainttl, FIELDS_STRP ); + fields_setused( in, nmainttl ); } - if ( n1==-1 ) { - n1 = fields_find( info, "TITLE", level ); - n2 = fields_find( info, "SUBTITLE", level ); + + if ( nsubttl!=-1 ) { + subttl = fields_value( in, nsubttl, FIELDS_STRP ); + fields_setused( in, nsubttl ); } - if ( n1!=-1 ) { - newstr_init( &title ); - mainttl = fields_value( info, n1, FIELDS_STRP ); - newstr_newstrcpy( &title, mainttl ); - fields_setused( info, n1 ); - if ( n2!=-1 ) { - subttl = fields_value( info, n2, FIELDS_STRP ); - if ( mainttl->len > 0 && - mainttl->data[mainttl->len-1]!='?' ) - newstr_strcat( &title, ": " ); - else newstr_addchar( &title, ' ' ); - newstr_newstrcat( &title, subttl ); - fields_setused( info, n2 ); - } - output_element( fp, bibtag, title.data, format_opts ); - newstr_free( &title ); + + title_combine( &fulltitle, mainttl, subttl ); + + if ( str_memerr( &fulltitle ) ) { + ret = BIBL_ERR_MEMERR; + goto out; } + + if ( str_has_value( &fulltitle ) ) { + status = fields_add( out, bibtag, str_cstr( &fulltitle ), LEVEL_MAIN ); + if ( status!=FIELDS_OK ) ret = BIBL_ERR_MEMERR; + } + +out: + str_free( &fulltitle ); + return ret; } +static int +append_title( fields *in, char *bibtag, int level, fields *out, int format_opts ) +{ + int title = -1, short_title = -1; + int subtitle = -1, short_subtitle = -1; + int use_title = -1, use_subtitle = -1; + + title = fields_find( in, "TITLE", level ); + short_title = fields_find( in, "SHORTTITLE", level ); + subtitle = fields_find( in, "SUBTITLE", level ); + short_subtitle = fields_find( in, "SHORTSUBTITLE", level ); + + if ( title==-1 || ( ( format_opts & BIBL_FORMAT_BIBOUT_SHORTTITLE ) && level==1 ) ) { + use_title = short_title; + use_subtitle = short_subtitle; + } + + else { + use_title = title; + use_subtitle = subtitle; + } + + return append_title_chosen( in, bibtag, out, use_title, use_subtitle ); +} + static void -output_date( FILE *fp, fields *info, unsigned long refnum, int format_opts ) +append_titles( fields *in, int type, fields *out, int format_opts, int *status ) { + /* item=main level title */ + *status = append_title( in, "title", 0, out, format_opts ); + if ( *status!=BIBL_OK ) return; + + switch( type ) { + + case TYPE_ARTICLE: + *status = append_title( in, "journal", 1, out, format_opts ); + break; + + case TYPE_INBOOK: + *status = append_title( in, "bookTitle", 1, out, format_opts ); + if ( *status!=BIBL_OK ) return; + *status = append_title( in, "series", 2, out, format_opts ); + break; + + case TYPE_INCOLLECTION: + case TYPE_INPROCEEDINGS: + *status = append_title( in, "booktitle", 1, out, format_opts ); + if ( *status!=BIBL_OK ) return; + *status = append_title( in, "series", 2, out, format_opts ); + break; + + case TYPE_PHDTHESIS: + case TYPE_MASTERSTHESIS: + *status = append_title( in, "series", 1, out, format_opts ); + break; + + case TYPE_BOOK: + case TYPE_REPORT: + case TYPE_COLLECTION: + case TYPE_PROCEEDINGS: + *status = append_title( in, "series", 1, out, format_opts ); + if ( *status!=BIBL_OK ) return; + *status = append_title( in, "series", 2, out, format_opts ); + break; + + default: + /* do nothing */ + break; + + } +} + +static int +find_date( fields *in, char *date_element ) +{ + char date[100], partdate[100]; + int n; + + sprintf( date, "DATE:%s", date_element ); + n = fields_find( in, date, LEVEL_ANY ); + + if ( n==-1 ) { + sprintf( partdate, "PARTDATE:%s", date_element ); + n = fields_find( in, partdate, LEVEL_ANY ); + } + + return n; +} + +static void +append_date( fields *in, fields *out, int *status ) +{ char *months[12] = { "Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec" }; - int n, month; - n = fields_find( info, "YEAR", -1 ); - if ( n==-1 ) n = fields_find( info, "PARTYEAR", -1 ); + int n, month, fstatus; + + n = find_date( in, "YEAR" ); if ( n!=-1 ) { - output_element( fp, "year", info->data[n].data, format_opts ); - fields_setused( info, n ); + fields_setused( in, n ); + fstatus = fields_add( out, "year", in->data[n].data, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + return; + } } - n = fields_find( info, "MONTH", -1 ); - if ( n==-1 ) n = fields_find( info, "PARTMONTH", -1 ); + + n = find_date( in, "MONTH" ); if ( n!=-1 ) { - month = atoi( info->data[n].data ); + fields_setused( in, n ); + month = atoi( in->data[n].data ); if ( month>0 && month<13 ) - output_element( fp, "month", months[month-1], format_opts ); + fstatus = fields_add( out, "month", months[month-1], LEVEL_MAIN ); else - output_element( fp, "month", info->data[n].data, format_opts ); - fields_setused( info, n ); + fstatus = fields_add( out, "month", in->data[n].data, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + return; + } } - n = fields_find( info, "DAY", -1 ); - if ( n==-1 ) n = fields_find( info, "PARTDAY", -1 ); + + n = find_date( in, "DAY" ); if ( n!=-1 ) { - output_element( fp, "day", info->data[n].data, format_opts ); - fields_setused( info, n ); + fields_setused( in, n ); + fstatus = fields_add( out, "day", in->data[n].data, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + return; + } } -} +} -/* output article number as pages if true pages aren't found */ static void -output_articlenumber( FILE *fp, fields *info, unsigned long refnum, - int format_opts ) +append_arxiv( fields *in, fields *out, int *status ) { - int ar = fields_find( info, "ARTICLENUMBER", -1 ); - if ( ar!=-1 ) { - newstr pages; - newstr_init( &pages ); - newstr_strcat( &pages, info->data[ar].data ); - output_element( fp, "pages", pages.data, format_opts ); - fields_setused( info, ar ); - newstr_free( &pages ); + int n, fstatus1, fstatus2; + str url; + + n = fields_find( in, "ARXIV", LEVEL_ANY ); + if ( n==-1 ) return; + + fields_setused( in, n ); + + /* ...write: + * archivePrefix = "arXiv", + * eprint = "#####", + * ...for arXiv references + */ + fstatus1 = fields_add( out, "archivePrefix", "arXiv", LEVEL_MAIN ); + fstatus2 = fields_add( out, "eprint", fields_value( in, n, FIELDS_CHRP ), LEVEL_MAIN ); + if ( fstatus1!=FIELDS_OK || fstatus2!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + return; } + + /* ...also write: + * url = "http://arxiv.org/abs/####", + * ...to maximize compatibility + */ + str_init( &url ); + arxiv_to_url( in, n, "URL", &url ); + if ( str_has_value( &url ) ) { + fstatus1 = fields_add( out, "url", str_cstr( &url ), LEVEL_MAIN ); + if ( fstatus1!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + str_free( &url ); } static void -output_arxiv( FILE *fp, fields *info, int format_opts ) +append_urls( fields *in, fields *out, int *status ) { - int ar = fields_find( info, "ARXIV", -1 ); - if ( ar!=-1 ) { - newstr arxiv; - newstr_init( &arxiv ); - arxiv_to_url( info, ar, "URL", &arxiv ); - if ( arxiv.len ) - output_element( fp, "url", arxiv.data, format_opts ); - newstr_free( &arxiv ); + int lstatus; + slist types; + + lstatus = slist_init_valuesc( &types, "URL", "DOI", "PMID", "PMC", "JSTOR", NULL ); + if ( lstatus!=SLIST_OK ) { + *status = BIBL_ERR_MEMERR; + return; } + + *status = urls_merge_and_add( in, LEVEL_ANY, out, "url", LEVEL_MAIN, &types ); + + slist_free( &types ); } static void -output_pmid( FILE *fp, fields *info, int format_opts ) +append_isi( fields *in, fields *out, int *status ) { - int pm = fields_find( info, "PMID", -1 ); - if ( pm!=-1 ) { - newstr pmid; - newstr_init( &pmid ); - pmid_to_url( info, pm, "URL", &pmid ); - if ( pmid.len ) - output_element( fp, "url", pmid.data, format_opts ); - newstr_free( &pmid ); + int n, fstatus; + + n = fields_find( in, "ISIREFNUM", LEVEL_ANY ); + if ( n!=-1 ) { + fstatus = fields_add( out, "note", fields_value( in, n, FIELDS_CHRP ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } } -static void -output_jstor( FILE *fp, fields *info, int format_opts ) +static int +append_articlenumber( fields *in, fields *out ) { - int js = fields_find( info, "JSTOR", -1 ); - if ( js!=-1 ) { - newstr jstor; - newstr_init( &jstor ); - jstor_to_url( info, js, "URL", &jstor ); - if ( jstor.len ) - output_element( fp, "url", jstor.data, format_opts ); - newstr_free( &jstor ); + int n, fstatus; + + n = fields_find( in, "ARTICLENUMBER", LEVEL_ANY ); + if ( n!=-1 ) { + fields_setused( in, n ); + fstatus = fields_add( out, "pages", fields_value( in, n, FIELDS_CHRP ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } + return BIBL_OK; } -static void -output_pages( FILE *fp, fields *info, unsigned long refnum, int format_opts ) +static int +pages_build_pagestr( str *pages, fields *in, int sn, int en, int format_opts ) { - newstr pages; - int sn, en; - sn = fields_find( info, "PAGESTART", -1 ); - en = fields_find( info, "PAGEEND", -1 ); - if ( sn==-1 && en==-1 ) { - output_articlenumber( fp, info, refnum, format_opts ); - return; - } - newstr_init( &pages ); + /* ...append if starting page number is defined */ if ( sn!=-1 ) { - newstr_strcat( &pages, info->data[sn].data ); - fields_setused( info, sn ); + str_strcat( pages, fields_value( in, sn, FIELDS_STRP ) ); + fields_setused( in, sn ); } + + /* ...append dashes if both starting and ending page numbers are defined */ if ( sn!=-1 && en!=-1 ) { - if ( format_opts & BIBOUT_SINGLEDASH ) - newstr_strcat( &pages, "-" ); + if ( format_opts & BIBL_FORMAT_BIBOUT_SINGLEDASH ) + str_strcatc( pages, "-" ); else - newstr_strcat( &pages, "--" ); + str_strcatc( pages, "--" ); } + + /* ...append ending page number is defined */ if ( en!=-1 ) { - newstr_strcat( &pages, info->data[en].data ); - fields_setused( info, en ); + str_strcat( pages, fields_value( in, en, FIELDS_STRP ) ); + fields_setused( in, en ); } - output_element( fp, "pages", pages.data, format_opts ); - newstr_free( &pages ); + + if ( str_memerr( pages ) ) return BIBL_ERR_MEMERR; + else return BIBL_OK; } +static int +pages_are_defined( fields *in, int *sn, int *en ) +{ + *sn = fields_find( in, "PAGES:START", LEVEL_ANY ); + *en = fields_find( in, "PAGES:STOP", LEVEL_ANY ); + if ( *sn==-1 && *en==-1 ) return 0; + else return 1; +} + +static void +append_pages( fields *in, fields *out, int format_opts, int *status ) +{ + int sn, en, fstatus; + str pages; + + if ( !pages_are_defined( in, &sn, &en ) ) { + *status = append_articlenumber( in, out ); + return; + } + + str_init( &pages ); + *status = pages_build_pagestr( &pages, in, sn, en, format_opts ); + if ( *status==BIBL_OK ) { + fstatus = fields_add( out, "pages", str_cstr( &pages ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + str_free( &pages ); +} + /* * from Tim Hicks: * I'm no expert on bibtex, but those who know more than I on our mailing @@ -518,108 +739,94 @@ */ static void -output_issue_number( FILE *fp, fields *info, int format_opts ) +append_issue_number( fields *in, fields *out, int *status ) { - int nissue = fields_find( info, "ISSUE", -1 ); - int nnumber = fields_find( info, "NUMBER", -1 ); + int nissue = fields_find( in, "ISSUE", LEVEL_ANY ); + int nnumber = fields_find( in, "NUMBER", LEVEL_ANY ); + int fstatus; + if ( nissue!=-1 && nnumber!=-1 ) { - output_and_use( fp, info, nissue, "issue", format_opts ); - output_and_use( fp, info, nnumber, "number", format_opts ); -/* output_element( fp, "issue", info->data[nissue].data, - format_opts ); - fields_setused( info, nissue ); - output_element( fp, "number", info->data[nnumber].data, - format_opts ); - fields_setused( info, nnumber );*/ + fields_setused( in, nissue ); + fields_setused( in, nnumber ); + fstatus = fields_add( out, "issue", fields_value( in, nissue, FIELDS_CHRP ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + *status = BIBL_ERR_MEMERR; + return; + } + fstatus = fields_add( out, "number", fields_value( in, nnumber, FIELDS_CHRP ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } else if ( nissue!=-1 ) { - output_and_use( fp, info, nissue, "number", format_opts ); -/* - output_element( fp, "number", info->data[nissue].data, - format_opts ); - fields_setused( info, nissue );*/ + fields_setused( in, nissue ); + fstatus = fields_add( out, "number", fields_value( in, nissue, FIELDS_CHRP ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } else if ( nnumber!=-1 ) { - output_and_use( fp, info, nnumber, "number", format_opts ); -/* - output_element( fp, "number", info->data[nnumber].data, - format_opts ); - fields_setused( info, nnumber ); -*/ + fields_setused( in, nnumber ); + fstatus = fields_add( out, "number", fields_value( in, nnumber, FIELDS_CHRP ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } } -void -bibtexout_write( fields *info, FILE *fp, param *p, unsigned long refnum ) +static int +append_data( fields *in, fields *out, param *p, unsigned long refnum ) { - int type; - fields_clearused( info ); - type = bibtexout_type( info, "", refnum, p ); - output_type( fp, type, p->format_opts ); - if ( !( p->format_opts & BIBOUT_DROPKEY ) ) - output_citekey( fp, info, refnum, p->format_opts ); - output_people( fp, info, refnum, "AUTHOR", "AUTHOR:CORP", "AUTHOR:ASIS", "author", 0, - p->format_opts ); - output_people( fp, info, refnum, "EDITOR", "EDITOR:CORP", "EDITOR:ASIS", "editor", -1, - p->format_opts ); - output_people( fp, info, refnum, "TRANSLATOR", "TRANSLATOR:CORP", "TRANSLATOR:ASIS", "translator", -1, p->format_opts ); + int type, status = BIBL_OK; - /* item=main level title */ - if ( type==TYPE_INBOOK ) - output_title( fp, info, refnum, "chapter", 0, p->format_opts ); - else - output_title( fp, info, refnum, "title", 0, p->format_opts ); + type = bibtexout_type( in, "", refnum, p ); - /* item=host level title */ - if ( type==TYPE_ARTICLE ) - output_title( fp, info, refnum, "journal", 1, p->format_opts ); - else if ( type==TYPE_INBOOK ) { - output_title( fp, info, refnum, "title", 1, p->format_opts ); - output_title( fp, info, refnum, "series", 2, p->format_opts ); - } - else if ( type==TYPE_INPROCEEDINGS || type==TYPE_INCOLLECTION ) { - output_title( fp, info, refnum, "booktitle", 1, p->format_opts ); - output_title( fp, info, refnum, "series", 2, p->format_opts ); - } - else if ( type==TYPE_PHDTHESIS || type==TYPE_MASTERSTHESIS ) { - output_title( fp, info, refnum, "series", 1, p->format_opts ); - } - else if ( type==TYPE_BOOK || type==TYPE_COLLECTION || type==TYPE_PROCEEDINGS || type==TYPE_REPORT ) { - output_title( fp, info, refnum, "series", 1, p->format_opts ); - output_title( fp, info, refnum, "series", 2, p->format_opts ); - } + append_type ( type, out, &status ); + append_citekey ( in, out, p->format_opts, &status ); + append_people ( in, "AUTHOR", "AUTHOR:CORP", "AUTHOR:ASIS", "author", 0, out, p->format_opts ); + append_people ( in, "EDITOR", "EDITOR:CORP", "EDITOR:ASIS", "editor", -1, out, p->format_opts ); + append_people ( in, "TRANSLATOR", "TRANSLATOR:CORP", "TRANSLATOR:ASIS", "translator", -1, out, p->format_opts ); + append_titles ( in, type, out, p->format_opts, &status ); + append_date ( in, out, &status ); + append_simple ( in, "EDITION", "edition", out, &status ); + append_simple ( in, "PUBLISHER", "publisher", out, &status ); + append_simple ( in, "ADDRESS", "address", out, &status ); + append_simple ( in, "VOLUME", "volume", out, &status ); + append_issue_number( in, out, &status ); + append_pages ( in, out, p->format_opts, &status ); + append_keywords ( in, out, &status ); + append_simple ( in, "CONTENTS", "contents", out, &status ); + append_simple ( in, "ABSTRACT", "abstract", out, &status ); + append_simple ( in, "LOCATION", "location", out, &status ); + append_simple ( in, "DEGREEGRANTOR", "school", out, &status ); + append_simple ( in, "DEGREEGRANTOR:ASIS", "school", out, &status ); + append_simple ( in, "DEGREEGRANTOR:CORP", "school", out, &status ); + append_simpleall ( in, "NOTES", "note", out, &status ); + append_simpleall ( in, "ANNOTE", "annote", out, &status ); + append_simple ( in, "ISBN", "isbn", out, &status ); + append_simple ( in, "ISSN", "issn", out, &status ); + append_simple ( in, "MRNUMBER", "mrnumber", out, &status ); + append_simple ( in, "CODEN", "coden", out, &status ); + append_simple ( in, "DOI", "doi", out, &status ); + append_urls ( in, out, &status ); + append_fileattach ( in, out, &status ); + append_arxiv ( in, out, &status ); + append_simple ( in, "EPRINTCLASS", "primaryClass", out, &status ); + append_isi ( in, out, &status ); + append_simple ( in, "LANGUAGE", "language", out, &status ); - output_date( fp, info, refnum, p->format_opts ); - output_simple( fp, info, "EDITION", "edition", p->format_opts ); - output_simple( fp, info, "PUBLISHER", "publisher", p->format_opts ); - output_simple( fp, info, "ADDRESS", "address", p->format_opts ); - output_simple( fp, info, "VOLUME", "volume", p->format_opts ); - output_issue_number( fp, info, p->format_opts ); -/* output_simple( fp, info, "ISSUE", "issue", p->format_opts ); - output_simple( fp, info, "NUMBER", "number", p->format_opts );s*/ - output_pages( fp, info, refnum, p->format_opts ); - output_keywords( fp, info, p->format_opts ); - output_simple( fp, info, "CONTENTS", "contents", p->format_opts ); - output_simple( fp, info, "ABSTRACT", "abstract", p->format_opts ); - output_simple( fp, info, "LOCATION", "location", p->format_opts ); - output_simple( fp, info, "DEGREEGRANTOR", "school", p->format_opts ); - output_simple( fp, info, "DEGREEGRANTOR:ASIS", "school", p->format_opts ); - output_simple( fp, info, "DEGREEGRANTOR:CORP", "school", p->format_opts ); - output_simpleall( fp, info, "NOTES", "note", p->format_opts ); - output_simpleall( fp, info, "ANNOTE", "annote", p->format_opts ); - output_simple( fp, info, "ISBN", "isbn", p->format_opts ); - output_simple( fp, info, "ISSN", "issn", p->format_opts ); - output_simple( fp, info, "DOI", "doi", p->format_opts ); - output_simpleall( fp, info, "URL", "url", p->format_opts ); - output_fileattach( fp, info, p->format_opts ); - output_arxiv( fp, info, p->format_opts ); - output_pmid( fp, info, p->format_opts ); - output_jstor( fp, info, p->format_opts ); - output_simple( fp, info, "LANGUAGE", "language", p->format_opts ); - if ( p->format_opts & BIBOUT_FINALCOMMA ) fprintf( fp, "," ); - fprintf( fp, "\n}\n\n" ); - fflush( fp ); + return status; } -void +static int +bibtexout_write( fields *in, FILE *fp, param *p, unsigned long refnum ) +{ + int status; + fields out; + + fields_init( &out ); + + status = append_data( in, &out, p, refnum ); + if ( status==BIBL_OK ) output( fp, &out, p->format_opts ); + + fields_free( &out ); + + return status; +} + +static void bibtexout_writeheader( FILE *outptr, param *p ) { if ( p->utf8bom ) utf8_writebom( outptr ); diff --git a/bibutils/bibtexout.h b/bibutils/bibtexout.h deleted file mode 100644 --- a/bibutils/bibtexout.h +++ /dev/null @@ -1,31 +0,0 @@ -/* - * bibtexout.h - * - * Copyright (c) Chris Putnam 2005-2013 - * - * Source code released under GPL version 2 - * - */ -#ifndef BIBTEXOUT_H -#define BIBTEXOUT_H - -#include -#include "fields.h" -#include "bibutils.h" - -/* bibtexout output options */ -#define BIBOUT_FINALCOMMA (2) -#define BIBOUT_SINGLEDASH (4) -#define BIBOUT_WHITESPACE (8) -#define BIBOUT_BRACKETS (16) -#define BIBOUT_UPPERCASE (32) -#define BIBOUT_STRICTKEY (64) -#define BIBOUT_SHORTTITLE (128) -#define BIBOUT_DROPKEY (256) - -extern void bibtexout_write( fields *info, FILE *fp, param *p, - unsigned long refnum ); -extern void bibtexout_writeheader( FILE *outptr, param *p ); -extern void bibtexout_initparams( param *p, const char *progname ); - -#endif diff --git a/bibutils/bibtextypes.c b/bibutils/bibtextypes.c --- a/bibutils/bibtextypes.c +++ b/bibutils/bibtextypes.c @@ -1,7 +1,7 @@ /* * bibtypes.c * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Program and source code released under the GPL version 2 * @@ -16,38 +16,44 @@ * Journal Article */ static lookups article[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "year", "PARTYEAR", SIMPLE, LEVEL_MAIN }, - { "month", "PARTMONTH", SIMPLE, LEVEL_MAIN }, - { "day", "PARTDAY", SIMPLE, LEVEL_MAIN }, - { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, - { "pages", "PAGES", PAGES, LEVEL_MAIN }, - { "number", "ISSUE", SIMPLE, LEVEL_MAIN }, - { "issue", "ISSUE", SIMPLE, LEVEL_MAIN }, - { "journal", "TITLE", TITLE, LEVEL_HOST }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, - { "address", "ADDRESS", SIMPLE, LEVEL_HOST }, - { "issn", "ISSN", SIMPLE, LEVEL_HOST }, - { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, - { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, - { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, - { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, - { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, - { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, - { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, - { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|ARTICLE", ALWAYS, LEVEL_MAIN }, + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, + { "title", "", TITLE, LEVEL_MAIN }, + { "year", "PARTDATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "PARTDATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "PARTDATE:DAY", SIMPLE, LEVEL_MAIN }, + { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, + { "pages", "PAGES", PAGES, LEVEL_MAIN }, + { "number", "ISSUE", SIMPLE, LEVEL_MAIN }, + { "issue", "ISSUE", SIMPLE, LEVEL_MAIN }, + { "journal", "", TITLE, LEVEL_HOST }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, + { "address", "ADDRESS", SIMPLE, LEVEL_HOST }, + { "issn", "ISSN", SIMPLE, LEVEL_HOST }, + { "coden", "CODEN", SIMPLE, LEVEL_HOST }, + { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, + { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, + { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, + { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, + { "pdf", "FILEATTACH", SIMPLE, LEVEL_MAIN }, + { "eprint", "", EPRINT, LEVEL_MAIN }, + { "archivePrefix","ARCHIVEPREFIX", SIMPLE, LEVEL_MAIN }, + { "eprintclass", "EPRINTCLASS", SIMPLE, LEVEL_MAIN }, + { "primaryClass", "EPRINTCLASS", SIMPLE, LEVEL_MAIN }, + { "sentelink", "FILEATTACH", BT_SENTE, LEVEL_MAIN }, + { "file", "FILEATTACH", LINKEDFILE, LEVEL_MAIN }, + { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, + { "mrnumber", "MRNUMBER", SIMPLE, LEVEL_MAIN }, + { "doi", "DOI", SIMPLE, LEVEL_MAIN }, + { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, + { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|ARTICLE", ALWAYS, LEVEL_MAIN }, { "", "ISSUANCE|continuing", ALWAYS, LEVEL_HOST }, { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { "", "NGENRE|journal article", ALWAYS, LEVEL_MAIN }, @@ -58,43 +64,43 @@ /* Book */ static lookups book[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "booktitle", "TITLE", TITLE, LEVEL_MAIN }, - { "series", "TITLE", TITLE, LEVEL_HOST }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "organization", "ORGANIZER:CORP", BT_ORG, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "editor", "EDITOR", PERSON, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, - { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, - { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, - { "lccn", "LCCN", SIMPLE, LEVEL_MAIN }, - { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, - { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, - { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, - { "type", "GENRE", SIMPLE, LEVEL_MAIN }, - { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, - { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, - { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, - { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, - { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, + { "title", "", TITLE, LEVEL_MAIN }, + { "booktitle", "", TITLE, LEVEL_MAIN }, + { "series", "", TITLE, LEVEL_HOST }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "organization", "ORGANIZER:CORP", BT_ORG, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "editor", "EDITOR", PERSON, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, + { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, + { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, + { "lccn", "LCCN", SIMPLE, LEVEL_MAIN }, + { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, + { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, + { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, + { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, + { "type", "GENRE", SIMPLE, LEVEL_MAIN }, + { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, + { "pdf", "FILEATTACH", SIMPLE, LEVEL_MAIN }, + { "sentelink", "FILEATTACH", BT_SENTE, LEVEL_MAIN }, + { "file", "FILEATTACH", LINKEDFILE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, + { "doi", "DOI", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, + { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, { "", "INTERNAL_TYPE|BOOK", ALWAYS, LEVEL_MAIN }, { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { "", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, @@ -104,39 +110,40 @@ /* Technical reports */ static lookups report[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "booktitle", "TITLE", TITLE, LEVEL_MAIN }, - { "series", "TITLE", TITLE, LEVEL_HOST }, - { "editor", "EDITOR", PERSON, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "institution", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, - { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, - { "lccn", "LCCN", SIMPLE, LEVEL_MAIN }, - { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, - { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, - { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, - { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, - { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, - { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, - { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, - { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, - { "type", "GENRE", SIMPLE, LEVEL_MAIN }, - { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, + { "title", "", TITLE, LEVEL_MAIN }, + { "booktitle", "", TITLE, LEVEL_MAIN }, + { "series", "", TITLE, LEVEL_HOST }, + { "editor", "EDITOR", PERSON, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "institution", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, + { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, + { "lccn", "LCCN", SIMPLE, LEVEL_MAIN }, + { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, + { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, + { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, + { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, + { "doi", "DOI", SIMPLE, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, + { "mrnumber", "MRNUMBER", SIMPLE, LEVEL_MAIN }, + { "pdf", "FILEATTACH", SIMPLE, LEVEL_MAIN }, + { "sentelink", "FILEATTACH", BT_SENTE, LEVEL_MAIN }, + { "file", "FILEATTACH", LINKEDFILE, LEVEL_MAIN }, + { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, + { "type", "GENRE", SIMPLE, LEVEL_MAIN }, + { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, { "", "INTERNAL_TYPE|REPORT", ALWAYS, LEVEL_MAIN }, { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { "", "GENRE|report", ALWAYS, LEVEL_MAIN } @@ -145,27 +152,27 @@ static lookups manual[] = { { "author", "AUTHOR", PERSON, LEVEL_MAIN }, { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "booktitle", "TITLE", TITLE, LEVEL_MAIN }, + { "title", "", TITLE, LEVEL_MAIN }, + { "booktitle", "", TITLE, LEVEL_MAIN }, { "editor", "EDITOR", PERSON, LEVEL_MAIN }, { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, { "organization", "ORGANIZER:CORP", BT_ORG, LEVEL_MAIN }, { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, { "lccn", "LCCN", SIMPLE, LEVEL_MAIN }, { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, @@ -182,65 +189,65 @@ /* Part of a book (e.g. chapter or section) */ static lookups inbook[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "editor", "EDITOR", PERSON, LEVEL_HOST }, - { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_HOST }, - { "booktitle", "TITLE", TITLE, LEVEL_HOST }, - { "series", "TITLE", TITLE, LEVEL_SERIES }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, - { "address", "ADDRESS", SIMPLE, LEVEL_HOST }, - { "year", "YEAR", SIMPLE, LEVEL_HOST }, - { "month", "MONTH", SIMPLE, LEVEL_HOST }, - { "day", "DAY", SIMPLE, LEVEL_HOST }, - { "volume", "VOLUME", SIMPLE, LEVEL_SERIES }, - { "number", "NUMBER", SIMPLE, LEVEL_SERIES }, - { "pages", "PAGES", PAGES, LEVEL_HOST }, - { "isbn", "ISBN", SIMPLE, LEVEL_HOST }, - { "lccn", "LCCN", SIMPLE, LEVEL_HOST }, - { "edition", "EDITION", SIMPLE, LEVEL_HOST }, - { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "contents", "CONTENTS", SIMPLE, LEVEL_HOST }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "location", "LOCATION", SIMPLE, LEVEL_HOST }, - { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "editor", "EDITOR", PERSON, LEVEL_HOST }, + { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, /* chapter number */ + { "title", "", TITLE, LEVEL_MAIN }, /* chapter name */ + { "booktitle", "", TITLE, LEVEL_HOST }, + { "series", "", TITLE, LEVEL_SERIES }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, + { "address", "ADDRESS", SIMPLE, LEVEL_HOST }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_HOST }, + { "month", "DATE:MONTH",SIMPLE, LEVEL_HOST }, + { "day", "DATE:DAY", SIMPLE, LEVEL_HOST }, + { "volume", "VOLUME", SIMPLE, LEVEL_SERIES }, + { "number", "NUMBER", SIMPLE, LEVEL_SERIES }, + { "pages", "PAGES", PAGES, LEVEL_HOST }, + { "isbn", "ISBN", SIMPLE, LEVEL_HOST }, + { "lccn", "LCCN", SIMPLE, LEVEL_HOST }, + { "edition", "EDITION", SIMPLE, LEVEL_HOST }, + { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, + { "contents", "CONTENTS", SIMPLE, LEVEL_HOST }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "location", "LOCATION", SIMPLE, LEVEL_HOST }, + { "doi", "DOI", SIMPLE, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, - { "type", "GENRE", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, + { "type", "GENRE", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|INBOOK", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { "", "ISSUANCE|monographic", ALWAYS, LEVEL_HOST }, - { "", "NGENRE|book chapter", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|book", ALWAYS, LEVEL_HOST } + { "", "INTERNAL_TYPE|INBOOK", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "ISSUANCE|monographic", ALWAYS, LEVEL_HOST }, + { "", "NGENRE|book chapter", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|book", ALWAYS, LEVEL_HOST } }; /* References of papers in conference proceedings */ static lookups inproceedings[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "editor", "EDITOR", PERSON, LEVEL_HOST }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "booktitle", "TITLE", TITLE, LEVEL_HOST }, - { "series", "TITLE", TITLE, LEVEL_SERIES }, - { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, + { "editor", "EDITOR", PERSON, LEVEL_HOST }, + { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, /* chapter number */ + { "title", "", TITLE, LEVEL_MAIN }, /* chapter name */ + { "booktitle", "", TITLE, LEVEL_HOST }, + { "series", "", TITLE, LEVEL_SERIES }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, { "organization", "ORGANIZER:CORP", BT_ORG, LEVEL_HOST }, { "address", "ADDRESS", SIMPLE, LEVEL_HOST }, - { "year", "PARTYEAR", SIMPLE, LEVEL_MAIN }, - { "month", "PARTMONTH", SIMPLE, LEVEL_MAIN }, - { "day", "PARTDAY", SIMPLE, LEVEL_MAIN }, + { "year", "PARTDATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "PARTDATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "PARTDATE:DAY", SIMPLE, LEVEL_MAIN }, { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, { "pages", "PAGES", PAGES, LEVEL_MAIN }, @@ -252,13 +259,13 @@ { "paper", "PAPER", SIMPLE, LEVEL_MAIN }, { "location", "LOCATION", SIMPLE, LEVEL_HOST }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, { "type", "GENRE", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, @@ -273,18 +280,18 @@ /* Used for a section of a book with its own title */ static lookups incollection[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "editor", "EDITOR", PERSON, LEVEL_HOST }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, - { "booktitle", "TITLE", TITLE, LEVEL_HOST }, - { "series", "TITLE", TITLE, LEVEL_SERIES }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, + { "editor", "EDITOR", PERSON, LEVEL_HOST }, + { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, /* chapter number */ + { "title", "", TITLE, LEVEL_MAIN }, /* chapter name */ + { "booktitle", "", TITLE, LEVEL_HOST }, + { "series", "", TITLE, LEVEL_SERIES }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, { "address", "ADDRESS", SIMPLE, LEVEL_HOST }, - { "year", "YEAR", SIMPLE, LEVEL_HOST }, - { "month", "MONTH", SIMPLE, LEVEL_HOST }, - { "day", "DAY", SIMPLE, LEVEL_HOST }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_HOST }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_HOST }, + { "day", "DATE:DAY", SIMPLE, LEVEL_HOST }, { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, { "pages", "PAGES", PAGES, LEVEL_MAIN }, @@ -293,17 +300,17 @@ { "edition", "EDITION", SIMPLE, LEVEL_HOST }, { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "contents", "CONTENTS", SIMPLE, LEVEL_HOST }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "type", "GENRE", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, - { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, - { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "type", "GENRE", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, + { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, + { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, - { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, - { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, - { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, + { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, + { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, + { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, { "location", "LOCATION", SIMPLE, LEVEL_HOST }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, @@ -321,15 +328,15 @@ { "author", "AUTHOR", PERSON, LEVEL_MAIN }, { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "editor", "EDITOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "booktitle", "TITLE", TITLE, LEVEL_MAIN }, - { "series", "TITLE", TITLE, LEVEL_HOST }, + { "title", "", TITLE, LEVEL_MAIN }, + { "booktitle", "", TITLE, LEVEL_MAIN }, + { "series", "", TITLE, LEVEL_HOST }, { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, { "organization", "ORGANIZER:CORP", BT_ORG, LEVEL_MAIN }, { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, { "pages", "PAGES", PAGES, LEVEL_MAIN }, @@ -338,15 +345,15 @@ { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, @@ -360,24 +367,24 @@ static lookups phds[] = { { "author", "AUTHOR", PERSON, LEVEL_MAIN }, { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, + { "title", "", TITLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, { "school", "DEGREEGRANTOR:ASIS",SIMPLE, LEVEL_MAIN }, { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, { "howpublished", "" , HOWPUBLISHED, LEVEL_MAIN }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, { "type", "GENRE", SIMPLE, LEVEL_MAIN }, @@ -393,23 +400,23 @@ static lookups masters[] = { { "author", "AUTHOR", PERSON, LEVEL_MAIN }, { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, + { "title", "", TITLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, { "school", "DEGREEGRANTOR:ASIS",SIMPLE, LEVEL_MAIN }, { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, { "type", "GENRE", SIMPLE, LEVEL_MAIN }, @@ -428,26 +435,26 @@ static lookups unpublished[] = { { "author", "AUTHOR", PERSON, LEVEL_MAIN }, { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "booktitle", "TITLE", TITLE, LEVEL_MAIN }, + { "title", "", TITLE, LEVEL_MAIN }, + { "booktitle", "", TITLE, LEVEL_MAIN }, { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "editor", "EDITOR", PERSON, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, @@ -466,32 +473,32 @@ { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "organization", "ORGANIZER:CORP", BT_ORG, LEVEL_MAIN }, { "institution", "AUTHOR:CORP", SIMPLE, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "booktitle", "TITLE", TITLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "editor", "EDITOR", PERSON, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, - { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, - { "lccn", "LCCN", SIMPLE, LEVEL_MAIN }, - { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, - { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, - { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, - { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, + { "title", "", TITLE, LEVEL_MAIN }, + { "booktitle", "", TITLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "editor", "EDITOR", PERSON, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, + { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, + { "lccn", "LCCN", SIMPLE, LEVEL_MAIN }, + { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, + { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, + { "doi", "DOI", SIMPLE, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, + { "pdf", "FILEATTACH", SIMPLE, LEVEL_MAIN }, + { "sentelink", "FILEATTACH", BT_SENTE, LEVEL_MAIN }, { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, { "type", "GENRE", SIMPLE, LEVEL_MAIN }, - { "number", "NUMBER", TITLE, LEVEL_MAIN }, - { "revision", "REVISION", TITLE, LEVEL_MAIN }, + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, + { "revision", "EDITION", SIMPLE, LEVEL_MAIN }, { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, @@ -504,30 +511,31 @@ * For Journals and Magazines */ static lookups periodical[] = { - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "series", "TITLE", TITLE, LEVEL_HOST }, + { "title", "", TITLE, LEVEL_MAIN }, + { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, + { "series", "", TITLE, LEVEL_HOST }, { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "editor", "EDITOR", PERSON, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, { "issn", "ISSN", SIMPLE, LEVEL_MAIN }, + { "coden", "CODEN", SIMPLE, LEVEL_MAIN }, { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "volume", "VOLUME", TITLE, LEVEL_MAIN }, - { "number", "NUMBER", TITLE, LEVEL_MAIN }, + { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, - { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, - { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, - { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, - { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, + { "pdf", "FILEATTACH", SIMPLE, LEVEL_MAIN }, + { "sentelink", "FILEATTACH", BT_SENTE, LEVEL_MAIN }, + { "file", "FILEATTACH", LINKEDFILE, LEVEL_MAIN }, + { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, { "organization", "ORGANIZER:CORP", BT_ORG, LEVEL_MAIN }, { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, @@ -540,38 +548,38 @@ * For Patent */ static lookups patent[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "assignee", "ASSIGNEE", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "editor", "EDITOR", PERSON, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, /* date granted */ - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, - { "yearfiled", "YEAR", SIMPLE, LEVEL_MAIN }, /* date filed */ - { "monthfiled","MONTH", SIMPLE, LEVEL_MAIN }, - { "dayfiled", "DAY", SIMPLE, LEVEL_MAIN }, - { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "nationality", "NATIONALITY", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, - { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, - { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, - { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, - { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, - { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, - { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, - { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "type", "GENRE", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, - { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, + { "assignee", "ASSIGNEE", PERSON, LEVEL_MAIN }, + { "title", "", TITLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "editor", "EDITOR", PERSON, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, /* date granted */ + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, + { "yearfiled", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, /* date filed */ + { "monthfiled", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "dayfiled", "DATE:DAY", SIMPLE, LEVEL_MAIN }, + { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, + { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, + { "nationality", "NATIONALITY", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, + { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, + { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, + { "doi", "DOI", SIMPLE, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, + { "pdf", "FILEATTACH", SIMPLE, LEVEL_MAIN }, + { "sentelink", "FILEATTACH", BT_SENTE, LEVEL_MAIN }, + { "file", "FILEATTACH", LINKEDFILE, LEVEL_MAIN }, + { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, + { "type", "GENRE", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, + { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { "", "INTERNAL_TYPE|PATENT", ALWAYS, LEVEL_MAIN }, { "", "GENRE|patent", ALWAYS, LEVEL_MAIN }, @@ -581,70 +589,70 @@ * Electronic Source */ static lookups electronic[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "organization", "ORGANIZER:CORP", BT_ORG, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "booktitle", "TITLE", TITLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "editor", "EDITOR", PERSON, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, - { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, - { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, - { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, - { "pdf", "FILEATTACH",SIMPLE, LEVEL_MAIN }, - { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, - { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, - { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, - { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, - { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, - { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, + { "organization", "ORGANIZER:CORP", BT_ORG, LEVEL_MAIN }, + { "title", "", TITLE, LEVEL_MAIN }, + { "booktitle", "", TITLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "editor", "EDITOR", PERSON, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, + { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, + { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, + { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, + { "doi", "DOI", SIMPLE, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, + { "pdf", "FILEATTACH", SIMPLE, LEVEL_MAIN }, + { "sentelink", "FILEATTACH", BT_SENTE, LEVEL_MAIN }, + { "file", "FILEATTACH", LINKEDFILE, LEVEL_MAIN }, + { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, + { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, + { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, + { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, { "", "RESOURCE|software, multimedia", ALWAYS, LEVEL_MAIN }, { "", "GENRE|electronic", ALWAYS, LEVEL_MAIN }, }; static lookups misc[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "translator", "TRANSLATOR",PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "booktitle", "TITLE", TITLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "organization", "ORGANIZER:CORP", BT_ORG, LEVEL_MAIN }, - { "pages", "PAGES", PAGES, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "editor", "EDITOR", PERSON, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, - { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, - { "doi", "DOI", SIMPLE, LEVEL_MAIN }, - { "ftp", "", BT_URL, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, - { "pdf", "FILEATTACH", SIMPLE, LEVEL_MAIN }, - { "sentelink", "FILEATTACH",BT_SENTE, LEVEL_MAIN }, - { "file", "FILEATTACH",LINKEDFILE, LEVEL_MAIN }, - { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, - { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", BT_NOTE, LEVEL_MAIN }, - { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, - { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|MISC", ALWAYS, LEVEL_MAIN }, + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, + { "title", "", TITLE, LEVEL_MAIN }, + { "booktitle", "", TITLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "organization", "ORGANIZER:CORP", BT_ORG, LEVEL_MAIN }, + { "pages", "PAGES", PAGES, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "editor", "EDITOR", PERSON, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, + { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, + { "contents", "CONTENTS", SIMPLE, LEVEL_MAIN }, + { "doi", "DOI", SIMPLE, LEVEL_MAIN }, + { "ftp", "", URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, + { "pdf", "FILEATTACH", SIMPLE, LEVEL_MAIN }, + { "sentelink", "FILEATTACH", BT_SENTE, LEVEL_MAIN }, + { "file", "FILEATTACH", LINKEDFILE, LEVEL_MAIN }, + { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "crossref", "CROSSREF", SIMPLE, LEVEL_MAIN }, + { "location", "LOCATION", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, + { "annote", "ANNOTE", SIMPLE, LEVEL_MAIN }, + { "key", "BIBKEY", SIMPLE, LEVEL_MAIN }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "keywords", "KEYWORD", KEYWORD, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|MISC", ALWAYS, LEVEL_MAIN }, }; #define ORIG(a) ( &(a[0]) ) diff --git a/bibutils/bibutils.c b/bibutils/bibutils.c --- a/bibutils/bibutils.c +++ b/bibutils/bibutils.c @@ -1,7 +1,7 @@ /* * bibutils.c * - * Copyright (c) Chris Putnam 2005-2013 + * Copyright (c) Chris Putnam 2005-2017 * * Source code released under the GPL version 2 * @@ -9,26 +9,7 @@ #include #include #include "bibutils.h" - -/* bibl format includes */ -#include "adsout.h" -#include "biblatexin.h" -#include "bibtexin.h" -#include "bibtexout.h" -#include "copacin.h" -#include "ebiin.h" -#include "endin.h" -#include "endxmlin.h" -#include "endout.h" -#include "isiin.h" -#include "isiout.h" -#include "medin.h" -#include "modsin.h" -#include "modsout.h" -#include "risin.h" -#include "risout.h" -#include "wordin.h" -#include "wordout.h" +#include "bibformats.h" void bibl_initparams( param *p, int readmode, int writemode, char *progname ) diff --git a/bibutils/bibutils.h b/bibutils/bibutils.h --- a/bibutils/bibutils.h +++ b/bibutils/bibutils.h @@ -1,7 +1,7 @@ /* * bibutils.h * - * Copyright (c) Chris Putnam 2005-2014 + * Copyright (c) Chris Putnam 2005-2017 * * Source code released under GPL version 2 * @@ -15,9 +15,9 @@ #include #include "bibl.h" -#include "list.h" +#include "slist.h" #include "charsets.h" -#include "newstr_conv.h" +#include "str_conv.h" #define BIBL_OK (0) #define BIBL_ERR_BADINPUT (-1) @@ -36,7 +36,8 @@ #define BIBL_BIBLATEXIN (BIBL_FIRSTIN+8) #define BIBL_EBIIN (BIBL_FIRSTIN+9) #define BIBL_WORDIN (BIBL_FIRSTIN+10) -#define BIBL_LASTIN (BIBL_FIRSTIN+10) +#define BIBL_NBIBIN (BIBL_FIRSTIN+11) +#define BIBL_LASTIN (BIBL_FIRSTIN+11) #define BIBL_FIRSTOUT (200) #define BIBL_MODSOUT (BIBL_FIRSTOUT) @@ -48,7 +49,16 @@ #define BIBL_ADSABSOUT (BIBL_FIRSTOUT+6) #define BIBL_LASTOUT (BIBL_FIRSTOUT+6) -#define BIBL_FORMAT_VERBOSE (1) +#define BIBL_FORMAT_VERBOSE (1) +#define BIBL_FORMAT_BIBOUT_FINALCOMMA (2) +#define BIBL_FORMAT_BIBOUT_SINGLEDASH (4) +#define BIBL_FORMAT_BIBOUT_WHITESPACE (8) +#define BIBL_FORMAT_BIBOUT_BRACKETS (16) +#define BIBL_FORMAT_BIBOUT_UPPERCASE (32) +#define BIBL_FORMAT_BIBOUT_STRICTKEY (64) +#define BIBL_FORMAT_BIBOUT_SHORTTITLE (128) +#define BIBL_FORMAT_BIBOUT_DROPKEY (256) +#define BIBL_FORMAT_MODSOUT_DROPKEY (512) #define BIBL_RAW_WITHCHARCONVERT (4) #define BIBL_RAW_WITHMAKEREFID (8) @@ -64,9 +74,9 @@ #define BIBL_SRC_FILE (1) /* value from file, priority over default */ #define BIBL_SRC_USER (2) /* value from user, priority over file, default */ -#define BIBL_XMLOUT_FALSE NEWSTR_CONV_XMLOUT_FALSE -#define BIBL_XMLOUT_TRUE NEWSTR_CONV_XMLOUT_TRUE -#define BIBL_XMLOUT_ENTITIES NEWSTR_CONV_XMLOUT_ENTITIES +#define BIBL_XMLOUT_FALSE STR_CONV_XMLOUT_FALSE +#define BIBL_XMLOUT_TRUE STR_CONV_XMLOUT_TRUE +#define BIBL_XMLOUT_ENTITIES STR_CONV_XMLOUT_ENTITIES typedef unsigned char uchar; @@ -95,20 +105,20 @@ uchar verbose; uchar singlerefperfile; - list asis; /* Names that shouldn't be mangled */ - list corps; /* Names that shouldn't be mangled-MODS corporation type */ + slist asis; /* Names that shouldn't be mangled */ + slist corps; /* Names that shouldn't be mangled-MODS corporation type */ char *progname; - int (*readf)(FILE*,char*,int,int*,newstr*,newstr*,int*); - int (*processf)(fields*,char*,char*,long); + int (*readf)(FILE*,char*,int,int*,str*,str*,int*); + int (*processf)(fields*,char*,char*,long,struct param*); int (*cleanf)(bibl*,struct param*); - int (*typef) (fields*,char*,int,struct param*,variants*,int); - int (*convertf)(fields*,fields*,int,struct param*,variants*,int); + int (*typef) (fields*,char*,int,struct param*); + int (*convertf)(fields*,fields*,int,struct param*); void (*headerf)(FILE*,struct param*); void (*footerf)(FILE*); - void (*writef)(fields*,FILE*,struct param*,unsigned long); + int (*writef)(fields*,FILE*,struct param*,unsigned long); variants *all; int nall; diff --git a/bibutils/bltypes.c b/bibutils/bltypes.c --- a/bibutils/bltypes.c +++ b/bibutils/bltypes.c @@ -1,8 +1,8 @@ /* * bltypes.c * - * Copyright (c) Chris Putnam 2008-2013 - * Copyright (c) Johannes Wilm 2010-2013 + * Copyright (c) Chris Putnam 2008-2017 + * Copyright (c) Johannes Wilm 2010-2017 * * Program and source code released under the GPL version 2 * @@ -47,7 +47,7 @@ { "issuesubtitle", "SUBTITLE", TITLE, LEVEL_SERIES }, /*WRONG*/ { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origyear", "DATE:YEAR", SIMPLE, LEVEL_ORIG }, { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, @@ -58,22 +58,23 @@ { "eid", "EID", SIMPLE, LEVEL_MAIN }, { "issue", "ISSUE", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ - { "day", "PARTDAY", SIMPLE, LEVEL_MAIN }, - { "month", "PARTMONTH", SIMPLE, LEVEL_MAIN }, - { "year", "PARTYEAR", SIMPLE, LEVEL_MAIN }, + { "day", "PARTDATE:DAY", SIMPLE, LEVEL_MAIN }, + { "month", "PARTDATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "PARTDATE:YEAR", SIMPLE, LEVEL_MAIN }, { "pages", "PAGES", PAGES, LEVEL_MAIN }, { "version", "EDITION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "issn", "ISSN", SIMPLE, LEVEL_HOST }, + { "coden", "CODEN", SIMPLE, LEVEL_HOST }, { "abstract", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, /* WRONG */ { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, /* WRONG */ @@ -120,11 +121,11 @@ { "mainsubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origyear", "DATE:YEAR", SIMPLE, LEVEL_ORIG }, { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, @@ -135,7 +136,7 @@ { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, { "series", "TITLE", SIMPLE, LEVEL_HOST }, /* WRONG */ { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, @@ -143,13 +144,13 @@ { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, { "pages", "PAGES", PAGES, LEVEL_MAIN }, /* WRONG */ - { "pagetotal", "TOTALPAGES", SIMPLE, LEVEL_MAIN }, + { "pagetotal", "PAGES:TOTAL", SIMPLE, LEVEL_MAIN }, { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, @@ -184,25 +185,25 @@ { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, { "pages", "PAGES", PAGES, LEVEL_MAIN }, - { "pagetotal", "TOTALPAGES", SIMPLE, LEVEL_MAIN }, + { "pagetotal", "PAGES:TOTAL", SIMPLE, LEVEL_MAIN }, { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, @@ -233,8 +234,8 @@ { "annotator", "ANNOTATOR", PERSON, LEVEL_MAIN }, { "commentator", "COMMENTATOR", PERSON, LEVEL_MAIN }, { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "introduction", "INTROAUTHOR", PERSON, LEVEL_MAIN }, { "foreword", "INTROAUTHOR", PERSON, LEVEL_MAIN }, @@ -248,7 +249,7 @@ { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origyear", "DATE:YEAR", SIMPLE, LEVEL_ORIG }, { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, @@ -259,7 +260,7 @@ { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, { "series", "TITLE", SIMPLE, LEVEL_HOST }, { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, @@ -267,13 +268,13 @@ { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, { "pages", "PAGES", PAGES, LEVEL_MAIN }, - { "pagetotal", "TOTALPAGES", SIMPLE, LEVEL_MAIN }, + { "pagetotal", "PAGES:TOTAL", SIMPLE, LEVEL_MAIN }, { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, @@ -307,8 +308,8 @@ { "annotator", "ANNOTATOR", PERSON, LEVEL_HOST }, { "commentator", "COMMENTATOR", PERSON, LEVEL_HOST }, { "translator", "TRANSLATOR", PERSON, LEVEL_HOST }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "introduction", "INTROAUTHOR", PERSON, LEVEL_HOST }, { "foreword", "INTROAUTHOR", PERSON, LEVEL_HOST }, @@ -326,7 +327,7 @@ { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_SERIES }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origyear", "DATE:YEAR", SIMPLE, LEVEL_ORIG }, { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, @@ -338,7 +339,7 @@ { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, { "series", "TITLE", SIMPLE, LEVEL_SERIES+1 }, /* WRONG */ { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, @@ -350,7 +351,7 @@ { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, @@ -369,8 +370,8 @@ static lookups incollection[] = { { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "title", "TITLE", TITLE, LEVEL_MAIN }, { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, @@ -379,7 +380,7 @@ { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "introduction", "INTROAUTHOR", PERSON, LEVEL_HOST }, @@ -416,7 +417,7 @@ { "series", "TITLE", SIMPLE, LEVEL_SERIES+1 }, /* WRONG */ { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origyear", "DATE:YEAR", SIMPLE, LEVEL_ORIG }, { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, @@ -432,7 +433,7 @@ { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, @@ -467,8 +468,8 @@ { "commentator", "COMMENTATOR", PERSON, LEVEL_HOST }, { "translator", "TRANSLATOR", PERSON, LEVEL_HOST }, { "eventtitle", "EVENT:CONF", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "introduction", "INTROAUTHOR", PERSON, LEVEL_HOST }, { "foreword", "INTROAUTHOR", PERSON, LEVEL_HOST }, @@ -493,7 +494,7 @@ { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origyear", "DATE:YEAR", SIMPLE, LEVEL_ORIG }, { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, @@ -502,7 +503,7 @@ { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, @@ -515,7 +516,7 @@ { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, @@ -547,8 +548,8 @@ { "annotator", "ANNOTATOR", PERSON, LEVEL_MAIN }, { "commentator", "COMMENTATOR", PERSON, LEVEL_MAIN }, { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "introduction", "INTROAUTHOR", PERSON, LEVEL_MAIN }, { "foreword", "INTROAUTHOR", PERSON, LEVEL_MAIN }, @@ -563,7 +564,7 @@ { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, { "series", "TITLE", SIMPLE, LEVEL_HOST }, { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, @@ -572,13 +573,13 @@ { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, { "pages", "PAGES", PAGES, LEVEL_MAIN }, - { "pagetotal", "TOTALPAGES", SIMPLE, LEVEL_MAIN }, + { "pagetotal", "PAGES:TOTAL", SIMPLE, LEVEL_MAIN }, { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, @@ -609,15 +610,15 @@ { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, { "version", "EDITION", SIMPLE, LEVEL_MAIN }, { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, @@ -629,7 +630,7 @@ { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, @@ -658,13 +659,13 @@ { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "version", "EDITION", SIMPLE, LEVEL_MAIN }, { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, @@ -675,7 +676,7 @@ { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, @@ -695,19 +696,19 @@ { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "version", "EDITION", SIMPLE, LEVEL_MAIN }, { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, @@ -753,20 +754,21 @@ { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, { "issue", "ISSUE", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ - { "day", "PARTDAY", SIMPLE, LEVEL_MAIN }, - { "month", "PARTMONTH", SIMPLE, LEVEL_MAIN }, - { "year", "PARTYEAR", SIMPLE, LEVEL_MAIN }, + { "day", "PARTDATE:DAY", SIMPLE, LEVEL_MAIN }, + { "month", "PARTDATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "PARTDATE:YEAR", SIMPLE, LEVEL_MAIN }, { "pages", "PAGES", PAGES, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "issn", "ISSN", SIMPLE, LEVEL_HOST }, + { "coden", "CODEN", SIMPLE, LEVEL_HOST }, { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?????", SIMPLE, LEVEL_MAIN }, /* WRONG */ { "urlmonth", "?????", SIMPLE, LEVEL_MAIN }, /* WRONG */ @@ -798,8 +800,8 @@ { "commentator", "COMMENTATOR", PERSON, LEVEL_MAIN }, { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, { "eventtitle", "EVENT:CONF", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "introduction", "INTROAUTHOR", PERSON, LEVEL_MAIN }, { "foreword", "INTROAUTHOR", PERSON, LEVEL_MAIN }, @@ -814,7 +816,7 @@ { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origyear", "DATE:YEAR", SIMPLE, LEVEL_ORIG }, { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, @@ -824,7 +826,7 @@ { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, { "series", "TITLE", SIMPLE, LEVEL_SERIES }, { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, @@ -833,13 +835,13 @@ { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, { "pages", "PAGES", SIMPLE, LEVEL_MAIN }, - { "pagetotal", "TOTALPAGES", SIMPLE, LEVEL_MAIN }, + { "pagetotal", "PAGES:TOTAL", SIMPLE, LEVEL_MAIN }, { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, @@ -862,12 +864,12 @@ { "series", "TITLE", TITLE, LEVEL_HOST }, { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, { "institution", "SPONSOR:ASIS", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "number", "REPORTNUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "version", "EDITION", SIMPLE, LEVEL_MAIN }, @@ -875,13 +877,13 @@ { "isrn", "ISRN", SIMPLE, LEVEL_MAIN }, { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, { "pages", "PAGES", SIMPLE, LEVEL_MAIN }, - { "pagetotal", "TOTALPAGES", SIMPLE, LEVEL_MAIN }, + { "pagetotal", "PAGES:TOTAL", SIMPLE, LEVEL_MAIN }, { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, { "eprint", "", BT_EPRINT, LEVEL_MAIN }, { "eprinttype", "", BT_EPRINT, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, @@ -902,16 +904,16 @@ { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, @@ -930,23 +932,23 @@ { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "type", "", BLT_THESIS_TYPE, LEVEL_MAIN }, { "institution", "DEGREEGRANTOR:ASIS", SIMPLE, LEVEL_MAIN }, { "school", "DEGREEGRANTOR:ASIS", BLT_SCHOOL, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, @@ -964,23 +966,23 @@ { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "type", "", BLT_THESIS_TYPE, LEVEL_MAIN }, { "institution", "DEGREEGRANTOR:ASIS", SIMPLE, LEVEL_MAIN }, { "school", "DEGREEGRANTOR:ASIS", BLT_SCHOOL, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, @@ -999,23 +1001,23 @@ { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "day", "DAY", SIMPLE, LEVEL_MAIN }, + { "year", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, + { "day", "DATE:DAY", SIMPLE, LEVEL_MAIN }, { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ { "type", "", BLT_THESIS_TYPE, LEVEL_MAIN }, { "institution", "DEGREEGRANTOR:ASIS", SIMPLE, LEVEL_MAIN }, { "school", "DEGREEGRANTOR:ASIS", BLT_SCHOOL, LEVEL_MAIN }, { "doi", "DOI", SIMPLE, LEVEL_MAIN }, { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "url", "", BT_URL, LEVEL_MAIN }, + { "url", "", URL, LEVEL_MAIN }, { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", NOTES, LEVEL_MAIN }, { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, diff --git a/bibutils/charsets.c b/bibutils/charsets.c --- a/bibutils/charsets.c +++ b/bibutils/charsets.c @@ -1,7 +1,7 @@ /* * charsets.c * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/charsets.h b/bibutils/charsets.h --- a/bibutils/charsets.h +++ b/bibutils/charsets.h @@ -1,7 +1,7 @@ /* * charsets.h * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/copacin.c b/bibutils/copacin.c --- a/bibutils/copacin.c +++ b/bibutils/copacin.c @@ -1,7 +1,7 @@ /* * copacin.c * - * Copyright (c) Chris Putnam 2004-2014 + * Copyright (c) Chris Putnam 2004-2017 * * Program and source code released under the GPL version 2 * @@ -10,19 +10,26 @@ #include #include #include "is_ws.h" -#include "newstr.h" -#include "newstr_conv.h" -#include "list.h" +#include "str.h" +#include "str_conv.h" +#include "slist.h" #include "name.h" -#include "title.h" #include "fields.h" #include "reftypes.h" -#include "serialno.h" -#include "copacin.h" +#include "bibformats.h" +#include "generic.h" +extern variants copac_all[]; +extern int copac_nall; + /***************************************************** PUBLIC: void copacin_initparams() *****************************************************/ + +static int copacin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int copacin_processf( fields *bibin, char *p, char *filename, long nref, param *pm ); +static int copacin_convertf( fields *bibin, fields *info, int reftype, param *pm ); + void copacin_initparams( param *p, const char *progname ) { @@ -45,8 +52,8 @@ p->all = copac_all; p->nall = copac_nall; - list_init( &(p->asis) ); - list_init( &(p->corps) ); + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); if ( !progname ) p->progname = NULL; else p->progname = strdup( progname ); @@ -74,14 +81,14 @@ return 1; } static int -readmore( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line ) +readmore( FILE *fp, char *buf, int bufsize, int *bufpos, str *line ) { if ( line->len ) return 1; - else return newstr_fget( fp, buf, bufsize, bufpos, line ); + else return str_fget( fp, buf, bufsize, bufpos, line ); } -int -copacin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ) +static int +copacin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) { int haveref = 0, inref=0; char *p; @@ -100,22 +107,22 @@ p += 3; } if ( copacin_istag( p ) ) { - if ( inref ) newstr_addchar( reference, '\n' ); - newstr_strcat( reference, p ); - newstr_empty( line ); + if ( inref ) str_addchar( reference, '\n' ); + str_strcatc( reference, p ); + str_empty( line ); inref = 1; } else if ( inref ) { if ( p ) { /* copac puts tag only on 1st line */ - newstr_addchar( reference, ' ' ); + str_addchar( reference, ' ' ); if ( *p ) p++; if ( *p ) p++; if ( *p ) p++; - newstr_strcat( reference, p ); + str_strcatc( reference, p ); } - newstr_empty( line ); + str_empty( line ); } else { - newstr_empty( line ); + str_empty( line ); } } return haveref; @@ -126,20 +133,20 @@ *****************************************************/ static char* -copacin_addtag2( char *p, newstr *tag, newstr *data ) +copacin_addtag2( char *p, str *tag, str *data ) { int i; i =0; while ( i<3 && *p ) { - newstr_addchar( tag, *p++ ); + str_addchar( tag, *p++ ); i++; } while ( *p==' ' || *p=='\t' ) p++; while ( *p && *p!='\r' && *p!='\n' ) { - newstr_addchar( data, *p ); + str_addchar( data, *p ); p++; } - newstr_trimendingws( data ); + str_trimendingws( data ); while ( *p=='\n' || *p=='\r' ) p++; return p; } @@ -152,29 +159,29 @@ return p; } -int -copacin_processf( fields *copacin, char *p, char *filename, long nref ) +static int +copacin_processf( fields *copacin, char *p, char *filename, long nref, param *pm ) { - newstr tag, data; + str tag, data; int status; - newstr_init( &tag ); - newstr_init( &data ); + str_init( &tag ); + str_init( &data ); while ( *p ) { p = skip_ws( p ); if ( copacin_istag( p ) ) { p = copacin_addtag2( p, &tag, &data ); /* don't add empty strings */ - if ( tag.len && data.len ) { + if ( str_has_value( &tag ) && str_has_value( &data ) ) { status = fields_add( copacin, tag.data, data.data, 0 ); if ( status!=FIELDS_OK ) return 0; } - newstr_empty( &tag ); - newstr_empty( &data ); + str_empty( &tag ); + str_empty( &data ); } else p = copacin_nextline( p ); } - newstr_free( &tag ); - newstr_free( &data ); + str_free( &tag ); + str_free( &data ); return 1; } @@ -188,48 +195,54 @@ * editors seem to be stuck in as authors with the tag "[Editor]" in it */ static int -copacin_addname( fields *info, char *tag, newstr *name, int level, list *asis, - list *corps ) +copacin_person( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) { - char *usetag = tag, editor[]="EDITOR"; - newstr usename, *s; - list tokens; - int comma = 0, i, ok; + char *usetag = outtag, editor[]="EDITOR"; + int comma = 0, i, ok, status; + str usename, *s; + slist tokens; - if ( list_find( asis, name->data ) !=-1 || - list_find( corps, name->data ) !=-1 ) { - ok = name_add( info, tag, name->data, level, asis, corps ); + if ( slist_find( &(pm->asis), invalue ) !=-1 || + slist_find( &(pm->corps), invalue ) !=-1 ) { + ok = name_add( bibout, outtag, invalue->data, level, &(pm->asis), &(pm->corps) ); if ( ok ) return BIBL_OK; else return BIBL_ERR_MEMERR; } - list_init( &tokens ); - newstr_init( &usename ); + slist_init( &tokens ); + str_init( &usename ); - list_tokenize( &tokens, name, " ", 1 ); + status = slist_tokenize( &tokens, invalue, " ", 1 ); + if ( status!=SLIST_OK ) return BIBL_ERR_MEMERR; + for ( i=0; idata, "[Editor]" ) ) { + s = slist_str( &tokens, i ); + if ( !strcmp( str_cstr( s ), "[Editor]" ) ) { usetag = editor; - newstr_strcpy( s, "" ); + str_empty( s ); } else if ( s->len && s->data[s->len-1]==',' ) { comma++; } } if ( comma==0 && tokens.n ) { - s = list_get( &tokens, 0 ); - newstr_addchar( s, ',' ); + s = slist_str( &tokens, 0 ); + str_addchar( s, ',' ); } for ( i=0; iasis), &(pm->corps) ); + + str_free( &usename ); + if ( ok ) return BIBL_OK; else return BIBL_ERR_MEMERR; } @@ -244,66 +257,37 @@ } static int -copacin_simple( fields *out, char *tag, char *value, int level ) +copacin_convertf( fields *bibin, fields *bibout, int reftype, param *p ) { - int fstatus = fields_add( out, tag, value, level ); - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} + static int (*convertfns[NUM_REFTYPES])(fields *, int, str *, str *, int, param *, char *, fields *) = { + [ 0 ... NUM_REFTYPES-1 ] = generic_null, + [ SIMPLE ] = generic_simple, + [ TITLE ] = generic_title, + [ NOTES ] = generic_notes, + [ SERIALNO ] = generic_serialno, + [ PERSON ] = copacin_person + }; -int -copacin_convertf( fields *copacin, fields *out, int reftype, param *p, variants *all, int nall ) -{ - int process, level, i, n, nfields, ok, status = BIBL_OK; - newstr *tag, *data; - char *newtag; + int process, level, i, nfields, status = BIBL_OK; + str *intag, *invalue; + char *outtag; - nfields = fields_num( copacin ); + nfields = fields_num( bibin ); for ( i=0; idata, reftype, all, nall, &process, &level, &newtag ); - if ( n==-1 ) { - copacin_report_notag( p, tag->data ); + if ( !translate_oldtag( intag->data, reftype, p->all, p->nall, &process, &level, &outtag ) ) { + copacin_report_notag( p, intag->data ); continue; } - if ( process == ALWAYS ) continue; /*add these later*/ - data = fields_value( copacin, i, FIELDS_STRP ); - - switch ( process ) { - - case SIMPLE: - status = copacin_simple( out, newtag, data->data, level ); - break; - - case TITLE: - ok = title_process( out, newtag, data->data, level, p->nosplittitle ); - if ( ok ) status = BIBL_OK; - else status = BIBL_ERR_MEMERR; - break; - - case PERSON: - status = copacin_addname( out, newtag, data, level, &(p->asis), &(p->corps) ); - break; - - case SERIALNO: - ok = addsn( out, data->data, level ); - if ( ok ) status = BIBL_OK; - else status = BIBL_ERR_MEMERR; - break; - - default: - fprintf(stderr,"%s: internal error -- " "illegal process value %d\n", p->progname, process ); - status = BIBL_OK; - break; - } + invalue = fields_value( bibin, i, FIELDS_STRP ); + status = convertfns[ process ] ( bibin, i, intag, invalue, level, p, outtag, bibout ); if ( status!=BIBL_OK ) return status; } return status; } - diff --git a/bibutils/copacin.h b/bibutils/copacin.h deleted file mode 100644 --- a/bibutils/copacin.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * copacin.h - * - * Copyright (c) Chris Putnam 2004-2014 - * - * Source code released under the GPL - * - */ -#ifndef COPACIN_H -#define COPACIN_H - -#include "newstr.h" -#include "fields.h" -#include "reftypes.h" -#include "bibutils.h" - -extern int copacin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, - newstr *line, newstr *reference, int *fcharset ); -extern int copacin_processf( fields *copacin, char *p, char *filename, - long nref ); -extern int copacin_convertf( fields *copacin, fields *info, int reftype, param *p, variants *all, int nall ); - -extern void copacin_initparams( param *p, const char *progname ); - - -extern variants copac_all[]; -extern int copac_nall; - - -#endif diff --git a/bibutils/copactypes.c b/bibutils/copactypes.c --- a/bibutils/copactypes.c +++ b/bibutils/copactypes.c @@ -1,7 +1,7 @@ /* * copactypes.c * - * Copyright (c) Chris Putnam 2004-2014 + * Copyright (c) Chris Putnam 2004-2017 * * Program and source code released under the GPL version 2 * @@ -14,22 +14,22 @@ /* if no specific type can be identified */ static lookups generic[] = { - { "TI-", "TITLE" , TITLE, LEVEL_MAIN }, - { "AU-", "AUTHOR", PERSON, LEVEL_MAIN }, - { "MV-", "VOLUME", SIMPLE, LEVEL_MAIN }, - { "SE-", "TITLE", TITLE, LEVEL_HOST }, - { "ED-", "EDITION", SIMPLE, LEVEL_MAIN }, - { "SC-", "SCALE", SIMPLE, LEVEL_MAIN }, /* for maps */ - { "PU-", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "PY-", "YEAR", SIMPLE, LEVEL_MAIN }, - { "PD-", "DESCRIPTION",SIMPLE, LEVEL_MAIN }, /* physical description */ - { "DT-", "TYPE", SIMPLE, LEVEL_MAIN }, - { "LA-", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "TI-", "TITLE" , TITLE, LEVEL_MAIN }, + { "AU-", "AUTHOR", PERSON, LEVEL_MAIN }, + { "MV-", "VOLUME", SIMPLE, LEVEL_MAIN }, + { "SE-", "TITLE", TITLE, LEVEL_HOST }, + { "ED-", "EDITION", SIMPLE, LEVEL_MAIN }, + { "SC-", "SCALE", SIMPLE, LEVEL_MAIN }, /* for maps */ + { "PU-", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "PY-", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "PD-", "DESCRIPTION", SIMPLE, LEVEL_MAIN }, /* physical description */ + { "DT-", "TYPE", SIMPLE, LEVEL_MAIN }, + { "LA-", "LANGUAGE", SIMPLE, LEVEL_MAIN }, { "IS-", "SERIALNUMBER", SERIALNO, LEVEL_MAIN }, - { "NT-", "NOTES", SIMPLE, LEVEL_MAIN }, - { "KW-", "KEYWORD", SIMPLE, LEVEL_MAIN }, - { "UL-", "URL", SIMPLE, LEVEL_MAIN }, - { "HL-", "LOCATION", SIMPLE, LEVEL_MAIN } + { "NT-", "NOTES", NOTES, LEVEL_MAIN }, + { "KW-", "KEYWORD", SIMPLE, LEVEL_MAIN }, + { "UL-", "URL", SIMPLE, LEVEL_MAIN }, + { "HL-", "LOCATION", SIMPLE, LEVEL_MAIN } }; /* order is important....."Book" matches "Book" and "Book Section", hence diff --git a/bibutils/doi.c b/bibutils/doi.c deleted file mode 100644 --- a/bibutils/doi.c +++ /dev/null @@ -1,115 +0,0 @@ -/* - * doi.c - * - * doi_to_url() - * Handle outputing DOI as a URL (Endnote and RIS formats) - * 1) Append http://dx.doi.org as necessary - * 2) Check for overlap with pre-existing URL for the DOI - * - * is_doi() - * Check for DOI buried in another field. - * - * Copyright (c) Chris Putnam 2008-2013 - * - * Source code released under the GPL version 2 - * - */ -#include -#include -#include -#include -#include "newstr.h" -#include "fields.h" - -static void -construct_url( char *prefix, newstr *id, newstr *id_url ) -{ - if ( !strncasecmp( id->data, "http:", 5 ) ) - newstr_newstrcpy( id_url, id ); - else { - newstr_strcpy( id_url, prefix ); - if ( id->data[0]!='/' ) newstr_addchar( id_url, '/' ); - newstr_newstrcat( id_url, id ); - } -} - -static int -url_exists( fields *f, char *urltag, newstr *doi_url ) -{ - int i, n; - if ( urltag ) { - n = fields_num( f ); - for ( i=0; idata ) ) continue; - return 1; - } - } - return 0; -} - -static void -xxx_to_url( fields *f, int n, char *http_prefix, char *urltag, newstr *xxx_url ) -{ - newstr_empty( xxx_url ); - construct_url( http_prefix, fields_value( f, n, FIELDS_STRP ), xxx_url ); - if ( url_exists( f, urltag, xxx_url ) ) - newstr_empty( xxx_url ); -} -void -doi_to_url( fields *f, int n, char *urltag, newstr *url ) -{ - xxx_to_url( f, n, "http://dx.doi.org", urltag, url ); -} -void -jstor_to_url( fields *f, int n, char *urltag, newstr *url ) -{ - xxx_to_url( f, n, "http://www.jstor.org/stable", urltag, url ); -} -void -pmid_to_url( fields *f, int n, char *urltag, newstr *url ) -{ - xxx_to_url( f, n, "http://www.ncbi.nlm.nih.gov/pubmed", urltag, url ); -} -void -arxiv_to_url( fields *f, int n, char *urltag, newstr *url ) -{ - xxx_to_url( f, n, "http://arxiv.org/abs", urltag, url ); -} - -/* Rules for the pattern: - * '#' = number - * isalpha() = match precisely (matchcase==1) or match regardless of case - * (matchcase==0) - * all others must match precisely - */ -static int -string_pattern( char *s, char *pattern, int matchcase ) -{ - int patlen, match, i; - patlen = strlen( pattern ); - if ( strlen( s ) < patlen ) return 0; /* too short */ - for ( i=0; i #include #include "is_ws.h" -#include "newstr.h" -#include "newstr_conv.h" +#include "str.h" +#include "str_conv.h" #include "fields.h" #include "xml.h" #include "xml_encoding.h" -#include "ebiin.h" +#include "bibformats.h" +static int ebiin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int ebiin_processf( fields *ebiin, char *data, char *filename, long nref, param *p ); + + /***************************************************** PUBLIC: void ebiin_initparams() *****************************************************/ @@ -42,8 +46,8 @@ p->all = NULL; p->nall = 0; - list_init( &(p->asis) ); - list_init( &(p->corps) ); + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); if ( !progname ) p->progname = NULL; else p->progname = strdup( progname ); @@ -52,14 +56,14 @@ /***************************************************** PUBLIC: int ebiin_readf() *****************************************************/ -int -ebiin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ) +static int +ebiin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) { - newstr tmp; - char *startptr = NULL, *endptr; int haveref = 0, inref = 0, file_charset = CHARSET_UNKNOWN, m; - newstr_init( &tmp ); - while ( !haveref && newstr_fget( fp, buf, bufsize, bufpos, line ) ) { + char *startptr = NULL, *endptr; + str tmp; + str_init( &tmp ); + while ( !haveref && str_fget( fp, buf, bufsize, bufpos, line ) ) { if ( line->data ) { m = xml_getencoding( line ); if ( m!=CHARSET_UNKNOWN ) file_charset = m; @@ -67,19 +71,19 @@ if ( line->data ) startptr = xml_findstart( line->data, "Publication" ); if ( startptr || inref ) { - if ( inref ) newstr_strcat( &tmp, line->data ); + if ( inref ) str_strcat( &tmp, line ); else { - newstr_strcat( &tmp, startptr ); + str_strcatc( &tmp, startptr ); inref = 1; } - endptr = xml_findend( tmp.data, "Publication" ); + endptr = xml_findend( str_cstr( &tmp ), "Publication" ); if ( endptr ) { - newstr_segcpy( reference, tmp.data, endptr ); + str_segcpy( reference, str_cstr( &tmp ), endptr ); haveref = 1; } } } - newstr_free( &tmp ); + str_free( &tmp ); *fcharset = file_charset; return haveref; } @@ -101,9 +105,9 @@ int i, status; char *d; - if ( !xml_hasdata( node ) ) goto out; + if ( !xml_hasvalue( node ) ) goto out; - d = xml_data( node ); + d = xml_value( node ); for ( i=0; i2003 Jan-Feb */ static int -ebiin_medlinedate_year( fields *info, char *p, newstr *s, int level, char **end ) +ebiin_medlinedate_year( fields *info, char *p, str *s, int level, char **end ) { int status; - *end = newstr_cpytodelim( s, p, " \t\n\r", 0 ); - if ( newstr_memerr( s ) ) return BIBL_ERR_MEMERR; - if ( s->len ) { - status = fields_add( info, "PARTYEAR", s->data, level ); + *end = str_cpytodelim( s, p, " \t\n\r", 0 ); + if ( str_memerr( s ) ) return BIBL_ERR_MEMERR; + if ( str_has_value( s ) ) { + status = fields_add( info, "PARTDATE:YEAR", s->data, level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } return BIBL_OK; } static int -ebiin_medlinedate_month( fields *info, char *p, newstr *s, int level, char **end ) +ebiin_medlinedate_month( fields *info, char *p, str *s, int level, char **end ) { int status; - *end = newstr_cpytodelim( s, p, " \t\n\r", 0 ); - newstr_findreplace( s, "-", "/" ); - if ( newstr_memerr( s ) ) return BIBL_ERR_MEMERR; - if ( s->len ) { - status = fields_add( info, "PARTMONTH", s->data, level ); + *end = str_cpytodelim( s, p, " \t\n\r", 0 ); + str_findreplace( s, "-", "/" ); + if ( str_memerr( s ) ) return BIBL_ERR_MEMERR; + if ( str_has_value( s ) ) { + status = fields_add( info, "PARTDATE:MONTH", s->data, level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } return BIBL_OK; } static int -ebiin_medlinedate_day( fields *info, char *p, newstr *s, int level, char **end ) +ebiin_medlinedate_day( fields *info, char *p, str *s, int level, char **end ) { int status; - *end = newstr_cpytodelim( s, p, " \t\n\r", 0 ); - if ( newstr_memerr( s ) ) return BIBL_ERR_MEMERR; - if ( s->len ) { - status = fields_add( info, "PARTDAY", s->data, level ); + *end = str_cpytodelim( s, p, " \t\n\r", 0 ); + if ( str_memerr( s ) ) return BIBL_ERR_MEMERR; + if ( str_has_value( s ) ) { + status = fields_add( info, "PARTDATE:DAY", s->data, level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } return BIBL_OK; @@ -188,14 +192,14 @@ ebiin_medlinedate( fields *info, char *p, int level ) { int status; - newstr s; - newstr_init( &s ); + str s; + str_init( &s ); status = ebiin_medlinedate_year( info, skip_ws( p ), &s, level, &p ); if ( status==BIBL_OK && *p ) status = ebiin_medlinedate_month( info, skip_ws( p ), &s, level, &p ); if ( status==BIBL_OK && *p ) status = ebiin_medlinedate_day( info, skip_ws( p ), &s, level, &p ); - newstr_free( &s ); + str_free( &s ); return status; } @@ -231,21 +235,21 @@ ebiin_journal1( xml *node, fields *info ) { xml_convert c[] = { - { "ISSN", NULL, NULL, "ISSN", 1 }, - { "Volume", NULL, NULL, "VOLUME", 1 }, - { "Issue", NULL, NULL, "ISSUE", 1 }, - { "Year", NULL, NULL, "PARTYEAR", 1 }, - { "Month", NULL, NULL, "PARTMONTH", 1 }, - { "Day", NULL, NULL, "PARTDAY", 1 }, - { "Language", NULL, NULL, "LANGUAGE", 1 }, + { "ISSN", NULL, NULL, "ISSN", 1 }, + { "Volume", NULL, NULL, "VOLUME", 1 }, + { "Issue", NULL, NULL, "ISSUE", 1 }, + { "Year", NULL, NULL, "PARTDATE:YEAR", 1 }, + { "Month", NULL, NULL, "PARTDATE:MONTH", 1 }, + { "Day", NULL, NULL, "PARTDATE:DAY", 1 }, + { "Language", NULL, NULL, "LANGUAGE", 1 }, }; int nc = sizeof( c ) / sizeof( c[0] ), status, found; - if ( xml_hasdata( node ) ) { + if ( xml_hasvalue( node ) ) { status = ebiin_doconvert( node, info, c, nc, &found ); if ( status!=BIBL_OK ) return status; if ( !found ) { if ( xml_tagexact( node, "MedlineDate" ) ) { - status = ebiin_medlinedate( info, xml_data( node ), 1 ); + status = ebiin_medlinedate( info, xml_value( node ), 1 ); if ( status!=BIBL_OK ) return status; } } @@ -270,26 +274,26 @@ { int i, status, ret = BIBL_OK; const int level = 1; - newstr sp, ep, *up; + str sp, ep, *up; - newstrs_init( &sp, &ep, NULL ); + strs_init( &sp, &ep, NULL ); /* ...start page */ - p = newstr_cpytodelim( &sp, skip_ws( p ), "-", 1 ); - if ( newstr_memerr( &sp ) ) { + p = str_cpytodelim( &sp, skip_ws( p ), "-", 1 ); + if ( str_memerr( &sp ) ) { ret = BIBL_ERR_MEMERR; goto out; } /* ...end page */ - p = newstr_cpytodelim( &ep, skip_ws( p ), " \t\n\r", 0 ); - if ( newstr_memerr( &ep ) ) { + p = str_cpytodelim( &ep, skip_ws( p ), " \t\n\r", 0 ); + if ( str_memerr( &ep ) ) { ret = BIBL_ERR_MEMERR; goto out; } if ( sp.len ) { - status = fields_add( info, "PAGESTART", sp.data, level ); + status = fields_add( info, "PAGES:START", sp.data, level ); if ( status!=FIELDS_OK ) { ret = BIBL_ERR_MEMERR; goto out; @@ -301,12 +305,12 @@ sp.data[i] = ep.data[i-sp.len+ep.len]; up = &(sp); } else up = &(ep); - status = fields_add( info, "PAGEEND", up->data, level ); + status = fields_add( info, "PAGES:STOP", up->data, level ); if ( status!=FIELDS_OK ) ret = BIBL_ERR_MEMERR; } out: - newstrs_free( &sp, &ep, NULL ); + strs_free( &sp, &ep, NULL ); return ret; } static int @@ -314,7 +318,7 @@ { int status; if ( xml_tagexact( node, "Pages" ) && node->value ) { - status = ebiin_pages( info, xml_data( node ) ); + status = ebiin_pages( info, xml_value( node ) ); if ( status!=BIBL_OK ) return status; } if ( node->down ) { @@ -336,8 +340,8 @@ ebiin_abstract( xml *node, fields *info ) { int status; - if ( xml_hasdata( node ) && xml_tagexact( node, "AbstractText" ) ) { - status = fields_add( info, "ABSTRACT", xml_data( node ), 0 ); + if ( xml_hasvalue( node ) && xml_tagexact( node, "AbstractText" ) ) { + status = fields_add( info, "ABSTRACT", xml_value( node ), 0 ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } else if ( node->next ) { @@ -357,32 +361,32 @@ * */ static int -ebiin_author( xml *node, newstr *name ) +ebiin_author( xml *node, str *name ) { int status; char *p; if ( xml_tagexact( node, "LastName" ) ) { if ( name->len ) { - newstr_prepend( name, "|" ); - newstr_prepend( name, xml_data( node ) ); + str_prepend( name, "|" ); + str_prepend( name, xml_value( node ) ); } - else newstr_strcat( name, xml_data( node ) ); + else str_strcatc( name, xml_value( node ) ); } else if ( xml_tagexact( node, "ForeName" ) || xml_tagexact( node, "FirstName" ) ) { - p = xml_data( node ); + p = xml_value( node ); while ( p && *p ) { - if ( name->len ) newstr_addchar( name, '|' ); + if ( name->len ) str_addchar( name, '|' ); while ( *p && *p==' ' ) p++; - while ( *p && *p!=' ' ) newstr_addchar( name, *p++ ); + while ( *p && *p!=' ' ) str_addchar( name, *p++ ); } } else if ( xml_tagexact( node, "Initials" ) && !strchr( name->data, '|' ) ) { - p = xml_data( node ); + p = xml_value( node ); while ( p && *p ) { - if ( name->len ) newstr_addchar( name, '|' ); - if ( !is_ws(*p ) ) newstr_addchar( name, *p++ ); + if ( name->len ) str_addchar( name, '|' ); + if ( !is_ws(*p ) ) str_addchar( name, *p++ ); } } - if ( newstr_memerr( name ) ) return BIBL_ERR_MEMERR; + if ( str_memerr( name ) ) return BIBL_ERR_MEMERR; if ( node->down ) { status = ebiin_author( node->down, name ); @@ -399,9 +403,9 @@ ebiin_authorlist( xml *node, fields *info, int level ) { int fstatus, status = BIBL_OK; - newstr name; + str name; - newstr_init( &name ); + str_init( &name ); node = node->down; while ( node ) { if ( xml_tagexact( node, "Author" ) && node->down ) { @@ -410,13 +414,13 @@ if ( name.len ) { fstatus = fields_add(info,"AUTHOR",name.data,level); if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } - newstr_empty( &name ); + str_empty( &name ); } } node = node->next; } out: - newstr_free( &name ); + str_free( &name ); return status; } @@ -436,8 +440,8 @@ ebiin_journal2( xml *node, fields *info ) { int status; - if ( xml_tagwithdata( node, "TitleAbbreviation" ) ) { - status = fields_add( info, "TITLE", xml_data( node ), 1 ); + if ( xml_tagwithvalue( node, "TitleAbbreviation" ) ) { + status = fields_add( info, "TITLE", xml_value( node ), 1 ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } if ( node->down ) { @@ -465,8 +469,8 @@ ebiin_meshheading( xml *node, fields *info ) { int status; - if ( xml_tagwithdata( node, "DescriptorName" ) ) { - status = fields_add( info, "KEYWORD", xml_data( node ), 0 ); + if ( xml_tagwithvalue( node, "DescriptorName" ) ) { + status = fields_add( info, "KEYWORD", xml_value( node ), 0 ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } if ( node->next ) { @@ -495,46 +499,46 @@ ebiin_book( xml *node, fields *info, int book_level ) { xml_convert book[] = { - { "Publisher", NULL, NULL, "PUBLISHER", 0 }, - { "Language", NULL, NULL, "LANGUAGE", 0 }, - { "ISBN10", NULL, NULL, "ISBN", 0 }, - { "ISBN13", NULL, NULL, "ISBN13", 0 }, - { "Year", NULL, NULL, "YEAR", 0 }, - { "Month", NULL, NULL, "MONTH", 0 }, - { "Day", NULL, NULL, "DAY", 0 }, - { "PageTotal", NULL, NULL, "TOTALPAGES", 0 }, - { "SeriesName", NULL, NULL, "TITLE", 1 }, - { "SeriesISSN", NULL, NULL, "ISSN", 0 }, - { "OtherReportInformation", NULL, NULL, "NOTES", 0 }, - { "Edition", NULL, NULL, "EDITION", 0 }, + { "Publisher", NULL, NULL, "PUBLISHER", 0 }, + { "Language", NULL, NULL, "LANGUAGE", 0 }, + { "ISBN10", NULL, NULL, "ISBN", 0 }, + { "ISBN13", NULL, NULL, "ISBN13", 0 }, + { "Year", NULL, NULL, "DATE:YEAR", 0 }, + { "Month", NULL, NULL, "DATE:MONTH", 0 }, + { "Day", NULL, NULL, "DATE:DAY", 0 }, + { "PageTotal", NULL, NULL, "PAGES:TOTAL", 0 }, + { "SeriesName", NULL, NULL, "TITLE", 1 }, + { "SeriesISSN", NULL, NULL, "ISSN", 0 }, + { "OtherReportInformation", NULL, NULL, "NOTES", 0 }, + { "Edition", NULL, NULL, "EDITION", 0 }, }; int nbook = sizeof( book ) / sizeof( book[0] ); xml_convert inbook[] = { - { "Publisher", NULL, NULL, "PUBLISHER", 1 }, - { "Language", NULL, NULL, "LANGUAGE", 0 }, - { "ISBN10", NULL, NULL, "ISBN", 1 }, - { "ISBN13", NULL, NULL, "ISBN13", 1 }, - { "Year", NULL, NULL, "PARTYEAR", 1 }, - { "Month", NULL, NULL, "PARTMONTH", 1 }, - { "Day", NULL, NULL, "PARTDAY", 1 }, - { "PageTotal", NULL, NULL, "TOTALPAGES", 1 }, - { "SeriesName", NULL, NULL, "TITLE", 2 }, - { "SeriesISSN", NULL, NULL, "ISSN", 1 }, - { "OtherReportInformation", NULL, NULL, "NOTES", 1 }, - { "Edition", NULL, NULL, "EDITION", 1 }, + { "Publisher", NULL, NULL, "PUBLISHER", 1 }, + { "Language", NULL, NULL, "LANGUAGE", 0 }, + { "ISBN10", NULL, NULL, "ISBN", 1 }, + { "ISBN13", NULL, NULL, "ISBN13", 1 }, + { "Year", NULL, NULL, "PARTDATE:YEAR", 1 }, + { "Month", NULL, NULL, "PARTDATE:MONTH", 1 }, + { "Day", NULL, NULL, "PARTDATE:DAY", 1 }, + { "PageTotal", NULL, NULL, "PAGES:TOTAL", 1 }, + { "SeriesName", NULL, NULL, "TITLE", 2 }, + { "SeriesISSN", NULL, NULL, "ISSN", 1 }, + { "OtherReportInformation", NULL, NULL, "NOTES", 1 }, + { "Edition", NULL, NULL, "EDITION", 1 }, }; int ninbook = sizeof( inbook ) / sizeof( inbook[0] ); xml_convert *c; int nc, status, found; if ( book_level==0 ) { c = book; nc = nbook; } else { c = inbook; nc = ninbook; } - if ( xml_hasdata( node ) ) { + if ( xml_hasvalue( node ) ) { status = ebiin_doconvert( node, info, c, nc, &found ); if ( status!=BIBL_OK ) return status; if ( !found ) { status = BIBL_OK; if ( xml_tagexact( node, "MedlineDate" ) ) - status = ebiin_medlinedate( info, xml_data( node ), book_level); + status = ebiin_medlinedate( info, xml_value( node ), book_level); else if ( xml_tagexact( node, "Title" ) ) status = ebiin_title( node, info, book_level ); else if ( xml_tagexact( node, "Pagination" ) && node->down ) @@ -586,7 +590,7 @@ static int ebiin_publication( xml *node, fields *info ) { - int status; + int status = BIBL_OK; if ( node->down ) { if ( xml_tagexact( node, "Article" ) ) status = ebiin_article( node->down, info ); @@ -612,7 +616,7 @@ ebiin_fixtype( xml *node, fields *info ) { char *resource = NULL, *issuance = NULL, *genre1 = NULL, *genre2 = NULL; - newstr *type; + str *type; int reslvl, isslvl, gen1lvl, gen2lvl; int status; @@ -684,8 +688,8 @@ return BIBL_OK; } -int -ebiin_processf( fields *ebiin, char *data, char *filename, long nref ) +static int +ebiin_processf( fields *ebiin, char *data, char *filename, long nref, param *p ) { int status; xml top; diff --git a/bibutils/ebiin.h b/bibutils/ebiin.h deleted file mode 100644 --- a/bibutils/ebiin.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * ebiin.h - * - * Copyright (c) Chris Putnam 2004-2013 - * - * Source code released under the GPL version 2 - * - */ -#ifndef PUBIN_H -#define PUBIN_H - -#include "newstr.h" -#include "fields.h" -#include "reftypes.h" -#include "bibutils.h" - -extern int ebiin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ); -extern int ebiin_processf( fields *ebiin, char *data, char *filename, long nref ); - -extern void ebiin_initparams( param *p, const char *progname ); - - -extern variants med_all[]; -extern int med_nall; - -#endif - diff --git a/bibutils/endin.c b/bibutils/endin.c --- a/bibutils/endin.c +++ b/bibutils/endin.c @@ -1,7 +1,7 @@ /* * endin.c * - * Copyright (c) Chris Putnam 2003-2014 + * Copyright (c) Chris Putnam 2003-2017 * * Program and source code released under the GPL version 2 * @@ -11,19 +11,27 @@ #include #include #include "is_ws.h" -#include "doi.h" -#include "newstr.h" -#include "newstr_conv.h" +#include "str.h" +#include "str_conv.h" #include "fields.h" -#include "name.h" -#include "title.h" -#include "serialno.h" +#include "url.h" #include "reftypes.h" -#include "endin.h" +#include "bibformats.h" +#include "generic.h" +extern variants end_all[]; +extern int end_nall; + /***************************************************** PUBLIC: void endin_initparams() *****************************************************/ + +static int endin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int endin_processf( fields *endin, char *p, char *filename, long nref, param *pm ); +int endin_typef( fields *endin, char *filename, int nrefs, param *p ); +int endin_convertf( fields *endin, fields *info, int reftype, param *p ); +int endin_cleanf( bibl *bin, param *p ); + void endin_initparams( param *p, const char *progname ) { @@ -46,8 +54,8 @@ p->all = end_all; p->nall = end_nall; - list_init( &(p->asis) ); - list_init( &(p->corps) ); + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); if ( !progname ) p->progname = NULL; else p->progname = strdup( progname ); @@ -76,14 +84,14 @@ } static int -readmore( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line ) +readmore( FILE *fp, char *buf, int bufsize, int *bufpos, str *line ) { if ( line->len ) return 1; - else return newstr_fget( fp, buf, bufsize, bufpos, line ); + else return str_fget( fp, buf, bufsize, bufpos, line ); } -int -endin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ) +static int +endin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) { int haveref = 0, inref = 0; unsigned char *up; @@ -108,14 +116,14 @@ } /* Each reference starts with a tag && ends with a blank line */ if ( endin_istag( p ) ) { - if ( reference->len ) newstr_addchar( reference, '\n' ); - newstr_strcat( reference, p ); + if ( reference->len ) str_addchar( reference, '\n' ); + str_strcatc( reference, p ); inref = 1; } else if ( inref && p ) { - newstr_addchar( reference, '\n' ); - newstr_strcat( reference, p ); + str_addchar( reference, '\n' ); + str_strcatc( reference, p ); } - newstr_empty( line ); + str_empty( line ); } if ( reference->len ) haveref = 1; return haveref; @@ -125,20 +133,20 @@ PUBLIC: int endin_processf() *****************************************************/ static char* -process_endline( newstr *tag, newstr *data, char *p ) +process_endline( str *tag, str *data, char *p ) { int i; i = 0; while ( i<2 && *p ) { - newstr_addchar( tag, *p++); + str_addchar( tag, *p++); i++; } while ( *p==' ' || *p=='\t' ) p++; while ( *p && *p!='\r' && *p!='\n' ) - newstr_addchar( data, *p++ ); - newstr_trimendingws( data ); + str_addchar( data, *p++ ); + str_trimendingws( data ); while ( *p=='\r' || *p=='\n' ) p++; @@ -146,45 +154,45 @@ } static char * -process_endline2( newstr *tag, newstr *data, char *p ) +process_endline2( str *tag, str *data, char *p ) { while ( *p==' ' || *p=='\t' ) p++; while ( *p && *p!='\r' && *p!='\n' ) - newstr_addchar( data, *p++ ); - newstr_trimendingws( data ); + str_addchar( data, *p++ ); + str_trimendingws( data ); while ( *p=='\r' || *p=='\n' ) p++; return p; } -int -endin_processf( fields *endin, char *p, char *filename, long nref ) +static int +endin_processf( fields *endin, char *p, char *filename, long nref, param *pm ) { - newstr tag, data; + str tag, data; int status, n; - newstrs_init( &tag, &data, NULL ); + strs_init( &tag, &data, NULL ); while ( *p ) { - newstrs_empty( &tag, &data, NULL ); + strs_empty( &tag, &data, NULL ); if ( endin_istag( p ) ) { p = process_endline( &tag, &data, p ); - if ( data.len==0 ) continue; - status = fields_add( endin, tag.data, data.data, 0 ); + if ( str_is_empty( &data ) ) continue; + status = fields_add( endin, str_cstr( &tag ), str_cstr( &data ), 0 ); if ( status!=FIELDS_OK ) return 0; } else { p = process_endline2( &tag, &data, p ); /* endnote puts %K only on 1st line of keywords */ n = fields_num( endin ); - if ( n>0 && data.len ) { + if ( n>0 && str_has_value( &data ) ) { if ( !strncmp( endin->tag[n-1].data, "%K", 2 ) ) { - status = fields_add( endin, "%K", data.data, 0 ); + status = fields_add( endin, "%K", str_cstr( &data ), 0 ); if ( status!=FIELDS_OK ) return 0; } else { - newstr_addchar( &(endin->data[n-1]), ' ' ); - newstr_strcat( &(endin->data[n-1]), data.data ); + str_addchar( &(endin->data[n-1]), ' ' ); + str_strcat( &(endin->data[n-1]), &data ); } } } } - newstrs_free( &tag, &data, NULL ); + strs_free( &tag, &data, NULL ); return 1; } @@ -192,7 +200,7 @@ PUBLIC: int endin_typef() *****************************************************/ -/* Endnote defaults if no %0 +/* Endnote defaults if no %0 tag * * if %J & %V - journal article * if %B - book section @@ -201,18 +209,16 @@ * if !%B & !%J & !%R & !%I - journal article */ int -endin_typef( fields *endin, char *filename, int nrefs, param *p, - variants *all, int nall ) +endin_typef( fields *endin, char *filename, int nrefs, param *p ) { - char *refnum = ""; - int n, reftype, nrefnum, nj, nv, nb, nr, nt, ni; - n = fields_find( endin, "%0", 0 ); - nrefnum = fields_find( endin, "%F", 0 ); - if ( nrefnum!=-1 ) refnum = endin->data[nrefnum].data; - if ( n!=-1 ) { - reftype = get_reftype( endin->data[n].data, nrefs, - p->progname, all, nall, refnum ); - } else { + int ntypename, nrefname, is_default, nj, nv, nb, nr, nt, ni; + char *refname = "", *typename=""; + + ntypename = fields_find( endin, "%0", LEVEL_MAIN ); + nrefname = fields_find( endin, "%F", LEVEL_MAIN ); + if ( nrefname!=-1 ) refname = fields_value( endin, nrefname, FIELDS_CHRP_NOUSE ); + if ( ntypename!=-1 ) typename = fields_value( endin, ntypename, FIELDS_CHRP_NOUSE ); + else { nj = fields_find( endin, "%J", 0 ); nv = fields_find( endin, "%V", 0 ); nb = fields_find( endin, "%B", 0 ); @@ -220,26 +226,19 @@ nt = fields_find( endin, "%T", 0 ); ni = fields_find( endin, "%I", 0 ); if ( nj!=-1 && nv!=-1 ) { - reftype = get_reftype( "Journal Article", nrefs, - p->progname, all, nall, refnum ); + typename = "Journal Article"; } else if ( nb!=-1 ) { - reftype = get_reftype( "Book Section", nrefs, - p->progname, all, nall, refnum ); + typename = "Book Section"; } else if ( nr!=-1 && nt==-1 ) { - reftype = get_reftype( "Report", nrefs, - p->progname, all, nall, refnum ); + typename = "Report"; } else if ( ni!=-1 && nb==-1 && nj==-1 && nr==-1 ) { - reftype = get_reftype( "Book", nrefs, - p->progname, all, nall, refnum ); + typename = "Book"; } else if ( nb==-1 && nj==-1 && nr==-1 && ni==-1 ) { - reftype = get_reftype( "Journal Article", nrefs, - p->progname, all, nall, refnum ); - } else { - reftype = get_reftype( "", nrefs, p->progname, - all, nall, refnum ); /* default */ + typename = "Journal Article"; } } - return reftype; + + return get_reftype( typename, nrefs, p->progname, p->all, p->nall, refname, &is_default, REFTYPE_CHATTY ); } /***************************************************** @@ -247,43 +246,44 @@ *****************************************************/ /* Wiley puts multiple authors separated by commas on the %A lines. - * We can detect this by finding the terminal comma in the data. + * We can detect this by finding the terminal comma in the value + * from the tag/value pair. * * "%A" "Author A. X. Last, Author N. B. Next," */ static int is_wiley_author( fields *endin, int n ) { - newstr *t, *d; - t = &(endin->tag[n]); - if ( !t->data || strcmp( t->data, "%A" ) ) return 0; - d = &( endin->data[n] ); - if ( !(d->data) || d->len==0 ) return 0; - if ( d->data[d->len-1]!=',' ) return 0; + str *t, *v; + t = fields_tag( endin, n, FIELDS_STRP_NOUSE ); + if ( str_is_empty( t ) || strcmp( t->data, "%A" ) ) return 0; + v = fields_value( endin, n, FIELDS_STRP_NOUSE ); + if ( str_is_empty( v ) ) return 0; + if ( v->data[v->len-1]!=',' ) return 0; return 1; } static int cleanup_wiley_author( fields *endin, int n ) { - newstr *instring, copy, name; + str *instring, copy, name; int status, nauthor = 0; char *p; - newstrs_init( ©, &name, NULL ); + strs_init( ©, &name, NULL ); instring = &( endin->data[n] ); - newstr_newstrcpy( ©, instring ); + str_strcpy( ©, instring ); p = copy.data; while ( *p ) { if ( *p==',' ) { - if ( newstr_memerr( &name ) ) + if ( str_memerr( &name ) ) return BIBL_ERR_MEMERR; if ( nauthor==0 ) { /* ...replace the first author in the field */ - newstr_newstrcpy( instring, &name ); - if ( newstr_memerr( instring ) ) + str_strcpy( instring, &name ); + if ( str_memerr( instring ) ) return BIBL_ERR_MEMERR; } else { status = fields_add( endin, endin->tag[n].data, @@ -291,17 +291,17 @@ if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - newstr_empty( &name ); + str_empty( &name ); nauthor++; p++; while ( is_ws( *p ) ) p++; } else { - newstr_addchar( &name, *p ); + str_addchar( &name, *p ); p++; } } - newstrs_free( ©, &name, NULL ); + strs_free( ©, &name, NULL ); return BIBL_OK; } @@ -332,35 +332,6 @@ PUBLIC: int endin_convertf(), returns BIBL_OK or BIBL_ERR_MEMERR *****************************************************/ -static int -endin_addpage( fields *info, char *p, int level ) -{ - newstr page; - int status; - - newstr_init( &page ); - - p = newstr_cpytodelim( &page, skip_ws( p ), "- \t\r\n", 0 ); - if ( newstr_memerr( &page ) ) return BIBL_ERR_MEMERR; - if ( page.len>0 ) { - status = fields_add( info, "PAGESTART", page.data, level ); - if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } - - while ( *p && (is_ws(*p) || *p=='-' ) ) p++; - - p = newstr_cpytodelim( &page, p, "- \t\r\n", 0 ); - if ( newstr_memerr( &page ) ) return BIBL_ERR_MEMERR; - if ( page.len>0 ) { - status = fields_add( info, "PAGEEND", page.data, level ); - if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } - - newstr_free( &page ); - - return BIBL_OK; -} - /* month_convert() * convert month name to number in format MM, e.g. "January" -> "01" * if converted, return 1 @@ -403,28 +374,29 @@ } static int -endin_adddate( fields *info, char *tag, char *newtag, char *p, int level ) +endin_date( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) { char *tags[3][2] = { - { "YEAR", "PARTYEAR" }, - { "MONTH", "PARTMONTH" }, - { "DAY", "PARTDAY" } + { "DATE:YEAR", "PARTDATE:YEAR" }, + { "DATE:MONTH", "PARTDATE:MONTH" }, + { "DATE:DAY", "PARTDATE:DAY" } }; + char *p = invalue->data; char month[10], *m; int part, status; - newstr date; + str date; - newstr_init( &date ); + str_init( &date ); - if ( !strncasecmp( newtag, "PART", 4 ) ) part = 1; + if ( !strncasecmp( outtag, "PART", 4 ) ) part = 1; else part = 0; /* %D YEAR */ - if ( !strcasecmp( tag, "%D" ) ) { - newstr_cpytodelim( &date, skip_ws( p ), "", 0 ); - if ( newstr_memerr( &date ) ) return BIBL_ERR_MEMERR; - if ( date.len>0 ) { - status = fields_add( info, tags[0][part], date.data, level ); + if ( !strcasecmp( intag->data, "%D" ) ) { + str_cpytodelim( &date, skip_ws( p ), "", 0 ); + if ( str_memerr( &date ) ) return BIBL_ERR_MEMERR; + if ( str_has_value( &date ) ) { + status = fields_add( bibout, tags[0][part], date.data, level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } } @@ -432,15 +404,15 @@ /* %8 MONTH DAY, YEAR */ /* %8 MONTH, YEAR */ /* %8 MONTH YEAR */ - else if ( !strcasecmp( tag, "%8" ) ) { + else if ( !strcasecmp( intag->data, "%8" ) ) { /* ...get month */ - p = newstr_cpytodelim( &date, skip_ws( p ), " ,\n", 0 ); - if ( newstr_memerr( &date ) ) return BIBL_ERR_MEMERR; - if ( date.len>0 ) { + p = str_cpytodelim( &date, skip_ws( p ), " ,\n", 0 ); + if ( str_memerr( &date ) ) return BIBL_ERR_MEMERR; + if ( str_has_value( &date ) ) { if ( month_convert( date.data, month ) ) m = month; - else m = date.data; - status = fields_add( info, tags[1][part], m, level ); + else m = str_cstr( &date ); + status = fields_add( bibout, tags[1][part], m, level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } @@ -448,13 +420,13 @@ if ( *p==',' ) p++; /* ...get days */ - p = newstr_cpytodelim( &date, skip_ws( p ), ",\n", 0 ); - if ( newstr_memerr( &date ) ) return BIBL_ERR_MEMERR; + p = str_cpytodelim( &date, skip_ws( p ), ",\n", 0 ); + if ( str_memerr( &date ) ) return BIBL_ERR_MEMERR; if ( date.len>0 && date.len<3 ) { - status = fields_add( info, tags[2][part], date.data, level ); + status = fields_add( bibout, tags[2][part], date.data, level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } else if ( date.len==4 ) { - status = fields_add( info, tags[0][part], date.data, level ); + status = fields_add( bibout, tags[0][part], date.data, level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } @@ -462,19 +434,19 @@ if ( *p==',' ) p++; /* ...get year */ - p = newstr_cpytodelim( &date, skip_ws( p ), " \t\n\r", 0 ); - if ( newstr_memerr( &date ) ) return BIBL_ERR_MEMERR; - if ( date.len > 0 ) { - status = fields_add( info, tags[0][part], date.data, level ); + p = str_cpytodelim( &date, skip_ws( p ), " \t\n\r", 0 ); + if ( str_memerr( &date ) ) return BIBL_ERR_MEMERR; + if ( str_has_value( &date ) ) { + status = fields_add( bibout, tags[0][part], date.data, level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } } - newstr_free( &date ); + str_free( &date ); return BIBL_OK; } static int -endin_addtype( fields *info, char *data, int level ) +endin_type( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) { lookups types[] = { { "GENERIC", "ARTICLE" }, @@ -506,17 +478,16 @@ int ntypes = sizeof( types ) / sizeof( lookups ); int i, status, found=0; for ( i=0; idata ) ) { found = 1; - status = fields_add( info, "INTERNAL_TYPE", types[i].newstr, level ); + status = fields_add( bibout, "INTERNAL_TYPE", types[i].newstr, level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } } if ( !found ) { - fprintf( stderr, "Did not identify reference type '%s'\n", - data ); + fprintf( stderr, "Did not identify reference type '%s'\n", invalue->data ); fprintf( stderr, "Defaulting to journal article type\n"); - status = fields_add( info, "INTERNAL_TYPE", types[0].newstr, level ); + status = fields_add( bibout, "INTERNAL_TYPE", types[0].newstr, level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } return BIBL_OK; @@ -531,110 +502,57 @@ } } -/* Wiley's EndNote download has DOI's in "%1" tag */ -static int -endin_addnotes( fields *info, char *tag, char *value, int level ) -{ - int fstatus, doi; - doi = is_doi( value ); - if ( doi!=-1 ) - fstatus = fields_add( info, "DOI", &(value[doi]), level ); - else - fstatus = fields_add( info, tag, value, level ); - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} - -static int -endin_simple( fields *info, char *tag, char *value, int level ) -{ - int fstatus = fields_add( info, tag, value, level ); - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} - int -endin_convertf( fields *endin, fields *info, int reftype, param *p, variants *all, int nall ) +endin_convertf( fields *bibin, fields *bibout, int reftype, param *p ) { - int i, level, n, process, nfields, ok, fstatus, status = BIBL_OK; - char *newtag, *t; - newstr *d; + static int (*convertfns[NUM_REFTYPES])(fields *, int, str *, str *, int, param *, char *, fields *) = { + [ 0 ... NUM_REFTYPES-1 ] = generic_null, + [ SIMPLE ] = generic_simple, + [ TITLE ] = generic_title, + [ PERSON ] = generic_person, + [ SERIALNO ] = generic_serialno, + [ PAGES ] = generic_pages, + [ NOTES ] = generic_notes, + [ URL ] = generic_url, + [ TYPE ] = endin_type, + [ DATE ] = endin_date, + }; - nfields = fields_num( endin ); + int i, level, process, nfields, fstatus, status = BIBL_OK; + char *outtag; + str *intag, *invalue; + + nfields = fields_num( bibin ); for ( i=0; ilen == 0 ) { - fields_setused( endin, i ); + + /* Ensure we have data */ + if ( fields_nodata( bibin, i ) ) { + fields_setused( bibin, i ); continue; } + + intag = fields_tag( bibin, i, FIELDS_STRP ); + invalue = fields_value( bibin, i, FIELDS_STRP ); + /* - * All refer format tags start with '%'. If we have one + * Refer format tags start with '%'. If we have one * that doesn't, assume that it comes from endx2xml * and just copy and paste to output */ - t = fields_tag( endin, i, FIELDS_CHRP ); - if ( t[0]!='%' ) { - fstatus = fields_add( info, t, d->data, endin->level[i] ); + if ( str_has_value( intag ) && intag->data[0]!='%' ) { + fstatus = fields_add( bibout, str_cstr( intag ), str_cstr( invalue ), bibin->level[i] ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; continue; } - n = translate_oldtag( t, reftype, all, nall, &process, &level, &newtag ); - if ( n==-1 ) { - endin_notag( p, t, d->data ); + if ( !translate_oldtag( str_cstr( intag ), reftype, p->all, p->nall, &process, &level, &outtag ) ) { + endin_notag( p, str_cstr( intag ), str_cstr( invalue ) ); continue; } - if ( process == ALWAYS ) continue; /* add these later */ - fields_setused( endin, i ); - - switch ( process ) { - - case SIMPLE: - status = endin_simple( info, newtag, d->data, level ); - break; - - case TYPE: - status = endin_addtype( info, d->data, level ); - break; - - case TITLE: - ok = title_process( info, newtag, d->data, level, p->nosplittitle ); - if ( !ok ) status = BIBL_ERR_MEMERR; - status = BIBL_OK; - break; - - case PERSON: - ok = name_add( info, newtag, d->data, level, &(p->asis), &(p->corps) ); - if ( !ok ) status = BIBL_ERR_MEMERR; - status = BIBL_OK; - break; - - case DATE: - status = endin_adddate( info, t, newtag,d->data,level); - break; - - case PAGES: - status = endin_addpage( info, d->data, level ); - break; - - case SERIALNO: - ok = addsn( info, d->data, level ); - if ( !ok ) status = BIBL_ERR_MEMERR; - status = BIBL_OK; - break; - - case NOTES: - status = endin_addnotes( info, newtag, d->data, level ); - break; - - default: - fprintf(stderr,"%s: internal error -- illegal process number %d\n", p->progname, process ); - status = BIBL_OK; - break; - } + fields_setused( bibin, i ); + status = convertfns[ process ]( bibin, i, intag, invalue, level, p, outtag, bibout ); if ( status!=BIBL_OK ) return status; } diff --git a/bibutils/endin.h b/bibutils/endin.h deleted file mode 100644 --- a/bibutils/endin.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * endin.h - * - * Copyright (c) Chris Putnam 2003-2014 - * - * Source code released under the GPL version 2 - * - */ -#ifndef ENDIN_H -#define ENDIN_H - -#include "newstr.h" -#include "fields.h" -#include "reftypes.h" -#include "bibutils.h" - -extern int endin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ); -extern int endin_processf( fields *endin, char *p, char *filename, long nref ); -extern int endin_typef( fields *endin, char *filename, int nrefs, param *p, variants *all, int nall ); -extern int endin_convertf( fields *endin, fields *info, int reftype, param *p, variants *all, int nall ); -extern int endin_cleanf( bibl *bin, param *p ); - -extern void endin_initparams( param *p, const char *progname ); - -extern variants end_all[]; -extern int end_nall; - - -#endif - diff --git a/bibutils/endout.c b/bibutils/endout.c --- a/bibutils/endout.c +++ b/bibutils/endout.c @@ -1,7 +1,7 @@ /* * endout.c * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2017 * * Program and source code released under the GPL version 2 * @@ -11,13 +11,18 @@ #include #include #include "utf8.h" -#include "newstr.h" +#include "str.h" #include "strsearch.h" #include "fields.h" -#include "doi.h" #include "name.h" -#include "endout.h" +#include "title.h" +#include "url.h" +#include "bibformats.h" +static int endout_write( fields *in, FILE *fp, param *p, unsigned long refnum ); +static void endout_writeheader( FILE *outptr, param *p ); + + void endout_initparams( param *p, const char *progname ) { @@ -142,7 +147,7 @@ } match_type; static int -get_type( fields *info, param *p, unsigned long refnum ) +get_type( fields *in, param *p, unsigned long refnum ) { /* Comment out TYPE_GENERIC entries as that is default, but * keep in source as record of mapping decision. */ @@ -257,20 +262,20 @@ char *tag, *data; /* Determine type from genre information */ - for ( i=0; in; ++i ) { - tag = info->tag[i].data; + for ( i=0; in; ++i ) { + tag = fields_tag( in, i, FIELDS_CHRP ); if ( strcasecmp( tag, "GENRE" )!=0 && strcasecmp( tag, "NGENRE" )!=0 ) continue; - data = info->data[i].data; + data = fields_value( in, i, FIELDS_CHRP ); for ( j=0; jverbose ) { if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, "Type from tag '%s' data '%s': ", info->tag[i].data, info->data[i].data ); + fprintf( stderr, "Type from tag '%s' data '%s': ", tag, data ); write_type( stderr, type ); fprintf( stderr, "\n" ); } @@ -280,17 +285,17 @@ else if ( !strcasecmp( data, "thesis" ) ) type = TYPE_THESIS; else if ( !strcasecmp( data, "book" ) ) { - if ( info->level[i]==0 ) type = TYPE_BOOK; + if ( in->level[i]==0 ) type = TYPE_BOOK; else type = TYPE_INBOOK; } else if ( !strcasecmp( data, "collection" ) ) { - if ( info->level[i]==0 ) type = TYPE_BOOK; + if ( in->level[i]==0 ) type = TYPE_BOOK; else type = TYPE_INBOOK; } - if ( type!=TYPE_UNKNOWN ) fields_setused( info, i ); + if ( type!=TYPE_UNKNOWN ) fields_setused( in, i ); } /* the inbook type should be defined if 'book' in host */ - if ( type==TYPE_BOOK && info->level[i]>0 ) type = TYPE_INBOOK; + if ( type==TYPE_BOOK && in->level[i]>0 ) type = TYPE_INBOOK; } if ( p->verbose ) { if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); @@ -301,15 +306,15 @@ /* Determine from resource information */ if ( type==TYPE_UNKNOWN ) { - for ( i=0; in; ++i ) { - if ( strcasecmp( info->tag[i].data, "RESOURCE" ) ) + for ( i=0; in; ++i ) { + if ( strcasecmp( fields_tag( in, i, FIELDS_CHRP ), "RESOURCE" ) ) continue; - data = info->data[i].data; + data = fields_value( in, i, FIELDS_CHRP ); if ( !strcasecmp( data, "moving image" ) ) type = TYPE_FILMBROADCAST; else if ( !strcasecmp( data, "software, multimedia" ) ) type = TYPE_PROGRAM; - if ( type!=TYPE_UNKNOWN ) fields_setused( info, i ); + if ( type!=TYPE_UNKNOWN ) fields_setused( in, i ); } if ( p->verbose ) { if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); @@ -321,12 +326,12 @@ /* Determine from issuance information */ if ( type==TYPE_UNKNOWN ) { - for ( i=0; in; ++i ) { - if ( strcasecmp( info->tag[i].data, "ISSUANCE" ) ) + for ( i=0; in; ++i ) { + if ( strcasecmp( fields_tag( in, i, FIELDS_CHRP ), "ISSUANCE" ) ) continue; - data = info->data[i].data; + data = fields_value( in, i, FIELDS_CHRP ); if ( !strcasecmp( data, "monographic" ) ) { - if ( info->level[i]==0 ) type = TYPE_BOOK; + if ( in->level[i]==0 ) type = TYPE_BOOK; else type = TYPE_INBOOK; } } @@ -340,14 +345,14 @@ /* default to generic or book chapter, depending on maxlevel */ if ( type==TYPE_UNKNOWN ) { - maxlevel = fields_maxlevel( info ); + maxlevel = fields_maxlevel( in ); if ( maxlevel > 0 ) type = TYPE_INBOOK; else { if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); fprintf( stderr, "Cannot identify TYPE in reference %lu ", refnum+1 ); - n = fields_find( info, "REFNUM", -1 ); + n = fields_find( in, "REFNUM", -1 ); if ( n!=-1 ) - fprintf( stderr, " %s", info->data[n].data ); + fprintf( stderr, " %s", (char *) fields_value( in, n, FIELDS_CHRP ) ); fprintf( stderr, " (defaulting to generic)\n" ); type = TYPE_GENERIC; } @@ -364,7 +369,7 @@ } static void -output_type( FILE *fp, int type, param *p ) +append_type( int type, fields *out, param *p, int *status ) { /* These are restricted to Endnote-defined types */ match_type genrenames[] = { @@ -410,315 +415,338 @@ { "Unpublished Work", TYPE_UNPUBLISHED }, }; int ngenrenames = sizeof( genrenames ) / sizeof( genrenames[0] ); - int i, found = 0; - fprintf( fp, "%%0 "); + int i, fstatus, found = 0; for ( i=0; iprogname ) fprintf( stderr, "%s: ", p->progname ); fprintf( stderr, "Cannot identify type %d\n", type ); } - fprintf( fp, "\n" ); } -static void -output_title( FILE *fp, fields *info, char *full, char *sub, char *endtag, - int level ) +static int +append_title( fields *in, char *full, char *sub, char *endtag, + int level, fields *out, int *status ) { - newstr *mainttl = fields_findv( info, level, FIELDS_STRP, full ); - newstr *subttl = fields_findv( info, level, FIELDS_STRP, sub ); + str *mainttl = fields_findv( in, level, FIELDS_STRP, full ); + str *subttl = fields_findv( in, level, FIELDS_STRP, sub ); + str fullttl; + int fstatus; - if ( !mainttl ) return; + str_init( &fullttl ); + title_combine( &fullttl, mainttl, subttl ); - fprintf( fp, "%s %s", endtag, mainttl->data ); - if ( subttl ) { - if ( mainttl->len > 0 && - mainttl->data[ mainttl->len-1 ]!='?' ) - fprintf( fp, ":" ); - fprintf( fp, " %s", subttl->data ); + if ( str_memerr( &fullttl ) ) { + *status = BIBL_ERR_MEMERR; + goto out; } - fprintf( fp, "\n" ); + + if ( str_has_value( &fullttl ) ) { + fstatus = fields_add( out, endtag, str_cstr( &fullttl ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } +out: + str_free( &fullttl ); + return 1; } static void -output_people( FILE *fp, fields *info, char *tag, char *entag, int level ) +append_people( fields *in, char *tag, char *entag, int level, fields *out, int *status ) { - newstr oneperson; - int i, n, flvl; + int i, n, flvl, fstatus; + str oneperson; char *ftag; - newstr_init( &oneperson ); - n = fields_num( info ); + + str_init( &oneperson ); + n = fields_num( in ); for ( i=0; i0 && m<13 ) fprintf( fp, "%s", months[m-1] ); - else fprintf( fp, "%s", month ); + if ( m>0 && m<13 ) str_strcpyc( &monday, months[m-1] ); + else str_strcpyc( &monday, month ); } - if ( month && day ) fprintf( fp, " " ); - if ( day ) fprintf( fp, "%s", day ); - fprintf( fp, "\n" ); + if ( month && day ) str_strcatc( &monday, " " ); + if ( day ) str_strcatc( &monday, day ); + fstatus = fields_add( out, "%8", str_cstr( &monday ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } + str_free( &monday ); } static void -output_thesishint( FILE *fp, int type ) +append_thesishint( int type, fields *out, int *status ) { - if ( type==TYPE_MASTERSTHESIS ) - fprintf( fp, "%%9 Masters thesis\n" ); - else if ( type==TYPE_PHDTHESIS ) - fprintf( fp, "%%9 Ph.D. thesis\n" ); - else if ( type==TYPE_DIPLOMATHESIS ) - fprintf( fp, "%%9 Diploma thesis\n" ); - else if ( type==TYPE_DOCTORALTHESIS ) - fprintf( fp, "%%9 Doctoral thesis\n" ); - else if ( type==TYPE_HABILITATIONTHESIS ) - fprintf( fp, "%%9 Habilitation thesis\n" ); + int fstatus; + + if ( type==TYPE_MASTERSTHESIS ) { + fstatus = fields_add( out, "%9", "Masters thesis", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + else if ( type==TYPE_PHDTHESIS ) { + fstatus = fields_add( out, "%9", "Ph.D. thesis", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + else if ( type==TYPE_DIPLOMATHESIS ) { + fstatus = fields_add( out, "%9", "Diploma thesis", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + else if ( type==TYPE_DOCTORALTHESIS ) { + fstatus = fields_add( out, "%9", "Doctoral thesis", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + else if ( type==TYPE_HABILITATIONTHESIS ) { + fstatus = fields_add( out, "%9", "Habilitation thesis", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } } static void -output_easyall( FILE *fp, fields *info, char *tag, char *entag, int level ) +append_easyall( fields *in, char *tag, char *entag, int level, fields *out, int *status ) { + vplist_index i; + int fstatus; vplist a; - int i; vplist_init( &a ); - fields_findv_each( info, level, FIELDS_CHRP, &a, tag ); - for ( i=0; in; ++i ) { + fprintf( fp, "%s %s\n", + (char*) fields_tag( out, i, FIELDS_CHRP ), + (char*) fields_value( out, i, FIELDS_CHRP ) + ); + } + fprintf( fp, "\n" ); fflush( fp ); } -void +static int +endout_write( fields *in, FILE *fp, param *p, unsigned long refnum ) +{ + int status; + fields out; + + fields_init( &out ); + status = append_data( in, &out, p, refnum ); + if ( status==BIBL_OK ) output( fp, &out ); + fields_free( &out ); + + return status; +} + +static void endout_writeheader( FILE *outptr, param *p ) { if ( p->utf8bom ) utf8_writebom( outptr ); diff --git a/bibutils/endout.h b/bibutils/endout.h deleted file mode 100644 --- a/bibutils/endout.h +++ /dev/null @@ -1,22 +0,0 @@ -/* - * endout.h - * - * Copyright (c) Chris Putnam 2005-2013 - * - * Source code released under the GPL version 2 - * - */ -#ifndef ENDOUT_H -#define ENDOUT_H - -#include -#include "bibutils.h" - -extern void endout_write( fields *info, FILE *fp, param *p, - unsigned long refnum ); -extern void endout_writeheader( FILE *outptr, param *p ); - -extern void endout_initparams( param *p, const char *progname ); - - -#endif diff --git a/bibutils/endtypes.c b/bibutils/endtypes.c --- a/bibutils/endtypes.c +++ b/bibutils/endtypes.c @@ -1,7 +1,7 @@ /* * endtypes.c * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Program and source code released under the GPL version 2 * @@ -18,7 +18,7 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%J", "TITLE", TITLE, LEVEL_HOST }, /* for refer formats */ { "%E", "2ND_AUTHOR",PERSON, LEVEL_MAIN }, @@ -33,7 +33,7 @@ { "%Y", "AUTHOR", PERSON, LEVEL_SERIES }, { "%S", "TITLE", TITLE, LEVEL_SERIES }, { "%7", "EDITION", SIMPLE, LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%9", "GENRE", SIMPLE, LEVEL_MAIN }, { "%?", "SUB_AUTHOR", PERSON, LEVEL_MAIN }, /* subsidiary-authors */ { "%!", "SHORTTITLE", TITLE, LEVEL_MAIN }, @@ -53,7 +53,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%>", "PDFLINK", SIMPLE, LEVEL_MAIN }, { "%Z", "NOTES", SIMPLE, LEVEL_MAIN }, { "%W", "PHYSICALLOC", SIMPLE, LEVEL_MAIN }, /* physical location */ @@ -70,7 +70,7 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR", PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE",SIMPLE, LEVEL_MAIN }, - { "%D", "PARTYEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "PARTDATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%J", "TITLE", TITLE, LEVEL_HOST }, /* journal title */ { "%B", "TITLE", TITLE, LEVEL_HOST }, /* journal title */ @@ -79,7 +79,7 @@ { "%N", "ISSUE", SIMPLE, LEVEL_MAIN }, { "%P", "PAGES", PAGES, LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE, LEVEL_HOST }, - { "%8", "PARTMONTH", DATE, LEVEL_MAIN }, + { "%8", "PARTDATE:MONTH", DATE, LEVEL_MAIN }, { "%9", "GENRE", SIMPLE, LEVEL_MAIN }, { "%!", "SHORTTITLE", TITLE, LEVEL_MAIN }, { "%@", "SERIALNUMBER", SERIALNO, LEVEL_HOST }, @@ -91,7 +91,7 @@ { "%F", "REFNUM", SIMPLE, LEVEL_MAIN }, { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, @@ -120,7 +120,7 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "PARTYEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "PARTDATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE", TITLE, LEVEL_MAIN }, { "%J", "TITLE", TITLE, LEVEL_HOST }, /* magazine name */ { "%B", "TITLE", TITLE, LEVEL_HOST }, /* magazine name */ @@ -129,7 +129,7 @@ { "%N", "ISSUE", SIMPLE, LEVEL_MAIN }, { "%P", "PAGES", PAGES, LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE, LEVEL_HOST }, - { "%8", "PARTMONTH", DATE, LEVEL_MAIN }, + { "%8", "PARTDATE:MONTH", DATE, LEVEL_MAIN }, { "%!", "SHORTTITLE",TITLE, LEVEL_MAIN }, { "%@", "SERIALNUMBER", SERIALNO,LEVEL_HOST }, { "%(", "TITLE", SIMPLE, LEVEL_ORIG }, /* original pub */ @@ -140,7 +140,7 @@ { "%F", "REFNUM", SIMPLE, LEVEL_MAIN }, { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%O", "NOTES", SIMPLE, LEVEL_MAIN }, { "%Z", "NOTES", SIMPLE, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, @@ -168,7 +168,7 @@ { "%A", "REPORTER", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "PARTYEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "PARTDATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%J", "TITLE", TITLE, LEVEL_HOST }, /* newspaper name */ { "%B", "TITLE", TITLE, LEVEL_HOST }, /* newspaper name */ @@ -177,7 +177,7 @@ { "%N", "ISSUE", SIMPLE, LEVEL_MAIN }, { "%P", "PAGES", PAGES, LEVEL_MAIN }, { "%7", "EDITION", SIMPLE, LEVEL_MAIN }, - { "%8", "PARTMONTH", DATE, LEVEL_MAIN }, + { "%8", "PARTDATE:MONTH", DATE, LEVEL_MAIN }, { "%!", "SHORTTITLE",TITLE, LEVEL_MAIN }, { "%@", "SERIALNUMBER", SERIALNO, LEVEL_MAIN }, { "%(", "TITLE", SIMPLE, LEVEL_ORIG }, /* original pub */ @@ -188,7 +188,7 @@ { "%F", "REFNUM", SIMPLE, LEVEL_MAIN }, { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%O", "NOTES", SIMPLE, LEVEL_MAIN }, { "%Z", "NOTES", SIMPLE, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, @@ -215,7 +215,7 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%E", "AUTHOR", PERSON, LEVEL_HOST }, /* SERIES_AUTHOR */ { "%B", "TITLE", TITLE, LEVEL_HOST }, /* SERIES_TITLE */ @@ -225,7 +225,7 @@ { "%V", "VOLUME" , SIMPLE, LEVEL_MAIN }, { "%N", "NUMBER", SIMPLE, LEVEL_MAIN }, { "%6", "NUMVOLUMES",SIMPLE, LEVEL_MAIN }, - { "%P", "TOTALPAGES", SIMPLE,LEVEL_MAIN }, + { "%P", "PAGES:TOTAL", SIMPLE,LEVEL_MAIN }, { "%7", "EDITION", SIMPLE, LEVEL_MAIN }, { "%?", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%!", "SHORTTITLE",TITLE, LEVEL_MAIN }, @@ -244,7 +244,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", SIMPLE, LEVEL_MAIN }, { "%+", "AUTHORADDRESS",SIMPLE, LEVEL_MAIN }, { "%>", "PDFLINK", SIMPLE, LEVEL_MAIN }, @@ -264,7 +264,7 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_HOST }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_HOST }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%E", "EDITOR", PERSON, LEVEL_HOST }, /* editor for book */ { "%B", "TITLE", TITLE, LEVEL_HOST }, /* book title */ @@ -294,7 +294,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", SIMPLE, LEVEL_MAIN }, { "%+", "AUTHORADDRESS",SIMPLE, LEVEL_MAIN }, { "%>", "PDFLINK", SIMPLE, LEVEL_MAIN }, @@ -315,7 +315,7 @@ { "%A", "EDITOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%E", "EDITOR", PERSON, LEVEL_HOST }, /* SERIES_EDITOR */ { "%B", "TITLE", TITLE, LEVEL_HOST }, /* SERIES_TITLE */ @@ -324,7 +324,7 @@ { "%N", "NUMBER", SIMPLE, LEVEL_MAIN }, { "%V", "VOLUME" , SIMPLE, LEVEL_MAIN }, { "%6", "NUMVOLUMES",SIMPLE, LEVEL_HOST }, - { "%P", "TOTALPAGES", SIMPLE,LEVEL_MAIN }, + { "%P", "PAGES:TOTAL", SIMPLE,LEVEL_MAIN }, { "%7", "EDITION", SIMPLE, LEVEL_MAIN }, { "%?", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%!", "SHORTTITLE",TITLE, LEVEL_MAIN }, @@ -343,7 +343,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%+", "AUTHORADDRESS",SIMPLE, LEVEL_MAIN }, { "%>", "PDFLINK", SIMPLE, LEVEL_MAIN }, @@ -363,13 +363,13 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE", TITLE, LEVEL_MAIN }, { "%B", "TITLE", TITLE, LEVEL_HOST }, /* COLLECTION_TITLE */ { "%C", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "%N", "NUMBER", SIMPLE, LEVEL_MAIN }, { "%P", "PAGES", PAGES, LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%9", "GENRE", SIMPLE, LEVEL_MAIN }, { "%!", "SHORTTITLE",TITLE, LEVEL_MAIN }, { "%M", "ACCESSNUM", SIMPLE, LEVEL_MAIN }, @@ -378,7 +378,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -403,13 +403,13 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%E", "RECIPIENT", PERSON, LEVEL_MAIN }, { "%C", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "%V", "VOLUME", SIMPLE, LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%9", "GENRE", SIMPLE, LEVEL_MAIN }, { "%!", "SHORTTITLE",TITLE, LEVEL_MAIN }, { "%M", "ACCESSNUM", SIMPLE, LEVEL_MAIN }, @@ -418,7 +418,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -442,7 +442,7 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_HOST }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_HOST }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%E", "EDITOR", PERSON, LEVEL_MAIN }, { "%B", "TITLE", SIMPLE, LEVEL_HOST }, @@ -455,7 +455,7 @@ { "%Y", "EDITOR", PERSON, LEVEL_SERIES }, { "%S", "TITLE", TITLE, LEVEL_SERIES }, { "%7", "EDITION", SIMPLE, LEVEL_HOST }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%!", "SHORTTITLE",TITLE, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -469,7 +469,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%+", "AUTHORADDRESS",SIMPLE,LEVEL_MAIN}, { "%>", "PDFLINK", SIMPLE, LEVEL_MAIN }, @@ -488,7 +488,7 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR", PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE",SIMPLE, LEVEL_MAIN }, - { "%D", "PARTYEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "PARTDATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%J", "TITLE", TITLE, LEVEL_HOST }, /* journal title */ { "%B", "TITLE", TITLE, LEVEL_HOST }, /* journal title */ @@ -497,7 +497,7 @@ { "%N", "ISSUE", SIMPLE, LEVEL_MAIN }, { "%P", "PAGES", PAGES, LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE, LEVEL_HOST }, - { "%8", "PARTMONTH", DATE, LEVEL_MAIN }, + { "%8", "PARTDATE:MONTH", DATE, LEVEL_MAIN }, { "%9", "GENRE", SIMPLE, LEVEL_MAIN }, { "%!", "SHORTTITLE", TITLE, LEVEL_MAIN }, { "%@", "SERIALNUMBER", SERIALNO, LEVEL_HOST }, @@ -509,7 +509,7 @@ { "%F", "REFNUM", SIMPLE, LEVEL_MAIN }, { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, @@ -535,15 +535,15 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR", PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%B", "ACADEMIC_DEPARTMENT", SIMPLE, LEVEL_MAIN }, { "%C", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE, LEVEL_MAIN }, { "%V", "VOLUME", SIMPLE, LEVEL_MAIN }, - { "%P", "NUMPAGES", PAGES, LEVEL_MAIN }, + { "%P", "PAGES:TOTAL", PAGES, LEVEL_MAIN }, { "%9", "GENRE", SIMPLE, LEVEL_MAIN }, /* thesis type */ - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%!", "SHORTTITLE", TITLE, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -557,7 +557,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%+", "AUTHORADDRESS",SIMPLE, LEVEL_MAIN }, { "%>", "PDFLINK", SIMPLE, LEVEL_MAIN }, @@ -576,7 +576,7 @@ { "%A", "AUTHOR", PERSON , LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE , LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE , LEVEL_MAIN }, { "%T", "TITLE" , TITLE , LEVEL_MAIN }, { "%C", "ADDRESS", SIMPLE , LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE , LEVEL_MAIN }, @@ -588,7 +588,7 @@ { "%K", "KEYWORD", SIMPLE , LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE , LEVEL_MAIN }, { "%O", "NOTES", SIMPLE , LEVEL_MAIN }, - { "%U", "URL", SIMPLE , LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", SIMPLE , LEVEL_MAIN }, { "%1", "COMPUTER", SIMPLE , LEVEL_MAIN }, { "%2", "CUSTOM2", SIMPLE , LEVEL_MAIN }, @@ -613,14 +613,14 @@ { "%A", "WRITER", PERSON , LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE , LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE , LEVEL_MAIN }, { "%T", "TITLE" , TITLE , LEVEL_MAIN }, { "%B", "TITLE", TITLE , LEVEL_HOST }, /* COLLECTION_TITLE */ { "%C", "ADDRESS", SIMPLE , LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE , LEVEL_MAIN }, { "%V", "EXTENTOFWORK", SIMPLE , LEVEL_MAIN }, { "%N", "NUMBER", SIMPLE , LEVEL_MAIN }, - { "%8", "MONTH", DATE , LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE , LEVEL_MAIN }, { "%9", "GENRE", SIMPLE , LEVEL_MAIN }, { "%?", "PERFORMER", PERSON , LEVEL_MAIN }, { "%!", "SHORTTITLE",TITLE , LEVEL_MAIN }, @@ -630,7 +630,7 @@ { "%K", "KEYWORD", SIMPLE , LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE , LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE , LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -654,14 +654,14 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR", PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%E", "DIRECTOR", PERSON, LEVEL_MAIN }, { "%B", "TITLE", TITLE, LEVEL_HOST }, /* SERIES_TITLE */ { "%C", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE, LEVEL_MAIN }, { "%Y", "PRODUCER", PERSON, LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%9", "GENRE", SIMPLE, LEVEL_MAIN }, { "%!", "SHORTTITLE", TITLE, LEVEL_MAIN }, { "%@", "SERIALNUMBER", SERIALNO, LEVEL_MAIN }, @@ -672,7 +672,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", SIMPLE, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -696,7 +696,7 @@ { "%A", "AUTHOR", PERSON , LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE , LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE , LEVEL_MAIN }, { "%T", "TITLE" , TITLE , LEVEL_MAIN }, { "%C", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE , LEVEL_MAIN }, @@ -717,7 +717,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%V", "VOLUME", SIMPLE, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%W", "PHYSICALLOC", SIMPLE, LEVEL_MAIN }, /* physical location */ @@ -737,7 +737,7 @@ { "%A", "AUTHOR", PERSON , LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE , LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE , LEVEL_MAIN }, { "%T", "TITLE" , TITLE , LEVEL_MAIN }, { "%C", "ADDRESS", SIMPLE, LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE , LEVEL_MAIN }, @@ -758,7 +758,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%V", "VOLUME", SIMPLE, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%W", "PHYSICALLOC", SIMPLE, LEVEL_MAIN }, /* physical location */ @@ -778,11 +778,11 @@ { "%A", "ARTIST", PERSON , LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE , LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE , LEVEL_MAIN }, { "%T", "TITLE" , TITLE , LEVEL_MAIN }, { "%C", "ADDRESS", SIMPLE , LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE , LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%9", "GENRE", SIMPLE, LEVEL_MAIN }, { "%!", "SHORTTITLE", TITLE, LEVEL_MAIN }, { "%M", "ACCESSNUM", SIMPLE, LEVEL_MAIN }, @@ -791,7 +791,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -815,12 +815,12 @@ { "%A", "AUTHOR", PERSON , LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE , LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE , LEVEL_MAIN }, { "%T", "TITLE" , TITLE , LEVEL_MAIN }, { "%C", "ADDRESS", SIMPLE , LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE, LEVEL_MAIN }, { "%P", "PAGES", PAGES, LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%9", "GENRE", SIMPLE, LEVEL_MAIN }, { "%N", "NUMBER", SIMPLE, LEVEL_MAIN }, { "%@", "SERIALNUMBER", SERIALNO, LEVEL_MAIN }, @@ -831,7 +831,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -856,7 +856,7 @@ { "%A", "CARTOGRAPHER", PERSON , LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE , LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE , LEVEL_MAIN }, { "%T", "TITLE" , TITLE , LEVEL_MAIN }, { "%C", "ADDRESS", SIMPLE , LEVEL_MAIN }, { "%I", "PUBLISHER", SIMPLE , LEVEL_MAIN }, @@ -869,7 +869,7 @@ { "%K", "KEYWORD", SIMPLE , LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE , LEVEL_MAIN }, { "%O", "NOTES", SIMPLE , LEVEL_MAIN }, - { "%U", "URL", SIMPLE , LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", SIMPLE , LEVEL_MAIN }, { "%1", "SCALE", SIMPLE , LEVEL_MAIN }, { "%2", "CUSTOM2", SIMPLE , LEVEL_MAIN }, @@ -894,7 +894,7 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%B", "PUBLISHED_SOURCE", SIMPLE, LEVEL_MAIN}, { "%C", "COUNTRY", SIMPLE, LEVEL_MAIN }, @@ -909,7 +909,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", SIMPLE, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", SIMPLE, LEVEL_MAIN }, { "%1", "SCALE", SIMPLE, LEVEL_MAIN }, { "%2", "CUSTOM2", SIMPLE, LEVEL_MAIN }, @@ -931,7 +931,7 @@ static lookups hearing[] = { { "%0", "INTERNAL_TYPE", TYPE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%H", "TRANSLATOR", PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, @@ -940,10 +940,10 @@ { "%I", "PUBLISHER", SIMPLE, LEVEL_MAIN }, { "%6", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, { "%N", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "%P", "NUMPAGES", PAGES, LEVEL_MAIN }, + { "%P", "PAGES:TOTAL", PAGES, LEVEL_MAIN }, { "%S", "LEGISLATIVEBODY:CORP", SIMPLE, LEVEL_MAIN }, { "%7", "SESSION", SIMPLE, LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%!", "SHORTTITLE", TITLE, LEVEL_MAIN }, { "%(", "TITLE", SIMPLE, LEVEL_ORIG }, /* orig publication */ { "%M", "ACCESSNUM", SIMPLE, LEVEL_MAIN }, @@ -952,7 +952,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -973,7 +973,7 @@ static lookups bill[] = { { "%0", "INTERNAL_TYPE", TYPE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, @@ -984,7 +984,7 @@ { "%&", "CODESECTION",SIMPLE, LEVEL_MAIN }, { "%S", "LEGISLATIVEBODY:CORP", SIMPLE, LEVEL_MAIN }, { "%7", "SESSION", SIMPLE, LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%?", "SPONSOR", PERSON, LEVEL_MAIN }, { "%!", "SHORTTITLE",TITLE, LEVEL_MAIN }, { "%(", "TITLE", SIMPLE, LEVEL_ORIG }, /* original pub */ @@ -994,7 +994,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -1015,7 +1015,7 @@ static lookups statute[] = { { "%0", "INTERNAL_TYPE", TYPE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, @@ -1025,7 +1025,7 @@ { "%P", "PAGES", PAGES, LEVEL_MAIN }, { "%&", "SECTION", SIMPLE, LEVEL_MAIN }, { "%7", "SESSION", SIMPLE, LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%!", "SHORTTITLE",TITLE, LEVEL_MAIN }, { "%(", "TITLE", SIMPLE, LEVEL_ORIG }, /* original pub */ { "%M", "ACCESSNUM", SIMPLE, LEVEL_MAIN }, @@ -1034,7 +1034,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -1055,7 +1055,7 @@ static lookups lawcase[] = { { "%0", "INTERNAL_TYPE", TYPE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, @@ -1065,7 +1065,7 @@ { "%V", "VOLUME", SIMPLE, LEVEL_MAIN }, { "%N", "PUBLICLAWNUMBER", SIMPLE, LEVEL_MAIN }, { "%P", "STARTPAGE", SIMPLE, LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%?", "COUNSEL", PERSON, LEVEL_MAIN }, { "%!", "SHORTTITLE",TITLE, LEVEL_MAIN }, { "%(", "TITLE", SIMPLE, LEVEL_ORIG }, /* original pub */ @@ -1075,7 +1075,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%1", "CUSTOM1", NOTES, LEVEL_MAIN }, { "%2", "CUSTOM2", NOTES, LEVEL_MAIN }, @@ -1099,7 +1099,7 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%J", "TITLE", TITLE, LEVEL_HOST }, /* for refer formats */ { "%E", "2ND_AUTHOR",PERSON, LEVEL_MAIN }, @@ -1114,7 +1114,7 @@ { "%Y", "AUTHOR", PERSON, LEVEL_SERIES }, { "%S", "TITLE", TITLE, LEVEL_SERIES }, { "%7", "EDITION", SIMPLE, LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%9", "GENRE", SIMPLE, LEVEL_MAIN }, { "%?", "SUB_AUTHOR", PERSON, LEVEL_MAIN }, /* subsidiary-authors */ { "%!", "SHORTTITLE", TITLE, LEVEL_MAIN }, @@ -1134,7 +1134,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%W", "PHYSICALLOC", SIMPLE, LEVEL_MAIN }, /* physical location */ { "%+", "AUTHORADDRESS",SIMPLE, LEVEL_MAIN }, @@ -1152,7 +1152,7 @@ { "%A", "AUTHOR", PERSON, LEVEL_MAIN }, { "%H", "TRANSLATOR",PERSON, LEVEL_MAIN }, { "%Q", "TRANSLATEDTITLE", SIMPLE, LEVEL_MAIN }, - { "%D", "YEAR", SIMPLE, LEVEL_MAIN }, + { "%D", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, { "%T", "TITLE" , TITLE, LEVEL_MAIN }, { "%J", "TITLE", TITLE, LEVEL_HOST }, /* for refer formats */ { "%E", "2ND_AUTHOR",PERSON, LEVEL_MAIN }, @@ -1167,7 +1167,7 @@ { "%Y", "AUTHOR", PERSON, LEVEL_SERIES }, { "%S", "TITLE", TITLE, LEVEL_SERIES }, { "%7", "EDITION", SIMPLE, LEVEL_MAIN }, - { "%8", "MONTH", DATE, LEVEL_MAIN }, + { "%8", "DATE:MONTH", DATE, LEVEL_MAIN }, { "%9", "GENRE", SIMPLE, LEVEL_MAIN }, { "%?", "SUB_AUTHOR", PERSON, LEVEL_MAIN }, /* subsidiary-authors */ { "%!", "SHORTTITLE", TITLE, LEVEL_MAIN }, @@ -1187,7 +1187,7 @@ { "%K", "KEYWORD", SIMPLE, LEVEL_MAIN }, { "%X", "ABSTRACT", SIMPLE, LEVEL_MAIN }, { "%O", "NOTES", NOTES, LEVEL_MAIN }, - { "%U", "URL", SIMPLE, LEVEL_MAIN }, + { "%U", "URL", URL, LEVEL_MAIN }, { "%>", "PDFLINK", SIMPLE, LEVEL_MAIN }, { "%Z", "NOTES", NOTES, LEVEL_MAIN }, { "%W", "PHYSICALLOC", SIMPLE, LEVEL_MAIN }, /* physical location */ diff --git a/bibutils/endxmlin.c b/bibutils/endxmlin.c --- a/bibutils/endxmlin.c +++ b/bibutils/endxmlin.c @@ -1,28 +1,37 @@ /* * endxmlin.c * - * Copyright (c) Chris Putnam 2006-2014 + * Copyright (c) Chris Putnam 2006-2017 * * Program and source code released under the GPL version 2 * */ #include #include -#include "newstr.h" -#include "newstr_conv.h" +#include "str.h" +#include "str_conv.h" #include "fields.h" #include "name.h" #include "xml.h" #include "xml_encoding.h" #include "reftypes.h" -#include "endxmlin.h" -#include "endin.h" +#include "bibformats.h" typedef struct { char *attrib; char *internal; } attribs; +extern variants end_all[]; +extern int end_nall; + +static int endxmlin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int endxmlin_processf( fields *endin, char *p, char *filename, long nref, param *pm ); +extern int endin_typef( fields *endin, char *filename, int nrefs, param *p ); +extern int endin_convertf( fields *endin, fields *info, int reftype, param *p ); +extern int endin_cleanf( bibl *bin, param *p ); + + /***************************************************** PUBLIC: void endxmlin_initparams() *****************************************************/ @@ -48,8 +57,8 @@ p->all = end_all; p->nall = end_nall; - list_init( &(p->asis) ); - list_init( &(p->corps) ); + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); if ( !progname ) p->progname = NULL; else p->progname = strdup( progname ); @@ -66,14 +75,13 @@ return 1; } -int -endxmlin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, - newstr *reference, int *fcharset ) +static int +endxmlin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) { - newstr tmp; + str tmp; char *startptr = NULL, *endptr = NULL; int haveref = 0, inref = 0, done = 0, file_charset = CHARSET_UNKNOWN, m; - newstr_init( &tmp ); + str_init( &tmp ); while ( !haveref && !done ) { if ( line->data ) { if ( !inref ) { @@ -90,21 +98,21 @@ int n = 8; char *p = &(line->data[line->len-1]); while ( *p && n ) { p--; n--; } - newstr_segdel( line, line->data, p ); + str_segdel( line, line->data, p ); } } if ( !startptr || !endptr ) { done = xml_readmore( fp, buf, bufsize, bufpos ); - newstr_strcat( line, buf ); + str_strcatc( line, buf ); } else { - /* we can reallocate in the newstr_strcat, so re-find */ + /* we can reallocate in the str_strcat, so re-find */ startptr = xml_findstart( line->data, "RECORD" ); endptr = xml_findend( line->data, "RECORD" ); - newstr_segcpy( reference, startptr, endptr ); + str_segcpy( reference, startptr, endptr ); /* clear out information in line */ - newstr_strcpy( &tmp, endptr ); - newstr_newstrcpy( line, &tmp ); + str_strcpyc( &tmp, endptr ); + str_strcpy( line, &tmp ); haveref = 1; } if ( line->data ) { @@ -112,7 +120,7 @@ if ( m!=CHARSET_UNKNOWN ) file_charset = m; } } - newstr_free( &tmp ); + str_free( &tmp ); *fcharset = file_charset; return haveref; } @@ -139,12 +147,13 @@ * */ static int -endxmlin_datar( xml *node, newstr *s ) +endxmlin_datar( xml *node, str *s ) { int status; - if ( node->value && node->value->len ) { - newstr_strcat( s, node->value->data ); - if ( newstr_memerr( s ) ) return BIBL_ERR_MEMERR; + + if ( str_has_value( node->value ) ) { + str_strcat( s, node->value ); + if ( str_memerr( s ) ) return BIBL_ERR_MEMERR; } if ( node->down && xml_tagexact( node->down, "style" ) ) { status = endxmlin_datar( node->down, s ); @@ -154,6 +163,7 @@ status = endxmlin_datar( node->next, s ); if ( status!=BIBL_OK ) return status; } + return BIBL_OK; } @@ -161,15 +171,19 @@ endxmlin_data( xml *node, char *inttag, fields *info, int level ) { int status; - newstr s; - newstr_init( &s ); + str s; + + str_init( &s ); + status = endxmlin_datar( node, &s ); if ( status!=BIBL_OK ) return status; - if ( s.len ) { + + if ( str_has_value( &s ) ) { status = fields_add( info, inttag, s.data, level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - newstr_free( &s ); + + str_free( &s ); return BIBL_OK; } @@ -190,15 +204,15 @@ { "short-title", "SHORTTITLE" }, }; int i, status, n = sizeof( a ) / sizeof ( a[0] ); - newstr title; - newstr_init( &title ); + str title; + str_init( &title ); for ( i=0; idown ) { - newstr_empty( &title ); + str_empty( &title ); status = endxmlin_datar( node, &title ); if ( status!=BIBL_OK ) return BIBL_ERR_MEMERR; - newstr_trimstartingws( &title ); - newstr_trimendingws( &title ); + str_trimstartingws( &title ); + str_trimendingws( &title ); status = fields_add( info, a[i].internal, title.data, 0); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } @@ -207,7 +221,7 @@ status = endxmlin_titles( node->next, info ); if ( status!=BIBL_OK ) return status; } - newstr_free( &title ); + str_free( &title ); return BIBL_OK; } @@ -410,13 +424,14 @@ endxmlin_reftype( xml *node, fields *info ) { int status; - newstr *s; + str *s; + s = xml_getattrib( node, "name" ); - if ( s && s->len ) { - status = fields_add( info, "%0", s->data, 0 ); - newstr_free( s ); + if ( str_has_value( s ) ) { + status = fields_add( info, "%0", str_cstr( s ), 0 ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } + return BIBL_OK; } @@ -523,7 +538,7 @@ endxmlin_assembleref( xml *node, fields *info ) { int status; - if ( node->tag->len==0 ) { + if ( str_is_empty( node->tag ) ) { if ( node->down ) return endxmlin_assembleref( node->down, info ); } else if ( xml_tagexact( node, "RECORD" ) ) { @@ -541,8 +556,8 @@ * this is necessary as the xml format is as nasty and as overloaded * as the tags used in the Refer format output */ -int -endxmlin_processf( fields *fin, char *data, char *filename, long nref ) +static int +endxmlin_processf( fields *fin, char *data, char *filename, long nref, param *pm ) { int status; xml top; diff --git a/bibutils/endxmlin.h b/bibutils/endxmlin.h deleted file mode 100644 --- a/bibutils/endxmlin.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * endxmlin.h - * - * Copyright (c) Chris Putnam 2006-2014 - * - * Source code released under the GPL version 2 - * - */ -#ifndef ENDXMLIN_H -#define ENDXMLIN_H - -#include "newstr.h" -#include "fields.h" -#include "reftypes.h" -#include "bibutils.h" - -extern int endxmlin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, - newstr *line, newstr *reference, int *fcharset ); -extern int endxmlin_processf( fields *endin, char *p, char *filename, long nref ); - -extern void endxmlin_initparams( param *p, const char *progname ); - -#endif diff --git a/bibutils/entities.c b/bibutils/entities.c --- a/bibutils/entities.c +++ b/bibutils/entities.c @@ -1,7 +1,7 @@ /* * entities.c * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/entities.h b/bibutils/entities.h --- a/bibutils/entities.h +++ b/bibutils/entities.h @@ -1,7 +1,7 @@ /* * entities.h * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/fields.c b/bibutils/fields.c --- a/bibutils/fields.c +++ b/bibutils/fields.c @@ -1,7 +1,7 @@ /* * fields.c * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * @@ -36,8 +36,8 @@ int i; for ( i=0; imax; ++i ) { - newstr_free( &(f->tag[i]) ); - newstr_free( &(f->data[i]) ); + str_free( &(f->tag[i]) ); + str_free( &(f->data[i]) ); } if ( f->tag ) free( f->tag ); if ( f->data ) free( f->data ); @@ -52,8 +52,8 @@ { int i, alloc = 20; - f->tag = (newstr *) malloc( sizeof(newstr) * alloc ); - f->data = (newstr *) malloc( sizeof(newstr) * alloc ); + f->tag = (str *) malloc( sizeof(str) * alloc ); + f->data = (str *) malloc( sizeof(str) * alloc ); f->used = (int *) calloc( alloc, sizeof(int) ); f->level = (int *) calloc( alloc, sizeof(int) ); if ( !f->tag || !f->data || !f->used || !f->level ){ @@ -68,8 +68,8 @@ f->max = alloc; f->n = 0; for ( i=0; itag[i]) ); - newstr_init( &(f->data[i]) ); + str_init( &(f->tag[i]) ); + str_init( &(f->data[i]) ); } return FIELDS_OK; } @@ -77,12 +77,12 @@ static int fields_realloc( fields *f ) { - newstr *newtags, *newdata; + str *newtags, *newdata; int *newused, *newlevel; int i, alloc = f->max * 2; - newtags = (newstr*) realloc( f->tag, sizeof(newstr) * alloc ); - newdata = (newstr*) realloc( f->data, sizeof(newstr) * alloc ); + newtags = (str*) realloc( f->tag, sizeof(str) * alloc ); + newdata = (str*) realloc( f->data, sizeof(str) * alloc ); newused = (int*) realloc( f->used, sizeof(int) * alloc ); newlevel= (int*) realloc( f->level, sizeof(int) * alloc ); @@ -97,17 +97,17 @@ f->max = alloc; for ( i=f->n; itag[i]) ); - newstr_init( &(f->data[i]) ); + str_init( &(f->tag[i]) ); + str_init( &(f->data[i]) ); } return FIELDS_OK; } int -fields_add( fields *f, char *tag, char *data, int level ) +_fields_add( fields *f, char *tag, char *data, int level, int mode ) { - int i, status, found; + int i, n, status; if ( !tag || !data ) return FIELDS_OK; @@ -119,38 +119,42 @@ if ( status!=FIELDS_OK ) return status; } - /* Don't duplicate identical entries */ - found = 0; - for ( i=0; in && !found; ++i ) { - if ( f->level[i]==level && - !strcasecmp( f->tag[i].data, tag ) && - !strcasecmp( f->data[i].data, data ) ) found = 1; - } - if ( !found ) { - f->used[ f->n ] = 0; - f->level[ f->n ] = level; - newstr_strcpy( &(f->tag[f->n]), tag ); - newstr_strcpy( &(f->data[f->n]), data ); - if ( newstr_memerr( &(f->tag[f->n]) ) || - newstr_memerr( &(f->data[f->n] ) ) ) - return FIELDS_ERR; - f->n++; + /* Don't duplicate identical entries if FIELDS_NO_DUPS */ + if ( mode == FIELDS_NO_DUPS ) { + for ( i=0; in; i++ ) { + if ( f->level[i]==level && + !strcasecmp( f->tag[i].data, tag ) && + !strcasecmp( f->data[i].data, data ) ) + return FIELDS_OK; + } } + + n = f->n; + f->used[ n ] = 0; + f->level[ n ] = level; + str_strcpyc( &(f->tag[n]), tag ); + str_strcpyc( &(f->data[n]), data ); + + if ( str_memerr( &(f->tag[n]) ) || str_memerr( &(f->data[n] ) ) ) + return FIELDS_ERR; + + f->n++; + return FIELDS_OK; } int -fields_add_tagsuffix( fields *f, char *tag, char *suffix, - char *data, int level ) +_fields_add_tagsuffix( fields *f, char *tag, char *suffix, + char *data, int level, int mode ) { - newstr newtag; + str newtag; int ret; - newstr_init( &newtag ); - newstr_mergestrs( &newtag, tag, suffix, NULL ); - if ( newstr_memerr( &newtag ) ) ret = FIELDS_ERR; - else ret = fields_add( f, newtag.data, data, level ); - newstr_free( &newtag ); + str_init( &newtag ); + str_mergestrs( &newtag, tag, suffix, NULL ); + if ( str_memerr( &newtag ) ) ret = FIELDS_ERR; + else ret = _fields_add( f, newtag.data, data, level, mode ); + str_free( &newtag ); return ret; } @@ -161,7 +165,7 @@ * * level==LEVEL_ANY is a special flag meaning any level can match */ -inline int +int fields_match_level( fields *f, int n, int level ) { if ( level==LEVEL_ANY ) return 1; @@ -174,28 +178,28 @@ * returns 1 if tag matches, 0 if not * */ -inline int +int fields_match_tag( fields *info, int n, char *tag ) { if ( !strcmp( fields_tag( info, n, FIELDS_CHRP ), tag ) ) return 1; return 0; } -inline int +int fields_match_casetag( fields *info, int n, char *tag ) { if ( !strcasecmp( fields_tag( info, n, FIELDS_CHRP ), tag ) ) return 1; return 0; } -inline int +int fields_match_tag_level( fields *info, int n, char *tag, int level ) { if ( !fields_match_level( info, n, level ) ) return 0; return fields_match_tag( info, n, tag ); } -inline int +int fields_match_casetag_level( fields *info, int n, char *tag, int level ) { if ( !fields_match_level( info, n, level ) ) return 0; @@ -268,35 +272,44 @@ int n = fields_find( f, tag, level ); if ( n==-1 ) return fields_add( f, tag, data, level ); else { - newstr_strcpy( &(f->data[n]), data ); - if ( newstr_memerr( &(f->data[n]) ) ) return FIELDS_ERR; + str_strcpyc( &(f->data[n]), data ); + if ( str_memerr( &(f->data[n]) ) ) return FIELDS_ERR; return FIELDS_OK; } } char *fields_null_value = "\0"; -inline int +int fields_used( fields *f, int n ) { if ( n >= 0 && n < f->n ) return f->used[n]; else return 0; } -inline int +int +fields_notag( fields *f, int n ) +{ + str *t; + if ( n >= 0 && n < f->n ) { + t = &( f->tag[n] ); + if ( t->len > 0 ) return 0; + } + return 1; +} + +int fields_nodata( fields *f, int n ) { - newstr *d; + str *d; if ( n >= 0 && n < f->n ) { d = &( f->data[n] ); if ( d->len > 0 ) return 0; - return 1; - } else { - return 1; } + return 1; } -inline int +int fields_num( fields *f ) { return f->n; @@ -311,7 +324,7 @@ * If the length of the tagged value is zero and the mode is * FIELDS_STRP_NOLEN or FIELDS_CHRP_NOLEN, return a pointer to * a static null string as the data field could be new due to - * the way newstr handles initialized strings with no data. + * the way str handles initialized strings with no data. * */ @@ -504,3 +517,20 @@ vplist_free( &tags ); } + +void +fields_report( fields *f, FILE *fp ) +{ + int i, n; + n = fields_num( f ); + fprintf( fp, "# NUM level = LEVEL 'TAG' = 'VALUE'\n" ); + for ( i=0; i -#include "newstr.h" +#include "str.h" #include "vplist.h" -typedef struct { - newstr *tag; - newstr *data; +typedef struct fields { + str *tag; + str *data; int *used; int *level; int n; int max; } fields; -extern void fields_init( fields *f ); -extern fields *fields_new( void ); -extern void fields_free( fields *f ); +void fields_init( fields *f ); +fields *fields_new( void ); +void fields_free( fields *f ); -extern int fields_add( fields *f, char *tag, char *data, int level ); -extern int fields_add_tagsuffix( fields *f, char *tag, char *suffix, - char *data, int level ); +#define FIELDS_CAN_DUP (0) +#define FIELDS_NO_DUPS (1) -extern int fields_maxlevel( fields *f ); -extern void fields_clearused( fields *f ); -extern void fields_setused( fields *f, int n ); -extern int fields_replace_or_add( fields *f, char *tag, char *data, int level ); +#define fields_add( a, b, c, d ) _fields_add( a, b, c, d, FIELDS_NO_DUPS ) +#define fields_add_can_dup( a, b, c, d ) _fields_add( a, b, c, d, FIELDS_CAN_DUP ) +#define fields_add_tagsuffix( a, b, c, d, e ) _fields_add( a, b, c, d, e, FIELDS_NO_DUPS ) +#define fields_add_tagsuffix_can_dup( a, b, c, d, e ) _fields_add( a, b, c, d, e, FIELDS_CAN_DUP ) -extern inline int fields_num( fields *f ); -extern inline int fields_used( fields *f, int n ); -extern inline int fields_nodata( fields *f, int n ); +int _fields_add( fields *f, char *tag, char *data, int level, int mode ); +int _fields_add_tagsuffix( fields *f, char *tag, char *suffix, + char *data, int level, int mode ); -extern inline int fields_match_level( fields *f, int n, int level ); -extern inline int fields_match_tag( fields *f, int n, char *tag ); -extern inline int fields_match_casetag( fields *f, int n, char *tag ); -extern inline int fields_match_tag_level( fields *f, int n, char *tag, int level ); -extern inline int fields_match_casetag_level( fields *f, int n, char *tag, int level ); +int fields_maxlevel( fields *f ); +void fields_clearused( fields *f ); +void fields_setused( fields *f, int n ); +int fields_replace_or_add( fields *f, char *tag, char *data, int level ); +int fields_num( fields *f ); +int fields_used( fields *f, int n ); +int fields_notag( fields *f, int n ); +int fields_nodata( fields *f, int n ); + +int fields_match_level( fields *f, int n, int level ); +int fields_match_tag( fields *f, int n, char *tag ); +int fields_match_casetag( fields *f, int n, char *tag ); +int fields_match_tag_level( fields *f, int n, char *tag, int level ); +int fields_match_casetag_level( fields *f, int n, char *tag, int level ); + +void fields_report( fields *f, FILE *fp ); + #define FIELDS_STRP_FLAG (2) #define FIELDS_POSP_FLAG (4) #define FIELDS_NOLENOK_FLAG (8) @@ -69,16 +80,16 @@ #define FIELDS_CHRP_NOUSE ( 0 ) #define FIELDS_STRP_NOUSE ( FIELDS_STRP_FLAG ) -extern void *fields_tag( fields *f, int n, int mode ); -extern void *fields_value( fields *f, int n, int mode ); -extern int fields_level( fields *f, int n ); +void *fields_tag( fields *f, int n, int mode ); +void *fields_value( fields *f, int n, int mode ); +int fields_level( fields *f, int n ); -extern int fields_find( fields *f, char *searchtag, int level ); +int fields_find( fields *f, char *searchtag, int level ); -extern void *fields_findv( fields *f, int level, int mode, char *tag ); -extern void *fields_findv_firstof( fields *f, int level, int mode, ... ); +void *fields_findv( fields *f, int level, int mode, char *tag ); +void *fields_findv_firstof( fields *f, int level, int mode, ... ); -extern void fields_findv_each( fields *f, int level, int mode, vplist *a, char *tag ); -extern void fields_findv_eachof( fields *f, int level, int mode, vplist *a, ... ); +void fields_findv_each( fields *f, int level, int mode, vplist *a, char *tag ); +void fields_findv_eachof( fields *f, int level, int mode, vplist *a, ... ); #endif diff --git a/bibutils/gb18030.h b/bibutils/gb18030.h --- a/bibutils/gb18030.h +++ b/bibutils/gb18030.h @@ -1,7 +1,7 @@ /* * gb18030.h * - * Copyright (c) Chris Putnam 2008-2013 + * Copyright (c) Chris Putnam 2008-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/generic.c b/bibutils/generic.c new file mode 100644 --- /dev/null +++ b/bibutils/generic.c @@ -0,0 +1,81 @@ +/* generic.c + * + * Copyright (c) Chris Putnam 2016-2017 + * + * Source code released under GPL version 2 + * + * xxxx_convertf() stubs that can be shared. + */ +#include "name.h" +#include "notes.h" +#include "pages.h" +#include "serialno.h" +#include "title.h" +#include "url.h" +#include "generic.h" + +/* stub for processtypes that aren't used, such as DEFAULT and ALWAYS handled by bibcore.c */ +int +generic_null( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + return BIBL_OK; +} + +int +generic_url( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + return urls_split_and_add( invalue->data, bibout, level ); +} + +int +generic_notes( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + if ( notes_add( bibout, invalue, level ) ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + +int +generic_pages( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + if ( pages_add( bibout, outtag, invalue, level ) ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + +int +generic_person( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + if ( name_add( bibout, outtag, invalue->data, level, &(pm->asis), &(pm->corps) ) ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + +int +generic_serialno( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + if ( addsn( bibout, invalue->data, level ) ) return BIBL_OK; + return BIBL_ERR_MEMERR; +} + +/* SIMPLE = just copy */ +int +generic_simple( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + if ( fields_add( bibout, outtag, invalue->data, level ) == FIELDS_OK ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + +/* just like generic_null(), but useful if we need one that isn't identical to generic_null() ala biblatexin.c */ +int +generic_skip( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + fields_setused( bibin, n ); + return BIBL_OK; +} + +int +generic_title( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + if ( title_process( bibout, outtag, invalue->data, level, pm->nosplittitle ) ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + + diff --git a/bibutils/generic.h b/bibutils/generic.h new file mode 100644 --- /dev/null +++ b/bibutils/generic.h @@ -0,0 +1,23 @@ +/* generic.h + * + * Copyright (c) Chris Putnam 2016-2017 + * + * Source code released under GPL version 2 + * + */ +#ifndef GENERIC_H +#define GENERIC_H + +#include "bibutils.h" + +int generic_null ( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ); +int generic_url ( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ); +int generic_notes ( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ); +int generic_pages ( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ); +int generic_person ( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ); +int generic_serialno( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ); +int generic_simple ( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ); +int generic_skip ( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ); +int generic_title ( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ); + +#endif diff --git a/bibutils/intlist.c b/bibutils/intlist.c --- a/bibutils/intlist.c +++ b/bibutils/intlist.c @@ -1,79 +1,142 @@ /* * intlist.c * - * Copyright (c) Chris Putnam 2007-2013 + * Copyright (c) Chris Putnam 2007-2017 * - * Version 9/5/2013 + * Version 1/12/2017 * * Source code released under the GPL version 2 * * Implements a simple managed array of ints * */ +#include +#include #include "intlist.h" +#define INTLIST_MINALLOC (20) + static int -intlist_alloc( intlist *il ) +intlist_validn( intlist *il, int n ) { - int alloc = 20, i; - il->data = ( int * ) malloc( sizeof( int ) * alloc ); - if ( !(il->data) ) return 0; - for ( i=0; idata[i] = 0; - il->max = alloc; - il->n = 0; + if ( n < 0 || n >= il->n ) return 0; return 1; } +int +intlist_wasfound( intlist *il, int n ) +{ + if ( n!=-1 ) return 1; + else return 0; +} + +int +intlist_wasnotfound( intlist *il, int n ) +{ + if ( n==-1 ) return 1; + else return 0; +} + static int -intlist_realloc( intlist *il ) +intlist_alloc( intlist *il, int alloc_size ) { - int *more; - int alloc = il->max * 2, i; - more = ( int * ) realloc( il->data, sizeof( int ) * alloc ); - if ( !more ) return 0; + il->data = ( int * ) calloc( alloc_size, sizeof( int ) ); + if ( !(il->data) ) return INTLIST_MEMERR; + il->max = alloc_size; + il->n = 0; + return INTLIST_OK; +} + +static int +intlist_realloc( intlist *il, int alloc_size ) +{ + int i, *more; + + more = ( int * ) realloc( il->data, sizeof( int ) * alloc_size ); + if ( !more ) return INTLIST_MEMERR; + il->data = more; - for ( i=il->max; imax = alloc_size; + + for ( i=il->max; idata[i] = 0; - il->max = alloc; - return 1; + + return INTLIST_OK; } +static int +intlist_ensure_space( intlist *il, int n ) +{ + int alloc = n; + + if ( il->max == 0 ) { + if ( alloc < INTLIST_MINALLOC ) alloc = INTLIST_MINALLOC; + return intlist_alloc( il, alloc ); + } + + else if ( il->max <= n ) { + if ( alloc < il->max * 2 ) alloc = il->max * 2; + return intlist_realloc( il, alloc ); + } + + return INTLIST_OK; +} + /* intlist_add() * - * Returns position of newly added value in range [0,n), -1 on error + * Returns INTLIST_OK/INTLIST_MEMERR */ int intlist_add( intlist *il, int value ) { - if ( il->max==0 ) { - if ( !intlist_alloc( il ) ) return -1; - } else if ( il->n >= il->max ) { - if ( !intlist_realloc( il ) ) return -1; + int status; + + assert( il ); + + status = intlist_ensure_space( il, il->n+1 ); + + if ( status == INTLIST_OK ) { + il->data[ il->n ] = value; + il->n++; } - il->data[ il->n ] = value; - il->n++; - return il->n - 1; + + return status; } /* intlist_add_unique() * - * Returns position of newly added (or previously added) value - * Returns -1 on (memory) error + * Returns INTLIST_OK/INTLIST_MEMERR */ int intlist_add_unique( intlist *il, int value ) { int n; + + assert( il ); + n = intlist_find( il, value ); - if ( n==-1 ) - n = intlist_add( il, value ); - return n; + if ( intlist_wasnotfound( il, n ) ) + return intlist_add( il, value ); + else + return INTLIST_OK; } + int intlist_find_or_add( intlist *il, int value ) { - return intlist_add_unique( il, value ); + int n, status; + + n = intlist_find( il, value ); + + if ( intlist_wasfound( il, n ) ) { + return n; + } + + else { + status = intlist_add( il, value ); + if ( status!=INTLIST_OK ) return -1; + else return il->n - 1; + } } /* intlist_find() @@ -85,56 +148,74 @@ intlist_find( intlist *il, int value ) { int i; + + assert( il ); + for ( i=0; in; ++i ) if ( il->data[i]==value ) return i; + return -1; } -static void +static int intlist_remove_pos_core( intlist *il, int pos ) { int i; + + assert( il ); + for ( i=pos; in-1; ++i ) il->data[i] = il->data[i+1]; il->n -= 1; + + return INTLIST_OK; } /* intlist_remove_pos() * - * Returns 1 on success, 0 on failure. + * Returns INTLIST_OK on success. */ int intlist_remove_pos( intlist *il, int pos ) { - if ( pos < 0 || pos >= il->n ) return 0; - intlist_remove_pos_core( il, pos ); - return 1; + assert( il ); + assert( intlist_validn( il, pos ) ); + + return intlist_remove_pos_core( il, pos ); } /* intlist_remove() * * Removes first instance of value from the intlist. - * Returns 1 on success, 0 on error. + * Returns INTLIST_OK/INTLIST_VALUE_MISSING */ int intlist_remove( intlist *il, int value ) { - int pos = intlist_find( il, value ); - if ( pos==-1 ) return 0; - intlist_remove_pos_core( il, pos ); - return 1; + int pos; + + assert( il ); + + pos = intlist_find( il, value ); + if ( pos==-1 ) return INTLIST_VALUE_MISSING; + + return intlist_remove_pos_core( il, pos ); } /* don't actually free space, just reset counter */ void intlist_empty( intlist *il ) { + assert( il ); + il->n = 0; } void intlist_free( intlist *il ) { + assert( il ); + if ( il->data ) free( il->data ); intlist_init( il ); } @@ -142,33 +223,41 @@ void intlist_delete( intlist *il ) { - intlist_free( il ); + assert( il ); + + if ( il->data ) free( il->data ); free( il ); } void intlist_init( intlist *il ) { + assert( il ); + il->data = NULL; il->max = 0; il->n = 0; } +/* Returns INTLIST_OK/INTLIST_MEMERR + */ +int +intlist_init_fill( intlist *il, int n, int v ) +{ + intlist_init( il ); + return intlist_fill( il, n, v ); +} + /* intlist_init_range() * * Initializes intlist to values from [low,high) with step step. - * Returns -1 on failure, number of elements on success. + * Returns INTLIST_OK/INTLIST_MEMERR. */ int intlist_init_range( intlist *il, int low, int high, int step ) { - int i, n; intlist_init( il ); - for ( i=low; in; + return intlist_fill_range( il, low, high, step ); } /* intlist_new() @@ -179,25 +268,27 @@ intlist * intlist_new( void ) { - intlist *il = ( intlist * ) malloc( sizeof( intlist ) ); + intlist *il; + il = ( intlist * ) malloc( sizeof( intlist ) ); if ( il ) intlist_init( il ); return il; } /* intlist_new_range() * - * Allocates a intlist initialized to values from [low,high) with step step. - * Returns pointer to intlist on success, NULL on memory error; + * Allocates a intlist initialized to values from [low,high) in increments of step. + * Returns pointer to intlist on success, NULL on memory error. */ intlist * intlist_new_range( int low, int high, int step ) { intlist *il; - int n; - il = ( intlist * ) malloc( sizeof( intlist ) ); + int status; + + il = intlist_new(); if ( il ) { - n = intlist_init_range( il, low, high, step ); - if ( n==-1 ) { + status = intlist_fill_range( il, low, high, step ); + if ( status==INTLIST_MEMERR ) { intlist_free( il ); free( il ); il = NULL; @@ -206,6 +297,96 @@ return il; } +/* intlist_new_range() + * + * Allocates a intlist initialized to n elements with value v. + * Returns pointer to intlist on success, NULL on memory error. + */ +intlist * +intlist_new_fill( int n, int v ) +{ + intlist *il; + int status; + + il = intlist_new(); + if ( il ) { + status = intlist_fill( il, n, v ); + if ( status==INTLIST_MEMERR ) { + intlist_free( il ); + free( il ); + il = NULL; + } + } + return il; +} + +/* intlist_fill() + * + * Fill an intlist with n elements of value v. + * + * Returns INTLIST_OK or INTLIST_MEMERR. + */ +int +intlist_fill( intlist *il, int n, int v ) +{ + int i, status; + + assert ( n > 0 ); + + status = intlist_ensure_space( il, n ); + + if ( status==INTLIST_OK ) { + + for ( i=0; idata[i] = v; + + il->n = n; + + } + + return status; +} + +/* intlist_fill_range() + * + * Fill an intlist with the values [low,high) in increments of step + * + * Returns INTLIST_OK or INTLIST_MEMERR. + */ +int +intlist_fill_range( intlist *il, int low, int high, int step ) +{ + int i, n, status; + + n = ( high - low ) / step + 1; + + assert ( n > 0 ); + + status = intlist_ensure_space( il, n ); + + if ( status==INTLIST_OK ) { + + il->n = 0; + + /* ...fill intlist with range */ + if ( step > 0 ) { + for ( i=low; idata[il->n] = i; + il->n += 1; + } + } + else { + for ( i=low; i>high; i+=step ) { + il->data[il->n] = i; + il->n += 1; + } + } + + } + + return status; +} + static int intcomp( const void *v1, const void *v2 ) { @@ -219,6 +400,8 @@ void intlist_sort( intlist *il ) { + assert( il ); + qsort( il->data, il->n, sizeof( int ), intcomp ); } @@ -243,6 +426,9 @@ intlist_randomize( intlist *il ) { int i, j; + + assert( il ); + if ( il->n < 2 ) return; for ( i=0; in; ++i ) { j = randomint( i, il->n ); @@ -251,18 +437,27 @@ } } -/* Returns 1 on success, 0 on error */ +/* Returns INTLIST_OK/INTLIST_MEMERR */ int intlist_copy( intlist *to, intlist *from ) { - int i; - intlist_free( to ); - to->data = ( int* ) malloc( sizeof( int ) * from->n ); - if ( !to->data ) return 0; - to->n = to->max = from->n; - for ( i=0; in; ++i ) - to->data[i] = from->data[i]; - return 1; + int i, status; + + assert( to ); + assert( from ); + + status = intlist_ensure_space( to, from->n ); + + if ( status==INTLIST_OK ) { + + to->n = from->n; + + for ( i=0; in; ++i ) + to->data[i] = from->data[i]; + + } + + return status; } /* Returns pointer on success, NULL on error */ @@ -270,12 +465,14 @@ intlist_dup( intlist *il ) { intlist *l; - int n; + int status; + assert( il ); + l = intlist_new(); if ( l ) { - n = intlist_copy( l, il ); - if ( !n ) { + status = intlist_copy( l, il ); + if ( status==INTLIST_MEMERR ) { intlist_delete( l ); l = NULL; } @@ -287,49 +484,64 @@ int intlist_append( intlist *to, intlist *from ) { - int i, n, nsave = to->n; - for ( i=0; in; ++i ) { - n = intlist_add( to, from->data[i] ); - if ( n==-1 ) { - to->n = nsave; - return -1; - } + int i, status; + + assert( to ); + assert( from ); + + status = intlist_ensure_space( to, to->n + from->n ); + + if ( status == INTLIST_OK ) { + + for ( i=0; in; ++i ) + to->data[ to->n + i ] = from->data[ i ]; + + to->n += from->n; } - return to->n; + + return status; } int intlist_append_unique( intlist *to, intlist *from ) { - int i, n, nsave = to->n; + int i, nsave, status = INTLIST_OK; + + assert( to ); + assert( from ); + + nsave = to->n; for ( i=0; in; ++i ) { if ( intlist_find( to, from->data[i] )!=-1 ) continue; - n = intlist_add( to, from->data[i] ); - if ( n==-1 ) { + status = intlist_add( to, from->data[i] ); + if ( status==INTLIST_MEMERR ) { to->n = nsave; - return -1; } } - return to->n; + return status; } int intlist_get( intlist *il, int pos ) { - if ( pos<0 || pos>=il->n ) return 0; - else return il->data[pos]; + assert( il ); + assert( intlist_validn( il, pos ) ); + + return il->data[pos]; } /* intlist_set() * - * Returns 1 on success, 0 on failure + * Returns INTLIST_OK */ int intlist_set( intlist *il, int pos, int value ) { - if ( pos<0 || pos>=il->n ) return 0; + assert( il ); + assert( intlist_validn( il, pos ) ); + il->data[pos] = value; - return 1; + return INTLIST_OK; } float @@ -339,6 +551,8 @@ float median; int m1, m2; + assert( il ); + if ( il->n==0 ) return 0.0; tmp = intlist_dup( il ); @@ -350,7 +564,7 @@ median = intlist_get( tmp, tmp->n / 2 ); } else { m1 = intlist_get( tmp, tmp->n / 2 ); - m2 = intlist_get( tmp, tmp->n / 2 + 1); + m2 = intlist_get( tmp, tmp->n / 2 - 1); median = ( m1 + m2 ) / 2.0; } @@ -364,6 +578,8 @@ { float sum = 0.0; int i; + + assert( il ); if ( il->n==0 ) return 0.0; diff --git a/bibutils/intlist.h b/bibutils/intlist.h --- a/bibutils/intlist.h +++ b/bibutils/intlist.h @@ -1,9 +1,9 @@ /* * intlist.h * - * Copyright (c) Chris Putnam 2007-2013 + * Copyright (c) Chris Putnam 2007-2017 * - * Version 9/5/2013 + * Version 01/12/2017 * * Source code released under the GPL version 2 * @@ -12,35 +12,41 @@ #ifndef INTLIST_H #define INTLIST_H -#include -#include +#define INTLIST_OK (0) +#define INTLIST_MEMERR (-1) +#define INTLIST_VALUE_MISSING (-2) typedef struct intlist { int n, max; int *data; } intlist; -extern void intlist_init( intlist *il ); -extern int intlist_init_range( intlist *il, int low, int high, int step ); -extern intlist * intlist_new( void ); -extern intlist * intlist_new_range( int low, int high, int step ); -extern void intlist_delete( intlist *il ); -extern void intlist_sort( intlist *il ); -extern void intlist_randomize( intlist *il ); -extern int intlist_add( intlist *il, int value ); -extern int intlist_add_unique( intlist *il, int value ); -extern int intlist_find( intlist *il, int searchvalue ); -extern int intlist_find_or_add( intlist *il, int searchvalue ); -extern void intlist_empty( intlist *il ); -extern void intlist_free( intlist *il ); -extern int intlist_copy( intlist *to, intlist *from ); -extern int intlist_get( intlist *il, int pos ); -extern int intlist_set( intlist *il, int pos, int value ); -extern int intlist_remove( intlist *il, int searchvalue ); -extern int intlist_remove_pos( intlist *il, int pos ); -extern int intlist_append( intlist *to, intlist *from ); -extern int intlist_append_unique( intlist *to, intlist *from ); -extern float intlist_median( intlist *il ); -extern float intlist_mean( intlist *il ); +void intlist_init( intlist *il ); +int intlist_init_fill( intlist *il, int n, int value ); +int intlist_init_range( intlist *il, int low, int high, int step ); +intlist * intlist_new( void ); +intlist * intlist_new_fill( int n, int value ); +intlist * intlist_new_range( int low, int high, int step ); +void intlist_delete( intlist *il ); +void intlist_sort( intlist *il ); +void intlist_randomize( intlist *il ); +int intlist_add( intlist *il, int value ); +int intlist_add_unique( intlist *il, int value ); +int intlist_fill( intlist *il, int n, int value ); +int intlist_fill_range( intlist *il, int low, int high, int step ); +int intlist_find( intlist *il, int searchvalue ); +int intlist_find_or_add( intlist *il, int searchvalue ); +void intlist_empty( intlist *il ); +void intlist_free( intlist *il ); +int intlist_copy( intlist *to, intlist *from ); +intlist * intlist_dup( intlist *from ); +int intlist_get( intlist *il, int pos ); +int intlist_set( intlist *il, int pos, int value ); +int intlist_remove( intlist *il, int searchvalue ); +int intlist_remove_pos( intlist *il, int pos ); +int intlist_append( intlist *to, intlist *from ); +int intlist_append_unique( intlist *to, intlist *from ); +float intlist_median( intlist *il ); +float intlist_mean( intlist *il ); #endif diff --git a/bibutils/is_ws.c b/bibutils/is_ws.c --- a/bibutils/is_ws.c +++ b/bibutils/is_ws.c @@ -1,7 +1,7 @@ /* * is_ws.c * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/is_ws.h b/bibutils/is_ws.h --- a/bibutils/is_ws.h +++ b/bibutils/is_ws.h @@ -1,7 +1,7 @@ /* * is_ws.h * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/isiin.c b/bibutils/isiin.c --- a/bibutils/isiin.c +++ b/bibutils/isiin.c @@ -1,7 +1,7 @@ /* * isiin.c * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2017 * * Program and source code released under the GPL version 2 * @@ -10,15 +10,23 @@ #include #include #include "is_ws.h" -#include "newstr.h" -#include "newstr_conv.h" -#include "fields.h" +#include "str.h" +#include "str_conv.h" #include "name.h" -#include "title.h" -#include "serialno.h" +#include "fields.h" #include "reftypes.h" -#include "isiin.h" +#include "bibformats.h" +#include "generic.h" +extern variants isi_all[]; +extern int isi_nall; + +static int isiin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int isiin_typef( fields *isiin, char *filename, int nref, param *p ); +static int isiin_convertf( fields *isiin, fields *info, int reftype, param *p ); +static int isiin_processf( fields *isiin, char *p, char *filename, long nref, param *pm ); + + /***************************************************** PUBLIC: void isiin_initparams() *****************************************************/ @@ -44,8 +52,8 @@ p->all = isi_all; p->nall = isi_nall; - list_init( &(p->asis) ); - list_init( &(p->corps) ); + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); if ( !progname ) p->progname = NULL; else p->progname = strdup( progname ); @@ -60,7 +68,7 @@ * char 2 = uppercase alphabetic character or digit */ static int -isiin_istag( char *buf ) +is_isi_tag( char *buf ) { if ( ! (buf[0]>='A' && buf[0]<='Z') ) return 0; if ( ! (((buf[1]>='A' && buf[1]<='Z'))||(buf[1]>='0'&&buf[1]<='9'))) @@ -69,14 +77,14 @@ } static int -readmore( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line ) +readmore( FILE *fp, char *buf, int bufsize, int *bufpos, str *line ) { if ( line->len ) return 1; - else return newstr_fget( fp, buf, bufsize, bufpos, line ); + else return str_fget( fp, buf, bufsize, bufpos, line ); } -int -isiin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ) +static int +isiin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) { int haveref = 0, inref = 0; char *p; @@ -93,7 +101,7 @@ p += 3; } /* Each reference ends with 'ER ' */ - if ( isiin_istag( p ) ) { + if ( is_isi_tag( p ) ) { if ( !strncmp( p, "FN ", 3 ) ) { if (strncasecmp( p, "FN ISI Export Format",20)){ fprintf( stderr, ": warning file FN type not '%s' not recognized.\n", /*r->progname,*/ p ); @@ -104,20 +112,20 @@ } } else if ( !strncmp( p, "ER", 2 ) ) haveref = 1; else { - newstr_addchar( reference, '\n' ); - newstr_strcat( reference, p ); + str_addchar( reference, '\n' ); + str_strcatc( reference, p ); inref = 1; } - newstr_empty( line ); + str_empty( line ); } /* not a tag, but we'll append to the last values */ else if ( inref ) { - newstr_addchar( reference, '\n' ); - newstr_strcat( reference, p ); - newstr_empty( line ); + str_addchar( reference, '\n' ); + str_strcatc( reference, p ); + str_empty( line ); } else { - newstr_empty( line ); + str_empty( line ); } } return haveref; @@ -128,114 +136,159 @@ *****************************************************/ static char * -process_isiline( newstr *tag, newstr *data, char *p ) +process_tagged_line( str *tag, str *data, char *p ) { int i; /* collect tag and skip past it */ i = 0; while ( i<2 && *p && *p!='\r' && *p!='\n') { - newstr_addchar( tag, *p++ ); + str_addchar( tag, *p++ ); i++; } while ( *p==' ' || *p=='\t' ) p++; while ( *p && *p!='\r' && *p!='\n' ) - newstr_addchar( data, *p++ ); - newstr_trimendingws( data ); + str_addchar( data, *p++ ); + str_trimendingws( data ); while ( *p=='\r' || *p=='\n' ) p++; return p; } -int -isiin_processf( fields *isiin, char *p, char *filename, long nref ) +static char * +process_untagged_line( str *data, char *p ) { - int status, n, ret = 1; - newstr tag, data; - newstrs_init( &tag, &data, NULL ); + while ( *p==' ' || *p=='\t' ) p++; + while ( *p && *p!='\r' && *p!='\n' ) + str_addchar( data, *p++ ); + str_trimendingws( data ); + while ( *p=='\r' || *p=='\n' ) p++; + return p; +} + +static int +add_tag_value( fields *isiin, str *tag, str *value, int *tag_added ) +{ + int status; + + if ( str_has_value( value ) ) { + status = fields_add( isiin, str_cstr( tag ), str_cstr( value ), 0 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + *tag_added = 1; + } + + else { + *tag_added = 0; + } + + return BIBL_OK; +} + +static int +merge_tag_value( fields *isiin, str *tag, str *value, int *tag_added ) +{ + int n, status; + + if ( str_has_value( value ) ) { + + if ( *tag_added==1 ) { + + n = fields_num( isiin ); + if ( n==0 ) return BIBL_OK; + + /* only one AU or AF for list of authors */ + if ( !strcmp( str_cstr( tag ), "AU" ) ) { + status = fields_add( isiin, "AU", str_cstr( value ), 0 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } else if ( !strcmp( str_cstr( tag ), "AF" ) ) { + status = fields_add( isiin, "AF", str_cstr( value ), 0 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + /* otherwise append multiline data */ + else { + str_addchar( &(isiin->data[n-1]),' '); + str_strcat( &(isiin->data[n-1]), value ); + if ( str_memerr( &(isiin->data[n-1]) ) ) return BIBL_ERR_MEMERR; + } + } + + else { + status = fields_add( isiin, str_cstr( tag ), str_cstr( value ), 0 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + *tag_added = 1; + } + } + + return BIBL_OK; +} + +static int +isiin_processf( fields *isiin, char *p, char *filename, long nref, param *pm ) +{ + int status, tag_added = 0, ret = 1; + str tag, value; + + strs_init( &tag, &value, NULL ); + while ( *p ) { - newstrs_empty( &tag, &data, NULL ); - p = process_isiline( &tag, &data, p ); - if ( !data.len ) continue; - if ( (tag.len>1) && isiin_istag( tag.data ) ) { - status = fields_add( isiin, tag.data, data.data, 0 ); - if ( status!=FIELDS_OK ) { + + /* ...with tag, add */ + if ( is_isi_tag( p ) ) { + str_empty( &tag ); + str_empty( &value ); + p = process_tagged_line( &tag, &value, p ); + status = add_tag_value( isiin, &tag, &value, &tag_added ); + if ( status!=BIBL_OK ) { ret = 0; goto out; } - } else { - n = fields_num( isiin ); - if ( n>0 ) { - /* only one AU or AF for list of authors */ - if ( !strcmp( isiin->tag[n-1].data,"AU") ){ - status = fields_add( isiin, "AU", data.data, 0); - if ( status!=FIELDS_OK ) ret = 0; - } else if ( !strcmp( isiin->tag[n-1].data,"AF") ){ - status = fields_add( isiin, "AF", data.data, 0); - if ( status!=FIELDS_OK ) ret = 0; - } - /* otherwise append multiline data */ - else { - newstr_addchar( &(isiin->data[n-1]),' '); - newstr_strcat( &(isiin->data[n-1]), data.data ); - if ( newstr_memerr( &(isiin->data[n-1]) ) ) ret = 0; - } - if ( ret==0 ) goto out; + } + + /* ...untagged, merge -- one AU or AF for list of authors */ + else { + str_empty( &value ); + p = process_untagged_line( &value, p ); + status = merge_tag_value( isiin, &tag, &value, &tag_added ); + if ( status!=BIBL_OK ) { + ret = 0; + goto out; } } + } out: - newstrs_free( &data, &tag, NULL ); + strs_free( &value, &tag, NULL ); return ret; } /***************************************************** PUBLIC: int isiin_typef() *****************************************************/ -int -isiin_typef( fields *isiin, char *filename, int nref, param *p, variants *all, int nall ) +static int +isiin_typef( fields *isiin, char *filename, int nref, param *p ) { - char *refnum = ""; - int n, reftype, nrefnum; - n = fields_find( isiin, "PT", 0 ); - nrefnum = fields_find ( isiin, "UT", 0 ); - if ( nrefnum!=-1 ) refnum = isiin->data[nrefnum].data; - if ( n!=-1 ) - reftype = get_reftype( (isiin->data[n]).data, nref, p->progname, all, nall, refnum ); - else - reftype = get_reftype( "", nref, p->progname, all, nall, refnum ); /* default */ - return reftype; + int ntypename, nrefname, is_default; + char *refname = "", *typename=""; + + ntypename = fields_find( isiin, "PT", LEVEL_MAIN ); + nrefname = fields_find( isiin, "UT", LEVEL_MAIN ); + + if ( nrefname!=-1 ) refname = fields_value( isiin, nrefname, FIELDS_CHRP_NOUSE ); + if ( ntypename!=-1 ) typename = fields_value( isiin, ntypename, FIELDS_CHRP_NOUSE ); + + return get_reftype( typename, nref, p->progname, p->all, p->nall, refname, &is_default, REFTYPE_CHATTY ); } /***************************************************** PUBLIC: int isiin_convertf(), returns BIBL_OK or BIBL_ERR_MEMERR *****************************************************/ -static int -isiin_keyword_process( fields *info, char *newtag, char *p, int level ) -{ - int fstatus, status = BIBL_OK; - newstr keyword; - newstr_init( &keyword ); - while ( *p ) { - p = newstr_cpytodelim( &keyword, skip_ws( p ), ";", 1 ); - if ( newstr_memerr( &keyword ) ) { status = BIBL_ERR_MEMERR; goto out; } - if ( keyword.len ) { - fstatus = fields_add( info, newtag, keyword.data, level ); - if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } - } - } -out: - newstr_free( &keyword ); - return status; -} - /* pull off authors first--use AF before AU */ static int -isiin_addauthors( fields *isiin, fields *info, int reftype, variants *all, int nall, list *asis, list *corps ) +isiin_addauthors( fields *isiin, fields *info, int reftype, variants *all, int nall, slist *asis, slist *corps ) { char *newtag, *authortype, use_af[]="AF", use_au[]="AU"; int level, i, n, has_af=0, has_au=0, nfields, ok; - newstr *t, *d; + str *t, *d; nfields = fields_num( isiin ); for ( i=0; idata; + str keyword; + + str_init( &keyword ); + while ( *p ) { + p = str_cpytodelim( &keyword, skip_ws( p ), ";", 1 ); + if ( str_memerr( &keyword ) ) { status = BIBL_ERR_MEMERR; goto out; } + if ( str_has_value( &keyword ) ) { + fstatus = fields_add( bibout, outtag, keyword.data, level ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + } + } +out: + str_free( &keyword ); + return status; +} + static void isiin_report_notag( param *p, char *tag ) { @@ -269,79 +343,45 @@ } static int -isiin_simple( fields *info, char *tag, char *value, int level ) +isiin_convertf( fields *bibin, fields *bibout, int reftype, param *p ) { - int fstatus = fields_add( info, tag, value, level ); - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} + static int (*convertfns[NUM_REFTYPES])(fields *, int, str *, str *, int, param *, char *, fields *) = { + [ 0 ... NUM_REFTYPES-1 ] = generic_null, + [ SIMPLE ] = generic_simple, + [ TITLE ] = generic_title, + [ PERSON ] = generic_person, + [ SERIALNO ] = generic_serialno, + [ DATE ] = generic_simple, + [ NOTES ] = generic_notes, + [ KEYWORD ] = isiin_keyword, + }; -int -isiin_convertf( fields *isiin, fields *info, int reftype, param *p, variants *all, int nall ) -{ - int process, level, i, n, nfields, ok, status; - newstr *t, *d; - char *newtag; + int process, level, i, nfields, status; + str *intag, *invalue; + char *outtag; - status = isiin_addauthors( isiin, info, reftype, all, nall, &(p->asis), &(p->corps) ); + status = isiin_addauthors( bibin, bibout, reftype, p->all, p->nall, &(p->asis), &(p->corps) ); if ( status!=BIBL_OK ) return status; - nfields = fields_num( isiin ); + nfields = fields_num( bibin ); for ( i=0; idata, "AU" ) || !strcasecmp( t->data, "AF" ) ) + intag = fields_tag( bibin, i, FIELDS_STRP ); + if ( !strcasecmp( str_cstr( intag ), "AU" ) || !strcasecmp( str_cstr( intag ), "AF" ) ) continue; - n = translate_oldtag( t->data, reftype, all, nall, &process, &level, &newtag ); - if ( n==-1 ) { - isiin_report_notag( p, t->data ); + if ( !translate_oldtag( str_cstr( intag ), reftype, p->all, p->nall, &process, &level, &outtag ) ) { + isiin_report_notag( p, str_cstr( intag ) ); continue; } - if ( process == ALWAYS ) continue; /* add in core code */ - d = fields_value( isiin, i, FIELDS_STRP ); - - ok = 1; - - switch ( process ) { - - case SIMPLE: - case DATE: - status = isiin_simple( info, newtag, d->data, level ); - break; - - case PERSON: - ok = name_add( info, newtag, d->data, level, &(p->asis), &(p->corps) ); - if ( ok ) status = BIBL_OK; - else status = BIBL_ERR_MEMERR; - break; - - case TITLE: - ok = title_process( info, newtag, d->data, level, p->nosplittitle ); - if ( ok ) status = BIBL_OK; - else status = BIBL_ERR_MEMERR; - break; - - case KEYWORD: - status = isiin_keyword_process( info, newtag, d->data, level ); - break; - - case SERIALNO: - ok = addsn( info, d->data, level ); - if ( ok ) status = BIBL_OK; - else status = BIBL_ERR_MEMERR; - break; - - /* do nothing if process==TYPE || process==ALWAYS */ - default: - status = BIBL_OK; - break; - - } + invalue = fields_value( bibin, i, FIELDS_STRP ); + status = convertfns[ process ] ( bibin, i, intag, invalue, level, p, outtag, bibout ); if ( status!=BIBL_OK ) return status; } + + if ( status==BIBL_OK && p->verbose ) fields_report( bibout, stderr ); return status; } diff --git a/bibutils/isiin.h b/bibutils/isiin.h deleted file mode 100644 --- a/bibutils/isiin.h +++ /dev/null @@ -1,28 +0,0 @@ -/* - * isiin.h - * - * Copyright (c) Chris Putnam 2004-2013 - * - * Source code released under the GPL version 2 - * - */ -#ifndef ISIIN_H -#define ISIIN_H - -#include "newstr.h" -#include "fields.h" -#include "reftypes.h" -#include "bibutils.h" - -extern int isiin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ); -extern int isiin_typef( fields *isiin, char *filename, int nref, param *p, variants *all, int nall ); -extern int isiin_convertf( fields *isiin, fields *info, int reftype, param *p, variants *all, int nall ); -extern int isiin_processf( fields *isiin, char *p, char *filename, long nref ); - -extern void isiin_initparams( param *p, const char *progname ); - -extern variants isi_all[]; -extern int isi_nall; - -#endif - diff --git a/bibutils/isiout.c b/bibutils/isiout.c --- a/bibutils/isiout.c +++ b/bibutils/isiout.c @@ -1,7 +1,7 @@ /* * isiout.c * - * Copyright (c) Chris Putnam 2008-2013 + * Copyright (c) Chris Putnam 2008-2017 * * Source code released under the GPL version 2 * @@ -11,12 +11,16 @@ #include #include #include "utf8.h" -#include "newstr.h" +#include "str.h" #include "strsearch.h" #include "fields.h" +#include "title.h" #include "bibutils.h" -#include "isiout.h" +#include "bibformats.h" +static int isiout_write( fields *info, FILE *fp, param *p, unsigned long refnum ); +static void isiout_writeheader( FILE *outptr, param *p ); + void isiout_initparams( param *p, const char *progname ) { @@ -49,29 +53,18 @@ TYPE_BOOK = 3, }; -static void -output_type( FILE *fp, int type ) -{ - fprintf( fp, "PT " ); - if ( type==TYPE_ARTICLE ) fprintf( fp, "Journal" ); - else if ( type==TYPE_INBOOK ) fprintf( fp, "Chapter" ); - else if ( type==TYPE_BOOK ) fprintf( fp, "Book" ); - else fprintf( fp, "Unknown" ); - fprintf( fp, "\n" ); -} - static int -get_type( fields *f ) +get_type( fields *in ) { int type = TYPE_UNKNOWN, i, n, level; char *tag, *value; - n = fields_num( f ); + n = fields_num( in ); for ( i=0; idata ); - if ( subttl ) { - if ( mainttl->len > 0 && - mainttl->data[ mainttl->len - 1 ]!='?' ) - fprintf( fp, ":" ); - fprintf( fp, " %s", subttl->data ); + fstatus = fields_add( out, "PT", s, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; +} + +static void +append_titlecore( fields *in, char *isitag, int level, char *maintag, char *subtag, fields *out, int *status ) +{ + str *mainttl = fields_findv( in, level, FIELDS_STRP, maintag ); + str *subttl = fields_findv( in, level, FIELDS_STRP, subtag ); + str fullttl; + int fstatus; + + str_init( &fullttl ); + title_combine( &fullttl, mainttl, subttl ); + + if ( str_memerr( &fullttl ) ) { + *status = BIBL_ERR_MEMERR; + goto out; } - fprintf( fp, "\n" ); + + if ( str_has_value( &fullttl ) ) { + fstatus = fields_add( out, isitag, str_cstr( &fullttl ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } +out: + str_free( &fullttl ); } static void -output_title( FILE *fp, fields *f, char *isitag, int level ) +append_title( fields *in, char *isitag, int level, fields *out, int *status ) { - output_titlecore( fp, f, isitag, level, "TITLE", "SUBTITLE" ); + append_titlecore( in, isitag, level, "TITLE", "SUBTITLE", out, status ); } static void -output_abbrtitle( FILE *fp, fields *f, char *isitag, int level ) +append_abbrtitle( fields *in, char *isitag, int level, fields *out, int *status ) { - output_titlecore( fp, f, isitag, level, "SHORTTITLE", "SHORTSUBTITLE" ); + append_titlecore( in, isitag, level, "SHORTTITLE", "SHORTSUBTITLE", out, status ); } static void -output_keywords( FILE *fp, fields *f ) +append_keywords( fields *in, fields *out, int *status ) { + vplist_index i; + str keywords; + int fstatus; vplist kw; - int i; + + str_init( &keywords ); vplist_init( &kw ); - fields_findv_each( f, LEVEL_ANY, FIELDS_CHRP, &kw, "KEYWORD" ); + + fields_findv_each( in, LEVEL_ANY, FIELDS_STRP, &kw, "KEYWORD" ); if ( kw.n ) { - fprintf( fp, "DE " ); for ( i=0; i0 ) fprintf( fp, "; " ); - fprintf( fp, "%s", (char *)vplist_get( &kw, i ) ); + if ( i>0 ) str_strcatc( &keywords, "; " ); + str_strcat( &keywords, (str *) vplist_get( &kw, i ) ); } - fprintf( fp, "\n" ); + if ( str_memerr( &keywords ) ) { *status = BIBL_ERR_MEMERR; goto out; } + fstatus = fields_add( out, "DE", str_cstr( &keywords ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { *status = BIBL_ERR_MEMERR; goto out; } } +out: vplist_free( &kw ); + str_free( &keywords ); } static void -output_person( FILE *fp, char *name ) +process_person( str *person, char *name ) { - newstr family, given, suffix; + str family, given, suffix; char *p = name; - newstrs_init( &family, &given, &suffix, NULL ); + str_empty( person ); + strs_init( &family, &given, &suffix, NULL ); + while ( *p && *p!='|' ) - newstr_addchar( &family, *p++ ); + str_addchar( &family, *p++ ); while ( *p=='|' && *(p+1)!='|' ) { p++; - if ( *p!='|' ) newstr_addchar( &given, *p++ ); + if ( *p!='|' ) str_addchar( &given, *p++ ); while ( *p && *p!='|' ) p++; } if ( *p=='|' && *(p+1)=='|' ) { p += 2; - while ( *p && *p!='|' ) newstr_addchar( &suffix, *p++ ); + while ( *p && *p!='|' ) str_addchar( &suffix, *p++ ); } - if ( family.len ) fprintf( fp, "%s", family.data ); - if ( suffix.len ) { - if ( family.len ) fprintf( fp, " %s", suffix.data ); - else fprintf( fp, "%s", suffix.data ); + if ( str_has_value( &family ) ) str_strcat( person, &family ); + if ( str_has_value( &suffix ) ) { + if ( str_has_value( &family ) ) str_strcatc( person, " " ); + str_strcat( person, &suffix ); } - if ( given.len ) fprintf( fp, ", %s", given.data ); + if ( str_has_value( &given ) ) { + if ( str_has_value( person ) ) str_strcatc( person, ", " ); + str_strcat( person, &given ); + } - newstrs_free( &family, &given, &suffix, NULL ); + strs_free( &family, &given, &suffix, NULL ); } static void -output_people( FILE *fp, fields *f, char *tag, char *isitag, int level ) +append_people( fields *f, char *tag, char *isitag, int level, fields *out, int *status ) { + vplist_index i; vplist people; - int i; + str person; + int fstatus; + + str_init( &person ); vplist_init( &people ); + fields_findv_each( f, level, FIELDS_CHRP, &people, tag ); - if ( people.n ) { - fprintf( fp, "%s ", isitag ); - for ( i=0; iformat_opts & BIBL_FORMAT_VERBOSE ) - output_verbose( f, refnum ); + for ( i=0; in; ++i ) { + fprintf( fp, "%s %s\n", + ( char * ) fields_tag ( out, i, FIELDS_CHRP ), + ( char * ) fields_value( out, i, FIELDS_CHRP ) + ); + } + fprintf( fp, "ER\n\n" ); + fflush( fp ); +} - output_type( fp, type ); - output_people( fp, f, "AUTHOR", "AU", 0 ); - output_easyall( fp, f, "AUTHOR:CORP", "AU", 0 ); - output_easyall( fp, f, "AUTHOR:ASIS", "AU", 0 ); -/* output_people( fp, f, "AUTHOR", "A2", 1 ); - output_people( fp, f, "AUTHOR:CORP", "A2", 1 ); - output_people( fp, f, "AUTHOR:ASIS", "A2", 1 ); - output_people( fp, f, "AUTHOR", "A3", 2 ); - output_people( fp, f, "AUTHOR:CORP", "A3", 2 ); - output_people( fp, f, "AUTHOR:ASIS", "A3", 2 ); - output_people( fp, f, "EDITOR", "ED", -1 ); - output_people( fp, f, "EDITOR:CORP", "ED", -1 ); - output_people( fp, f, "EDITOR:ASIS", "ED", -1 );*/ -/* output_date( fp, f, refnum );*/ +static int +isiout_write( fields *in, FILE *fp, param *p, unsigned long refnum ) +{ + int status; + fields out; - output_title( fp, f, "TI", 0 ); - if ( type==TYPE_ARTICLE ) { - output_title( fp, f, "SO", 1 ); - output_abbrtitle( fp, f, "JI", 1 ); - output_title( fp, f, "SE", 2 ); - } else if ( type==TYPE_INBOOK ) { - output_title( fp, f, "BT", 1 ); - output_title( fp, f, "SE", 2 ); - } else { /* type==BOOK */ - output_title( fp, f, "SE", 1 ); - } + fields_init( &out ); - output_date( fp, f ); -/* output_easy( fp, f, "PARTMONTH", "PD", -1 ); - output_easy( fp, f, "PARTYEAR", "PY", -1 );*/ + if ( p->format_opts & BIBL_FORMAT_VERBOSE ) + output_verbose( in, "IN", refnum ); - output_easy( fp, f, "PAGESTART", "BP", -1 ); - output_easy( fp, f, "PAGEEND", "EP", -1 ); - output_easy( fp, f, "ARTICLENUMBER", "AR", -1 ); - /* output article number as pages */ - output_easy( fp, f, "TOTALPAGES","PG", -1 ); + status = append_data( in, &out ); - output_easy( fp, f, "VOLUME", "VL", -1 ); - output_easy( fp, f, "ISSUE", "IS", -1 ); - output_easy( fp, f, "NUMBER", "IS", -1 ); - output_easy( fp, f, "DOI", "DI", -1 ); - output_easy( fp, f, "ISIREFNUM", "UT", -1 ); - output_easy( fp, f, "LANGUAGE", "LA", -1 ); - output_easy( fp, f, "ISIDELIVERNUM", "GA", -1 ); - output_keywords( fp, f ); - output_easy( fp, f, "ABSTRACT", "AB", -1 ); - output_easy( fp, f, "TIMESCITED", "TC", -1 ); - output_easy( fp, f, "NUMBERREFS", "NR", -1 ); - output_easy( fp, f, "CITEDREFS", "CR", -1 ); - output_easy( fp, f, "ADDRESS", "PI", -1 ); + if ( status==BIBL_OK ) output( fp, &out ); -/* output_easy( fp, f, "PUBLISHER", "PB", -1 ); - output_easy( fp, f, "DEGREEGRANTOR", "PB", -1 ); - output_easy( fp, f, "ADDRESS", "CY", -1 ); - output_easy( fp, f, "ABSTRACT", "AB", -1 ); - output_easy( fp, f, "ISSN", "SN", -1 ); - output_easy( fp, f, "ISBN", "SN", -1 ); - output_easyall( fp, f, "URL", "UR", -1 ); - output_easyall( fp, f, "FILEATTACH", "UR", -1 ); - output_pubmed( fp, f, refnum ); - output_easyall( fp, f, "NOTES", "N1", -1 ); - output_easyall( fp, f, "REFNUM", "ID", -1 );*/ - fprintf( fp, "ER\n\n" ); - fflush( fp ); + if ( p->format_opts & BIBL_FORMAT_VERBOSE ) + output_verbose( &out, "OUT", refnum ); + + fields_free( &out ); + + return status; } -void +static void isiout_writeheader( FILE *outptr, param *p ) { if ( p->utf8bom ) utf8_writebom( outptr ); diff --git a/bibutils/isiout.h b/bibutils/isiout.h deleted file mode 100644 --- a/bibutils/isiout.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * isiout.h - * - * Copyright (c) Chris Putnam 2007-2013 - * - * Source code released under the GPL version 2 - * - */ -#ifndef ISIOUT_H -#define ISIOUT_H - -#include -#include "bibutils.h" - -extern void isiout_write( fields *info, FILE *fp, param *p, - unsigned long refnum ); -extern void isiout_writeheader( FILE *outptr, param *p ); - -extern void isiout_initparams( param *p, const char *progname ); - -#endif diff --git a/bibutils/isitypes.c b/bibutils/isitypes.c --- a/bibutils/isitypes.c +++ b/bibutils/isitypes.c @@ -1,7 +1,7 @@ /* * isitypes.c * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2017 * * Program and source code released under the GPL version 2 * @@ -24,17 +24,17 @@ { "C1", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* author address */ { "PA", "ADDRESS", SIMPLE, LEVEL_HOST }, /* publisher address */ { "RP", "REPRINTADDRESS", SIMPLE, LEVEL_MAIN }, - { "PY", "PARTYEAR", SIMPLE, LEVEL_MAIN }, - { "PD", "PARTMONTH", SIMPLE, LEVEL_MAIN }, + { "PY", "PARTDATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "PD", "PARTDATE:MONTH", SIMPLE, LEVEL_MAIN }, { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, { "AR", "ARTICLENUMBER", SIMPLE, LEVEL_MAIN }, /* AR=article number that Phys. Rev. B uses instead of page numbers */ - { "BP", "PAGESTART", SIMPLE, LEVEL_MAIN }, - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, - { "PG", "TOTALPAGES", SIMPLE, LEVEL_MAIN }, + { "BP", "PAGES:START", SIMPLE, LEVEL_MAIN }, + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, + { "PG", "PAGES:TOTAL", SIMPLE, LEVEL_MAIN }, { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, { "SN", "SERIALNUMBER", SERIALNO, LEVEL_HOST }, { "AB", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "NF", "NOTES", SIMPLE, LEVEL_MAIN }, + { "NF", "NOTES", NOTES, LEVEL_MAIN }, { "DE", "KEYWORD", KEYWORD, LEVEL_MAIN }, /* author keywords */ { "ID", "KEYWORD", KEYWORD, LEVEL_MAIN }, /* new ISI keywords */ { "LA", "LANGUAGE", SIMPLE, LEVEL_MAIN }, @@ -67,16 +67,16 @@ { "C1", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* author address */ { "PA", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* publisher address */ { "RP", "REPRINTADDRESS", SIMPLE, LEVEL_MAIN }, - { "PY", "YEAR", SIMPLE, LEVEL_MAIN }, - { "PD", "MONTH", SIMPLE, LEVEL_MAIN }, + { "PY", "DATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "PD", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, - { "BP", "PAGESTART", SIMPLE, LEVEL_MAIN }, - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, - { "PG", "TOTALPAGES", SIMPLE, LEVEL_MAIN }, - { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, + { "BP", "PAGES:START", SIMPLE, LEVEL_MAIN }, + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, + { "PG", "PAGES:TOTAL", SIMPLE, LEVEL_MAIN }, + { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, { "SN", "SERIALNUMBER", SERIALNO, LEVEL_HOST }, { "AB", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "NF", "NOTES", SIMPLE, LEVEL_MAIN }, + { "NF", "NOTES", NOTES, LEVEL_MAIN }, { "DE", "KEYWORD", KEYWORD, LEVEL_MAIN }, /* author keywords */ { "ID", "KEYWORD", KEYWORD, LEVEL_MAIN }, /* new ISI keywords */ { "LA", "LANGUAGE", SIMPLE, LEVEL_MAIN }, @@ -108,16 +108,16 @@ { "C1", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* author address */ { "PA", "ADDRESS", SIMPLE, LEVEL_HOST }, /* publisher address */ { "RP", "REPRINTADDRESS", SIMPLE, LEVEL_MAIN }, - { "PY", "PARTYEAR", SIMPLE, LEVEL_MAIN }, - { "PD", "PARTMONTH", SIMPLE, LEVEL_MAIN }, + { "PY", "PARTDATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "PD", "PARTDATE:MONTH", SIMPLE, LEVEL_MAIN }, { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, - { "BP", "PAGESTART", SIMPLE, LEVEL_MAIN }, - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, - { "PG", "TOTALPAGES", SIMPLE, LEVEL_HOST }, - { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, + { "BP", "PAGES:START", SIMPLE, LEVEL_MAIN }, + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, + { "PG", "PAGES:TOTAL", SIMPLE, LEVEL_HOST }, + { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, { "SN", "SERIALNUMBER", SERIALNO, LEVEL_HOST }, { "AB", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "NF", "NOTES", SIMPLE, LEVEL_MAIN }, + { "NF", "NOTES", NOTES, LEVEL_MAIN }, { "DE", "KEYWORD", KEYWORD, LEVEL_MAIN }, /* author keywords */ { "ID", "KEYWORD", KEYWORD, LEVEL_MAIN }, /* new ISI keywords */ { "LA", "LANGUAGE", SIMPLE, LEVEL_MAIN }, @@ -150,16 +150,16 @@ { "C1", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* author address */ { "PA", "ADDRESS", SIMPLE, LEVEL_HOST }, /* publisher address */ { "RP", "REPRINTADDRESS", SIMPLE, LEVEL_MAIN }, - { "PY", "PARTYEAR", SIMPLE, LEVEL_MAIN }, - { "PD", "PARTMONTH", SIMPLE, LEVEL_MAIN }, + { "PY", "PARTDATE:YEAR", SIMPLE, LEVEL_MAIN }, + { "PD", "PARTDATE:MONTH", SIMPLE, LEVEL_MAIN }, { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, - { "BP", "PAGESTART", SIMPLE, LEVEL_MAIN }, - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, - { "PG", "TOTALPAGES", SIMPLE, LEVEL_MAIN }, + { "BP", "PAGES:START", SIMPLE, LEVEL_MAIN }, + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, + { "PG", "PAGES:TOTAL", SIMPLE, LEVEL_MAIN }, { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, { "SN", "SERIALNUMBER", SERIALNO, LEVEL_HOST }, { "AB", "ABSTRACT", SIMPLE, LEVEL_MAIN }, - { "NF", "NOTES", SIMPLE, LEVEL_MAIN }, + { "NF", "NOTES", NOTES, LEVEL_MAIN }, { "DE", "KEYWORD", KEYWORD, LEVEL_MAIN }, /* author keywords */ { "ID", "KEYWORD", KEYWORD, LEVEL_MAIN }, /* new ISI keywords */ { "LA", "LANGUAGE", SIMPLE, LEVEL_MAIN }, diff --git a/bibutils/latex.c b/bibutils/latex.c --- a/bibutils/latex.c +++ b/bibutils/latex.c @@ -3,489 +3,493 @@ * * convert between latex special chars and unicode * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * */ #include +#include #include #include "latex.h" +#define LATEX_COMBO (0) /* 'combo' no need for protection on output */ +#define LATEX_MACRO (1) /* 'macro_name' to be protected by {\macro_name} on output */ +#define LATEX_MATH (2) /* 'math_expression' to be protected by $math_expression$ on output */ + struct latex_chars { - unsigned int unicode; - char *bib1, *bib2, *bib3; + unsigned int unicode; /* unicode code point */ + unsigned char type; /* LATEX_COMBO/LATEX_MACRO/LATEX_MATH */ + char *out; /* unadorned latex combination for output */ + char *variant[3]; /* possible variations on input */ }; static struct latex_chars latex_chars[] = { - { 35, "\\#", "", "" }, /* Number/pound/hash sign */ - { 36, "\\$", "", "" }, /* Dollar Sign */ - { 37, "\\%", "", "" }, /* Percent Sign */ - { 38, "\\&", "", "" }, /* Ampersand */ - { 92, "{\\backslash}", "\\backslash", "" }, /* Backslash */ - { 123, "\\{", "{\\textbraceleft}", "\\textbraceleft" }, /* Left Curly Bracket */ - { 125, "\\}", "{\\textbraceright}", "\\textbraceright" }, /* Right Curly Bracket */ - { 95, "\\_", "", "" }, /* Underscore alone indicates subscript */ - { 176, "{\\textdegree}", "\\textdegree", "^\\circ" }, /* Degree sign */ -/* fix sticky spaces in bibtex token cleaning--allows tokens to be parsed properly */ -/* { 32, "~", "\\ ", "" }, */ /* "sticky" space */ - { 32, "\\ ", "", "" }, /* escaping the space is used to avoid extra space after periods */ - { 126, "{\\textasciitilde}", "\\textasciitilde", "\\~{}" }, /* Tilde in latex */ - /* This is a cheat, should use "\verb" */ - /* Need same for ^ character */ + /* LaTeX special characters */ + { 32, LATEX_COMBO, " ", { "\\ ", NULL, NULL } }, /* escaping the space is used to avoid extra space after periods */ + { 35, LATEX_MACRO, "#", { "\\#", NULL, NULL } }, /* Number/pound/hash sign */ + { 36, LATEX_MACRO, "$", { "\\$", NULL, NULL } }, /* Dollar Sign */ + { 37, LATEX_MACRO, "%", { "\\%", NULL, NULL } }, /* Percent Sign */ + { 38, LATEX_MACRO, "&", { "\\&", NULL, NULL } }, /* Ampersand */ + { 95, LATEX_MACRO, "_", { "\\_", NULL, NULL } }, /* Underscore alone indicates subscript */ + { 123, LATEX_MACRO, "{", { "\\{", "{\\textbraceleft}", "\\textbraceleft" } }, /* Left Curly Bracket */ + { 125, LATEX_MACRO, "}", { "\\}", "{\\textbraceright}", "\\textbraceright" } }, /* Right Curly Bracket */ + { 92, LATEX_MACRO, "backslash", { "{\\backslash}", "\\backslash", NULL } }, /* Backslash */ + { 176, LATEX_MACRO, "textdegree", { "{\\textdegree}", "\\textdegree", "^\\circ" } }, /* Degree sign */ + { 126, LATEX_MACRO, "textasciitilde", { "{\\textasciitilde}", "\\textasciitilde", "\\~{}" } }, /* Tilde in latex */ +/* fix sticky spaces "~" in bibtex token cleaning--allows tokens to be parsed properly */ - /* Latin Capital A */ - { 192, "{\\`A}", "\\`{A}", "\\`A" }, /* with grave */ - { 193, "{\\'A}", "\\'{A}", "\\'A" }, /* with acute */ - { 194, "{\\^A}", "\\^{A}", "\\^A" }, /* with circumflex */ - { 195, "{\\~A}", "\\~{A}", "\\~A" }, /* with tilde */ - { 196, "{\\\"A}", "\\\"{A}", "\\\"A" }, /* with diuresis */ - { 197, "{\\AA}", "{\\r{A}}","\\r{A}"}, /* with ring above */ - { 256, "{\\={A}}","\\={A}", "\\=A" }, /* with macron */ - { 258, "{\\u{A}}","\\u{A}", "\\u A" }, /* with breve */ - { 260, "{\\k{A}}","\\k{A}", "\\k A" }, /* with ogonek */ - { 461, "{\\v{A}}","\\v{A}", "\\v A" }, /* with caron */ + /* Latin Capital A */ + { 192, LATEX_MACRO, "`A", { "{\\`A}", "\\`{A}", "\\`A" } }, /* with grave */ + { 193, LATEX_MACRO, "'A", { "{\\'A}", "\\'{A}", "\\'A" } }, /* with acute */ + { 194, LATEX_MACRO, "^A", { "{\\^A}", "\\^{A}", "\\^A" } }, /* with circumflex */ + { 195, LATEX_MACRO, "~A", { "{\\~A}", "\\~{A}", "\\~A" } }, /* with tilde */ + { 196, LATEX_MACRO, "\"A", { "{\\\"A}", "\\\"{A}", "\\\"A" } }, /* with diuresis */ + { 197, LATEX_MACRO, "AA", { "{\\AA}", "{\\r{A}}", "\\r{A}"} }, /* with ring above */ + { 256, LATEX_MACRO, "={A}", { "{\\={A}}", "\\={A}", "\\=A" } }, /* with macron */ + { 258, LATEX_MACRO, "u{A}", { "{\\u{A}}", "\\u{A}", "\\u A" } }, /* with breve */ + { 260, LATEX_MACRO, "k{A}", { "{\\k{A}}", "\\k{A}", "\\k A" } }, /* with ogonek */ + { 461, LATEX_MACRO, "v{A}", { "{\\v{A}}", "\\v{A}", "\\v A" } }, /* with caron */ /* Latin Small a */ - { 224, "{\\`a}", "\\`{a}", "\\`a" }, /* with grave */ - { 225, "{\\'a}", "\\'{a}", "\\'a" }, /* with acute */ - { 226, "{\\^a}", "\\^{a}", "\\^a" }, /* with circumflex */ - { 227, "{\\~a}", "\\~{a}", "\\~a" }, /* with tilde */ - { 228, "{\\\"a}", "\\\"{a}", "\\\"a" }, /* with diuresis */ - { 229, "{\\aa}", "{\\r{a}}","\\r{a}"}, /* with ring above */ - { 257, "{\\={a}}","\\={a}", "\\=a" }, /* with macron */ - { 259, "{\\u{a}}","\\u{a}", "\\u a" }, /* with breve */ - { 261, "{\\k{a}}","\\k{a}", "\\k a" }, /* with ogonek */ - { 462, "{\\v{a}}","\\v{a}", "\\v a" }, /* with caron */ + { 224, LATEX_MACRO, "`a", { "{\\`a}", "\\`{a}", "\\`a" } }, /* with grave */ + { 225, LATEX_MACRO, "'a", { "{\\'a}", "\\'{a}", "\\'a" } }, /* with acute */ + { 226, LATEX_MACRO, "^a", { "{\\^a}", "\\^{a}", "\\^a" } }, /* with circumflex */ + { 227, LATEX_MACRO, "~a", { "{\\~a}", "\\~{a}", "\\~a" } }, /* with tilde */ + { 228, LATEX_MACRO, "\"a", { "{\\\"a}", "\\\"{a}", "\\\"a" } }, /* with diuresis */ + { 229, LATEX_MACRO, "aa", { "{\\aa}", "{\\r{a}}", "\\r{a}"} }, /* with ring above */ + { 257, LATEX_MACRO, "={a}", { "{\\={a}}", "\\={a}", "\\=a" } }, /* with macron */ + { 259, LATEX_MACRO, "u{a}", { "{\\u{a}}", "\\u{a}", "\\u a" } }, /* with breve */ + { 261, LATEX_MACRO, "k{a}", { "{\\k{a}}", "\\k{a}", "\\k a" } }, /* with ogonek */ + { 462, LATEX_MACRO, "v{a}", { "{\\v{a}}", "\\v{a}", "\\v a" } }, /* with caron */ - { 198, "{\\AE}", "\\AE", "" }, /* Latin Capital AE */ - { 230, "{\\ae}", "\\ae", "" }, /* Latin Small ae */ + { 198, LATEX_MACRO, "AE", { "{\\AE}", "\\AE", NULL } }, /* Latin Capital AE */ + { 230, LATEX_MACRO, "ae", { "{\\ae}", "\\ae", NULL } }, /* Latin Small ae */ /* Latin Capital C */ - { 199, "{\\c{C}}","\\c{C}", "\\c c" }, /* with cedilla */ - { 262, "{\\'{C}}","\\'{C}", "\\'C" }, /* with acute */ - { 264, "{\\^{C}}","\\^{C}", "\\^C" }, /* with circumflex */ - { 266, "{\\.{C}}","\\.{C}", "\\.C" }, /* with dot above */ - { 268, "{\\v{C}}","\\v{C}", "\\v C" }, /* with caron (hacek) */ + { 199, LATEX_MACRO, "c{C}", { "{\\c{C}}", "\\c{C}", "\\c c" } }, /* with cedilla */ + { 262, LATEX_MACRO, "'{C}", { "{\\'{C}}", "\\'{C}", "\\'C" } }, /* with acute */ + { 264, LATEX_MACRO, "^{C}", { "{\\^{C}}", "\\^{C}", "\\^C" } }, /* with circumflex */ + { 266, LATEX_MACRO, ".{C}", { "{\\.{C}}", "\\.{C}", "\\.C" } }, /* with dot above */ + { 268, LATEX_MACRO, "v{C}", { "{\\v{C}}", "\\v{C}", "\\v C" } }, /* with caron (hacek) */ /* Latin Small c */ - { 231, "{\\c{c}}","\\c{c}", "\\c C" }, /* with cedilla*/ - { 263, "{\\'{c}}","\\'{c}", "\\'c" }, /* with acute */ - { 265, "{\\^{c}}","\\^{c}", "\\^c" }, /* with circumflex */ - { 267, "{\\.{c}}","\\.{c}", "\\.c" }, /* with dot above */ - { 269, "{\\v{c}}","\\v{c}", "\\v c" }, /* with caron (hacek) */ + { 231, LATEX_MACRO, "c{c}", { "{\\c{c}}", "\\c{c}", "\\c C" } }, /* with cedilla*/ + { 263, LATEX_MACRO, "'{c}", { "{\\'{c}}", "\\'{c}", "\\'c" } }, /* with acute */ + { 265, LATEX_MACRO, "^{c}", { "{\\^{c}}", "\\^{c}", "\\^c" } }, /* with circumflex */ + { 267, LATEX_MACRO, ".{c}", { "{\\.{c}}", "\\.{c}", "\\.c" } }, /* with dot above */ + { 269, LATEX_MACRO, "v{c}", { "{\\v{c}}", "\\v{c}", "\\v c" } }, /* with caron (hacek) */ /* Latin Capital D */ - { 270, "{\\v{D}}","\\v{D}", "\\v D" }, /* with caron */ - { 272, "{\\DJ}", "", "" }, /* with stroke */ + { 270, LATEX_MACRO, "v{D}", { "{\\v{D}}", "\\v{D}", "\\v D" } }, /* with caron */ + { 272, LATEX_MACRO, "DJ", { "{\\DJ}", NULL, NULL } }, /* with stroke */ /* Latin Small d */ - { 271, "{\\v{d}}","\\v{d}", "\\v d" }, /* with caron */ - { 273, "{\\dj}", "", "" }, /* with stroke */ + { 271, LATEX_MACRO, "v{d}", { "{\\v{d}}", "\\v{d}", "\\v d" } }, /* with caron */ + { 273, LATEX_MACRO, "dj", { "{\\dj}", NULL, NULL } }, /* with stroke */ /* Latin Capital E */ - { 200, "{\\`E}", "\\`{E}", "\\`E" }, /* with grave */ - { 201, "{\\'E}", "\\'{E}", "\\'E" }, /* with acute */ - { 202, "{\\^E}", "\\^{E}", "\\^E" }, /* with circumflex */ - { 203, "{\\\"E}", "\\\"{E}", "\\\"E" }, /* with diuresis */ - { 274, "{\\={E}}","\\={E}", "\\=E" }, /* with macron */ - { 276, "{\\u{E}}","\\u{E}", "\\u E" }, /* with breve */ - { 278, "{\\.{E}}","\\.{E}", "\\.E" }, /* with dot above */ - { 280, "{\\k{E}}","\\k{E}", "\\k E" }, /* with ogonek */ - { 282, "{\\v{E}}","\\v{E}", "\\v E" }, /* with caron */ + { 200, LATEX_MACRO, "`E", { "{\\`E}", "\\`{E}", "\\`E" } }, /* with grave */ + { 201, LATEX_MACRO, "'E", { "{\\'E}", "\\'{E}", "\\'E" } }, /* with acute */ + { 202, LATEX_MACRO, "^E", { "{\\^E}", "\\^{E}", "\\^E" } }, /* with circumflex */ + { 203, LATEX_MACRO, "\"E", { "{\\\"E}", "\\\"{E}", "\\\"E" } }, /* with diuresis */ + { 274, LATEX_MACRO, "={E}", { "{\\={E}}", "\\={E}", "\\=E" } }, /* with macron */ + { 276, LATEX_MACRO, "u{E}", { "{\\u{E}}", "\\u{E}", "\\u E" } }, /* with breve */ + { 278, LATEX_MACRO, ".{E}", { "{\\.{E}}", "\\.{E}", "\\.E" } }, /* with dot above */ + { 280, LATEX_MACRO, "k{E}", { "{\\k{E}}", "\\k{E}", "\\k E" } }, /* with ogonek */ + { 282, LATEX_MACRO, "v{E}", { "{\\v{E}}", "\\v{E}", "\\v E" } }, /* with caron */ /* Latin Small e */ - { 232, "{\\`e}", "\\`{e}", "\\`e" }, /* with grave */ - { 233, "{\\'e}", "\\'{e}", "\\'e" }, /* with acute */ - { 234, "{\\^e}", "\\^{e}", "\\^e" }, /* with circumflex */ - { 235, "{\\\"e}", "\\\"{e}", "\\\"e" }, /* with diuresis */ - { 275, "{\\={e}}","\\={e}", "\\=e" }, /* with macron */ - { 277, "{\\u{e}}","\\u{e}", "\\u e" }, /* with breve */ - { 279, "{\\.{e}}","\\.{e}", "\\.e" }, /* with dot above */ - { 281, "{\\k{e}}","\\k{e}", "\\k e" }, /* with ogonek */ - { 283, "{\\v{e}}","\\v{e}", "\\v e" }, /* with caron */ + { 232, LATEX_MACRO, "`e", { "{\\`e}", "\\`{e}", "\\`e" } }, /* with grave */ + { 233, LATEX_MACRO, "'e", { "{\\'e}", "\\'{e}", "\\'e" } }, /* with acute */ + { 234, LATEX_MACRO, "^e", { "{\\^e}", "\\^{e}", "\\^e" } }, /* with circumflex */ + { 235, LATEX_MACRO, "\"e", { "{\\\"e}", "\\\"{e}", "\\\"e" } }, /* with diuresis */ + { 275, LATEX_MACRO, "={e}", { "{\\={e}}", "\\={e}", "\\=e" } }, /* with macron */ + { 277, LATEX_MACRO, "u{e}", { "{\\u{e}}", "\\u{e}", "\\u e" } }, /* with breve */ + { 279, LATEX_MACRO, ".{e}", { "{\\.{e}}", "\\.{e}", "\\.e" } }, /* with dot above */ + { 281, LATEX_MACRO, "k{e}", { "{\\k{e}}", "\\k{e}", "\\k e" } }, /* with ogonek */ + { 283, LATEX_MACRO, "v{e}", { "{\\v{e}}", "\\v{e}", "\\v e" } }, /* with caron */ /* Latin Capital G */ - { 284, "{\\^{G}}","\\^{G}", "\\^G" }, /* with circumflex */ - { 286, "{\\u{G}}","\\u{G}", "\\u G" }, /* with breve */ - { 288, "{\\.{G}}","\\.{G}", "\\.G" }, /* with dot above */ - { 290, "{\\c{G}}","\\c{G}", "\\c G" }, /* with cedilla */ - { 486, "{\\v{G}}","\\v{G}", "\\v G" }, /* with caron */ - { 500, "{\\'{G}}","\\'{G}", "\\'G" }, /* with acute */ + { 284, LATEX_MACRO, "^{G}", { "{\\^{G}}", "\\^{G}", "\\^G" } }, /* with circumflex */ + { 286, LATEX_MACRO, "u{G}", { "{\\u{G}}", "\\u{G}", "\\u G" } }, /* with breve */ + { 288, LATEX_MACRO, ".{G}", { "{\\.{G}}", "\\.{G}", "\\.G" } }, /* with dot above */ + { 290, LATEX_MACRO, "c{G}", { "{\\c{G}}", "\\c{G}", "\\c G" } }, /* with cedilla */ + { 486, LATEX_MACRO, "v{G}", { "{\\v{G}}", "\\v{G}", "\\v G" } }, /* with caron */ + { 500, LATEX_MACRO, "'{G}", { "{\\'{G}}", "\\'{G}", "\\'G" } }, /* with acute */ /* Latin Small g */ - { 285, "{\\^{g}}","\\^{g}", "\\^g" }, /* with circumflex */ - { 287, "{\\u{g}}","\\u{g}", "\\u g" }, /* with breve */ - { 289, "{\\.{g}}","\\.{g}", "\\.g" }, /* with dot above */ - { 291, "{\\c{g}}","\\c{g}", "\\c g" }, /* with cedilla */ - { 487, "{\\v{g}}","\\v{g}", "\\v g" }, /* with caron */ - { 501, "{\\'{g}}","\\'{g}", "\\'g" }, /* with acute */ + { 285, LATEX_MACRO, "^{g}", { "{\\^{g}}", "\\^{g}", "\\^g" } }, /* with circumflex */ + { 287, LATEX_MACRO, "u{g}", { "{\\u{g}}", "\\u{g}", "\\u g" } }, /* with breve */ + { 289, LATEX_MACRO, ".{g}", { "{\\.{g}}", "\\.{g}", "\\.g" } }, /* with dot above */ + { 291, LATEX_MACRO, "c{g}", { "{\\c{g}}", "\\c{g}", "\\c g" } }, /* with cedilla */ + { 487, LATEX_MACRO, "v{g}", { "{\\v{g}}", "\\v{g}", "\\v g" } }, /* with caron */ + { 501, LATEX_MACRO, "'{g}", { "{\\'{g}}", "\\'{g}", "\\'g" } }, /* with acute */ /* Latin Capital H */ - { 292, "{\\^{H}}","\\^{H}", "\\^H" }, /* with circumflex */ -/* { 294, "", "", "" },*//* with stroke */ + { 292, LATEX_MACRO, "^{H}", { "{\\^{H}}", "\\^{H}", "\\^H" } }, /* with circumflex */ +/* { 294, LATEX_MACRO, "", { NULL, NULL, NULL } },*//* with stroke */ /* Latin Capital h */ - { 293, "{\\^{h}}","\\^{h}", "\\^h" }, /* with circumflex */ -/* { 295, "", "", "" },*//* with stroke */ + { 293, LATEX_MACRO, "^{h}", { "{\\^{h}}", "\\^{h}", "\\^h" } }, /* with circumflex */ +/* { 295, LATEX_MACRO, "", { NULL, NULL, NULL } },*//* with stroke */ /* Latin Capital I */ - { 204, "{\\`I}", "\\`{I}", "\\`I" }, /* with grave */ - { 205, "{\\'I}", "\\'{I}", "\\'I" }, /* with acute */ - { 206, "{\\^I}", "\\^{I}", "\\^I" }, /* with circumflex */ - { 207, "{\\\"I}", "\\\"{I}", "\\\"I" }, /* with diuresis */ - { 296, "{\\~{I}}","\\~{I}", "\\~I" }, /* with tilde */ - { 298, "{\\={I}}","\\={I}", "\\=I" }, /* with macron */ - { 300, "{\\u{I}}","\\u{I}", "\\u I" }, /* with breve */ - { 302, "{\\k{I}}","\\k{I}", "\\k I" }, /* with ogonek */ - { 304, "{\\.{I}}","\\.{I}", "\\. I" }, /* with dot above */ - { 463, "{\\v{I}}","\\v{I}", "\\v I" }, /* with caron */ + { 204, LATEX_MACRO, "`I", { "{\\`I}", "\\`{I}", "\\`I" } }, /* with grave */ + { 205, LATEX_MACRO, "'I", { "{\\'I}", "\\'{I}", "\\'I" } }, /* with acute */ + { 206, LATEX_MACRO, "^I", { "{\\^I}", "\\^{I}", "\\^I" } }, /* with circumflex */ + { 207, LATEX_MACRO, "\"I", { "{\\\"I}", "\\\"{I}", "\\\"I" } }, /* with diuresis */ + { 296, LATEX_MACRO, "~{I}", { "{\\~{I}}", "\\~{I}", "\\~I" } }, /* with tilde */ + { 298, LATEX_MACRO, "={I}", { "{\\={I}}", "\\={I}", "\\=I" } }, /* with macron */ + { 300, LATEX_MACRO, "u{I}", { "{\\u{I}}", "\\u{I}", "\\u I" } }, /* with breve */ + { 302, LATEX_MACRO, "k{I}", { "{\\k{I}}", "\\k{I}", "\\k I" } }, /* with ogonek */ + { 304, LATEX_MACRO, ".{I}", { "{\\.{I}}", "\\.{I}", "\\. I" } }, /* with dot above */ + { 463, LATEX_MACRO, "v{I}", { "{\\v{I}}", "\\v{I}", "\\v I" } }, /* with caron */ /* Latin Small i */ - { 236, "{\\`i}", "\\`{i}", "\\`i" }, /* with grave */ - { 237, "{\\'i}", "\\'{i}", "\\'i" }, /* with acute */ - { 238, "{\\^i}", "\\^{i}", "\\^i" }, /* with circumflex */ - { 239, "{\\\"i}", "\\\"{i}", "\\\"i" }, /* with diuresis */ - { 236, "{\\`\\i}", "\\`{\\i}", "\\`\\i" }, /* with grave */ - { 237, "{\\'\\i}", "\\'{\\i}", "\\'\\i" }, /* with acute */ - { 238, "{\\^\\i}", "\\^{\\i}", "\\^\\i" }, /* with circumflex */ - { 239, "{\\\"\\i}", "\\\"{\\i}", "\\\"\\i" }, /* with diuresis */ - { 297, "{\\~{\\i}}","\\~{\\i}", "\\~\\i{}"}, /* with tilde */ - { 299, "{\\={\\i}}", "\\={\\i}", "\\=\\i{}"}, /* with macron */ - { 301, "{\\u{\\i}}","\\u{\\i}", "\\u\\i{}"}, /* with breve */ - { 303, "{\\k{i}}","\\k{i}", "\\k i" }, /* with ogonek */ - /* Latex \i has no dot on "i"*/ - { 305, "{\\i}", "\\i{}", "" }, /* without dot above */ - { 464, "{\\v \\i{}}", "\\v \\i{}", "" }, /* with caron */ + { 236, LATEX_MACRO, "`i", { "{\\`i}", "\\`{i}", "\\`i" } }, /* with grave */ + { 237, LATEX_MACRO, "'i", { "{\\'i}", "\\'{i}", "\\'i" } }, /* with acute */ + { 238, LATEX_MACRO, "^i", { "{\\^i}", "\\^{i}", "\\^i" } }, /* with circumflex */ + { 239, LATEX_MACRO, "\"i", { "{\\\"i}", "\\\"{i}", "\\\"i" } }, /* with diuresis */ + { 303, LATEX_MACRO, "k{i}", { "{\\k{i}}", "\\k{i}", "\\k i" } }, /* with ogonek */ + /* Latex "\i" has no dot on "i" */ + { 305, LATEX_MACRO, "i", { "{\\i}", "\\i{}", NULL } }, /* without dot above */ + { 236, LATEX_MACRO, "`{\\i}", { "{\\`\\i}", "\\`{\\i}", "\\`\\i" } }, /* with grave */ + { 237, LATEX_MACRO, "'{\\i}", { "{\\'\\i}", "\\'{\\i}", "\\'\\i" } }, /* with acute */ + { 238, LATEX_MACRO, "^{\\i}", { "{\\^\\i}", "\\^{\\i}", "\\^\\i" } }, /* with circumflex */ + { 239, LATEX_MACRO, "\"{\\i}", { "{\\\"\\i}", "\\\"{\\i}","\\\"\\i" } }, /* with diuresis */ + { 297, LATEX_MACRO, "`{\\i}", { "{\\~{\\i}}", "\\~{\\i}", "\\~\\i{}" } }, /* with tilde */ + { 299, LATEX_MACRO, "={\\i}", { "{\\={\\i}}", "\\={\\i}", "\\=\\i{}" } }, /* with macron */ + { 301, LATEX_MACRO, "u{\\i}", { "{\\u{\\i}}", "\\u{\\i}", "\\u\\i{}" } }, /* with breve */ + { 464, LATEX_MACRO, "v{\\i}", { "{\\v \\i{}}", "\\v \\i{}", NULL } }, /* with caron */ -/* { 306, "", "", "" },*/ /* Latin Capital IJ */ -/* { 307, "" "", "" },*/ /* Latin Small ij */ +/* { 306, LATEX_MACRO, "", { NULL, NULL, NULL } },*/ /* Latin Capital IJ */ +/* { 307, LATEX_MACRO, "", { NULL, NULL, NULL } },*/ /* Latin Small ij */ /* Latin Capital J */ - { 308, "{\\^{J}}","\\^{J}", "\\^J" }, /* with circumflex */ + { 308, LATEX_MACRO, "^{J}", { "{\\^{J}}", "\\^{J}", "\\^J" } }, /* with circumflex */ /* Latin Small j */ - { 309, "{\\^{j}}","\\^{j}", "\\^j" }, /* with circumflex */ + { 309, LATEX_MACRO, "^{j}", { "{\\^{j}}", "\\^{j}", "\\^j" } }, /* with circumflex */ /* Latin Capital K */ - { 310, "{\\c{K}}","\\c{K}", "\\c K" }, /* with cedilla */ - { 488, "{\\v{K}}","\\v{K}", "\\v K" }, /* with caron */ + { 310, LATEX_MACRO, "c{K}", { "{\\c{K}}", "\\c{K}", "\\c K" } }, /* with cedilla */ + { 488, LATEX_MACRO, "v{K}", { "{\\v{K}}", "\\v{K}", "\\v K" } }, /* with caron */ /* Latin Small k */ - { 311, "{\\c{k}}","\\c{k}", "\\c k" }, /* with cedilla */ - { 489, "{\\v{k}}","\\v{k}", "\\v k" }, /* with caron */ + { 311, LATEX_MACRO, "c{k}", { "{\\c{k}}", "\\c{k}", "\\c k" } }, /* with cedilla */ + { 489, LATEX_MACRO, "v{k}", { "{\\v{k}}", "\\v{k}", "\\v k" } }, /* with caron */ /* Latin Capital L */ - { 313, "{\\'{L}}","\\'{L}", "\\'L" }, /* with acute */ - { 315, "{\\c{L}}","\\c{L}", "\\c L" }, /* with cedilla */ - { 317, "{\\v{L}}","\\v{l}", "\\v L" }, /* with caron */ - { 319, "{L\\hspace{-0.35em}$\\cdot$}","L\\hspace{-0.35em}$\\cdot$", "" }, /* with middle dot */ - { 321, "{\\L}", "{\\L{}}", "\\L{}" }, /* with stroke */ + { 313, LATEX_MACRO, "'{L}", { "{\\'{L}}", "\\'{L}", "\\'L" } }, /* with acute */ + { 315, LATEX_MACRO, "c{L}", { "{\\c{L}}", "\\c{L}", "\\c L" } }, /* with cedilla */ + { 317, LATEX_MACRO, "v{L}", { "{\\v{L}}", "\\v{l}", "\\v L" } }, /* with caron */ + { 319, LATEX_COMBO, "{L\\hspace{-0.35em}$\\cdot$}", { "{L\\hspace{-0.35em}$\\cdot$}","L\\hspace{-0.35em}$\\cdot$", NULL } }, /* with middle dot */ + { 321, LATEX_MACRO, "L", { "{\\L}", "{\\L{}}", "\\L{}" } }, /* with stroke */ /* Latin Small l */ - { 314, "{\\'{l}}","\\'{l}", "\\'l" }, /* with acute */ - { 316, "{\\c{l}}","\\c{l}", "\\c l" }, /* with cedilla */ - { 318, "{\\v{l}}","\\v{l}", "\\v l" }, /* with caron */ - { 320, "{l$\\cdot$}","l$\\cdot$", "" }, /* with middle dot */ - { 322, "{\\l}", "{\\l{}}", "\\l{}" }, /* with stroke */ + { 314, LATEX_MACRO, "'{l}", { "{\\'{l}}", "\\'{l}", "\\'l" } }, /* with acute */ + { 316, LATEX_MACRO, "c{l}", { "{\\c{l}}", "\\c{l}", "\\c l" } }, /* with cedilla */ + { 318, LATEX_MACRO, "v{l}", { "{\\v{l}}", "\\v{l}", "\\v l" } }, /* with caron */ + { 320, LATEX_COMBO, "{l$\\cdot$}", { "{l$\\cdot$}","l$\\cdot$", NULL } }, /* with middle dot */ + { 322, LATEX_MACRO, "l", { "{\\l}", "{\\l{}}", "\\l{}" } }, /* with stroke */ /* Latin Capital N */ - { 209, "{\\~{N}}","\\~{N}", "\\~N" }, /* with tilde */ - { 323, "{\\'{N}}","\\'{N}", "\\'N" }, /* with acute */ - { 325, "{\\c{N}}","\\c{N}", "\\c N" }, /* with cedilla */ - { 327, "{\\v{N}}","\\v{N}", "\\v N" }, /* with caron */ + { 209, LATEX_MACRO, "~{N}", { "{\\~{N}}", "\\~{N}", "\\~N" } }, /* with tilde */ + { 323, LATEX_MACRO, "'{N}", { "{\\'{N}}", "\\'{N}", "\\'N" } }, /* with acute */ + { 325, LATEX_MACRO, "c{N}", { "{\\c{N}}", "\\c{N}", "\\c N" } }, /* with cedilla */ + { 327, LATEX_MACRO, "v{N}", { "{\\v{N}}", "\\v{N}", "\\v N" } }, /* with caron */ /* Latin Small n */ - { 241, "{\\~{n}}","\\~{n}", "\\~n" }, /* with tilde */ - { 324, "{\\'{n}}","\\'{n}", "\\'n" }, /* with acute */ - { 326, "{\\c{n}}","\\c{n}", "\\c N" }, /* with cedilla */ - { 328, "{\\v{n}}","\\v{n}", "\\v n" }, /* with caron */ - { 329, "\n", "", "" }, /* preceeded by apostrophe */ + { 241, LATEX_MACRO, "~{n}", { "{\\~{n}}", "\\~{n}", "\\~n" } }, /* with tilde */ + { 324, LATEX_MACRO, "'{n}", { "{\\'{n}}", "\\'{n}", "\\'n" } }, /* with acute */ + { 326, LATEX_MACRO, "c{n}", { "{\\c{n}}", "\\c{n}", "\\c N" } }, /* with cedilla */ + { 328, LATEX_MACRO, "v{n}", { "{\\v{n}}", "\\v{n}", "\\v n" } }, /* with caron */ + { 329, LATEX_MACRO, "n", { "\\n", NULL, NULL } }, /* preceeded by apostrophe */ /* Latin Capital O */ - { 210, "{\\`O}", "\\`{O}", "\\`O" }, /* with grave */ - { 211, "{\\'O}", "\\'{O}", "\\'O" }, /* with acute */ - { 212, "{\\^O}", "\\^{O}", "\\^O" }, /* with circumflex */ - { 213, "{\\~O}", "\\~{O}", "\\~O" }, /* with tilde */ - { 214, "{\\\"O}", "\\\"{O}", "\\\"O" }, /* with diaeresis */ - { 216, "{\\O}", "\\O", "" }, /* with stroke */ - { 332, "{\\={O}}", "\\={O}", "\\=O" }, /* with macron */ - { 334, "{\\u{O}}", "\\u{O}", "\\u O" }, /* with breve */ - { 336, "{\\H{O}}", "\\H{O}", "\\H O" }, /* with double acute */ - { 465, "{\\v{O}}", "\\v{O}", "\\v O" }, /* with caron */ - { 490, "{\\k{O}}", "\\k{O}", "\\k O" }, /* with ogonek */ + { 210, LATEX_MACRO, "`O", { "{\\`O}", "\\`{O}", "\\`O" } }, /* with grave */ + { 211, LATEX_MACRO, "'O", { "{\\'O}", "\\'{O}", "\\'O" } }, /* with acute */ + { 212, LATEX_MACRO, "^O", { "{\\^O}", "\\^{O}", "\\^O" } }, /* with circumflex */ + { 213, LATEX_MACRO, "~O", { "{\\~O}", "\\~{O}", "\\~O" } }, /* with tilde */ + { 214, LATEX_MACRO, "\"O", { "{\\\"O}", "\\\"{O}", "\\\"O" } }, /* with diaeresis */ + { 216, LATEX_MACRO, "O", { "{\\O}", "\\O", NULL } }, /* with stroke */ + { 332, LATEX_MACRO, "={O}", { "{\\={O}}", "\\={O}", "\\=O" } }, /* with macron */ + { 334, LATEX_MACRO, "u{O}", { "{\\u{O}}", "\\u{O}", "\\u O" } }, /* with breve */ + { 336, LATEX_MACRO, "H{O}", { "{\\H{O}}", "\\H{O}", "\\H O" } }, /* with double acute */ + { 465, LATEX_MACRO, "v{O}", { "{\\v{O}}", "\\v{O}", "\\v O" } }, /* with caron */ + { 490, LATEX_MACRO, "k{O}", { "{\\k{O}}", "\\k{O}", "\\k O" } }, /* with ogonek */ /* Latin Small o */ - { 242, "{\\`o}", "\\`{o}", "\\`o" }, /* with grave */ - { 243, "{\\'o}", "\\'{o}", "\\'o" }, /* with acute */ - { 244, "{\\^o}", "\\^{o}", "\\^o" }, /* with circumflex */ - { 245, "{\\~o}", "\\~{o}", "\\~o" }, /* with tilde */ - { 246, "{\\\"o}", "\\\"{o}", "\\\"o" }, /* with diaeresis */ - { 248, "{\\o}", "\\o", "" }, /* with stroke */ - { 333, "{\\={o}}", "\\={o}", "\\=o" }, /* with macron */ - { 335, "{\\u{o}}", "\\u{o}", "\\u o" }, /* with breve */ - { 337, "{\\H{o}}", "\\H{o}", "\\H o" }, /* with double acute */ - { 466, "{\\v{o}}", "\\v{o}", "\\v o" }, /* with caron */ - { 491, "{\\k{o}}", "\\k{o}", "\\k o" }, /* with ogonek */ + { 242, LATEX_MACRO, "`o", { "{\\`o}", "\\`{o}", "\\`o" } }, /* with grave */ + { 243, LATEX_MACRO, "'o", { "{\\'o}", "\\'{o}", "\\'o" } }, /* with acute */ + { 244, LATEX_MACRO, "^o", { "{\\^o}", "\\^{o}", "\\^o" } }, /* with circumflex */ + { 245, LATEX_MACRO, "~o", { "{\\~o}", "\\~{o}", "\\~o" } }, /* with tilde */ + { 246, LATEX_MACRO, "\"o", { "{\\\"o}", "\\\"{o}", "\\\"o" } }, /* with diaeresis */ + { 248, LATEX_MACRO, "o", { "{\\o}", "\\o", NULL } }, /* with stroke */ + { 333, LATEX_MACRO, "={o}", { "{\\={o}}", "\\={o}", "\\=o" } }, /* with macron */ + { 335, LATEX_MACRO, "u{o}", { "{\\u{o}}", "\\u{o}", "\\u o" } }, /* with breve */ + { 337, LATEX_MACRO, "H{o}", { "{\\H{o}}", "\\H{o}", "\\H o" } }, /* with double acute */ + { 466, LATEX_MACRO, "v{o}", { "{\\v{o}}", "\\v{o}", "\\v o" } }, /* with caron */ + { 491, LATEX_MACRO, "k{o}", { "{\\k{o}}", "\\k{o}", "\\k o" } }, /* with ogonek */ - { 338, "{\\OE}", "\\OE", "" }, /* Latin Capital OE */ - { 339, "{\\oe}", "\\oe", "" }, /* Latin Small oe */ + { 338, LATEX_MACRO, "OE", { "{\\OE}", "\\OE", NULL } }, /* Latin Capital OE */ + { 339, LATEX_MACRO, "oe", { "{\\oe}", "\\oe", NULL } }, /* Latin Small oe */ /* Latin Capital R */ - { 340, "{\\'{R}}", "\\'{R}", "\\'R" }, /* with acute */ - { 342, "{\\c{R}}", "\\c{R}", "\\c R" }, /* with cedilla */ - { 344, "{\\v{R}}", "\\v{R}", "\\v R" }, /* with caron */ + { 340, LATEX_MACRO, "'R", { "{\\'{R}}", "\\'{R}", "\\'R" } }, /* with acute */ + { 342, LATEX_MACRO, "c{R}", { "{\\c{R}}", "\\c{R}", "\\c R" } }, /* with cedilla */ + { 344, LATEX_MACRO, "v{R}", { "{\\v{R}}", "\\v{R}", "\\v R" } }, /* with caron */ /* Latin Small r */ - { 341, "{\\'{r}}", "\\'{r}", "\\'r" }, /* with acute */ - { 343, "{\\c{r}}", "\\c{r}", "\\c r" }, /* with cedilla */ - { 345, "{\\v{r}}", "\\v{r}", "\\v r" }, /* with caron */ + { 341, LATEX_MACRO, "'r", { "{\\'{r}}", "\\'{r}", "\\'r" } }, /* with acute */ + { 343, LATEX_MACRO, "c{r}", { "{\\c{r}}", "\\c{r}", "\\c r" } }, /* with cedilla */ + { 345, LATEX_MACRO, "v{r}", { "{\\v{r}}", "\\v{r}", "\\v r" } }, /* with caron */ /* Latin Capital S */ - { 346, "{\\'{S}}", "\\'{S}", "\\'S" }, /* with acute */ - { 348, "{\\^{S}}", "\\^{S}", "\\^S" }, /* with circumflex */ - { 350, "{\\c{S}}", "\\c{S}", "\\c S" }, /* with cedilla */ - { 352, "{\\v{S}}", "\\v{S}", "\\v S" }, /* with caron */ + { 346, LATEX_MACRO, "'{S}", { "{\\'{S}}", "\\'{S}", "\\'S" } }, /* with acute */ + { 348, LATEX_MACRO, "^{S}", { "{\\^{S}}", "\\^{S}", "\\^S" } }, /* with circumflex */ + { 350, LATEX_MACRO, "c{S}", { "{\\c{S}}", "\\c{S}", "\\c S" } }, /* with cedilla */ + { 352, LATEX_MACRO, "v{S}", { "{\\v{S}}", "\\v{S}", "\\v S" } }, /* with caron */ /* Latin Small s */ - { 347, "{\\'{s}}","\\'{s}", "\\'s" }, /* with acute */ - { 349, "{\\^{s}}","\\^{s}", "\\^s" }, /* with circumflex */ - { 351, "{\\c{s}}","\\c{s}", "\\c s" }, /* with cedilla */ - { 353, "{\\v{s}}","\\v{s}", "\\v s" }, /* with caron */ + { 347, LATEX_MACRO, "'{s}", { "{\\'{s}}", "\\'{s}", "\\'s" } }, /* with acute */ + { 349, LATEX_MACRO, "^{s}", { "{\\^{s}}", "\\^{s}", "\\^s" } }, /* with circumflex */ + { 351, LATEX_MACRO, "c{s}", { "{\\c{s}}", "\\c{s}", "\\c s" } }, /* with cedilla */ + { 353, LATEX_MACRO, "v{s}", { "{\\v{s}}", "\\v{s}", "\\v s" } }, /* with caron */ /* Latin Capital T */ - { 354, "{\\c{T}}", "\\c{T}", "" }, /* with cedilla */ - { 356, "{\\v{T}}", "\\v{T}", "" }, /* with caron */ -/* { 358, "", "", "" },*//* with stroke */ + { 354, LATEX_MACRO, "c{T}", { "{\\c{T}}", "\\c{T}", NULL } }, /* with cedilla */ + { 356, LATEX_MACRO, "v{T}", { "{\\v{T}}", "\\v{T}", NULL } }, /* with caron */ +/* { 358, LATEX_MACRO, "", { NULL, NULL, NULL } },*//* with stroke */ /* Latin Small t */ - { 355, "{\\c{t}}", "\\c{t}", "" }, /* with cedilla */ - { 357, "{\\v{t}}", "\\v{t}", "" }, /* with caron */ -/* { 359, "", "", "" },*//* with stroke */ + { 355, LATEX_MACRO, "c{T}", { "{\\c{t}}", "\\c{t}", NULL } }, /* with cedilla */ + { 357, LATEX_MACRO, "v{T}", { "{\\v{t}}", "\\v{t}", NULL } }, /* with caron */ +/* { 359, LATEX_MACRO, "", { NULL, NULL, NULL } },*//* with stroke */ - { 223, "{\\ss}", "\\ss", "" }, /* German sz ligature, "sharp s" */ + { 223, LATEX_MACRO, "ss", { "{\\ss}", "\\ss", NULL } }, /* German sz ligature, "sharp s" */ /* Latin Capital U */ - { 217, "{\\`U}", "\\`{U}", "\\`U" }, /* with grave */ - { 218, "{\\'U}", "\\'{U}", "\\'U" }, /* with acute */ - { 219, "{\\^U}", "\\^{U}", "\\^U" }, /* with circumflex */ - { 220, "{\\\"U}", "\\\"{U}", "\\\"U" }, /* with diaeresis */ - { 360, "{\\~{U}}","\\~{U}", "\\~U" }, /* with tilde */ - { 362, "{\\={U}}","\\={U}", "\\=U" }, /* with macron */ - { 364, "{\\u{U}}","\\u{U}", "\\u U" }, /* with breve */ - { 366, "{\\r{U}}","\\r{U}", "\\r U" }, /* with ring above */ - { 368, "{\\H{U}}","\\H{U}", "\\H U" }, /* with double acute */ - { 370, "{\\k{U}}","\\k{U}", "\\k U" }, /* with ogonek */ - { 467, "{\\v{U}}","\\v{U}", "\\v U" }, /* with caron */ + { 217, LATEX_MACRO, "`U", { "{\\`U}", "\\`{U}", "\\`U" } }, /* with grave */ + { 218, LATEX_MACRO, "'U", { "{\\'U}", "\\'{U}", "\\'U" } }, /* with acute */ + { 219, LATEX_MACRO, "^U", { "{\\^U}", "\\^{U}", "\\^U" } }, /* with circumflex */ + { 220, LATEX_MACRO, "\"U", { "{\\\"U}", "\\\"{U}","\\\"U" } }, /* with diaeresis */ + { 360, LATEX_MACRO, "~{U}", { "{\\~{U}}", "\\~{U}", "\\~U" } }, /* with tilde */ + { 362, LATEX_MACRO, "={U}", { "{\\={U}}", "\\={U}", "\\=U" } }, /* with macron */ + { 364, LATEX_MACRO, "u{U}", { "{\\u{U}}", "\\u{U}", "\\u U" } }, /* with breve */ + { 366, LATEX_MACRO, "r{U}", { "{\\r{U}}", "\\r{U}", "\\r U" } }, /* with ring above */ + { 368, LATEX_MACRO, "H{U}", { "{\\H{U}}", "\\H{U}", "\\H U" } }, /* with double acute */ + { 370, LATEX_MACRO, "k{U}", { "{\\k{U}}", "\\k{U}", "\\k U" } }, /* with ogonek */ + { 467, LATEX_MACRO, "v{U}", { "{\\v{U}}", "\\v{U}", "\\v U" } }, /* with caron */ /* Latin Small u */ - { 249, "{\\`u}", "\\`{u}", "\\`u" }, /* with grave */ - { 250, "{\\'u}", "\\'{u}", "\\'u" }, /* with acute */ - { 251, "{\\^u}", "\\^{u}", "\\^u" }, /* with circumflex */ - { 252, "{\\\"u}", "\\\"{u}", "\\\"u" }, /* with diaeresis */ - { 361, "{\\~{u}}","\\~{u}", "" }, /* with tilde */ - { 363, "{\\={u}}","\\={u}", "\\=u" }, /* with macron */ - { 365, "{\\u{u}}","\\u{u}", "\\u u" }, /* with breve */ - { 367, "{\\r{u}}","\\r{u}", "\\r u" }, /* with ring above */ - { 369, "{\\H{u}}","\\H{u}", "\\H u" }, /* with double acute */ - { 371, "{\\k{u}}","\\k{u}", "\\k u" }, /* with ogonek */ - { 468, "{\\v{u}}","\\v{u}", "\\v u" }, /* with caron */ + { 249, LATEX_MACRO, "`u", { "{\\`u}", "\\`{u}", "\\`u" } }, /* with grave */ + { 250, LATEX_MACRO, "'u", { "{\\'u}", "\\'{u}", "\\'u" } }, /* with acute */ + { 251, LATEX_MACRO, "^u", { "{\\^u}", "\\^{u}", "\\^u" } }, /* with circumflex */ + { 252, LATEX_MACRO, "\"u", { "{\\\"u}", "\\\"{u}","\\\"u" } }, /* with diaeresis */ + { 361, LATEX_MACRO, "~{u}", { "{\\~{u}}", "\\~{u}", NULL } }, /* with tilde */ + { 363, LATEX_MACRO, "={u}", { "{\\={u}}", "\\={u}", "\\=u" } }, /* with macron */ + { 365, LATEX_MACRO, "u{u}", { "{\\u{u}}", "\\u{u}", "\\u u" } }, /* with breve */ + { 367, LATEX_MACRO, "r{u}", { "{\\r{u}}", "\\r{u}", "\\r u" } }, /* with ring above */ + { 369, LATEX_MACRO, "H{u}", { "{\\H{u}}", "\\H{u}", "\\H u" } }, /* with double acute */ + { 371, LATEX_MACRO, "k{u}", { "{\\k{u}}", "\\k{u}", "\\k u" } }, /* with ogonek */ + { 468, LATEX_MACRO, "v{u}", { "{\\v{u}}", "\\v{u}", "\\v u" } }, /* with caron */ /* Latin Capital W */ - { 372, "{\\^{W}}", "\\^{W}", "\\^W" }, /* with circumflex */ + { 372, LATEX_MACRO, "^{W}", { "{\\^{W}}", "\\^{W}", "\\^W" } }, /* with circumflex */ /* Latin Small w */ - { 373, "{\\^{w}}", "\\^{w}", "\\^w" }, /* with circumflex */ + { 373, LATEX_MACRO, "^{w}", { "{\\^{w}}", "\\^{w}", "\\^w" } }, /* with circumflex */ /* Latin Capital Y */ - { 221, "{\\'{Y}}","\\'{Y}", "\\'Y" }, /* with acute */ - { 374, "{\\^{Y}}","\\^{Y}", "\\^Y" }, /* with circumflex */ - { 376, "{\\\"{Y}}","\\\"{Y}","\\\"Y" }, /* with diaeresis */ + { 221, LATEX_MACRO, "'{Y}", { "{\\'{Y}}", "\\'{Y}", "\\'Y" } }, /* with acute */ + { 374, LATEX_MACRO, "^{Y}", { "{\\^{Y}}", "\\^{Y}", "\\^Y" } }, /* with circumflex */ + { 376, LATEX_MACRO, "\"{Y}",{ "{\\\"{Y}}","\\\"{Y}","\\\"Y" } }, /* with diaeresis */ /* Latin Small y */ - { 253, "{\\'y}", "\\'{y}", "\\'y" }, /* with acute */ - { 255, "{\\\"y}", "\\\"{y}","\\\"y" }, /* with diaeresis */ - { 375, "{\\^{y}}","\\^{y}", "\\^y" }, /* with circumflex */ + { 253, LATEX_MACRO, "'y", { "{\\'y}", "\\'{y}", "\\'y" } }, /* with acute */ + { 255, LATEX_MACRO, "\"y", { "{\\\"y}", "\\\"{y}","\\\"y" } }, /* with diaeresis */ + { 375, LATEX_MACRO, "^{y}", { "{\\^{y}}","\\^{y}", "\\^y" } }, /* with circumflex */ /* Latin Capital Z */ - { 377, "{\\'{Z}}","\\'{Z}", "\\'Z" }, /* with acute */ - { 379, "{\\.{Z}}","\\.{Z}", "\\.Z" }, /* with dot above */ - { 381, "{\\v{Z}}","\\v{Z}", "\\v Z" }, /* with caron */ + { 377, LATEX_MACRO, "'{Z}", { "{\\'{Z}}","\\'{Z}", "\\'Z" } }, /* with acute */ + { 379, LATEX_MACRO, ".{Z}", { "{\\.{Z}}","\\.{Z}", "\\.Z" } }, /* with dot above */ + { 381, LATEX_MACRO, "v{Z}", { "{\\v{Z}}","\\v{Z}", "\\v Z" } }, /* with caron */ /* Latin Small z */ - { 378, "{\\'{z}}","\\'{z}", "\\'z" }, /* with acute */ - { 380, "{\\.{z}}","\\.{z}", "\\.z" }, /* with dot above */ - { 382, "{\\v{z}}","\\v{z}", "\\v z" }, /* with caron */ + { 378, LATEX_MACRO, "'{z}", { "{\\'{z}}","\\'{z}", "\\'z" } }, /* with acute */ + { 380, LATEX_MACRO, ".{z}", { "{\\.{z}}","\\.{z}", "\\.z" } }, /* with dot above */ + { 382, LATEX_MACRO, "v{z}", { "{\\v{z}}","\\v{z}", "\\v z" } }, /* with caron */ /* Needs to be before \nu */ - { 8203, "$\\null$", "\\null", "" }, /* No space ​ */ + { 8203,LATEX_MATH, "null", { "$\\null$", "\\null", NULL } }, /* No space ​ */ - { 913, "$\\Alpha$", "\\Alpha", "" }, /*GREEKCAPITALLETTERALPHA*/ - /* 902 = GREEKCAPITALLETTERALPHAWITHTONOS*/ - { 914, "$\\Beta$", "\\Beta", "" }, /*GREEKCAPITALLETTERBETA*/ - { 915, "$\\Gamma$", "\\Gamma", "" }, /*GREEKCAPITALLETTERGAMMA*/ - { 916, "$\\Delta$", "\\Delta", "" }, /*GREEKCAPITALLETTERDELTA*/ - { 917, "$\\Epsilon$", "\\Epsilon", "" }, /*GREEKCAPITALLETTEREPSILON*/ - /* 904 = GREEKCAPITALLETTEREPSILONWITHTONOS*/ - { 918, "$\\Zeta$", "\\Zeta", "" }, /*GREEKCAPITALLETTERZETA*/ - { 919, "$\\Eta$", "\\Eta", "" }, /*GREEKCAPITALLETTERETA*/ - /* 905 = GREEKCAPITALLETTERETAWITHTONOS*/ - { 920, "$\\Theta$", "\\Theta", "" }, /*GREEKCAPITALLETTERTHETA*/ - { 921, "$\\Iota$", "\\Iota", "" }, /*GREEKCAPITALLETTERIOTA*/ - /* 938 = GREEKCAPITALLETTERIOTAWITHDIALYTIKA*/ - /* 906 = GREEKCAPITALLETTERIOTAWITHTONOS*/ - { 922, "$\\Kappa$", "\\Kappa", "" }, /*GREEKCAPITALLETTERKAPPA*/ - { 923, "$\\Lambda$", "\\Lambda", "" }, /*GREEKCAPITALLETTERLAMDA*/ - { 924, "$\\Mu$", "\\Mu", "" }, /*GREEKCAPITALLETTERMU*/ - { 925, "$\\Nu$", "\\Nu", "" }, /*GREEKCAPITALLETTERNU*/ - { 926, "$\\Xi$", "\\Xi", "" }, /*GREEKCAPITALLETTERXI*/ - { 927, "$\\Omicron$", "\\Omicron", "" }, /*GREEKCAPITALLETTEROMICRON*/ - /* 908 = GREEKCAPITALLETTEROMICRONWITHTONOS*/ - { 928, "$\\Pi$", "\\Pi", "" }, /*GREEKCAPITALLETTERPI*/ - { 929, "$\\Rho$", "\\Rho", "" }, /*GREEKCAPITALLETTERRHO*/ - { 931, "$\\Sigma$", "\\Sigma", "" }, /*GREEKCAPITALLETTERSIGMA*/ - { 932, "$\\Tau$", "\\Tau", "" }, /*GREEKCAPITALLETTERTAU*/ - { 933, "$\\Upsilon$", "\\Upsilon", "" }, /*GREEKCAPITALLETTERUPSILON*/ - /* 939 = GREEKCAPITALLETTERUPSILONWITHDIALYTIKA*/ - /* 910 = GREEKCAPITALLETTERUPSILONWITHTONOS*/ - { 934, "$\\Phi$", "\\Phi", "" }, /*GREEKCAPITALLETTERPHI*/ - { 935, "$\\Chi$", "\\Chi", "" }, /*GREEKCAPITALLETTERCHI*/ - { 936, "$\\Psi$", "\\Psi", "" }, /*GREEKCAPITALLETTERPSI*/ - { 937, "$\\Omega$", "\\Omega", "" }, /*GREEKCAPITALLETTEROMEGA*/ - /* 911, = GREEKCAPITALLETTEROMEGAWITHTONOS*/ + { 913, LATEX_MATH, "Alpha", { "$\\Alpha$", "\\Alpha", NULL } }, /*GREEK CAPITAL LETTERALPHA*/ + { 914, LATEX_MATH, "Beta", { "$\\Beta$", "\\Beta", NULL } }, /*GREEK CAPITAL LETTERBETA*/ + { 915, LATEX_MATH, "Gamma", { "$\\Gamma$", "\\Gamma", NULL } }, /*GREEK CAPITAL LETTERGAMMA*/ + { 916, LATEX_MATH, "Delta", { "$\\Delta$", "\\Delta", NULL } }, /*GREEK CAPITAL LETTERDELTA*/ + { 917, LATEX_MATH, "Epsilon", { "$\\Epsilon$", "\\Epsilon", NULL } }, /*GREEK CAPITAL LETTEREPSILON*/ + { 918, LATEX_MATH, "Zeta", { "$\\Zeta$", "\\Zeta", NULL } }, /*GREEK CAPITAL LETTERZETA*/ + { 919, LATEX_MATH, "Eta", { "$\\Eta$", "\\Eta", NULL } }, /*GREEK CAPITAL LETTERETA*/ + { 920, LATEX_MATH, "Theta", { "$\\Theta$", "\\Theta", NULL } }, /*GREEK CAPITAL LETTERTHETA*/ + { 921, LATEX_MATH, "Iota", { "$\\Iota$", "\\Iota", NULL } }, /*GREEK CAPITAL LETTERIOTA*/ + { 922, LATEX_MATH, "Kappa", { "$\\Kappa$", "\\Kappa", NULL } }, /*GREEK CAPITAL LETTERKAPPA*/ + { 923, LATEX_MATH, "Lambda", { "$\\Lambda$", "\\Lambda", NULL } }, /*GREEK CAPITAL LETTERLAMDA*/ + { 924, LATEX_MATH, "Mu", { "$\\Mu$", "\\Mu", NULL } }, /*GREEK CAPITAL LETTERMU*/ + { 925, LATEX_MATH, "Nu", { "$\\Nu$", "\\Nu", NULL } }, /*GREEK CAPITAL LETTERNU*/ + { 926, LATEX_MATH, "Xi", { "$\\Xi$", "\\Xi", NULL } }, /*GREEK CAPITAL LETTERXI*/ + { 927, LATEX_MATH, "Omicron", { "$\\Omicron$", "\\Omicron", NULL } }, /*GREEK CAPITAL LETTEROMICRON*/ + { 928, LATEX_MATH, "Pi", { "$\\Pi$", "\\Pi", NULL } }, /*GREEK CAPITAL LETTERPI*/ + { 929, LATEX_MATH, "Rho", { "$\\Rho$", "\\Rho", NULL } }, /*GREEK CAPITAL LETTERRHO*/ + { 931, LATEX_MATH, "Sigma", { "$\\Sigma$", "\\Sigma", NULL } }, /*GREEK CAPITAL LETTERSIGMA*/ + { 932, LATEX_MATH, "Tau", { "$\\Tau$", "\\Tau", NULL } }, /*GREEK CAPITAL LETTERTAU*/ + { 933, LATEX_MATH, "Upsilon", { "$\\Upsilon$", "\\Upsilon", NULL } }, /*GREEK CAPITAL LETTERUPSILON*/ + { 934, LATEX_MATH, "Phi", { "$\\Phi$", "\\Phi", NULL } }, /*GREEK CAPITAL LETTERPHI*/ + { 935, LATEX_MATH, "Chi", { "$\\Chi$", "\\Chi", NULL } }, /*GREEK CAPITAL LETTERCHI*/ + { 936, LATEX_MATH, "Psi", { "$\\Psi$", "\\Psi", NULL } }, /*GREEK CAPITAL LETTERPSI*/ + { 937, LATEX_MATH, "Omega", { "$\\Omega$", "\\Omega", NULL } }, /*GREEK CAPITAL LETTEROMEGA*/ + /* 902 = GREEK CAPITAL LETTER ALPHAWITHTONOS*/ + /* 904 = GREEK CAPITAL LETTER EPSILONWITHTONOS*/ + /* 905 = GREEK CAPITAL LETTER ETAWITHTONOS*/ + /* 938 = GREEK CAPITAL LETTER IOTAWITHDIALYTIKA*/ + /* 906 = GREEK CAPITAL LETTER IOTAWITHTONOS*/ + /* 908 = GREEK CAPITAL LETTER OMICRONWITHTONOS*/ + /* 939 = GREEK CAPITAL LETTER UPSILONWITHDIALYTIKA*/ + /* 910 = GREEK CAPITAL LETTER UPSILONWITHTONOS*/ + /* 911, = GREEK CAPITAL LETTER OMEGAWITHTONOS*/ - { 945, "$\\alpha$", "\\alpha", "" }, /*GREEKSMALLLETTERALPHA*/ - /* 940 = GREEKSMALLLETTERALPHAWITHTONOS*/ - { 946, "$\\beta$", "\\beta", "" }, /*GREEKSMALLLETTERBETA*/ - { 968, "$\\psi$", "\\psi", "" }, /*GREEKSMALLLETTERPSI*/ - { 948, "$\\delta$", "\\delta", "" }, /*GREEKSMALLLETTERDELTA*/ - { 949, "$\\epsilon$", "\\epsilon", "" }, /*GREEKSMALLLETTEREPSILON*/ - /* 941 = GREEKSMALLLETTEREPSILONWITHTONOS*/ - { 966, "$\\phi$", "\\phi", "" }, /*GREEKSMALLLETTERPHI*/ - { 947, "$\\gamma$", "\\gamma", "" }, /*GREEKSMALLLETTERGAMMA*/ - { 951, "$\\eta$", "\\eta", "" }, /*GREEKSMALLLETTERETA*/ - /* 942 = GREEKSMALLLETTERETAWITHTONOS */ - { 953, "$\\iota$", "\\iota", "" }, /*GREEKSMALLLETTERIOTA*/ - /* 912 = GREEKSMALLLETTERIOTAWITHDIALYTIKAANDTONOS*/ - /* 943 = GREEKSMALLLETTERIOTAWITHTONOS */ - /* 970 = GREEKSMALLLETTERIOTAWITHDIALYTIKA */ - { 958, "$\\xi$", "\\xi", "" }, /*GREEKSMALLLETTERXI*/ - { 954, "$\\kappa$", "\\kappa" , "" }, /*GREEKSMALLLETTERKAPPA*/ - { 955, "$\\lambda$", "\\lambda", "" }, /*GREEKSMALLLETTERLAMDA*/ - { 956, "$\\mu$", "\\mu", "" }, /*GREEKSMALLLETTERMU*/ - { 957, "$\\nu$", "\\nu", "" }, /*GREEKSMALLLETTERNU*/ - { 959, "$\\omicron$", "\\omicron", "" }, /*GREEKSMALLLETTEROMICRON*/ - /* 972 = GREEKSMALLLETTEROMICRONWITHTONOS*/ - { 960, "$\\pi$", "\\pi", "" }, /*GREEKSMALLLETTERPI*/ - { 961, "$\\rho$", "\\rho", "" }, /*GREEKSMALLLETTERRHO*/ - { 963, "$\\sigma$", "\\sigma", "" }, /*GREEKSMALLLETTERSIGMA*/ - { 964, "$\\tau$", "\\tau", "" }, /*GREEKSMALLLETTERTAU*/ - { 952, "$\\theta$", "\\theta", "" }, /*GREEKSMALLLETTERTHETA*/ - { 969, "$\\omega$", "\\omega", "" }, /*GREEKSMALLLETTEROMEGA*/ - /* 974 = GREEKSMALLLETTEROMEGAWITHTONOS*/ - { 967, "$\\chi$", "\\chi", "" }, /*GREEKSMALLLETTERCHI*/ - { 965, "$\\upsilon$", "\\upsilon", "" }, /*GREEKSMALLLETTERUPSILON*/ - /* 973 = GREEKSMALLLETTERUPSILONWITHTONOS*/ - /* 971 = GREEKSMALLLETTERUPSILONWITHDIALYTIKA*/ - /* 944 = GREEKSMALLLETTERUPSILONWITHDIALYTIKAANDTONOS*/ - { 950, "$\\zeta$", "\\zeta", "" }, /*GREEKSMALLLETTERZETA*/ + { 945, LATEX_MATH, "alpha", { "$\\alpha$", "\\alpha", NULL } }, /*GREEK SMALL LETTER ALPHA*/ + { 946, LATEX_MATH, "beta", { "$\\beta$", "\\beta", NULL } }, /*GREEK SMALL LETTER BETA*/ + { 968, LATEX_MATH, "psi", { "$\\psi$", "\\psi", NULL } }, /*GREEK SMALL LETTER PSI*/ + { 948, LATEX_MATH, "delta", { "$\\delta$", "\\delta", NULL } }, /*GREEK SMALL LETTER DELTA*/ + { 949, LATEX_MATH, "epsilon", { "$\\epsilon$", "\\epsilon", NULL } }, /*GREEK SMALL LETTER EPSILON*/ + { 966, LATEX_MATH, "phi", { "$\\phi$", "\\phi", NULL } }, /*GREEK SMALL LETTER PHI*/ + { 947, LATEX_MATH, "gamma", { "$\\gamma$", "\\gamma", NULL } }, /*GREEK SMALL LETTER GAMMA*/ + { 951, LATEX_MATH, "eta", { "$\\eta$", "\\eta", NULL } }, /*GREEK SMALL LETTER ETA*/ + { 953, LATEX_MATH, "iota", { "$\\iota$", "\\iota", NULL } }, /*GREEK SMALL LETTER IOTA*/ + { 958, LATEX_MATH, "xi", { "$\\xi$", "\\xi", NULL } }, /*GREEK SMALL LETTER XI*/ + { 954, LATEX_MATH, "kappa", { "$\\kappa$", "\\kappa" , NULL } }, /*GREEK SMALL LETTER KAPPA*/ + { 955, LATEX_MATH, "lambda", { "$\\lambda$", "\\lambda", NULL } }, /*GREEK SMALL LETTER LAMDA*/ + { 956, LATEX_MATH, "mu", { "$\\mu$", "\\mu", NULL } }, /*GREEK SMALL LETTER MU*/ + { 957, LATEX_MATH, "nu", { "$\\nu$", "\\nu", NULL } }, /*GREEK SMALL LETTER NU*/ + { 959, LATEX_MATH, "omicron", { "$\\omicron$", "\\omicron", NULL } }, /*GREEK SMALL LETTER OMICRON*/ + { 960, LATEX_MATH, "pi", { "$\\pi$", "\\pi", NULL } }, /*GREEK SMALL LETTER PI*/ + { 961, LATEX_MATH, "rho", { "$\\rho$", "\\rho", NULL } }, /*GREEK SMALL LETTER RHO*/ + { 963, LATEX_MATH, "sigma", { "$\\sigma$", "\\sigma", NULL } }, /*GREEK SMALL LETTER SIGMA*/ + { 964, LATEX_MATH, "tau", { "$\\tau$", "\\tau", NULL } }, /*GREEK SMALL LETTER TAU*/ + { 952, LATEX_MATH, "theta", { "$\\theta$", "\\theta", NULL } }, /*GREEK SMALL LETTER THETA*/ + { 969, LATEX_MATH, "omega", { "$\\omega$", "\\omega", NULL } }, /*GREEK SMALL LETTER OMEGA*/ + { 967, LATEX_MATH, "chi", { "$\\chi$", "\\chi", NULL } }, /*GREEK SMALL LETTER CHI*/ + { 965, LATEX_MATH, "upsilon", { "$\\upsilon$", "\\upsilon", NULL } }, /*GREEK SMALL LETTER UPSILON*/ + { 950, LATEX_MATH, "zeta", { "$\\zeta$", "\\zeta", NULL } }, /*GREEK SMALL LETTER ZETA*/ + /* 940 = GREEK SMALL LETTER ALPHAWITHTONOS*/ + /* 941 = GREEK SMALL LETTER EPSILONWITHTONOS*/ + /* 942 = GREEK SMALL LETTER ETAWITHTONOS */ + /* 912 = GREEK SMALL LETTER IOTAWITHDIALYTIKAANDTONOS*/ + /* 943 = GREEK SMALL LETTER IOTAWITHTONOS */ + /* 970 = GREEK SMALL LETTER IOTAWITHDIALYTIKA */ + /* 972 = GREEK SMALL LETTER OMICRONWITHTONOS*/ + /* 974 = GREEK SMALL LETTER OMEGAWITHTONOS*/ + /* 973 = GREEK SMALL LETTER UPSILONWITHTONOS*/ + /* 971 = GREEK SMALL LETTER UPSILONWITHDIALYTIKA*/ + /* 944 = GREEK SMALL LETTER UPSILONWITHDIALYTIKAANDTONOS*/ - { 181, "{\\textmu}", "\\textmu", "$\\mu$" }, /* 181=micro sign, techically µ */ + { 181, LATEX_MACRO, "textmu", { "{\\textmu}", "\\textmu", "$\\mu$" } }, /* 181=micro sign, techically µ */ /* Make sure that these don't stomp on other latex things above */ - { 8242, "{\\textasciiacutex}", "\\textasciiacutex", "$'$" }, /* Prime symbol ′ */ - { 180, "{\\textasciiacute}", "\\textasciiacute", "\\'" }, /* acute accent ´ */ -/* { 769, "\\'", "", "" },*/ /* Acute accent ́--apply to next char */ - - { 8243, "{\\textacutedbl}", "\\textacutedbl", "$''$" }, /* Double prime ″ */ - { 8245, "{\\textasciigrave}", "\\textasciigrave", "\\`" }, /* Grave accent ‵ */ -/* { 768, "\\`", "", "" },*/ /* Grave accent ̀--apply to next char */ + { 8242, LATEX_MACRO, "textasciiacutex", { "{\\textasciiacutex}", "\\textasciiacutex", "$'$" } }, /* Prime symbol ′ */ + { 180, LATEX_MACRO, "textasciiacute", { "{\\textasciiacute}", "\\textasciiacute", "\\'" } }, /* acute accent ´ */ + { 8243, LATEX_MACRO, "textacutedbl", { "{\\textacutedbl}", "\\textacutedbl", "$''$" } }, /* Double prime ″ */ + { 8245, LATEX_MACRO, "textasciigrave", { "{\\textasciigrave}", "\\textasciigrave", "\\`" } }, /* Grave accent ‵ */ +/* { 768, LATEX_MACRO, "`", { "\\`", NULL, NULL } },*//* Grave accent ̀--apply to next char */ +/* { 769, LATEX_MACRO, "'", { "\\'", NULL, NULL } },*//* Acute accent ́--apply to next char */ - { 8963, "{\\textasciicircum}", "\\textasciicircum", ""} , /* ⌃ */ - { 184, "{\\textasciicedilla}", "\\textasciicedilla", "" }, /* cedilla ¸ */ - { 168, "{\\textasciidieresis}", "\\textasciidieresis", "" }, /* dieresis ¨ */ - { 175, "{\\textasciimacron}", "\\textasciimacron", "" }, /* macron ¯ */ + { 8963, LATEX_MACRO, "textasciicircum", { "{\\textasciicircum}", "\\textasciicircum", NULL } }, /* ⌃ */ + { 184, LATEX_MACRO, "textasciicedilla", { "{\\textasciicedilla}", "\\textasciicedilla", NULL } }, /* cedilla ¸ */ + { 168, LATEX_MACRO, "textasciidieresis", { "{\\textasciidieresis}", "\\textasciidieresis", NULL } }, /* dieresis ¨ */ + { 175, LATEX_MACRO, "textasciimacron", { "{\\textasciimacron}", "\\textasciimacron", NULL } }, /* macron ¯ */ - { 8593, "{\\textuparrow}", "\\textuparrow", "" }, /* Up arrow ↑ */ - { 8595, "{\\textdownarrow}", "\\textdownarrow", "" }, /* Down arrow ↓ */ - { 8594, "{\\textrightarrow}", "\\textrightarrow", "" }, /* Right arrow → */ - { 8592, "{\\textleftarrow}", "\\textleftarrow", "" }, /* Left arrow ← */ - { 12296, "{\\textlangle}", "\\textlangle", "" } , /* L-angle 〈 */ - { 12297, "{\\textrangle}", "\\textrangle", "" } , /* L-angle 〉 */ + { 8593, LATEX_MACRO, "textuparrow", { "{\\textuparrow}", "\\textuparrow", NULL } }, /* Up arrow ↑ */ + { 8595, LATEX_MACRO, "textdownarrow", { "{\\textdownarrow}", "\\textdownarrow", NULL } }, /* Down arrow ↓ */ + { 8594, LATEX_MACRO, "textrightarrow", { "{\\textrightarrow}", "\\textrightarrow", NULL } }, /* Right arrow → */ + { 8592, LATEX_MACRO, "textleftarrow", { "{\\textleftarrow}", "\\textleftarrow", NULL } }, /* Left arrow ← */ + { 12296,LATEX_MACRO, "textlangle", { "{\\textlangle}", "\\textlangle", NULL } }, /* L-angle 〈 */ + { 12297,LATEX_MACRO, "textrangle", { "{\\textrangle}", "\\textrangle", NULL } }, /* L-angle 〉 */ - { 166, "{\\textbrokenbar}", "\\textbrokenbar", "" }, /* Broken vertical bar ¦ */ - { 167, "{\\textsection}", "\\textsection", "\\S{}" }, /* Section sign, § */ - { 170, "{\\textordfeminine}", "\\textordfeminine", "$^a$" }, /* ª */ - { 172, "{\\textlnot}", "\\textlnot", "" }, /* Lnot ¬ */ - { 182, "{\\textparagraph}", "\\textparagraph", "" }, /* Paragraph sign ¶ */ - { 183, "{\\textperiodcentered}", "\\textperiodcentered", "" }, /* Period-centered · */ - { 186, "{\\textordmasculine}", "\\textordmasculine", "" }, /* º */ - { 8214, "{\\textbardbl}", "\\textbardbl", "" }, /* Double vertical bar ‖ */ - { 8224, "{\\textdagger}", "\\textdagger", "" }, /* Dagger † */ - { 8225, "{\\textdaggerdbl}", "\\textdaggerdbl", "" },/* Double dagger &x2021; */ - { 8226, "{\\textbullet}", "\\textbullet", "" }, /* Bullet • */ - { 8494, "{\\textestimated}", "\\textestimated", "" },/* Estimated ℮ */ - { 9526, "{\\textopenbullet}", "\\textopenbullet", "" },/* ┶ */ + { 166, LATEX_MACRO, "textbrokenbar", { "{\\textbrokenbar}", "\\textbrokenbar", NULL } }, /* Broken vertical bar ¦ */ + { 167, LATEX_MACRO, "textsection", { "{\\textsection}", "\\textsection", "\\S{}" } }, /* Section sign, § */ + { 170, LATEX_MACRO, "textordfeminine", { "{\\textordfeminine}", "\\textordfeminine", "$^a$" } }, /* ª */ + { 172, LATEX_MACRO, "textlnot", { "{\\textlnot}", "\\textlnot", NULL } }, /* Lnot ¬ */ + { 182, LATEX_MACRO, "textparagraph", { "{\\textparagraph}", "\\textparagraph", NULL } }, /* Paragraph sign ¶ */ + { 183, LATEX_MACRO, "textperiodcentered",{ "{\\textperiodcentered}","\\textperiodcentered", NULL } }, /* Period-centered · */ + { 186, LATEX_MACRO, "textordmasculine", { "{\\textordmasculine}", "\\textordmasculine", NULL } }, /* º */ + { 8214, LATEX_MACRO, "textbardbl", { "{\\textbardbl}", "\\textbardbl", NULL } }, /* Double vertical bar ‖ */ + { 8224, LATEX_MACRO, "textdagger", { "{\\textdagger}", "\\textdagger", NULL } }, /* Dagger † */ + { 8225, LATEX_MACRO, "textdaggerdbl", { "{\\textdaggerdbl}", "\\textdaggerdbl", NULL } }, /* Double dagger &x2021; */ + { 8226, LATEX_MACRO, "textbullet", { "{\\textbullet}", "\\textbullet", NULL } }, /* Bullet • */ + { 8494, LATEX_MACRO, "textestimated", { "{\\textestimated}", "\\textestimated", NULL } }, /* Estimated ℮ */ + { 9526, LATEX_MACRO, "textopenbullet", { "{\\textopenbullet}", "\\textopenbullet", NULL } }, /* ┶ */ - { 8220, "``", "{\\textquotedblleft}", "\\textquotedblleft" }, /* Opening double quote “ */ - { 8221, "''", "{\\textquotedblright}","\\textquotedblright" }, /* Closing double quote ” */ - { 8216, "`", "{\\textquoteleft}", "\\textquoteleft" }, /* Opening single quote ‘ */ - { 8217, "'", "{\\textquoteright}", "\\textquoteright" }, /* Closing single quote ’ */ - { 8261, "{\\textlquill}", "\\textlquill", "" }, /* Left quill ⁅ */ - { 8262, "{\\textrquill}", "\\textrquill", "" }, /* Right quill ⁆ */ + { 8220, LATEX_COMBO, "``", { "``", "{\\textquotedblleft}", "\\textquotedblleft" } }, /* Opening double quote “ */ + { 8221, LATEX_COMBO, "''", { "''", "{\\textquotedblright}", "\\textquotedblright" } }, /* Closing double quote ” */ + { 8216, LATEX_COMBO, "`", { "`", "{\\textquoteleft}", "\\textquoteleft" } }, /* Opening single quote ‘ */ + { 8217, LATEX_COMBO, "'", { "'", "{\\textquoteright}", "\\textquoteright" } }, /* Closing single quote ’ */ + { 8261, LATEX_MACRO, "textlquill", { "{\\textlquill}", "\\textlquill", NULL } }, /* Left quill ⁅ */ + { 8262, LATEX_MACRO, "textrquill", { "{\\textrquill}", "\\textrquill", NULL } }, /* Right quill ⁆ */ - { 8212, "---", "{\\textemdash}", "\\textemdash" }, /* Em-dash — */ - { 8211, "--", "{\\textendash}", "\\textendash" }, /* En-dash – */ - { 8230, "\\ldots", "{\\textellipsis}", "\\textellipsis" }, /* Ellipsis … */ + { 8212, LATEX_COMBO, "---", { "---", "{\\textemdash}", "\\textemdash" } }, /* Em-dash — */ + { 8211, LATEX_COMBO, "--", { "--", "{\\textendash}", "\\textendash" } }, /* En-dash – */ + { 8230, LATEX_MACRO, "ldots", { "{\\ldots}", "{\\textellipsis}", "\\textellipsis" } }, /* Ellipsis … */ - { 8194, "\\enspace", "\\hspace{.5em}", "" }, /* En-space   */ - { 8195, "\\emspace", "\\hspace{1em}", "" }, /* Em-space   */ - { 8201, "\\thinspace", "", ""}, /* Thin space   */ - { 8203, "{\\textnospace}", "\\textnospace", "" }, /* No space ​ */ - { 9251, "{\\textvisiblespace}", "\\textvisiblespace", "" }, /* Visible space ␣ */ + { 8194, LATEX_MACRO, "enspace", { "{\\enspace}", "\\hspace{.5em}", NULL } }, /* En-space   */ + { 8195, LATEX_MACRO, "emspace", { "{\\emspace}", "\\hspace{1em}", NULL } }, /* Em-space   */ + { 8201, LATEX_MACRO, "thinspace", { "{\\thinspace}", NULL, NULL } }, /* Thin space   */ + { 8203, LATEX_MACRO, "textnospace", { "{\\textnospace}", "\\textnospace", NULL } }, /* No space ​ */ + { 9251, LATEX_MACRO, "textvisiblespace", { "{\\textvisiblespace}", "\\textvisiblespace", NULL } }, /* Visible space ␣ */ - { 215, "{\\texttimes}", "\\texttimes", "" }, /* Multiplication symbol × */ - { 247, "{\\textdiv}", "\\textdiv", "" }, /* Division symbol ÷ */ - { 177, "{\\textpm}", "\\textpm", "" }, /* Plus-minus character &#B1; */ - { 189, "{\\textonehalf}", "\\textonehalf", "" }, /* Vulgar fraction one half ½ */ - { 188, "{\\textonequarter}", "\\textonequarter", "" }, /* Vulgar fraction one quarter ½ */ - { 190, "{\\textthreequarters}", "\\textthreequarters", "" }, /* Vulgar fraction three quarters ¾ */ - { 8240, "{\\texttenthousand}", "\\texttenthousand", "" }, /* Per thousand sign ‰ */ - { 8241, "{\\textpertenthousand}", "\\textpertenthousand", "" }, /* Per ten thousand sign ‱*/ - { 8260, "{\\textfractionsolidus}", "\\textfractionsolidus", "" }, /* &x8260; */ - { 8451, "{\\textcelcius}", "\\textcelcius", "" }, /* Celcicus ℃ */ - { 8470, "{\\textnumero}", "\\textnumero", "" }, /* Numero symbol № */ - { 8486, "{\\textohm}", "\\textohm", "" }, /* Ohm symbol Ω */ - { 8487, "{\\textmho}", "\\textmho", "" }, /* Mho symbol ℧ */ - { 8730, "{\\textsurd}", "\\textsurd", "" }, /* √ */ + { 215, LATEX_MACRO, "texttimes", { "{\\texttimes}", "\\texttimes", NULL } }, /* Multiplication symbol × */ + { 247, LATEX_MACRO, "textdiv", { "{\\textdiv}", "\\textdiv", NULL } }, /* Division symbol ÷ */ + { 177, LATEX_MACRO, "textpm", { "{\\textpm}", "\\textpm", NULL } }, /* Plus-minus character &#B1; */ + { 189, LATEX_MACRO, "textonehalf", { "{\\textonehalf}", "\\textonehalf", NULL } }, /* Vulgar fraction one half ½ */ + { 188, LATEX_MACRO, "textonequarter", { "{\\textonequarter}", "\\textonequarter", NULL } }, /* Vulgar fraction one quarter ½ */ + { 190, LATEX_MACRO, "textthreequarters", { "{\\textthreequarters}", "\\textthreequarters", NULL } }, /* Vulgar fraction three quarters ¾ */ + { 8240, LATEX_MACRO, "texttenthousand", { "{\\texttenthousand}", "\\texttenthousand", NULL } }, /* Per thousand sign ‰ */ + { 8241, LATEX_MACRO, "textpertenthousand",{ "{\\textpertenthousand}","\\textpertenthousand", NULL } }, /* Per ten thousand sign ‱*/ + { 8260, LATEX_MACRO, "textfractionssolidus",{"{\\textfractionsolidus}", "\\textfractionsolidus", NULL } }, /* &x8260; */ + { 8451, LATEX_MACRO, "textcelcius", { "{\\textcelcius}", "\\textcelcius", NULL } }, /* Celcicus ℃ */ + { 8470, LATEX_MACRO, "textnumero", { "{\\textnumero}", "\\textnumero", NULL } }, /* Numero symbol № */ + { 8486, LATEX_MACRO, "textohm", { "{\\textohm}", "\\textohm", NULL } }, /* Ohm symbol Ω */ + { 8487, LATEX_MACRO, "textmho", { "{\\textmho}", "\\textmho", NULL } }, /* Mho symbol ℧ */ + { 8730, LATEX_MACRO, "textsurd", { "{\\textsurd}", "\\textsurd", NULL } }, /* √ */ - { 185, "{\\textonesuperior}", "\\textonesuperior", "" }, /*Superscript 1 ¹ */ - { 178, "{\\texttwosuperior}", "\\texttwosuperior", "" }, /*Superscript 2 ² */ - { 179, "{\\textthreesuperior}", "\\textthreesuperior", "" }, /*Superscript 3 ³ */ + { 185, LATEX_MACRO, "textonesuperior", { "{\\textonesuperior}", "\\textonesuperior", "$^1$" } }, /*Superscript 1 ¹ */ + { 178, LATEX_MACRO, "texttwosuperior", { "{\\texttwosuperior}", "\\texttwosuperior", "$^2$" } }, /*Superscript 2 ² */ + { 179, LATEX_MACRO, "textthreesuperior", { "{\\textthreesuperior}", "\\textthreesuperior", "$^3$" } }, /*Superscript 3 ³ */ - { 161, "{\\textexclamdown}", "\\textexclamdown", "" }, /* Inverted exclamation mark ¡*/ - { 191, "{\\textquestiondown}", "\\textquestiondown", "" }, /* Inverted question mark ¿ */ + { 161, LATEX_MACRO, "textexclamdown", { "{\\textexclamdown}", "\\textexclamdown", NULL } }, /* Inverted exclamation mark ¡*/ + { 191, LATEX_MACRO, "textquestiondown", { "{\\textquestiondown}", "\\textquestiondown", NULL } }, /* Inverted question mark ¿ */ - { 162, "{\\textcent}", "\\textcent", "" }, /* Cent sign ¢ */ - { 163, "{\\textsterling}", "\\textsterling", "\\pounds" }, /* Pound sign £ */ - { 165, "{\\textyen}", "\\textyen", "" }, /* Yen sign ¥ */ - { 402, "{\\textflorin}", "\\textflorin", "" }, /* Florin sign ƒ */ - { 3647, "{\\textbaht}", "\\textbaht", "" }, /* Thai currency ฿ */ - { 8355, "{\\textfrenchfranc}", "\\textfrenchfranc", "" }, /* French franc ₣ */ - { 8356, "{\\textlira}", "\\textlira", "" }, /* Lira ₤ */ - { 8358, "{\\textnaira}", "\\textnaria", "" }, /* Naira ₦ */ - { 8361, "{\\textwon}", "\\textwon", "" }, /* ₩ */ - { 8363, "{\\textdong}", "\\textdong", "" }, /* Vietnamese currency ₫ */ - { 8364, "{\\texteuro}", "\\texteuro", "" }, /* Euro sign */ + { 162, LATEX_MACRO, "textcent", { "{\\textcent}", "\\textcent", NULL } }, /* Cent sign ¢ */ + { 163, LATEX_MACRO, "textsterling", { "{\\textsterling}", "\\textsterling", "\\pounds" } }, /* Pound sign £ */ + { 165, LATEX_MACRO, "textyen", { "{\\textyen}", "\\textyen", NULL } }, /* Yen sign ¥ */ + { 402, LATEX_MACRO, "textflorin", { "{\\textflorin}", "\\textflorin", NULL } }, /* Florin sign ƒ */ + { 3647, LATEX_MACRO, "textbaht", { "{\\textbaht}", "\\textbaht", NULL } }, /* Thai currency ฿ */ + { 8355, LATEX_MACRO, "textfrenchfranc", { "{\\textfrenchfranc}", "\\textfrenchfranc", NULL } }, /* French franc ₣ */ + { 8356, LATEX_MACRO, "textlira", { "{\\textlira}", "\\textlira", NULL } }, /* Lira ₤ */ + { 8358, LATEX_MACRO, "textnaira", { "{\\textnaira}", "\\textnaria", NULL } }, /* Naira ₦ */ + { 8361, LATEX_MACRO, "textwon", { "{\\textwon}", "\\textwon", NULL } }, /* ₩ */ + { 8363, LATEX_MACRO, "textdong", { "{\\textdong}", "\\textdong", NULL } }, /* Vietnamese currency ₫ */ + { 8364, LATEX_MACRO, "texteuro", { "{\\texteuro}", "\\texteuro", NULL } }, /* Euro sign */ - { 169, "{\\textcopyright}", "\\textcopyright", "" }, /* Copyright (C) © */ - { 175, "{\\textregistered}", "\\textregistered", "" }, /* Registered sign (R) ¯*/ - { 8482, "{\\texttrademark}", "\\texttrademark", "$^{TM}$" }, /* Trademark (TM) ™ */ - { 8480, "{\\textservicemark}", "\\textservicemark", "$^{SM}$" }, /* Servicemark (SM) ℠*/ - { 8471, "{\\textcircledP}", "\\textcircledP", "" }, /* Circled P ࡅ */ + { 169, LATEX_MACRO, "textcopyright", { "{\\textcopyright}", "\\textcopyright", NULL } }, /* Copyright (C) © */ + { 175, LATEX_MACRO, "textregistered", { "{\\textregistered}", "\\textregistered", NULL } }, /* Registered sign (R) ¯*/ + { 8482, LATEX_MACRO, "texttrademark", { "{\\texttrademark}", "\\texttrademark", "$^{TM}$" } }, /* Trademark (TM) ™ */ + { 8480, LATEX_MACRO, "textservicemark", { "{\\textservicemark}", "\\textservicemark", "$^{SM}$" } }, /* Servicemark (SM) ℠*/ + { 8471, LATEX_MACRO, "textcircledP", { "{\\textcircledP}", "\\textcircledP", NULL } }, /* Circled P ࡅ */ }; @@ -505,31 +509,35 @@ latex2char( char *s, unsigned int *pos, int *unicode ) { unsigned int value; - char *p, *q[3]; - int i, j, l[3]; +// char *p, *q[3]; + int i, j, len; + char *p; + p = &( s[*pos] ); value = (unsigned char) *p; if ( value=='{' || value=='\\' || value=='~' || value=='$' || value=='\'' || value=='`' || value=='-' || value=='^' ) { - if ( *p=='\\' && ( *p=='{' || *p=='}' ) ) { - } else { +// if ( *p=='\\' && ( *p=='{' || *p=='}' ) ) { +// } else { for ( i=0; istr = NULL; - a->max = 0; - a->n = 0; - a->sorted = 1; -} - -void -list_empty( list *a ) -{ - int i; - for ( i=0; imax; ++i ) - newstr_empty( &(a->str[i]) ); - a->n = 0; - a->sorted = 1; -} - -void -list_free( list *a ) -{ - int i; - for ( i=0; imax; ++i ) - newstr_free( &(a->str[i]) ); - free( a->str ); - list_init( a ); -} - -list * -list_new( void ) -{ - list *a = ( list * ) malloc( sizeof ( list ) ); - if ( a ) list_init( a ); - return a; -} - -void -list_delete( list *a ) -{ - list_free( a ); - free( a ); -} - -/* - * returns 1 if n is valid string in list - */ -static inline int -list_valid_num( list *a, int n ) -{ - if ( n < 0 || n >= a->n ) return 0; - return 1; -} - -static int -list_comp( const void *v1, const void *v2 ) -{ - newstr *s1 = ( newstr *) v1; - newstr *s2 = ( newstr *) v2; - if ( !s1->len && !s2->len ) return 0; - else if ( !s1->len ) return -1; - else if ( !s2->len ) return 1; - else return strcmp( s1->data, s2->data ); -} - -static int -list_comp_step( list *a, int n1, int n2 ) -{ - return list_comp( (const void*) &(a->str[n1]), (const void*) &(a->str[n2]) ); -} - -static newstr * -list_set_cleanup( list *a, int n ) -{ - if ( newstr_memerr( &(a->str[n]) ) ) return NULL; - if ( a->sorted ) { - if ( n>0 && list_comp_step( a, n-1, n )>0 ) - a->sorted = 0; - } - if ( a->sorted ) { - if ( nn-1 && list_comp_step( a, n, n+1 )>0 ) - a->sorted = 0; - } - return &(a->str[n]); -} - -newstr * -list_set( list *a, int n, newstr *s ) -{ - if ( !list_valid_num( a, n ) ) return NULL; - newstr_newstrcpy( &(a->str[n]), s ); - return list_set_cleanup( a, n ); -} - -newstr * -list_setc( list *a, int n, const char *s ) -{ - if ( !list_valid_num( a, n ) ) return NULL; - newstr_strcpy( &(a->str[n]), s ); - return list_set_cleanup( a, n ); -} - -/* - * return pointer to newstr 'n' - */ -newstr * -list_get( list *a, int n ) -{ - if ( !list_valid_num( a, n ) ) return NULL; - else return &(a->str[n]); -} - -/* - * return pointer to C string 'n' - * - * So long as the index is a valid number ensure - * that a pointer is returned even if the newstr doesn't - * point to data. Only return NULL if the index - * is invalid. Thus we can convert loops like: - * - * for ( i=0; in; ++i ) { - * p = list_getc( a, i ); - * if ( p==NULL ) continue; // empty string - * ... - * } - * - * to - * - * i = 0; - * while ( ( p = list_getc( a, i ) ) ) { - * ... - * i++; - * } - * - */ -char * -list_getc( list *a, int n ) -{ - static char empty[] = ""; - char *p; - if ( !list_valid_num( a, n ) ) return NULL; - p = a->str[n].data; - if ( p ) return p; - else return empty; -} - -static int -list_alloc( list *a ) -{ - int i, alloc = 20; - a->str = ( newstr* ) malloc( sizeof( newstr ) * alloc ); - if ( !(a->str) ) return LIST_ERR; - a->max = alloc; - a->n = 0; - for ( i=0; istr[i]) ); - return LIST_OK; -} - -static int -list_realloc( list *a ) -{ - newstr *more; - int i, alloc = a->max * 2; - more = ( newstr* ) realloc( a->str, sizeof( newstr ) * alloc ); - if ( !more ) return LIST_ERR; - a->str = more; - for ( i=a->max; istr[i]) ); - a->max = alloc; - return LIST_OK; -} - - -static int -list_ensure_space( list *a ) -{ - int status = LIST_OK; - if ( a->max==0 ) - status = list_alloc( a ); - else if ( a->n >= a->max ) - status = list_realloc( a ); - return status; -} - -newstr * -list_addvp( list *a, unsigned char mode, void *vp ) -{ - newstr *s = NULL; - int status; - status = list_ensure_space( a ); - if ( status==LIST_OK ) { - s = &( a->str[a->n] ); - if ( mode==LIST_CHR ) - newstr_strcpy( s, (const char*) vp ); - else if ( mode==LIST_STR ) - newstr_newstrcpy( s, (newstr*) vp ); - else - return NULL; - if ( newstr_memerr( s ) ) return NULL; - a->n++; - if ( a->sorted && a->n > 1 ) { - if ( list_comp_step( a, a->n-2, a->n-1 ) > 0 ) - a->sorted = 0; - } - } - return s; -} -newstr * -list_addc( list *a, const char *s ) -{ - return list_addvp( a, LIST_CHR, (void*)s ); -} -newstr * -list_add( list *a, newstr *s ) -{ - return list_addvp( a, LIST_STR, (void*)s ); -} - -newstr * -list_addvp_unique( list *a, unsigned char mode, void *vp ) -{ - newstr *s; - int n; - if ( mode==LIST_CHR ) - n = list_find( a, (const char*) vp ); - else if ( mode==LIST_STR ) - n = list_find( a, ( (newstr*) vp )->data ); - else - return NULL; - if ( n!=-1 ) - s = &( a->str[n] ); - else { - s = list_addvp( a, mode, vp ); - } - return s; -} -newstr * -list_addc_unique( list *a, const char *s ) -{ - return list_addvp_unique( a, LIST_CHR, (void*)s ); -} -newstr * -list_add_unique( list *a, newstr *s ) -{ - return list_addvp_unique( a, LIST_STR, (void*)s ); -} - -int -list_addvp_all( list *a, unsigned char mode, ... ) -{ - int ret = LIST_OK; - va_list ap; - newstr *s; - void *v; - va_start( ap, mode ); - do { - if ( mode==LIST_CHR ) v = va_arg( ap, char * ); - else v = va_arg( ap, newstr * ); - if ( v ) { - s = list_addvp( a, mode, v ); - if ( s==NULL ) { ret = LIST_ERR; goto out; } - } - } while ( v ); -out: - va_end( ap ); - return ret; -} - -int -list_add_all( list *a, ... ) -{ - int ret = LIST_OK; - va_list ap; - newstr *s, *v; - va_start( ap, a ); - do { - v = va_arg( ap, newstr * ); - if ( v ) { - s = list_addvp( a, LIST_STR, (void*)v ); - if ( s==NULL ) { ret = LIST_ERR; goto out; } - } - } while ( v ); -out: - va_end( ap ); - return ret; -} - -int -list_addc_all( list *a, ... ) -{ - int ret = LIST_OK; - va_list ap; - newstr *s; - const char *v; - va_start( ap, a ); - do { - v = va_arg( ap, const char * ); - if ( v ) { - s = list_addvp( a, LIST_CHR, (void*)v ); - if ( s==NULL ) { ret = LIST_ERR; goto out; } - } - } while ( v ); -out: - va_end( ap ); - return ret; -} - -int -list_append( list *a, list *toadd ) -{ - newstr *s; - int i; - for ( i=0; in; ++i ) { - s = list_add( a, &(toadd->str[i]) ); - if ( !s ) return LIST_ERR; - } - return LIST_OK; -} - -int -list_append_unique( list *a, list *toadd ) -{ - newstr *s; - int i; - for ( i=0; in; ++i ) { - s = list_add_unique( a, &(toadd->str[i]) ); - if ( !s ) return LIST_ERR; - } - return LIST_OK; -} - -int -list_remove( list *a, int n ) -{ - int i; - if ( !list_valid_num( a, n ) ) return -1; - for ( i=n+1; in; ++i ) { - newstr_newstrcpy( &(a->str[i-1]), &(a->str[i]) ); - if ( newstr_memerr( &(a->str[i-1]) ) ) return LIST_ERR; - } - a->n--; - return LIST_OK; -} - -void -list_swap( list *a, int n1, int n2 ) -{ - newstr_swapstrings( &(a->str[n1]), &(a->str[n2]) ); -} - -void -list_sort( list *a ) -{ - qsort( a->str, a->n, sizeof( newstr ), list_comp ); - a->sorted = 1; -} - -static int -list_find_sorted( list *a, const char *searchstr ) -{ - int min, max, mid, comp; - newstr s, *cs; - newstr_init( &s ); - newstr_strcpy( &s, searchstr ); - min = 0; - max = a->n - 1; - while ( min <= max ) { - mid = ( min + max ) / 2; - cs = list_get( a, mid ); - comp = list_comp( (void*)cs, (void*) (&s) ); - if ( comp==0 ) { - newstr_free( &s ); - return mid; - } - else if ( comp > 0 ) max = mid - 1; - else if ( comp < 0 ) min = mid + 1; - } - newstr_free( &s ); - return -1; -} - -static int -list_find_simple( list *a, const char *searchstr, int nocase ) -{ - int i; - if ( nocase ) { - for ( i=0; in; ++i ) - if ( !strcasecmp(a->str[i].data,searchstr) ) - return i; - } else { - for ( i=0; in; ++i ) - if ( !strcmp(a->str[i].data,searchstr) ) - return i; - } - return -1; -} - -int -list_find( list *a, const char *searchstr ) -{ - if ( a->n==0 ) return -1; - if ( a->sorted ) - return list_find_sorted( a, searchstr ); - else - return list_find_simple( a, searchstr, 0 ); -} - -int -list_findnocase( list *a, const char *searchstr ) -{ - return list_find_simple( a, searchstr, 1 ); -} - -int -list_fillfp( list *a, FILE *fp, unsigned char skip_blank_lines ) -{ - int bufpos = 0, ret = LIST_OK; - char buf[512]=""; - newstr line; - - list_empty( a ); - newstr_init( &line ); - while ( newstr_fget( fp, buf, sizeof(buf), &bufpos, &line ) ) { - if ( skip_blank_lines && line.len==0 ) continue; - if ( !list_add( a, &line ) ) { ret = LIST_ERR; goto out; } - } -out: - newstr_free( &line ); - return ret; -} - -int -list_fill( list *a, const char *filename, unsigned char skip_blank_lines ) -{ - FILE *fp; - int ret; - - fp = fopen( filename, "r" ); - if ( !fp ) return LIST_ERR_CANNOTOPEN; - - ret = list_fillfp( a, fp, skip_blank_lines ); - - fclose( fp ); - - return ret; -} - -int -list_copy( list *to, list *from ) -{ - int i; - - list_free( to ); - - if ( from->n==0 ) return LIST_OK; - - to->str = ( newstr * ) malloc( sizeof( newstr ) * from->n ); - if ( !to->str ) { - to->n = to->max = 0; - return LIST_ERR; - } - - to->max = from->n; - to->sorted = from->sorted; - - for ( i=0; in; i++ ) - newstr_init( &(to->str[i]) ); - - for ( i=0; in; i++ ) { - newstr_newstrcpy( &(to->str[i]), &(from->str[i]) ); - if ( newstr_memerr( &(to->str[i]) ) ) return LIST_ERR; - to->n += 1; - } - return LIST_OK; -} - -list * -list_dup( list *from ) -{ - list *to; - int ok; - - to = list_new(); - if ( to ) { - ok = list_copy( to, from ); - if ( !ok ) { - list_delete( to ); - to = NULL; - } - } - - return to; -} - -int -list_match_entry( list *a, int n, char *s ) -{ - if ( n < 0 || n >= a->n ) return 0; - if ( strcmp( a->str[n].data, s ) ) return 0; - return 1; -} - -void -list_trimend( list *a, int n ) -{ - int i; - if ( a->n - n < 1 ) { - list_empty( a ); - } else { - for ( i=a->n -n; in; ++i ) { - newstr_empty( &(a->str[i]) ); - } - a->n -= n; - } -} - -int -list_tokenizec( list *tokens, char *p, const char *delim, int merge_delim ) -{ - int ret = LIST_OK; - newstr s, *t; - char *q; - list_empty( tokens ); - newstr_init( &s ); - while ( p && *p ) { - q = p; - while ( *q && !strchr( delim, *q ) ) q++; - newstr_segcpy( &s, p, q ); - if ( newstr_memerr( &s ) ) { ret = LIST_ERR; goto out; } - if ( s.len ) { - t = list_addvp( tokens, LIST_STR, (void*) &s ); - if ( !t ) { ret = LIST_ERR; goto out; } - } else if ( !merge_delim ) { - t = list_addvp( tokens, LIST_CHR, (void*) "" ); - if ( !t ) { ret = LIST_ERR; goto out; } - } - p = q; - if ( *p ) p++; - } -out: - newstr_free( &s ); - return ret; -} - -int -list_tokenize( list *tokens, newstr *in, const char *delim, int merge_delim ) -{ - return list_tokenizec( tokens, in->data, delim, merge_delim ); -} - -void -lists_init( list *a, ... ) -{ - list *a2; - va_list ap; - list_init( a ); - va_start( ap, a ); - do { - a2 = va_arg( ap, list * ); - if ( a2 ) list_init( a2 ); - } while ( a2 ); - va_end( ap ); -} - -void -lists_free( list *a, ... ) -{ - list *a2; - va_list ap; - list_free( a ); - va_start( ap, a ); - do { - a2 = va_arg( ap, list * ); - if ( a2 ) list_free( a2 ); - } while ( a2 ); - va_end( ap ); -} - -void -lists_empty( list *a, ... ) -{ - list *a2; - va_list ap; - list_empty( a ); - va_start( ap, a ); - do { - a2 = va_arg( ap, list * ); - if ( a2 ) list_empty( a2 ); - } while ( a2 ); - va_end( ap ); -} - diff --git a/bibutils/list.h b/bibutils/list.h deleted file mode 100644 --- a/bibutils/list.h +++ /dev/null @@ -1,87 +0,0 @@ -/* - * list.h - * - * version: 2014-11-15 - * - * Copyright (c) Chris Putnam 2004-2014 - * - * Source code released under the GPL version 2 - * - */ - -#ifndef LISTS_H -#define LISTS_H - -#include -#include -#include -#include -#include "newstr.h" - -#define LIST_ERR (0) -#define LIST_ERR_CANNOTOPEN (-1) -#define LIST_OK (1) - -#define LIST_CHR (0) -#define LIST_STR (1) - -typedef struct list { - int n, max; - newstr *str; - unsigned char sorted; -} list; - - -extern void lists_init( list *a, ... ); -extern void lists_free( list *a, ... ); -extern void lists_empty( list *a, ... ); - - -extern void list_init( list *a ); -extern void list_free( list *a ); -extern void list_empty( list *a ); - -extern list * list_new( void ); -extern void list_delete( list * ); - -extern list* list_dup( list *a ); -extern int list_copy( list *to, list *from ); - -extern newstr * list_addvp( list *a, unsigned char mode, void *vp ); -extern newstr * list_addc( list *a, const char *value ); -extern newstr * list_add( list *a, newstr *value ); - -extern int list_addvp_all( list *a, unsigned char mode, ... ); -extern int list_addc_all( list *a, ... ); -extern int list_add_all( list *a, ... ); - -extern newstr * list_addvp_unique( list *a, unsigned char mode, void *vp ); -extern newstr * list_addc_unique( list *a, const char *value ); -extern newstr * list_add_unique( list *a, newstr *value ); - -extern int list_append( list *a, list *toadd ); -extern int list_append_unique( list *a, list *toadd ); - -extern int list_remove( list *a, int n ); - -extern newstr* list_get( list *a, int n ); -extern char* list_getc( list *a, int n ); - -extern newstr* list_set( list *a, int n, newstr *s ); -extern newstr* list_setc( list *a, int n, const char *s ); - -extern void list_sort( list *a ); - -extern void list_swap( list *a, int n1, int n2 ); - -extern int list_find( list *a, const char *searchstr ); -extern int list_findnocase( list *a, const char *searchstr ); -extern int list_match_entry( list *a, int n, char *s ); -extern void list_trimend( list *a, int n ); - -extern int list_fill( list *a, const char *filename, unsigned char skip_blank_lines ); -extern int list_fillfp( list *a, FILE *fp, unsigned char skip_blank_lines ); -extern int list_tokenize( list *tokens, newstr *in, const char *delim, int merge_delim ); -extern int list_tokenizec( list *tokens, char *p, const char *delim, int merge_delim ); - -#endif diff --git a/bibutils/marc.c b/bibutils/marc.c --- a/bibutils/marc.c +++ b/bibutils/marc.c @@ -1,7 +1,7 @@ /* * marc.c * - * Copyright (c) Chris Putnam 2004-2014 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/marc.h b/bibutils/marc.h --- a/bibutils/marc.h +++ b/bibutils/marc.h @@ -1,7 +1,7 @@ /* * marc.h * - * Copyright (c) Chris Putnam 2008-2013 + * Copyright (c) Chris Putnam 2008-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/medin.c b/bibutils/medin.c --- a/bibutils/medin.c +++ b/bibutils/medin.c @@ -1,7 +1,7 @@ /* * medin.c * - * Copyright (c) Chris Putnam 2004-2014 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * @@ -9,15 +9,19 @@ #include #include #include "is_ws.h" -#include "newstr.h" -#include "newstr_conv.h" +#include "str.h" +#include "str_conv.h" #include "fields.h" #include "xml.h" #include "xml_encoding.h" -#include "medin.h" #include "iso639_2.h" #include "bibutils.h" +#include "bibformats.h" +static int medin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int medin_processf( fields *medin, char *data, char *filename, long nref, param *p ); + + /***************************************************** PUBLIC: void medin_initparams() *****************************************************/ @@ -44,8 +48,8 @@ p->all = NULL; p->nall = 0; - list_init( &(p->asis) ); - list_init( &(p->corps) ); + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); if ( !progname ) p->progname = NULL; else p->progname = strdup( progname ); @@ -82,14 +86,14 @@ return endptr; } -int -medin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ) +static int +medin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) { - newstr tmp; + str tmp; char *startptr = NULL, *endptr; int haveref = 0, inref = 0, file_charset = CHARSET_UNKNOWN, m, type = -1; - newstr_init( &tmp ); - while ( !haveref && newstr_fget( fp, buf, bufsize, bufpos, line ) ) { + str_init( &tmp ); + while ( !haveref && str_fget( fp, buf, bufsize, bufpos, line ) ) { if ( line->data ) { m = xml_getencoding( line ); if ( m!=CHARSET_UNKNOWN ) file_charset = m; @@ -98,19 +102,19 @@ startptr = medin_findstartwrapper( line->data, &type ); } if ( startptr || inref ) { - if ( inref ) newstr_strcat( &tmp, line->data ); + if ( inref ) str_strcat( &tmp, line ); else { - newstr_strcat( &tmp, startptr ); + str_strcatc( &tmp, startptr ); inref = 1; } - endptr = medin_findendwrapper( tmp.data, type ); + endptr = medin_findendwrapper( str_cstr( &tmp ), type ); if ( endptr ) { - newstr_segcpy( reference, tmp.data, endptr ); + str_segcpy( reference, str_cstr( &tmp ), endptr ); haveref = 1; } } } - newstr_free( &tmp ); + str_free( &tmp ); *fcharset = file_charset; return haveref; } @@ -132,8 +136,8 @@ int i, fstatus; char *d; *found = 0; - if ( !xml_hasdata( node ) ) return BIBL_OK; - d = xml_data( node ); + if ( !xml_hasvalue( node ) ) return BIBL_OK; + d = xml_value( node ); for ( i=0; i 0 ) { - fstatus = fields_add( info, "PARTYEAR", tmp.data, level ); + p = str_cpytodelim( &tmp, skip_ws( p ), " \t\n\r", 0 ); + if ( str_memerr( &tmp ) ) return BIBL_ERR_MEMERR; + + if ( str_has_value( &tmp ) ) { + fstatus = fields_add( info, "PARTDATE:YEAR", str_cstr( &tmp ), level ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - p = newstr_cpytodelim( &tmp, skip_ws( p ), " \t\n\r", 0 ); - if ( newstr_memerr( &tmp ) ) return BIBL_ERR_MEMERR; - if ( tmp.len > 0 ) { - newstr_findreplace( &tmp, "-", "/" ); - fstatus = fields_add( info, "PARTMONTH", tmp.data, level ); + p = str_cpytodelim( &tmp, skip_ws( p ), " \t\n\r", 0 ); + if ( str_memerr( &tmp ) ) return BIBL_ERR_MEMERR; + + if ( str_has_value( &tmp ) ) { + str_findreplace( &tmp, "-", "/" ); + fstatus = fields_add( info, "PARTDATE:MONTH", str_cstr( &tmp ), level ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - p = newstr_cpytodelim( &tmp, skip_ws( p ), " \t\n\r", 0 ); - if ( newstr_memerr( &tmp ) ) return BIBL_ERR_MEMERR; - if ( tmp.len > 0 ) { - fstatus = fields_add( info, "PARTDAY", tmp.data, level ); + p = str_cpytodelim( &tmp, skip_ws( p ), " \t\n\r", 0 ); + if ( str_memerr( &tmp ) ) return BIBL_ERR_MEMERR; + + if ( str_has_value( &tmp ) ) { + fstatus = fields_add( info, "PARTDATE:DAY", str_cstr( &tmp ), level ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - newstr_free( &tmp ); + str_free( &tmp ); return BIBL_OK; } @@ -209,7 +216,7 @@ { char *code, *language; int fstatus; - code = xml_data( node ); + code = xml_value( node ); if ( !code ) return BIBL_OK; language = iso639_2_from_code( code ); if ( language ) @@ -252,22 +259,22 @@ medin_journal1( xml *node, fields *info ) { xml_convert c[] = { - { "Title", NULL, NULL, "TITLE", 1 }, - { "ISOAbbreviation", NULL, NULL, "SHORTTITLE", 1 }, - { "ISSN", NULL, NULL, "ISSN", 1 }, - { "Volume", NULL, NULL, "VOLUME", 1 }, - { "Issue", NULL, NULL, "ISSUE", 1 }, - { "Year", NULL, NULL, "PARTYEAR", 1 }, - { "Month", NULL, NULL, "PARTMONTH", 1 }, - { "Day", NULL, NULL, "PARTDAY", 1 }, + { "Title", NULL, NULL, "TITLE", 1 }, + { "ISOAbbreviation", NULL, NULL, "SHORTTITLE", 1 }, + { "ISSN", NULL, NULL, "ISSN", 1 }, + { "Volume", NULL, NULL, "VOLUME", 1 }, + { "Issue", NULL, NULL, "ISSUE", 1 }, + { "Year", NULL, NULL, "PARTDATE:YEAR", 1 }, + { "Month", NULL, NULL, "PARTDATE:MONTH", 1 }, + { "Day", NULL, NULL, "PARTDATE:DAY", 1 }, }; int nc = sizeof( c ) / sizeof( c[0] ), status, found; - if ( xml_hasdata( node ) ) { + if ( xml_hasvalue( node ) ) { status = medin_doconvert( node, info, c, nc, &found ); if ( status!=BIBL_OK ) return status; if ( !found ) { if ( xml_tagexact( node, "MedlineDate" ) ) { - status = medin_medlinedate( info, xml_data( node ), 1 ); + status = medin_medlinedate( info, xml_value( node ), 1 ); if ( status!=BIBL_OK ) return status; } if ( xml_tagexact( node, "Language" ) ) { @@ -295,28 +302,28 @@ medin_pagination( xml *node, fields *info ) { int i, fstatus, status; - newstr sp, ep; + str sp, ep; char *p, *pp; if ( xml_tagexact( node, "MedlinePgn" ) && node->value ) { - newstrs_init( &sp, &ep, NULL ); - p = newstr_cpytodelim( &sp, xml_data( node ), "-", 1 ); - if ( newstr_memerr( &sp ) ) return BIBL_ERR_MEMERR; - if ( sp.len ) { - fstatus = fields_add( info, "PAGESTART", sp.data, 1 ); + strs_init( &sp, &ep, NULL ); + p = str_cpytodelim( &sp, xml_value( node ), "-", 1 ); + if ( str_memerr( &sp ) ) return BIBL_ERR_MEMERR; + if ( str_has_value( &sp ) ) { + fstatus = fields_add( info, "PAGES:START", str_cstr( &sp ), 1 ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - p = newstr_cpytodelim( &ep, p, "", 0 ); - if ( newstr_memerr( &ep ) ) return BIBL_ERR_MEMERR; - if ( ep.len ) { + p = str_cpytodelim( &ep, p, "", 0 ); + if ( str_memerr( &ep ) ) return BIBL_ERR_MEMERR; + if ( str_has_value( &ep ) ) { if ( sp.len > ep.len ) { for ( i=sp.len-ep.len; idown ) { status = medin_pagination( node->down, info ); @@ -337,8 +344,8 @@ medin_abstract( xml *node, fields *info ) { int fstatus; - if ( xml_tagwithdata( node, "AbstractText" ) ) { - fstatus = fields_add( info, "ABSTRACT", xml_data( node ), 0 ); + if ( xml_tagwithvalue( node, "AbstractText" ) ) { + fstatus = fields_add( info, "ABSTRACT", xml_value( node ), 0 ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } else if ( node->next ) return medin_abstract( node->next, info ); return BIBL_OK; @@ -357,28 +364,28 @@ * */ static int -medin_author( xml *node, newstr *name ) +medin_author( xml *node, str *name ) { char *p; if ( xml_tagexact( node, "LastName" ) ) { - if ( name->len ) { - newstr_prepend( name, "|" ); - newstr_prepend( name, xml_data( node ) ); + if ( str_has_value( name ) ) { + str_prepend( name, "|" ); + str_prepend( name, xml_value( node ) ); } - else newstr_strcat( name, xml_data( node ) ); + else str_strcatc( name, xml_value( node ) ); } else if ( xml_tagexact( node, "ForeName" ) || xml_tagexact( node, "FirstName" ) ) { - p = xml_data( node ); + p = xml_value( node ); while ( p && *p ) { - if ( name->len ) newstr_addchar( name, '|' ); + if ( str_has_value( name ) ) str_addchar( name, '|' ); while ( *p && *p==' ' ) p++; - while ( *p && *p!=' ' ) newstr_addchar( name, *p++ ); + while ( *p && *p!=' ' ) str_addchar( name, *p++ ); } } else if ( xml_tagexact( node, "Initials" ) && !strchr( name->data, '|' )) { - p = xml_data( node ); + p = xml_value( node ); while ( p && *p ) { - if ( name->len ) newstr_addchar( name, '|' ); - if ( !is_ws(*p) ) newstr_addchar( name, *p++ ); + if ( str_has_value( name ) ) str_addchar( name, '|' ); + if ( !is_ws(*p) ) str_addchar( name, *p++ ); } } if ( node->next ) medin_author( node->next, name ); @@ -386,10 +393,10 @@ } static int -medin_corpauthor( xml *node, newstr *name ) +medin_corpauthor( xml *node, str *name ) { if ( xml_tagexact( node, "CollectiveName" ) ) { - newstr_strcpy( name, xml_data( node ) ); + str_strcpyc( name, xml_value( node ) ); } else if ( node->next ) medin_corpauthor( node->next, name ); return BIBL_OK; } @@ -398,28 +405,28 @@ medin_authorlist( xml *node, fields *info ) { int fstatus, status; - newstr name; + str name; char *tag; - newstr_init( &name ); + str_init( &name ); node = node->down; while ( node ) { if ( xml_tagexact( node, "Author" ) && node->down ) { status = medin_author( node->down, &name ); tag = "AUTHOR"; - if ( !name.len ) { + if ( str_is_empty( &name ) ) { status = medin_corpauthor( node->down, &name ); tag = "AUTHOR:CORP"; } - if ( newstr_memerr( &name ) || status!=BIBL_OK ) return BIBL_ERR_MEMERR; - if ( name.len ) { + if ( str_memerr( &name ) || status!=BIBL_OK ) return BIBL_ERR_MEMERR; + if ( str_has_value( &name ) ) { fstatus = fields_add(info,tag,name.data,0); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - newstr_empty( &name ); + str_empty( &name ); } node = node->next; } - newstr_free( &name ); + str_free( &name ); return BIBL_OK; } @@ -439,8 +446,8 @@ medin_journal2( xml *node, fields *info ) { int fstatus, status = BIBL_OK; - if ( xml_tagwithdata( node, "MedlineTA" ) && fields_find( info, "TITLE", 1 )==-1 ) { - fstatus = fields_add( info, "TITLE", xml_data( node ), 1 ); + if ( xml_tagwithvalue( node, "MedlineTA" ) && fields_find( info, "TITLE", 1 )==-1 ) { + fstatus = fields_add( info, "TITLE", xml_value( node ), 1 ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } if ( node->down ) { @@ -465,8 +472,8 @@ medin_meshheading( xml *node, fields *info ) { int fstatus, status = BIBL_OK; - if ( xml_tagwithdata( node, "DescriptorName" ) ) { - fstatus = fields_add( info, "KEYWORD", xml_data( node ), 0 ); + if ( xml_tagwithvalue( node, "DescriptorName" ) ) { + fstatus = fields_add( info, "KEYWORD", xml_value( node ), 0 ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } if ( node->next ) status = medin_meshheading( node->next, info ); @@ -491,7 +498,7 @@ * 14523232 * 10.1073/pnas.2133463100 * 2133463100 - * 22922082 + * PMC4833866 * * * @@ -504,6 +511,7 @@ { "ArticleId", "IdType", "doi", "DOI", 0 }, { "ArticleId", "IdType", "pubmed", "PMID", 0 }, { "ArticleId", "IdType", "medline", "MEDLINE", 0 }, + { "ArticleId", "IdType", "pmc", "PMC", 0 }, { "ArticleId", "IdType", "pii", "PII", 0 }, }; int nc = sizeof( c ) / sizeof( c[0] ), found, status; @@ -537,12 +545,12 @@ else if ( xml_tagexact( node, "Language" ) ) status = medin_language( node, info, 0 ); else if ( xml_tagexact( node, "Affiliation" ) ) { - fstatus = fields_add( info, "ADDRESS", xml_data( node ), 0 ); + fstatus = fields_add( info, "ADDRESS", xml_value( node ), 0 ); if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; } if ( status!=BIBL_OK ) return status; if ( node->next ) status = medin_article( node->next, info ); - return BIBL_OK; + return status; } static int @@ -616,8 +624,8 @@ return status; } -int -medin_processf( fields *medin, char *data, char *filename, long nref ) +static int +medin_processf( fields *medin, char *data, char *filename, long nref, param *p ) { int status; xml top; diff --git a/bibutils/medin.h b/bibutils/medin.h deleted file mode 100644 --- a/bibutils/medin.h +++ /dev/null @@ -1,26 +0,0 @@ -/* - * medin.h - * - * Copyright (c) Chris Putnam 2004-2014 - * - * Source code released under the GPL version 2 - * - */ -#ifndef MEDIN_H -#define MEDIN_H - -#include "newstr.h" -#include "fields.h" -#include "reftypes.h" -#include "bibutils.h" - -extern int medin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ); -extern int medin_processf( fields *medin, char *data, char *filename, long nref ); - -extern void medin_initparams( param *p, const char *progname ); - -extern variants med_all[]; -extern int med_nall; - -#endif - diff --git a/bibutils/modsin.c b/bibutils/modsin.c --- a/bibutils/modsin.c +++ b/bibutils/modsin.c @@ -1,7 +1,7 @@ /* * modsin.c * - * Copyright (c) Chris Putnam 2004-2014 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * @@ -11,8 +11,8 @@ #include #include #include "is_ws.h" -#include "newstr.h" -#include "newstr_conv.h" +#include "str.h" +#include "str_conv.h" #include "xml.h" #include "xml_encoding.h" #include "fields.h" @@ -20,12 +20,16 @@ #include "reftypes.h" #include "modstypes.h" #include "marc.h" +#include "url.h" #include "iso639_1.h" #include "iso639_2.h" #include "iso639_3.h" #include "bibutils.h" -#include "modsin.h" +#include "bibformats.h" +static int modsin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int modsin_processf( fields *medin, char *data, char *filename, long nref, param *p ); + /***************************************************** PUBLIC: void modsin_initparams() *****************************************************/ @@ -55,8 +59,8 @@ p->all = NULL; p->nall = 0; - list_init( &(p->asis) ); - list_init( &(p->corps) ); + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); if ( !progname ) p->progname = NULL; else p->progname = strdup( progname ); @@ -69,13 +73,13 @@ static char modsns[]="mods"; static int -modsin_detailr( xml *node, newstr *value ) +modsin_detailr( xml *node, str *value ) { int status = BIBL_OK; if ( node->value && node->value->len ) { - if ( value->len ) newstr_addchar( value, ' ' ); - newstr_newstrcat( value, node->value ); - if ( newstr_memerr( value ) ) return BIBL_ERR_MEMERR; + if ( value->len ) str_addchar( value, ' ' ); + str_strcat( value, node->value ); + if ( str_memerr( value ) ) return BIBL_ERR_MEMERR; } if ( node->down ) { status = modsin_detailr( node->down, value ); @@ -89,26 +93,26 @@ static int modsin_detail( xml *node, fields *info, int level ) { - newstr type, value, *tp; + str type, value, *tp; int fstatus, status = BIBL_OK; if ( node->down ) { - newstrs_init( &type, &value, NULL ); + strs_init( &type, &value, NULL ); tp = xml_getattrib( node, "type" ); if ( tp ) { - newstr_newstrcpy( &type, tp ); - newstr_toupper( &type ); - if ( newstr_memerr( &type ) ) goto out; + str_strcpy( &type, tp ); + str_toupper( &type ); + if ( str_memerr( &type ) ) goto out; } status = modsin_detailr( node->down, &value ); if ( status!=BIBL_OK ) goto out; if ( type.data && !strcasecmp( type.data, "PAGE" ) ) { - fstatus = fields_add( info, "PAGESTART", value.data, level ); + fstatus = fields_add( info, "PAGES:START", value.data, level ); } else { fstatus = fields_add( info, type.data, value.data, level ); } if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; out: - newstrs_free( &type, &value, NULL ); + strs_free( &type, &value, NULL ); } return status; } @@ -118,56 +122,56 @@ { int fstatus, status = BIBL_OK; char *tag, *p = NULL; - newstr s; + str s; if ( node->value ) p = node->value->data; if ( p ) { - newstr_init( &s ); + str_init( &s ); - p = newstr_cpytodelim( &s, skip_ws( p ), "-", 1 ); - if ( newstr_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } - if ( s.len ) { - tag = ( part ) ? "PARTYEAR" : "YEAR"; - fstatus = fields_add( info, tag, s.data, level ); + p = str_cpytodelim( &s, skip_ws( p ), "-", 1 ); + if ( str_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } + if ( str_has_value( &s ) ) { + tag = ( part ) ? "PARTDATE:YEAR" : "DATE:YEAR"; + fstatus = fields_add( info, tag, str_cstr( &s ), level ); if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } - p = newstr_cpytodelim( &s, skip_ws( p ), "-", 1 ); - if ( newstr_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } - if ( s.len ) { - tag = ( part ) ? "PARTMONTH" : "MONTH"; - fstatus = fields_add( info, tag, s.data, level ); + p = str_cpytodelim( &s, skip_ws( p ), "-", 1 ); + if ( str_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } + if ( str_has_value( &s ) ) { + tag = ( part ) ? "PARTDATE:MONTH" : "DATE:MONTH"; + fstatus = fields_add( info, tag, str_cstr( &s ), level ); if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } - p = newstr_cpytodelim( &s, skip_ws( p ), "", 0 ); - if ( newstr_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } - if ( s.len ) { - tag = ( part ) ? "PARTDAY" : "DAY"; - fstatus = fields_add( info, tag, s.data, level ); + p = str_cpytodelim( &s, skip_ws( p ), "", 0 ); + if ( str_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } + if ( str_has_value( &s ) ) { + tag = ( part ) ? "PARTDATE:DAY" : "DATE:DAY"; + fstatus = fields_add( info, tag, str_cstr( &s ), level ); if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } out: - newstr_free( &s ); + str_free( &s ); } return status; } static int -modsin_pager( xml *node, newstr *sp, newstr *ep, newstr *tp, newstr *lp ) +modsin_pager( xml *node, str *sp, str *ep, str *tp, str *lp ) { int status = BIBL_OK; if ( xml_tagexact( node, "start" ) ) { - newstr_newstrcpy( sp, node->value ); - if ( newstr_memerr( sp ) ) return BIBL_ERR_MEMERR; + str_strcpy( sp, node->value ); + if ( str_memerr( sp ) ) return BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "end" ) ) { - newstr_newstrcpy( ep, node->value ); - if ( newstr_memerr( ep ) ) return BIBL_ERR_MEMERR; + str_strcpy( ep, node->value ); + if ( str_memerr( ep ) ) return BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "total" ) ) { - newstr_newstrcpy( tp, node->value ); - if ( newstr_memerr( tp ) ) return BIBL_ERR_MEMERR; + str_strcpy( tp, node->value ); + if ( str_memerr( tp ) ) return BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "list" ) ) { - newstr_newstrcpy( lp, node->value ); - if ( newstr_memerr( lp ) ) return BIBL_ERR_MEMERR; + str_strcpy( lp, node->value ); + if ( str_memerr( lp ) ) return BIBL_ERR_MEMERR; } if ( node->down ) { status = modsin_pager( node->down, sp, ep, tp, lp ); @@ -182,53 +186,49 @@ modsin_page( xml *node, fields *info, int level ) { int fstatus, status = BIBL_OK; - newstr sp, ep, tp, lp; + str sp, ep, tp, lp; xml *dnode = node->down; if ( !dnode ) return BIBL_OK; - newstrs_init( &sp, &ep, &tp, &lp, NULL ); + strs_init( &sp, &ep, &tp, &lp, NULL ); status = modsin_pager( dnode, &sp, &ep, &tp, &lp ); if ( status!=BIBL_OK ) goto out; - if ( sp.len || ep.len ) { - if ( sp.len ) { - fstatus = fields_add( info, "PAGESTART", sp.data, level ); + if ( str_has_value( &sp ) || str_has_value( &ep ) ) { + if ( str_has_value( &sp ) ) { + fstatus = fields_add( info, "PAGES:START", str_cstr( &sp ), level ); if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } - if ( ep.len ) { - fstatus = fields_add( info, "PAGEEND", ep.data, level ); + if ( str_has_value( &ep ) ) { + fstatus = fields_add( info, "PAGES:STOP", str_cstr( &ep ), level ); if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } - } else if ( lp.len ) { - fstatus = fields_add( info, "PAGESTART", lp.data, level ); + } else if ( str_has_value( &lp ) ) { + fstatus = fields_add( info, "PAGES:START", str_cstr( &lp ), level ); if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } - if ( tp.len ) { - fstatus = fields_add( info, "TOTALPAGES", tp.data, level ); + if ( str_has_value( &tp ) ) { + fstatus = fields_add( info, "PAGES:TOTAL", str_cstr( &tp ), level ); if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } out: - newstrs_free( &sp, &ep, &tp, &lp, NULL ); - return BIBL_OK; + strs_free( &sp, &ep, &tp, &lp, NULL ); + return status; } static int -modsin_titler( xml *node, newstr *title, newstr *subtitle ) +modsin_titler( xml *node, str *title, str *subtitle ) { int status = BIBL_OK; if ( xml_tagexact( node, "title" ) ) { - if ( title->len ) { - newstr_strcat( title, " : " ); - newstr_newstrcat( title, node->value ); - } else { - newstr_newstrcat( title, node->value ); - } - if ( newstr_memerr( title ) ) return BIBL_ERR_MEMERR; + if ( str_has_value( title ) ) str_strcatc( title, " : " ); + str_strcat( title, node->value ); + if ( str_memerr( title ) ) return BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "subTitle" ) ) { - newstr_newstrcat( subtitle, node->value ); - if ( newstr_memerr( subtitle ) ) return BIBL_ERR_MEMERR; + str_strcat( subtitle, node->value ); + if ( str_memerr( subtitle ) ) return BIBL_ERR_MEMERR; } if ( node->down ) { status = modsin_titler( node->down, title, subtitle ); @@ -247,31 +247,31 @@ { "SUBTITLE", "SHORTSUBTITLE" }, }; int fstatus, status = BIBL_OK; - newstr title, subtitle; - xml *dnode = node->down; + str title, subtitle; + xml *dnode; int abbr; dnode = node->down; if ( !dnode ) return status; - newstrs_init( &title, &subtitle, NULL ); + strs_init( &title, &subtitle, NULL ); abbr = xml_tag_attrib( node, "titleInfo", "type", "abbreviated" ); status = modsin_titler( dnode, &title, &subtitle ); if ( status!=BIBL_OK ) goto out; - if ( title.len ) { - fstatus = fields_add( info, titletag[0][abbr], title.data, level ); + if ( str_has_value( &title ) ) { + fstatus = fields_add( info, titletag[0][abbr], str_cstr( &title ), level ); if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } - if ( subtitle.len ) { - fstatus = fields_add( info, titletag[1][abbr], subtitle.data, level ); + if ( str_has_value( &subtitle ) ) { + fstatus = fields_add( info, titletag[1][abbr], str_cstr( &subtitle ), level ); if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } out: - newstrs_free( &title, &subtitle, NULL ); + strs_free( &title, &subtitle, NULL ); return status; } @@ -284,24 +284,24 @@ * "author" or "author|creator" or "edt" or "editor|edt". */ static int -modsin_marcrole_convert( newstr *s, char *suffix, newstr *out ) +modsin_marcrole_convert( str *s, char *suffix, str *out ) { convert roles[] = { - { "author", "AUTHOR" }, - { "aut", "AUTHOR" }, - { "aud", "AUTHOR" }, - { "aui", "AUTHOR" }, - { "aus", "AUTHOR" }, - { "creator", "AUTHOR" }, - { "cre", "AUTHOR" }, - { "editor", "EDITOR" }, - { "edt", "EDITOR" }, - { "degree grantor", "DEGREEGRANTOR" }, - { "dgg", "DEGREEGRANTOR" }, - { "organizer of meeting","ORGANIZER" }, - { "orm", "ORGANIZER" }, - { "patent holder", "ASSIGNEE" }, - { "pth", "ASSIGNEE" } + { "author", "AUTHOR", 0, 0 }, + { "aut", "AUTHOR", 0, 0 }, + { "aud", "AUTHOR", 0, 0 }, + { "aui", "AUTHOR", 0, 0 }, + { "aus", "AUTHOR", 0, 0 }, + { "creator", "AUTHOR", 0, 0 }, + { "cre", "AUTHOR", 0, 0 }, + { "editor", "EDITOR", 0, 0 }, + { "edt", "EDITOR", 0, 0 }, + { "degree grantor", "DEGREEGRANTOR", 0, 0 }, + { "dgg", "DEGREEGRANTOR", 0, 0 }, + { "organizer of meeting","ORGANIZER", 0, 0 }, + { "orm", "ORGANIZER", 0, 0 }, + { "patent holder", "ASSIGNEE", 0, 0 }, + { "pth", "ASSIGNEE", 0, 0 } }; int nroles = sizeof( roles ) / sizeof( roles[0] ); int i, nmismatch, n = -1, status = BIBL_OK; @@ -330,26 +330,26 @@ } if ( n!=-1 ) { - newstr_strcpy( out, roles[n].internal ); - if ( suffix ) newstr_strcat( out, suffix ); + str_strcpyc( out, roles[n].internal ); + if ( suffix ) str_strcatc( out, suffix ); } else { - newstr_strcpy( out, s->data ); + str_strcpy( out, s ); } - if ( newstr_memerr( out ) ) status = BIBL_ERR_MEMERR; + if ( str_memerr( out ) ) status = BIBL_ERR_MEMERR; return status; } static int -modsin_asis_corp_r( xml *node, newstr *name, newstr *role ) +modsin_asis_corp_r( xml *node, str *name, str *role ) { int status = BIBL_OK; if ( xml_tagexact( node, "namePart" ) ) { - newstr_newstrcpy( name, node->value ); - if ( newstr_memerr( name ) ) return BIBL_ERR_MEMERR; + str_strcpy( name, node->value ); + if ( str_memerr( name ) ) return BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "roleTerm" ) ) { - if ( role->len ) newstr_addchar( role, '|' ); - newstr_newstrcat( role, node->value ); - if ( newstr_memerr( role ) ) return BIBL_ERR_MEMERR; + if ( role->len ) str_addchar( role, '|' ); + str_strcat( role, node->value ); + if ( str_memerr( role ) ) return BIBL_ERR_MEMERR; } if ( node->down ) { status = modsin_asis_corp_r( node->down, name, role ); @@ -361,84 +361,141 @@ } static int -modsin_personr( xml *node, newstr *name, newstr *suffix, newstr *roles ) -{ - newstr outname; - int status = BIBL_OK; - newstr_init( &outname ); - if ( xml_tagexact( node, "namePart" ) ) { - if ( xml_tag_attrib( node, "namePart", "type", "family" ) ) { - if ( name->len ) newstr_prepend( name, "|" ); - newstr_prepend( name, node->value->data ); - } else if (xml_tag_attrib( node, "namePart", "type", "suffix") || - xml_tag_attrib( node, "namePart", "type", "termsOfAddress" )) { - if ( suffix->len ) newstr_addchar( suffix, ' ' ); - newstr_strcat( suffix, node->value->data ); - } else if (xml_tag_attrib( node, "namePart", "type", "date")){ - } else { - if ( name->len ) newstr_addchar( name, '|' ); - name_parse( &outname, node->value, NULL, NULL ); - newstr_newstrcat( name, &outname ); - } - } else if ( xml_tagexact( node, "roleTerm" ) ) { - if ( roles->len ) newstr_addchar( roles, '|' ); - newstr_newstrcat( roles, node->value ); - } - if ( node->down ) { - status = modsin_personr( node->down, name, suffix, roles ); - if ( status!=BIBL_OK ) goto out; - } - if ( node->next ) status = modsin_personr( node->next, name, suffix, roles ); -out: - newstr_free( &outname ); - return status; -} - -static int modsin_asis_corp( xml *node, fields *info, int level, char *suffix ) { int fstatus, status = BIBL_OK; - newstr name, roles, role_out; + str name, roles, role_out; xml *dnode = node->down; if ( dnode ) { - newstrs_init( &name, &roles, &role_out, NULL ); + strs_init( &name, &roles, &role_out, NULL ); status = modsin_asis_corp_r( dnode, &name, &roles ); if ( status!=BIBL_OK ) goto out; status = modsin_marcrole_convert( &roles, suffix, &role_out ); if ( status!=BIBL_OK ) goto out; - fstatus = fields_add( info, role_out.data, name.data, level ); + fstatus = fields_add( info, str_cstr( &role_out ), str_cstr( &name ), level ); if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; out: - newstrs_free( &name, &roles, &role_out, NULL ); + strs_free( &name, &roles, &role_out, NULL ); } return status; } static int +modsin_roler( xml *node, str *roles ) +{ + if ( roles->len ) str_addchar( roles, '|' ); + str_strcat( roles, node->value ); + if ( str_memerr( roles ) ) return BIBL_ERR_MEMERR; + else return BIBL_OK; +} + +static int +modsin_personr( xml *node, str *familyname, str *givenname, str *suffix ) +{ + int status = BIBL_OK; + + if ( xml_tag_attrib( node, "namePart", "type", "family" ) ) { + if ( str_has_value( familyname ) ) str_addchar( familyname, ' ' ); + str_strcat( familyname, node->value ); + if ( str_memerr( familyname ) ) status = BIBL_ERR_MEMERR; + } + + else if ( xml_tag_attrib( node, "namePart", "type", "suffix") || + xml_tag_attrib( node, "namePart", "type", "termsOfAddress" )) { + if ( str_has_value( suffix ) ) str_addchar( suffix, ' ' ); + str_strcat( suffix, node->value ); + if ( str_memerr( suffix ) ) status = BIBL_ERR_MEMERR; + } + + else if (xml_tag_attrib( node, "namePart", "type", "date") ){ + /* no nothing */ + } + + else { + if ( str_has_value( givenname ) ) str_addchar( givenname, '|' ); + str_strcat( givenname, node->value ); + if ( str_memerr( givenname ) ) status = BIBL_ERR_MEMERR; + } + + return status; +} + +static int modsin_person( xml *node, fields *info, int level ) { - newstr name, suffix, roles, role_out; + str familyname, givenname, name, suffix, roles, role_out; int fstatus, status = BIBL_OK; - xml *dnode = node->down; - if ( dnode ) { - newstrs_init( &name, &suffix, &roles, &role_out, NULL ); + xml *dnode, *rnode; - status = modsin_personr( dnode, &name, &suffix, &roles ); - if ( status!=BIBL_OK ) goto out; - if ( suffix.len ) { - newstr_strcat( &name, "||" ); - newstr_newstrcat( &name, &suffix ); - if ( newstr_memerr( &name ) ) { status=BIBL_ERR_MEMERR; goto out; } + dnode = node->down; + if ( !dnode ) return status; + + strs_init( &name, &familyname, &givenname, &suffix, &roles, &role_out, NULL ); + + while ( dnode ) { + + if ( xml_tagexact( dnode, "namePart" ) ) { + status = modsin_personr( dnode, &familyname, &givenname, &suffix ); + if ( status!=BIBL_OK ) goto out; } - status = modsin_marcrole_convert( &roles, NULL, &role_out ); - if ( status!=BIBL_OK ) goto out; + else if ( xml_tagexact( dnode, "role" ) ) { + rnode = dnode->down; + while ( rnode ) { + if ( xml_tagexact( rnode, "roleTerm" ) ) { + status = modsin_roler( rnode, &roles ); + if ( status!=BIBL_OK ) goto out; + } + rnode = rnode->next; + } + } - fstatus = fields_add( info, role_out.data, name.data, level ); - if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; -out: - newstrs_free( &name, &suffix, &roles, &role_out, NULL ); + dnode = dnode->next; + } + + /* + * Handle: + * Noah A. + * Smith + * without mangling the order of "Noah A." + */ + if ( str_has_value( &familyname ) ) { + str_strcpy( &name, &familyname ); + if ( givenname.len ) { + str_addchar( &name, '|' ); + str_strcat( &name, &givenname ); + } + } + + /* + * Handle: + * Noah A. Smith + * with name order mangling. + */ + else { + if ( str_has_value( &givenname ) ) + name_parse( &name, &givenname, NULL, NULL ); + } + + if ( str_has_value( &suffix ) ) { + str_strcatc( &name, "||" ); + str_strcat( &name, &suffix ); + } + + if ( str_memerr( &name ) ) { + status=BIBL_ERR_MEMERR; + goto out; + } + + status = modsin_marcrole_convert( &roles, NULL, &role_out ); + if ( status!=BIBL_OK ) goto out; + + fstatus = fields_add_can_dup( info, str_cstr( &role_out ), str_cstr( &name ), level ); + if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; + +out: + strs_free( &name, &familyname, &givenname, &suffix, &roles, &role_out, NULL ); return status; } @@ -452,7 +509,7 @@ tag = ( school ) ? school_tag : address_tag; - fstatus = fields_add( info, tag, xml_data( node ), level ); + fstatus = fields_add( info, tag, xml_value( node ), level ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; return BIBL_OK; @@ -462,26 +519,26 @@ modsin_placeterm_code( xml *node, fields *info, int level ) { int fstatus, status = BIBL_OK; - newstr s, *auth; + str s, *auth; - newstr_init( &s ); + str_init( &s ); auth = xml_getattrib( node, "authority" ); if ( auth && auth->len ) { - newstr_newstrcpy( &s, auth ); - newstr_addchar( &s, '|' ); + str_strcpy( &s, auth ); + str_addchar( &s, '|' ); } - newstr_newstrcat( &s, node->value ); + str_strcat( &s, node->value ); - if ( newstr_memerr( &s ) ) { + if ( str_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } - fstatus = fields_add( info, "CODEDADDRESS", s.data, level ); + fstatus = fields_add( info, "CODEDADDRESS", str_cstr( &s ), level ); if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; out: - newstr_free( &s ); + str_free( &s ); return status; } @@ -489,13 +546,13 @@ modsin_placeterm( xml *node, fields *info, int level, int school ) { int status = BIBL_OK; - newstr *type; + str *type; type = xml_getattrib( node, "type" ); - if ( type && type->len ) { - if ( !strcmp( type->data, "text" ) ) + if ( str_has_value( type ) ) { + if ( !strcmp( str_cstr( type ), "text" ) ) status = modsin_placeterm_text( node, info, level, school ); - else if ( !strcmp( type->data, "code" ) ) + else if ( !strcmp( str_cstr( type ), "code" ) ) status = modsin_placeterm_code( node, info, level ); } @@ -520,21 +577,21 @@ } static int -modsin_origininfor( xml *node, fields *info, int level, newstr *pub, newstr *add, newstr *addc, newstr *ed, newstr *iss ) +modsin_origininfor( xml *node, fields *info, int level, str *pub, str *add, str *addc, str *ed, str *iss ) { int status = BIBL_OK; if ( xml_tagexact( node, "dateIssued" ) ) status = modsin_date( node, info, level, 0 ); - else if ( xml_tagexact( node, "publisher" ) && xml_hasdata( node ) ) { - newstr_newstrcat( pub, node->value ); - if ( newstr_memerr( pub ) ) return BIBL_ERR_MEMERR; - } else if ( xml_tagexact( node, "edition" ) && xml_hasdata( node ) ) { - newstr_newstrcat( ed, node->value ); - if( newstr_memerr( ed ) ) return BIBL_ERR_MEMERR; - } else if ( xml_tagexact( node, "issuance" ) && xml_hasdata( node ) ) { - newstr_newstrcat( iss, node->value ); - if ( newstr_memerr( iss ) ) return BIBL_ERR_MEMERR; - } else if ( xml_tagexact( node, "place" ) && xml_hasdata( node ) ) + else if ( xml_tagexact( node, "publisher" ) && xml_hasvalue( node ) ) { + str_strcat( pub, node->value ); + if ( str_memerr( pub ) ) return BIBL_ERR_MEMERR; + } else if ( xml_tagexact( node, "edition" ) && xml_hasvalue( node ) ) { + str_strcat( ed, node->value ); + if( str_memerr( ed ) ) return BIBL_ERR_MEMERR; + } else if ( xml_tagexact( node, "issuance" ) && xml_hasvalue( node ) ) { + str_strcat( iss, node->value ); + if ( str_memerr( iss ) ) return BIBL_ERR_MEMERR; + } else if ( xml_tagexact( node, "place" ) && xml_hasvalue( node ) ) status = modsin_placer( node, info, level, 0 ); if ( status!=BIBL_OK ) return status; if ( node->down ) { @@ -549,35 +606,35 @@ static int modsin_origininfo( xml *node, fields *info, int level ) { - newstr publisher, address, addcode, edition, issuance; + str publisher, address, addcode, edition, issuance; int fstatus, status = BIBL_OK; if ( node->down ) { - newstrs_init( &publisher, &address, &addcode, &edition, &issuance, NULL ); + strs_init( &publisher, &address, &addcode, &edition, &issuance, NULL ); status = modsin_origininfor( node->down, info, level, &publisher, &address, &addcode, &edition, &issuance ); if ( status!=BIBL_OK ) goto out; - if ( publisher.len ) { - fstatus = fields_add( info, "PUBLISHER", publisher.data, level ); + if ( str_has_value( &publisher ) ) { + fstatus = fields_add( info, "PUBLISHER", str_cstr( &publisher ), level ); if ( fstatus!=FIELDS_OK ) { status=BIBL_ERR_MEMERR; goto out; } } - if ( address.len ) { - fstatus = fields_add( info, "ADDRESS", address.data, level ); + if ( str_has_value( &address ) ) { + fstatus = fields_add( info, "ADDRESS", str_cstr( &address ), level ); if ( fstatus!=FIELDS_OK ) { status=BIBL_ERR_MEMERR; goto out; } } - if ( addcode.len ) { - fstatus = fields_add( info, "CODEDADDRESS", addcode.data, level ); + if ( str_has_value( &addcode ) ) { + fstatus = fields_add( info, "CODEDADDRESS", str_cstr( &addcode ), level ); if ( fstatus!=FIELDS_OK ) { status=BIBL_ERR_MEMERR; goto out; } } - if ( edition.len ) { - fstatus = fields_add( info, "EDITION", edition.data, level ); + if ( str_has_value( &edition ) ) { + fstatus = fields_add( info, "EDITION", str_cstr( &edition ), level ); if ( fstatus!=FIELDS_OK ) { status=BIBL_ERR_MEMERR; goto out; } } - if ( issuance.len ) { - fstatus = fields_add( info, "ISSUANCE", issuance.data, level ); + if ( str_has_value( &issuance ) ) { + fstatus = fields_add( info, "ISSUANCE", str_cstr( &issuance ), level ); if ( fstatus!=FIELDS_OK ) { status=BIBL_ERR_MEMERR; goto out; } } out: - newstrs_free( &publisher, &address, &addcode, &edition, &issuance, NULL ); + strs_free( &publisher, &address, &addcode, &edition, &issuance, NULL ); } return status; } @@ -586,7 +643,11 @@ modsin_subjectr( xml *node, fields *info, int level ) { int fstatus, status = BIBL_OK; - if ( xml_tagexact( node, "topic" ) || xml_tagexact( node, "geographic" )) { + if ( xml_tag_attrib( node, "topic", "class", "primary" ) ) { + fstatus = fields_add( info, "EPRINTCLASS", node->value->data, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + else if ( xml_tagexact( node, "topic" ) || xml_tagexact( node, "geographic" )) { fstatus = fields_add( info, "KEYWORD", node->value->data, level ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } @@ -610,10 +671,10 @@ modsin_id1( xml *node, fields *info, int level ) { int fstatus; - newstr *ns; + str *ns; ns = xml_getattrib( node, "ID" ); - if ( ns && ns->len ) { - fstatus = fields_add( info, "REFNUM", ns->data, level ); + if ( str_has_value( ns ) ) { + fstatus = fields_add( info, "REFNUM", str_cstr( ns ), level ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } return BIBL_OK; @@ -633,8 +694,8 @@ int i, ismarc = 0, isadded = 0, fstatus; char *d; - if ( !xml_hasdata( node ) ) return BIBL_OK; - d = xml_data( node ); + if ( !xml_hasvalue( node ) ) return BIBL_OK; + d = xml_value( node ); if ( marc_findgenre( d )!=-1 ) ismarc = 1; if ( !ismarc ) { for ( i=0; iEnglish */ - if ( xml_hasdata( node ) ) { - fstatus = fields_add( info, "LANGUAGE", xml_data( node ), level ); + if ( xml_hasvalue( node ) ) { + fstatus = fields_add( info, "LANGUAGE", xml_value( node ), level ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } @@ -702,8 +763,8 @@ modsin_simple( xml *node, fields *info, char *tag, int level ) { int fstatus; - if ( xml_hasdata( node ) ) { - fstatus = fields_add( info, tag, xml_data( node ), level ); + if ( xml_hasvalue( node ) ) { + fstatus = fields_add( info, tag, xml_value( node ), level ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } return BIBL_OK; @@ -713,22 +774,29 @@ modsin_locationr( xml *node, fields *info, int level ) { int fstatus, status = BIBL_OK; + char *url = "URL"; + char *fileattach = "FILEATTACH"; char *tag=NULL; if ( xml_tagexact( node, "url" ) ) { if ( xml_hasattrib( node, "access", "raw object" ) ) - tag = "FILEATTACH"; + tag = fileattach; else - tag = "URL"; - } else if ( xml_tagexact( node, "physicalLocation" ) ) { + tag = url; + } + else if ( xml_tagexact( node, "physicalLocation" ) ) { if ( xml_hasattrib( node, "type", "school" ) ) tag = "SCHOOL"; else tag = "LOCATION"; } - if ( tag ) { - fstatus = fields_add( info, tag, node->value->data, level ); + if ( tag == url ) { + status = urls_split_and_add( xml_value( node ), info, level ); + if ( status!=BIBL_OK ) return status; + } + else if ( tag ) { + fstatus = fields_add( info, tag, xml_value( node ), level ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } @@ -749,13 +817,13 @@ } static int -modsin_descriptionr( xml *node, newstr *s ) +modsin_descriptionr( xml *node, str *s ) { int status = BIBL_OK; if ( xml_tagexact( node, "extent" ) || xml_tagexact( node, "note" ) ) { - newstr_newstrcpy( s, node->value ); - if ( newstr_memerr( s ) ) return BIBL_ERR_MEMERR; + str_strcpy( s, node->value ); + if ( str_memerr( s ) ) return BIBL_ERR_MEMERR; } if ( node->down ) { status = modsin_descriptionr( node->down, s ); @@ -769,29 +837,29 @@ modsin_description( xml *node, fields *info, int level ) { int fstatus, status = BIBL_OK; - newstr s; - newstr_init( &s ); + str s; + str_init( &s ); if ( node->down ) { status = modsin_descriptionr( node->down, &s ); if ( status!=BIBL_OK ) goto out; } else { if ( node->value && node->value->len > 0 ) - newstr_newstrcpy( &s, node->value ); - if ( newstr_memerr( &s ) ) { + str_strcpy( &s, node->value ); + if ( str_memerr( &s ) ) { status = BIBL_ERR_MEMERR; goto out; } } - if ( s.len ) { - fstatus = fields_add( info, "DESCRIPTION", s.data, level ); + if ( str_has_value( &s ) ) { + fstatus = fields_add( info, "DESCRIPTION", str_cstr( &s ), level ); if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } out: - newstr_free( &s ); - return BIBL_OK; + str_free( &s ); + return status; } static int @@ -824,8 +892,8 @@ { int fstatus, status = BIBL_OK; char *tag, *d; - if ( xml_hasdata( node ) ) { - d = xml_data( node ); + if ( xml_hasvalue( node ) ) { + d = xml_value( node ); if ( xml_tag_attrib( node, "classification", "authority", "lcc" ) ) tag = "LCC"; else @@ -847,8 +915,8 @@ /* extract recordIdentifier */ curr = node; while ( curr ) { - if ( xml_tagexact( curr, "recordIdentifier" ) && xml_hasdata( curr ) ) { - d = xml_data( curr ); + if ( xml_tagexact( curr, "recordIdentifier" ) && xml_hasvalue( curr ) ) { + d = xml_value( curr ); fstatus = fields_add( info, "REFNUM", d, level ); if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } @@ -861,21 +929,24 @@ modsin_identifier( xml *node, fields *info, int level ) { convert ids[] = { - { "citekey", "REFNUM" }, - { "issn", "ISSN" }, - { "isbn", "ISBN" }, - { "doi", "DOI" }, - { "url", "URL" }, - { "uri", "URL" }, - { "pmid", "PMID" }, - { "pubmed", "PMID" }, - { "medline", "MEDLINE" }, - { "arXiv", "ARXIV" }, - { "pii", "PII" }, - { "isi", "ISIREFNUM" }, - { "serial number", "SERIALNUMBER" }, - { "accessnum", "ACCESSNUM" }, - { "jstor", "JSTOR" }, + { "citekey", "REFNUM", 0, 0 }, + { "issn", "ISSN", 0, 0 }, + { "coden", "CODEN", 0, 0 }, + { "isbn", "ISBN", 0, 0 }, + { "doi", "DOI", 0, 0 }, + { "url", "URL", 0, 0 }, + { "uri", "URL", 0, 0 }, + { "pmid", "PMID", 0, 0 }, + { "pubmed", "PMID", 0, 0 }, + { "medline", "MEDLINE", 0, 0 }, + { "pmc", "PMC", 0, 0 }, + { "arXiv", "ARXIV", 0, 0 }, + { "MRnumber", "MRNUMBER", 0, 0 }, + { "pii", "PII", 0, 0 }, + { "isi", "ISIREFNUM", 0, 0 }, + { "serial number", "SERIALNUMBER",0, 0 }, + { "accessnum", "ACCESSNUM", 0, 0 }, + { "jstor", "JSTOR", 0, 0 }, }; int i, fstatus, n = sizeof( ids ) / sizeof( ids[0] ); if ( !node->value || node->value->len==0 ) return BIBL_OK; @@ -892,11 +963,11 @@ modsin_mods( xml *node, fields *info, int level ) { convert simple[] = { - { "note", "NOTES" }, - { "abstract", "ABSTRACT" }, - { "bibtex-annote", "ANNOTE" }, - { "typeOfResource", "RESOURCE" }, - { "tableOfContents", "CONTENTS" }, + { "note", "NOTES", 0, 0 }, + { "abstract", "ABSTRACT", 0, 0 }, + { "bibtex-annote", "ANNOTE", 0, 0 }, + { "typeOfResource", "RESOURCE", 0, 0 }, + { "tableOfContents", "CONTENTS", 0, 0 }, }; int nsimple = sizeof( simple ) / sizeof( simple[0] ); int i, found = 0, status = BIBL_OK; @@ -944,6 +1015,10 @@ xml_tag_attrib( node, "relatedItem", "type", "series" ) ) { if ( node->down ) status = modsin_mods( node->down, info, level+1 ); } + else if ( xml_tag_attrib( node, "relatedItem", "type", "original" ) ) { + if ( node->down ) status = modsin_mods( node->down, info, LEVEL_ORIG ); + } + if ( status!=BIBL_OK ) return status; } @@ -971,8 +1046,8 @@ return status; } -int -modsin_processf( fields *modsin, char *data, char *filename, long nref ) +static int +modsin_processf( fields *modsin, char *data, char *filename, long nref, param *p ) { int status; xml top; @@ -1011,32 +1086,31 @@ return xml_findend( p, "mods" ); } -int -modsin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, - newstr *reference, int *fcharset ) +static int +modsin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) { - newstr tmp; + str tmp; int m, file_charset = CHARSET_UNKNOWN; char *startptr = NULL, *endptr = NULL; - newstr_init( &tmp ); + str_init( &tmp ); do { - if ( line->data ) newstr_newstrcat( &tmp, line ); - if ( tmp.data ) { + if ( line->data ) str_strcat( &tmp, line ); + if ( str_has_value( &tmp ) ) { m = xml_getencoding( &tmp ); if ( m!=CHARSET_UNKNOWN ) file_charset = m; startptr = modsin_startptr( tmp.data ); endptr = modsin_endptr( tmp.data ); } else startptr = endptr = NULL; - newstr_empty( line ); + str_empty( line ); if ( startptr && endptr ) { - newstr_segcpy( reference, startptr, endptr ); - newstr_strcpy( line, endptr ); + str_segcpy( reference, startptr, endptr ); + str_strcpyc( line, endptr ); } - } while ( !endptr && newstr_fget( fp, buf, bufsize, bufpos, line ) ); + } while ( !endptr && str_fget( fp, buf, bufsize, bufpos, line ) ); - newstr_free( &tmp ); + str_free( &tmp ); *fcharset = file_charset; return ( reference->len > 0 ); } diff --git a/bibutils/modsin.h b/bibutils/modsin.h deleted file mode 100644 --- a/bibutils/modsin.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * modsin.h - * - * Copyright (c) Chris Putnam 2004-2014 - * - * Source code released under the GPL version 2 - * - */ -#ifndef MODSIN_H -#define MODSIN_H - -#include "newstr.h" -#include "fields.h" -#include "reftypes.h" - -extern int modsin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ); -extern int modsin_processf( fields *medin, char *data, char *filename, long nref ); -extern void modsin_initparams( param *p, const char *progname ); - -#endif diff --git a/bibutils/modsout.c b/bibutils/modsout.c --- a/bibutils/modsout.c +++ b/bibutils/modsout.c @@ -1,25 +1,30 @@ /* * modsout.c * - * Copyright (c) Chris Putnam 2003-2014 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * */ #include #include +#include #include #include "is_ws.h" -#include "newstr.h" +#include "str.h" #include "charsets.h" -#include "newstr_conv.h" +#include "str_conv.h" #include "fields.h" #include "iso639_2.h" #include "utf8.h" -#include "modsout.h" #include "modstypes.h" #include "marc.h" +#include "bibformats.h" +static void modsout_writeheader( FILE *outptr, param *p ); +static void modsout_writefooter( FILE *outptr ); +static int modsout_write( fields *info, FILE *outptr, param *p, unsigned long numrefs ); + void modsout_initparams( param *p, const char *progname ) { @@ -41,96 +46,134 @@ p->writef = modsout_write; } -static int -increment_level( int level, int amt ) -{ - if ( level > -1 ) return level+amt; - else return level-amt; -} +/* output_tag() + * + * mode = TAG_OPEN, "" + * mode = TAG_CLOSE, "" + * mode = TAG_OPENCLOSE, "data" + * mode = TAG_SELFCLOSE, "" + * + * newline = TAG_NONEWLINE, "" + * newline = TAG_NEWLINE, "\n" + * + */ +#define TAG_OPEN (0) +#define TAG_CLOSE (1) +#define TAG_OPENCLOSE (2) +#define TAG_SELFCLOSE (3) +#define TAG_NONEWLINE (0) +#define TAG_NEWLINE (1) + static void -output_tab0( FILE *outptr, int level ) +output_tag_core( FILE *outptr, int nindents, char *tag, char *data, unsigned char mode, unsigned char newline, va_list *attrs ) { + char *attr, *val; int i; - level = abs( level ); - for ( i=0; i<=level; ++i ) fprintf( outptr, " " ); -} -static void -output_tab1( FILE *outptr, int level, char *tag ) -{ - output_tab0( outptr, level ); + for ( i=0; i%s", data, tag ); - if ( cr ) fprintf( outptr, "\n" ); -} + do { + attr = va_arg( *attrs, char * ); + if ( attr ) val = va_arg( *attrs, char * ); + if ( attr && val ) + fprintf( outptr, " %s=\"%s\"", attr, val ); + } while ( attr && val ); -static void -output_tab4( FILE *outptr, int level, char *tag, char *aname, char *avalue, - char *data, int cr ) -{ - output_tab0( outptr, level ); - fprintf( outptr, "<%s %s=\"%s\">%s", tag,aname,avalue,data,tag); - if ( cr ) fprintf( outptr, "\n" ); + if ( mode!=TAG_SELFCLOSE ) + fprintf( outptr, ">" ); + else + fprintf( outptr, "/>" ); + + if ( mode==TAG_OPENCLOSE ) { + fprintf( outptr, "%s", data, tag ); + } + + if ( newline==TAG_NEWLINE ) + fprintf( outptr, "\n" ); } +/* output_tag() + * + * output XML tag + * + * mode = [ TAG_OPEN | TAG_CLOSE | TAG_OPENCLOSE | TAG_SELFCLOSE ] + * newline = [ TAG_NEWLINE | TAG_NONEWLINE ] + * + * for mode TAG_OPENCLOSE, ensure that value is non-NULL, as string pointed to by value + * will be output in the tag + */ static void -output_tab6( FILE *outptr, int level, char *tag, char *aname, char *avalue, - char *bname, char *bvalue, char *data, int cr ) +output_tag( FILE *outptr, int nindents, char *tag, char *value, unsigned char mode, unsigned char newline, ... ) { - output_tab0( outptr, level ); - fprintf( outptr, "<%s %s=\"%s\" %s=\"%s\">%s", tag,aname,avalue,bname,bvalue,data,tag); - if ( cr ) fprintf( outptr, "\n" ); + va_list attrs; + + va_start( attrs, newline ); + output_tag_core( outptr, nindents, tag, value, mode, newline, &attrs ); + va_end( attrs ); } +/* output_fil() + * + * output XML tag, but lookup data in fields struct + * + * mode = [ TAG_OPEN | TAG_CLOSE | TAG_OPENCLOSE | TAG_SELFCLOSE ] + * newline = [ TAG_NEWLINE | TAG_NONEWLINE ] + * + * value looked up in fields will only be used in mode TAG_OPENCLOSE + */ static void -output_fill2( FILE *outptr, int level, char *tag, fields *f, int n, int cr ) +output_fil( FILE *outptr, int nindents, char *tag, fields *f, int n, unsigned char mode, unsigned char newline, ... ) { + va_list attrs; char *value; + if ( n!=-1 ) { - value = fields_value( f, n, FIELDS_CHRP ); - output_tab2_attrib( outptr, level, tag, value, - NULL, NULL, cr ); - fields_setused( f, n ); + value = (char *) fields_value( f, n, FIELDS_CHRP ); + va_start( attrs, newline ); + output_tag_core( outptr, nindents, tag, value, mode, newline, &attrs ); + va_end( attrs ); } } -static void -output_fill4( FILE *outptr, int level, char *tag, char *aname, char *avalue, - fields *f, int n, int cr ) +static inline int +lvl2indent( int level ) { - char *value; - if ( n!=-1 ) { - value = fields_value( f, n, FIELDS_CHRP ); - output_tab4( outptr, level, tag, aname, avalue, - value, cr ); - fields_setused( f, n ); - } + if ( level < -1 ) return -level + 1; + else return level + 1; } -/* - * Find the positions of all convert.internal tags and store the - * locations in convert.code. +static inline int +incr_level( int level, int amt ) +{ + if ( level > -1 ) return level+amt; + else return level-amt; +} + +/* convert_findallfields() * - * Return number of the tags found + * Find the positions of all convert.internal tags in the fields + * structure and store the locations in convert.pos element. + * + * Return number of the tags found. */ static int -find_alltags( fields *f, convert *parts, int nparts, int level ) +convert_findallfields( fields *f, convert *parts, int nparts, int level ) { - int i, n=0; + int i, n = 0; + for ( i=0; i\n" ); - output_fill2( outptr, increment_level(level,1), "title", f, ttl, 1 ); - output_fill2( outptr, increment_level(level,1), "subTitle", f, subttl, 1 ); - output_fill2( outptr, increment_level(level,1), "partName", f, parttl, 1 ); + output_tag( outptr, lvl2indent(level), "titleInfo", NULL, TAG_OPEN, TAG_NEWLINE, NULL ); + output_fil( outptr, lvl2indent(incr_level(level,1)), "title", f, ttl, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + output_fil( outptr, lvl2indent(incr_level(level,1)), "subTitle", f, subttl, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + output_fil( outptr, lvl2indent(incr_level(level,1)), "partName", f, parttl, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + /* MODS output doesn't verify if we don't at least have a element */ if ( ttl==-1 && subttl==-1 ) - output_tab1( outptr, increment_level(level,1), "<title/>\n" ); - output_tab1( outptr, level, "</titleInfo>\n" ); + output_tag( outptr, lvl2indent(incr_level(level,1)), "title", NULL, TAG_SELFCLOSE, TAG_NEWLINE, NULL ); + output_tag( outptr, lvl2indent(level), "titleInfo", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); /* output shorttitle if it's different from normal title */ if ( shrttl!=-1 ) { - if ( ttl==-1 || subttl!=-1 || - strcmp(f->data[ttl].data,f->data[shrttl].data) ) { - output_tab1( outptr, level, - "<titleInfo type=\"abbreviated\">\n" ); - output_fill2( outptr, level+1, "title", f, shrttl,1); - output_tab1( outptr, level, "</titleInfo>\n" ); + val = (char *) fields_value( f, shrttl, FIELDS_CHRP ); + if ( ttl==-1 || subttl!=-1 || strcmp(f->data[ttl].data,val) ) { + output_tag( outptr, lvl2indent(level), "titleInfo", NULL, TAG_OPEN, TAG_NEWLINE, "type", "abbreviated", NULL ); + output_tag( outptr, lvl2indent(incr_level(level,1)), "title", val, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + output_tag( outptr, lvl2indent(level), "titleInfo", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); } - fields_setused( f, shrttl ); } } static void -output_personalstart( FILE *outptr, int level ) -{ - int j; - for ( j=0; j<=level; ++j ) fprintf( outptr, " " ); - fprintf( outptr, "<name type=\"personal\">\n" ); -} - -static void output_name( FILE *outptr, char *p, int level ) { - newstr family, part, suffix; + str family, part, suffix; int n=0; - newstrs_init( &family, &part, &suffix, NULL ); + strs_init( &family, &part, &suffix, NULL ); - while ( *p && *p!='|' ) newstr_addchar( &family, *p++ ); + while ( *p && *p!='|' ) str_addchar( &family, *p++ ); if ( *p=='|' ) p++; while ( *p ) { - while ( *p && *p!='|' ) newstr_addchar( &part, *p++ ); + while ( *p && *p!='|' ) str_addchar( &part, *p++ ); /* truncate periods from "A. B. Jones" names */ if ( part.len ) { if ( part.len==2 && part.data[1]=='.' ) { part.len=1; part.data[1]='\0'; } - if ( n==0 ) output_personalstart( outptr, level ); - output_tab4( outptr, increment_level(level,1), "namePart", "type", - "given", part.data, 1 ); + if ( n==0 ) + output_tag( outptr, lvl2indent(level), "name", NULL, TAG_OPEN, TAG_NEWLINE, "type", "personal", NULL ); + output_tag( outptr, lvl2indent(incr_level(level,1)), "namePart", part.data, TAG_OPENCLOSE, TAG_NEWLINE, "type", "given", NULL ); n++; } if ( *p=='|' ) { p++; if ( *p=='|' ) { p++; - while ( *p && *p!='|' ) newstr_addchar( &suffix, *p++ ); + while ( *p && *p!='|' ) str_addchar( &suffix, *p++ ); } - newstr_empty( &part ); + str_empty( &part ); } } if ( family.len ) { - if ( n==0 ) output_personalstart( outptr, level ); - output_tab4( outptr, increment_level(level,1), "namePart", "type", "family", - family.data, 1 ); + if ( n==0 ) + output_tag( outptr, lvl2indent(level), "name", NULL, TAG_OPEN, TAG_NEWLINE, "type", "personal", NULL ); + output_tag( outptr, lvl2indent(incr_level(level,1)), "namePart", family.data, TAG_OPENCLOSE, TAG_NEWLINE, "type", "family", NULL ); + n++; } if ( suffix.len ) { - if ( n==0 ) output_personalstart( outptr, level ); - output_tab4( outptr, increment_level(level,1), "namePart", "type", "suffix", - suffix.data, 1 ); + if ( n==0 ) + output_tag( outptr, lvl2indent(level), "name", NULL, TAG_OPEN, TAG_NEWLINE, "type", "personal", NULL ); + output_tag( outptr, lvl2indent(incr_level(level,1)), "namePart", suffix.data, TAG_OPENCLOSE, TAG_NEWLINE, "type", "suffix", NULL ); } - newstrs_free( &part, &family, &suffix, NULL ); + strs_free( &part, &family, &suffix, NULL ); } @@ -241,140 +277,166 @@ output_names( fields *f, FILE *outptr, int level ) { convert names[] = { - { "author", "AUTHOR", MARC_AUTHORITY }, - { "editor", "EDITOR", MARC_AUTHORITY }, - { "annotator", "ANNOTATOR", MARC_AUTHORITY }, - { "artist", "ARTIST", MARC_AUTHORITY }, - { "author", "2ND_AUTHOR", MARC_AUTHORITY }, - { "author", "3RD_AUTHOR", MARC_AUTHORITY }, - { "author", "SUB_AUTHOR", MARC_AUTHORITY }, - { "author", "COMMITTEE", MARC_AUTHORITY }, - { "author", "COURT", MARC_AUTHORITY }, - { "author", "LEGISLATIVEBODY", MARC_AUTHORITY }, - { "author of afterword, colophon, etc.", "AFTERAUTHOR", MARC_AUTHORITY }, - { "author of introduction, etc.", "INTROAUTHOR", MARC_AUTHORITY }, - { "cartographer", "CARTOGRAPHER", MARC_AUTHORITY }, - { "collaborator", "COLLABORATOR", MARC_AUTHORITY }, - { "commentator", "COMMENTATOR", MARC_AUTHORITY }, - { "compiler", "COMPILER", MARC_AUTHORITY }, - { "degree grantor", "DEGREEGRANTOR", MARC_AUTHORITY }, - { "director", "DIRECTOR", MARC_AUTHORITY }, - { "event", "EVENT", NO_AUTHORITY }, - { "inventor", "INVENTOR", MARC_AUTHORITY }, - { "organizer of meeting", "ORGANIZER", MARC_AUTHORITY }, - { "patent holder", "ASSIGNEE", MARC_AUTHORITY }, - { "performer", "PERFORMER", MARC_AUTHORITY }, - { "producer", "PRODUCER", MARC_AUTHORITY }, - { "recipient", "RECIPIENT", MARC_AUTHORITY }, - { "redactor", "REDACTOR", MARC_AUTHORITY }, - { "reporter", "REPORTER", MARC_AUTHORITY }, - { "sponsor", "SPONSOR", MARC_AUTHORITY }, - { "translator", "TRANSLATOR", MARC_AUTHORITY }, - { "writer", "WRITER", MARC_AUTHORITY }, + { "author", "AUTHOR", 0, MARC_AUTHORITY }, + { "editor", "EDITOR", 0, MARC_AUTHORITY }, + { "annotator", "ANNOTATOR", 0, MARC_AUTHORITY }, + { "artist", "ARTIST", 0, MARC_AUTHORITY }, + { "author", "2ND_AUTHOR", 0, MARC_AUTHORITY }, + { "author", "3RD_AUTHOR", 0, MARC_AUTHORITY }, + { "author", "SUB_AUTHOR", 0, MARC_AUTHORITY }, + { "author", "COMMITTEE", 0, MARC_AUTHORITY }, + { "author", "COURT", 0, MARC_AUTHORITY }, + { "author", "LEGISLATIVEBODY", 0, MARC_AUTHORITY }, + { "author of afterword, colophon, etc.", "AFTERAUTHOR", 0, MARC_AUTHORITY }, + { "author of introduction, etc.", "INTROAUTHOR", 0, MARC_AUTHORITY }, + { "cartographer", "CARTOGRAPHER", 0, MARC_AUTHORITY }, + { "collaborator", "COLLABORATOR", 0, MARC_AUTHORITY }, + { "commentator", "COMMENTATOR", 0, MARC_AUTHORITY }, + { "compiler", "COMPILER", 0, MARC_AUTHORITY }, + { "degree grantor", "DEGREEGRANTOR", 0, MARC_AUTHORITY }, + { "director", "DIRECTOR", 0, MARC_AUTHORITY }, + { "event", "EVENT", 0, NO_AUTHORITY }, + { "inventor", "INVENTOR", 0, MARC_AUTHORITY }, + { "organizer of meeting", "ORGANIZER", 0, MARC_AUTHORITY }, + { "patent holder", "ASSIGNEE", 0, MARC_AUTHORITY }, + { "performer", "PERFORMER", 0, MARC_AUTHORITY }, + { "producer", "PRODUCER", 0, MARC_AUTHORITY }, + { "recipient", "RECIPIENT", 0, MARC_AUTHORITY }, + { "redactor", "REDACTOR", 0, MARC_AUTHORITY }, + { "reporter", "REPORTER", 0, MARC_AUTHORITY }, + { "sponsor", "SPONSOR", 0, MARC_AUTHORITY }, + { "translator", "TRANSLATOR", 0, MARC_AUTHORITY }, + { "writer", "WRITER", 0, MARC_AUTHORITY }, }; int i, n, nfields, ntypes = sizeof( names ) / sizeof( convert ); int f_asis, f_corp, f_conf; - newstr role; + str role; - newstr_init( &role ); + str_init( &role ); nfields = fields_num( f ); for ( n=0; n<ntypes; ++n ) { for ( i=0; i<nfields; ++i ) { if ( fields_level( f, i )!=level ) continue; if ( f->data[i].len==0 ) continue; f_asis = f_corp = f_conf = 0; - newstr_strcpy( &role, f->tag[i].data ); - if ( newstr_findreplace( &role, ":ASIS", "" )) f_asis=1; - if ( newstr_findreplace( &role, ":CORP", "" )) f_corp=1; - if ( newstr_findreplace( &role, ":CONF", "" )) f_conf=1; + str_strcpyc( &role, f->tag[i].data ); + if ( str_findreplace( &role, ":ASIS", "" )) f_asis=1; + if ( str_findreplace( &role, ":CORP", "" )) f_corp=1; + if ( str_findreplace( &role, ":CONF", "" )) f_conf=1; if ( strcasecmp( role.data, names[n].internal ) ) continue; if ( f_asis ) { - output_tab0( outptr, level ); - fprintf( outptr, "<name>\n" ); - output_fill2( outptr, increment_level(level,1), "namePart", f, i, 1 ); + output_tag( outptr, lvl2indent(level), "name", NULL, TAG_OPEN, TAG_NEWLINE, NULL ); + output_fil( outptr, lvl2indent(incr_level(level,1)), "namePart", f, i, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); } else if ( f_corp ) { - output_tab0( outptr, level ); - fprintf( outptr, "<name type=\"corporate\">\n" ); - output_fill2( outptr, increment_level(level,1), "namePart", f, i, 1 ); + output_tag( outptr, lvl2indent(level), "name", NULL, TAG_OPEN, TAG_NEWLINE, "type", "corporate", NULL ); + output_fil( outptr, lvl2indent(incr_level(level,1)), "namePart", f, i, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); } else if ( f_conf ) { - output_tab0( outptr, level ); - fprintf( outptr, "<name type=\"conference\">\n" ); - output_fill2( outptr, increment_level(level,1), "namePart", f, i, 1 ); + output_tag( outptr, lvl2indent(level), "name", NULL, TAG_OPEN, TAG_NEWLINE, "type", "conference", NULL ); + output_fil( outptr, lvl2indent(incr_level(level,1)), "namePart", f, i, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); } else { output_name(outptr, f->data[i].data, level); } - output_tab1( outptr, increment_level(level,1), "<role>\n" ); - output_tab1( outptr, increment_level(level,2), "<roleTerm" ); + output_tag( outptr, lvl2indent(incr_level(level,1)), "role", NULL, TAG_OPEN, TAG_NEWLINE, NULL ); if ( names[n].code & MARC_AUTHORITY ) - fprintf( outptr, " authority=\"marcrelator\""); - fprintf( outptr, " type=\"text\">"); - fprintf( outptr, "%s", names[n].mods ); - fprintf( outptr, "</roleTerm>\n"); - output_tab1( outptr, increment_level(level,1), "</role>\n" ); - output_tab1( outptr, level, "</name>\n" ); + output_tag( outptr, lvl2indent(incr_level(level,2)), "roleTerm", names[n].mods, TAG_OPENCLOSE, TAG_NEWLINE, "authority", "marcrelator", "type", "text", NULL ); + else + output_tag( outptr, lvl2indent(incr_level(level,2)), "roleTerm", names[n].mods, TAG_OPENCLOSE, TAG_NEWLINE, "type", "text", NULL ); + output_tag( outptr, lvl2indent(incr_level(level,1)), "role", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); + output_tag( outptr, lvl2indent(level), "name", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); fields_setused( f, i ); } } - newstr_free( &role ); + str_free( &role ); } +/* datepos[ NUM_DATE_TYPES ] + * use define to ensure that the array and loops don't get out of sync + * datepos[0] -> DATE:YEAR/PARTDATE:YEAR + * datepos[1] -> DATE:MONTH/PARTDATE:MONTH + * datepos[2] -> DATE:DAY/PARTDATE:DAY + * datepos[3] -> DATE/PARTDATE + */ +#define DATE_YEAR (0) +#define DATE_MONTH (1) +#define DATE_DAY (2) +#define DATE_ALL (3) +#define NUM_DATE_TYPES (4) + static int -output_finddateissued( fields *f, int level, int pos[] ) +find_datepos( fields *f, int level, unsigned char use_altnames, int datepos[NUM_DATE_TYPES] ) { - char *src_names[] = { "YEAR", "MONTH", "DAY", "DATE" }; - char *alt_names[] = { "PARTYEAR", "PARTMONTH", "PARTDAY", "PARTDATE" }; - int i, found = -1, ntypes = 4; + char *src_names[] = { "DATE:YEAR", "DATE:MONTH", "DATE:DAY", "DATE" }; + char *alt_names[] = { "PARTDATE:YEAR", "PARTDATE:MONTH", "PARTDATE:DAY", "PARTDATE" }; + int found = 0; + int i; - for ( i=0; i<ntypes; ++i ) { - pos[i] = fields_find( f, src_names[i], level ); - if ( pos[i]!=-1 ) found = pos[i]; - } - /* for LEVEL_MAIN, do what it takes to find a date */ - if ( found==-1 && level==0 ) { - for ( i=0; i<ntypes; ++i ) { - pos[i] = fields_find( f, src_names[i], -1 ); - if ( pos[i]!=-1 ) found = pos[i]; - } - } - if ( found==-1 && level==0 ) { - for ( i=0; i<ntypes; ++i ) { - pos[i] = fields_find( f, alt_names[i], -1 ); - if ( pos[i]!=-1 ) found = pos[i]; - } + for ( i=0; i<NUM_DATE_TYPES; ++i ) { + if ( !use_altnames ) + datepos[i] = fields_find( f, src_names[i], level ); + else + datepos[i] = fields_find( f, alt_names[i], level ); + if ( datepos[i]!=-1 ) found = 1; } + return found; } -static void -output_datepieces( fields *f, FILE *outptr, int pos[4] ) +/* find_dateinfo() + * + * fill datepos[] array with position indexes to date information in fields *f + * + * when generating dates for LEVEL_MAIN, first look at level=LEVEL_MAIN, but if that + * fails, use LEVEL_ANY (-1) + * + * returns 1 if date information found, 0 otherwise + */ +static int +find_dateinfo( fields *f, int level, int datepos[ NUM_DATE_TYPES ] ) { - int nprinted = 0, i; - for ( i=0; i<3 && pos[i]!=-1; ++i ) { - if ( nprinted>0 ) fprintf( outptr, "-" ); - if ( i>0 && f->data[pos[i]].len==1 ) - fprintf( outptr, "0" ); /*zero pad Jan,Feb,etc*/ - fprintf( outptr,"%s",f->data[pos[i]].data ); - nprinted++; - fields_setused( f, pos[i] ); + int found; + + /* default to finding date information for the current level */ + found = find_datepos( f, level, 0, datepos ); + + /* for LEVEL_MAIN, do whatever it takes to find a date */ + if ( !found && level == LEVEL_MAIN ) { + found = find_datepos( f, -1, 0, datepos ); } + if ( !found && level == LEVEL_MAIN ) { + found = find_datepos( f, -1, 1, datepos ); + } + + return found; } static void -output_dateall( fields *f, FILE *outptr, int pos ) +output_datepieces( fields *f, FILE *outptr, int pos[ NUM_DATE_TYPES ] ) { - fprintf( outptr, "%s", f->data[pos].data ); - fields_setused( f, pos ); + str *s; + int i; + + for ( i=0; i<3 && pos[i]!=-1; ++i ) { + if ( i>0 ) fprintf( outptr, "-" ); + /* zero pad month or days written as "1", "2", "3" ... */ + if ( i==DATE_MONTH || i==DATE_DAY ) { + s = fields_value( f, pos[i], FIELDS_STRP_NOUSE ); + if ( s->len==1 ) { + fprintf( outptr, "0" ); + } + } + fprintf( outptr, "%s", (char *) fields_value( f, pos[i], FIELDS_CHRP ) ); + } } static void -output_dateissued( fields *f, FILE *outptr, int level, int pos[4] ) +output_dateissued( fields *f, FILE *outptr, int level, int pos[ NUM_DATE_TYPES ] ) { - output_tab1( outptr, increment_level(level,1), "<dateIssued>" ); - if ( pos[0]!=-1 || pos[1]!=-1 || pos[2]!=-1 ) { + output_tag( outptr, lvl2indent(incr_level(level,1)), "dateIssued", NULL, TAG_OPEN, TAG_NONEWLINE, NULL ); + if ( pos[ DATE_YEAR ]!=-1 || pos[ DATE_MONTH ]!=-1 || pos[ DATE_DAY ]!=-1 ) { output_datepieces( f, outptr, pos ); } else { - output_dateall( f, outptr, pos[3] ); + fprintf( outptr, "%s", (char *) fields_value( f, pos[ DATE_ALL ], FIELDS_CHRP ) ); } fprintf( outptr, "</dateIssued>\n" ); } @@ -382,73 +444,83 @@ static void output_origin( fields *f, FILE *outptr, int level ) { - convert origin[] = { - { "issuance", "ISSUANCE", 0 }, - { "publisher", "PUBLISHER", 0 }, - { "place", "ADDRESS", 1 }, - { "place", "AUTHORADDRESS", 0 }, - { "edition", "EDITION", 0 }, - { "dateCaptured", "URLDATE", 0 } + convert parts[] = { + { "issuance", "ISSUANCE", 0, 0 }, + { "publisher", "PUBLISHER", 0, 0 }, + { "place", "ADDRESS", 0, 1 }, + { "place", "AUTHORADDRESS", 0, 0 }, + { "edition", "EDITION", 0, 0 }, + { "dateCaptured", "URLDATE", 0, 0 } }; - int n, ntypes = sizeof( origin ) / sizeof ( convert ); - int found, datefound, pos[5], date[4]; + int nparts = sizeof( parts ) / sizeof( parts[0] ); + int i, found, datefound, datepos[ NUM_DATE_TYPES ]; - /* find all information to be outputted */ - found = -1; - for ( n=0; n<ntypes; ++n ) { - pos[n] = fields_find( f, origin[n].internal, level ); - if ( pos[n]!=-1 ) found = pos[n]; - } - datefound = output_finddateissued( f, level, date ); - if ( found==-1 && datefound==-1 ) return; + found = convert_findallfields( f, parts, nparts, level ); + datefound = find_dateinfo( f, level, datepos ); + if ( !found && !datefound ) return; - output_tab1( outptr, level, "<originInfo>\n" ); - output_fill2( outptr, increment_level(level,1), "issuance", f, pos[0], 1 ); - if ( datefound!=-1 ) output_dateissued( f, outptr, level, date ); - for ( n=1; n<ntypes; n++ ) { - if ( pos[n]==-1 ) continue; - output_tab0( outptr, increment_level(level,1) ); - fprintf( outptr, "<%s", origin[n].mods ); - fprintf( outptr, ">" ); - if ( origin[n].code ) { - fprintf( outptr, "\n" ); - output_fill4( outptr, increment_level(level,2), - "placeTerm", "type", "text", f, pos[n], 1 ); - output_tab0( outptr, increment_level(level,1) ); - } else { - fprintf( outptr, "%s", f->data[pos[n]].data ); - fields_setused( f, pos[n] ); + output_tag( outptr, lvl2indent(level), "originInfo", NULL, TAG_OPEN, TAG_NEWLINE, NULL ); + + /* issuance must precede date */ + if ( parts[0].pos!=-1 ) + output_fil( outptr, lvl2indent(incr_level(level,1)), "issuance", f, parts[0].pos, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + + /* date */ + if ( datefound ) + output_dateissued( f, outptr, level, datepos ); + + /* rest of the originInfo elements */ + for ( i=1; i<nparts; i++ ) { + + /* skip missing originInfo elements */ + if ( parts[i].pos==-1 ) continue; + + /* normal originInfo element */ + if ( parts[i].code==0 ) { + output_fil( outptr, lvl2indent(incr_level(level,1)), parts[i].mods, f, parts[i].pos, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); } - fprintf( outptr, "</%s>\n", origin[n].mods ); + + /* originInfo with placeTerm info */ + else { + output_tag( outptr, lvl2indent(incr_level(level,1)), parts[i].mods, NULL, TAG_OPEN, TAG_NEWLINE, NULL ); + output_fil( outptr, lvl2indent(incr_level(level,2)), "placeTerm", f, parts[i].pos, TAG_OPENCLOSE, TAG_NEWLINE, "type", "text", NULL ); + output_tag( outptr, lvl2indent(incr_level(level,1)), parts[i].mods, NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); + } } - output_tab1( outptr, level, "</originInfo>\n" ); + + output_tag( outptr, lvl2indent(level), "originInfo", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); } +/* output_language_core() + * + * generates language output for tag="langauge" or tag="languageOfCataloging" + * if possible, outputs iso639-2b code for the language + * + * <language> + * <languageTerm type="text">xxx</languageTerm> + * </language> + * + * <language> + * <languageTerm type="text">xxx</languageTerm> + * <languageTerm type="code" authority="iso639-2b">xxx</languageTerm> + * </language> + * + */ static void output_language_core( fields *f, int n, FILE *outptr, char *tag, int level ) { - newstr usetag; char *lang, *code; - lang = fields_value( f, n, FIELDS_CHRP ); + + lang = (char *) fields_value( f, n, FIELDS_CHRP ); code = iso639_2_from_language( lang ); - newstr_init( &usetag ); - newstr_addchar( &usetag, '<' ); - newstr_strcat( &usetag, tag ); - newstr_strcat( &usetag, ">\n" ); - output_tab1( outptr, level, usetag.data ); - output_fill4( outptr, increment_level(level,1), - "languageTerm", "type", "text", f, n, 1 ); + + output_tag( outptr, lvl2indent(level), tag, NULL, TAG_OPEN, TAG_NEWLINE, NULL ); + output_tag( outptr, lvl2indent(incr_level(level,1)), "languageTerm", lang, TAG_OPENCLOSE, TAG_NEWLINE, "type", "text", NULL ); if ( code ) { - output_tab6( outptr, increment_level(level,1), - "languageTerm", "type", "code", "authority", "iso639-2b", - code, 1 ); + output_tag( outptr, lvl2indent(incr_level(level,1)), "languageTerm", code, TAG_OPENCLOSE, TAG_NEWLINE, "type", "code", "authority", "iso639-2b", NULL ); } - newstr_strcpy( &usetag, "</" ); - newstr_strcat( &usetag, tag ); - newstr_strcat( &usetag, ">\n" ); - output_tab1( outptr, level, usetag.data ); - newstr_free( &usetag ); + output_tag( outptr, lvl2indent(level), tag, NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); } static void @@ -463,19 +535,29 @@ static void output_description( fields *f, FILE *outptr, int level ) { - int n = fields_find( f, "DESCRIPTION", level ); + char *val; + int n; + + n = fields_find( f, "DESCRIPTION", level ); if ( n!=-1 ) { - output_tab1( outptr, level, "<physicalDescription>\n" ); - output_fill2( outptr, increment_level(level,1), "note", f, n, 1 ); - output_tab1( outptr, level, "</physicalDescription>\n" ); + val = ( char * ) fields_value( f, n, FIELDS_CHRP ); + output_tag( outptr, lvl2indent(level), "physicalDescription", NULL, TAG_OPEN, TAG_NEWLINE, NULL ); + output_tag( outptr, lvl2indent(incr_level(level,1)), "note", val, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + output_tag( outptr, lvl2indent(level), "physicalDescription", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); } } static void output_toc( fields *f, FILE *outptr, int level ) { - int n = fields_find( f, "CONTENTS", level ); - output_fill2( outptr, level, "tableOfContents", f, n, 1 ); + char *val; + int n; + + n = fields_find( f, "CONTENTS", level ); + if ( n!=-1 ) { + val = (char *) fields_value( f, n, FIELDS_CHRP ); + output_tag( outptr, lvl2indent(level), "tableOfContents", val, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + } } /* detail output @@ -485,14 +567,13 @@ * <detail type="volume"><number>xxx</number></detail */ static void -mods_output_detail( fields *f, FILE *outptr, int item, char *item_name, - int level ) +mods_output_detail( fields *f, FILE *outptr, int n, char *item_name, int level ) { - if ( item==-1 ) return; - output_tab0( outptr, increment_level( level, 1 ) ); - fprintf( outptr, "<detail type=\"%s\"><number>%s</number></detail>\n", - item_name, f->data[item].data ); - fields_setused( f, item ); + if ( n!=-1 ) { + output_tag( outptr, lvl2indent(incr_level(level,1)), "detail", NULL, TAG_OPEN, TAG_NONEWLINE, "type", item_name, NULL ); + output_fil( outptr, 0, "number", f, n, TAG_OPENCLOSE, TAG_NONEWLINE, NULL ); + output_tag( outptr, 0, "detail", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); + } } @@ -504,27 +585,38 @@ * </extent> */ static void -mods_output_extents( fields *f, FILE *outptr, int start, int end, - int total, char *extype, int level ) +mods_output_extents( fields *f, FILE *outptr, int start, int end, int total, char *extype, int level ) { - output_tab0( outptr, increment_level(level,1) ); - fprintf( outptr, "<extent unit=\"%s\">\n", extype); - output_fill2( outptr, increment_level(level,2), "start", f, start, 1 ); - output_fill2( outptr, increment_level(level,2), "end", f, end, 1 ); - output_fill2( outptr, increment_level(level,2), "total", f, total, 1 ); - output_tab1 ( outptr, increment_level(level,1), "</extent>\n" ); + char *val; + + output_tag( outptr, lvl2indent(incr_level(level,1)), "extent", NULL, TAG_OPEN, TAG_NEWLINE, "unit", extype, NULL ); + if ( start!=-1 ) { + val = (char *) fields_value( f, start, FIELDS_CHRP ); + output_tag( outptr, lvl2indent(incr_level(level,2)), "start", val, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + } + if ( end!=-1 ) { + val = (char *) fields_value( f, end, FIELDS_CHRP ); + output_tag( outptr, lvl2indent(incr_level(level,2)), "end", val, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + } + if ( total!=-1 ) { + val = (char *) fields_value( f, total, FIELDS_CHRP ); + output_tag( outptr, lvl2indent(incr_level(level,2)), "total", val, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + } + output_tag( outptr, lvl2indent(incr_level(level,1)), "extent", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); } static void try_output_partheader( FILE *outptr, int wrote_header, int level ) { - if ( !wrote_header ) output_tab1( outptr, level, "<part>\n" ); + if ( !wrote_header ) + output_tag( outptr, lvl2indent(level), "part", NULL, TAG_OPEN, TAG_NEWLINE, NULL ); } static void try_output_partfooter( FILE *outptr, int wrote_header, int level ) { - if ( wrote_header ) output_tab1( outptr, level, "</part>\n" ); + if ( wrote_header ) + output_tag( outptr, lvl2indent(level), "part", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); } /* part date output @@ -535,33 +627,31 @@ static int output_partdate( fields *f, FILE *outptr, int level, int wrote_header ) { - convert parts[3] = { - { "", "PARTYEAR", -1 }, - { "", "PARTMONTH", -1 }, - { "", "PARTDAY", -1 }, + convert parts[] = { + { "", "PARTDATE:YEAR", 0, 0 }, + { "", "PARTDATE:MONTH", 0, 0 }, + { "", "PARTDATE:DAY", 0, 0 }, }; int nparts = sizeof(parts)/sizeof(parts[0]); - if ( !find_alltags( f, parts, nparts, level ) ) return 0; + if ( !convert_findallfields( f, parts, nparts, level ) ) return 0; try_output_partheader( outptr, wrote_header, level ); - output_tab1( outptr, increment_level(level,1), "<date>" ); - if ( parts[0].code!=-1 ) { - fprintf( outptr, "%s", f->data[ parts[0].code ].data); - fields_setused( f, parts[0].code ); + output_tag( outptr, lvl2indent(incr_level(level,1)), "date", NULL, TAG_OPEN, TAG_NONEWLINE, NULL ); + + if ( parts[0].pos!=-1 ) { + fprintf( outptr, "%s", (char *) fields_value( f, parts[0].pos, FIELDS_CHRP ) ); } else fprintf( outptr, "XXXX" ); - if ( parts[1].code!=-1 ) { - fprintf( outptr, "-%s", f->data[parts[1].code].data ); - fields_setused( f, parts[1].code ); + if ( parts[1].pos!=-1 ) { + fprintf( outptr, "-%s", (char *) fields_value( f, parts[1].pos, FIELDS_CHRP ) ); } - if ( parts[2].code!=-1 ) { - if ( parts[1].code!=-1 ) fprintf( outptr, "-" ); - else fprintf( outptr, "-XX-" ); - fprintf( outptr, "%s", f->data[parts[2].code].data ); - fields_setused( f, parts[2].code ); + if ( parts[2].pos!=-1 ) { + if ( parts[1].pos==-1 ) + fprintf( outptr, "-XX" ); + fprintf( outptr, "-%s", (char *) fields_value( f, parts[2].pos, FIELDS_CHRP ) ); } fprintf( outptr,"</date>\n"); @@ -572,37 +662,32 @@ static int output_partpages( fields *f, FILE *outptr, int level, int wrote_header ) { - convert parts[4] = { - { "", "PAGESTART", -1 }, - { "", "PAGEEND", -1 }, - { "", "PAGES", -1 }, - { "", "TOTALPAGES", -1 } + convert parts[] = { + { "", "PAGES:START", 0, 0 }, + { "", "PAGES:STOP", 0, 0 }, + { "", "PAGES", 0, 0 }, + { "", "PAGES:TOTAL", 0, 0 } }; int nparts = sizeof(parts)/sizeof(parts[0]); - if ( !find_alltags( f, parts, nparts, level ) ) return 0; + if ( !convert_findallfields( f, parts, nparts, level ) ) return 0; try_output_partheader( outptr, wrote_header, level ); - /* If PAGESTART or PAGEEND are undefined */ - if ( parts[0].code==-1 || parts[1].code==-1 ) { - if ( parts[0].code!=-1 ) - mods_output_detail( f, outptr, parts[0].code, - "page", level ); - if ( parts[1].code!=-1 ) - mods_output_detail( f, outptr, parts[1].code, - "page", level ); - if ( parts[2].code!=-1 ) - mods_output_detail( f, outptr, parts[2].code, - "page", level ); - if ( parts[3].code!=-1 ) - mods_output_extents( f, outptr, -1, -1, - parts[3].code, "page", level ); + /* If PAGES:START or PAGES:STOP are undefined */ + if ( parts[0].pos==-1 || parts[1].pos==-1 ) { + if ( parts[0].pos!=-1 ) + mods_output_detail( f, outptr, parts[0].pos, "page", level ); + if ( parts[1].pos!=-1 ) + mods_output_detail( f, outptr, parts[1].pos, "page", level ); + if ( parts[2].pos!=-1 ) + mods_output_detail( f, outptr, parts[2].pos, "page", level ); + if ( parts[3].pos!=-1 ) + mods_output_extents( f, outptr, -1, -1, parts[3].pos, "page", level ); } - /* If both PAGESTART and PAGEEND are defined */ + /* If both PAGES:START and PAGES:STOP are defined */ else { - mods_output_extents( f, outptr, parts[0].code, - parts[1].code, parts[3].code, "page", level ); + mods_output_extents( f, outptr, parts[0].pos, parts[1].pos, parts[3].pos, "page", level ); } return 1; @@ -612,34 +697,32 @@ output_partelement( fields *f, FILE *outptr, int level, int wrote_header ) { convert parts[] = { - { "volume", "VOLUME", -1 }, - { "section", "SECTION", -1 }, - { "issue", "ISSUE", -1 }, - { "number", "NUMBER", -1 }, - { "publiclawnumber", "PUBLICLAWNUMBER", -1 }, - { "session", "SESSION", -1 }, - { "articlenumber", "ARTICLENUMBER", -1 }, - { "part", "PART", -1 }, - { "chapter", "CHAPTER", -1 }, - { "report number", "REPORTNUMBER", -1 }, + { "", "NUMVOLUMES", 0, 0 }, + { "volume", "VOLUME", 0, 0 }, + { "section", "SECTION", 0, 0 }, + { "issue", "ISSUE", 0, 0 }, + { "number", "NUMBER", 0, 0 }, + { "publiclawnumber", "PUBLICLAWNUMBER", 0, 0 }, + { "session", "SESSION", 0, 0 }, + { "articlenumber", "ARTICLENUMBER", 0, 0 }, + { "part", "PART", 0, 0 }, + { "chapter", "CHAPTER", 0, 0 }, + { "report number", "REPORTNUMBER", 0, 0 }, }; - int i, nparts = sizeof( parts ) / sizeof( convert ), n; + int i, nparts = sizeof( parts ) / sizeof( convert ); - n = fields_find( f, "NUMVOLUMES", level ); - if ( !find_alltags( f, parts, nparts, level ) && n==-1 ) return 0; + if ( !convert_findallfields( f, parts, nparts, level ) ) return 0; + try_output_partheader( outptr, wrote_header, level ); - for ( i=0; i<nparts; ++i ) { - if ( parts[i].code==-1 ) continue; - mods_output_detail( f, outptr, parts[i].code, parts[i].mods, - level ); + /* start loop at 1 to skip NUMVOLUMES */ + for ( i=1; i<nparts; ++i ) { + if ( parts[i].pos==-1 ) continue; + mods_output_detail( f, outptr, parts[i].pos, parts[i].mods, level ); } - if ( n!=-1 ) { - output_tab1( outptr, level, "<extent unit=\"volumes\">\n" ); - output_fill2( outptr, increment_level(level,1), "total", f, n, 1 ); - output_tab1( outptr, level, "</extent>\n" ); - } + if ( parts[0].pos!=-1 ) + mods_output_extents( f, outptr, -1, -1, parts[0].pos, "volumes", level ); return 1; } @@ -660,66 +743,78 @@ int n; n = fields_find( f, "LANGCATALOG", level ); if ( n!=-1 ) { - output_tab1( outptr, level, "<recordInfo>\n" ); - output_language_core( f, n, outptr, "languageOfCataloging", increment_level(level,1) ); - output_tab1( outptr, level, "</recordInfo>\n" ); + output_tag( outptr, lvl2indent(level), "recordInfo", NULL, TAG_OPEN, TAG_NEWLINE, NULL ); + output_language_core( f, n, outptr, "languageOfCataloging", incr_level(level,1) ); + output_tag( outptr, lvl2indent(level), "recordInfo", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); } } +/* output_genre() + * + * <genre authority="marcgt">thesis</genre> + * <genre>Diploma thesis</genre> + */ static void output_genre( fields *f, FILE *outptr, int level ) { - int i, ismarc, n; - char *value; + char *value, *attr, *attrvalue="marcgt"; + int i, n; + n = fields_num( f ); for ( i=0; i<n; ++i ) { if ( fields_level( f, i ) != level ) continue; - if ( !fields_match_tag( f, i, "GENRE" ) && - !fields_match_tag( f, i, "NGENRE" ) ) - continue; + if ( !fields_match_tag( f, i, "GENRE" ) && !fields_match_tag( f, i, "NGENRE" ) ) continue; value = fields_value( f, i, FIELDS_CHRP ); - if ( marc_findgenre( value )!=-1 ) ismarc = 1; - else ismarc = 0; - output_tab1( outptr, level, "<genre" ); - if ( ismarc ) - fprintf( outptr, " authority=\"marcgt\"" ); - fprintf( outptr, ">%s</genre>\n", value ); - fields_setused( f, i ); + attr = ( marc_findgenre( value ) == -1 ) ? NULL : "authority"; + output_tag( outptr, lvl2indent(level), "genre", value, TAG_OPENCLOSE, TAG_NEWLINE, attr, attrvalue, NULL ); } } +/* output_resource() + * + * <typeOfResource>text</typeOfResource> + */ static void -output_typeresource( fields *f, FILE *outptr, int level ) +output_resource( fields *f, FILE *outptr, int level ) { - int n, ismarc = 0; char *value; + int n; + n = fields_find( f, "RESOURCE", level ); if ( n!=-1 ) { value = fields_value( f, n, FIELDS_CHRP ); - if ( marc_findresource( value )!=-1 ) ismarc = 1; - if ( !ismarc ) { - fprintf( stderr, "Illegal typeofResource = '%s'\n", value ); + if ( marc_findresource( value )!=-1 ) { + output_fil( outptr, lvl2indent(level), "typeOfResource", f, n, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); } else { - output_fill2( outptr, level, "typeOfResource", f, n, 1 ); + fprintf( stderr, "Illegal typeofResource = '%s'\n", value ); } - fields_setused( f, n ); } } static void output_type( fields *f, FILE *outptr, int level ) { - int n = fields_find( f, "INTERNAL_TYPE", 0 ); + int n; + + /* silence warnings about INTERNAL_TYPE being unused */ + n = fields_find( f, "INTERNAL_TYPE", 0 ); if ( n!=-1 ) fields_setused( f, n ); - output_typeresource( f, outptr, level ); + + output_resource( f, outptr, level ); output_genre( f, outptr, level ); } +/* output_abs() + * + * <abstract>xxxx</abstract> + */ static void output_abs( fields *f, FILE *outptr, int level ) { - int nabs = fields_find( f, "ABSTRACT", level ); - output_fill2( outptr, level, "abstract", f, nabs, 1 ); + int n; + + n = fields_find( f, "ABSTRACT", level ); + output_fil( outptr, lvl2indent(level), "abstract", f, n, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); } static void @@ -727,39 +822,52 @@ { int i, n; char *t; + n = fields_num( f ); for ( i=0; i<n; ++i ) { if ( fields_level( f, i ) != level ) continue; t = fields_tag( f, i, FIELDS_CHRP_NOUSE ); if ( !strcasecmp( t, "NOTES" ) ) - output_fill2( outptr, level, "note", f, i, 1 ); + output_fil( outptr, lvl2indent(level), "note", f, i, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); else if ( !strcasecmp( t, "PUBSTATE" ) ) - output_fill4( outptr, level, "note", "type", "publication status", f, i, 1 ); + output_fil( outptr, lvl2indent(level), "note", f, i, TAG_OPENCLOSE, TAG_NEWLINE, "type", "publication status", NULL ); else if ( !strcasecmp( t, "ANNOTE" ) ) - output_fill2( outptr, level, "bibtex-annote", f, i, 1 ); + output_fil( outptr, lvl2indent(level), "bibtex-annote", f, i, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); else if ( !strcasecmp( t, "TIMESCITED" ) ) - output_fill4( outptr, level, "note", "type", "times cited", f, i, 1 ); + output_fil( outptr, lvl2indent(level), "note", f, i, TAG_OPENCLOSE, TAG_NEWLINE, "type", "times cited", NULL ); else if ( !strcasecmp( t, "ANNOTATION" ) ) - output_fill4( outptr, level, "note", "type", "annotation", f, i, 1 ); + output_fil( outptr, lvl2indent(level), "note", f, i, TAG_OPENCLOSE, TAG_NEWLINE, "type", "annotation", NULL ); else if ( !strcasecmp( t, "ADDENDUM" ) ) - output_fill4( outptr, level, "note", "type", "addendum", f, i, 1 ); + output_fil( outptr, lvl2indent(level), "note", f, i, TAG_OPENCLOSE, TAG_NEWLINE, "type", "addendum", NULL ); else if ( !strcasecmp( t, "BIBKEY" ) ) - output_fill4( outptr, level, "note", "type", "bibliography key", f, i, 1 ); + output_fil( outptr, lvl2indent(level), "note", f, i, TAG_OPENCLOSE, TAG_NEWLINE, "type", "bibliography key", NULL ); } } +/* output_key() + * + * <subject> + * <topic>xxxx</topic> + * </subject> + */ static void output_key( fields *f, FILE *outptr, int level ) { int i, n; + n = fields_num( f ); for ( i=0; i<n; ++i ) { if ( fields_level( f, i ) != level ) continue; if ( !strcasecmp( f->tag[i].data, "KEYWORD" ) ) { - output_tab1( outptr, level, "<subject>\n" ); - output_fill2( outptr, increment_level(level,1), "topic", f, i, 1 ); - output_tab1( outptr, level, "</subject>\n" ); + output_tag( outptr, lvl2indent(level), "subject", NULL, TAG_OPEN, TAG_NEWLINE, NULL ); + output_fil( outptr, lvl2indent(incr_level(level,1)), "topic", f, i, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + output_tag( outptr, lvl2indent(level), "subject", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); } + else if ( !strcasecmp( f->tag[i].data, "EPRINTCLASS" ) ) { + output_tag( outptr, lvl2indent(level), "subject", NULL, TAG_OPEN, TAG_NEWLINE, NULL ); + output_fil( outptr, lvl2indent(incr_level(level,1)), "topic", f, i, TAG_OPENCLOSE, TAG_NEWLINE, "class", "primary", NULL ); + output_tag( outptr, lvl2indent(level), "subject", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); + } } } @@ -767,89 +875,92 @@ output_sn( fields *f, FILE *outptr, int level ) { convert sn_types[] = { - { "isbn", "ISBN", 0 }, - { "isbn", "ISBN13", 0 }, - { "lccn", "LCCN", 0 }, - { "issn", "ISSN", 0 }, - { "citekey", "REFNUM", 0 }, - { "doi", "DOI", 0 }, - { "eid", "EID", 0 }, - { "eprint", "EPRINT", 0 }, - { "eprinttype","EPRINTTYPE",0 }, - { "pubmed", "PMID", 0 }, - { "medline", "MEDLINE", 0 }, - { "pii", "PII", 0 }, - { "arXiv", "ARXIV", 0 }, - { "isi", "ISIREFNUM", 0 }, - { "accessnum", "ACCESSNUM", 0 }, - { "jstor", "JSTOR", 0 }, - { "isrn", "ISRN", 0 }, + { "isbn", "ISBN", 0, 0 }, + { "isbn", "ISBN13", 0, 0 }, + { "lccn", "LCCN", 0, 0 }, + { "issn", "ISSN", 0, 0 }, + { "coden", "CODEN", 0, 0 }, + { "citekey", "REFNUM", 0, 0 }, + { "doi", "DOI", 0, 0 }, + { "eid", "EID", 0, 0 }, + { "eprint", "EPRINT", 0, 0 }, + { "eprinttype","EPRINTTYPE",0, 0 }, + { "pubmed", "PMID", 0, 0 }, + { "MRnumber", "MRNUMBER", 0, 0 }, + { "medline", "MEDLINE", 0, 0 }, + { "pii", "PII", 0, 0 }, + { "pmc", "PMC", 0, 0 }, + { "arXiv", "ARXIV", 0, 0 }, + { "isi", "ISIREFNUM", 0, 0 }, + { "accessnum", "ACCESSNUM", 0, 0 }, + { "jstor", "JSTOR", 0, 0 }, + { "isrn", "ISRN", 0, 0 }, }; - int n, ntypes = sizeof( sn_types ) / sizeof( sn_types[0] ); - int found, i, nfields; + int ntypes = sizeof( sn_types ) / sizeof( sn_types[0] ); + int i, n; - found = fields_find ( f, "CALLNUMBER", level ); - output_fill2( outptr, level, "classification", f, found, 1 ); + /* output call number */ + n = fields_find( f, "CALLNUMBER", level ); + output_fil( outptr, lvl2indent(level), "classification", f, n, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); - for ( n=0; n<ntypes; ++n ) { - found = fields_find( f, sn_types[n].internal, level ); - if ( found==-1 ) continue; - output_tab0( outptr, level ); - fprintf( outptr, "<identifier type=\"%s\">%s</identifier>\n", - sn_types[n].mods, - f->data[found].data - ); - fields_setused( f, found ); + /* output specialized serialnumber */ + convert_findallfields( f, sn_types, ntypes, level ); + for ( i=0; i<ntypes; ++i ) { + if ( sn_types[i].pos==-1 ) continue; + output_fil( outptr, lvl2indent(level), "identifier", f, sn_types[i].pos, TAG_OPENCLOSE, TAG_NEWLINE, "type", sn_types[i].mods, NULL ); } - nfields = fields_num( f ); - for ( i=0; i<nfields; ++i ) { + + /* output _all_ elements of type SERIALNUMBER */ + n = fields_num( f ); + for ( i=0; i<n; ++i ) { if ( f->level[i]!=level ) continue; - if ( !strcasecmp( f->tag[i].data, "SERIALNUMBER" ) ) { - output_tab0( outptr, level ); - fprintf( outptr, "<identifier type=\"%s\">%s</identifier>\n", - "serial number", f->data[i].data ); - fields_setused( f, i ); - } + if ( strcasecmp( f->tag[i].data, "SERIALNUMBER" ) ) continue; + output_fil( outptr, lvl2indent(level), "identifier", f, i, TAG_OPENCLOSE, TAG_NEWLINE, "type", "serial number", NULL ); } } +/* output_url() + * + * <location> + * <url>URL</url> + * <url urlType="pdf">PDFLINK</url> + * <url displayLabel="Electronic full text" access="raw object">PDFLINK</url> + * <physicalLocation>LOCATION</physicalLocation> + * </location> + */ static void output_url( fields *f, FILE *outptr, int level ) { - int location = fields_find( f, "LOCATION", level ); - int url = fields_find( f, "URL", level ); + int location = fields_find( f, "LOCATION", level ); + int url = fields_find( f, "URL", level ); int fileattach = fields_find( f, "FILEATTACH", level ); - int pdflink = fields_find( f, "PDFLINK", level ); + int pdflink = fields_find( f, "PDFLINK", level ); int i, n; + if ( url==-1 && location==-1 && pdflink==-1 && fileattach==-1 ) return; - output_tab1( outptr, level, "<location>\n" ); + output_tag( outptr, lvl2indent(level), "location", NULL, TAG_OPEN, TAG_NEWLINE, NULL ); + n = fields_num( f ); for ( i=0; i<n; ++i ) { if ( f->level[i]!=level ) continue; - if ( !strcasecmp( f->tag[i].data, "URL" ) ) { - output_fill2( outptr, increment_level(level,1), "url", f, i, 1 ); - } + if ( strcasecmp( f->tag[i].data, "URL" ) ) continue; + output_fil( outptr, lvl2indent(incr_level(level,1)), "url", f, i, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); } for ( i=0; i<n; ++i ) { if ( f->level[i]!=level ) continue; - if ( !strcasecmp( f->tag[i].data, "PDFLINK" ) ) { - output_fill2( outptr, increment_level(level,1), "url", - /*"urlType", "pdf",*/ f, i, 1 ); - } + if ( strcasecmp( f->tag[i].data, "PDFLINK" ) ) continue; +/* output_fil( outptr, lvl2indent(incr_level(level,1)), "url", f, i, TAG_OPENCLOSE, TAG_NEWLINE, "urlType", "pdf", NULL ); */ + output_fil( outptr, lvl2indent(incr_level(level,1)), "url", f, i, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); } for ( i=0; i<n; ++i ) { if ( f->level[i]!=level ) continue; - if ( !strcasecmp( f->tag[i].data, "FILEATTACH" ) ){ - output_tab0( outptr, increment_level(level,1) ); - fprintf( outptr, "<url displayLabel=\"Electronic full text\" access=\"raw object\">" ); - fprintf( outptr, "%s</url>\n", f->data[i].data ); - fields_setused( f, i ); - } + if ( strcasecmp( f->tag[i].data, "FILEATTACH" ) ) continue; + output_fil( outptr, lvl2indent(incr_level(level,1)), "url", f, i, TAG_OPENCLOSE, TAG_NEWLINE, "displayLabel", "Electronic full text", "access", "raw object", NULL ); } if ( location!=-1 ) - output_fill2( outptr, increment_level(level,1), "physicalLocation", f, - location, 1 ); - output_tab1( outptr, level, "</location>\n" ); + output_fil( outptr, lvl2indent(incr_level(level,1)), "physicalLocation", f, location, TAG_OPENCLOSE, TAG_NEWLINE, NULL ); + + output_tag( outptr, lvl2indent(level), "location", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); } /* refnum should start with a non-number and not include spaces -- ignore this */ @@ -913,20 +1024,16 @@ output_description( f, outptr, level ); if ( level >= 0 && level < max ) { - output_tab0( outptr, level ); - fprintf( outptr, "<relatedItem type=\"host\">\n" ); - output_citeparts( f, outptr, increment_level(level,1), max ); - output_tab0( outptr, level ); - fprintf( outptr, "</relatedItem>\n"); + output_tag( outptr, lvl2indent(level), "relatedItem", NULL, TAG_OPEN, TAG_NEWLINE, "type", "host", NULL ); + output_citeparts( f, outptr, incr_level(level,1), max ); + output_tag( outptr, lvl2indent(level), "relatedItem", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); } /* Look for original item things */ orig_level = original_items( f, level ); if ( orig_level ) { - output_tab0( outptr, level ); - fprintf( outptr, "<relatedItem type=\"original\">\n" ); + output_tag( outptr, lvl2indent(level), "relatedItem", NULL, TAG_OPEN, TAG_NEWLINE, "type", "original", NULL ); output_citeparts( f, outptr, orig_level, max ); - output_tab0( outptr, level ); - fprintf( outptr, "</relatedItem>\n" ); + output_tag( outptr, lvl2indent(level), "relatedItem", NULL, TAG_CLOSE, TAG_NEWLINE, NULL ); } output_abs( f, outptr, level ); output_notes( f, outptr, level ); @@ -957,7 +1064,7 @@ for ( i=0; i<n; ++i ) { if ( fields_level( f, i ) != 0 ) continue; tag = fields_tag( f, i, FIELDS_CHRP_NOUSE ); - if ( strncasecmp( tag, "AUTHOR", 6 ) ) continue; + if ( strcasecmp( tag, "AUTHOR" ) && strcasecmp( tag, "AUTHOR:ASIS" ) && strcasecmp( tag, "AUTHOR:CORP" ) ) continue; value = fields_value( f, i, FIELDS_CHRP_NOUSE ); if ( nwritten==0 ) fprintf( stderr, "\tAuthor(s) (level=0):\n" ); fprintf( stderr, "\t\t'%s'\n", value ); @@ -967,7 +1074,7 @@ for ( i=0; i<n; ++i ) { if ( fields_level( f, i ) != 0 ) continue; tag = fields_tag( f, i, FIELDS_CHRP_NOUSE ); - if ( strcasecmp( tag, "YEAR" ) && strcasecmp( tag, "PARTYEAR" ) ) continue; + if ( strcasecmp( tag, "DATE:YEAR" ) && strcasecmp( tag, "PARTDATE:YEAR" ) ) continue; value = fields_value( f, i, FIELDS_CHRP_NOUSE ); if ( nwritten==0 ) fprintf( stderr, "\tYear(s) (level=0):\n" ); fprintf( stderr, "\t\t'%s'\n", value ); @@ -996,12 +1103,12 @@ } } -void +static int modsout_write( fields *f, FILE *outptr, param *p, unsigned long numrefs ) { int max, dropkey; max = fields_maxlevel( f ); - dropkey = ( p->format_opts & MODSOUT_DROPKEY ); + dropkey = ( p->format_opts & BIBL_FORMAT_MODSOUT_DROPKEY ); output_head( f, outptr, dropkey, numrefs ); output_citeparts( f, outptr, 0, max ); @@ -1009,9 +1116,11 @@ fprintf( outptr, "</mods>\n" ); fflush( outptr ); + + return BIBL_OK; } -void +static void modsout_writeheader( FILE *outptr, param *p ) { if ( p->utf8bom ) utf8_writebom( outptr ); @@ -1020,7 +1129,7 @@ fprintf(outptr,"<modsCollection xmlns=\"http://www.loc.gov/mods/v3\">\n"); } -void +static void modsout_writefooter( FILE *outptr ) { fprintf(outptr,"</modsCollection>\n"); diff --git a/bibutils/modsout.h b/bibutils/modsout.h deleted file mode 100644 --- a/bibutils/modsout.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * modsout.h - * - * Copyright (c) Chris Putnam 2003-2014 - * - * Source code released under the GPL version 2 - * - */ -#ifndef MODSOUT_H -#define MODSOUT_H - -/* format-specific options */ -#define MODSOUT_DROPKEY (2) - -#include <stdio.h> -#include <stdlib.h> -#include "bibl.h" -#include "bibutils.h" - -extern void modsout_writeheader( FILE *outptr, param *p ); -extern void modsout_writefooter( FILE *outptr ); -extern void modsout_write( fields *info, FILE *outptr, - param *p, unsigned long numrefs ); -extern void modsout_initparams( param *p, const char *progname ); - -#endif - diff --git a/bibutils/modstypes.c b/bibutils/modstypes.c --- a/bibutils/modstypes.c +++ b/bibutils/modstypes.c @@ -1,7 +1,7 @@ /* * modstypes.c * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * @@ -16,19 +16,20 @@ * */ convert identifier_types[] = { - { "citekey", "REFNUM" }, - { "issn", "ISSN" }, - { "isbn", "ISBN" }, - { "doi", "DOI" }, - { "url", "URL" }, - { "uri", "URL" }, - { "pubmed", "PUBMED" }, - { "medline", "MEDLINE" }, - { "pii", "PII" }, - { "isi", "ISIREFNUM" }, - { "lccn", "LCCN" }, - { "serial number", "SERIALNUMBER" }, - { "accessnum", "ACCESSNUM" } + { "citekey", "REFNUM" }, + { "issn", "ISSN" }, + { "isbn", "ISBN" }, + { "doi", "DOI" }, + { "url", "URL" }, + { "uri", "URL" }, + { "pubmed", "PMID", }, + { "medline", "MEDLINE" }, + { "pmc", "PMC" }, + { "pii", "PII" }, + { "isi", "ISIREFNUM" }, + { "lccn", "LCCN" }, + { "serial number", "SERIALNUMBER" }, + { "accessnum", "ACCESSNUM" } }; int nidentifier_types = sizeof( identifier_types ) / sizeof( identifier_types[0] ); diff --git a/bibutils/modstypes.h b/bibutils/modstypes.h --- a/bibutils/modstypes.h +++ b/bibutils/modstypes.h @@ -1,7 +1,7 @@ /* * modstypes.h * - * Copyright (c) Chris Putnam 2008-2013 + * Copyright (c) Chris Putnam 2008-2017 * * Source code released under the GPL version 2 * @@ -9,8 +9,9 @@ #ifndef MODSTYPES_H #define MODSTYPES_H typedef struct convert { - char *mods; /* old */ - char *internal; /* new */ + char *mods; /* old */ + char *internal; /* new */ + int pos; int code; } convert; diff --git a/bibutils/name.c b/bibutils/name.c --- a/bibutils/name.c +++ b/bibutils/name.c @@ -3,7 +3,7 @@ * * mangle names w/ and w/o commas * - * Copyright (c) Chris Putnam 2004-2014 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * @@ -14,9 +14,9 @@ #include "utf8.h" #include "unicode.h" #include "is_ws.h" -#include "newstr.h" +#include "str.h" #include "fields.h" -#include "list.h" +#include "slist.h" #include "intlist.h" #include "name.h" @@ -26,12 +26,12 @@ * to 'family suffix, given given */ void -name_build_withcomma( newstr *s, char *p ) +name_build_withcomma( str *s, char *p ) { int nseps = 0, nch; char *suffix, *stopat; - newstr_empty( s ); + str_empty( s ); suffix = strstr( p, "||" ); if ( suffix ) stopat = suffix; @@ -41,18 +41,18 @@ nch = 0; if ( nseps==1 ) { if ( suffix ) { - newstr_addchar( s, ' ' ); - newstr_strcat( s, suffix+2 ); + str_addchar( s, ' ' ); + str_strcatc( s, suffix+2 ); } - newstr_addchar( s, ',' ); + str_addchar( s, ',' ); } - if ( nseps ) newstr_addchar( s, ' ' ); + if ( nseps ) str_addchar( s, ' ' ); while ( p!=stopat && *p!='|' ) { - newstr_addchar( s, *p++ ); + str_addchar( s, *p++ ); nch++; } if ( p!=stopat && *p=='|' ) p++; - if ( nseps!=0 && nch==1 ) newstr_addchar( s, '.' ); + if ( nseps!=0 && nch==1 ) str_addchar( s, '.' ); nseps++; } } @@ -63,14 +63,14 @@ * of name lists. */ int -name_findetal( list *tokens ) +name_findetal( slist *tokens ) { - newstr *s1, *s2; + str *s1, *s2; if ( tokens->n==0 ) return 0; /* ...check last entry for full 'et al.' or variant */ - s2 = list_get( tokens, tokens->n - 1 ); + s2 = slist_str( tokens, tokens->n - 1 ); if ( !strcasecmp( s2->data, "et alia" ) || !strcasecmp( s2->data, "et al." ) || !strcasecmp( s2->data, "et al.," ) || @@ -84,7 +84,7 @@ if ( tokens->n==1 ) return 0; /* ...check last two entries for full 'et' and 'al.' */ - s1 = list_get( tokens, tokens->n - 2 ); + s1 = slist_str( tokens, tokens->n - 2 ); if ( !strcasecmp( s1->data, "et" ) ) { if ( !strcasecmp( s2->data, "alia" ) || !strcasecmp( s2->data, "al." ) || @@ -134,13 +134,13 @@ } static int -has_suffix( list *tokens, int begin, int end, int *suffixpos ) +has_suffix( slist *tokens, int begin, int end, int *suffixpos ) { int i, ret; - newstr *s; + str *s; /* ...check last element, e.g. "H. F. Author, Sr." */ - s = list_get( tokens, end - 1 ); + s = slist_str( tokens, end - 1 ); ret = identify_suffix( s->data ); if ( ret ) { *suffixpos = end - 1; @@ -149,9 +149,9 @@ /* ...try to find one after a comma, e.g. "Author, Sr., H. F." */ for ( i=begin; i<end-1; ++i ) { - s = list_get( tokens, i ); + s = slist_str( tokens, i ); if ( s->len && s->data[ s->len - 1 ]==',' ) { - s = list_get( tokens, i+1 ); + s = slist_str( tokens, i+1 ); ret = identify_suffix( s->data ); if ( ret ) { *suffixpos = i+1; @@ -164,7 +164,7 @@ } static int -add_given_split( newstr *name, newstr *s ) +add_given_split( str *name, str *s ) { unsigned int unicode_char; unsigned int pos = 0; @@ -174,49 +174,49 @@ if ( is_ws( (char) unicode_char ) ) continue; else if ( unicode_char==(unsigned int)'.' ) { if ( s->data[pos]=='-' ) { - newstr_strcat( name, ".-" ); + str_strcatc( name, ".-" ); pos += 1; unicode_char = utf8_decode( s->data, &pos ); utf8_encode_str( unicode_char, utf8s ); - newstr_strcat( name, utf8s ); - newstr_addchar( name, '.' ); + str_strcatc( name, utf8s ); + str_addchar( name, '.' ); } } else if ( unicode_char==(unsigned int)'-' ) { - newstr_strcat( name, ".-" ); + str_strcatc( name, ".-" ); unicode_char = utf8_decode( s->data, &pos ); utf8_encode_str( unicode_char, utf8s ); - newstr_strcat( name, utf8s ); - newstr_addchar( name, '.' ); + str_strcatc( name, utf8s ); + str_addchar( name, '.' ); } else if ( unicode_char==(unsigned int)',' ) { /* nothing */ } else { - newstr_addchar( name, '|' ); + str_addchar( name, '|' ); utf8_encode_str( unicode_char, utf8s ); - newstr_strcat( name, utf8s ); + str_strcatc( name, utf8s ); } } return 1; } static unsigned char -token_has_no_upper( list *tokens, int n ) +token_has_no_upper( slist *tokens, int n ) { unsigned short m; - newstr *s; - s = list_get( tokens, n ); - m = unicode_utf8_classify_newstr( s ); + str *s; + s = slist_str( tokens, n ); + m = unicode_utf8_classify_str( s ); if ( m & UNICODE_UPPER ) return 0; else return 1; } static unsigned char -token_has_upper( list *tokens, int n ) +token_has_upper( slist *tokens, int n ) { if ( token_has_no_upper( tokens, n ) ) return 0; else return 1; } static int -name_multielement_nocomma( intlist *given, intlist *family, list *tokens, int begin, int end, int suffixpos ) +name_multielement_nocomma( intlist *given, intlist *family, slist *tokens, int begin, int end, int suffixpos ) { int family_start, family_end; int i, n; @@ -253,9 +253,9 @@ } static int -name_multielement_comma( intlist *given, intlist *family, list *tokens, int begin, int end, int comma, int suffixpos ) +name_multielement_comma( intlist *given, intlist *family, slist *tokens, int begin, int end, int comma, int suffixpos ) { - newstr *s; + str *s; int i; /* ...family names */ @@ -263,8 +263,8 @@ if ( i==suffixpos ) continue; intlist_add( family, i ); } - s = list_get( tokens, comma ); - newstr_trimend( s, 1 ); /* remove comma */ + s = slist_str( tokens, comma ); + str_trimend( s, 1 ); /* remove comma */ intlist_add( family, comma ); /* ...given names */ @@ -277,26 +277,26 @@ } static int -name_mutlielement_build( newstr *name, intlist *given, intlist *family, list *tokens ) +name_mutlielement_build( str *name, intlist *given, intlist *family, slist *tokens ) { unsigned short case_given = 0, case_family = 0, should_split = 0; - newstr *s; + str *s; int i, m; /* ...copy and analyze family name */ for ( i=0; i<family->n; ++i ) { m = intlist_get( family, i ); - s = list_get( tokens, m ); - if ( i ) newstr_addchar( name, ' ' ); - newstr_newstrcat( name, s ); - case_family |= unicode_utf8_classify_newstr( s ); + s = slist_str( tokens, m ); + if ( i ) str_addchar( name, ' ' ); + str_strcat( name, s ); + case_family |= unicode_utf8_classify_str( s ); } /* ...check given name case */ for ( i=0; i<given->n; ++i ) { m = intlist_get( given, i ); - s = list_get( tokens, m ); - case_given |= unicode_utf8_classify_newstr( s ); + s = slist_str( tokens, m ); + case_given |= unicode_utf8_classify_str( s ); } if ( ( ( case_family & UNICODE_MIXEDCASE ) == UNICODE_MIXEDCASE ) && @@ -306,35 +306,35 @@ for ( i=0; i<given->n; ++i ) { m = intlist_get( given, i ); - s = list_get( tokens, m ); + s = slist_str( tokens, m ); if ( !should_split ) { - newstr_addchar( name, '|' ); - newstr_newstrcat( name, s ); + str_addchar( name, '|' ); + str_strcat( name, s ); } else add_given_split( name, s ); } return 1; } static int -name_construct_multi( newstr *outname, list *tokens, int begin, int end ) +name_construct_multi( str *outname, slist *tokens, int begin, int end ) { int i, suffix, suffixpos=-1, comma=-1; intlist given, family; - newstr *s; + str *s; intlist_init( &family ); intlist_init( &given ); - newstr_empty( outname ); + str_empty( outname ); suffix = has_suffix( tokens, begin, end, &suffixpos ); for ( i=begin; i<end && comma==-1; i++ ) { if ( i==suffixpos ) continue; - s = list_get( tokens, i ); + s = slist_str( tokens, i ); if ( s->data[ s->len -1 ] == ',' ) { if ( suffix && i==suffixpos-1 && !(suffix&WITHCOMMA) ) - newstr_trimend( s, 1 ); + str_trimend( s, 1 ); else comma = i; } @@ -348,10 +348,10 @@ name_mutlielement_build( outname, &given, &family, tokens ); if ( suffix ) { - if ( suffix & JUNIOR ) newstr_strcat( outname, "||Jr." ); - if ( suffix & SENIOR ) newstr_strcat( outname, "||Sr." ); - if ( suffix & THIRD ) newstr_strcat( outname, "||III" ); - if ( suffix & FOURTH ) newstr_strcat( outname, "||IV" ); + if ( suffix & JUNIOR ) str_strcatc( outname, "||Jr." ); + if ( suffix & SENIOR ) str_strcatc( outname, "||Sr." ); + if ( suffix & THIRD ) str_strcatc( outname, "||III" ); + if ( suffix & FOURTH ) str_strcatc( outname, "||IV" ); } intlist_free( &given ); @@ -361,18 +361,18 @@ } int -name_addmultielement( fields *info, char *tag, list *tokens, int begin, int end, int level ) +name_addmultielement( fields *info, char *tag, slist *tokens, int begin, int end, int level ) { int status, ok = 1; - newstr name; + str name; - newstr_init( &name ); + str_init( &name ); name_construct_multi( &name, tokens, begin, end ); - status = fields_add( info, tag, name.data, level ); + status = fields_add_can_dup( info, tag, name.data, level ); if ( status!=FIELDS_OK ) ok = 0; - newstr_free( &name ); + str_free( &name ); return ok; } @@ -388,14 +388,14 @@ name_addsingleelement( fields *info, char *tag, char *name, int level, int corp ) { int status, ok = 1; - newstr outtag; - newstr_init( &outtag ); - newstr_strcpy( &outtag, tag ); - if ( !corp ) newstr_strcat( &outtag, ":ASIS" ); - else newstr_strcat( &outtag, ":CORP" ); - status = fields_add( info, outtag.data, name, level ); + str outtag; + str_init( &outtag ); + str_strcpyc( &outtag, tag ); + if ( !corp ) str_strcatc( &outtag, ":ASIS" ); + else str_strcatc( &outtag, ":CORP" ); + status = fields_add_can_dup( info, outtag.data, name, level ); if ( status!=FIELDS_OK ) ok = 0; - newstr_free( &outtag ); + str_free( &outtag ); return ok; } @@ -409,31 +409,31 @@ * Returns 3 on ok and name in corps list */ int -name_parse( newstr *outname, newstr *inname, list *asis, list *corps ) +name_parse( str *outname, str *inname, slist *asis, slist *corps ) { - list tokens; + slist tokens; int ret = 1; - newstr_empty( outname ); + str_empty( outname ); if ( !inname || !inname->len ) return ret; - list_init( &tokens ); + slist_init( &tokens ); - if ( asis && list_find( asis, inname->data ) !=-1 ) { - newstr_newstrcpy( outname, inname ); + if ( asis && slist_find( asis, inname ) !=-1 ) { + str_strcpy( outname, inname ); ret = 2; goto out; - } else if ( corps && list_find( corps, inname->data ) != -1 ) { - newstr_newstrcpy( outname, inname ); + } else if ( corps && slist_find( corps, inname ) != -1 ) { + str_strcpy( outname, inname ); ret = 3; goto out; } - newstr_findreplace( inname, ",", ", " ); - list_tokenize( &tokens, inname, " ", 1 ); + str_findreplace( inname, ",", ", " ); + slist_tokenize( &tokens, inname, " ", 1 ); if ( tokens.n==1 ) { - newstr_newstrcpy( outname, inname ); + str_strcpy( outname, inname ); ret = 2; } else { name_construct_multi( outname, &tokens, 0, tokens.n ); @@ -442,17 +442,17 @@ out: - list_free( &tokens ); + slist_free( &tokens ); return ret; } static char * -name_copy( newstr *name, char *p ) +name_copy( str *name, char *p ) { char *start, *end, *q; - newstr_empty( name ); + str_empty( name ); start = p = skip_ws( p ); @@ -465,7 +465,7 @@ if ( *p=='|' ) p++; for ( q=start; q<=end; q++ ) - newstr_addchar( name, *q ); + str_addchar( name, *q ); return p; } @@ -486,16 +486,16 @@ * "Author, H. F." */ int -name_add( fields *info, char *tag, char *q, int level, list *asis, list *corps ) +name_add( fields *info, char *tag, char *q, int level, slist *asis, slist *corps ) { int ok, status, nametype, ret = 1; - newstr inname, outname; - list tokens; + str inname, outname; + slist tokens; if ( !q ) return 0; - list_init( &tokens ); - newstrs_init( &inname, &outname, NULL ); + slist_init( &tokens ); + strs_init( &inname, &outname, NULL ); while ( *q ) { @@ -505,7 +505,7 @@ if ( !nametype ) { ret = 0; goto out; } if ( nametype==1 ) { - status = fields_add( info, tag, outname.data, level ); + status = fields_add_can_dup( info, tag, outname.data, level ); ok = ( status==FIELDS_OK ) ? 1 : 0; } else if ( nametype==2 ) @@ -518,8 +518,8 @@ } out: - newstrs_free( &inname, &outname, NULL ); - list_free( &tokens ); + strs_free( &inname, &outname, NULL ); + slist_free( &tokens ); return ret; } diff --git a/bibutils/name.h b/bibutils/name.h --- a/bibutils/name.h +++ b/bibutils/name.h @@ -3,7 +3,7 @@ * * mangle names w/ and w/o commas * - * Copyright (c) Chris Putnam 2004-2014 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * @@ -11,16 +11,16 @@ #ifndef NAME_H #define NAME_H -#include "newstr.h" -#include "list.h" +#include "str.h" +#include "slist.h" #include "fields.h" -extern int name_add( fields *info, char *tag, char *q, int level, list *asis, list *corps ); -extern void name_build_withcomma( newstr *s, char *p ); -extern int name_parse( newstr *outname, newstr *inname, list *asis, list *corps ); +extern int name_add( fields *info, char *tag, char *q, int level, slist *asis, slist *corps ); +extern void name_build_withcomma( str *s, char *p ); +extern int name_parse( str *outname, str *inname, slist *asis, slist *corps ); extern int name_addsingleelement( fields *info, char *tag, char *name, int level, int corp ); -extern int name_addmultielement( fields *info, char *tag, list *tokens, int begin, int end, int level ); -extern int name_findetal( list *tokens ); +extern int name_addmultielement( fields *info, char *tag, slist *tokens, int begin, int end, int level ); +extern int name_findetal( slist *tokens ); #endif diff --git a/bibutils/nbibin.c b/bibutils/nbibin.c new file mode 100644 --- /dev/null +++ b/bibutils/nbibin.c @@ -0,0 +1,505 @@ +/* + * nbibin.c + * + * Copyright (c) Chris Putnam 2016-2017 + * + * Source code released under the GPL version 2 + * + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <ctype.h> +#include "is_ws.h" +#include "str.h" +#include "str_conv.h" +#include "fields.h" +#include "name.h" +#include "title.h" +#include "url.h" +#include "serialno.h" +#include "reftypes.h" +#include "bibformats.h" +#include "generic.h" + +extern variants nbib_all[]; +extern int nbib_nall; + +/***************************************************** + PUBLIC: void nbib_initparams() +*****************************************************/ + +static int nbib_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int nbib_processf( fields *nbib, char *p, char *filename, long nref, param *pm ); +static int nbib_typef( fields *nbib, char *filename, int nref, param *p ); +static int nbib_convertf( fields *nbib, fields *info, int reftype, param *p ); + +void +nbibin_initparams( param *p, const char *progname ) +{ + p->readformat = BIBL_NBIBIN; + p->charsetin = BIBL_CHARSET_DEFAULT; + p->charsetin_src = BIBL_SRC_DEFAULT; + p->latexin = 0; + p->xmlin = 0; + p->utf8in = 0; + p->nosplittitle = 0; + p->verbose = 0; + p->addcount = 0; + p->output_raw = 0; + + p->readf = nbib_readf; + p->processf = nbib_processf; + p->cleanf = NULL; + p->typef = nbib_typef; + p->convertf = nbib_convertf; + p->all = nbib_all; + p->nall = nbib_nall; + + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); + + if ( !progname ) p->progname = NULL; + else p->progname = strdup( progname ); +} + +/***************************************************** + PUBLIC: int nbib_readf() +*****************************************************/ + +/* RIS definition of a tag is strict: + character 1 = uppercase alphabetic character + character 2 = uppercase alphabetic character + character 3 = character or space (ansi 32) + character 4 = character or space (ansi 32) + character 5 = dash (ansi 45) + character 6 = space (ansi 32) +*/ +static int +is_upperchar( char c ) +{ + if ( c>='A' && c<='Z' ) return 1; + else return 0; +} + +static int +is_upperchar_space( char c ) +{ + if ( c==' ' ) return 1; + if ( c>='A' && c<='Z' ) return 1; + else return 0; +} + +static int +nbib_istag( char *buf ) +{ + if ( !is_upperchar( buf[0] ) ) return 0; + if ( !is_upperchar( buf[1] ) ) return 0; + if ( !is_upperchar_space( buf[2] ) ) return 0; + if ( !is_upperchar_space( buf[3] ) ) return 0; + if (buf[4]!='-') return 0; + if (buf[5]!=' ') return 0; + return 1; +} + +static int +readmore( FILE *fp, char *buf, int bufsize, int *bufpos, str *line ) +{ + if ( line->len ) return 1; + else return str_fget( fp, buf, bufsize, bufpos, line ); +} + +static int +skip_utf8_bom( str *line, int *fcharset ) +{ + unsigned char *up; + + if ( line->len < 3 ) return 0; + + up = ( unsigned char *) str_cstr( line ); + if ( up[0]==0xEF && up[1]==0xBB && up[2]==0xBF ) { + *fcharset = CHARSET_UNICODE; + return 3; + } + + return 0; +} + +static int +nbib_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) +{ + int n, haveref = 0, inref = 0, readtoofar = 0; + char *p; + + *fcharset = CHARSET_UNKNOWN; + + while ( !haveref && readmore( fp, buf, bufsize, bufpos, line ) ) { + + /* ...references are terminated by an empty line */ + if ( !line->data || line->len==0 ) { + if ( reference->len ) haveref = 1; + continue; + } + + /* ...recognize and skip over UTF8 BOM */ + n = skip_utf8_bom( line, fcharset ); + p = &( line->data[n] ); + + /* Each reference starts with 'PMID- ' && ends with blank line */ + if ( strncmp(p,"PMID- ",6)==0 ) { + if ( !inref ) { + inref = 1; + } else { + /* we've read too far.... */ + readtoofar = 1; + inref = 0; + } + } + if ( nbib_istag( p ) ) { + if ( !inref ) { + fprintf(stderr,"Warning. Tagged line not " + "in properly started reference.\n"); + fprintf(stderr,"Ignored: '%s'\n", p ); + } else if ( !strncmp(p,"ER -",5) ) { + inref = 0; + } else { + str_addchar( reference, '\n' ); + str_strcatc( reference, p ); + } + } + /* not a tag, but we'll append to last values ...*/ + else if ( inref && strlen( p ) >= 6 ) { + str_strcatc( reference, p+5 ); + } + if ( !readtoofar ) str_empty( line ); + } + if ( inref ) haveref = 1; + return haveref; +} + +/***************************************************** + PUBLIC: int nbib_processf() +*****************************************************/ + +static char* +process_line2( str *tag, str *data, char *p ) +{ + while ( *p==' ' || *p=='\t' ) p++; + while ( *p && *p!='\r' && *p!='\n' ) + str_addchar( data, *p++ ); + while ( *p=='\r' || *p=='\n' ) p++; + return p; +} + +static char* +process_line( str *tag, str *data, char *p ) +{ + int i; + + i = 0; + while ( i<6 && *p ) { + if ( *p!=' ' && *p!='-' ) str_addchar( tag, *p ); + p++; + i++; + } + while ( *p==' ' || *p=='\t' ) p++; + while ( *p && *p!='\r' && *p!='\n' ) + str_addchar( data, *p++ ); + str_trimendingws( data ); + while ( *p=='\n' || *p=='\r' ) p++; + return p; +} + +static int +nbib_processf( fields *nbib, char *p, char *filename, long nref, param *pm ) +{ + str tag, data; + int status, n; + + strs_init( &tag, &data, NULL ); + + while ( *p ) { + if ( nbib_istag( p ) ) + p = process_line( &tag, &data, p ); + /* no anonymous fields allowed */ + if ( str_has_value( &tag ) ) { + status = fields_add( nbib, str_cstr( &tag ), str_cstr( &data ), 0 ); + if ( status!=FIELDS_OK ) return 0; + } else { + p = process_line2( &tag, &data, p ); + n = fields_num( nbib ); + if ( data.len && n>0 ) { + str *od; + od = fields_value( nbib, n-1, FIELDS_STRP ); + str_addchar( od, ' ' ); + str_strcat( od, &data ); + } + } + strs_empty( &tag, &data, NULL ); + } + + strs_free( &tag, &data, NULL ); + return 1; +} + +/***************************************************** + PUBLIC: int nbib_typef() +*****************************************************/ + +/* + * PT - Case Reports + * PT - Journal Article + * PT - Research Support, N.I.H., Extramural + * PT - Review + */ +static int +nbib_typef( fields *nbib, char *filename, int nref, param *p ) +{ + int reftype, nrefname, is_default; + char *typename, *refname = ""; + vplist_index i; + vplist a; + + nrefname = fields_find( nbib, "PMID", LEVEL_MAIN ); + if ( nrefname!=-1 ) refname = fields_value( nbib, nrefname, FIELDS_CHRP_NOUSE ); + + vplist_init( &a ); + + fields_findv_each( nbib, LEVEL_MAIN, FIELDS_CHRP_NOUSE, &a, "PT" ); + is_default = 1; + for ( i=0; i<a.n; ++i ) { + typename = vplist_get( &a, i ); + reftype = get_reftype( typename, nref, p->progname, p->all, p->nall, refname, &is_default, REFTYPE_SILENT ); + if ( !is_default ) break; + } + + if ( a.n==0 ) + reftype = get_reftype( "", nref, p->progname, p->all, p->nall, refname, &is_default, REFTYPE_CHATTY ); + else if ( is_default ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Did not recognize type of refnum %d (%s).\n" + "\tDefaulting to %s.\n", nref, refname, p->all[0].type ); + } + + vplist_free( &a ); + + return reftype; +} + +/***************************************************** + PUBLIC: int nbib_convertf() +*****************************************************/ + +/* PB - 2016 May 7 */ + +static int +nbibin_date( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + int fstatus, status = BIBL_OK; + str s; + char *p; + + p = str_cstr( invalue ); + if ( !p ) return status; + + str_init( &s ); + + /* ...handle year */ + while ( *p && !is_ws( *p ) ) { + str_addchar( &s, *p ); + p++; + } + + if ( str_memerr( &s ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } + + if ( str_has_value( &s ) ) { + fstatus = fields_add( bibout, "DATE:YEAR", str_cstr( &s ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + } + + /* ...handle month */ + str_empty( &s ); + while ( is_ws( *p ) ) p++; + while ( *p && !is_ws( *p ) ) { + str_addchar( &s, *p ); + p++; + } + + if ( str_memerr( &s ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } + + if ( str_has_value( &s ) ) { + fstatus = fields_add( bibout, "DATE:MONTH", str_cstr( &s ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + } + + /* ...handle day */ + str_empty( &s ); + while ( is_ws( *p ) ) p++; + while ( *p && !is_ws( *p ) ) { + str_addchar( &s, *p ); + p++; + } + + if ( str_memerr( &s ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } + + if ( str_has_value( &s ) ) { + fstatus = fields_add( bibout, "DATE:DAY", str_cstr( &s ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + } + +out: + str_free( &s ); + + return status; +} + +/* the LID and AID fields that can be doi's or pii's */ +static int +nbibin_doi( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + int fstatus, sstatus, status = BIBL_OK; + char *id, *type, *usetag=""; + slist tokens; + + slist_init( &tokens ); + + sstatus = slist_tokenize( &tokens, invalue, " ", 1 ); + if ( sstatus!=SLIST_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + + if ( tokens.n == 2 ) { + id = slist_cstr( &tokens, 0 ); + type = slist_cstr( &tokens, 1 ); + if ( !strcmp( type, "[doi]" ) ) usetag = "DOI"; + else if ( !strcmp( type, "[pii]" ) ) usetag = "PII"; + if ( strlen( outtag ) > 0 ) { + fstatus = fields_add( bibout, usetag, id, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + } + } +out: + slist_free( &tokens ); + return status; +} + +static int +nbibin_pages( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) +{ + int fstatus, status = BIBL_OK; + str sp, tmp, ep; + char *p; + int i; + + p = str_cstr( invalue ); + if ( !p ) return BIBL_OK; + + strs_init( &sp, &tmp, &ep, NULL ); + + while ( *p && *p!='-' ) { + str_addchar( &sp, *p ); + p++; + } + + if ( str_memerr( &sp ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } + + while ( *p=='-' ) p++; + + while ( *p ) { + str_addchar( &tmp, *p ); + p++; + } + + if ( sp.len ) { + fstatus = fields_add( bibout, "PAGES:START", str_cstr( &sp ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + } + + if ( tmp.len ) { + for ( i=0; i<sp.len - tmp.len; ++i ) + str_addchar( &ep, sp.data[i] ); + str_strcat( &ep, &tmp ); + + fstatus = fields_add( bibout, "PAGES:STOP", str_cstr( &ep ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + } +out: + strs_free( &sp, &tmp, &ep, NULL ); + return status; +} + +static void +nbib_report_notag( param *p, char *tag ) +{ + if ( p->verbose && strcmp( tag, "TY" ) ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Did not identify NBIB tag '%s'\n", tag ); + } +} + +static int +nbib_convertf( fields *bibin, fields *bibout, int reftype, param *p ) +{ + static int (*convertfns[NUM_REFTYPES])(fields *, int i, str *, str *, int, param *, char *, fields *) = { + [ 0 ... NUM_REFTYPES-1 ] = generic_null, + [ SIMPLE ] = generic_simple, + [ TITLE ] = generic_title, + [ PERSON ] = generic_person, + [ SKIP ] = generic_skip, + [ DATE ] = nbibin_date, + [ PAGES ] = nbibin_pages, + [ DOI ] = nbibin_doi, + }; + int process, level, i, nfields, status = BIBL_OK; + str *intag, *invalue; + char *outtag; + + nfields = fields_num( bibin ); + + for ( i=0; i<nfields; ++i ) { + intag = fields_tag( bibin, i, FIELDS_STRP ); + if ( !translate_oldtag( intag->data, reftype, p->all, p->nall, &process, &level, &outtag ) ) { + nbib_report_notag( p, intag->data ); + continue; + } + invalue = fields_value( bibin, i, FIELDS_STRP ); + + status = convertfns[ process ] ( bibin, i, intag, invalue, level, p, outtag, bibout ); + if ( status!=BIBL_OK ) return status; + } + + if ( status==BIBL_OK && p->verbose ) fields_report( bibout, stderr ); + + return status; +} diff --git a/bibutils/nbibtypes.c b/bibutils/nbibtypes.c new file mode 100644 --- /dev/null +++ b/bibutils/nbibtypes.c @@ -0,0 +1,68 @@ +/* + * nbibtypes.c + * + * Copyright (c) Chris Putnam 2016-2017 + * + * Program and source code released under the GPL version 2 + * + */ +#include <stdio.h> +#include <string.h> +#include "is_ws.h" +#include "fields.h" +#include "reftypes.h" + +static lookups article[] = { + { "PMID", "PMID", SIMPLE, LEVEL_MAIN }, + { "OWN", "", SKIP, LEVEL_MAIN }, + { "STAT", "", SKIP, LEVEL_MAIN }, + { "DA", "", SKIP, LEVEL_MAIN }, + { "DCOM", "", SKIP, LEVEL_MAIN }, + { "LR", "", SKIP, LEVEL_MAIN }, + { "IS", "", SKIP, LEVEL_MAIN }, + { "VI", "VOLUME", SIMPLE, LEVEL_MAIN }, + { "IP", "ISSUE", SIMPLE, LEVEL_MAIN }, + { "DP", "", DATE, LEVEL_MAIN }, /* date published? */ + { "TI", "TITLE", TITLE, LEVEL_MAIN }, + { "PG", "PAGES", PAGES, LEVEL_MAIN }, + { "LID", "DOI", DOI, LEVEL_MAIN }, /* linking ID? -- can be DOI/PII */ + { "AB", "ABSTRACT", SIMPLE, LEVEL_MAIN }, + { "FAU", "AUTHOR", PERSON, LEVEL_MAIN }, + { "AU", "", SKIP, LEVEL_MAIN }, + { "AD", "", SKIP, LEVEL_MAIN }, + { "LA", "", SKIP, LEVEL_MAIN }, + { "GR", "", SKIP, LEVEL_MAIN }, + { "DEP", "", SKIP, LEVEL_MAIN }, /* a date */ + { "PL", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Publisher location */ + { "TA", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* Journal title abbreviation */ + { "JT", "TITLE", SIMPLE, LEVEL_HOST }, /* Journal title */ + { "JID", "", SKIP, LEVEL_HOST }, /* Journal ID? */ + { "SB", "", SKIP, LEVEL_MAIN }, + { "PMC", "PMC", SIMPLE, LEVEL_MAIN }, + { "OID", "", SKIP, LEVEL_MAIN }, + { "EDAT", "", SKIP, LEVEL_MAIN }, + { "MHDA", "", SKIP, LEVEL_MAIN }, + { "CRDT", "", SKIP, LEVEL_MAIN }, + { "PHST", "", SKIP, LEVEL_MAIN }, /* Publication history? */ + { "AID", "DOI", DOI, LEVEL_MAIN }, /* Article ID? -- can be DOI/PII */ + { "PST", "", SKIP, LEVEL_MAIN }, + { "SO", "", SKIP, LEVEL_MAIN }, + { " ", "INTERNAL_TYPE|ARTICLE", ALWAYS, LEVEL_MAIN }, + { " ", "ISSUANCE|continuing", ALWAYS, LEVEL_HOST }, + { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { " ", "GENRE|journal article", ALWAYS, LEVEL_MAIN }, + { " ", "GENRE|periodical", ALWAYS, LEVEL_HOST }, + { " ", "GENRE|academic journal", ALWAYS, LEVEL_HOST } +}; + +#define ORIG(a) ( &(a[0]) ) +#define SIZE(a) ( sizeof( a ) / sizeof( lookups ) ) +#define REFTYPE(a,b) { a, ORIG(b), SIZE(b) } + +variants nbib_all[] = { + REFTYPE( "Journal article", article ), + REFTYPE( "News", article ), +}; + +int nbib_nall = sizeof( nbib_all ) / sizeof( variants ); + diff --git a/bibutils/newstr.c b/bibutils/newstr.c deleted file mode 100644 --- a/bibutils/newstr.c +++ /dev/null @@ -1,901 +0,0 @@ -/* - * newstr.c - * - * Version: 04/27/14 - * - * Copyright (c) Chris Putnam 1999-2014 - * - * Source code released under the GPL version 2 - * - * - * routines for dynamically allocated strings - * - */ -#include <stdio.h> -#include <stdlib.h> -#include <stdarg.h> -#include <string.h> -#include <ctype.h> -#include <limits.h> -#include "newstr.h" -#include "is_ws.h" - -/* Do not use asserts in NEWSTR_NOASSERT defined */ -#ifdef NEWSTR_NOASSERT -#define NDEBUG -#endif -#include <assert.h> - -#define newstr_initlen (64) - - -/* Clear memory in resize/free if NEWSTR_PARANOIA defined */ - -#ifndef NEWSTR_PARANOIA - -static void -newstr_realloc( newstr *s, unsigned long minsize ) -{ - char *newptr; - unsigned long size; - assert( s ); - size = 2 * s->dim; - if (size < minsize) size = minsize; - newptr = (char *) realloc( s->data, sizeof( *(s->data) )*size ); - if ( !newptr ) { - fprintf(stderr,"Error. Cannot reallocate memory (%ld bytes) in newstr_realloc.\n", sizeof(*(s->data))*size); - exit( EXIT_FAILURE ); - } - s->data = newptr; - s->dim = size; -} - -/* define as a no-op */ -#define newstr_nullify( s ) - -#else - -static void -newstr_realloc( newstr *s, unsigned long minsize ) -{ - char *newptr; - unsigned long size; - assert( s ); - size = 2 * s->dim; - if ( size < minsize ) size = minsize; - newptr = (char *) malloc( sizeof( *(s->data) ) * size ); - if ( !newptr ) { - fprintf( stderr, "Error. Cannot reallocate memory (%d bytes)" - " in newstr_realloc.\n", sizeof(*(s->data))*size ); - exit( EXIT_FAILURE ); - } - if ( s->data ) { - newstr_nullify( s ); - free( s->data ); - } - s->data = newptr; - s->dim = size; -} - -static inline void -newstr_nullify( newstr *s ) -{ - memset( s->data, 0, s->dim ); -} - -#endif - -void -newstr_init( newstr *s ) -{ - assert( s ); - s->dim = 0; - s->len = 0; - s->data = NULL; -} - -void -newstr_initstr( newstr *s, const char *initstr ) -{ - assert( s ); - assert( initstr ); - newstr_init( s ); - newstr_strcpy( s, initstr ); -} - -void -newstrs_init( newstr *s, ... ) -{ - newstr *s2; - va_list ap; - newstr_init( s ); - va_start( ap, s ); - do { - s2 = va_arg( ap, newstr * ); - if ( s2 ) newstr_init( s2 ); - } while ( s2 ); - va_end( ap ); -} - -/* - * This is currently a stub. Later it will - * report whether or not a newstr function - * could not be performed due to a memory - * error. - */ -int -newstr_memerr( newstr *s ) -{ - return 0; -} - -void -newstr_mergestrs( newstr *s, ... ) -{ - va_list ap; - const char *cp; - newstr_empty( s ); - va_start( ap, s ); - do { - cp = va_arg( ap, const char * ); - if ( cp ) newstr_strcat( s, cp ); - } while ( cp ); - va_end( ap ); -} - -static void -newstr_initalloc( newstr *s, unsigned long minsize ) -{ - unsigned long size = newstr_initlen; - assert( s ); - if ( minsize > newstr_initlen ) size = minsize; - s->data = (char *) malloc (sizeof( *(s->data) ) * size); - if ( !s->data ) { - fprintf(stderr,"Error. Cannot allocate memory in newstr_initalloc.\n"); - exit( EXIT_FAILURE ); - } - s->data[0]='\0'; - s->dim=size; - s->len=0; -} - -newstr * -newstr_new( void ) -{ - newstr *s = (newstr *) malloc( sizeof( *s ) ); - if ( s ) - newstr_initalloc( s, newstr_initlen ); - return s; -} - -void -newstr_free( newstr *s ) -{ - assert( s ); - if ( s->data ) { - newstr_nullify( s ); - free( s->data ); - } - s->dim = 0; - s->len = 0; - s->data = NULL; -} - -void -newstrs_free( newstr *s, ... ) -{ - newstr *s2; - va_list ap; - newstr_free( s ); - va_start( ap, s ); - do { - s2 = va_arg( ap, newstr * ); - if ( s2 ) newstr_free( s2 ); - } while ( s2 ); - va_end( ap ); -} - -void -newstr_delete( newstr *s ) -{ - assert( s ); - newstr_free( s ); - free( s ); -} - -void -newstr_empty( newstr *s ) -{ - assert( s ); - if ( s->data ) { - newstr_nullify( s ); - s->data[0] = '\0'; - } - s->len = 0; -} - -void -newstrs_empty( newstr *s, ... ) -{ - newstr *s2; - va_list ap; - newstr_empty( s ); - va_start( ap, s ); - do { - s2 = va_arg( ap, newstr * ); - if ( s2 ) newstr_empty( s2 ); - } while ( s2 ); - va_end( ap ); -} - -void -newstr_addchar( newstr *s, char newchar ) -{ - assert( s ); - if ( newchar=='\0' ) return; /* appending '\0' is a null operation */ - if ( !s->data || s->dim==0 ) - newstr_initalloc( s, newstr_initlen ); - if ( s->len + 2 > s->dim ) - newstr_realloc( s, s->len*2 ); - s->data[s->len++] = newchar; - s->data[s->len] = '\0'; -} - -/* newstr_addutf8 - * - * Add potential multibyte character to s starting at pointer p. - * Multibyte Unicode characters have the high bit set. - * - * Since we can progress more than one byte at p, return the - * properly updated pointer p. - */ -const char * -newstr_addutf8( newstr *s, const char *p ) -{ - if ( ! ((*p) & 128 ) ) { - newstr_addchar( s, *p ); - p++; - } else { - while ( ((*p) & 128) ) { - newstr_addchar( s, *p ); - p++; - } - } - return p; -} - -void -newstr_fprintf( FILE *fp, newstr *s ) -{ - assert( s ); - if ( s->data ) fprintf( fp, "%s", s->data ); -} - -void -newstr_prepend( newstr *s, const char *addstr ) -{ - unsigned long lenaddstr, i; - assert( s && addstr ); - lenaddstr = strlen( addstr ); - if ( lenaddstr==0 ) return; - if ( !s->data || !s->dim ) - newstr_initalloc( s, lenaddstr+1 ); - else { - if ( s->len + lenaddstr + 1 > s->dim ) - newstr_realloc( s, s->len + lenaddstr + 1 ); - for ( i=s->len+lenaddstr-1; i>=lenaddstr; i-- ) - s->data[i] = s->data[i-lenaddstr]; - } - strncpy( s->data, addstr, lenaddstr ); - s->len += lenaddstr; - s->data[ s->len ] = '\0'; -} - -static inline void -newstr_strcat_ensurespace( newstr *s, unsigned long n ) -{ - unsigned long m = s->len + n + 1; - if ( !s->data || !s->dim ) - newstr_initalloc( s, m ); - else if ( s->len + n + 1 > s->dim ) - newstr_realloc( s, m ); -} - -static inline void -newstr_strcat_internal( newstr *s, const char *addstr, unsigned long n ) -{ - newstr_strcat_ensurespace( s, n ); - strncat( &(s->data[s->len]), addstr, n ); - s->len += n; - s->data[s->len]='\0'; -} - -void -newstr_newstrcat( newstr *s, newstr *old ) -{ - assert ( s && old ); - if ( !old->data ) return; - else newstr_strcat_internal( s, old->data, old->len ); -} - -void -newstr_strcat( newstr *s, const char *addstr ) -{ - unsigned long n; - assert( s && addstr ); - n = strlen( addstr ); - newstr_strcat_internal( s, addstr, n ); -} - -void -newstr_segcat( newstr *s, char *startat, char *endat ) -{ - unsigned long n; - char *p; - - assert( s && startat && endat ); - assert( (size_t) startat < (size_t) endat ); - - if ( startat==endat ) return; - - n = 0; - p = startat; - while ( p!=endat ) { - n++; - p++; - } - - newstr_strcat_internal( s, startat, n ); -} - -void -newstr_indxcat( newstr *s, char *p, unsigned long start, unsigned long stop ) -{ - unsigned long i; - assert( s && p ); - assert( start <= stop ); - for ( i=start; i<stop; ++i ) - newstr_addchar( s, p[i] ); -} - -/* newstr_cpytodelim() - * term = string of characters to be used as terminators - * finalstep = set to non-zero to position return value past the - * terminating character - */ -char * -newstr_cpytodelim( newstr *s, char *p, const char *delim, unsigned char finalstep ) -{ - newstr_empty( s ); - return newstr_cattodelim( s, p, delim, finalstep ); -} - -/* newstr_cpytodelim() - * term = string of characters to be used as terminators - * finalstep = set to non-zero to position return value past the - * terminating character - */ -char * -newstr_cattodelim( newstr *s, char *p, const char *delim, unsigned char finalstep ) -{ - while ( p && *p && !strchr( delim, *p ) ) { - newstr_addchar( s, *p ); - p++; - } - if ( *p && finalstep ) p++; - return p; -} - -static inline void -newstr_strcpy_ensurespace( newstr *s, unsigned long n ) -{ - unsigned long m = n + 1; - if ( !s->data || !s->dim ) - newstr_initalloc( s, m ); - else if ( m > s->dim ) - newstr_realloc( s, m ); -} - -static inline void -newstr_strcpy_internal( newstr *s, const char *p, unsigned long n ) -{ - newstr_strcpy_ensurespace( s, n ); - strncpy( s->data, p, n ); - s->data[n] = '\0'; - s->len = n; -} - -void -newstr_newstrcpy( newstr *s, newstr *old ) -{ - assert( s ); - if ( s==old ) return; - else if ( !old || old->len==0 ) newstr_empty( s ); - else newstr_strcpy_internal( s, old->data, old->len ); -} - -void -newstr_strcpy( newstr *s, const char *addstr ) -{ - unsigned long n; - assert( s && addstr ); - n = strlen( addstr ); - newstr_strcpy_internal( s, addstr, n ); -} - -/* newstr_segcpy( s, start, end ); - * - * copies [start,end) into s - */ -void -newstr_segcpy( newstr *s, char *startat, char *endat ) -{ - unsigned long n; - char *p; - - assert( s && startat && endat ); - assert( ((size_t) startat) <= ((size_t) endat) ); - - if ( startat==endat ) { - newstr_empty( s ); - return; - } - - n = 0; - p = startat; - while ( p!=endat ) { - p++; - n++; - } - - newstr_strcpy_internal( s, startat, n ); -} - -/* - * newstr_indxcpy( s, in, start, stop ); - * - * copies in[start,stop) (excludes stop) into s - */ -void -newstr_indxcpy( newstr *s, char *p, unsigned long start, unsigned long stop ) -{ - unsigned long i; - assert( s && p ); - assert( start <= stop ); - if ( start == stop ) { - newstr_empty( s ); - return; - } - newstr_strcpy_ensurespace( s, stop-start+1 ); - for ( i=start; i<stop; ++i ) - s->data[i-start] = p[i]; - s->len = stop-start; - s->data[s->len] = '\0'; -} - -newstr * -newstr_strdup( const char *s1 ) -{ - newstr *s2 = newstr_new(); - if ( s2 ) - newstr_strcpy( s2, s1 ); - return s2; -} - -void -newstr_segdel( newstr *s, char *p, char *q ) -{ - newstr tmp1, tmp2; - char *r; - assert( s ); - r = &(s->data[s->len]); - newstr_init( &tmp1 ); - newstr_init( &tmp2 ); - newstr_segcpy( &tmp1, s->data, p ); - newstr_segcpy( &tmp2, q, r ); - newstr_empty( s ); - if ( tmp1.data ) newstr_strcat( s, tmp1.data ); - if ( tmp2.data ) newstr_strcat( s, tmp2.data ); - newstr_free( &tmp2 ); - newstr_free( &tmp1 ); -} - -/* - * newstr_findreplace() - * - * if replace is "" or NULL, then delete find - */ - -int -newstr_findreplace( newstr *s, const char *find, const char *replace ) -{ - long diff; - size_t findstart, searchstart; - size_t p1, p2; - size_t find_len, rep_len, curr_len; - char empty[2] = ""; - unsigned long minsize; - char *p; - int n = 0; - - assert( s && find ); - if ( !s->data || !s->dim ) return n; - if ( !replace ) replace = empty; - - find_len = strlen( find ); - rep_len = strlen( replace ); - diff = rep_len - find_len; - if ( diff < 0 ) diff = 0; - - searchstart=0; - while ((p=strstr(s->data + searchstart,find))!=NULL) { - curr_len = strlen(s->data); - findstart=(size_t) p - (size_t) s->data; - minsize = curr_len + diff + 1; - if (s->dim <= minsize) newstr_realloc( s, minsize ); - if ( find_len > rep_len ) { - p1 = findstart + rep_len; - p2 = findstart + find_len; - while( s->data[p2] ) - s->data[p1++]=s->data[p2++]; - s->data[p1]='\0'; - n++; - } else if ( find_len < rep_len ) { - for ( p1=curr_len; p1>=findstart+find_len; p1-- ) - s->data[p1+diff] = s->data[p1]; - n++; - } - for (p1=0; p1<rep_len; p1++) - s->data[findstart+p1]=replace[p1]; - searchstart = findstart + rep_len; - s->len += rep_len - find_len; - } - return n; -} - - -/* newstr_fget() - * returns 0 if we're done, 1 if we're not done - * extracts line by line (regardless of end characters) - * and feeds from buf.... - */ -int -newstr_fget( FILE *fp, char *buf, int bufsize, int *pbufpos, newstr *outs ) -{ - int bufpos = *pbufpos, done = 0; - char *ok; - assert( fp && outs ); - newstr_empty( outs ); - while ( !done ) { - while ( buf[bufpos] && buf[bufpos]!='\r' && buf[bufpos]!='\n' ) - newstr_addchar( outs, buf[bufpos++] ); - if ( buf[bufpos]=='\0' ) { - ok = fgets( buf, bufsize, fp ); - bufpos=*pbufpos=0; - if ( !ok && feof(fp) ) { /* end-of-file */ - buf[bufpos] = 0; - if ( outs->len==0 ) return 0; /*nothing in out*/ - else return 1; /*one last out */ - } - } else if ( buf[bufpos]=='\r' || buf[bufpos]=='\n' ) done=1; - } - if ( ( buf[bufpos]=='\n' && buf[bufpos+1]=='\r') || - ( buf[bufpos]=='\r' && buf[bufpos+1]=='\n') ) bufpos+=2; - else if ( buf[bufpos]=='\n' || buf[bufpos]=='\r' ) bufpos+=1; - *pbufpos = bufpos; - return 1; -} - -void -newstr_toupper( newstr *s ) -{ - unsigned long i; - assert( s ); - for ( i=0; i<s->len; ++i ) - s->data[i] = toupper( (unsigned char)s->data[i] ); -} - -void -newstr_tolower( newstr *s ) -{ - unsigned long i; - assert( s ); - for ( i=0; i<s->len; ++i ) - s->data[i] = tolower( (unsigned char)s->data[i] ); -} - -/* newstr_swapstrings( s1, s2 ) - * be sneaky and swap internal newstring data from one - * string to another - */ -void -newstr_swapstrings( newstr *s1, newstr *s2 ) -{ - char *tmpp; - int tmp; - - assert( s1 && s2 ); - - /* swap dimensioning info */ - tmp = s1->dim; - s1->dim = s2->dim; - s2->dim = tmp; - - /* swap length info */ - tmp = s1->len; - s1->len = s2->len; - s2->len = tmp; - - /* swap data */ - tmpp = s1->data; - s1->data = s2->data; - s2->data = tmpp; -} - -void -newstr_trimstartingws( newstr *s ) -{ - char *p, *q; - int n; - - assert( s ); - - if ( s->len==0 || !is_ws( s->data[0] ) ) return; - - n = 0; - p = s->data; - while ( is_ws( *p ) ) p++; - - q = s->data; - while ( *p ) { - *q++ = *p++; - n++; - } - *q = '\0'; - - s->len = n; -} - -void -newstr_trimendingws( newstr *s ) -{ - assert( s ); - while ( s->len > 0 && is_ws( s->data[s->len-1] ) ) { - s->data[s->len-1] = '\0'; - s->len--; - } -} - -int -newstr_match_first( newstr *s, char ch ) -{ - assert( s ); - if ( !s->len ) return 0; - if ( s->data[0] == ch ) return 1; - return 0; -} - -int -newstr_match_end( newstr *s, char ch ) -{ - assert( s ); - if ( !s->len ) return 0; - if ( s->data[ s->len - 1 ] == ch ) return 1; - return 0; -} - -void -newstr_trimbegin( newstr *s, unsigned long n ) -{ - char *p, *q; - - assert( s ); - - if ( n==0 ) return; - if ( s->len==0 ) return; - if ( n >= s->len ) { - newstr_empty( s ); - return; - } - - p = s->data; - while ( n-- > 0 ) p++; - - n = 0; - q = s->data; - while ( *p ) { - *q++ = *p++; - n++; - } - *q = '\0'; - - s->len = n; -} - -void -newstr_trimend( newstr *s, unsigned long n ) -{ - assert( s ); - - if ( n==0 ) return; - if ( n >= s->len ) { - newstr_empty( s ); - return; - } - - s->len -= n; - s->data[ s->len ] = '\0'; -} - -void -newstr_pad( newstr *s, unsigned long len, char ch ) -{ - unsigned long i; - assert( s ); - for ( i=s->len; i<len; i++ ) - newstr_addchar( s, ch ); -} - -void -newstr_copyposlen( newstr *s, newstr *in, unsigned long pos, unsigned long len ) -{ - unsigned long i, max; - assert( s ); - newstr_empty( s ); - max = pos+len; - if ( max > in->len ) max = in->len; - for ( i=pos; i<max; ++i ) - newstr_addchar( s, in->data[i] ); -} - -static void -newstr_check_case( newstr *s, int *lowercase, int *uppercase ) -{ - int i; - assert( s ); - *lowercase = 0; - *uppercase = 0; - if ( s->len < 1 ) return; - for ( i=0; i<s->len && !( *lowercase && *uppercase ); ++i ) { - if ( isalpha( (unsigned char)s->data[i] ) ) { - if ( isupper( (unsigned char)s->data[i] ) ) *uppercase += 1; - else if ( islower( (unsigned char)s->data[i] ) ) *lowercase += 1; - } - } -} - -int -newstr_is_mixedcase( newstr *s ) -{ - int lowercase, uppercase; - newstr_check_case( s, &lowercase, &uppercase ); - if ( lowercase > 0 && uppercase > 0 ) return 1; - return 0; -} - -int -newstr_is_lowercase( newstr *s ) -{ - int lowercase, uppercase; - newstr_check_case( s, &lowercase, &uppercase ); - if ( lowercase > 0 && uppercase == 0 ) return 1; - return 0; -} - -int -newstr_is_uppercase( newstr *s ) -{ - int lowercase, uppercase; - newstr_check_case( s, &lowercase, &uppercase ); - if ( lowercase == 0 && uppercase > 0 ) return 1; - return 0; -} - -void -newstr_stripws( newstr *s ) -{ - unsigned long len = 0; - char *p, *q; - assert( s ); - if ( s->len ) { - p = q = s->data; - while ( *p ) { - if ( !is_ws( *p ) ) { - *q = *p; - q++; - len++; - } - p++; - } - *q = '\0'; - } - s->len = len; -} - -int -newstr_newstrcmp( const newstr *s, const newstr *t ) -{ - assert( s ); - assert( t ); - if ( s->len == 0 && t->len == 0 ) return 0; - if ( s->len == 0 ) return strcmp( "", t->data ); - if ( t->len == 0 ) return strcmp( s->data, "" ); - return strcmp( s->data, t->data ); -} - -void -newstr_reverse( newstr *s ) -{ - unsigned long i, max; - char tmp; - assert( s ); - max = s->len / 2; - for ( i=0; i<max; ++i ) { - tmp = s->data[ i ]; - s->data[ i ] = s->data[ s->len - 1 - i ]; - s->data[ s->len - 1 - i ] = tmp; - } -} - -int -newstr_fgetline( newstr *s, FILE *fp ) -{ - int ch, eol = 0; - assert( s ); - assert( fp ); - newstr_empty( s ); - if ( feof( fp ) ) return 0; - while ( !feof( fp ) && !eol ) { - ch = fgetc( fp ); - if ( ch == EOF ) { - if ( s->len ) return 1; - else return 0; - } - else if ( ch == '\n' ) eol = 1; - else if ( ch == '\r' ) { - ch = fgetc( fp ); - if ( ch != '\n' ) ungetc( ch, fp ); - eol = 1; - } else { - newstr_addchar( s, (char) ch ); - } - } - return 1; -} - -/* - * s = "Hi!\0", s.len = 3 - * - * newstr_char( s, 0 ) = 'H' newstr_revchar( s, 0 ) = '!' - * newstr_char( s, 1 ) = 'i' newstr_revchar( s, 1 ) = 'i' - * newstr_char( s, 2 ) = '!' newstr_revchar( s, 2 ) = 'H' - * newstr_char( s, 3 ) = '\0' newstr_revchar( s, 3 ) = '\0' - */ -char -newstr_char( newstr *s, unsigned long n ) -{ - assert( s ); - if ( s->len==0 || n >= s->len ) return '\0'; - return s->data[ n ]; -} - -char -newstr_revchar( newstr *s, unsigned long n ) -{ - assert( s ); - if ( s->len==0 || n >= s->len ) return '\0'; - return s->data[ s->len - n - 1]; -} - -void -newstr_makepath( newstr *path, const char *dirname, const char *filename, char sep ) -{ - assert( path ); - if ( dirname ) newstr_strcpy( path, dirname ); - else newstr_empty( path ); - - if ( path->len && path->data[path->len-1]!=sep ) - newstr_addchar( path, sep ); - - if ( filename ) newstr_strcat( path, filename ); -} diff --git a/bibutils/newstr.h b/bibutils/newstr.h deleted file mode 100644 --- a/bibutils/newstr.h +++ /dev/null @@ -1,101 +0,0 @@ -/* - * newstr.h - * - * Version: 04/27/14 - * - * Copyright (c) Chris Putnam 1999-2014 - * - * Source code released under the GPL version 2 - * - */ -#ifndef NEWSTR_H -#define NEWSTR_H - -#include <stdio.h> - -typedef struct newstr { - char *data; - unsigned long dim; - unsigned long len; -} newstr; - -newstr *newstr_new ( void ); -void newstr_delete ( newstr *s ); - -void newstr_init ( newstr *s ); -void newstr_initstr ( newstr *s, const char *initstr ); -void newstr_empty ( newstr *s ); -void newstr_free ( newstr *s ); - -void newstrs_init ( newstr *s, ... ); -void newstrs_empty ( newstr *s, ... ); -void newstrs_free ( newstr *s, ... ); - -void newstr_mergestrs ( newstr *s, ... ); -newstr *newstr_strdup ( const char *p ); -void newstr_addchar ( newstr *s, char newchar ); -void newstr_reverse ( newstr *s ); -const char *newstr_addutf8 ( newstr *s, const char *p ); -void newstr_strcat ( newstr *s, const char *addstr ); -void newstr_newstrcat ( newstr *s, newstr *old ); -void newstr_segcat ( newstr *s, char *startat, char *endat ); -char *newstr_cpytodelim ( newstr *s, char *p, const char *delim, unsigned char finalstep ); -char *newstr_cattodelim ( newstr *s, char *p, const char *delim, unsigned char finalstep ); -void newstr_prepend ( newstr *s, const char *addstr ); -void newstr_strcpy ( newstr *s, const char *addstr ); -void newstr_newstrcpy ( newstr *s, newstr *old ); -void newstr_segcpy ( newstr *s, char *startat, char *endat ); -void newstr_segdel ( newstr *s, char *startat, char *endat ); -void newstr_indxcpy ( newstr *s, char *p, unsigned long start, unsigned long stop ); -void newstr_indxcat ( newstr *s, char *p, unsigned long start, unsigned long stop ); -void newstr_fprintf ( FILE *fp, newstr *s ); -int newstr_fget ( FILE *fp, char *buf, int bufsize, int *pbufpos, - newstr *outs ); -char newstr_char ( newstr *s, unsigned long n ); -char newstr_revchar ( newstr *s, unsigned long n ); -int newstr_fgetline ( newstr *s, FILE *fp ); -int newstr_findreplace ( newstr *s, const char *find, const char *replace ); -void newstr_toupper ( newstr *s ); -void newstr_tolower ( newstr *s ); -void newstr_trimstartingws( newstr *s ); -void newstr_trimendingws( newstr *s ); -void newstr_swapstrings ( newstr *s1, newstr *s2 ); -void newstr_stripws ( newstr *s ); - -int newstr_match_first ( newstr *s, char ch ); -int newstr_match_end ( newstr *s, char ch ); -void newstr_trimbegin ( newstr *s, unsigned long n ); -void newstr_trimend ( newstr *s, unsigned long n ); - -void newstr_pad ( newstr *s, unsigned long len, char ch ); -void newstr_copyposlen ( newstr *s, newstr *in, unsigned long pos, unsigned long len ); - -void newstr_makepath ( newstr *path, const char *dirname, const char *filename, char sep ); - - -int newstr_is_mixedcase( newstr *s ); -int newstr_is_lowercase( newstr *s ); -int newstr_is_uppercase( newstr *s ); - -int newstr_newstrcmp ( const newstr *s, const newstr *t ); - -int newstr_memerr( newstr *s ); - - -/* #define NEWSTR_PARANOIA - * - * set to clear memory before it is freed or reallocated - * note that this is slower...may be important if string - * contains sensitive information - */ - -/* #define NEWSTR_NOASSERT - * - * set to turn off the use of asserts (and associated call to exit) - * in newstr functions...useful for library construction for - * Linux distributions that don't want libraries calling exit, but - * not useful during code development - */ - -#endif - diff --git a/bibutils/newstr_conv.c b/bibutils/newstr_conv.c deleted file mode 100644 --- a/bibutils/newstr_conv.c +++ /dev/null @@ -1,197 +0,0 @@ -/* - * newstr_conv.c - * - * Copyright (c) Chris Putnam 1999-2014 - * - * Source code released under the GPL version 2 - * - * newstring routines for converting newstrings between character sets - * - */ -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <ctype.h> -#include <limits.h> -#include "newstr.h" -#include "latex.h" -#include "entities.h" -#include "utf8.h" -#include "gb18030.h" -#include "charsets.h" -#include "newstr_conv.h" - -static void -addentity( newstr *s, unsigned int ch ) -{ - char buf[512]; - sprintf( buf, "&#%d;", ch ); - newstr_strcat( s, buf ); -} - -/* These are the five minimal predefined entites in XML */ -static int -minimalxmlchars( newstr *s, unsigned int ch ) -{ - if ( ch==34 ) { newstr_strcat( s, """ ); return 1; } - else if ( ch==38 ) { newstr_strcat( s, "&" ); return 1; } - else if ( ch==39 ) { newstr_strcat( s, "'" ); return 1; } - else if ( ch==60 ) { newstr_strcat( s, "<" ); return 1; } - else if ( ch==62 ) { newstr_strcat( s, ">" ); return 1; } - return 0; -} - -static void -addxmlchar( newstr *s, unsigned int ch ) -{ - if ( minimalxmlchars( s, ch ) ) return; - if ( ch > 127 ) addentity( s, ch ); - else newstr_addchar( s, ch ); -} - -static void -addutf8char( newstr *s, unsigned int ch, int xmlout ) -{ - unsigned char code[6]; - int nc, i; - if ( xmlout ) { - if ( minimalxmlchars( s, ch ) ) return; - if ( ch > 127 && xmlout == NEWSTR_CONV_XMLOUT_ENTITIES ) - { addentity( s, ch ); return; } - } - nc = utf8_encode( ch, code ); - for ( i=0; i<nc; ++i ) - newstr_addchar( s, code[i] ); -} - -static void -addgb18030char( newstr *s, unsigned int ch, int xmlout ) -{ - unsigned char code[4]; - int nc, i; - if ( xmlout ) { - if ( minimalxmlchars( s, ch ) ) return; - if ( ch > 127 && xmlout == NEWSTR_CONV_XMLOUT_ENTITIES ) - { addentity( s, ch ); return; } - } - nc = gb18030_encode( ch, code ); - for ( i=0; i<nc; ++i ) - newstr_addchar( s, code[i] ); -} - -static void -addlatexchar( newstr *s, unsigned int ch, int xmlout, int utf8out ) -{ - char buf[512]; - uni2latex( ch, buf, sizeof( buf ) ); - /* If the unicode character isn't recognized as latex output - * a '?' unless the user has requested unicode output. If so, - * output the unicode. - */ - if ( utf8out && !strcmp( buf, "?" ) ) { - addutf8char( s, ch, xmlout ); - } else { - newstr_strcat( s, buf ); - } -} - -/* - * get_unicode() - * - * This can be a little tricky. If the character is simply encoded - * such as UTF8 for > 128 or by numeric xml entities such as "Ȗ" - * then the output of decode_entity() and utf8_decode will necessarily - * be in the charsetin character set. On the other hand, if it's a - * fancy latex expression, such as "\alpha", or a non-numeric xml entity - * like "&", then we'll get the Unicode value (because our lists only - * keep the Unicode equivalent). - * - * The unicode variable indicates whether or not a Unicode-based listing - * was used to convert the character (remember that charsetin could be - * Unicode independently). - * - * The charset variable is used to keep track of what character set - * the character is in prior to conversion. - * - */ - -static unsigned int -get_unicode( newstr *s, unsigned int *pi, int charsetin, int latexin, int utf8in, int xmlin ) -{ - unsigned int ch; - int unicode = 0, err = 0; - if ( xmlin && s->data[*pi]=='&' ) { - ch = decode_entity( s->data, pi, &unicode, &err ); - } else if ( charsetin==CHARSET_GB18030 ) { - ch = gb18030_decode( s->data, pi ); - unicode = 1; - } else if ( latexin ) { - /* Must handle bibtex files in UTF8/Unicode */ - if ( utf8in && ( s->data[*pi] & 128 ) ) { - ch = utf8_decode( s->data, pi ); - unicode = 1; - } else ch = latex2char( s->data, pi, &unicode ); - } - else if ( utf8in ) - ch = utf8_decode( s->data, pi ); - else { - ch = (unsigned int) s->data[*pi]; - *pi = *pi + 1; - } - if ( !unicode && charsetin!=CHARSET_UNICODE ) - ch = charset_lookupchar( charsetin, ch ); - return ch; -} - -static int -write_unicode( newstr *s, unsigned int ch, int charsetout, int latexout, - int utf8out, int xmlout ) -{ - unsigned int c; - if ( latexout ) { - addlatexchar( s, ch, xmlout, utf8out ); - } else if ( utf8out ) { - addutf8char( s, ch, xmlout ); - } else if ( charsetout==CHARSET_GB18030 ) { - addgb18030char( s, ch, xmlout ); - } else { - c = charset_lookupuni( charsetout, ch ); - if ( xmlout ) addxmlchar( s, c ); - else newstr_addchar( s, c ); - } - return 1; -} - -/* - * Returns 1 on memory error condition - */ -int -newstr_convert( newstr *s, - int charsetin, int latexin, int utf8in, int xmlin, - int charsetout, int latexout, int utf8out, int xmlout ) -{ - unsigned int pos = 0; - unsigned int ch; - newstr ns; - int ok = 1; - - if ( !s || s->len==0 ) return ok; - - newstr_init( &ns ); - - if ( charsetin==CHARSET_UNKNOWN ) charsetin = CHARSET_DEFAULT; - if ( charsetout==CHARSET_UNKNOWN ) charsetout = CHARSET_DEFAULT; - - while ( s->data[pos] ) { - ch = get_unicode( s, &pos, charsetin, latexin, utf8in, xmlin ); - ok = write_unicode( &ns, ch, charsetout, latexout, utf8out, xmlout ); - if ( !ok ) goto out; - } - - newstr_swapstrings( s, &ns ); -out: - newstr_free( &ns ); - - return ok; -} - diff --git a/bibutils/newstr_conv.h b/bibutils/newstr_conv.h deleted file mode 100644 --- a/bibutils/newstr_conv.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * newstring_conv.h - * - * Copyright (c) Chris Putnam 1999-2014 - * - * Source code released under the GPL version 2 - * - */ -#ifndef NEWSTR_CONV_H -#define NEWSTR_CONV_H - -#define NEWSTR_CONV_XMLOUT_FALSE (0) -#define NEWSTR_CONV_XMLOUT_TRUE (1) -#define NEWSTR_CONV_XMLOUT_ENTITIES (3) - -#include "newstr.h" - -extern int newstr_convert( newstr *s, - int charsetin, int latexin, int utf8in, int xmlin, - int charsetout, int latexout, int utf8out, int xmlout ); - -#endif - diff --git a/bibutils/notes.c b/bibutils/notes.c new file mode 100644 --- /dev/null +++ b/bibutils/notes.c @@ -0,0 +1,102 @@ +/* + * notes.c + * + * Copyright (c) Chris Putnam 2016-2017 + * + * Program and source code released under the GPL version 2 + * + */ +#include <string.h> +#include "url.h" +#include "notes.h" + +/* + * notes are mostly directly copies; however, lots of formats hide + * URLs/DOIs in the notes fields. For example: + * + * For RIS, Oxford Journals hides DOI in the N1 field. + * For Endnote, Wiley hides DOI in the %1 field. + * etc. + */ + +typedef struct url_t { + char *prefix; + char *tag; + int offset; +} url_t; + +static void +notes_added_url( fields *bibout, str *invalue, int level, int *ok ) +{ + url_t prefixes[] = { + { "arXiv:", "ARXIV", 6 }, + { "http://arxiv.org/abs/", "ARXIV", 21 }, + { "jstor:", "JSTOR", 6 }, + { "http://www.jstor.org/stable/", "JSTOR", 28 }, + { "medline:", "MEDLINE", 8 }, + { "pubmed:", "PMID", 7 }, + { "http://www.ncbi.nlm.nih.gov/pubmed/", "PMID", 35 }, + { "http://www.ncbi.nlm.nih.gov/pmc/articles/", "PMC", 41 }, + { "http://dx.doi.org/", "DOI", 19 }, + { "isi:", "ISIREFNUM", 4 }, + }; + int nprefixes = sizeof( prefixes ) / sizeof( prefixes[0] ); + + char *p = invalue->data; + char *tag = "URL"; + int fstatus; + int i; + + /* bibtex/biblatex-specific */ + if ( !strncasecmp( p, "\\urllink", 8 ) ) p += 8; + if ( !strncasecmp( p, "\\url", 4 ) ) p += 4; + + for ( i=0; i<nprefixes; ++i ) { + if ( !strncasecmp( p, prefixes[i].prefix, prefixes[i].offset ) ) { + tag = prefixes[i].tag; + p = p + prefixes[i].offset; + break; + } + } + + fstatus = fields_add( bibout, tag, p, level ); + + if ( fstatus==FIELDS_OK ) *ok = 1; + else *ok = 0; +} + +static int +notes_added_doi( fields *bibout, str *invalue, int level, int *ok ) +{ + int doi, fstatus; + + doi = is_doi( invalue->data ); + + if ( doi != -1 ) { + fstatus = fields_add( bibout, "DOI", &(invalue->data[doi]), level ); + if ( fstatus != FIELDS_OK ) *ok = 0; + return 1; + } + + else return 0; +} + +int +notes_add( fields *bibout, str *invalue, int level ) +{ + int fstatus, done = 0, ok = 1; + + if ( !is_embedded_link( invalue->data ) ) { + fstatus = fields_add( bibout, "NOTES", invalue->data, level ); + if ( fstatus != FIELDS_OK ) ok = 0; + } + + else { + + done = notes_added_doi( bibout, invalue, level, &ok ); + if ( !done ) notes_added_url( bibout, invalue, level, &ok ); + + } + + return ok; +} diff --git a/bibutils/notes.h b/bibutils/notes.h new file mode 100644 --- /dev/null +++ b/bibutils/notes.h @@ -0,0 +1,17 @@ +/* + * notes.h + * + * Copyright (c) Chris Putnam 2016-2017 + * + * Source code released under the GPL version 2 + * + */ +#ifndef NOTES_H +#define NOTES_H + +#include "bibutils.h" + +int notes_add( fields *bibout, str *invalue, int level ); + +#endif + diff --git a/bibutils/pages.c b/bibutils/pages.c new file mode 100644 --- /dev/null +++ b/bibutils/pages.c @@ -0,0 +1,87 @@ +/* + * pages.c + * + * Copyright (c) Chris Putnam 2016-2017 + * + * Program and source code released under GPL verison 2 + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include "is_ws.h" +#include "utf8.h" +#include "pages.h" + +/* extract_range() + * + * Handle input strings like: + * + * "1-15" + * " 1 - 15 " + * " 1000--- 1500" + * " 1 <<em-dash>> 10" + * " 107 111" + */ +static void +extract_range( str *input, str *begin, str *end ) +{ + /* -30 is the first character of a UTF8 em-dash and en-dash */ + const char terminators[] = { ' ', '-', '\t', '\r', '\n', -30, '\0' }; + char *p; + + str_empty( begin ); + str_empty( end ); + + if ( input->len==0 ) return; + + p = skip_ws( input->data ); + while ( *p && !strchr( terminators, *p ) ) + str_addchar( begin, *p++ ); + + p = skip_ws( p ); + + while ( *p=='-' ) p++; + while ( utf8_is_emdash( p ) ) p+=3; + while ( utf8_is_endash( p ) ) p+=3; + + p = skip_ws( p ); + + while ( *p && !strchr( terminators, *p ) ) + str_addchar( end, *p++ ); +} + +int +pages_add( fields *bibout, char *outtag, str *invalue, int level ) +{ + int fstatus, status = 1; + str start, stop; + + str_init( &start ); + str_init( &stop ); + + extract_range( invalue, &start, &stop ); + + if ( str_memerr( &start ) || str_memerr( &stop ) ) { + status = 0; + goto out; + } + + if ( start.len>0 ) { + fstatus = fields_add( bibout, "PAGES:START", start.data, level ); + if ( fstatus!=FIELDS_OK ) { + status = 0; + goto out; + } + } + + if ( stop.len>0 ) { + fstatus = fields_add( bibout, "PAGES:STOP", stop.data, level ); + if ( fstatus!=FIELDS_OK ) status = 0; + } + +out: + str_free( &start ); + str_free( &stop ); + return status; +} + diff --git a/bibutils/pages.h b/bibutils/pages.h new file mode 100644 --- /dev/null +++ b/bibutils/pages.h @@ -0,0 +1,16 @@ +/* + * pages.h + * + * Copyright (c) Chris Putnam 2016-2017 + * + * Program and source code released under the GPL version 2 + */ +#ifndef PAGES_H +#define PAGES_H + +#include "bibl.h" + +int pages_add( fields *bibout, char *outtag, str *invalue, int level ); + +#endif + diff --git a/bibutils/reftypes.c b/bibutils/reftypes.c --- a/bibutils/reftypes.c +++ b/bibutils/reftypes.c @@ -1,7 +1,7 @@ /* * reftypes.c * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * @@ -13,16 +13,27 @@ #include "reftypes.h" int -get_reftype( char *p, long refnum, char *progname, variants *all, int nall, char *tag ) +get_reftype( char *p, long refnum, char *progname, variants *all, int nall, char *tag, int *is_default, int chattiness ) { int i; + p = skip_ws( p ); - for ( i=0; i<nall; ++i ) + + *is_default = 0; + + for ( i=0; i<nall; ++i ) { if ( !strncasecmp( all[i].type, p, strlen(all[i].type) ) ) return i; - if ( progname ) fprintf( stderr, "%s: ", progname ); - fprintf( stderr, "Did not recognize type '%s' of refnum %ld (%s).\n" - "\tDefaulting to article.\n", p, refnum, tag ); + } + + *is_default = 1; + + if ( chattiness==REFTYPE_CHATTY ) { + if ( progname ) fprintf( stderr, "%s: ", progname ); + fprintf( stderr, "Did not recognize type '%s' of refnum %ld (%s).\n" + "\tDefaulting to %s.\n", p, refnum, tag, all[0].type ); + } + return 0; } @@ -52,6 +63,7 @@ *processingtype = ((all[reftype]).tags[n]).processingtype; *level = ((all[reftype]).tags[n]).level; *newtag = ((all[reftype]).tags[n]).newstr; + return 1; } - return n; + return 0; } diff --git a/bibutils/reftypes.h b/bibutils/reftypes.h --- a/bibutils/reftypes.h +++ b/bibutils/reftypes.h @@ -1,7 +1,7 @@ /* * reftypes.h * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * @@ -9,9 +9,13 @@ #ifndef REFTYPES_H #define REFTYPES_H +#define REFTYPE_CHATTY (0) +#define REFTYPE_SILENT (1) + /* Reftypes handled by core code */ #define ALWAYS (0) #define DEFAULT (1) +#define SKIP (2) /* Reftypes to be handled by converters */ #define SIMPLE (2) @@ -26,17 +30,18 @@ #define HOWPUBLISHED (11) #define LINKEDFILE (12) #define KEYWORD (13) -#define BT_URL (14) /* Bibtex URL */ -#define BT_NOTE (15) /* Bibtex Note */ -#define BT_SENTE (16) /* Bibtex 'Sente' */ -#define BT_GENRE (17) /* Bibtex Genre */ -#define BT_EPRINT (18) /* Bibtex 'Eprint' */ -#define BT_ORG (19) /* Bibtex Organization */ -#define BLT_THESIS_TYPE (20) /* Biblatex Thesis Type */ -#define BLT_SCHOOL (21) /* Biblatex School */ -#define BLT_EDITOR (22) /* Biblatex Editor */ -#define BLT_SUBTYPE (23) /* Biblatex entrysubtype */ -#define BLT_SKIP (24) /* Biblatex Skip Entry */ +#define URL (14) +#define BT_SENTE (15) /* Bibtex 'Sente' */ +#define BT_GENRE (16) /* Bibtex Genre */ +#define BT_EPRINT (17) /* Bibtex 'Eprint' */ +#define BT_ORG (18) /* Bibtex Organization */ +#define BLT_THESIS_TYPE (19) /* Biblatex Thesis Type */ +#define BLT_SCHOOL (20) /* Biblatex School */ +#define BLT_EDITOR (21) /* Biblatex Editor */ +#define BLT_SUBTYPE (22) /* Biblatex entrysubtype */ +#define BLT_SKIP (23) /* Biblatex Skip Entry */ +#define EPRINT (24) +#define NUM_REFTYPES (25) typedef struct { char *oldstr; @@ -51,10 +56,8 @@ int ntags; } variants; -extern int get_reftype( char *q, long refnum, char *progname, variants *all, int nall, char *tag ); -extern int process_findoldtag( char *oldtag, int reftype, variants all[], int nall ); -extern int translate_oldtag( char *oldtag, int reftype, variants all[], int nall, int *processingtype, int *level, char **newtag ); - - +int get_reftype( char *q, long refnum, char *progname, variants *all, int nall, char *tag, int *is_default, int chattiness ); +int process_findoldtag( char *oldtag, int reftype, variants all[], int nall ); +int translate_oldtag( char *oldtag, int reftype, variants all[], int nall, int *processingtype, int *level, char **newtag ); #endif diff --git a/bibutils/risin.c b/bibutils/risin.c --- a/bibutils/risin.c +++ b/bibutils/risin.c @@ -1,7 +1,7 @@ /* * risin.c * - * Copyright (c) Chris Putnam 2003-2014 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * @@ -10,19 +10,30 @@ #include <stdlib.h> #include <string.h> #include <ctype.h> -#include "newstr.h" -#include "newstr_conv.h" +#include "str.h" +#include "str_conv.h" #include "fields.h" #include "name.h" #include "title.h" +#include "url.h" +#include "utf8.h" #include "serialno.h" #include "reftypes.h" -#include "doi.h" -#include "risin.h" +#include "bibformats.h" +#include "generic.h" +extern variants ris_all[]; +extern int ris_nall; + /***************************************************** PUBLIC: void risin_initparams() *****************************************************/ + +static int risin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int risin_processf( fields *risin, char *p, char *filename, long nref, param *pm ); +static int risin_typef( fields *risin, char *filename, int nref, param *p ); +static int risin_convertf( fields *risin, fields *info, int reftype, param *p ); + void risin_initparams( param *p, const char *progname ) { @@ -45,8 +56,8 @@ p->all = ris_all; p->nall = ris_nall; - list_init( &(p->asis) ); - list_init( &(p->corps) ); + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); if ( !progname ) p->progname = NULL; else p->progname = strdup( progname ); @@ -63,77 +74,114 @@ character 4 = space (ansi 32) character 5 = dash (ansi 45) character 6 = space (ansi 32) + + some sources don't have a space at character 6 if there + is no data (such as "ER -" records). Handle this. + + www.omicsonline.org mangles the RIS specification and + puts _three_ spaces before the dash. Handle this too. */ static int -risin_istag( char *buf ) +is_ris_tag( char *buf ) { if (! (buf[0]>='A' && buf[0]<='Z') ) return 0; if (! (((buf[1]>='A' && buf[1]<='Z'))||(buf[1]>='0'&&buf[1]<='9')) ) return 0; if (buf[2]!=' ') return 0; if (buf[3]!=' ') return 0; - if (buf[4]!='-') return 0; - if (buf[5]!=' ') return 0; - return 1; + + /*...RIS fits specifications with two spaces */ + if (buf[4]=='-') { + if ( buf[5]==' ' || buf[5]=='\0' || buf[5]=='\n' || buf[5]=='\r' ) return 1; + } + + /* ...extra space in tag? */ + else if (buf[4]==' ') { + if ( buf[5]=='-' && ( buf[6]==' ' || buf[6]=='\0' || buf[6]=='\n' || buf[6]=='\r' ) ) return 1; + } + + return 0; } static int -readmore( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line ) +is_ris_start_tag( char *p ) { + /* ...TY tag that fits specifications */ + if ( !strncmp( p, "TY - ", 6 ) ) return 1; + /* ...TY tag with an extra space? */ + if ( !strncmp( p, "TY - ", 7 ) ) return 1; + return 0; +} + +static int +is_ris_end_tag( char *p ) +{ + /* ...ER tag that fits specifications */ + if ( !strncmp( p, "ER -", 5 ) ) return 1; + /* ...ER tag with an extra space? */ + if ( !strncmp( p, "ER -", 6 ) ) return 1; + return 0; +} + +static int +readmore( FILE *fp, char *buf, int bufsize, int *bufpos, str *line ) +{ if ( line->len ) return 1; - else return newstr_fget( fp, buf, bufsize, bufpos, line ); + else return str_fget( fp, buf, bufsize, bufpos, line ); } -int -risin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, - newstr *reference, int *fcharset ) +static int +risin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) { int haveref = 0, inref = 0, readtoofar = 0; - unsigned char *up; char *p; + *fcharset = CHARSET_UNKNOWN; + while ( !haveref && readmore( fp, buf, bufsize, bufpos, line ) ) { - if ( !line->data || line->len==0 ) continue; + + if ( str_is_empty( line ) ) continue; + p = &( line->data[0] ); - /* Recognize UTF8 BOM */ - up = (unsigned char * ) p; - if ( line->len > 2 && - up[0]==0xEF && up[1]==0xBB && up[2]==0xBF ) { + + if ( utf8_is_bom( p ) ) { *fcharset = CHARSET_UNICODE; p += 3; } - /* Each reference starts with 'TY - ' && - * ends with 'ER - ' */ - if ( strncmp(p,"TY - ",6)==0 ) { - if ( !inref ) { - inref = 1; - } else { + + /* References are bounded by tags 'TY - ' && 'ER - ' */ + if ( is_ris_start_tag( p ) ) { + if ( !inref ) inref = 1; + else { /* we've read too far.... */ readtoofar = 1; inref = 0; } } - if ( risin_istag( p ) ) { + + if ( is_ris_tag( p ) ) { if ( !inref ) { fprintf(stderr,"Warning. Tagged line not " "in properly started reference.\n"); fprintf(stderr,"Ignored: '%s'\n", p ); - } else if ( !strncmp(p,"ER -",5) ) { + } else if ( is_ris_end_tag( p ) ) { inref = 0; } else { - newstr_addchar( reference, '\n' ); - newstr_strcat( reference, p ); + str_addchar( reference, '\n' ); + str_strcatc( reference, p ); } } /* not a tag, but we'll append to last values ...*/ - else if ( inref && strncmp(p,"ER -",5)) { - newstr_addchar( reference, '\n' ); - newstr_strcat( reference, p ); + else if ( inref && !is_ris_end_tag( p ) ) { + str_addchar( reference, '\n' ); + str_strcatc( reference, p ); } if ( !inref && reference->len ) haveref = 1; - if ( !readtoofar ) newstr_empty( line ); + if ( !readtoofar ) str_empty( line ); } + if ( inref ) haveref = 1; + return haveref; } @@ -142,103 +190,143 @@ *****************************************************/ static char* -process_line2( newstr *tag, newstr *data, char *p ) +process_untagged_line( str *value, char *p ) { while ( *p==' ' || *p=='\t' ) p++; while ( *p && *p!='\r' && *p!='\n' ) - newstr_addchar( data, *p++ ); + str_addchar( value, *p++ ); while ( *p=='\r' || *p=='\n' ) p++; return p; } static char* -process_line( newstr *tag, newstr *data, char *p ) +process_tagged_line( str *tag, str *value, char *p ) { int i = 0; - while ( i<6 && *p ) { - if ( i<2 ) newstr_addchar( tag, *p ); + + while ( i<6 && *p && *p!='\n' && *p!='\r' ) { + if ( i<2 ) str_addchar( tag, *p ); p++; i++; } + while ( *p==' ' || *p=='\t' ) p++; + while ( *p && *p!='\r' && *p!='\n' ) - newstr_addchar( data, *p++ ); - newstr_trimendingws( data ); + str_addchar( value, *p++ ); + str_trimendingws( value ); + while ( *p=='\n' || *p=='\r' ) p++; + return p; } -int -risin_processf( fields *risin, char *p, char *filename, long nref ) +static int +merge_tag_value( fields *risin, str *tag, str *value, int *tag_added ) { - newstr tag, data; - int status, n; + str *oldval; + int n, status; - newstrs_init( &tag, &data, NULL ); + if ( str_has_value( value ) ) { + if ( *tag_added==1 ) { + n = fields_num( risin ); + if ( n>0 ) { + oldval = fields_value( risin, n-1, FIELDS_STRP ); + str_addchar( oldval, ' ' ); + str_strcat( oldval, value ); + if ( str_memerr( oldval ) ) return BIBL_ERR_MEMERR; + } + } + else { + status = fields_add( risin, str_cstr( tag ), str_cstr( value ), 0 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + *tag_added = 1; + } + } + return BIBL_OK; +} +static int +add_tag_value( fields *risin, str *tag, str *value, int *tag_added ) +{ + int status; + + if ( str_has_value( value ) ) { + status = fields_add( risin, str_cstr( tag ), str_cstr( value ), 0 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + *tag_added = 1; + } + + else { + *tag_added = 0; + } + + return BIBL_OK; +} + +static int +risin_processf( fields *risin, char *p, char *filename, long nref, param *pm ) +{ + int status, tag_added = 0, ret = 1; + str tag, value; + + strs_init( &tag, &value, NULL ); + while ( *p ) { - if ( risin_istag( p ) ) { - p = process_line( &tag, &data, p ); - /* no anonymous fields allowed */ - if ( tag.len ) - status = fields_add( risin, tag.data, data.data, 0 ); - if ( status!=FIELDS_OK ) return 0; - } else { - p = process_line2( &tag, &data, p ); - n = fields_num( risin ); - if ( data.len && n>0 ) { - newstr *od; - od = fields_value( risin, n-1, FIELDS_STRP ); - newstr_addchar( od, ' ' ); - newstr_strcat( od, data.data ); + + /* ...tag, add entry */ + if ( is_ris_tag( p ) ) { + str_empty( &tag ); + str_empty( &value ); + p = process_tagged_line( &tag, &value, p ); + status = add_tag_value( risin, &tag, &value, &tag_added ); + if ( status!=BIBL_OK ) { + ret = 0; + goto out; } } - newstrs_empty( &tag, &data, NULL ); + + /* ...no tag, merge with previous line */ + else { + str_empty( &value ); + p = process_untagged_line( &value, p ); + status = merge_tag_value( risin, &tag, &value, &tag_added ); + if ( status!=BIBL_OK ) { + ret = 0; + goto out; + } + } + } +out: - newstrs_free( &tag, &data, NULL ); - return 1; + strs_free( &tag, &value, NULL ); + return ret; } /***************************************************** PUBLIC: int risin_typef() *****************************************************/ -int -risin_typef( fields *risin, char *filename, int nref, param *p, variants *all, int nall ) +static int +risin_typef( fields *risin, char *filename, int nref, param *p ) { - char *refnum = ""; - int n, reftype, nreftype; - n = fields_find( risin, "TY", 0 ); - nreftype = fields_find( risin, "ID", 0 ); - if ( nreftype!=-1 ) refnum = risin[n].data->data; - if ( n!=-1 ) - reftype = get_reftype( (risin[n].data)->data, nref, p->progname, - all, nall, refnum ); - else - reftype = get_reftype( "", nref, p->progname, all, nall, refnum ); /*default */ - return reftype; + int ntypename, nrefname, is_default; + char *refname = "", *typename = ""; + + ntypename = fields_find( risin, "TY", LEVEL_MAIN ); + nrefname = fields_find( risin, "ID", LEVEL_MAIN ); + if ( ntypename!=-1 ) typename = fields_value( risin, ntypename, FIELDS_CHRP_NOUSE ); + if ( nrefname!=-1 ) refname = fields_value( risin, nrefname, FIELDS_CHRP_NOUSE ); + + return get_reftype( typename, nref, p->progname, p->all, p->nall, refname, &is_default, REFTYPE_CHATTY ); } /***************************************************** PUBLIC: int risin_convertf() *****************************************************/ -/* oxfordjournals hide the DOI in the NOTES N1 field */ static int -risin_addnotes( fields *f, char *tag, newstr *s, int level ) -{ - int doi, status; - doi = is_doi( s->data ); - if ( doi!=-1 ) - status = fields_add( f, "DOI", &(s->data[doi]), level ); - else - status = fields_add( f, tag, s->data, level ); - if ( status==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} - -static int is_uri_file_scheme( char *p ) { if ( !strncmp( p, "file:", 5 ) ) return 5; @@ -246,209 +334,214 @@ } static int -is_uri_remote_scheme( char *p ) -{ - char *scheme[] = { "http:", "ftp:", "git:", "gopher:" }; - int i, len, nschemes = sizeof( scheme ) / sizeof( scheme[0] ); - for ( i=0; i<nschemes; ++i ) { - len = strlen( scheme[i] ); - if ( !strncmp( p, scheme[i], len ) ) return len; - } - return 0; -} - -static int -risin_addfile( fields *f, char *tag, newstr *s, int level ) +risin_linkedfile( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) { - int status, n; + int fstatus, m; char *p; /* if URL is file:///path/to/xyz.pdf, only store "///path/to/xyz.pdf" */ - n = is_uri_file_scheme( s->data ); - if ( n ) { + m = is_uri_file_scheme( str_cstr( invalue ) ); + if ( m ) { /* skip past "file:" and store only actual path */ - p = s->data + n; - status = fields_add( f, tag, p, level ); - if ( status==FIELDS_OK ) return BIBL_OK; + p = invalue->data + m; + fstatus = fields_add( bibout, outtag, p, level ); + if ( fstatus==FIELDS_OK ) return BIBL_OK; else return BIBL_ERR_MEMERR; } /* if URL is http:, ftp:, etc. store as a URL */ - n = is_uri_remote_scheme( s->data ); - if ( n ) { - status = fields_add( f, "URL", s->data, level ); - if ( status==FIELDS_OK ) return BIBL_OK; + m = is_uri_remote_scheme( str_cstr( invalue ) ); + if ( m!=-1 ) { + fstatus = fields_add( bibout, "URL", str_cstr( invalue ), level ); + if ( fstatus==FIELDS_OK ) return BIBL_OK; else return BIBL_ERR_MEMERR; } /* badly formed, RIS wants URI, but store value anyway */ - status = fields_add( f, tag, s->data, level ); - if ( status==FIELDS_OK ) return BIBL_OK; + fstatus = fields_add( bibout, outtag, str_cstr( invalue ), level ); + if ( fstatus==FIELDS_OK ) return BIBL_OK; else return BIBL_ERR_MEMERR; } /* scopus puts DOI in the DO or DI tag, but it needs cleaning */ static int -risin_adddoi( fields *f, char *tag, newstr *s, int level ) +risin_doi( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) { - int status, doi; - doi = is_doi( s->data ); + int fstatus, doi; + doi = is_doi( str_cstr( invalue ) ); if ( doi!=-1 ) { - status = fields_add( f, "DOI", &(s->data[doi]), level ); - if ( status==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; + fstatus = fields_add( bibout, "DOI", &(invalue->data[doi]), level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - else return BIBL_OK; + return BIBL_OK; } static int -risin_adddate( fields *f, char *tag, newstr *d, int level ) +risin_date( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) { - char *p = d->data; - newstr date; + char *p = invalue->data; int part, status; + str date; - part = ( !strncasecmp( tag, "PART", 4 ) ); + part = ( !strncasecmp( outtag, "PART", 4 ) ); - newstr_init( &date ); - while ( *p && *p!='/' ) newstr_addchar( &date, *p++ ); + str_init( &date ); + while ( *p && *p!='/' ) str_addchar( &date, *p++ ); + if ( str_memerr( &date ) ) return BIBL_ERR_MEMERR; if ( *p=='/' ) p++; - if ( date.len>0 ) { - if ( part ) status = fields_add( f, "PARTYEAR", date.data, level ); - else status = fields_add( f, "YEAR", date.data, level ); + if ( str_has_value( &date ) ) { + if ( part ) status = fields_add( bibout, "PARTDATE:YEAR", str_cstr( &date ), level ); + else status = fields_add( bibout, "DATE:YEAR", str_cstr( &date ), level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - newstr_empty( &date ); - while ( *p && *p!='/' ) newstr_addchar( &date, *p++ ); + str_empty( &date ); + while ( *p && *p!='/' ) str_addchar( &date, *p++ ); + if ( str_memerr( &date ) ) return BIBL_ERR_MEMERR; if ( *p=='/' ) p++; - if ( date.len>0 ) { - if ( part ) status = fields_add( f, "PARTMONTH", date.data, level ); - else status = fields_add( f, "MONTH", date.data, level ); + if ( str_has_value( &date ) ) { + if ( part ) status = fields_add( bibout, "PARTDATE:MONTH", str_cstr( &date ), level ); + else status = fields_add( bibout, "DATE:MONTH", str_cstr( &date ), level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - newstr_empty( &date ); - while ( *p && *p!='/' ) newstr_addchar( &date, *p++ ); + str_empty( &date ); + while ( *p && *p!='/' ) str_addchar( &date, *p++ ); + if ( str_memerr( &date ) ) return BIBL_ERR_MEMERR; if ( *p=='/' ) p++; - if ( date.len>0 ) { - if ( part ) status = fields_add( f, "PARTDAY", date.data, level ); - else status = fields_add( f, "DAY", date.data, level ); + if ( str_has_value( &date ) ) { + if ( part ) status = fields_add( bibout, "PARTDATE:DAY", str_cstr( &date ), level ); + else status = fields_add( bibout, "DATE:DAY", str_cstr( &date ), level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - newstr_empty( &date ); - while ( *p ) newstr_addchar( &date, *p++ ); - if ( date.len>0 ) { - if ( part ) status = fields_add( f, "PARTDATEOTHER", date.data,level); - else status = fields_add( f, "DATEOTHER", date.data, level ); + str_empty( &date ); + while ( *p ) str_addchar( &date, *p++ ); + if ( str_memerr( &date ) ) return BIBL_ERR_MEMERR; + if ( str_has_value( &date ) ) { + if ( part ) status = fields_add( bibout, "PARTDATE:OTHER", str_cstr( &date ), level ); + else status = fields_add( bibout, "DATE:OTHER", str_cstr( &date ), level ); if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - newstr_free( &date ); + str_free( &date ); return BIBL_OK; } -static void -risin_report_notag( param *p, char *tag ) -{ - if ( p->verbose && strcmp( tag, "TY" ) ) { - if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, "Did not identify RIS tag '%s'\n", tag ); - } -} - static int -risin_simple( fields *f, char *tag, char *value, int level ) +risin_person( fields *bibin, int n, str *intag, str *invalue, int level, param *pm, char *outtag, fields *bibout ) { - int fstatus = fields_add( f, tag, value, level ); - if ( fstatus==FIELDS_OK ) return BIBL_OK; - else return BIBL_ERR_MEMERR; -} + int i, begin, end, ok, status = BIBL_OK; + slist tokens; + str name; -int -risin_convertf( fields *risin, fields *f, int reftype, param *p, variants *all, int nall ) -{ - int process, level, i, n, nfields, ok, fstatus, status = BIBL_OK; - char *outtag, *tag, *value; - newstr *t, *d; + str_init( &name ); + slist_init( &tokens ); - nfields = fields_num( risin ); + status = slist_tokenize( &tokens, invalue, " \t\r\n", 1 ); + if ( status!=SLIST_OK ) { status = BIBL_ERR_MEMERR; goto out; } - for ( i=0; i<nfields; ++i ) { - t = fields_tag( risin, i, FIELDS_STRP ); - n = translate_oldtag( t->data, reftype, all, nall, &process, &level, &outtag ); - if ( n==-1 ) { - risin_report_notag( p, t->data ); - continue; + begin = 0; + while ( begin < tokens.n ) { + + end = begin + 1; + + while ( end < tokens.n && strcasecmp( slist_cstr( &tokens, end ), "and" ) ) + end++; + + str_empty( &name ); + for ( i=begin; i<end; ++i ) { + if ( i>begin ) str_addchar( &name, ' ' ); + str_strcat( &name, slist_str( &tokens, i ) ); } - if ( process==ALWAYS ) continue; /* add in core code */ - d = fields_value( risin, i, FIELDS_STRP ); + ok = name_add( bibout, outtag, str_cstr( &name ), level, &(pm->asis), &(pm->corps) ); + if ( !ok ) { status = BIBL_ERR_MEMERR; goto out; } - switch ( process ) { + begin = end + 1; - case SIMPLE: - status = risin_simple( f, outtag, d->data, level ); - break; + /* Handle repeated 'and' errors */ + while ( begin < tokens.n && !strcasecmp( slist_cstr( &tokens, begin ), "and" ) ) + begin++; - case PERSON: - ok = name_add( f, outtag, d->data, level, &(p->asis), &(p->corps) ); - if ( ok ) status = BIBL_OK; - else status = BIBL_ERR_MEMERR; - break; + } - case TITLE: - ok = title_process( f, outtag, d->data, level, p->nosplittitle ); - if ( ok ) status = BIBL_OK; - else status = BIBL_ERR_MEMERR; - break; +out: + str_free( &name ); + slist_free( &tokens ); + return status; +} - case SERIALNO: - ok = addsn( f, d->data, level ); - if ( ok ) status = BIBL_OK; - else status = BIBL_ERR_MEMERR; - break; +/* look for thesis-type hint */ +static int +risin_thesis_hints( fields *bibin, int reftype, param *p, fields *bibout ) +{ + int i, nfields, fstatus; + char *tag, *value; - case DATE: - status = risin_adddate( f, outtag, d, level ); - break; + if ( strcasecmp( p->all[reftype].type, "THES" ) ) return BIBL_OK; - case NOTES: - status = risin_addnotes( f, outtag, d, level ); - break; + nfields = fields_num( bibin ); + for ( i=0; i<nfields; ++i ) { + tag = fields_tag( bibin, i, FIELDS_CHRP ); + if ( strcasecmp( tag, "U1" ) ) continue; + value = fields_value( bibin, i, FIELDS_CHRP ); + if ( !strcasecmp(value,"Ph.D. Thesis")|| + !strcasecmp(value,"Masters Thesis")|| + !strcasecmp(value,"Diploma Thesis")|| + !strcasecmp(value,"Doctoral Thesis")|| + !strcasecmp(value,"Habilitation Thesis")) { + fstatus = fields_add( bibout, "GENRE", value, 0 ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + } + return BIBL_OK; +} - case DOI: - status = risin_adddoi( f, outtag, d, level ); - break; +static void +risin_report_notag( param *p, char *tag ) +{ + if ( p->verbose && strcmp( tag, "TY" ) ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Did not identify RIS tag '%s'\n", tag ); + } +} - case LINKEDFILE: - status = risin_addfile( f, outtag, d, level ); - break; +static int +risin_convertf( fields *bibin, fields *bibout, int reftype, param *p ) +{ + static int (*convertfns[NUM_REFTYPES])(fields *, int, str *, str *, int, param *, char *, fields *) = { + [ 0 ... NUM_REFTYPES-1 ] = generic_null, + [ SIMPLE ] = generic_simple, + [ TITLE ] = generic_title, + [ PERSON ] = risin_person, + [ SERIALNO ] = generic_serialno, + [ NOTES ] = generic_notes, + [ URL ] = generic_url, + [ DATE ] = risin_date, + [ DOI ] = risin_doi, + [ LINKEDFILE ] = risin_linkedfile, + }; + int process, level, i, nfields, status = BIBL_OK; + str *intag, *invalue; + char *outtag; - default: - status = BIBL_OK; - break; + nfields = fields_num( bibin ); + for ( i=0; i<nfields; ++i ) { + intag = fields_tag( bibin, i, FIELDS_STRP ); + if ( !translate_oldtag( intag->data, reftype, p->all, p->nall, &process, &level, &outtag ) ) { + risin_report_notag( p, intag->data ); + continue; } + invalue = fields_value( bibin, i, FIELDS_STRP ); + + status = convertfns[ process ] ( bibin, i, intag, invalue, level, p, outtag, bibout ); if ( status!=BIBL_OK ) return status; } - /* look for thesis-type hint */ - if ( !strcasecmp( all[reftype].type, "THES" ) ) { - for ( i=0; i<nfields; ++i ) { - tag = fields_tag( risin, i, FIELDS_CHRP ); - if ( strcasecmp( tag, "U1" ) ) continue; - value = fields_value( risin, i, FIELDS_CHRP ); - if ( !strcasecmp(value,"Ph.D. Thesis")|| - !strcasecmp(value,"Masters Thesis")|| - !strcasecmp(value,"Diploma Thesis")|| - !strcasecmp(value,"Doctoral Thesis")|| - !strcasecmp(value,"Habilitation Thesis")) { - fstatus = fields_add( f, "GENRE", value, 0 ); - if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; - } - } - } + if ( status == BIBL_OK ) status = risin_thesis_hints( bibin, reftype, p, bibout ); + + if ( status==BIBL_OK && p->verbose ) fields_report( bibout, stderr ); return status; } diff --git a/bibutils/risin.h b/bibutils/risin.h deleted file mode 100644 --- a/bibutils/risin.h +++ /dev/null @@ -1,28 +0,0 @@ -/* - * risin.h - * - * Copyright (c) Chris Putnam 2003-2014 - * - * Source code released under the GPL version 2 - * - */ -#ifndef RISIN_H -#define RISIN_H - -#include "newstr.h" -#include "fields.h" -#include "reftypes.h" -#include "bibutils.h" - -extern int risin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ); -extern int risin_processf( fields *risin, char *p, char *filename, long nref ); -extern int risin_typef( fields *risin, char *filename, int nref, param *p, variants *all, int nall ); -extern int risin_convertf( fields *risin, fields *info, int reftype, param *p, variants *all, int nall ); - -extern void risin_initparams( param *p, const char *progname ); - -extern variants ris_all[]; -extern int ris_nall; - -#endif - diff --git a/bibutils/risout.c b/bibutils/risout.c --- a/bibutils/risout.c +++ b/bibutils/risout.c @@ -1,7 +1,7 @@ /* * risout.c * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * @@ -11,13 +11,18 @@ #include <string.h> #include <ctype.h> #include "utf8.h" -#include "newstr.h" +#include "str.h" #include "strsearch.h" #include "fields.h" -#include "doi.h" #include "name.h" -#include "risout.h" +#include "title.h" +#include "url.h" +#include "bibformats.h" +static int risout_write( fields *info, FILE *fp, param *p, unsigned long refnum ); +static void risout_writeheader( FILE *outptr, param *p ); + + void risout_initparams( param *p, const char *progname ) { @@ -44,7 +49,7 @@ } enum { - TYPE_UNKNOWN, + TYPE_UNKNOWN = 0, TYPE_STD, /* standard/generic */ TYPE_ABSTRACT, /* abstract */ TYPE_ARTICLE, /* article */ @@ -55,9 +60,9 @@ TYPE_ELEC, /* electronic */ TYPE_HEAR, /* hearing */ TYPE_MAGARTICLE, /* magazine article */ - TYPE_NEWS, /* newspaper */ + TYPE_NEWSPAPER, /* newspaper */ TYPE_MPCT, /* mpct */ - TYPE_PAMP, /* pamphlet */ + TYPE_PAMPHLET, /* pamphlet */ TYPE_PATENT, /* patent */ TYPE_PCOMM, /* personal communication */ TYPE_PROGRAM, /* program */ @@ -71,43 +76,80 @@ TYPE_HABILITATIONTHESIS, /* thesis */ TYPE_MAP, /* map, cartographic data */ TYPE_UNPUBLISHED, /* unpublished */ + NUM_TYPES }; +static int type_is_element[ NUM_TYPES ] = { + [ 0 ... NUM_TYPES-1 ] = 0, + [ TYPE_ARTICLE ] = 1, + [ TYPE_INBOOK ] = 1, + [ TYPE_MAGARTICLE ] = 1, + [ TYPE_NEWSPAPER ] = 1, + [ TYPE_ABSTRACT ] = 1, + [ TYPE_CONF ] = 1, +}; + +static int type_uses_journal[ NUM_TYPES ] = { + [ 0 ... NUM_TYPES-1 ] = 0, + [ TYPE_ARTICLE ] = 1, + [ TYPE_MAGARTICLE ] = 1, +}; + static void write_type( FILE *fp, int type ) { - switch( type ) { - case TYPE_UNKNOWN: fprintf( fp, "TYPE_UNKNOWN" ); break; - case TYPE_STD: fprintf( fp, "TYPE_STD" ); break; - case TYPE_ABSTRACT: fprintf( fp, "TYPE_ABSTRACT" ); break; - case TYPE_ARTICLE: fprintf( fp, "TYPE_ARTICLE" ); break; - case TYPE_BOOK: fprintf( fp, "TYPE_BOOK" ); break; - case TYPE_CASE: fprintf( fp, "TYPE_CASE" ); break; - case TYPE_INBOOK: fprintf( fp, "TYPE_INBOOK" ); break; - case TYPE_CONF: fprintf( fp, "TYPE_CONF" ); break; - case TYPE_ELEC: fprintf( fp, "TYPE_ELEC" ); break; - case TYPE_HEAR: fprintf( fp, "TYPE_HEAR" ); break; - case TYPE_MAGARTICLE: fprintf( fp, "TYPE_MAGARTICLE" ); break; - case TYPE_NEWS: fprintf( fp, "TYPE_NEWS" ); break; - case TYPE_MPCT: fprintf( fp, "TYPE_MCPT" ); break; - case TYPE_PAMP: fprintf( fp, "TYPE_PAMP" ); break; - case TYPE_PATENT: fprintf( fp, "TYPE_PATENT" ); break; - case TYPE_PCOMM: fprintf( fp, "TYPE_PCOMM" ); break; - case TYPE_PROGRAM: fprintf( fp, "TYPE_PROGRAM" ); break; - case TYPE_REPORT: fprintf( fp, "TYPE_REPORT" ); break; - case TYPE_STATUTE: fprintf( fp, "TYPE_STATUTE" ); break; - case TYPE_THESIS: fprintf( fp, "TYPE_THESIS" ); break; - case TYPE_MASTERSTHESIS: fprintf( fp, "TYPE_MASTERSTHESIS" ); break; - case TYPE_PHDTHESIS: fprintf( fp, "TYPE_PHDTHESIS" ); break; - case TYPE_DIPLOMATHESIS: fprintf( fp, "TYPE_DIPLOMATHESIS" ); break; - case TYPE_DOCTORALTHESIS: fprintf( fp, "TYPE_DOCTORALTHESIS" ); break; - case TYPE_HABILITATIONTHESIS: fprintf( fp, "TYPE_HABILITATIONTHESIS" ); break; - case TYPE_MAP: fprintf( fp, "TYPE_MAP" ); break; - case TYPE_UNPUBLISHED: fprintf( fp, "TYPE_UNPUBLISHED" ); break; - default: fprintf( fp, "Error - type not in enum" );break; - } + const char *typenames[ NUM_TYPES ] = { + [ TYPE_UNKNOWN ] = "TYPE_UNKNOWN", + [ TYPE_STD ] = "TYPE_STD", + [ TYPE_ABSTRACT ] = "TYPE_ABSTRACT", + [ TYPE_ARTICLE ] = "TYPE_ARTICLE", + [ TYPE_BOOK ] = "TYPE_BOOK", + [ TYPE_CASE ] = "TYPE_CASE", + [ TYPE_INBOOK ] = "TYPE_INBOOK", + [ TYPE_CONF ] = "TYPE_CONF", + [ TYPE_ELEC ] = "TYPE_ELEC", + [ TYPE_HEAR ] = "TYPE_HEAR", + [ TYPE_MAGARTICLE ] = "TYPE_MAGARTICLE", + [ TYPE_NEWSPAPER ] = "TYPE_NEWSPAPER", + [ TYPE_MPCT ] = "TYPE_MPCT", + [ TYPE_PAMPHLET ] = "TYPE_PAMPHLET", + [ TYPE_PATENT ] = "TYPE_PATENT", + [ TYPE_PCOMM ] = "TYPE_PCOMM", + [ TYPE_PROGRAM ] = "TYPE_PROGRAM", + [ TYPE_REPORT ] = "TYPE_REPORT", + [ TYPE_STATUTE ] = "TYPE_STATUTE", + [ TYPE_THESIS ] = "TYPE_THESIS", + [ TYPE_MASTERSTHESIS ] = "TYPE_MASTERSTHESIS", + [ TYPE_PHDTHESIS ] = "TYPE_PHDTHESIS", + [ TYPE_DIPLOMATHESIS ] = "TYPE_DIPLOMATHESIS", + [ TYPE_DOCTORALTHESIS ] = "TYPE_DOCTORALTHESIS", + [ TYPE_HABILITATIONTHESIS ] = "TYPE_HABILITATIONTHESIS", + [ TYPE_MAP ] = "TYPE_MAP", + [ TYPE_UNPUBLISHED ] = "TYPE_UNPUBLISHED", + }; + + if ( type < 0 || type >= NUM_TYPES ) fprintf( fp, "Error - type not in enum" ); + else fprintf( fp, "%s", typenames[ type ] ); } +static void +verbose_type_identified( char *element_type, param *p, int type ) +{ + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Type from %s element: ", element_type ); + write_type( stderr, type ); + fprintf( stderr, "\n" ); +} + +static void +verbose_type_assignment( char *tag, char *value, param *p, int type ) +{ + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Type from tag '%s' data '%s': ", tag, value ); + write_type( stderr, type ); + fprintf( stderr, "\n" ); +} + typedef struct match_type { char *name; int type; @@ -125,7 +167,7 @@ { "journal article", TYPE_ARTICLE }, { "magazine", TYPE_MAGARTICLE }, { "conference publication", TYPE_CONF }, - { "newspaper", TYPE_NEWS }, + { "newspaper", TYPE_NEWSPAPER }, { "legislation", TYPE_STATUTE }, { "communication", TYPE_PCOMM }, { "hearing", TYPE_HEAR }, @@ -144,26 +186,19 @@ { "map", TYPE_MAP }, }; int nmatch_genres = sizeof( match_genres ) / sizeof( match_genres[0] ); - int type, i, j; char *tag, *value; + int type, i, j; type = TYPE_UNKNOWN; for ( i=0; i<fields_num( f ); ++i ) { - if ( !fields_match_tag( f, i, "GENRE" ) && - !fields_match_tag( f, i, "NGENRE" ) ) - continue; + tag = ( char * ) fields_tag( f, i, FIELDS_CHRP ); + if ( strcmp( tag, "GENRE" ) && strcmp( tag, "NGENRE" ) ) continue; value = ( char * ) fields_value( f, i, FIELDS_CHRP ); for ( j=0; j<nmatch_genres; ++j ) if ( !strcasecmp( match_genres[j].name, value ) ) type = match_genres[j].type; - if ( p->verbose ) { - tag = ( char * ) fields_tag( f, i, FIELDS_CHRP ); - if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, "Type from tag '%s' data '%s': ", tag, value ); - write_type( stderr, type ); - fprintf( stderr, "\n" ); - } + if ( p->verbose ) verbose_type_assignment( tag, value, p, type ); if ( type==TYPE_UNKNOWN ) { if ( !strcasecmp( value, "periodical" ) ) type = TYPE_ARTICLE; @@ -181,12 +216,7 @@ } - if ( p->verbose ) { - if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, "Type from genre element: " ); - write_type( stderr, type ); - fprintf( stderr, "\n" ); - } + if ( p->verbose ) verbose_type_identified( "genre", p, type ); return type; } @@ -202,7 +232,8 @@ { "cartographic", TYPE_MAP }, }; int nmatch_res = sizeof( match_res ) / sizeof( match_res[0] ); - int type, i, j; + vplist_index i; + int type, j; char *value; vplist a; @@ -217,20 +248,10 @@ if ( !strcasecmp( value, match_res[j].name ) ) type = match_res[j].type; } - if ( p->verbose ) { - if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, "Type from tag 'RESOURCE' data '%s': ", value ); - write_type( stderr, type ); - fprintf( stderr, "\n" ); - } + if ( p->verbose ) verbose_type_assignment( "RESOURCE", value, p, type ); } - if ( p->verbose ) { - if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, "Type from resource element: " ); - write_type( stderr, type ); - fprintf( stderr, "\n" ); - } + if ( p->verbose ) verbose_type_identified( "resource", p, type ); vplist_free( &a ); return type; @@ -245,13 +266,13 @@ int i, monographic = 0, monographic_level = 0; // int text = 0; for ( i=0; i<f->n; ++i ) { - if ( !strcasecmp( f->tag[i].data, "issuance" ) && - !strcasecmp( f->data[i].data, "MONOGRAPHIC" ) ){ + if ( !strcasecmp( (char *) fields_tag( f, i, FIELDS_CHRP_NOUSE ), "issuance" ) && + !strcasecmp( (char *) fields_value( f, i, FIELDS_CHRP_NOUSE ), "MONOGRAPHIC" ) ){ monographic = 1; monographic_level = f->level[i]; } -// if ( !strcasecmp( f->tag[i].data, "typeOfResource" ) && -// !strcasecmp( f->data[i].data,"text") ) { +// if ( !strcasecmp( (char *) fields_tag( f, i, FIELDS_CHRP_NOUSE ), "typeOfResource" ) && +// !strcasecmp( (char *) fields_value( f, i, FIELDS_CHRP_NOUSE ), "text" ) ) { // text = 1; // } } @@ -295,242 +316,241 @@ } static void -output_type( FILE *fp, int type, param *p ) +append_type( int type, param *p, fields *out, int *status ) { - match_type tyout[] = { - { "STD", TYPE_STD }, - { "ABST", TYPE_ABSTRACT }, - { "JOUR", TYPE_ARTICLE }, - { "BOOK", TYPE_BOOK }, - { "CASE", TYPE_CASE }, - { "CHAP", TYPE_INBOOK }, - { "CONF", TYPE_CONF }, - { "ELEC", TYPE_ELEC }, - { "HEAR", TYPE_HEAR }, - { "MGZN", TYPE_MAGARTICLE }, - { "NEWS", TYPE_NEWS }, - { "MPCT", TYPE_MPCT }, - { "PAMP", TYPE_PAMP }, - { "PAT", TYPE_PATENT }, - { "PCOMM",TYPE_PCOMM }, - { "COMP", TYPE_PROGRAM }, - { "RPRT", TYPE_REPORT }, - { "STAT", TYPE_STATUTE }, - { "THES", TYPE_THESIS }, - { "THES", TYPE_MASTERSTHESIS }, - { "THES", TYPE_PHDTHESIS }, - { "THES", TYPE_DIPLOMATHESIS }, - { "THES", TYPE_DOCTORALTHESIS }, - { "THES", TYPE_HABILITATIONTHESIS }, - { "MAP", TYPE_MAP }, - { "UNPB", TYPE_UNPUBLISHED } + char *typenames[ NUM_TYPES ] = { + [ TYPE_STD ] = "STD", + [ TYPE_ABSTRACT ] = "ABST", + [ TYPE_ARTICLE ] = "JOUR", + [ TYPE_BOOK ] = "BOOK", + [ TYPE_CASE ] = "CASE", + [ TYPE_INBOOK ] = "CHAP", + [ TYPE_CONF ] = "CONF", + [ TYPE_ELEC ] = "ELEC", + [ TYPE_HEAR ] = "HEAR", + [ TYPE_MAGARTICLE ] = "MGZN", + [ TYPE_NEWSPAPER ] = "NEWS", + [ TYPE_MPCT ] = "MPCT", + [ TYPE_PAMPHLET ] = "PAMP", + [ TYPE_PATENT ] = "PAT", + [ TYPE_PCOMM ] = "PCOMM", + [ TYPE_PROGRAM ] = "COMP", + [ TYPE_REPORT ] = "RPRT", + [ TYPE_STATUTE ] = "STAT", + [ TYPE_THESIS ] = "THES", + [ TYPE_MASTERSTHESIS ] = "THES", + [ TYPE_PHDTHESIS ] = "THES", + [ TYPE_DIPLOMATHESIS ] = "THES", + [ TYPE_DOCTORALTHESIS ] = "THES", + [ TYPE_HABILITATIONTHESIS ] = "THES", + [ TYPE_MAP ] = "MAP", + [ TYPE_UNPUBLISHED ] = "UNPB", }; - int ntyout = sizeof( tyout ) / sizeof( tyout[0] ); - int i, found; + int fstatus; - fprintf( fp, "TY - " ); - found = 0; - for ( i=0; i<ntyout && !found ; ++i ) { - if ( tyout[i].type == type ) { - fprintf( fp, "%s", tyout[i].name ); - found = 1; - } - } - /* Report internal error, default to TYPE_STD */ - if ( !found ) { + if ( type < 0 || type >= NUM_TYPES ) { if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); - fprintf( stderr, "Internal Error: Cannot identify type %d\n", - type ); - fprintf( fp, "STD" ); + fprintf( stderr, "Internal error: Cannot recognize type %d, switching to TYPE_STD %d\n", type, TYPE_STD ); + type = TYPE_STD; } - fprintf( fp, "\n" ); + + fstatus = fields_add( out, "TY", typenames[ type ], LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } static void -output_people( FILE *fp, fields *f, char *tag, char *ristag, int level ) +append_people( fields *f, char *tag, char *ristag, int level, fields *out, int *status ) { - newstr oneperson; + vplist_index i; + str oneperson; vplist people; - int i; - newstr_init( &oneperson ); + int fstatus; + + str_init( &oneperson ); vplist_init( &people ); fields_findv_each( f, level, FIELDS_CHRP, &people, tag ); for ( i=0; i<people.n; ++i ) { name_build_withcomma( &oneperson, ( char * ) vplist_get( &people, i ) ); - fprintf( fp, "%s - %s\n", ristag, oneperson.data ); + if ( str_memerr( &oneperson ) ) { *status = BIBL_ERR_MEMERR; goto out; } + fstatus = fields_add_can_dup( out, ristag, str_cstr( &oneperson ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { *status = BIBL_ERR_MEMERR; goto out; } } +out: vplist_free( &people ); - newstr_free( &oneperson ); + str_free( &oneperson ); } static void -output_date( FILE *fp, fields *f ) +append_date( fields *in, fields *out, int *status ) { - char *year = fields_findv_firstof( f, LEVEL_ANY, FIELDS_CHRP, - "YEAR", "PARTYEAR", NULL ); - char *month = fields_findv_firstof( f, LEVEL_ANY, FIELDS_CHRP, - "MONTH", "PARTMONTH", NULL ); - char *day = fields_findv_firstof( f, LEVEL_ANY, FIELDS_CHRP, - "DAY", "PARTDAY", NULL ); - if ( year ) - fprintf( fp, "PY - %s\n", year ); + char *year, *month, *day; + str date; + int fstatus; + + year = fields_findv_firstof( in, LEVEL_ANY, FIELDS_CHRP, "DATE:YEAR", "PARTDATE:YEAR", NULL ); + month = fields_findv_firstof( in, LEVEL_ANY, FIELDS_CHRP, "DATE:MONTH", "PARTDATE:MONTH", NULL ); + day = fields_findv_firstof( in, LEVEL_ANY, FIELDS_CHRP, "DATE:DAY", "PARTDATE:DAY", NULL ); + + if ( year ) { + fstatus = fields_add( out, "PY", year, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + if ( year || month || day ) { - fprintf( fp, "DA - " ); - if ( year ) fprintf( fp, "%s", year ); - fprintf( fp, "/" ); - if ( month ) fprintf( fp, "%s", month ); - fprintf( fp, "/" ); - if ( day ) fprintf( fp, "%s", day ); - fprintf( fp, "\n" ); + str_init( &date ); + + if ( year ) str_strcatc( &date, year ); + str_addchar( &date, '/' ); + if ( month ) str_strcatc( &date, month ); + str_addchar( &date, '/' ); + if ( day ) str_strcatc( &date, day ); + + if ( str_memerr( &date ) ) { *status = BIBL_ERR_MEMERR; str_free( &date ); return; } + + fstatus = fields_add( out, "DA", str_cstr( &date ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + + str_free( &date ); } } static void -output_titlecore( FILE *fp, fields *f, char *ristag, int level, - char *maintag, char *subtag ) +append_titlecore( fields *in, char *ristag, int level, char *maintag, char *subtag, fields *out, int *status ) { - newstr *mainttl = fields_findv( f, level, FIELDS_STRP, maintag ); - newstr *subttl = fields_findv( f, level, FIELDS_STRP, subtag ); + str *mainttl = fields_findv( in, level, FIELDS_STRP, maintag ); + str *subttl = fields_findv( in, level, FIELDS_STRP, subtag ); + str fullttl; + int fstatus; - if ( !mainttl ) return; + str_init( &fullttl ); - fprintf( fp, "%s - %s", ristag, mainttl->data ); - if ( subttl ) { - if ( mainttl->len > 0 && - mainttl->data[ mainttl->len - 1 ]!='?' ) - fprintf( fp, ":" ); - fprintf( fp, " %s", subttl->data ); + title_combine( &fullttl, mainttl, subttl ); + + if ( str_memerr( &fullttl ) ) { + *status = BIBL_ERR_MEMERR; + goto out; } - fprintf( fp, "\n" ); -} -static int -type_is_element( int type ) -{ - if ( type==TYPE_ARTICLE ) return 1; - if ( type==TYPE_INBOOK ) return 1; - if ( type==TYPE_MAGARTICLE ) return 1; - if ( type==TYPE_NEWS ) return 1; - if ( type==TYPE_ABSTRACT ) return 1; - if ( type==TYPE_CONF ) return 1; - return 0; -} + if ( str_has_value( &fullttl ) ) { + fstatus = fields_add( out, ristag, str_cstr( &fullttl ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } -static int -type_uses_journal( int type ) -{ - if ( type==TYPE_ARTICLE ) return 1; - if ( type==TYPE_MAGARTICLE ) return 1; - return 0; +out: + str_free( &fullttl ); } static void -output_alltitles( FILE *fp, fields *f, int type ) +append_alltitles( fields *in, int type, fields *out, int *status ) { - output_titlecore( fp, f, "TI", 0, "TITLE", "SUBTITLE" ); - output_titlecore( fp, f, "T2", -1, "SHORTTITLE", "SHORTSUBTITLE" ); - if ( type_is_element( type ) ) { - if ( type_uses_journal( type ) ) - output_titlecore( fp, f, "JO", 1, "TITLE", "SUBTITLE" ); - else output_titlecore( fp, f, "BT", 1, "TITLE", "SUBTITLE" ); - output_titlecore( fp, f, "T3", 2, "TITLE", "SUBTITLE" ); + append_titlecore( in, "TI", 0, "TITLE", "SUBTITLE", out, status ); + append_titlecore( in, "T2", -1, "SHORTTITLE", "SHORTSUBTITLE", out, status ); + if ( type_is_element[ type ] ) { + if ( type_uses_journal[ type ] ) + append_titlecore( in, "JO", 1, "TITLE", "SUBTITLE", out, status ); + else append_titlecore( in, "BT", 1, "TITLE", "SUBTITLE", out, status ); + append_titlecore( in, "T3", 2, "TITLE", "SUBTITLE", out, status ); } else { - output_titlecore( fp, f, "T3", 1, "TITLE", "SUBTITLE" ); + append_titlecore( in, "T3", 1, "TITLE", "SUBTITLE", out, status ); } } static void -output_pages( FILE *fp, fields *f ) +append_pages( fields *in, fields *out, int *status ) { - char *sn = fields_findv( f, LEVEL_ANY, FIELDS_CHRP, "PAGESTART" ); - char *en = fields_findv( f, LEVEL_ANY, FIELDS_CHRP, "PAGEEND" ); - char *ar; + char *sn, *en, *ar; + int fstatus; + sn = fields_findv( in, LEVEL_ANY, FIELDS_CHRP, "PAGES:START" ); + en = fields_findv( in, LEVEL_ANY, FIELDS_CHRP, "PAGES:STOP" ); + if ( sn || en ) { - if ( sn ) fprintf( fp, "SP - %s\n", sn ); - if ( en ) fprintf( fp, "EP - %s\n", en ); + if ( sn ) { + fstatus = fields_add( out, "SP", sn, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + if ( en ) { + fstatus = fields_add( out, "EP", en, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } } else { - ar = fields_findv( f, LEVEL_ANY, FIELDS_CHRP, "ARTICLENUMBER" ); - if ( ar ) fprintf( fp, "SP - %s\n", ar ); + ar = fields_findv( in, LEVEL_ANY, FIELDS_CHRP, "ARTICLENUMBER" ); + if ( ar ) { + fstatus = fields_add( out, "SP", ar, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } } } static void -output_keywords( FILE *fp, fields *f ) +append_keywords( fields *in, fields *out, int *status ) { + vplist_index i; + int fstatus; vplist vpl; - int i; + vplist_init( &vpl ); - fields_findv_each( f, LEVEL_ANY, FIELDS_CHRP, &vpl, "KEYWORD" ); - for ( i=0; i<vpl.n; ++i ) - fprintf( fp, "KW - %s\n", ( char * ) vplist_get( &vpl, i ) ); + fields_findv_each( in, LEVEL_ANY, FIELDS_CHRP, &vpl, "KEYWORD" ); + for ( i=0; i<vpl.n; ++i ) { + fstatus = fields_add( out, "KW", ( char * ) vplist_get( &vpl, i ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } vplist_free( &vpl ); } static void -output_pmid( FILE *fp, fields *f ) +append_urls( fields *in, fields *out, int *status ) { - newstr s; - int i; - newstr_init( &s ); - for ( i=0; i<fields_num( f ); ++i ) { - if ( !fields_match_tag( f, i, "PMID" ) ) continue; - pmid_to_url( f, i, "URL", &s ); - if ( s.len ) - fprintf( fp, "UR - %s\n", s.data ); + int lstatus; + slist types; + + lstatus = slist_init_valuesc( &types, "URL", "DOI", "PMID", "PMC", "ARXIV", "JSTOR", "MRNUMBER", NULL ); + if ( lstatus!=SLIST_OK ) { + *status = BIBL_ERR_MEMERR; + return; } - newstr_free( &s ); + + *status = urls_merge_and_add( in, LEVEL_ANY, out, "UR", LEVEL_MAIN, &types ); + + slist_free( &types ); + } static void -output_arxiv( FILE *fp, fields *f ) +append_thesishint( int type, fields *out, int *status ) { - newstr s; - int i; - newstr_init( &s ); - for ( i=0; i<fields_num( f ); ++i ) { - if ( !fields_match_tag( f, i, "ARXIV" ) ) continue; - arxiv_to_url( f, i, "URL", &s ); - if ( s.len ) - fprintf( fp, "UR - %s\n", s.data ); + int fstatus; + + if ( type==TYPE_MASTERSTHESIS ) { + fstatus = fields_add( out, "U1", "Masters thesis", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } - newstr_free( &s ); -} -static void -output_jstor( FILE *fp, fields *f ) -{ - newstr s; - int i; - newstr_init( &s ); - for ( i=0; i<fields_num( f ); ++i ) { - if ( !fields_match_tag( f, i, "JSTOR" ) ) continue; - jstor_to_url( f, i, "URL", &s ); - if ( s.len ) - fprintf( fp, "UR - %s\n", s.data ); + else if ( type==TYPE_PHDTHESIS ) { + fstatus = fields_add( out, "U1", "Ph.D. thesis", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; } - newstr_free( &s ); -} -static void -output_thesishint( FILE *fp, int type ) -{ - if ( type==TYPE_MASTERSTHESIS ) - fprintf( fp, "%s - %s\n", "U1", "Masters thesis" ); - else if ( type==TYPE_PHDTHESIS ) - fprintf( fp, "%s - %s\n", "U1", "Ph.D. thesis" ); - else if ( type==TYPE_DIPLOMATHESIS ) - fprintf( fp, "%s - %s\n", "U1", "Diploma thesis" ); - else if ( type==TYPE_DOCTORALTHESIS ) - fprintf( fp, "%s - %s\n", "U1", "Doctoral thesis" ); - else if ( type==TYPE_HABILITATIONTHESIS ) - fprintf( fp, "%s - %s\n", "U1", "Habilitation thesis" ); + else if ( type==TYPE_DIPLOMATHESIS ) { + fstatus = fields_add( out, "U1", "Diploma thesis", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + + else if ( type==TYPE_DOCTORALTHESIS ) { + fstatus = fields_add( out, "U1", "Doctoral thesis", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } + + else if ( type==TYPE_HABILITATIONTHESIS ) { + fstatus = fields_add( out, "U1", "Habilitation thesis", LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } } static int is_uri_scheme( char *p ) { - char *scheme[] = { "http:", "file:", "ftp:", "git:", "gopher:" }; + char *scheme[] = { "http:", "https:", "file:", "ftp:", "git:", "gopher:" }; int i, len, nschemes = sizeof( scheme ) / sizeof( scheme[0] ); for ( i=0; i<nschemes; ++i ) { len = strlen( scheme[i] ); @@ -541,120 +561,164 @@ static void -output_file( FILE *fp, fields *f, char *tag, char *ristag, int level ) +append_file( fields *in, char *tag, char *ristag, int level, fields *out, int *status ) { + vplist_index i; + str filename; + int fstatus; vplist a; char *fl; - int i; + + str_init( &filename ); vplist_init( &a ); - fields_findv_each( f, level, FIELDS_CHRP, &a, tag ); + fields_findv_each( in, level, FIELDS_CHRP, &a, tag ); for ( i=0; i<a.n; ++i ) { - fprintf( fp, "%s - ", ristag ); fl = ( char * ) vplist_get( &a, i ); - if ( !is_uri_scheme( fl ) ) - fprintf( fp, "file:" ); - fprintf( fp, "%s\n", fl ); + str_empty( &filename ); + if ( !is_uri_scheme( fl ) ) str_strcatc( &filename, "file:" ); + str_strcatc( &filename, fl ); + if ( str_memerr( &filename ) ) { *status = BIBL_ERR_MEMERR; goto out; } + fstatus = fields_add( out, ristag, str_cstr( &filename ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) { *status = BIBL_ERR_MEMERR; goto out; } } +out: vplist_free( &a ); + str_free( &filename ); } static void -output_easy( FILE *fp, fields *f, char *tag, char *ristag, int level ) +append_easy( fields *in, char *tag, char *ristag, int level, fields *out, int *status ) { - char *value = fields_findv( f, level, FIELDS_CHRP, tag ); - if ( value ) fprintf( fp, "%s - %s\n", ristag, value ); + char *value; + int fstatus; + + value = fields_findv( in, level, FIELDS_CHRP, tag ); + if ( value ) { + fstatus = fields_add( out, ristag, value, LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } } static void -output_easyall( FILE *fp, fields *f, char *tag, char *ristag, int level ) +append_easyall( fields *in, char *tag, char *ristag, int level, fields *out, int *status ) { + vplist_index i; + int fstatus; vplist a; - int i; + vplist_init( &a ); - fields_findv_each( f, level, FIELDS_CHRP, &a, tag ); - for ( i=0; i<a.n; ++i ) - fprintf( fp, "%s - %s\n", ristag, (char *) vplist_get( &a, i ) ); + fields_findv_each( in, level, FIELDS_CHRP, &a, tag ); + for ( i=0; i<a.n; ++i ) { + fstatus = fields_add( out, ristag, (char *) vplist_get( &a, i ), LEVEL_MAIN ); + if ( fstatus!=FIELDS_OK ) *status = BIBL_ERR_MEMERR; + } vplist_free( &a ); } static void -output_allpeople( FILE *fp, fields *f, int type ) +append_allpeople( fields *in, int type, fields *out, int *status ) { - output_people( fp, f, "AUTHOR", "AU", LEVEL_MAIN ); - output_easyall( fp, f, "AUTHOR:CORP", "AU", LEVEL_MAIN ); - output_easyall( fp, f, "AUTHOR:ASIS", "AU", LEVEL_MAIN ); - output_people( fp, f, "AUTHOR", "A2", LEVEL_HOST ); - output_easyall( fp, f, "AUTHOR:CORP", "A2", LEVEL_HOST ); - output_easyall( fp, f, "AUTHOR:ASIS", "A2", LEVEL_HOST ); - output_people( fp, f, "AUTHOR", "A3", LEVEL_SERIES ); - output_easyall( fp, f, "AUTHOR:CORP", "A3", LEVEL_SERIES ); - output_easyall( fp, f, "AUTHOR:ASIS", "A3", LEVEL_SERIES ); - output_people( fp, f, "EDITOR", "ED", LEVEL_MAIN ); - output_easyall( fp, f, "EDITOR:CORP", "ED", LEVEL_MAIN ); - output_easyall( fp, f, "EDITOR:ASIS", "ED", LEVEL_MAIN ); - if ( type_is_element( type ) ) { - output_people( fp, f, "EDITOR", "ED", LEVEL_HOST ); - output_easyall( fp, f, "EDITOR:CORP", "ED", LEVEL_HOST ); - output_easyall( fp, f, "EDITOR:ASIS", "ED", LEVEL_HOST ); + append_people ( in, "AUTHOR", "AU", LEVEL_MAIN, out, status ); + append_easyall( in, "AUTHOR:CORP", "AU", LEVEL_MAIN, out, status ); + append_easyall( in, "AUTHOR:ASIS", "AU", LEVEL_MAIN, out, status ); + append_people ( in, "AUTHOR", "A2", LEVEL_HOST, out, status ); + append_easyall( in, "AUTHOR:CORP", "A2", LEVEL_HOST, out, status ); + append_easyall( in, "AUTHOR:ASIS", "A2", LEVEL_HOST, out, status ); + append_people ( in, "AUTHOR", "A3", LEVEL_SERIES, out, status ); + append_easyall( in, "AUTHOR:CORP", "A3", LEVEL_SERIES, out, status ); + append_easyall( in, "AUTHOR:ASIS", "A3", LEVEL_SERIES, out, status ); + append_people ( in, "EDITOR", "ED", LEVEL_MAIN, out, status ); + append_easyall( in, "EDITOR:CORP", "ED", LEVEL_MAIN, out, status ); + append_easyall( in, "EDITOR:ASIS", "ED", LEVEL_MAIN, out, status ); + if ( type_is_element[ type ] ) { + append_people ( in, "EDITOR", "ED", LEVEL_HOST, out, status ); + append_easyall( in, "EDITOR:CORP", "ED", LEVEL_HOST, out, status ); + append_easyall( in, "EDITOR:ASIS", "ED", LEVEL_HOST, out, status ); } else { - output_people( fp, f, "EDITOR", "A3", LEVEL_HOST ); - output_easyall( fp, f, "EDITOR:CORP", "A3", LEVEL_HOST ); - output_easyall( fp, f, "EDITOR:ASIS", "A3", LEVEL_HOST ); + append_people ( in, "EDITOR", "A3", LEVEL_HOST, out, status ); + append_easyall( in, "EDITOR:CORP", "A3", LEVEL_HOST, out, status ); + append_easyall( in, "EDITOR:ASIS", "A3", LEVEL_HOST, out, status ); } - output_people( fp, f, "EDITOR", "A3", LEVEL_SERIES ); - output_easyall( fp, f, "EDITOR:CORP", "A3", LEVEL_SERIES ); - output_easyall( fp, f, "EDITOR:ASIS", "A3", LEVEL_SERIES ); + append_people ( in, "EDITOR", "A3", LEVEL_SERIES, out, status ); + append_easyall( in, "EDITOR:CORP", "A3", LEVEL_SERIES, out, status ); + append_easyall( in, "EDITOR:ASIS", "A3", LEVEL_SERIES, out, status ); } -void -risout_write( fields *f, FILE *fp, param *p, unsigned long refnum ) +static void +output( FILE *fp, fields *out ) { - int type; - type = get_type( f, p ); - output_type( fp, type, p ); - - output_allpeople( fp, f, type ); - - output_date( fp, f ); + char *tag, *value; + int i; - output_alltitles( fp, f, type ); + for ( i=0; i<out->n; ++i ) { + tag = fields_tag( out, i, FIELDS_CHRP ); + value = fields_value( out, i, FIELDS_CHRP ); + fprintf( fp, "%s - %s\n", tag, value ); + } - output_pages( fp, f ); - output_easy( fp, f, "VOLUME", "VL", LEVEL_ANY ); - output_easy( fp, f, "ISSUE", "IS", LEVEL_ANY ); - output_easy( fp, f, "NUMBER", "IS", LEVEL_ANY ); - output_easy( fp, f, "EDITION", "ET", LEVEL_ANY ); - output_easy( fp, f, "NUMVOLUMES", "NV", LEVEL_ANY ); - output_easy( fp, f, "AUTHORADDRESS", "AD", LEVEL_ANY ); - output_easy( fp, f, "PUBLISHER", "PB", LEVEL_ANY ); - output_easy( fp, f, "DEGREEGRANTOR", "PB", LEVEL_ANY ); - output_easy( fp, f, "DEGREEGRANTOR:ASIS", "PB", LEVEL_ANY ); - output_easy( fp, f, "DEGREEGRANTOR:CORP", "PB", LEVEL_ANY ); - output_easy( fp, f, "ADDRESS", "CY", LEVEL_ANY ); - output_keywords( fp, f ); - output_easy( fp, f, "ABSTRACT", "AB", LEVEL_ANY ); - output_easy( fp, f, "CALLNUMBER", "CN", LEVEL_ANY ); - output_easy( fp, f, "ISSN", "SN", LEVEL_ANY ); - output_easy( fp, f, "ISBN", "SN", LEVEL_ANY ); - output_easyall( fp, f, "URL", "UR", LEVEL_ANY ); - output_easyall( fp, f, "DOI", "DO", LEVEL_ANY ); - output_file( fp, f, "FILEATTACH", "L1", LEVEL_ANY ); - output_file( fp, f, "FIGATTACH", "L4", LEVEL_ANY ); - output_easy( fp, f, "CAPTION", "CA", LEVEL_ANY ); - output_pmid( fp, f ); - output_arxiv( fp, f ); - output_jstor( fp, f ); - output_easy( fp, f, "LANGUAGE", "LA", LEVEL_ANY ); - output_easy( fp, f, "NOTES", "N1", LEVEL_ANY ); - output_easy( fp, f, "REFNUM", "ID", LEVEL_ANY ); - output_thesishint( fp, type ); fprintf( fp, "ER - \n" ); fflush( fp ); } -void +static int +append_data( fields *in, param *p, fields *out ) +{ + int type, status = BIBL_OK; + + type = get_type( in, p ); + + append_type ( type, p, out, &status ); + append_allpeople ( in, type, out, &status ); + append_date ( in, out, &status ); + append_alltitles ( in, type, out, &status ); + append_pages ( in, out, &status ); + append_easy ( in, "VOLUME", "VL", LEVEL_ANY, out, &status ); + append_easy ( in, "ISSUE", "IS", LEVEL_ANY, out, &status ); + append_easy ( in, "NUMBER", "IS", LEVEL_ANY, out, &status ); + append_easy ( in, "EDITION", "ET", LEVEL_ANY, out, &status ); + append_easy ( in, "NUMVOLUMES", "NV", LEVEL_ANY, out, &status ); + append_easy ( in, "AUTHORADDRESS", "AD", LEVEL_ANY, out, &status ); + append_easy ( in, "PUBLISHER", "PB", LEVEL_ANY, out, &status ); + append_easy ( in, "DEGREEGRANTOR", "PB", LEVEL_ANY, out, &status ); + append_easy ( in, "DEGREEGRANTOR:ASIS", "PB", LEVEL_ANY, out, &status ); + append_easy ( in, "DEGREEGRANTOR:CORP", "PB", LEVEL_ANY, out, &status ); + append_easy ( in, "ADDRESS", "CY", LEVEL_ANY, out, &status ); + append_keywords ( in, out, &status ); + append_easy ( in, "ABSTRACT", "AB", LEVEL_ANY, out, &status ); + append_easy ( in, "CALLNUMBER", "CN", LEVEL_ANY, out, &status ); + append_easy ( in, "ISSN", "SN", LEVEL_ANY, out, &status ); + append_easy ( in, "ISBN", "SN", LEVEL_ANY, out, &status ); + append_file ( in, "FILEATTACH", "L1", LEVEL_ANY, out, &status ); + append_file ( in, "FIGATTACH", "L4", LEVEL_ANY, out, &status ); + append_easy ( in, "CAPTION", "CA", LEVEL_ANY, out, &status ); + append_urls ( in, out, &status ); + append_easyall ( in, "DOI", "DO", LEVEL_ANY, out, &status ); + append_easy ( in, "LANGUAGE", "LA", LEVEL_ANY, out, &status ); + append_easy ( in, "NOTES", "N1", LEVEL_ANY, out, &status ); + append_easy ( in, "REFNUM", "ID", LEVEL_ANY, out, &status ); + append_thesishint( type, out, &status ); + + return status; +} + +static int +risout_write( fields *in, FILE *fp, param *p, unsigned long refnum ) +{ + int status; + fields out; + + fields_init( &out ); + + status = append_data( in, p, &out ); + if ( status==BIBL_OK ) output( fp, &out ); + + fields_free( &out ); + + return status; +} + +static void risout_writeheader( FILE *outptr, param *p ) { if ( p->utf8bom ) utf8_writebom( outptr ); } - diff --git a/bibutils/risout.h b/bibutils/risout.h deleted file mode 100644 --- a/bibutils/risout.h +++ /dev/null @@ -1,22 +0,0 @@ -/* - * risout.h - * - * Copyright (c) Chris Putnam 2005-2013 - * - * Source code released under the GPL version 2 - * - */ -#ifndef RISOUT_H -#define RISOUT_H - -#include <stdio.h> -#include "bibutils.h" - -extern void risout_write( fields *info, FILE *fp, param *p, - unsigned long refnum ); -extern void risout_writeheader( FILE *outptr, param *p ); - -extern void risout_initparams( param *p, const char *progname ); - - -#endif diff --git a/bibutils/ristypes.c b/bibutils/ristypes.c --- a/bibutils/ristypes.c +++ b/bibutils/ristypes.c @@ -1,7 +1,7 @@ /* * ristypes.c * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2017 * * Source code released under the GPL version 2 * @@ -34,13 +34,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Name of Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -62,13 +62,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Resarch Notes -> Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Resarch Notes -> Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -80,11 +80,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated? */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated? */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ }; static lookups article[] = { @@ -108,13 +108,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_HOST }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -136,13 +136,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_HOST }, /* Publisher */ - { "PY", "PARTYEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "PARTDATE:YEAR",DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_HOST }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -154,12 +154,12 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "PARTYEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "PARTMONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ - { " ", "INTERNAL_TYPE|ARTICLE", ALWAYS, LEVEL_MAIN }, + { "Y1", "PARTDATE:YEAR",DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "PARTDATE:MONTH",SIMPLE, LEVEL_MAIN }, /* Access Date */ + { " ", "INTERNAL_TYPE|ARTICLE", ALWAYS, LEVEL_MAIN }, { " ", "ISSUANCE|continuing", ALWAYS, LEVEL_HOST }, { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|journal article", ALWAYS, LEVEL_MAIN }, @@ -189,13 +189,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_HOST }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -217,13 +217,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_HOST }, /* Publisher */ - { "PY", "PARTYEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "PARTDATE:YEAR",DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_HOST }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -235,11 +235,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "PARTYEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "PARTMONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "PARTDATE:YEAR",DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "PARTDATE:MONTH",SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "ISSUANCE|continuing", ALWAYS, LEVEL_HOST }, { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|periodical", ALWAYS, LEVEL_HOST }, @@ -267,13 +267,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_HOST }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -295,13 +295,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_HOST }, /* Publisher */ - { "PY", "PARTYEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "PARTDATE:YEAR",DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_HOST }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -313,15 +313,15 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "PARTYEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "PARTMONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ - { " ", "INTERNAL_TYPE|NEWSARTICLE", ALWAYS, LEVEL_MAIN }, - { " ", "ISSUANCE|continuing", ALWAYS, LEVEL_HOST }, - { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { " ", "GENRE|newspaper", ALWAYS, LEVEL_HOST } + { "Y1", "PARTDATE:YEAR",DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "PARTDATE:MONTH",SIMPLE, LEVEL_MAIN }, /* Access Date */ + { " ", "INTERNAL_TYPE|NEWSARTICLE", ALWAYS, LEVEL_MAIN }, + { " ", "ISSUANCE|continuing", ALWAYS, LEVEL_HOST }, + { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { " ", "GENRE|newspaper", ALWAYS, LEVEL_HOST } }; static lookups book[] = { @@ -346,13 +346,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -374,13 +374,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title -- here abbreviated title for series*/ @@ -392,14 +392,14 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ - { " ", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, - { " ", "GENRE|book", ALWAYS, LEVEL_MAIN }, - { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN } + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { " ", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, + { " ", "GENRE|book", ALWAYS, LEVEL_MAIN }, + { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN } }; static lookups inbook[] = { @@ -424,13 +424,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_HOST }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_HOST }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_HOST }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_HOST }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_HOST }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_HOST }, /* Number */ @@ -452,13 +452,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_HOST }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_HOST }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_HOST }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_HOST }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_SERIES }, /* 'Secondary' Title -- here abbreviated title for series*/ @@ -470,11 +470,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_HOST }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_HOST }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_HOST }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_HOST }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_HOST }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_HOST }, /* Access Date */ { " ", "GENRE|book chapter", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|book", ALWAYS, LEVEL_HOST }, { " ", "ISSUANCE|monographic", ALWAYS, LEVEL_HOST }, @@ -502,13 +502,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -530,13 +530,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_HOST }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_HOST }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_HOST }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "BT", "TITLE", SIMPLE, LEVEL_HOST }, /* Book Title */ @@ -549,12 +549,12 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_HOST }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_HOST }, /* Access Date */ - { " ", "INTERNAL_TYPE|CONFERENCE", ALWAYS, LEVEL_MAIN }, + { "Y1", "DATE:YEAR", DATE, LEVEL_HOST }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_HOST }, /* Access Date */ + { " ", "INTERNAL_TYPE|CONFERENCE", ALWAYS, LEVEL_MAIN }, { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|conference publication", ALWAYS, LEVEL_HOST } }; @@ -581,13 +581,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -609,13 +609,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -627,12 +627,12 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ - { " ", "INTERNAL_TYPE|STATUTE", ALWAYS, LEVEL_MAIN }, + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { " ", "INTERNAL_TYPE|STATUTE", ALWAYS, LEVEL_MAIN }, { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|legislation", ALWAYS, LEVEL_MAIN } }; @@ -659,13 +659,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -687,13 +687,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -705,11 +705,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "INTERNAL_TYPE|HEARING", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|hearing", ALWAYS, LEVEL_MAIN } }; @@ -736,13 +736,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -764,13 +764,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -782,11 +782,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "INTERNAL_TYPE|CASE", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|legal case and case notes", ALWAYS, LEVEL_MAIN } }; @@ -813,13 +813,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -841,13 +841,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -859,11 +859,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "INTERNAL_TYPE|ARTICLE", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|communication", ALWAYS, LEVEL_MAIN } }; @@ -890,13 +890,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -918,13 +918,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -936,11 +936,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "INTERNAL_TYPE|THESIS", ALWAYS, LEVEL_MAIN }, { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|thesis", ALWAYS, LEVEL_MAIN }, @@ -968,13 +968,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -996,13 +996,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -1014,11 +1014,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "INTERNAL_TYPE|REPORT", ALWAYS, LEVEL_MAIN }, { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|report", ALWAYS, LEVEL_MAIN } @@ -1046,13 +1046,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -1074,13 +1074,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -1092,11 +1092,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "GENRE|abstract or summary", ALWAYS, LEVEL_MAIN } }; @@ -1122,13 +1122,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -1150,13 +1150,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -1168,11 +1168,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "RESOURCE|software, multimedia", ALWAYS, LEVEL_MAIN } }; @@ -1198,13 +1198,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -1226,13 +1226,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -1244,11 +1244,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|patent", ALWAYS, LEVEL_MAIN } }; @@ -1275,13 +1275,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -1303,13 +1303,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -1321,11 +1321,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "RESOURCE|software, multimedia", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|electronic", ALWAYS, LEVEL_MAIN }, }; @@ -1352,13 +1352,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -1380,13 +1380,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -1398,11 +1398,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|pamphlet", ALWAYS, LEVEL_MAIN }, }; @@ -1429,13 +1429,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Name of Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -1457,13 +1457,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Resarch Notes -> Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Resarch Notes -> Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -1475,11 +1475,11 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated? */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated? */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ { " ", "RESOURCE|cartographic", ALWAYS, LEVEL_MAIN }, { " ", "GENRE|map", ALWAYS, LEVEL_MAIN } }; @@ -1506,13 +1506,13 @@ { "CP", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CT", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "CY", "ADDRESS", SIMPLE, LEVEL_MAIN }, /* Place Published */ - { "DA", "YEAR", DATE, LEVEL_MAIN }, /* Date */ + { "DA", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Date */ { "DB", "DATABASE", SIMPLE, LEVEL_MAIN }, /* Database */ { "DI", "DOI", DOI, LEVEL_MAIN }, /* Deprecated? */ { "DO", "DOI", DOI, LEVEL_MAIN }, /* DOI */ { "DP", "DATABASEPROV", SIMPLE, LEVEL_MAIN }, /* Database Provider */ { "ED", "EDITOR", PERSON, LEVEL_MAIN }, /* Deprecated? */ - { "EP", "PAGEEND", SIMPLE, LEVEL_MAIN }, /* End Page */ + { "EP", "PAGES:STOP", SIMPLE, LEVEL_MAIN }, /* End Page */ { "ET", "EDITION", SIMPLE, LEVEL_MAIN }, /* Edition */ { "ID", "REFNUM", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ { "IS", "ISSUE", SIMPLE, LEVEL_MAIN }, /* Number */ @@ -1534,13 +1534,13 @@ { "NV", "NUMVOLUMES", SIMPLE, LEVEL_MAIN }, /* Number of Volumes */ { "OP", "ORIGPUB", SIMPLE, LEVEL_MAIN }, /* Original Publication */ { "PB", "PUBLISHER", SIMPLE, LEVEL_MAIN }, /* Publisher */ - { "PY", "YEAR", DATE, LEVEL_MAIN }, /* Year */ + { "PY", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Year */ { "RI", "REVIEWEDITEM", SIMPLE, LEVEL_MAIN }, /* Reviewed Item */ - { "RN", "NOTES", SIMPLE, LEVEL_MAIN }, /* Research Notes */ + { "RN", "NOTES", NOTES, LEVEL_MAIN }, /* Research Notes */ { "RP", "REPRINTSTATUS",SIMPLE, LEVEL_MAIN }, /* Reprint Edition */ { "SE", "SECTION", SIMPLE, LEVEL_MAIN }, /* Section */ { "SN", "SERIALNUMBER", SERIALNO,LEVEL_MAIN }, /* ISBN/ISSN */ - { "SP", "PAGESTART", SIMPLE, LEVEL_MAIN }, /* Start Page */ + { "SP", "PAGES:START", SIMPLE, LEVEL_MAIN }, /* Start Page */ { "ST", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, /* Short Title */ { "T1", "TITLE", TITLE, LEVEL_MAIN }, /* Deprecated? */ { "T2", "SHORTTITLE", SIMPLE, LEVEL_HOST }, /* 'Secondary' Title */ @@ -1552,13 +1552,13 @@ { "U3", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U4", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ { "U5", "NOTES", NOTES, LEVEL_MAIN }, /* 'User' - Deprecated? */ - { "UR", "URL", SIMPLE, LEVEL_MAIN }, /* URL */ + { "UR", "URL", URL, LEVEL_MAIN }, /* URL */ { "VL", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Volume */ { "VO", "VOLUME", SIMPLE, LEVEL_MAIN }, /* Deprecated? */ - { "Y1", "YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ - { "Y2", "MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ - { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { " ", "GENRE|unpublished", ALWAYS, LEVEL_MAIN } + { "Y1", "DATE:YEAR", DATE, LEVEL_MAIN }, /* Deprecated */ + { "Y2", "DATE:MONTH", SIMPLE, LEVEL_MAIN }, /* Access Date */ + { " ", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { " ", "GENRE|unpublished", ALWAYS, LEVEL_MAIN } }; #define ORIG(a) ( &(a[0]) ) diff --git a/bibutils/serialno.c b/bibutils/serialno.c --- a/bibutils/serialno.c +++ b/bibutils/serialno.c @@ -1,7 +1,7 @@ /* * serialno.c * - * Copyright (c) Chris Putnam 2005-2014 + * Copyright (c) Chris Putnam 2005-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/serialno.h b/bibutils/serialno.h --- a/bibutils/serialno.h +++ b/bibutils/serialno.h @@ -1,7 +1,7 @@ /* * serialno.h * - * Copyright (c) Chris Putnam 2005-2014 + * Copyright (c) Chris Putnam 2005-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/slist.c b/bibutils/slist.c new file mode 100644 --- /dev/null +++ b/bibutils/slist.c @@ -0,0 +1,865 @@ +/* + * slist.c + * + * version: 2017-07-04 + * + * Copyright (c) Chris Putnam 2004-2017 + * + * Source code released under the GPL version 2 + * + * Implements a simple managed array of strs. + * + */ +#include "slist.h" + +/* Do not use asserts in VPLIST_NOASSERT defined */ +#ifdef VPLIST_NOASSERT +#define NDEBUG +#endif +#include <assert.h> + +#define SLIST_MINALLOC (20) + +#define SLIST_EXACT_SIZE (0) +#define SLIST_DOUBLE_SIZE (1) + +/* + * returns 1 if n is valid string in slist + */ +static inline int +slist_valid_num( slist *a, slist_index n ) +{ + if ( n < 0 || n >= a->n ) return 0; + return 1; +} + +void +slist_init( slist *a ) +{ + assert( a ); + + a->strs = NULL; + a->max = 0; + a->n = 0; + a->sorted = 1; +} + +int +slist_init_values( slist *a, ... ) +{ + int status = SLIST_OK; + va_list ap; + str *s, *t; + + slist_init( a ); + + va_start( ap, a ); + do { + s = va_arg( ap, str * ); + if ( s ) { + t = slist_add( a, s ); + if ( !t ) { + status = SLIST_ERR_MEMERR; + goto out; + } + } + } while ( s ); +out: + va_end( ap ); + + return status; +} + +int +slist_init_valuesc( slist *a, ... ) +{ + int status = SLIST_OK; + va_list ap; + char *s; + str *t; + + slist_init( a ); + + va_start( ap, a ); + do { + s = va_arg( ap, char * ); + if ( s ) { + t = slist_addc( a, s ); + if ( !t ) { + status = SLIST_ERR_MEMERR; + goto out; + } + } + } while ( s ); +out: + va_end( ap ); + + return status; +} + +void +slist_empty( slist *a ) +{ + slist_index i; + + assert( a ); + + for ( i=0; i<a->max; ++i ) + str_empty( &(a->strs[i]) ); + + a->n = 0; + a->sorted = 1; +} + +void +slist_free( slist *a ) +{ + slist_index i; + + assert( a ); + + for ( i=0; i<a->max; ++i ) + str_free( &(a->strs[i]) ); + + free( a->strs ); + slist_init( a ); +} + +slist * +slist_new( void ) +{ + slist *a; + + a = ( slist * ) malloc( sizeof ( slist ) ); + if ( a ) slist_init( a ); + + return a; +} + +void +slist_delete( slist *a ) +{ + assert( a ); + + slist_free( a ); + free( a ); +} + +void +slist_deletev( void *v ) +{ + slist_delete( (slist*) v ); +} + +void +slist_swap( slist *a, slist_index n1, slist_index n2 ) +{ + assert( a ); + + if ( slist_valid_num( a, n1 ) && slist_valid_num( a, n2 ) ) + str_swapstrings( &(a->strs[n1]), &(a->strs[n2]) ); +} + +static int +slist_comp( const void *v1, const void *v2 ) +{ + str *s1 = ( str *) v1; + str *s2 = ( str *) v2; + if ( !s1->len && !s2->len ) return 0; + else if ( !s1->len ) return -1; + else if ( !s2->len ) return 1; + else return str_strcmp( s1, s2 ); +} + +static int +slist_comp_step( slist *a, slist_index n1, slist_index n2 ) +{ + return slist_comp( (const void*) &(a->strs[n1]), (const void*) &(a->strs[n2]) ); +} + +static str * +slist_set_cleanup( slist *a, slist_index n ) +{ + if ( str_memerr( &(a->strs[n]) ) ) return NULL; + if ( a->sorted ) { + if ( n>0 && slist_comp_step( a, n-1, n )>0 ) + a->sorted = 0; + } + if ( a->sorted ) { + if ( n<a->n-1 && slist_comp_step( a, n, n+1 )>0 ) + a->sorted = 0; + } + return &(a->strs[n]); +} + +str * +slist_setc( slist *a, slist_index n, const char *s ) +{ + assert( a ); + assert( s ); + + if ( !slist_valid_num( a, n ) ) return NULL; + str_strcpyc( &(a->strs[n]), s ); + return slist_set_cleanup( a, n ); +} + +str * +slist_set( slist *a, slist_index n, str *s ) +{ + assert( s ); + + return slist_setc( a, n, str_cstr( s ) ); +} + +/* + * return pointer to str 'n' + */ +str * +slist_str( slist *a, slist_index n ) +{ + assert( a ); + + if ( !slist_valid_num( a, n ) ) return NULL; + else return &(a->strs[n]); +} + +/* + * return pointer to C string 'n' + * + * So long as the index is a valid number ensure + * that a pointer is returned even if the newstr isn't + * allocated. Only return NULL if the index + * is invalid. Thus we can convert loops like: + * + * for ( i=0; i<a->n; ++i ) { + * p = slist_cstr( a, i ); + * if ( p==NULL ) continue; // empty string + * ... + * } + * + * to + * + * i = 0; + * while ( ( p = slist_cstr( a, i ) ) ) { + * ... + * i++; + * } + * + */ +char * +slist_cstr( slist *a, slist_index n ) +{ + static char empty[] = ""; + char *p; + + assert( a ); + + if ( !slist_valid_num( a, n ) ) return NULL; + p = str_cstr( &(a->strs[n]) ); + if ( p ) return p; + else return empty; +} + +static inline int +slist_alloc( slist *a, slist_index alloc ) +{ + slist_index i; + + a->strs = ( str* ) malloc( sizeof( str ) * alloc ); + if ( !(a->strs) ) return SLIST_ERR_MEMERR; + + a->max = alloc; + a->n = 0; + + for ( i=0; i<alloc; ++i ) + str_init( &(a->strs[i]) ); + + return SLIST_OK; +} + +static inline int +slist_realloc( slist *a, slist_index alloc ) +{ + slist_index i; + str *more; + + more = ( str* ) realloc( a->strs, sizeof( str ) * alloc ); + if ( !more ) return SLIST_ERR_MEMERR; + + a->strs = more; + + for ( i=a->max; i<alloc; ++i ) + str_init( &(a->strs[i]) ); + + a->max = alloc; + + return SLIST_OK; +} + +#define SLIST_EXACT_SIZE (0) +#define SLIST_DOUBLE_SIZE (1) + +static int +slist_ensure_space( slist *a, slist_index n, int mode ) +{ + int status = SLIST_OK; + int alloc = n; + + if ( a->max==0 ) { + if ( mode == SLIST_DOUBLE_SIZE && alloc < SLIST_MINALLOC ) alloc = SLIST_MINALLOC; + status = slist_alloc( a, alloc ); + } + + else if ( a->max < n ) { + if ( mode == SLIST_DOUBLE_SIZE && alloc < a->max * 2 ) alloc = a->max * 2; + status = slist_realloc( a, alloc ); + } + + return status; +} + +str * +slist_addvp( slist *a, unsigned char mode, void *vp ) +{ + str *s = NULL; + int status; + + status = slist_ensure_space( a, a->n+1, SLIST_DOUBLE_SIZE ); + + if ( status==SLIST_OK ) { + + s = &( a->strs[a->n] ); + + if ( mode==SLIST_CHR ) + str_strcpyc( s, (const char*) vp ); + else + str_strcpy( s, (str*) vp ); + + if ( str_memerr( s ) ) return NULL; + a->n++; + if ( a->sorted && a->n > 1 ) { + if ( slist_comp_step( a, a->n-2, a->n-1 ) > 0 ) + a->sorted = 0; + } + + } + + return s; +} +str * +slist_addc( slist *a, const char *s ) +{ + return slist_addvp( a, SLIST_CHR, (void*)s ); +} +str * +slist_add( slist *a, str *s ) +{ + return slist_addvp( a, SLIST_STR, (void*)s ); +} + +str * +slist_addvp_unique( slist *a, unsigned char mode, void *vp ) +{ + str *s; + int n; + + if ( mode==SLIST_CHR ) + n = slist_findc( a, (const char*) vp ); + else + n = slist_find( a, (str*) vp ); + + if ( slist_wasfound( a, n ) ) + s = &( a->strs[n] ); + else + s = slist_addvp( a, mode, vp ); + + return s; +} +str * +slist_addc_unique( slist *a, const char *s ) +{ + return slist_addvp_unique( a, SLIST_CHR, (void*)s ); +} +str * +slist_add_unique( slist *a, str *s ) +{ + return slist_addvp_unique( a, SLIST_STR, (void*)s ); +} + +int +slist_addvp_all( slist *a, unsigned char mode, ... ) +{ + int ret = SLIST_OK; + va_list ap; + void *v; + str *s; + + va_start( ap, mode ); + + do { + + if ( mode==SLIST_CHR ) + v = va_arg( ap, char * ); + else + v = va_arg( ap, str * ); + + if ( v ) { + s = slist_addvp( a, mode, v ); + if ( s==NULL ) { + ret = SLIST_ERR_MEMERR; + goto out; + } + } + + } while ( v ); + +out: + va_end( ap ); + return ret; +} + +int +slist_add_all( slist *a, ... ) +{ + int ret = SLIST_OK; + va_list ap; + str *s, *v; + + va_start( ap, a ); + + do { + v = va_arg( ap, str * ); + + if ( v ) { + s = slist_addvp( a, SLIST_STR, (void*)v ); + if ( s==NULL ) { + ret = SLIST_ERR_MEMERR; + goto out; + } + } + + } while ( v ); +out: + va_end( ap ); + return ret; +} + +int +slist_addc_all( slist *a, ... ) +{ + int ret = SLIST_OK; + const char *v; + va_list ap; + str *s; + + va_start( ap, a ); + + do { + + v = va_arg( ap, const char * ); + + if ( v ) { + s = slist_addvp( a, SLIST_CHR, (void*)v ); + if ( s==NULL ) { + ret = SLIST_ERR_MEMERR; + goto out; + } + } + + } while ( v ); +out: + va_end( ap ); + return ret; +} + +int +slist_append( slist *a, slist *toadd ) +{ + int i, status; + + assert( a ); + assert( toadd ); + + status = slist_ensure_space( a, a->n + toadd->n, SLIST_EXACT_SIZE ); + + if ( status == SLIST_OK ) { + + for ( i=0; i<toadd->n; ++i ) { + str_strcpy( &(a->strs[a->n+i]), &(toadd->strs[i]) ); + if ( str_memerr( &(a->strs[a->n+i]) ) ) return SLIST_ERR_MEMERR; + } + + a->n += toadd->n; + + } + + return status; +} + +int +slist_append_unique( slist *a, slist *toadd ) +{ + str *s; + int i; + + assert( a ); + assert( toadd ); + + for ( i=0; i<toadd->n; ++i ) { + s = slist_add_unique( a, &(toadd->strs[i]) ); + if ( !s ) return SLIST_ERR_MEMERR; + } + + return SLIST_OK; +} + +int +slist_remove( slist *a, slist_index n ) +{ + int i; + + assert( a ); + + if ( !slist_valid_num( a, n ) ) return SLIST_ERR_BADPARAM; + + for ( i=n+1; i<a->n; ++i ) { + str_strcpy( &(a->strs[i-1]), &(a->strs[i]) ); + if ( str_memerr( &(a->strs[i-1]) ) ) return SLIST_ERR_MEMERR; + } + + a->n--; + + return SLIST_OK; +} + +void +slist_sort( slist *a ) +{ + qsort( a->strs, a->n, sizeof( str ), slist_comp ); + a->sorted = 1; +} + +static slist_index +slist_find_sorted( slist *a, const char *searchstr ) +{ + slist_index min, max, mid; + str s, *cs; + int comp; + + assert( a ); + assert( searchstr ); + + str_initstrc( &s, searchstr ); + min = 0; + max = a->n - 1; + while ( min <= max ) { + mid = ( min + max ) / 2; + cs = slist_str( a, mid ); + comp = slist_comp( (void*)cs, (void*) (&s) ); + if ( comp==0 ) { + str_free( &s ); + return mid; + } + else if ( comp > 0 ) max = mid - 1; + else if ( comp < 0 ) min = mid + 1; + } + str_free( &s ); + return -1; +} + +static slist_index +slist_find_simple( slist *a, const char *searchstr, int nocase ) +{ + slist_index i; + + assert( a ); + assert( searchstr ); + + if ( nocase ) { + for ( i=0; i<a->n; ++i ) + if ( !str_strcasecmpc( &(a->strs[i]), searchstr ) ) + return i; + } else { + for ( i=0; i<a->n; ++i ) + if ( !str_strcmpc( &(a->strs[i]), searchstr ) ) + return i; + } + return -1; +} + +slist_index +slist_findc( slist *a, const char *searchstr ) +{ + assert( a ); + + if ( a->n==0 ) return -1; + if ( a->sorted ) + return slist_find_sorted( a, searchstr ); + else + return slist_find_simple( a, searchstr, 0 ); +} + +slist_index +slist_find( slist *a, str *searchstr ) +{ + if ( searchstr->len==0 ) return -1; + return slist_findc( a, str_cstr( searchstr ) ); +} + +slist_index +slist_findnocasec( slist *a, const char *searchstr ) +{ + assert( a ); + + return slist_find_simple( a, searchstr, 1 ); +} + +slist_index +slist_findnocase( slist *a, str *searchstr ) +{ + if ( searchstr->len==0 ) return -1; + return slist_findnocasec( a, str_cstr( searchstr ) ); +} + +int +slist_wasfound( slist *a, slist_index n ) +{ + return ( n!=-1 ); +} + +int +slist_wasnotfound( slist *a, slist_index n ) +{ + return ( n==-1 ); +} + +int +slist_fillfp( slist *a, FILE *fp, unsigned char skip_blank_lines ) +{ + int ret = SLIST_OK; + str line, *s; + + assert( a ); + assert( fp ); + + slist_empty( a ); + str_init( &line ); + + while ( str_fgetline( &line, fp ) ) { + if ( skip_blank_lines && line.len==0 ) continue; + s = slist_add( a, &line ); + if ( !s ) { + ret = SLIST_ERR_MEMERR; + goto out; + } + } + +out: + str_free( &line ); + return ret; +} + +int +slist_fill( slist *a, const char *filename, unsigned char skip_blank_lines ) +{ + FILE *fp; + int ret; + + fp = fopen( filename, "r" ); + if ( !fp ) return SLIST_ERR_CANTOPEN; + + ret = slist_fillfp( a, fp, skip_blank_lines ); + + fclose( fp ); + + return ret; +} + +int +slist_copy( slist *to, slist *from ) +{ + slist_index i; + int status; + + assert( to ); + assert( from ); + + slist_free( to ); + + if ( from->n==0 ) return SLIST_OK; + + status = slist_ensure_space( to, from->n, SLIST_EXACT_SIZE ); + + if ( status == SLIST_OK ) { + + to->sorted = from->sorted; + to->n = from->n; + + for ( i=0; i<from->n; i++ ) { + str_strcpy( &(to->strs[i]), &(from->strs[i]) ); + if ( str_memerr( &(to->strs[i]) ) ) return SLIST_ERR_MEMERR; + } + + } + return SLIST_OK; +} + +slist * +slist_dup( slist *from ) +{ + int status; + slist *to; + + to = slist_new(); + if ( to ) { + status = slist_copy( to, from ); + if ( status!=SLIST_OK ) { + slist_delete( to ); + to = NULL; + } + } + + return to; +} + +unsigned long +slist_get_maxlen( slist *a ) +{ + unsigned long max = 0; + slist_index i; + str *s; + + assert( a ); + + for ( i=0; i<a->n; ++i ) { + s = slist_str( a, i ); + if ( s->len > max ) max = s->len; + } + + return max; +} + +void +slist_dump( slist *a, FILE *fp, int newline ) +{ + slist_index i; + + assert( a ); + assert( fp ); + + if ( newline ) { + for ( i=0; i<a->n; ++i ) + fprintf( fp, "%s\n", slist_cstr( a, i ) ); + } + + else { + for ( i=0; i<a->n; ++i ) + fprintf( fp, "%s", slist_cstr( a, i ) ); + } +} + +int +slist_match_entry( slist *a, int n, const char *s ) +{ + assert( a ); + + if ( !slist_valid_num( a, n ) ) return 0; + if ( str_strcmpc( &(a->strs[n]), s ) ) return 0; + return 1; +} + +void +slist_trimend( slist *a, int n ) +{ + slist_index i; + + assert( a ); + + if ( a->n - n < 1 ) { + slist_empty( a ); + } else { + for ( i=a->n -n; i<a->n; ++i ) { + str_empty( &(a->strs[i]) ); + } + a->n -= n; + } +} + +int +slist_tokenizec( slist *tokens, char *p, const char *delim, int merge_delim ) +{ + int ret = SLIST_OK; + str s, *t; + char *q; + + assert( tokens ); + + slist_empty( tokens ); + str_init( &s ); + while ( p && *p ) { + q = p; + while ( *q && !strchr( delim, *q ) ) q++; + str_segcpy( &s, p, q ); + if ( str_memerr( &s ) ) { ret = SLIST_ERR_MEMERR; goto out; } + if ( s.len ) { + t = slist_addvp( tokens, SLIST_STR, (void*) &s ); + if ( !t ) { ret = SLIST_ERR_MEMERR; goto out; } + } else if ( !merge_delim ) { + t = slist_addvp( tokens, SLIST_CHR, (void*) "" ); + if ( !t ) { ret = SLIST_ERR_MEMERR; goto out; } + } + p = q; + if ( *p ) p++; + } +out: + str_free( &s ); + return ret; +} + +int +slist_tokenize( slist *tokens, str *in, const char *delim, int merge_delim ) +{ + return slist_tokenizec( tokens, str_cstr( in ), delim, merge_delim ); +} + +void +slists_init( slist *a, ... ) +{ + slist *a2; + va_list ap; + slist_init( a ); + va_start( ap, a ); + do { + a2 = va_arg( ap, slist * ); + if ( a2 ) slist_init( a2 ); + } while ( a2 ); + va_end( ap ); +} + +void +slists_free( slist *a, ... ) +{ + slist *a2; + va_list ap; + slist_free( a ); + va_start( ap, a ); + do { + a2 = va_arg( ap, slist * ); + if ( a2 ) slist_free( a2 ); + } while ( a2 ); + va_end( ap ); +} + +void +slists_empty( slist *a, ... ) +{ + slist *a2; + va_list ap; + slist_empty( a ); + va_start( ap, a ); + do { + a2 = va_arg( ap, slist * ); + if ( a2 ) slist_empty( a2 ); + } while ( a2 ); + va_end( ap ); +} diff --git a/bibutils/slist.h b/bibutils/slist.h new file mode 100644 --- /dev/null +++ b/bibutils/slist.h @@ -0,0 +1,100 @@ +/* + * slist.h + * + * version: 2017-07-04 + * + * Copyright (c) Chris Putnam 2004-2017 + * + * Source code released under the GPL version 2 + * + */ + +#ifndef SLIST_H +#define SLIST_H + +#include <stdio.h> +#include <stdlib.h> +#include <stdarg.h> +#include <string.h> +#include "str.h" + +#define SLIST_OK (0) +#define SLIST_ERR_MEMERR (-1) +#define SLIST_ERR_CANTOPEN (-2) +#define SLIST_ERR_BADPARAM (-3) + +#define SLIST_CHR (0) +#define SLIST_STR (1) + +typedef int slist_index; + +typedef struct slist { + slist_index n, max; + int sorted; + str *strs; +} slist; + + +void slists_init( slist *a, ... ); +void slists_free( slist *a, ... ); +void slists_empty( slist *a, ... ); + + +void slist_init( slist *a ); +int slist_init_values ( slist *a, ... ); +int slist_init_valuesc( slist *a, ... ); +void slist_free( slist *a ); +void slist_empty( slist *a ); + +slist * slist_new( void ); +void slist_delete( slist * ); +void slist_deletev( void *v ); + +slist * slist_dup( slist *a ); +int slist_copy( slist *to, slist *from ); +void slist_swap( slist *a, slist_index n1, slist_index n2 ); + +str * slist_addvp( slist *a, unsigned char mode, void *vp ); +str * slist_addc( slist *a, const char *value ); +str * slist_add( slist *a, str *value ); + +int slist_addvp_all( slist *a, unsigned char mode, ... ); +int slist_addc_all( slist *a, ... ); +int slist_add_all( slist *a, ... ); + +str * slist_addvp_unique( slist *a, unsigned char mode, void *vp ); +str * slist_addc_unique( slist *a, const char *value ); +str * slist_add_unique( slist *a, str *value ); + +int slist_append( slist *a, slist *toadd ); +int slist_append_unique( slist *a, slist *toadd ); + +int slist_remove( slist *a, slist_index n ); + +str * slist_str( slist *a, slist_index n ); +char * slist_cstr( slist *a, slist_index n ); + +str * slist_set( slist *a, slist_index n, str *s ); +str * slist_setc( slist *a, slist_index n, const char *s ); + +void slist_sort( slist *a ); + +int slist_find( slist *a, str *searchstr ); +int slist_findc( slist *a, const char *searchstr ); +int slist_findnocase( slist *a, str *searchstr ); +int slist_findnocasec( slist *a, const char *searchstr ); +int slist_wasfound( slist *a, slist_index n ); +int slist_wasnotfound( slist *a, slist_index n ); + +int slist_match_entry( slist *a, slist_index n, const char *s ); +void slist_trimend( slist *a, slist_index n ); + +unsigned long slist_get_maxlen( slist *a ); +void slist_dump( slist *a, FILE *fp, int newline ); + +int slist_fill( slist *a, const char *filename, unsigned char skip_blank_lines ); +int slist_fillfp( slist *a, FILE *fp, unsigned char skip_blank_lines ); +int slist_tokenize( slist *tokens, str *in, const char *delim, int merge_delim ); +int slist_tokenizec( slist *tokens, char *p, const char *delim, int merge_delim ); + +#endif diff --git a/bibutils/str.c b/bibutils/str.c new file mode 100644 --- /dev/null +++ b/bibutils/str.c @@ -0,0 +1,1041 @@ +/* + * str.c + * + * Version: 2017-07-03 + * + * Copyright (c) Chris Putnam 1999-2017 + * + * Source code released under the GPL version 2 + * + * + * routines for dynamically allocated strings + * + */ +#include <stdio.h> +#include <stdlib.h> +#include <stdarg.h> +#include <string.h> +#include <ctype.h> +#include <limits.h> +#include "is_ws.h" +#include "str.h" + +/* Do not use asserts in STR_NOASSERT defined */ +#ifdef STR_NOASSERT +#define NDEBUG +#endif +#include <assert.h> + +#define str_initlen (64) + + +/* Clear memory in resize/free if STR_PARANOIA defined */ + +#ifndef STR_PARANOIA + +static void +str_realloc( str *s, unsigned long minsize ) +{ + char *newptr; + unsigned long size; + assert( s ); + size = 2 * s->dim; + if (size < minsize) size = minsize; + newptr = (char *) realloc( s->data, sizeof( *(s->data) )*size ); + if ( !newptr ) { + fprintf(stderr,"Error. Cannot reallocate memory (%ld bytes) in str_realloc.\n", sizeof(*(s->data))*size); + exit( EXIT_FAILURE ); + } + s->data = newptr; + s->dim = size; +} + +/* define as a no-op */ +#define str_nullify( s ) + +#else + +static void +str_realloc( str *s, unsigned long minsize ) +{ + char *newptr; + unsigned long size; + assert( s ); + size = 2 * s->dim; + if ( size < minsize ) size = minsize; + newptr = (char *) malloc( sizeof( *(s->data) ) * size ); + if ( !newptr ) { + fprintf( stderr, "Error. Cannot reallocate memory (%d bytes)" + " in str_realloc.\n", sizeof(*(s->data))*size ); + exit( EXIT_FAILURE ); + } + if ( s->data ) { + str_nullify( s ); + free( s->data ); + } + s->data = newptr; + s->dim = size; +} + +static inline void +str_nullify( str *s ) +{ + memset( s->data, 0, s->dim ); +} + +#endif + +void +str_init( str *s ) +{ + assert( s ); + s->dim = 0; + s->len = 0; + s->data = NULL; +} + +void +str_initstr( str *s, str *from ) +{ + assert( s ); + assert( from ); + str_init( s ); + str_strcpy( s, from ); +} + +void +str_initstrc( str *s, const char *initstr ) +{ + assert( s ); + assert( initstr ); + str_init( s ); + str_strcpyc( s, initstr ); +} + +void +str_initstrsc( str *s, ... ) +{ + const char *c; + va_list ap; + str_init( s ); + va_start( ap, s ); + do { + c = va_arg( ap, const char * ); + if ( c ) str_strcatc( s, c ); + } while ( c ); + va_end( ap ); +} + +void +strs_init( str *s, ... ) +{ + str *s2; + va_list ap; + str_init( s ); + va_start( ap, s ); + do { + s2 = va_arg( ap, str * ); + if ( s2 ) str_init( s2 ); + } while ( s2 ); + va_end( ap ); +} + +/* + * This is currently a stub. Later it will + * report whether or not a str function + * could not be performed due to a memory + * error. + */ +int +str_memerr( str *s ) +{ + return 0; +} + +void +str_mergestrs( str *s, ... ) +{ + va_list ap; + const char *cp; + str_empty( s ); + va_start( ap, s ); + do { + cp = va_arg( ap, const char * ); + if ( cp ) str_strcatc( s, cp ); + } while ( cp ); + va_end( ap ); +} + +static void +str_initalloc( str *s, unsigned long minsize ) +{ + unsigned long size = str_initlen; + assert( s ); + if ( minsize > str_initlen ) size = minsize; + s->data = (char *) malloc (sizeof( *(s->data) ) * size); + if ( !s->data ) { + fprintf(stderr,"Error. Cannot allocate memory in str_initalloc.\n"); + exit( EXIT_FAILURE ); + } + s->data[0]='\0'; + s->dim=size; + s->len=0; +} + +str * +str_new( void ) +{ + str *s = (str *) malloc( sizeof( *s ) ); + if ( s ) + str_initalloc( s, str_initlen ); + return s; +} + +void +str_free( str *s ) +{ + assert( s ); + if ( s->data ) { + str_nullify( s ); + free( s->data ); + } + s->dim = 0; + s->len = 0; + s->data = NULL; +} + +void +strs_free( str *s, ... ) +{ + str *s2; + va_list ap; + str_free( s ); + va_start( ap, s ); + do { + s2 = va_arg( ap, str * ); + if ( s2 ) str_free( s2 ); + } while ( s2 ); + va_end( ap ); +} + +void +str_delete( str *s ) +{ + assert( s ); + str_free( s ); + free( s ); +} + +void +str_empty( str *s ) +{ + assert( s ); + if ( s->data ) { + str_nullify( s ); + s->data[0] = '\0'; + } + s->len = 0; +} + +void +strs_empty( str *s, ... ) +{ + str *s2; + va_list ap; + str_empty( s ); + va_start( ap, s ); + do { + s2 = va_arg( ap, str * ); + if ( s2 ) str_empty( s2 ); + } while ( s2 ); + va_end( ap ); +} + +void +str_addchar( str *s, char newchar ) +{ + assert( s ); + if ( newchar=='\0' ) return; /* appending '\0' is a null operation */ + if ( !s->data || s->dim==0 ) + str_initalloc( s, str_initlen ); + if ( s->len + 2 > s->dim ) + str_realloc( s, s->len*2 ); + s->data[s->len++] = newchar; + s->data[s->len] = '\0'; +} + +/* str_addutf8 + * + * Add potential multibyte character to s starting at pointer p. + * Multibyte Unicode characters have the high bit set. + * + * Since we can progress more than one byte at p, return the + * properly updated pointer p. + */ +const char * +str_addutf8( str *s, const char *p ) +{ + if ( ! ((*p) & 128 ) ) { + str_addchar( s, *p ); + p++; + } else { + while ( ((*p) & 128) ) { + str_addchar( s, *p ); + p++; + } + } + return p; +} + +char * +str_cstr( str *s ) +{ + assert( s ); + return s->data; +} + +void +str_fprintf( FILE *fp, str *s ) +{ + assert( s ); + if ( s->data ) fprintf( fp, "%s", s->data ); +} + +void +str_prepend( str *s, const char *addstr ) +{ + unsigned long lenaddstr, i; + assert( s && addstr ); + lenaddstr = strlen( addstr ); + if ( lenaddstr==0 ) return; + if ( !s->data || !s->dim ) + str_initalloc( s, lenaddstr+1 ); + else { + if ( s->len + lenaddstr + 1 > s->dim ) + str_realloc( s, s->len + lenaddstr + 1 ); + for ( i=s->len+lenaddstr-1; i>=lenaddstr; i-- ) + s->data[i] = s->data[i-lenaddstr]; + } + strncpy( s->data, addstr, lenaddstr ); + s->len += lenaddstr; + s->data[ s->len ] = '\0'; +} + +static inline void +str_strcat_ensurespace( str *s, unsigned long n ) +{ + unsigned long m = s->len + n + 1; + if ( !s->data || !s->dim ) + str_initalloc( s, m ); + else if ( s->len + n + 1 > s->dim ) + str_realloc( s, m ); +} + +static inline void +str_strcat_internal( str *s, const char *addstr, unsigned long n ) +{ + str_strcat_ensurespace( s, n ); + strncat( &(s->data[s->len]), addstr, n ); + s->len += n; + s->data[s->len]='\0'; +} + +void +str_strcat( str *s, str *from ) +{ + assert ( s && from ); + if ( !from->data ) return; + else str_strcat_internal( s, from->data, from->len ); +} + +void +str_strcatc( str *s, const char *from ) +{ + unsigned long n; + assert( s && from ); + n = strlen( from ); + str_strcat_internal( s, from, n ); +} + +void +str_segcat( str *s, char *startat, char *endat ) +{ + unsigned long n; + char *p; + + assert( s && startat && endat ); + assert( (size_t) startat < (size_t) endat ); + + if ( startat==endat ) return; + + n = 0; + p = startat; + while ( p!=endat ) { + n++; + p++; + } + + str_strcat_internal( s, startat, n ); +} + +void +str_indxcat( str *s, char *p, unsigned long start, unsigned long stop ) +{ + unsigned long i; + assert( s && p ); + assert( start <= stop ); + for ( i=start; i<stop; ++i ) + str_addchar( s, p[i] ); +} + +/* str_cpytodelim() + * term = string of characters to be used as terminators + * finalstep = set to non-zero to position return value past the + * terminating character + */ +char * +str_cpytodelim( str *s, char *p, const char *delim, unsigned char finalstep ) +{ + assert( s ); + str_empty( s ); + return str_cattodelim( s, p, delim, finalstep ); +} + +/* str_cpytodelim() + * term = string of characters to be used as terminators + * finalstep = set to non-zero to position return value past the + * terminating character + */ +char * +str_cattodelim( str *s, char *p, const char *delim, unsigned char finalstep ) +{ + assert( s ); + while ( p && *p && !strchr( delim, *p ) ) { + str_addchar( s, *p ); + p++; + } + if ( p && *p && finalstep ) p++; + return p; +} + +static inline void +str_strcpy_ensurespace( str *s, unsigned long n ) +{ + unsigned long m = n + 1; + if ( !s->data || !s->dim ) + str_initalloc( s, m ); + else if ( m > s->dim ) + str_realloc( s, m ); +} + +static inline void +str_strcpy_internal( str *s, const char *p, unsigned long n ) +{ + str_strcpy_ensurespace( s, n ); + strncpy( s->data, p, n ); + s->data[n] = '\0'; + s->len = n; +} + +void +str_strcpy( str *s, str *from ) +{ + assert( s ); + assert( from ); + if ( s==from ) return; + else if ( !from || from->len==0 ) str_empty( s ); + else str_strcpy_internal( s, from->data, from->len ); +} + +void +str_strcpyc( str *s, const char *from ) +{ + unsigned long n; + assert( s && from ); + n = strlen( from ); + str_strcpy_internal( s, from, n ); +} + +/* str_segcpy( s, start, end ); + * + * copies [start,end) into s + */ +void +str_segcpy( str *s, char *startat, char *endat ) +{ + unsigned long n; + char *p; + + assert( s && startat && endat ); + assert( ((size_t) startat) <= ((size_t) endat) ); + + if ( startat==endat ) { + str_empty( s ); + return; + } + + n = 0; + p = startat; + while ( p!=endat ) { + p++; + n++; + } + + str_strcpy_internal( s, startat, n ); +} + +/* + * str_indxcpy( s, in, start, stop ); + * + * copies in[start,stop) (excludes stop) into s + */ +void +str_indxcpy( str *s, char *p, unsigned long start, unsigned long stop ) +{ + unsigned long i; + assert( s && p ); + assert( start <= stop ); + if ( start == stop ) { + str_empty( s ); + return; + } + str_strcpy_ensurespace( s, stop-start+1 ); + for ( i=start; i<stop; ++i ) + s->data[i-start] = p[i]; + s->len = stop-start; + s->data[s->len] = '\0'; +} + +str * +str_strdup( str *from ) +{ + str *s = str_new(); + if ( s ) + str_strcpy( s, from ); + return s; +} + +str * +str_strdupc( const char *from ) +{ + str *s = str_new(); + if ( s ) + str_strcpyc( s, from ); + return s; +} + +void +str_segdel( str *s, char *p, char *q ) +{ + str tmp1, tmp2; + char *r; + assert( s ); + r = &(s->data[s->len]); + str_init( &tmp1 ); + str_init( &tmp2 ); + str_segcpy( &tmp1, s->data, p ); + str_segcpy( &tmp2, q, r ); + str_empty( s ); + if ( tmp1.data ) str_strcat( s, &tmp1 ); + if ( tmp2.data ) str_strcat( s, &tmp2 ); + str_free( &tmp2 ); + str_free( &tmp1 ); +} + +/* + * str_findreplace() + * + * if replace is "" or NULL, then delete find + */ + +int +str_findreplace( str *s, const char *find, const char *replace ) +{ + long diff; + size_t findstart, searchstart; + size_t p1, p2; + size_t find_len, rep_len, curr_len; + char empty[2] = ""; + unsigned long minsize; + char *p; + int n = 0; + + assert( s && find ); + if ( !s->data || !s->dim ) return n; + if ( !replace ) replace = empty; + + find_len = strlen( find ); + rep_len = strlen( replace ); + diff = rep_len - find_len; + if ( diff < 0 ) diff = 0; + + searchstart=0; + while ((p=strstr(s->data + searchstart,find))!=NULL) { + curr_len = strlen(s->data); + findstart=(size_t) p - (size_t) s->data; + minsize = curr_len + diff + 1; + if (s->dim <= minsize) str_realloc( s, minsize ); + if ( find_len > rep_len ) { + p1 = findstart + rep_len; + p2 = findstart + find_len; + while( s->data[p2] ) + s->data[p1++]=s->data[p2++]; + s->data[p1]='\0'; + n++; + } else if ( find_len < rep_len ) { + for ( p1=curr_len; p1>=findstart+find_len; p1-- ) + s->data[p1+diff] = s->data[p1]; + n++; + } + for (p1=0; p1<rep_len; p1++) + s->data[findstart+p1]=replace[p1]; + searchstart = findstart + rep_len; + s->len += rep_len - find_len; + } + return n; +} + + +/* str_fget() + * returns 0 if we're done, 1 if we're not done + * extracts line by line (regardless of end characters) + * and feeds from buf.... + */ +int +str_fget( FILE *fp, char *buf, int bufsize, int *pbufpos, str *outs ) +{ + int bufpos = *pbufpos, done = 0; + char *ok; + assert( fp && outs ); + str_empty( outs ); + while ( !done ) { + while ( buf[bufpos] && buf[bufpos]!='\r' && buf[bufpos]!='\n' ) + str_addchar( outs, buf[bufpos++] ); + if ( buf[bufpos]=='\0' ) { + ok = fgets( buf, bufsize, fp ); + bufpos=*pbufpos=0; + if ( !ok && feof(fp) ) { /* end-of-file */ + buf[bufpos] = 0; + if ( outs->len==0 ) return 0; /*nothing in out*/ + else return 1; /*one last out */ + } + } else if ( buf[bufpos]=='\r' || buf[bufpos]=='\n' ) done=1; + } + if ( ( buf[bufpos]=='\n' && buf[bufpos+1]=='\r') || + ( buf[bufpos]=='\r' && buf[bufpos+1]=='\n') ) bufpos+=2; + else if ( buf[bufpos]=='\n' || buf[bufpos]=='\r' ) bufpos+=1; + *pbufpos = bufpos; + return 1; +} + +void +str_toupper( str *s ) +{ + unsigned long i; + assert( s ); + for ( i=0; i<s->len; ++i ) + s->data[i] = toupper( (unsigned char)s->data[i] ); +} + +void +str_tolower( str *s ) +{ + unsigned long i; + assert( s ); + for ( i=0; i<s->len; ++i ) + s->data[i] = tolower( (unsigned char)s->data[i] ); +} + +/* str_swapstrings( s1, s2 ) + * be sneaky and swap internal string data from one + * string to another + */ +void +str_swapstrings( str *s1, str *s2 ) +{ + char *tmpp; + int tmp; + + assert( s1 && s2 ); + + /* swap dimensioning info */ + tmp = s1->dim; + s1->dim = s2->dim; + s2->dim = tmp; + + /* swap length info */ + tmp = s1->len; + s1->len = s2->len; + s2->len = tmp; + + /* swap data */ + tmpp = s1->data; + s1->data = s2->data; + s2->data = tmpp; +} + +void +str_trimstartingws( str *s ) +{ + char *p, *q; + int n; + + assert( s ); + + if ( s->len==0 || !is_ws( s->data[0] ) ) return; + + n = 0; + p = s->data; + while ( is_ws( *p ) ) p++; + + q = s->data; + while ( *p ) { + *q++ = *p++; + n++; + } + *q = '\0'; + + s->len = n; +} + +void +str_trimendingws( str *s ) +{ + assert( s ); + while ( s->len > 0 && is_ws( s->data[s->len-1] ) ) { + s->data[s->len-1] = '\0'; + s->len--; + } +} + +int +str_match_first( str *s, char ch ) +{ + assert( s ); + if ( !s->len ) return 0; + if ( s->data[0] == ch ) return 1; + return 0; +} + +int +str_match_end( str *s, char ch ) +{ + assert( s ); + if ( !s->len ) return 0; + if ( s->data[ s->len - 1 ] == ch ) return 1; + return 0; +} + +void +str_trimbegin( str *s, unsigned long n ) +{ + char *p, *q; + + assert( s ); + + if ( n==0 ) return; + if ( s->len==0 ) return; + if ( n >= s->len ) { + str_empty( s ); + return; + } + + p = s->data; + while ( n-- > 0 ) p++; + + n = 0; + q = s->data; + while ( *p ) { + *q++ = *p++; + n++; + } + *q = '\0'; + + s->len = n; +} + +void +str_trimend( str *s, unsigned long n ) +{ + assert( s ); + + if ( n==0 ) return; + if ( n >= s->len ) { + str_empty( s ); + return; + } + + s->len -= n; + s->data[ s->len ] = '\0'; +} + +void +str_pad( str *s, unsigned long len, char ch ) +{ + unsigned long i; + assert( s ); + for ( i=s->len; i<len; i++ ) + str_addchar( s, ch ); +} + +void +str_copyposlen( str *s, str *in, unsigned long pos, unsigned long len ) +{ + unsigned long i, max; + assert( s ); + str_empty( s ); + max = pos+len; + if ( max > in->len ) max = in->len; + for ( i=pos; i<max; ++i ) + str_addchar( s, in->data[i] ); +} + +static void +str_check_case( str *s, int *lowercase, int *uppercase ) +{ + int i; + assert( s ); + *lowercase = 0; + *uppercase = 0; + if ( s->len < 1 ) return; + for ( i=0; i<s->len && !( *lowercase && *uppercase ); ++i ) { + if ( isalpha( (unsigned char)s->data[i] ) ) { + if ( isupper( (unsigned char)s->data[i] ) ) *uppercase += 1; + else if ( islower( (unsigned char)s->data[i] ) ) *lowercase += 1; + } + } +} + +int +str_is_mixedcase( str *s ) +{ + int lowercase, uppercase; + str_check_case( s, &lowercase, &uppercase ); + if ( lowercase > 0 && uppercase > 0 ) return 1; + return 0; +} + +int +str_is_lowercase( str *s ) +{ + int lowercase, uppercase; + str_check_case( s, &lowercase, &uppercase ); + if ( lowercase > 0 && uppercase == 0 ) return 1; + return 0; +} + +int +str_is_uppercase( str *s ) +{ + int lowercase, uppercase; + str_check_case( s, &lowercase, &uppercase ); + if ( lowercase == 0 && uppercase > 0 ) return 1; + return 0; +} + +void +str_stripws( str *s ) +{ + unsigned long len = 0; + char *p, *q; + assert( s ); + if ( s->len ) { + p = q = s->data; + while ( *p ) { + if ( !is_ws( *p ) ) { + *q = *p; + q++; + len++; + } + p++; + } + *q = '\0'; + } + s->len = len; +} + +int +str_strcmp( const str *s, const str *t ) +{ + assert( s ); + assert( t ); + if ( s->len == 0 && t->len == 0 ) return 0; + if ( s->len == 0 ) return strcmp( "", t->data ); + if ( t->len == 0 ) return strcmp( s->data, "" ); + return strcmp( s->data, t->data ); +} + +int +str_strcmpc( const str *s, const char *t ) +{ + assert( s ); + assert( t ); + if ( s->len == 0 ) return strcmp( "", t ); + return strcmp( s->data, t ); +} + +int +str_strncmp( const str *s, const str *t, size_t n ) +{ + assert( s ); + assert( t ); + if ( s->len == 0 && t->len == 0 ) return 0; + if ( s->len == 0 ) return strncmp( "", t->data, n ); + if ( t->len == 0 ) return strncmp( s->data, "", n ); + return strncmp( s->data, t->data, n ); +} + +int +str_strncmpc( const str *s, const char *t, size_t n ) +{ + assert( s ); + assert( t ); + if ( s->len == 0 ) return strncmp( "", t, n ); + return strncmp( s->data, t, n ); +} + +int +str_strcasecmp( const str *s, const str *t ) +{ + assert( s ); + assert( t ); + if ( s->len == 0 && t->len == 0 ) return 0; + if ( s->len == 0 ) return strcasecmp( "", t->data ); + if ( t->len == 0 ) return strcasecmp( s->data, "" ); + return strcasecmp( s->data, t->data ); +} + +int +str_strcasecmpc( const str *s, const char *t ) +{ + assert( s ); + assert( t ); + if ( s->len == 0 ) return strcasecmp( "", t ); + return strcasecmp( s->data, t ); +} + +char * +str_strstr( const str *s, const str *t ) +{ + assert( s ); + assert( t ); + if ( s->len == 0 && t->len == 0 ) return strstr( "", "" ); + if ( s->len == 0 ) return strstr( "", t->data ); + if ( t->len == 0 ) return strstr( s->data, "" ); + return strstr( s->data, t->data ); +} + +char * +str_strstrc( const str *s, const char *t ) +{ + assert( s ); + assert( t ); + if ( s->len == 0 ) return strstr( "", t ); + return strstr( s->data, t ); +} + +void +str_reverse( str *s ) +{ + unsigned long i, max; + char tmp; + assert( s ); + max = s->len / 2; + for ( i=0; i<max; ++i ) { + tmp = s->data[ i ]; + s->data[ i ] = s->data[ s->len - 1 - i ]; + s->data[ s->len - 1 - i ] = tmp; + } +} + +int +str_fgetline( str *s, FILE *fp ) +{ + int ch, eol = 0; + assert( s ); + assert( fp ); + str_empty( s ); + if ( feof( fp ) ) return 0; + while ( !feof( fp ) && !eol ) { + ch = fgetc( fp ); + if ( ch == EOF ) { + if ( s->len ) return 1; + else return 0; + } + else if ( ch == '\n' ) eol = 1; + else if ( ch == '\r' ) { + ch = fgetc( fp ); + if ( ch != '\n' ) ungetc( ch, fp ); + eol = 1; + } else { + str_addchar( s, (char) ch ); + } + } + return 1; +} + +/* + * s = "Hi!\0", s.len = 3 + * + * str_char( s, 0 ) = 'H' str_revchar( s, 0 ) = '!' + * str_char( s, 1 ) = 'i' str_revchar( s, 1 ) = 'i' + * str_char( s, 2 ) = '!' str_revchar( s, 2 ) = 'H' + * str_char( s, 3 ) = '\0' str_revchar( s, 3 ) = '\0' + */ +char +str_char( str *s, unsigned long n ) +{ + assert( s ); + if ( s->len==0 || n >= s->len ) return '\0'; + return s->data[ n ]; +} + +char +str_revchar( str *s, unsigned long n ) +{ + assert( s ); + if ( s->len==0 || n >= s->len ) return '\0'; + return s->data[ s->len - n - 1]; +} + +void +str_makepath( str *path, const char *dirname, const char *filename, char sep ) +{ + assert( path ); + if ( dirname ) str_strcpyc( path, dirname ); + else str_empty( path ); + + if ( path->len && path->data[path->len-1]!=sep ) + str_addchar( path, sep ); + + if ( filename ) str_strcatc( path, filename ); +} + +void +str_fill( str *s, unsigned long n, char fillchar ) +{ + unsigned long i; + assert( s ); + if ( !s->data || s->dim==0 ) + str_initalloc( s, n+1 ); + if ( n + 1 > s->dim ) + str_realloc( s, n+1 ); + for ( i=0; i<n; ++i ) + s->data[i] = fillchar; + s->data[n] = '\0'; + s->len = n; +} + +int +str_has_value( str *s ) +{ + if ( !s || s->len==0 ) return 0; + return 1; +} + +int +str_is_empty( str *s ) +{ + if ( !s || s->len==0 ) return 1; + return 0; +} diff --git a/bibutils/str.h b/bibutils/str.h new file mode 100644 --- /dev/null +++ b/bibutils/str.h @@ -0,0 +1,124 @@ +/* + * str.h + * + * Version: 2017-07-03 + * + * Copyright (c) Chris Putnam 1999-2017 + * + * Source code released under the GPL version 2 + * + */ +#ifndef STR_H +#define STR_H + +#include <stdio.h> + +typedef struct str { + char *data; + unsigned long dim; + unsigned long len; +} str; + +str * str_new ( void ); +void str_delete ( str *s ); + +void str_init ( str *s ); +void str_initstr ( str *s, str *from ); +void str_initstrc ( str *s, const char *initstr ); +void str_initstrsc ( str *s, ... ); +void str_empty ( str *s ); +void str_free ( str *s ); + +void strs_init ( str *s, ... ); +void strs_empty ( str *s, ... ); +void strs_free ( str *s, ... ); + +str* str_strdup ( str *s ); +str* str_strdupc( const char *p ); + +void str_strcat ( str *s, str *from ); +void str_strcatc( str *s, const char *from ); + +void str_strcpy ( str *s, str *from ); +void str_strcpyc( str *s, const char *from ); + +int str_strcmp ( const str *s, const str *t ); +int str_strcmpc( const str *s, const char *t ); + +int str_strncmp ( const str *s, const str *t, size_t n ); +int str_strncmpc( const str *s, const char *t, size_t n ); + +int str_strcasecmp ( const str *s, const str *t ); +int str_strcasecmpc( const str *s, const char *t ); + +char * str_strstr ( const str *s, const str *t ); +char * str_strstrc( const str *s, const char *t ); + +void str_prepend ( str *s, const char *addstr ); +void str_mergestrs ( str *s, ... ); + +void str_addchar ( str *s, char newchar ); +void str_reverse ( str *s ); +const char *str_addutf8 ( str *s, const char *p ); +void str_segcat ( str *s, char *startat, char *endat ); +char *str_cpytodelim ( str *s, char *p, const char *delim, unsigned char finalstep ); +char *str_cattodelim ( str *s, char *p, const char *delim, unsigned char finalstep ); +void str_prepend ( str *s, const char *addstr ); +void str_segcpy ( str *s, char *startat, char *endat ); +void str_segdel ( str *s, char *startat, char *endat ); +void str_indxcpy ( str *s, char *p, unsigned long start, unsigned long stop ); +void str_indxcat ( str *s, char *p, unsigned long start, unsigned long stop ); +void str_fprintf ( FILE *fp, str *s ); +int str_fget ( FILE *fp, char *buf, int bufsize, int *pbufpos, + str *outs ); +char * str_cstr ( str *s ); +char str_char ( str *s, unsigned long n ); +char str_revchar ( str *s, unsigned long n ); +int str_fgetline ( str *s, FILE *fp ); +int str_findreplace ( str *s, const char *find, const char *replace ); +void str_toupper ( str *s ); +void str_tolower ( str *s ); +void str_trimstartingws( str *s ); +void str_trimendingws( str *s ); +void str_swapstrings ( str *s1, str *s2 ); +void str_stripws ( str *s ); + +int str_match_first ( str *s, char ch ); +int str_match_end ( str *s, char ch ); +void str_trimbegin ( str *s, unsigned long n ); +void str_trimend ( str *s, unsigned long n ); + +void str_pad ( str *s, unsigned long len, char ch ); +void str_copyposlen ( str *s, str *in, unsigned long pos, unsigned long len ); + +void str_makepath ( str *path, const char *dirname, const char *filename, char sep ); + +void str_fill ( str *s, unsigned long n, char fillchar ); + +int str_is_mixedcase( str *s ); +int str_is_lowercase( str *s ); +int str_is_uppercase( str *s ); + +int str_memerr( str *s ); + +int str_has_value( str *s ); +int str_is_empty( str *s ); + + +/* #define STR_PARANOIA + * + * set to clear memory before it is freed or reallocated + * note that this is slower...may be important if string + * contains sensitive information + */ + +/* #define STR_NOASSERT + * + * set to turn off the use of asserts (and associated call to exit) + * in str functions...useful for library construction for + * Linux distributions that don't want libraries calling exit, but + * not useful during code development + */ + +#endif + diff --git a/bibutils/str_conv.c b/bibutils/str_conv.c new file mode 100644 --- /dev/null +++ b/bibutils/str_conv.c @@ -0,0 +1,196 @@ +/* + * str_conv.c + * + * Copyright (c) Chris Putnam 1999-2017 + * + * Source code released under the GPL version 2 + * + * str routines for converting strs between character sets + * + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <ctype.h> +#include <limits.h> +#include "latex.h" +#include "entities.h" +#include "utf8.h" +#include "gb18030.h" +#include "charsets.h" +#include "str_conv.h" + +static void +addentity( str *s, unsigned int ch ) +{ + char buf[512]; + sprintf( buf, "&#%d;", ch ); + str_strcatc( s, buf ); +} + +/* These are the five minimal predefined entites in XML */ +static int +minimalxmlchars( str *s, unsigned int ch ) +{ + if ( ch==34 ) { str_strcatc( s, """ ); return 1; } + else if ( ch==38 ) { str_strcatc( s, "&" ); return 1; } + else if ( ch==39 ) { str_strcatc( s, "'" ); return 1; } + else if ( ch==60 ) { str_strcatc( s, "<" ); return 1; } + else if ( ch==62 ) { str_strcatc( s, ">" ); return 1; } + return 0; +} + +static void +addxmlchar( str *s, unsigned int ch ) +{ + if ( minimalxmlchars( s, ch ) ) return; + if ( ch > 127 ) addentity( s, ch ); + else str_addchar( s, ch ); +} + +static void +addutf8char( str *s, unsigned int ch, int xmlout ) +{ + unsigned char code[6]; + int nc, i; + if ( xmlout ) { + if ( minimalxmlchars( s, ch ) ) return; + if ( ch > 127 && xmlout == STR_CONV_XMLOUT_ENTITIES ) + { addentity( s, ch ); return; } + } + nc = utf8_encode( ch, code ); + for ( i=0; i<nc; ++i ) + str_addchar( s, code[i] ); +} + +static void +addgb18030char( str *s, unsigned int ch, int xmlout ) +{ + unsigned char code[4]; + int nc, i; + if ( xmlout ) { + if ( minimalxmlchars( s, ch ) ) return; + if ( ch > 127 && xmlout == STR_CONV_XMLOUT_ENTITIES ) + { addentity( s, ch ); return; } + } + nc = gb18030_encode( ch, code ); + for ( i=0; i<nc; ++i ) + str_addchar( s, code[i] ); +} + +static void +addlatexchar( str *s, unsigned int ch, int xmlout, int utf8out ) +{ + char buf[512]; + uni2latex( ch, buf, sizeof( buf ) ); + /* If the unicode character isn't recognized as latex output + * a '?' unless the user has requested unicode output. If so, + * output the unicode. + */ + if ( utf8out && !strcmp( buf, "?" ) ) { + addutf8char( s, ch, xmlout ); + } else { + str_strcatc( s, buf ); + } +} + +/* + * get_unicode() + * + * This can be a little tricky. If the character is simply encoded + * such as UTF8 for > 128 or by numeric xml entities such as "Ȗ" + * then the output of decode_entity() and utf8_decode will necessarily + * be in the charsetin character set. On the other hand, if it's a + * fancy latex expression, such as "\alpha", or a non-numeric xml entity + * like "&", then we'll get the Unicode value (because our lists only + * keep the Unicode equivalent). + * + * The unicode variable indicates whether or not a Unicode-based listing + * was used to convert the character (remember that charsetin could be + * Unicode independently). + * + * The charset variable is used to keep track of what character set + * the character is in prior to conversion. + * + */ + +static unsigned int +get_unicode( str *s, unsigned int *pi, int charsetin, int latexin, int utf8in, int xmlin ) +{ + unsigned int ch; + int unicode = 0, err = 0; + if ( xmlin && s->data[*pi]=='&' ) { + ch = decode_entity( s->data, pi, &unicode, &err ); + } else if ( charsetin==CHARSET_GB18030 ) { + ch = gb18030_decode( s->data, pi ); + unicode = 1; + } else if ( latexin ) { + /* Must handle bibtex files in UTF8/Unicode */ + if ( utf8in && ( s->data[*pi] & 128 ) ) { + ch = utf8_decode( s->data, pi ); + unicode = 1; + } else ch = latex2char( s->data, pi, &unicode ); + } + else if ( utf8in ) + ch = utf8_decode( s->data, pi ); + else { + ch = (unsigned int) s->data[*pi]; + *pi = *pi + 1; + } + if ( !unicode && charsetin!=CHARSET_UNICODE ) + ch = charset_lookupchar( charsetin, ch ); + return ch; +} + +static int +write_unicode( str *s, unsigned int ch, int charsetout, int latexout, + int utf8out, int xmlout ) +{ + unsigned int c; + if ( latexout ) { + addlatexchar( s, ch, xmlout, utf8out ); + } else if ( utf8out ) { + addutf8char( s, ch, xmlout ); + } else if ( charsetout==CHARSET_GB18030 ) { + addgb18030char( s, ch, xmlout ); + } else { + c = charset_lookupuni( charsetout, ch ); + if ( xmlout ) addxmlchar( s, c ); + else str_addchar( s, c ); + } + return 1; +} + +/* + * Returns 1 on memory error condition + */ +int +str_convert( str *s, + int charsetin, int latexin, int utf8in, int xmlin, + int charsetout, int latexout, int utf8out, int xmlout ) +{ + unsigned int pos = 0; + unsigned int ch; + str ns; + int ok = 1; + + if ( !s || s->len==0 ) return ok; + + str_init( &ns ); + + if ( charsetin==CHARSET_UNKNOWN ) charsetin = CHARSET_DEFAULT; + if ( charsetout==CHARSET_UNKNOWN ) charsetout = CHARSET_DEFAULT; + + while ( s->data[pos] ) { + ch = get_unicode( s, &pos, charsetin, latexin, utf8in, xmlin ); + ok = write_unicode( &ns, ch, charsetout, latexout, utf8out, xmlout ); + if ( !ok ) goto out; + } + + str_swapstrings( s, &ns ); +out: + str_free( &ns ); + + return ok; +} + diff --git a/bibutils/str_conv.h b/bibutils/str_conv.h new file mode 100644 --- /dev/null +++ b/bibutils/str_conv.h @@ -0,0 +1,23 @@ +/* + * str_conv.h + * + * Copyright (c) Chris Putnam 1999-2017 + * + * Source code released under the GPL version 2 + * + */ +#ifndef STR_CONV_H +#define STR_CONV_H + +#define STR_CONV_XMLOUT_FALSE (0) +#define STR_CONV_XMLOUT_TRUE (1) +#define STR_CONV_XMLOUT_ENTITIES (3) + +#include "str.h" + +extern int str_convert( str *s, + int charsetin, int latexin, int utf8in, int xmlin, + int charsetout, int latexout, int utf8out, int xmlout ); + +#endif + diff --git a/bibutils/strsearch.c b/bibutils/strsearch.c --- a/bibutils/strsearch.c +++ b/bibutils/strsearch.c @@ -1,6 +1,6 @@ /* strsearch.c * - * Copyright (c) Chris Putnam 1995-2013 + * Copyright (c) Chris Putnam 1995-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/strsearch.h b/bibutils/strsearch.h --- a/bibutils/strsearch.h +++ b/bibutils/strsearch.h @@ -1,7 +1,7 @@ /* * strsearch.h * - * Copyright (c) Chris Putnam 1995-2013 + * Copyright (c) Chris Putnam 1995-2017 * * Source code released under the GPL version 2 * diff --git a/bibutils/title.c b/bibutils/title.c --- a/bibutils/title.c +++ b/bibutils/title.c @@ -3,7 +3,7 @@ * * process titles into title/subtitle pairs for MODS * - * Copyright (c) Chris Putnam 2004-2014 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * @@ -11,7 +11,7 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include "newstr.h" +#include "str.h" #include "fields.h" #include "title.h" #include "is_ws.h" @@ -20,12 +20,12 @@ title_process( fields *info, char *tag, char *data, int level, unsigned char nosplittitle ) { - newstr title, subtitle; + str title, subtitle; char *p, *q; int status; - newstr_init( &title ); - newstr_init( &subtitle ); + str_init( &title ); + str_init( &subtitle ); if ( nosplittitle ) q = NULL; else { @@ -33,36 +33,68 @@ if ( !q ) q = strstr( data, "? " ); } - if ( !q ) newstr_strcpy( &title, data ); + if ( !q ) str_strcpyc( &title, data ); else { p = data; - while ( p!=q ) newstr_addchar( &title, *p++ ); - if ( *q=='?' ) newstr_addchar( &title, '?' ); + while ( p!=q ) str_addchar( &title, *p++ ); + if ( *q=='?' ) str_addchar( &title, '?' ); q++; q = skip_ws( q ); - while ( *q ) newstr_addchar( &subtitle, *q++ ); + while ( *q ) str_addchar( &subtitle, *q++ ); } if ( strncasecmp( "SHORT", tag, 5 ) ) { - if ( title.len>0 ) { - status = fields_add( info, "TITLE", title.data, level ); + if ( str_has_value( &title ) ) { + status = fields_add( info, "TITLE", str_cstr( &title ), level ); if ( status!=FIELDS_OK ) return 0; } - if ( subtitle.len>0 ) { - status = fields_add( info, "SUBTITLE", subtitle.data, level ); + if ( str_has_value( &subtitle ) ) { + status = fields_add( info, "SUBTITLE", str_cstr( &subtitle ), level ); if ( status!=FIELDS_OK ) return 0; } } else { - if ( title.len>0 ) { - status = fields_add( info, "SHORTTITLE", title.data, level ); + if ( str_has_value( &title ) ) { + status = fields_add( info, "SHORTTITLE", str_cstr( &title ), level ); if ( status!=FIELDS_OK ) return 0; } /* no SHORT-SUBTITLE! */ } - newstr_free( &subtitle ); - newstr_free( &title ); + str_free( &subtitle ); + str_free( &title ); return 1; } +/* title_combine() + * + * Combine a main title and a subtitle into a full title. + * + * Example: + * Main title = "A Clearing in the Distance" + * Subtitle = "The Biography of Frederick Law Olmstead" + * Full title = "A Clearing in the Distance: The Biography of Frederick Law Olmstead" + * Example: + * Main title = "What Makes a Good Team Player?" + * Subtitle = "Personality and Team Effectiveness" + * Full title = "What Makes a Good Team Player? Personality and Team Effectiveness" + */ +void +title_combine( str *fullttl, str *mainttl, str *subttl ) +{ + str_empty( fullttl ); + + if ( !mainttl ) return; + + str_strcpy( fullttl, mainttl ); + + if ( subttl ) { + if ( str_has_value( mainttl ) ) { + if ( mainttl->data[ mainttl->len - 1 ] != '?' && mainttl->data[ mainttl->len - 1] != ':' ) + str_strcatc( fullttl, ": " ); + else + str_strcatc( fullttl, " " ); + } + str_strcat( fullttl, subttl ); + } +} diff --git a/bibutils/title.h b/bibutils/title.h --- a/bibutils/title.h +++ b/bibutils/title.h @@ -3,7 +3,7 @@ * * process titles into title/subtitle pairs for MODS * - * Copyright (c) Chris Putnam 2004-2014 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL verison 2 * @@ -11,10 +11,10 @@ #ifndef TITLE_H #define TITLE_H -#include "newstr.h" +#include "str.h" #include "fields.h" -extern int title_process( fields *info, char *tag, char *data, int level, - unsigned char nosplittitle ); +int title_process( fields *info, char *tag, char *data, int level, unsigned char nosplittitle ); +void title_combine( str *fullttl, str *mainttl, str *subttl ); #endif diff --git a/bibutils/unicode.c b/bibutils/unicode.c --- a/bibutils/unicode.c +++ b/bibutils/unicode.c @@ -317,13 +317,13 @@ } unsigned short -unicode_utf8_classify_newstr( newstr *s ) +unicode_utf8_classify_str( str *s ) { unsigned int unicode_character, pos = 0; unsigned short value = 0; int n; while ( pos < s->len ) { - unicode_character = utf8_decode( s->data, &pos ); + unicode_character = utf8_decode( str_cstr( s ), &pos ); n = unicode_find( unicode_character ); if ( n==-1 ) value |= UNICODE_SYMBOL; else value |= unicodeinfo[n].info; diff --git a/bibutils/unicode.h b/bibutils/unicode.h --- a/bibutils/unicode.h +++ b/bibutils/unicode.h @@ -1,14 +1,14 @@ /* * unicode.h * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2017 * * Program and source code released under the GPL version 2 */ #ifndef UNICODE_H #define UNICODE_H -#include "newstr.h" +#include "str.h" #define UNICODE_SYMBOL (1) #define UNICODE_UPPER (2) /* Uppercase letter */ @@ -17,6 +17,6 @@ #define UNICODE_MIXEDCASE ( UNICODE_UPPER | UNICODE_LOWER ) extern unsigned short unicode_utf8_classify( char *p ); -extern unsigned short unicode_utf8_classify_newstr( newstr *s ); +extern unsigned short unicode_utf8_classify_str( str *s ); #endif diff --git a/bibutils/url.c b/bibutils/url.c new file mode 100644 --- /dev/null +++ b/bibutils/url.c @@ -0,0 +1,313 @@ +/* + * url.c + * + * doi_to_url() + * Handle outputing DOI as a URL (Endnote and RIS formats) + * 1) Append https://doi.org as necessary + * 2) Check for overlap with pre-existing URL for the DOI + * + * is_doi() + * Check for DOI buried in another field. + * + * Copyright (c) Chris Putnam 2008-2017 + * + * Source code released under the GPL version 2 + * + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <ctype.h> +#include "bibutils.h" +#include "url.h" + +static void +construct_url( char *prefix, str *id, str *id_url, char sep ) +{ + if ( !strncasecmp( str_cstr( id ), "http:", 5 ) ) + str_strcpy( id_url, id ); + else { + str_strcpyc( id_url, prefix ); + if ( sep!='\0' ) { + if ( id->data[0]!=sep ) str_addchar( id_url, sep ); + } + str_strcat( id_url, id ); + } +} + +static int +url_exists( fields *f, char *urltag, str *doi_url ) +{ + int i, n; + if ( urltag ) { + n = fields_num( f ); + for ( i=0; i<n; ++i ) { + if ( strcmp( fields_tag( f, i, FIELDS_CHRP ), urltag ) ) continue; + if ( strcmp( fields_value( f, i, FIELDS_CHRP ), str_cstr( doi_url ) ) ) continue; + return 1; + } + } + return 0; +} + +static void +xxx_to_url( fields *f, int n, char *http_prefix, char *urltag, str *xxx_url, char sep ) +{ + str_empty( xxx_url ); + construct_url( http_prefix, fields_value( f, n, FIELDS_STRP ), xxx_url, sep ); + if ( url_exists( f, urltag, xxx_url ) ) + str_empty( xxx_url ); +} +void +doi_to_url( fields *f, int n, char *urltag, str *url ) +{ + xxx_to_url( f, n, "https://doi.org", urltag, url, '/' ); +} +void +jstor_to_url( fields *f, int n, char *urltag, str *url ) +{ + xxx_to_url( f, n, "http://www.jstor.org/stable", urltag, url, '/' ); +} +void +pmid_to_url( fields *f, int n, char *urltag, str *url ) +{ + xxx_to_url( f, n, "http://www.ncbi.nlm.nih.gov/pubmed", urltag, url, '/' ); +} +void +pmc_to_url( fields *f, int n, char *urltag, str *url ) +{ + xxx_to_url( f, n, "http://www.ncbi.nlm.nih.gov/pmc/articles", urltag, url, '/' ); +} +void +arxiv_to_url( fields *f, int n, char *urltag, str *url ) +{ + xxx_to_url( f, n, "http://arxiv.org/abs", urltag, url, '/' ); +} +void +mrnumber_to_url( fields *f, int n, char *urltag, str *url ) +{ + xxx_to_url( f, n, "http://www.ams.org/mathscinet-getitem?mr=", urltag, url, '\0' ); +} + +/* Rules for the pattern: + * '#' = number + * isalpha() = match precisely (matchcase==1) or match regardless of case + * (matchcase==0) + * all others must match precisely + */ +static int +string_pattern( char *s, char *pattern, int matchcase ) +{ + int patlen, match, i; + patlen = strlen( pattern ); + if ( strlen( s ) < patlen ) return 0; /* too short */ + for ( i=0; i<patlen; ++i ) { + match = 0; + if ( pattern[i]=='#' ) { + if ( isdigit( (unsigned char)s[i] ) ) match = 1; + } else if ( !matchcase && isalpha( (unsigned char)pattern[i] ) ) { + if ( tolower((unsigned char)pattern[i])==tolower((unsigned char)s[i])) match = 1; + } else { + if ( pattern[i] == s[i] ) match = 1; + } + if ( !match ) return 0; + } + return 1; +} + +/* science direct is now doing "M3 - doi: DOI: 10.xxxx/xxxxx" */ +int +is_doi( char *s ) +{ + if ( string_pattern( s, "##.####/", 0 ) ) return 0; + if ( string_pattern( s, "doi:##.####/", 0 ) ) return 4; + if ( string_pattern( s, "doi: ##.####/", 0 ) ) return 5; + if ( string_pattern( s, "doi: DOI: ##.####/", 0 ) ) return 10; + return -1; +} + +/* determine if string has the header of a Universal Resource Identifier + * + * returns -1, if not true + * returns offset that skips over the URI scheme, if true + */ +int +is_uri_remote_scheme( char *p ) +{ + char *scheme[] = { "http:", "https:", "ftp:", "git:", "gopher:" }; + int schemelen[] = { 5, 6, 4, 4, 7 }; + int i, nschemes = sizeof( scheme ) / sizeof( scheme[0] ); + for ( i=0; i<nschemes; ++i ) { + if ( !strncasecmp( p, scheme[i], schemelen[i] ) ) return schemelen[i]; + } + return -1; +} + +int +is_reference_database( char *p ) +{ + char *scheme[] = { "arXiv:", "pubmed:", "medline:", "isi:" }; + int schemelen[] = { 6, 7, 8, 4 }; + int i, nschemes = sizeof( scheme ) / sizeof( scheme[0] ); + for ( i=0; i<nschemes; ++i ) { + if ( !strncasecmp( p, scheme[i], schemelen[i] ) ) return schemelen[i]; + } + return -1; +} + +/* many fields have been abused to embed URLs, DOIs, etc. */ +int +is_embedded_link( char *s ) +{ + if ( is_uri_remote_scheme( s ) != -1 ) return 1; + if ( is_reference_database( s ) != -1 ) return 1; + if ( is_doi( s ) !=-1 ) return 1; + return 0; +} + +typedef struct url_t { + char *tag; + char *prefix; + int offset; +} url_t; + +static url_t prefixes[] = { + /* 00000000001111111112222222222333333333344444444445 */ + /* 12345678901234567890123456789012345678901234567890 */ + { "ARXIV", "http://arxiv.org/abs/", 21 }, + { "DOI", "https://doi.org/", 16 }, + { "JSTOR", "http://www.jstor.org/stable/", 28 }, + { "MRNUMBER", "http://www.ams.org/mathscinet-getitem?mr=", 41 }, + { "PMID", "http://www.ncbi.nlm.nih.gov/pubmed/", 35 }, + { "PMC", "http://www.ncbi.nlm.nih.gov/pmc/articles/", 41 }, + { "ISIREFNUM", "isi:", 4 }, +}; +static int nprefixes = sizeof( prefixes ) / sizeof( prefixes[0] ); + +/* do not add, but recognize */ +static url_t extraprefixes[] = { + /* 00000000001111111112222222222333333333344444444445 */ + /* 12345678901234567890123456789012345678901234567890 */ + { "ARXIV", "arXiv:", 6 }, + { "DOI", "http://dx.doi.org/", 18 }, + { "JSTOR", "jstor:", 6 }, + { "PMID", "pmid:", 5 }, + { "PMID", "pubmed:", 7 }, + { "PMC", "pmc:", 4 }, + { "URL", "\\urllink", 8 }, + { "URL", "\\url", 4 }, +}; +static int nextraprefixes = sizeof( extraprefixes ) / sizeof( extraprefixes[0] ); + +static int +find_prefix( char *s, url_t *p, int np ) +{ + int i; + + for ( i=0; i<np; ++i ) + if ( !strncmp( p[i].prefix, s, p[i].offset ) ) return i; + + return -1; +} + +int +urls_split_and_add( char *value_in, fields *out, int lvl_out ) +{ + int n, fstatus, status = BIBL_OK; + char *tag = "URL"; + int offset = 0; + + n = find_prefix( value_in, prefixes, nprefixes ); + if ( n!=-1 ) { + tag = prefixes[n].tag; + offset = prefixes[n].offset; + } else { + n = find_prefix( value_in, extraprefixes, nextraprefixes ); + if ( n!=-1 ) { + tag = extraprefixes[n].tag; + offset = extraprefixes[n].offset; + } + } + + fstatus = fields_add( out, tag, &(value_in[offset]), lvl_out ); + if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; + + return status; +} + +/* urls_add_type() + * + * Append urls of a specific type with a specific prefix (which can be empty). + * We don't allow duplications here. + * + */ +static int +urls_merge_and_add_type( fields *out, char *tag_out, int lvl_out, char *prefix, vplist *values ) +{ + int fstatus, status = BIBL_OK; + vplist_index i; + str url; + + str_init( &url ); + + for ( i=0; i<values->n; ++i ) { + str_strcpyc( &url, prefix ); + str_strcatc( &url, ( char * ) vplist_get( values, i ) ); + fstatus = fields_add( out, tag_out, str_cstr( &url ), lvl_out ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + + } +out: + str_free( &url ); + return status; +} + +/* + * urls_merge_and_add() + * + * Append urls of types controlled by the list type and automatically append appropriate + * prefixes. If no prefix is found for the entry, don't add one (e.g. "URL" entries). + * + * Control of the types to be added by list type is necessary as some reference formats + * like bibtex ought to do special things with DOI, ARXIV, MRNUMBER, and the like. + */ +int +urls_merge_and_add( fields *in, int lvl_in, fields *out, char *tag_out, int lvl_out, slist *types ) +{ + int i, j, status = BIBL_OK; + char *tag, *prefix, *empty=""; + vplist a; + + vplist_init( &a ); + + for ( i=0; i<types->n; ++i ) { + + tag = slist_cstr( types, i ); + + /* ...look for data of requested type; if not found skip */ + vplist_empty( &a ); + fields_findv_each( in, lvl_in, FIELDS_CHRP, &a, tag ); + if ( a.n==0 ) continue; + + /* ...find the prefix (if present) */ + prefix = empty; + for ( j=0; j<nprefixes; ++j ) { + if ( !strcmp( prefixes[j].tag, tag ) ) { + prefix = prefixes[j].prefix; + break; /* take the first prefix in the list */ + } + } + + /* ...append all data of this type */ + status = urls_merge_and_add_type( out, tag_out, lvl_out, prefix, &a ); + if ( status!=BIBL_OK ) goto out; + } + +out: + vplist_free( &a ); + + return status; +} diff --git a/bibutils/url.h b/bibutils/url.h new file mode 100644 --- /dev/null +++ b/bibutils/url.h @@ -0,0 +1,30 @@ +/* + * url.h + * + * Copyright (c) Chris Putnam 2004-2017 + * + * Source code released under the GPL version 2 + * + */ +#ifndef URL_H +#define URL_H + +#include "slist.h" +#include "fields.h" + +int is_doi( char *s ); +int is_uri_remote_scheme( char *p ); +int is_embedded_link( char *s ); + +void doi_to_url( fields *info, int n, char *urltag, str *doi_url ); +void pmid_to_url( fields *info, int n, char *urltag, str *pmid_url ); +void pmc_to_url( fields *info, int n, char *urltag, str *pmid_url ); +void arxiv_to_url( fields *info, int n, char *urltag, str *arxiv_url ); +void jstor_to_url( fields *info, int n, char *urltag, str *jstor_url ); +void mrnumber_to_url( fields *info, int n, char *urltag, str *jstor_url ); + +int urls_merge_and_add( fields *in, int lvl_in, fields *out, char *tag_out, int lvl_out, slist *types ); +int urls_split_and_add( char *value_in, fields *out, int lvl_out ); + + +#endif diff --git a/bibutils/utf8.c b/bibutils/utf8.c --- a/bibutils/utf8.c +++ b/bibutils/utf8.c @@ -1,12 +1,13 @@ /* * utf8.c * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * */ #include <stdio.h> +#include <string.h> #include "utf8.h" /* UTF-8 encoding @@ -146,5 +147,42 @@ nc = utf8_encode( 0xFEFF, code ); for ( i=0; i<nc; ++i ) fprintf(outptr,"%c",code[i]); +} + +int +utf8_is_bom( char *p ) +{ + unsigned char *up = ( unsigned char * ) p; + + /* ...if null-terminated string is too short, we're ok */ + if ( up[0]!=0xEF ) return 0; + if ( up[1]!=0xBB ) return 0; + if ( up[2]!=0xBF ) return 0; + + return 1; +} + +/* utf8_is_emdash() + * + *emdash = 0xE2 (-30) 0x80 (-128) 0x94 (-108) + */ +int +utf8_is_emdash( char *p ) +{ + const char emdash[3] = { -30, -128, -108 }; + if ( strncmp( p, emdash, 3 ) ) return 0; + return 1; +} + +/* utf8_is_endash() + * + * endash = 0xE2 (-30) 0x80 (-128) 0x93 (-109) + */ +int +utf8_is_endash( char *p ) +{ + const char endash[3] = { -30, -128, -109 }; + if ( strncmp( p, endash, 3 ) ) return 0; + return 1; } diff --git a/bibutils/utf8.h b/bibutils/utf8.h --- a/bibutils/utf8.h +++ b/bibutils/utf8.h @@ -1,7 +1,7 @@ /* * utf8.h * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * @@ -11,10 +11,12 @@ #include <stdio.h> -extern int utf8_encode( unsigned int value, unsigned char out[6] ); -extern void utf8_encode_str( unsigned int value, char outstr[7] ); -extern unsigned int utf8_decode( char *s, unsigned int *pi ); -extern void utf8_writebom( FILE *outptr ); - +int utf8_encode( unsigned int value, unsigned char out[6] ); +void utf8_encode_str( unsigned int value, char outstr[7] ); +unsigned int utf8_decode( char *s, unsigned int *pi ); +void utf8_writebom( FILE *outptr ); +int utf8_is_bom( char *p ); +int utf8_is_emdash( char *p ); +int utf8_is_endash( char *p ); #endif diff --git a/bibutils/vplist.c b/bibutils/vplist.c --- a/bibutils/vplist.c +++ b/bibutils/vplist.c @@ -1,9 +1,9 @@ /* * vplist.c * - * Version: 4/08/2013 + * Version: 1/9/2017 * - * Copyright (c) Chris Putnam 2011-2013 + * Copyright (c) Chris Putnam 2011-2017 * * Source code released under the GPL version 2 * @@ -11,9 +11,19 @@ * */ #include <stdlib.h> -#include <assert.h> #include "vplist.h" +/* Do not use asserts in VPLIST_NOASSERT defined */ +#ifdef VPLIST_NOASSERT +#define NDEBUG +#endif +#include <assert.h> + +#define VPLIST_MINALLOC (20) + +#define VPLIST_EXACT_SIZE (0) +#define VPLIST_DOUBLE_SIZE (1) + void vplist_init( vplist *vpl ) { @@ -31,186 +41,347 @@ return vpl; } -int -vplist_find( vplist *vpl, void *v ) +static inline int +vplist_alloc( vplist *vpl, vplist_index alloc ) { - int i; - assert( vpl ); - for ( i=0; i<vpl->n; ++i ) - if ( vpl->data[i]==v ) return i; - return -1; + vpl->data = ( void ** ) malloc( sizeof( void * ) * alloc ); + if ( !vpl->data ) return VPLIST_MEMERR; + + vpl->max = alloc; + vpl->n = 0; + + return VPLIST_OK; } -int -vplist_copy( vplist *to, vplist *from ) +static inline int +vplist_realloc( vplist *vpl, vplist_index alloc ) { - int i; - assert( to ); - assert( from ); - if ( from->n > to->max ) { - if ( to->max ) free( to->data ); - to->data = ( void ** ) malloc( sizeof( void * ) * from->n ); - if ( !to->data ) return 0; - to->max = from->n; + void **more; + + more = ( void ** ) realloc( vpl->data, sizeof( void * ) * alloc ); + if ( !more ) return VPLIST_MEMERR; + + vpl->data = more; + vpl->max = alloc; + + return VPLIST_OK; +} + +/* vplist_ensure_space( vpl, n, mode ) + * + * Makes sure that vplist can hold at least n members, allocating memory if required. + * + * mode + * - Can either be VPLIST_DOUBLE_SIZE or VPLIST_EXACT_SIZE. + * - If VPLIST_EXACT_SIZE and current size < n, size will be exactly n. + * - If VPLIST_DOUBLE_SIZE and current size < n, size will be doubled (or VPLIST_MINALLOC + * if the vplist is empty) or n, whichever is bigger. + * + * Returns VPLIST_OK or VPLIST_MEMERR. + */ +static int +vplist_ensure_space( vplist *vpl, vplist_index n, unsigned char mode ) +{ + vplist_index alloc = n; + int status = VPLIST_OK; + + if ( vpl->max == 0 ) { + if ( mode == VPLIST_DOUBLE_SIZE && alloc < VPLIST_MINALLOC ) alloc = VPLIST_MINALLOC; + status = vplist_alloc( vpl, alloc ); } - for ( i=0; i<from->n; ++i ) - to->data[i] = from->data[i]; - to->n = from->n; - return 1; + + else if ( vpl->max < n ) { + if ( mode == VPLIST_DOUBLE_SIZE && alloc < 2 * vpl->max ) alloc = 2 * vpl->max; + status = vplist_realloc( vpl, alloc ); + } + + return status; } int -vplist_append( vplist *to, vplist *from ) +vplist_copy( vplist *to, vplist *from ) { - int i, ok; + vplist_index i; + int status; + assert( to ); assert( from ); - for ( i=0; i<from->n; ++i ) { - ok = vplist_add( to, from->data[i] ); - if ( !ok ) return 0; + + status = vplist_ensure_space( to, from->n, VPLIST_EXACT_SIZE ); + + if ( status == VPLIST_OK ) { + + for ( i=0; i<from->n; ++i ) + to->data[i] = from->data[i]; + to->n = from->n; + } - return 1; -} -static int -vplist_validindex( vplist *vpl, int n ) -{ - if ( n < 0 || n >= vpl->n ) return 0; - return 1; + return status; } -static int -vplist_alloc( vplist *vpl ) +int +vplist_fill( vplist *vpl, vplist_index n, void *v ) { - int alloc = 20; - vpl->data = ( void ** ) malloc( sizeof( void * ) * alloc ); - if ( !vpl->data ) return 0; - vpl->max = alloc; - vpl->n = 0; - return 1; -} + vplist_index i; + int status; -static int -vplist_realloc( vplist *vpl ) -{ - void **more; - int alloc = vpl->max * 2; - more = ( void ** ) realloc( vpl->data, sizeof( void * ) * alloc ); - if ( !more ) return 0; - vpl->data = more; - vpl->max = alloc; - return 1; + assert( vpl ); + + status = vplist_ensure_space( vpl, n, VPLIST_EXACT_SIZE ); + + if ( status == VPLIST_OK ) { + + for ( i=0; i<n; ++i ) + vpl->data[i] = v; + vpl->n = n; + + } + + return status; } int vplist_add( vplist *vpl, void *v ) { - int ok = 1; + int status; assert( vpl ); - /* ensure sufficient space */ - if ( vpl->max==0 ) ok = vplist_alloc( vpl ); - else if ( vpl->n >= vpl->max ) ok = vplist_realloc( vpl ); + status = vplist_ensure_space( vpl, vpl->n + 1, VPLIST_DOUBLE_SIZE ); - if ( ok ) { + if ( status == VPLIST_OK ) { + vpl->data[vpl->n] = v; vpl->n++; + } - return ok; + return status; } -void * -vplist_get( vplist *vpl, int n ) +int +vplist_insert_list( vplist *vpl, vplist_index pos, vplist *add ) { + vplist_index i; + int status; + assert( vpl ); - if ( !vplist_validindex( vpl, n ) ) return NULL; - return vpl->data[ n ]; + assert( add ); + assert( pos <= vpl->n ); + + /* nothing to do here */ + if ( add->n < 1 ) return VPLIST_OK; + + status = vplist_ensure_space( vpl, vpl->n + add->n, VPLIST_DOUBLE_SIZE ); + + if ( status == VPLIST_OK ) { + + for ( i=vpl->n-1; i>=pos; --i ) + vpl->data[i+add->n] = vpl->data[i]; + + for ( i=0; i<add->n; ++i ) + vpl->data[pos+i] = add->data[i]; + + vpl->n += add->n; + } + + return status; } -void -vplist_set( vplist *vpl, int n, void *v ) +int +vplist_append( vplist *vpl, vplist *add ) { + vplist_index i; + int status; + assert( vpl ); - if ( !vplist_validindex( vpl, n ) ) return; - vpl->data[ n ] = v; + assert( add ); + + status = vplist_ensure_space( vpl, vpl->n + add->n, VPLIST_DOUBLE_SIZE ); + + if ( status == VPLIST_OK ) { + + for ( i=0; i<add->n; ++i ) + vpl->data[ vpl->n + i ] = add->data[i]; + + vpl->n += add->n; + + } + + return status; } +static void +vplist_freemembers( vplist *vpl, vplist_ptrfree vpf ) +{ + vplist_index i; + void *v; + for ( i=0; i<vpl->n; ++i ) { + v = vplist_get( vpl, i ); + if ( v ) (*vpf)( v ); + } +} + void -vplist_remove( vplist *vpl, int n ) +vplist_emptyfn( vplist *vpl, vplist_ptrfree vpf ) { - int i; assert( vpl ); - if ( !vplist_validindex( vpl, n ) ) return; - for ( i=n+1; i<vpl->n; ++i ) - vpl->data[ i-1 ] = vpl->data[ i ]; - vpl->n -= 1; + if ( vpf ) vplist_freemembers( vpl, vpf ); + vpl->n = 0; } void -vplist_removevp( vplist *vpl, void *v ) +vplist_empty( vplist *vpl ) { - int n; + vplist_emptyfn( vpl, NULL ); +} + +void +vplist_freefn( vplist *vpl, vplist_ptrfree vpf ) +{ assert( vpl ); - do { - n = vplist_find( vpl, v ); - if ( n!=-1 ) vplist_remove( vpl, n ); - } while ( n!=-1 ); + if ( vpf ) vplist_freemembers( vpl, vpf ); + if ( vpl->data ) free( vpl->data ); + vplist_init( vpl ); } -static void -vplist_freemembers( vplist *vpl, vplist_ptrfree vpf ) +void +vplist_free( vplist *vpl ) { - int i; - for ( i=0; i<vpl->n; ++i ) - (*vpf)( vplist_get( vpl, i ) ); + vplist_freefn( vpl, NULL ); } void -vplist_empty( vplist *vpl ) +vplist_deletefn( vplist **vpl, vplist_ptrfree vpf ) { - assert( vpl ); - vpl->n = 0; + vplist_freefn( *vpl, vpf ); + free( *vpl ); + *vpl = NULL; } void -vplist_emptyfn( vplist *vpl, vplist_ptrfree vpf ) +vplist_delete( vplist **vpl ) { + vplist_deletefn( vpl, NULL ); +} + +static inline int +vplist_validindex( vplist *vpl, vplist_index n ) +{ + if ( n < 0 || n >= vpl->n ) return 0; + return 1; +} + +void * +vplist_get( vplist *vpl, vplist_index n ) +{ assert( vpl ); - vplist_freemembers( vpl, vpf ); - vplist_empty( vpl ); + if ( !vplist_validindex( vpl, n ) ) return NULL; + return vpl->data[ n ]; } void -vplist_free( vplist *vpl ) +vplist_set( vplist *vpl, vplist_index n, void *v ) { assert( vpl ); - if ( vpl->data ) free( vpl->data ); - vplist_init( vpl ); + assert( vplist_validindex( vpl, n ) ); + vpl->data[ n ] = v; } +int +vplist_find( vplist *vpl, void *v ) +{ + vplist_index i; + assert( vpl ); + for ( i=0; i<vpl->n; ++i ) + if ( vpl->data[i]==v ) return i; + return -1; +} + void -vplist_freefn( vplist *vpl, vplist_ptrfree vpf ) +vplist_swap( vplist *vpl, vplist_index n1, vplist_index n2 ) { + void *tmp; + assert( vpl ); - vplist_freemembers( vpl, vpf ); - vplist_free( vpl ); + assert( vplist_validindex( vpl, n1 ) ); + assert( vplist_validindex( vpl, n2 ) ); + + tmp = vpl->data[n1]; + vpl->data[n1] = vpl->data[n2]; + vpl->data[n2] = tmp; } +int +vplist_removefn( vplist *vpl, vplist_index n, vplist_ptrfree vpf ) +{ + vplist_index i; + + assert( vpl ); + assert( vplist_validindex( vpl, n ) ); + + if ( vpf ) (*vpf)( vplist_get( vpl, n ) ); + + for ( i=n+1; i<vpl->n; ++i ) + vpl->data[ i-1 ] = vpl->data[ i ]; + vpl->n -= 1; + + return 1; +} + +int +vplist_remove( vplist *vpl, vplist_index n ) +{ + return vplist_removefn( vpl, n, NULL ); +} + +int +vplist_removevpfn( vplist *vpl, void *v, vplist_ptrfree vpf ) +{ + vplist_index n; + int count = 0; + + assert( vpl ); + + do { + n = vplist_find( vpl, v ); + if ( vplist_found( vpl, n ) ) { + vplist_removefn( vpl, n, vpf ); + count++; + } + } while ( vplist_found( vpl, n ) ); + + return count; +} + +int +vplist_removevp( vplist *vpl, void *v ) +{ + return vplist_removevpfn( vpl, v, NULL ); +} + void -vplist_destroy( vplist **vpl ) +vplist_remove_rangefn( vplist *vpl, vplist_index start, vplist_index endplusone, vplist_ptrfree vpf ) { - assert( *vpl ); - vplist_free( *vpl ); - free( *vpl ); - *vpl = NULL; + vplist_index i, n; + + assert( endplusone <= vpl->n ); + assert( endplusone > start ); + + n = endplusone - start; + if ( vpf ) { + for ( i=start; i<endplusone; ++i ) + (*vpf)( vplist_get( vpl, i ) ); + } + for ( i=endplusone; i<vpl->n; ++i ) { + vpl->data[i-n] = vpl->data[i]; + } + vpl->n -= n; } void -vplist_destroyfn( vplist **vpl, vplist_ptrfree vpf ) +vplist_remove_range( vplist *vpl, vplist_index start, vplist_index endplusone ) { - assert( *vpl ); - vplist_freemembers( *vpl, vpf ); - vplist_destroy( vpl ); + vplist_remove_rangefn( vpl, start, endplusone, NULL ); } diff --git a/bibutils/vplist.h b/bibutils/vplist.h --- a/bibutils/vplist.h +++ b/bibutils/vplist.h @@ -1,10 +1,12 @@ /* * vplist.h * - * Version: 4/08/2013 + * generic container to hold a list of pointers to void * - * Copyright (c) Chris Putnam 2011-2013 + * Version: 1/9/2017 * + * Copyright (c) Chris Putnam 2011-2017 + * * Source code released under the GPL version 2 * */ @@ -12,25 +14,41 @@ #ifndef VPLIST_H #define VPLIST_H -/* vplist = void pointer list (generic container struct) - */ +#define VPLIST_MEMERR (-1) +#define VPLIST_OK (0) + +typedef int vplist_index; + typedef struct vplist { - int n, max; + vplist_index n, max; void **data; } vplist; +#define vplist_found( vpl, n ) ( n!=-1 ) +#define vplist_notfound( vpl, n ) ( n==-1 ) + typedef void (*vplist_ptrfree)(void*); -extern void vplist_init( vplist *vpl ); -extern vplist * vplist_new( void ); -extern int vplist_add( vplist *vpl, void *v ); -extern int vplist_copy( vplist *to, vplist *from ); -extern int vplist_append( vplist *to, vplist *from ); -extern void * vplist_get( vplist *vpl, int n ); -extern void vplist_set( vplist *vpl, int n, void *v ); -extern void vplist_remove( vplist *vpl, int n ); -extern void vplist_removevp( vplist *vpl, void *v ); -extern int vplist_find( vplist *vpl, void *v ); +vplist * vplist_new( void ); + +void vplist_init ( vplist *vpl ); +int vplist_add ( vplist *vpl, void *v ); +int vplist_fill ( vplist *vpl, vplist_index n, void *v ); +int vplist_copy ( vplist *to, vplist *from ); +int vplist_append ( vplist *vpl, vplist *add ); +int vplist_insert_list ( vplist *vpl, vplist_index pos, vplist *add ); +void * vplist_get ( vplist *vpl, vplist_index n ); +void vplist_set ( vplist *vpl, vplist_index n, void *v ); +void vplist_swap ( vplist *vpl, vplist_index n1, vplist_index n2 ); +int vplist_remove ( vplist *vpl, vplist_index n ); +int vplist_removefn ( vplist *vpl, vplist_index n, vplist_ptrfree vpf ); +int vplist_removevp ( vplist *vpl, void *v ); +int vplist_removevpfn ( vplist *vpl, void *v, vplist_ptrfree vpf ); +void vplist_remove_rangefn( vplist *vpl, vplist_index start, vplist_index endplusone, vplist_ptrfree vpf ); +void vplist_remove_range ( vplist *vpl, vplist_index start, vplist_index endplusone ); + +vplist_index vplist_find( vplist *vpl, void *v ); + /* * vplist_empty does not free space * @@ -49,20 +67,20 @@ * * vplist_emptyfn( &vpl, free ); */ -extern void vplist_empty( vplist *vpl ); -extern void vplist_emptyfn( vplist *vpl, vplist_ptrfree fn ); +void vplist_empty ( vplist *vpl ); +void vplist_emptyfn( vplist *vpl, vplist_ptrfree fn ); /* * vplist_free frees the space for the data array of void * elements. * * if members require their own free calls, then call vplist_freefn() */ -extern void vplist_free( vplist *vpl ); -extern void vplist_freefn( vplist *vpl, vplist_ptrfree fn ); +void vplist_free ( vplist *vpl ); +void vplist_freefn( vplist *vpl, vplist_ptrfree fn ); /* - * vplist_destroy does vplist_free and deallocates the struct + * vplist_delete does vplist_free and deallocates the struct * vplist * and replaces with NULL. */ -extern void vplist_destroy( vplist **vpl ); -extern void vplist_destroyfn( vplist **vpl, vplist_ptrfree fn ); +void vplist_delete ( vplist **vpl ); +void vplist_deletefn( vplist **vpl, vplist_ptrfree fn ); #endif diff --git a/bibutils/wordin.c b/bibutils/wordin.c --- a/bibutils/wordin.c +++ b/bibutils/wordin.c @@ -1,7 +1,7 @@ /* * wordin.c * - * Copyright (c) Chris Putnam 2010-2013 + * Copyright (c) Chris Putnam 2010-2017 * * Source code released under the GPL version 2 * @@ -9,13 +9,17 @@ #include <stdio.h> #include <stdlib.h> #include "is_ws.h" -#include "newstr.h" -#include "newstr_conv.h" +#include "str.h" +#include "str_conv.h" #include "fields.h" #include "xml.h" #include "xml_encoding.h" -#include "wordin.h" +#include "bibformats.h" +static int wordin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ); +static int wordin_processf( fields *wordin, char *data, char *filename, long nref, param *p ); + + /***************************************************** PUBLIC: void wordin_initparams() *****************************************************/ @@ -43,8 +47,8 @@ p->all = NULL; p->nall = 0; - list_init( &(p->asis) ); - list_init( &(p->corps) ); + slist_init( &(p->asis) ); + slist_init( &(p->corps) ); if ( !progname ) p->progname = NULL; else p->progname = strdup( progname ); @@ -68,35 +72,35 @@ return endptr; } -int -wordin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ) +static int +wordin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, str *line, str *reference, int *fcharset ) { - newstr tmp; + str tmp; char *startptr = NULL, *endptr; int haveref = 0, inref = 0, file_charset = CHARSET_UNKNOWN, m, type = 1; - newstr_init( &tmp ); - while ( !haveref && newstr_fget( fp, buf, bufsize, bufpos, line ) ) { - if ( line->data ) { + str_init( &tmp ); + while ( !haveref && str_fget( fp, buf, bufsize, bufpos, line ) ) { + if ( str_cstr( line ) ) { m = xml_getencoding( line ); if ( m!=CHARSET_UNKNOWN ) file_charset = m; } - if ( line->data ) { - startptr = wordin_findstartwrapper( line->data, &type ); + if ( str_cstr( line ) ) { + startptr = wordin_findstartwrapper( str_cstr( line ), &type ); } if ( startptr || inref ) { - if ( inref ) newstr_strcat( &tmp, line->data ); + if ( inref ) str_strcat( &tmp, line ); else { - newstr_strcat( &tmp, startptr ); + str_strcatc( &tmp, startptr ); inref = 1; } - endptr = wordin_findendwrapper( tmp.data, type ); + endptr = wordin_findendwrapper( str_cstr( &tmp ), type ); if ( endptr ) { - newstr_segcpy( reference, tmp.data, endptr ); + str_segcpy( reference, str_cstr( &tmp ), endptr ); haveref = 1; } } } - newstr_free( &tmp ); + str_free( &tmp ); *fcharset = file_charset; return haveref; } @@ -122,13 +126,13 @@ * Returns BIBL_ERR_MEMERR on memory error, BIBL_OK otherwise. */ static int -wordin_person_last( xml *node, newstr *name ) +wordin_person_last( xml *node, str *name ) { while ( node && !xml_tagexact( node, "b:Last" ) ) node = node->next; - if ( node && node->value->len ) { - newstr_strcpy( name, node->value->data ); - if ( newstr_memerr( name ) ) return BIBL_ERR_MEMERR; + if ( node && str_has_value( node->value ) ) { + str_strcpyc( name, xml_value( node ) ); + if ( str_memerr( name ) ) return BIBL_ERR_MEMERR; } return BIBL_OK; } @@ -141,14 +145,14 @@ * Returns BIBL_ERR_MEMERR on memory error, BIBL_OK otherwise */ static int -wordin_person_first( xml *node, newstr *name ) +wordin_person_first( xml *node, str *name ) { for ( ; node; node=node->next ) { if ( !xml_tagexact( node, "b:First" ) ) continue; - if ( node->value->len ) { - if ( name->len ) newstr_addchar( name, '|' ); - newstr_strcat( name, node->value->data ); - if ( newstr_memerr( name ) ) return BIBL_ERR_MEMERR; + if ( str_has_value( node->value ) ) { + if ( str_has_value( name ) ) str_addchar( name, '|' ); + str_strcatc( name, xml_value( node ) ); + if ( str_memerr( name ) ) return BIBL_ERR_MEMERR; } } return BIBL_OK; @@ -158,9 +162,9 @@ wordin_person( xml *node, fields *info, char *type ) { int status, ret = BIBL_OK; - newstr name; + str name; - newstr_init( &name ); + str_init( &name ); status = wordin_person_last( node, &name ); if ( status!=BIBL_OK ) { @@ -174,10 +178,10 @@ goto out; } - status = fields_add( info, type, name.data, 0 ); + status = fields_add( info, type, str_cstr( &name ), 0 ); if ( status != FIELDS_OK ) ret = BIBL_ERR_MEMERR; out: - newstr_free( &name ); + str_free( &name ); return ret; } @@ -201,42 +205,42 @@ wordin_pages( xml *node, fields *info ) { int i, status, ret = BIBL_OK; - newstr sp, ep; + str sp, ep; char *p; - newstrs_init( &sp, &ep, NULL ); + strs_init( &sp, &ep, NULL ); - p = xml_data( node ); + p = xml_value( node ); while ( *p && *p!='-' ) - newstr_addchar( &sp, *p++ ); - if ( newstr_memerr( &sp ) ) { + str_addchar( &sp, *p++ ); + if ( str_memerr( &sp ) ) { ret = BIBL_ERR_MEMERR; goto out; } if ( *p=='-' ) p++; while ( *p ) - newstr_addchar( &ep, *p++ ); - if ( newstr_memerr( &ep ) ) { + str_addchar( &ep, *p++ ); + if ( str_memerr( &ep ) ) { ret = BIBL_ERR_MEMERR; goto out; } - if ( sp.len ) { - status = fields_add( info, "PAGESTART", sp.data, 1 ); + if ( str_has_value( &sp ) ) { + status = fields_add( info, "PAGES:START", str_cstr( &sp ), 1 ); if ( status!=FIELDS_OK ) { ret = BIBL_ERR_MEMERR; goto out; } } - if ( ep.len ) { + if ( str_has_value( &ep ) ) { if ( sp.len > ep.len ) { for ( i=sp.len-ep.len; i<sp.len; ++i ) sp.data[i] = ep.data[i-sp.len+ep.len]; - status = fields_add( info, "PAGEEND", sp.data, 1 ); + status = fields_add( info, "PAGES:STOP", str_cstr( &sp ), 1 ); } else - status = fields_add( info, "PAGEEND", ep.data, 1 ); + status = fields_add( info, "PAGES:STOP", str_cstr( &ep ), 1 ); if ( status!=FIELDS_OK ) { ret = BIBL_ERR_MEMERR; goto out; @@ -244,7 +248,7 @@ } out: - newstrs_free( &sp, &ep, NULL ); + strs_free( &sp, &ep, NULL ); return ret; } @@ -252,28 +256,28 @@ wordin_reference( xml *node, fields *info ) { int status, ret = BIBL_OK; - if ( xml_hasdata( node ) ) { + if ( xml_hasvalue( node ) ) { if ( xml_tagexact( node, "b:Tag" ) ) { - status = fields_add( info, "REFNUM", xml_data( node ), 0 ); + status = fields_add( info, "REFNUM", xml_value( node ), 0 ); if ( status!=FIELDS_OK ) ret = BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "b:SourceType" ) ) { } else if ( xml_tagexact( node, "b:City" ) ) { - status = fields_add( info, "ADDRESS", xml_data( node ), 0 ); + status = fields_add( info, "ADDRESS", xml_value( node ), 0 ); if ( status!=FIELDS_OK ) ret = BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "b:Publisher" ) ) { - status = fields_add( info, "PUBLISHER", xml_data( node ), 0 ); + status = fields_add( info, "PUBLISHER", xml_value( node ), 0 ); if ( status!=FIELDS_OK ) ret = BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "b:Title" ) ) { - status = fields_add( info, "TITLE", xml_data( node ), 0 ); + status = fields_add( info, "TITLE", xml_value( node ), 0 ); if ( status!=FIELDS_OK ) ret = BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "b:JournalName" ) ) { - status = fields_add( info, "TITLE", xml_data( node ), 1 ); + status = fields_add( info, "TITLE", xml_value( node ), 1 ); if ( status!=FIELDS_OK ) ret = BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "b:Volume" ) ) { - status = fields_add( info, "VOLUME", xml_data( node ), 1 ); + status = fields_add( info, "VOLUME", xml_value( node ), 1 ); if ( status!=FIELDS_OK ) ret = BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "b:Comments" ) ) { - status = fields_add( info, "NOTES", xml_data( node ), 0 ); + status = fields_add( info, "NOTES", xml_value( node ), 0 ); if ( status!=FIELDS_OK ) ret = BIBL_ERR_MEMERR; } else if ( xml_tagexact( node, "b:Pages" ) ) { ret = wordin_pages( node, info ); @@ -293,14 +297,14 @@ int ret = BIBL_OK; if ( xml_tagexact( node, "b:Source" ) ) { if ( node->down ) ret = wordin_reference( node->down, info ); - } else if ( node->tag->len==0 && node->down ) { + } else if ( str_is_empty( node->tag ) && node->down ) { ret = wordin_assembleref( node->down, info ); } return ret; } -int -wordin_processf( fields *wordin, char *data, char *filename, long nref ) +static int +wordin_processf( fields *wordin, char *data, char *filename, long nref, param *p ) { int status, ret = 1; xml top; diff --git a/bibutils/wordin.h b/bibutils/wordin.h deleted file mode 100644 --- a/bibutils/wordin.h +++ /dev/null @@ -1,23 +0,0 @@ -/* - * wordin.h - * - * Copyright (c) Chris Putnam 2009-2013 - * - * Source code released under the GPL version 2 - * - */ -#ifndef WORDIN_H -#define WORDIN_H - -#include "newstr.h" -#include "fields.h" -#include "reftypes.h" -#include "bibutils.h" - -extern int wordin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ); -extern int wordin_processf( fields *wordin, char *data, char *filename, long nref ); - -extern void wordin_initparams( param *p, const char *progname ); - -#endif - diff --git a/bibutils/wordout.c b/bibutils/wordout.c --- a/bibutils/wordout.c +++ b/bibutils/wordout.c @@ -3,7 +3,7 @@ * * (Word 2007 format) * - * Copyright (c) Chris Putnam 2007-2014 + * Copyright (c) Chris Putnam 2007-2017 * * Source code released under the GPL version 2 * @@ -11,11 +11,15 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include "newstr.h" +#include "str.h" #include "fields.h" #include "utf8.h" -#include "wordout.h" +#include "bibformats.h" +static void wordout_writeheader( FILE *outptr, param *p ); +static void wordout_writefooter( FILE *outptr ); +static int wordout_write( fields *info, FILE *outptr, param *p, unsigned long numrefs ); + void wordout_initparams( param *p, const char *progname ) { @@ -41,8 +45,9 @@ } typedef struct convert { - char oldtag[25]; - char newtag[25]; + char *oldtag; + char *newtag; + char *prefix; int code; } convert; @@ -102,24 +107,28 @@ * fixed output */ static void -output_fixed( FILE *outptr, char *tag, char *data, int level ) +output_fixed( FILE *outptr, char *tag, char *value, int level ) { int i; for ( i=0; i<level; ++i ) fprintf( outptr, " " ); - fprintf( outptr, "<%s>%s</%s>\n", tag, data, tag ); + fprintf( outptr, "<%s>%s</%s>\n", tag, value, tag ); } /* detail output * */ static void -output_item( fields *info, FILE *outptr, char *tag, int item, int level ) +output_item( fields *info, FILE *outptr, char *tag, char *prefix, int item, int level ) { int i; if ( item==-1 ) return; for ( i=0; i<level; ++i ) fprintf( outptr, " " ); - fprintf( outptr, "<%s>%s</%s>\n", tag, info->data[item].data, tag ); - fields_setused( info, item ); + fprintf( outptr, "<%s>%s%s</%s>\n", + tag, + prefix, + (char*) fields_value( info, item, FIELDS_CHRP ), + tag + ); } static void @@ -157,7 +166,7 @@ int i, n; for ( i=0; i<nc; ++i ) { n = fields_find( info, c[i].oldtag, c[i].code ); - if ( n!=-1 ) output_item( info, outptr, c[i].newtag, n, 0 ); + if ( n!=-1 ) output_item( info, outptr, c[i].newtag, c[i].prefix, n, 0 ); } } @@ -195,11 +204,11 @@ get_type_from_genre( fields *info ) { int type = TYPE_UNKNOWN, i, j, level; - char *genre; + char *genre, *tag; for ( i=0; i<info->n; ++i ) { - if ( strcasecmp( info->tag[i].data, "GENRE" ) && - strcasecmp( info->tag[i].data, "NGENRE" ) ) continue; - genre = info->data[i].data; + tag = (char *) fields_tag( info, i, FIELDS_CHRP ); + if ( strcasecmp( tag, "GENRE" ) && strcasecmp( tag, "NGENRE" ) ) continue; + genre = (char *) fields_value( info, i, FIELDS_CHRP ); for ( j=0; j<ngenres; ++j ) { if ( !strcasecmp( genres[j].out, genre ) ) type = genres[j].value; @@ -220,7 +229,7 @@ } else if ( !strcasecmp( genre, "conference publication" ) ) { if ( level==0 ) type=TYPE_CONFERENCE; - type = TYPE_PROCEEDINGS; + else type = TYPE_PROCEEDINGS; } else if ( !strcasecmp( genre, "thesis" ) ) { if ( type==TYPE_UNKNOWN ) type=TYPE_THESIS; @@ -240,11 +249,11 @@ get_type_from_resource( fields *info ) { int type = TYPE_UNKNOWN, i; - char *resource; + char *tag, *resource; for ( i=0; i<info->n; ++i ) { - if ( strcasecmp( info->tag[i].data, "GENRE" )!=0 && - strcasecmp( info->tag[i].data, "NGENRE" )!=0 ) continue; - resource = info->data[i].data; + tag = (char *) fields_tag( info, i, FIELDS_CHRP ); + if ( strcasecmp( tag, "GENRE" ) && strcasecmp( tag, "NGENRE" ) ) continue; + resource = (char *) fields_value( info, i, FIELDS_CHRP ); if ( !strcasecmp( resource, "moving image" ) ) type = TYPE_FILM; } @@ -262,43 +271,68 @@ } static void -output_titleinfo( fields *info, FILE *outptr, char *tag, int level ) +output_titlebits( char *mainttl, char *subttl, FILE *outptr ) { - newstr *mainttl = fields_findv( info, level, FIELDS_STRP, "TITLE" ); - newstr *subttl = fields_findv( info, level, FIELDS_STRP, "SUBTITLE" ); + if ( mainttl ) fprintf( outptr, "%s", mainttl ); + if ( subttl ) { + if ( mainttl ) { + if ( mainttl[ strlen( mainttl ) - 1 ] != '?' ) + fprintf( outptr, ": " ); + else fprintf( outptr, " " ); + } + fprintf( outptr, "%s", subttl ); + } +} + +static void +output_titleinfo( char *mainttl, char *subttl, FILE *outptr, char *tag, int level ) +{ if ( mainttl || subttl ) { fprintf( outptr, "<%s>", tag ); - if ( mainttl ) fprintf( outptr, "%s", mainttl->data ); - if ( subttl ) { - if ( mainttl ) { - if ( mainttl->len > 0 && - mainttl->data[mainttl->len-1]!='?' ) - fprintf( outptr, ": " ); - else fprintf( outptr, " " ); - } - fprintf( outptr, "%s", subttl->data ); - } + output_titlebits( mainttl, subttl, outptr ); fprintf( outptr, "</%s>\n", tag ); } } static void -output_title( fields *info, FILE *outptr, int level ) +output_generaltitle( fields *info, FILE *outptr, char *tag, int level ) { - char *ttl = fields_findv( info, level, FIELDS_CHRP, "TITLE" ); - char *subttl = fields_findv( info, level, FIELDS_CHRP, "SUBTITLE" ); - char *shrttl = fields_findv( info, level, FIELDS_CHRP, "SHORTTITLE" ); + char *ttl = fields_findv( info, level, FIELDS_CHRP, "TITLE" ); + char *subttl = fields_findv( info, level, FIELDS_CHRP, "SUBTITLE" ); + char *shrttl = fields_findv( info, level, FIELDS_CHRP, "SHORTTITLE" ); + char *shrsubttl = fields_findv( info, level, FIELDS_CHRP, "SHORTSUBTITLE" ); - output_titleinfo( info, outptr, "b:Title", level ); + if ( ttl ) { + output_titleinfo( ttl, subttl, outptr, tag, level ); + } + else if ( shrttl ) { + output_titleinfo( shrttl, shrsubttl, outptr, tag, level ); + } +} - /* output shorttitle if it's different from normal title */ - if ( shrttl ) { - if ( !ttl || ( strcmp( shrttl, ttl ) || subttl ) ) { - fprintf( outptr, " <b:ShortTitle>" ); - fprintf( outptr, "%s", shrttl ); - fprintf( outptr, "</b:ShortTitle>\n" ); +static void +output_maintitle( fields *info, FILE *outptr, int level ) +{ + char *ttl = fields_findv( info, level, FIELDS_CHRP, "TITLE" ); + char *subttl = fields_findv( info, level, FIELDS_CHRP, "SUBTITLE" ); + char *shrttl = fields_findv( info, level, FIELDS_CHRP, "SHORTTITLE" ); + char *shrsubttl = fields_findv( info, level, FIELDS_CHRP, "SHORTSUBTITLE" ); + + if ( ttl ) { + output_titleinfo( ttl, subttl, outptr, "b:Title", level ); + + /* output shorttitle if it's different from normal title */ + if ( shrttl ) { + if ( !ttl || ( strcmp( shrttl, ttl ) || subttl ) ) { + fprintf( outptr, " <b:ShortTitle>" ); + output_titlebits( shrttl, shrsubttl, outptr ); + fprintf( outptr, "</b:ShortTitle>\n" ); + } } } + else if ( shrttl ) { + output_titleinfo( shrttl, shrsubttl, outptr, "b:Title", level ); + } } static void @@ -312,40 +346,39 @@ static void output_name( FILE *outptr, char *p ) { - newstr family, part; + str family, part; int n=0, npart=0; - newstr_init( &family ); - while ( *p && *p!='|' ) newstr_addchar( &family, *p++ ); + str_init( &family ); + while ( *p && *p!='|' ) str_addchar( &family, *p++ ); if ( *p=='|' ) p++; - if ( family.len ) { + if ( str_has_value( &family ) ) { fprintf( outptr, "<b:Person>" ); - fprintf( outptr, "<b:Last>%s</b:Last>",family.data ); + fprintf( outptr, "<b:Last>%s</b:Last>", str_cstr( &family ) ); n++; } - newstr_free( &family ); + str_free( &family ); - newstr_init( &part ); + str_init( &part ); while ( *p ) { - while ( *p && *p!='|' ) newstr_addchar( &part, *p++ ); - if ( part.len ) { + while ( *p && *p!='|' ) str_addchar( &part, *p++ ); + if ( str_has_value( &part ) ) { if ( n==0 ) fprintf( outptr, "<b:Person>" ); if ( npart==0 ) - fprintf( outptr, "<b:First>%s</b:First>", - part.data ); - else fprintf( outptr, "<b:Middle>%s</b:Middle>", - part.data ); + fprintf( outptr, "<b:First>%s</b:First>", str_cstr( &part ) ); + else + fprintf( outptr, "<b:Middle>%s</b:Middle>", str_cstr( &part ) ); n++; npart++; } if ( *p=='|' ) { p++; - newstr_empty( &part ); + str_empty( &part ); } } if ( n ) fprintf( outptr, "</b:Person>\n" ); - newstr_free( &part ); + str_free( &part ); } @@ -354,12 +387,12 @@ #define NAME_CORP (4) static int -extract_name_and_info( newstr *outtag, newstr *intag ) +extract_name_and_info( str *outtag, str *intag ) { int code = NAME; - newstr_newstrcpy( outtag, intag ); - if ( newstr_findreplace( outtag, ":ASIS", "" ) ) code = NAME_ASIS; - if ( newstr_findreplace( outtag, ":CORP", "" ) ) code = NAME_CORP; + str_strcpy( outtag, intag ); + if ( str_findreplace( outtag, ":ASIS", "" ) ) code = NAME_ASIS; + if ( str_findreplace( outtag, ":CORP", "" ) ) code = NAME_CORP; return code; } @@ -367,25 +400,24 @@ output_name_type( fields *info, FILE *outptr, int level, char *map[], int nmap, char *tag ) { - newstr ntag; + str ntag; int i, j, n=0, code, nfields; - newstr_init( &ntag ); + str_init( &ntag ); nfields = fields_num( info ); for ( j=0; j<nmap; ++j ) { for ( i=0; i<nfields; ++i ) { code = extract_name_and_info( &ntag, &(info->tag[i]) ); - if ( strcasecmp( ntag.data, map[j] ) ) continue; + if ( strcasecmp( str_cstr( &ntag ), map[j] ) ) continue; if ( n==0 ) fprintf( outptr, "<%s><b:NameList>\n", tag ); if ( code != NAME ) - output_name_nomangle( outptr, info->data[i].data ); + output_name_nomangle( outptr, (char *) fields_value( info, i, FIELDS_CHRP ) ); else - output_name( outptr, info->data[i].data ); - fields_setused( info, i ); + output_name( outptr, (char *) fields_value( info, i, FIELDS_CHRP ) ); n++; } } - newstr_free( &ntag ); + str_free( &ntag ); if ( n ) fprintf( outptr, "</b:NameList></%s>\n", tag ); } @@ -418,11 +450,11 @@ output_date( fields *info, FILE *outptr, int level ) { char *year = fields_findv_firstof( info, level, FIELDS_CHRP, - "PARTYEAR", "YEAR", NULL ); + "PARTDATE:YEAR", "DATE:YEAR", NULL ); char *month = fields_findv_firstof( info, level, FIELDS_CHRP, - "PARTMONTH", "MONTH", NULL ); + "PARTDATE:MONTH", "DATE:MONTH", NULL ); char *day = fields_findv_firstof( info, level, FIELDS_CHRP, - "PARTDAY", "DAY", NULL ); + "PARTDATE:DAY", "DATE:DAY", NULL ); if ( year ) output_itemv( outptr, "b:Year", year, 0 ); if ( month ) output_itemv( outptr, "b:Month", month, 0 ); if ( day ) output_itemv( outptr, "b:Day", day, 0 ); @@ -431,8 +463,8 @@ static void output_pages( fields *info, FILE *outptr, int level ) { - char *sn = fields_findv( info, LEVEL_ANY, FIELDS_CHRP, "PAGESTART" ); - char *en = fields_findv( info, LEVEL_ANY, FIELDS_CHRP, "PAGEEND" ); + char *sn = fields_findv( info, LEVEL_ANY, FIELDS_CHRP, "PAGES:START" ); + char *en = fields_findv( info, LEVEL_ANY, FIELDS_CHRP, "PAGES:STOP" ); char *ar = fields_findv( info, LEVEL_ANY, FIELDS_CHRP, "ARTICLENUMBER" ); if ( sn || en ) output_range( outptr, "b:Pages", sn, en, level ); @@ -444,13 +476,13 @@ output_includedin( fields *info, FILE *outptr, int type ) { if ( type==TYPE_JOURNALARTICLE ) { - output_titleinfo( info, outptr, "b:JournalName", 1 ); + output_generaltitle( info, outptr, "b:JournalName", 1 ); } else if ( type==TYPE_ARTICLEINAPERIODICAL ) { - output_titleinfo( info, outptr, "b:PeriodicalTitle", 1 ); + output_generaltitle( info, outptr, "b:PeriodicalTitle", 1 ); } else if ( type==TYPE_BOOKSECTION ) { - output_titleinfo( info, outptr, "b:ConferenceName", 1 ); /*??*/ + output_generaltitle( info, outptr, "b:ConferenceName", 1 ); /*??*/ } else if ( type==TYPE_PROCEEDINGS ) { - output_titleinfo( info, outptr, "b:ConferenceName", 1 ); + output_generaltitle( info, outptr, "b:ConferenceName", 1 ); } } @@ -483,7 +515,7 @@ strcasecmp( tag, "DEGREEGRANTOR:ASIS") & strcasecmp( tag, "DEGREEGRANTOR:CORP")) continue; - output_item( info, outptr, "b:Institution", i, 0 ); + output_item( info, outptr, "b:Institution", "", i, 0 ); } } @@ -534,9 +566,9 @@ static void output_comments( fields *info, FILE *outptr, int level ) { + vplist_index i; vplist notes; char *abs; - int i; vplist_init( ¬es ); @@ -564,20 +596,26 @@ output_citeparts( fields *info, FILE *outptr, int level, int max, int type ) { convert origin[] = { - { "ADDRESS", "b:City", LEVEL_ANY }, - { "PUBLISHER", "b:Publisher", LEVEL_ANY }, - { "EDITION", "b:Edition", LEVEL_ANY } + { "ADDRESS", "b:City", "", LEVEL_ANY }, + { "PUBLISHER", "b:Publisher", "", LEVEL_ANY }, + { "EDITION", "b:Edition", "", LEVEL_ANY } }; int norigin = sizeof( origin ) / sizeof ( convert ); convert parts[] = { - { "VOLUME", "b:Volume", LEVEL_ANY }, - { "SECTION", "b:Section", LEVEL_ANY }, - { "ISSUE", "b:Issue", LEVEL_ANY }, - { "NUMBER", "b:Issue", LEVEL_ANY }, - { "PUBLICLAWNUMBER", "b:Volume", LEVEL_ANY }, - { "SESSION", "b:Issue", LEVEL_ANY }, - { "URL", "b:Url", LEVEL_ANY }, + { "VOLUME", "b:Volume", "", LEVEL_ANY }, + { "SECTION", "b:Section", "", LEVEL_ANY }, + { "ISSUE", "b:Issue", "", LEVEL_ANY }, + { "NUMBER", "b:Issue", "", LEVEL_ANY }, + { "PUBLICLAWNUMBER", "b:Volume", "", LEVEL_ANY }, + { "SESSION", "b:Issue", "", LEVEL_ANY }, + { "URL", "b:Url", "", LEVEL_ANY }, + { "JSTOR", "b:Url", "http://www.jstor.org/stable/", LEVEL_ANY }, + { "ARXIV", "b:Url", "http://arxiv.org/abs/", LEVEL_ANY }, + { "PMID", "b:Url", "http://www.ncbi.nlm.nih.gov/pubmed/", LEVEL_ANY }, + { "PMC", "b:Url", "http://www.ncbi.nlm.nih.gov/pmc/articles/", LEVEL_ANY }, + { "DOI", "b:Url", "https://doi.org/", LEVEL_ANY }, + { "MRNUMBER", "b:Url", "http://www.ams.org/mathscinet-getitem?mr=", LEVEL_ANY }, }; int nparts=sizeof(parts)/sizeof(convert); @@ -589,11 +627,11 @@ output_list( info, outptr, parts, nparts ); output_pages( info, outptr, level ); output_names( info, outptr, level, type ); - output_title( info, outptr, 0 ); + output_maintitle( info, outptr, 0 ); output_comments( info, outptr, level ); } -void +static int wordout_write( fields *info, FILE *outptr, param *p, unsigned long numrefs ) { int max = fields_maxlevel( info ); @@ -604,9 +642,11 @@ fprintf( outptr, "</b:Source>\n" ); fflush( outptr ); + + return BIBL_OK; } -void +static void wordout_writeheader( FILE *outptr, param *p ) { if ( p->utf8bom ) utf8_writebom( outptr ); @@ -616,7 +656,7 @@ " xmlns=\"http://schemas.openxmlformats.org/officeDocument/2006/bibliography\" >\n"); } -void +static void wordout_writefooter( FILE *outptr ) { fprintf(outptr,"</b:Sources>\n"); diff --git a/bibutils/wordout.h b/bibutils/wordout.h deleted file mode 100644 --- a/bibutils/wordout.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * wordout.h - * - * Copyright (c) Chris Putnam 2008-2013 - * - * Source code released under the GPL version 2 - * - */ -#ifndef WORDOUT_H -#define WORDOUT_H - -/* format-specific options */ -#define WORDOUT_DROPKEY (2) - -#include <stdio.h> -#include "bibl.h" -#include "bibutils.h" - -extern void wordout_writeheader( FILE *outptr, param *p ); -extern void wordout_writefooter( FILE *outptr ); -extern void wordout_write( fields *info, FILE *outptr, param *p, - unsigned long numrefs ); -extern void wordout_initparams( param *p, const char *progname ); - - -#endif - diff --git a/bibutils/xml.c b/bibutils/xml.c --- a/bibutils/xml.c +++ b/bibutils/xml.c @@ -1,7 +1,7 @@ /* * xml.c * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * @@ -11,7 +11,6 @@ #include <string.h> #include "is_ws.h" #include "strsearch.h" -#include "newstr.h" #include "xml.h" char *xml_pns = NULL; @@ -21,8 +20,8 @@ { xml_attrib *a = (xml_attrib *) malloc( sizeof( xml_attrib ) ); if ( a ) { - list_init( &(a->attrib) ); - list_init( &(a->value) ); + slist_init( &(a->attrib) ); + slist_init( &(a->value) ); } return a; } @@ -30,17 +29,17 @@ static void xmlattrib_add( xml_attrib *a, char *attrib, char *value ) { - if ( attrib ) list_addc( &(a->attrib), attrib ); - else list_addc( &(a->attrib), "" ); - if ( value ) list_addc( &(a->value), value ); - else list_addc( &(a->value), "" ); + if ( attrib ) slist_addc( &(a->attrib), attrib ); + else slist_addc( &(a->attrib), "" ); + if ( value ) slist_addc( &(a->value), value ); + else slist_addc( &(a->value), "" ); } static void xmlattrib_free( xml_attrib *a ) { - list_free( &(a->attrib) ); - list_free( &(a->value ) ); + slist_free( &(a->attrib) ); + slist_free( &(a->value ) ); } static xml * @@ -55,11 +54,11 @@ xml_free( xml *x ) { if ( x->tag ) { - newstr_free( x->tag ); + str_free( x->tag ); free( x->tag ); } if ( x->value ) { - newstr_free( x->value ); + str_free( x->value ); free( x->value ); } if ( x->a ) { @@ -73,8 +72,8 @@ void xml_init( xml *x ) { - x->tag = newstr_new(); - x->value = newstr_new(); + x->tag = str_new(); + x->value = str_new(); x->a = NULL; x->down = NULL; x->next = NULL; @@ -117,14 +116,14 @@ xml_attrib *a = NULL; char quote_character = '\"'; int inquotes = 0; - newstr aname, aval; - newstr_init( &aname ); - newstr_init( &aval ); + str aname, aval; + str_init( &aname ); + str_init( &aval ); while ( *p && !xml_terminator(p,type) ) { /* get attribute name */ while ( *p==' ' || *p=='\t' ) p++; while ( *p && !strchr( "= \t", *p ) && !xml_terminator(p,type)){ - newstr_addchar( &aname, *p ); + str_addchar( &aname, *p ); p++; } while ( *p==' ' || *p=='\t' ) p++; @@ -138,18 +137,18 @@ } while ( *p && ((!xml_terminator(p,type) && !strchr("= \t", *p ))||inquotes)){ if ( *p==quote_character ) inquotes=0; - else newstr_addchar( &aval, *p ); + else str_addchar( &aval, *p ); p++; } - if ( aname.len ) { + if ( str_has_value( &aname ) ) { if ( !a ) a = xmlattrib_new(); - xmlattrib_add( a, aname.data, aval.data ); + xmlattrib_add( a, str_cstr( &aname ), str_cstr( &aval ) ); } - newstr_empty( &aname ); - newstr_empty( &aval ); + str_empty( &aname ); + str_empty( &aval ); } - newstr_free( &aname ); - newstr_free( &aval ); + str_free( &aname ); + str_free( &aval ); *ap = a; return p; } @@ -164,30 +163,30 @@ * XML_OPENCLOSE <A/> */ static char * -xml_processtag( char *p, newstr *tag, xml_attrib **attrib, int *type ) +xml_processtag( char *p, str *tag, xml_attrib **attrib, int *type ) { *attrib = NULL; if ( *p=='<' ) p++; if ( *p=='!' ) { - while ( *p && *p!='>' ) newstr_addchar( tag, *p++ ); + while ( *p && *p!='>' ) str_addchar( tag, *p++ ); *type = XML_COMMENT; } else if ( *p=='?' ) { *type = XML_DESCRIPTOR; p++; /* skip '?' */ while ( *p && !strchr( " \t", *p ) && !xml_terminator(p,type) ) - newstr_addchar( tag, *p++ ); + str_addchar( tag, *p++ ); if ( *p==' ' || *p=='\t' ) p = xml_processattrib( p, attrib, type ); } else if ( *p=='/' ) { while ( *p && !strchr( " \t", *p ) && !xml_terminator(p,type) ) - newstr_addchar( tag, *p++ ); + str_addchar( tag, *p++ ); *type = XML_CLOSE; if ( *p==' ' || *p=='\t' ) p = xml_processattrib( p, attrib, type ); } else { *type = XML_OPEN; while ( *p && !strchr( " \t", *p ) && !xml_terminator(p,type) ) - newstr_addchar( tag, *p++ ); + str_addchar( tag, *p++ ); if ( *p==' ' || *p=='\t' ) p = xml_processattrib( p, attrib, type ); } @@ -210,28 +209,28 @@ char * xml_tree( char *p, xml *onode ) { - newstr tag; + str tag; xml_attrib *attrib; int type, is_style = 0; - newstr_init( &tag ); + str_init( &tag ); while ( *p ) { /* retain white space for <style> tags in endnote xml */ - if ( onode->tag && onode->tag->data && - !strcasecmp(onode->tag->data,"style") ) is_style=1; + if ( onode->tag && str_cstr( onode->tag ) && + !strcasecmp( str_cstr( onode->tag ),"style") ) is_style=1; while ( *p && *p!='<' ) { if ( onode->value->len>0 || is_style || !is_ws( *p ) ) - newstr_addchar( onode->value, *p ); + str_addchar( onode->value, *p ); p++; } if ( *p=='<' ) { - newstr_empty( &tag ); + str_empty( &tag ); p = xml_processtag( p, &tag, &attrib, &type ); if ( type==XML_OPEN || type==XML_OPENCLOSE || type==XML_DESCRIPTOR ) { xml *nnode = xml_new(); - newstr_newstrcpy( nnode->tag, &tag ); + str_strcpy( nnode->tag, &tag ); nnode->a = attrib; xml_appendnode( onode, nnode ); if ( type==XML_OPEN ) @@ -243,7 +242,7 @@ } } out: - newstr_free( &tag ); + str_free( &tag ); return p; } @@ -253,13 +252,13 @@ int i,j; if ( !x ) return; for ( i=0; i<n; ++i ) printf( " " ); - printf("n=%d tag='%s' value='%s'\n", n, x->tag->data, x->value->data ); + printf("n=%d tag='%s' value='%s'\n", n, str_cstr( x->tag ), str_cstr( x->value ) ); if ( x->a ) { for ( j=0; j<x->a->value.n; ++j ) { for ( i=0; i<n; ++i ) printf( " " ); printf(" attrib='%s' value='%s'\n", - (x->a)->attrib.str[j].data, - (x->a)->value.str[j].data ); + slist_cstr( &(x->a)->attrib, j ), + slist_cstr( &(x->a)->attrib, j ) ); } } if ( x->down ) xml_draw( x->down, n+1 ); @@ -269,85 +268,95 @@ char * xml_findstart( char *buffer, char *tag ) { - newstr starttag; + str starttag; char *p; - newstr_init( &starttag ); - newstr_addchar( &starttag, '<' ); - newstr_strcat( &starttag, tag ); - newstr_addchar( &starttag, ' ' ); - p = strsearch( buffer, starttag.data ); + str_init( &starttag ); + str_addchar( &starttag, '<' ); + str_strcatc( &starttag, tag ); + str_addchar( &starttag, ' ' ); + p = strsearch( buffer, str_cstr( &starttag ) ); if ( !p ) { starttag.data[ starttag.len-1 ] = '>'; - p = strsearch( buffer, starttag.data ); + p = strsearch( buffer, str_cstr( &starttag ) ); } - newstr_free( &starttag ); + str_free( &starttag ); return p; } char * xml_findend( char *buffer, char *tag ) { - newstr endtag; + str endtag; char *p; - newstr_init( &endtag ); - newstr_strcpy( &endtag, "</" ); + str_init( &endtag ); + str_strcpyc( &endtag, "</" ); if ( xml_pns ) { - newstr_strcat( &endtag, xml_pns ); - newstr_addchar( &endtag, ':' ); + str_strcatc( &endtag, xml_pns ); + str_addchar( &endtag, ':' ); } - newstr_strcat( &endtag, tag ); - newstr_addchar( &endtag, '>' ); + str_strcatc( &endtag, tag ); + str_addchar( &endtag, '>' ); - p = strsearch( buffer, endtag.data ); + p = strsearch( buffer, str_cstr( &endtag ) ); if ( p && *p ) { if ( *p ) p++; /* skip <random_tag></end> combo */ while ( *p && *(p-1)!='>' ) p++; } - newstr_free( &endtag ); + str_free( &endtag ); return p; } -int -xml_tagexact( xml *node, char *s ) +static int +xml_tagexact_simple( xml* node, char *s ) { - newstr tag; + if ( node->tag->len!=strlen( s ) ) return 0; + if ( strcasecmp( str_cstr( node->tag ), s ) ) return 0; + return 1; +} +static int +xml_tagexact_pns( xml* node, char *s ) +{ int found = 0; - if ( xml_pns ) { - newstr_init( &tag ); - newstr_strcpy( &tag, xml_pns ); - newstr_addchar( &tag, ':' ); - newstr_strcat( &tag, s ); - if ( node->tag->len==tag.len && - !strcasecmp( node->tag->data, tag.data ) ) - found = 1; - newstr_free( &tag ); - } else { - if ( node->tag->len==strlen( s ) && - !strcasecmp( node->tag->data, s ) ) - found = 1; - } + str tag; + + str_init( &tag ); + str_strcpyc( &tag, xml_pns ); + str_addchar( &tag, ':' ); + str_strcatc( &tag, s ); + if ( node->tag->len==tag.len && + !strcasecmp( str_cstr( node->tag ), str_cstr( &tag ) ) ) + found = 1; + str_free( &tag ); + return found; } +int +xml_tagexact( xml *node, char *s ) +{ + if ( xml_pns ) return xml_tagexact_pns( node, s ); + else return xml_tagexact_simple( node, s ); +} int xml_hasattrib( xml *node, char *attrib, char *value ) { xml_attrib *na = node->a; + char *a, *v; int i; if ( na ) { for ( i=0; i<na->attrib.n; ++i ) { - if ( !na->attrib.str[i].data || !na->value.str[i].data ) - continue; - if ( !strcasecmp( na->attrib.str[i].data, attrib ) && - !strcasecmp( na->value.str[i].data, value ) ) + a = slist_cstr( &(na->attrib), i ); + v = slist_cstr( &(na->value), i ); + if ( !a || !v ) continue; + if ( !strcasecmp( a, attrib ) && !strcasecmp( v, value ) ) return 1; } @@ -363,38 +372,43 @@ return xml_hasattrib( node, attrib, value ); } -newstr * +str * xml_getattrib( xml *node, char *attrib ) { - newstr *ns = NULL; xml_attrib *na = node->a; - int i, nattrib; + str *ns = NULL; + int i; + if ( na ) { - nattrib = na->attrib.n; - for ( i=0; i<nattrib; ++i ) - if ( !strcasecmp( na->attrib.str[i].data, attrib ) ) - ns = &(na->value.str[i]); + for ( i=0; i<na->attrib.n; ++i ) + if ( !strcasecmp( slist_cstr( &(na->attrib), i ), attrib ) ) + ns = slist_str( &(na->value), i ); } return ns; } int -xml_hasdata( xml *node ) +xml_hasvalue( xml *node ) { - if ( node && node->value && node->value->data ) return 1; + if ( node && node->value && str_cstr( node->value ) ) return 1; return 0; } char * -xml_data( xml *node ) +xml_tag( xml *node ) { - return node->value->data; + return str_cstr( node->tag ); } +char * +xml_value( xml *node ) +{ + return str_cstr( node->value ); +} + int -xml_tagwithdata( xml *node, char *tag ) +xml_tagwithvalue( xml *node, char *tag ) { - if ( !xml_hasdata( node ) ) return 0; + if ( !xml_hasvalue( node ) ) return 0; return xml_tagexact( node, tag ); } - diff --git a/bibutils/xml.h b/bibutils/xml.h --- a/bibutils/xml.h +++ b/bibutils/xml.h @@ -1,7 +1,7 @@ /* * xml.h * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2017 * * Source code released under the GPL version 2 * @@ -9,36 +9,37 @@ #ifndef XML_H #define XML_H -#include "list.h" -#include "newstr.h" +#include "slist.h" +#include "str.h" typedef struct xml_attrib { - list attrib; - list value; + slist attrib; + slist value; } xml_attrib; typedef struct xml { - newstr *tag; - newstr *value; + str *tag; + str *value; xml_attrib *a; struct xml *down; struct xml *next; } xml; -extern void xml_init( xml *x ); -extern newstr * xml_getattrib( xml *node, char *attrib ); -extern char * xml_findstart( char *buffer, char *tag ); -extern char * xml_findend( char *buffer, char *tag ); -extern int xml_tagexact( xml *node, char *s ); -extern int xml_tag_attrib( xml *node, char *s, char *attrib, char *value ); -extern int xml_hasattrib( xml *node, char *attrib, char *value ); -extern void xml_free( xml *x ); -extern char * xml_tree( char *p, xml *onode ); -extern int xml_hasdata( xml *node ); -extern char * xml_data( xml *node ); -extern int xml_tagwithdata( xml *node, char *tag ); +void xml_init ( xml *x ); +void xml_free ( xml *x ); +str * xml_getattrib ( xml *node, char *attrib ); +char * xml_findstart ( char *buffer, char *tag ); +char * xml_findend ( char *buffer, char *tag ); +int xml_tagexact ( xml *node, char *s ); +int xml_tag_attrib ( xml *node, char *s, char *attrib, char *value ); +int xml_hasattrib ( xml *node, char *attrib, char *value ); +char * xml_tree ( char *p, xml *onode ); +int xml_hasvalue ( xml *node ); +char * xml_value ( xml *node ); +char * xml_tag ( xml *node ); +int xml_tagwithvalue( xml *node, char *tag ); -extern char *xml_pns; /* global Namespace */ +char * xml_pns; /* global Namespace */ #endif diff --git a/bibutils/xml_encoding.c b/bibutils/xml_encoding.c --- a/bibutils/xml_encoding.c +++ b/bibutils/xml_encoding.c @@ -1,7 +1,7 @@ /* * xml_getencoding.c * - * Copyright (c) Chris Putnam 2007-2013 + * Copyright (c) Chris Putnam 2007-2017 * * Source code released under the GPL version 2 * @@ -10,29 +10,31 @@ #include <stdlib.h> #include <string.h> #include "charsets.h" -#include "newstr.h" -#include "newstr_conv.h" +#include "str.h" +#include "str_conv.h" #include "xml.h" #include "xml_encoding.h" static int xml_getencodingr( xml *node ) { - newstr *s; int n = CHARSET_UNKNOWN, m; + str *s; + char *t; + if ( xml_tagexact( node, "xml" ) ) { s = xml_getattrib( node, "encoding" ); - if ( s && s->data ) { - if ( !strcasecmp( s->data, "UTF-8" ) ) + if ( str_has_value( s ) ) { + t = str_cstr( s ); + if ( !strcasecmp( t, "UTF-8" ) ) n = CHARSET_UNICODE; - else if ( !strcasecmp( s->data, "UTF8" ) ) + else if ( !strcasecmp( t, "UTF8" ) ) n = CHARSET_UNICODE; - else if ( !strcasecmp( s->data, "GB18030" ) ) + else if ( !strcasecmp( t, "GB18030" ) ) n = CHARSET_GB18030; - else n = charset_find( s->data ); + else n = charset_find( t ); if ( n==CHARSET_UNKNOWN ) { - fprintf( stderr, "Warning: did not recognize " - "encoding '%s'\n", s->data ); + fprintf( stderr, "Warning: did not recognize encoding '%s'\n", t ); } } } @@ -44,29 +46,31 @@ m = xml_getencodingr( node->next ); if ( m!=CHARSET_UNKNOWN ) n = m; } + return n; } int -xml_getencoding( newstr *s ) +xml_getencoding( str *s ) { - newstr descriptor; - xml descriptxml; int file_charset = CHARSET_UNKNOWN; + str descriptor; + xml descriptxml; char *p, *q; - p = strstr( s->data, "<?xml" ); - if ( !p ) p = strstr( s->data, "<?XML" ); + + p = strstr( str_cstr( s ), "<?xml" ); + if ( !p ) p = strstr( str_cstr( s ), "<?XML" ); if ( p ) { q = strstr( p, "?>" ); if ( q ) { - newstr_init( &descriptor ); - newstr_segcpy( &descriptor, p, q+2 ); + str_init( &descriptor ); + str_segcpy( &descriptor, p, q+2 ); xml_init( &descriptxml ); - xml_tree( descriptor.data, &descriptxml ); + xml_tree( str_cstr( &descriptor ), &descriptxml ); file_charset = xml_getencodingr( &descriptxml ); xml_free( &descriptxml ); - newstr_free( &descriptor ); - newstr_segdel( s, p, q+2 ); + str_free( &descriptor ); + str_segdel( s, p, q+2 ); } } return file_charset; diff --git a/bibutils/xml_encoding.h b/bibutils/xml_encoding.h --- a/bibutils/xml_encoding.h +++ b/bibutils/xml_encoding.h @@ -1,7 +1,7 @@ /* * xml_getencoding.h * - * Copyright (c) Chris Putnam 2007-2013 + * Copyright (c) Chris Putnam 2007-2017 * * Source code released under the GPL version 2 * @@ -9,6 +9,6 @@ #ifndef XML_GETENCODING_H #define XML_GETENCODING_H -extern int xml_getencoding( newstr *s ); +extern int xml_getencoding( str *s ); #endif diff --git a/hs-bibutils.cabal b/hs-bibutils.cabal --- a/hs-bibutils.cabal +++ b/hs-bibutils.cabal @@ -1,6 +1,6 @@ name: hs-bibutils -version: 5.5 -homepage: http://istitutocolli.org/repos/hs-bibutils/ +version: 6.2 +homepage: https://github.com/wilx/hs-bibutils synopsis: Haskell bindings to bibutils, the bibliography conversion utilities. @@ -9,15 +9,12 @@ library that interconverts between various bibliography formats using a common MODS-format XML intermediate. - . + . hs-bibutils is available under the GNU GPL license. See the LICENSE file for details. . For more details about bibutils, please check: - <http://sourceforge.net/p/bibutils/home/Bibutils/>. - . - The original API documentation is available here: - <http://www.scripps.edu/~cdputnam/software/bibutils/library_specs.html>. + <http://sourceforge.net/p/bibutils/home/Bibutils/>. . The package release number refers to the release number of the included bibutils library. @@ -26,78 +23,78 @@ license: GPL license-file: LICENSE author: Andrea Rossato -maintainer: andrea.rossato@unitn.it -cabal-version: >= 1.4 +maintainer: Václav Haisman <vhaisman@gmail.com> +cabal-version: >= 1.23 build-type: Simple extra-source-files: - bibutils/adsout.c bibutils/adsout.h bibutils/adsout_journals.c - bibutils/bibcore.c bibutils/bibl.c bibutils/bibl.h - bibutils/biblatexin.c bibutils/biblatexin.h - bibutils/bibtexin.c bibutils/bibtexin.h bibutils/bibtexout.c - bibutils/bibtexout.h bibutils/bibtextypes.c - bibutils/bibutils.c bibutils/bibutils.h bibutils/bltypes.c - bibutils/charsets.c bibutils/charsets.h bibutils/copacin.c - bibutils/copacin.h bibutils/copactypes.c bibutils/doi.c - bibutils/doi.h bibutils/ebiin.c bibutils/ebiin.h - bibutils/endin.c bibutils/endin.h bibutils/endout.c - bibutils/endout.h bibutils/endtypes.c bibutils/endxmlin.c - bibutils/endxmlin.h bibutils/entities.c bibutils/entities.h + bibutils/adsout.c bibutils/adsout_journals.c bibutils/bibcore.c + bibutils/bibformats.h bibutils/biblatexin.c bibutils/bibl.c + bibutils/bibl.h bibutils/bibtexin.c bibutils/bibtexout.c + bibutils/bibtextypes.c bibutils/bibutils.c bibutils/bibutils.h + bibutils/bltypes.c bibutils/charsets.c bibutils/charsets.h + bibutils/copacin.c bibutils/copactypes.c bibutils/ebiin.c + bibutils/endin.c bibutils/endout.c bibutils/endtypes.c + bibutils/endxmlin.c bibutils/entities.c bibutils/entities.h bibutils/fields.c bibutils/fields.h bibutils/gb18030.c - bibutils/gb18030.h bibutils/gb18030_enumeration.c - bibutils/intlist.c bibutils/intlist.h bibutils/is_ws.c - bibutils/is_ws.h bibutils/isiin.c bibutils/isiin.h - bibutils/isiout.c bibutils/isiout.h bibutils/isitypes.c + bibutils/gb18030_enumeration.c bibutils/gb18030.h bibutils/generic.c + bibutils/generic.h bibutils/intlist.c bibutils/intlist.h + bibutils/isiin.c bibutils/isiout.c bibutils/isitypes.c bibutils/iso639_1.c bibutils/iso639_1.h bibutils/iso639_2.c bibutils/iso639_2.h bibutils/iso639_3.c bibutils/iso639_3.h - bibutils/latex.c bibutils/latex.h bibutils/list.c - bibutils/list.h bibutils/marc.c bibutils/marc.h - bibutils/medin.c bibutils/medin.h bibutils/modsin.c - bibutils/modsin.h bibutils/modsout.c bibutils/modsout.h - bibutils/modstypes.c bibutils/modstypes.h bibutils/name.c - bibutils/name.h bibutils/newstr.c bibutils/newstr.h - bibutils/newstr_conv.c bibutils/newstr_conv.h - bibutils/reftypes.c bibutils/reftypes.h bibutils/risin.c - bibutils/risin.h bibutils/risout.c bibutils/risout.h + bibutils/is_ws.c bibutils/is_ws.h bibutils/latex.c bibutils/latex.h + bibutils/marc.c bibutils/marc.h bibutils/medin.c bibutils/modsin.c + bibutils/modsout.c bibutils/modstypes.c bibutils/modstypes.h + bibutils/name.c bibutils/name.h bibutils/nbibin.c + bibutils/nbibtypes.c bibutils/notes.c bibutils/notes.h + bibutils/pages.c bibutils/pages.h bibutils/reftypes.c + bibutils/reftypes.h bibutils/risin.c bibutils/risout.c bibutils/ristypes.c bibutils/serialno.c bibutils/serialno.h - bibutils/strsearch.c bibutils/strsearch.h bibutils/title.c - bibutils/title.h bibutils/unicode.c bibutils/unicode.h - bibutils/utf8.c bibutils/utf8.h bibutils/vplist.c - bibutils/vplist.h bibutils/wordin.c bibutils/wordin.h - bibutils/wordout.c bibutils/wordout.h bibutils/xml.c - bibutils/xml.h bibutils/xml_encoding.c bibutils/xml_encoding.h + bibutils/slist.c bibutils/slist.h bibutils/str.c bibutils/str_conv.c + bibutils/str_conv.h bibutils/str.h bibutils/strsearch.c + bibutils/strsearch.h bibutils/title.c bibutils/title.h + bibutils/unicode.c bibutils/unicode.h bibutils/url.c bibutils/url.h + bibutils/utf8.c bibutils/utf8.h bibutils/vplist.c bibutils/vplist.h + bibutils/wordin.c bibutils/wordout.c bibutils/xml.c + bibutils/xml_encoding.c bibutils/xml_encoding.h bibutils/xml.h + README.md ChangeLog.md library + default-language: Haskell2010 exposed-modules: Text.Bibutils other-modules: ghc-options: -funbox-strict-fields -Wall - ghc-prof-options: -prof -auto-all hs-source-dirs: src - extensions: ForeignFunctionInterface + default-extensions: ForeignFunctionInterface include-dirs: bibutils includes: bibutils.h c-sources: cbits/stub.c - bibutils/adsout.c bibutils/adsout_journals.c - bibutils/bibcore.c bibutils/bibl.c bibutils/biblatexin.c - bibutils/bibtexin.c bibutils/bibtexout.c - bibutils/bibtextypes.c bibutils/bibutils.c bibutils/bltypes.c - bibutils/charsets.c bibutils/copacin.c bibutils/copactypes.c - bibutils/doi.c bibutils/ebiin.c bibutils/endin.c + bibutils/adsout.c bibutils/adsout_journals.c bibutils/bibcore.c + bibutils/biblatexin.c bibutils/bibl.c bibutils/bibtexin.c + bibutils/bibtexout.c bibutils/bibtextypes.c bibutils/bibutils.c + bibutils/bltypes.c bibutils/charsets.c bibutils/copacin.c + bibutils/copactypes.c bibutils/ebiin.c bibutils/endin.c bibutils/endout.c bibutils/endtypes.c bibutils/endxmlin.c bibutils/entities.c bibutils/fields.c bibutils/gb18030.c - bibutils/intlist.c bibutils/is_ws.c bibutils/isiin.c - bibutils/isiout.c bibutils/isitypes.c bibutils/iso639_1.c - bibutils/iso639_2.c bibutils/iso639_3.c bibutils/latex.c - bibutils/list.c bibutils/marc.c bibutils/medin.c + bibutils/generic.c bibutils/intlist.c + bibutils/isiin.c bibutils/isiout.c bibutils/isitypes.c + bibutils/iso639_1.c bibutils/iso639_2.c bibutils/iso639_3.c + bibutils/is_ws.c bibutils/latex.c bibutils/marc.c bibutils/medin.c bibutils/modsin.c bibutils/modsout.c bibutils/modstypes.c - bibutils/name.c bibutils/newstr.c bibutils/newstr_conv.c - bibutils/reftypes.c bibutils/risin.c bibutils/risout.c - bibutils/ristypes.c bibutils/serialno.c bibutils/strsearch.c - bibutils/title.c bibutils/unicode.c bibutils/utf8.c - bibutils/vplist.c bibutils/wordin.c bibutils/wordout.c - bibutils/xml.c bibutils/xml_encoding.c + bibutils/name.c bibutils/nbibin.c bibutils/nbibtypes.c + bibutils/notes.c bibutils/pages.c bibutils/reftypes.c + bibutils/risin.c bibutils/risout.c bibutils/ristypes.c + bibutils/serialno.c bibutils/slist.c bibutils/str.c + bibutils/str_conv.c bibutils/strsearch.c bibutils/title.c + bibutils/unicode.c bibutils/url.c bibutils/utf8.c bibutils/vplist.c + bibutils/wordin.c bibutils/wordout.c bibutils/xml.c + bibutils/xml_encoding.c if impl(ghc >= 6.10) build-depends: base >= 4, syb else build-depends: base >= 3 && < 4 + +source-repository head + type: git + location: https://github.com/wilx/hs-bibutils diff --git a/src/Text/Bibutils.hsc b/src/Text/Bibutils.hsc --- a/src/Text/Bibutils.hsc +++ b/src/Text/Bibutils.hsc @@ -5,7 +5,7 @@ -- Copyright : (C) 2008 Andrea Rossato -- License : BSD3 -- --- Maintainer : andrea.rossato@unitn.it +-- Maintainer : vhaisman@gmail.com -- Stability : provisional -- Portability : portable -- @@ -98,7 +98,6 @@ , bibout_uppercase , bibout_strictkey , modsout_dropkey - , wordout_dropkey -- * Charsets , Charset @@ -403,19 +402,16 @@ newtype FormatOpt = FormatOpt { unFormatOpt :: CInt } -#include "bibtexout.h" -#include "modsout.h" -#include "wordout.h" +#include "bibutils.h" #{enum FormatOpt, FormatOpt - , bibout_finalcomma = BIBOUT_FINALCOMMA - , bibout_singledash = BIBOUT_SINGLEDASH - , bibout_whitespace = BIBOUT_WHITESPACE - , bibout_brackets = BIBOUT_BRACKETS - , bibout_uppercase = BIBOUT_UPPERCASE - , bibout_strictkey = BIBOUT_STRICTKEY - , modsout_dropkey = MODSOUT_DROPKEY - , wordout_dropkey = WORDOUT_DROPKEY + , bibout_finalcomma = BIBL_FORMAT_BIBOUT_FINALCOMMA + , bibout_singledash = BIBL_FORMAT_BIBOUT_SINGLEDASH + , bibout_whitespace = BIBL_FORMAT_BIBOUT_WHITESPACE + , bibout_brackets = BIBL_FORMAT_BIBOUT_BRACKETS + , bibout_uppercase = BIBL_FORMAT_BIBOUT_UPPERCASE + , bibout_strictkey = BIBL_FORMAT_BIBOUT_STRICTKEY + , modsout_dropkey = BIBL_FORMAT_MODSOUT_DROPKEY } newtype Status = Status { status :: CInt }