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 2007-2013 - * Copyright (c) Chris Putnam 2007-2013 + * Copyright (c) Richard Mathar 2007-2014 + * Copyright (c) Chris Putnam 2007-2014 * * Program and source code released under the GPL version 2 * @@ -29,7 +29,7 @@ p->latexout = 0; p->utf8out = BIBL_CHARSET_UTF8_DEFAULT; p->utf8bom = BIBL_CHARSET_BOM_DEFAULT; - p->xmlout = 0; + p->xmlout = BIBL_XMLOUT_FALSE; p->nosplittitle = 0; p->verbose = 0; p->addcount = 0; 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 2005-2013 + * Copyright (c) Chris Putnam 2005-2014 * * Source code released under the GPL version 2 * @@ -88,16 +88,26 @@ fflush( fp ); } -static void +/* bibl_duplicateparams() + * + * Returns status of BIBL_OK or BIBL_ERR_MEMERR + */ +static int bibl_duplicateparams( param *np, param *op ) { + int ok; list_init( &(np->asis) ); list_init( &(np->corps) ); - list_copy( &(np->asis), &(op->asis ) ); - list_copy( &(np->corps), &(op->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; if ( !op->progname ) np->progname = NULL; - else np->progname = strdup( op->progname ); + else { + np->progname = strdup( op->progname ); + if ( !np->progname ) return BIBL_ERR_MEMERR; + } np->readformat = op->readformat; np->writeformat = op->writeformat; @@ -133,78 +143,121 @@ np->all = op->all; np->nall = op->nall; + return BIBL_OK; } -static void +/* bibl_setreadparams() + * + * Returns status of BIBL_OK or BIBL_ERR_MEMERR + */ +static int bibl_setreadparams( param *np, param *op ) { - bibl_duplicateparams( np, op ); - np->utf8out = 1; - np->charsetout = BIBL_CHARSET_UNICODE; - np->charsetout_src = BIBL_SRC_DEFAULT; - np->xmlout = 0; - np->latexout = 0; - np->writeformat = BIBL_INTERNALOUT; + int status; + status = bibl_duplicateparams( np, op ); + if ( status == BIBL_OK ) { + np->utf8out = 1; + np->charsetout = BIBL_CHARSET_UNICODE; + np->charsetout_src = BIBL_SRC_DEFAULT; + np->xmlout = BIBL_XMLOUT_FALSE; + np->latexout = 0; + np->writeformat = BIBL_INTERNALOUT; + } + return status; } -static void +/* bibl_setwriteparams() + * + * Returns status of BIBL_OK or BIBL_ERR_MEMERR + */ +static int bibl_setwriteparams( param *np, param *op ) { - bibl_duplicateparams( np, op ); - np->xmlin = 0; - np->latexin = 0; - np->utf8in = 1; - np->charsetin = BIBL_CHARSET_UNICODE; - np->charsetin_src = BIBL_SRC_DEFAULT; - np->readformat = BIBL_INTERNALIN; + int status; + status = bibl_duplicateparams( np, op ); + if ( status == BIBL_OK ) { + np->xmlin = 0; + np->latexin = 0; + np->utf8in = 1; + np->charsetin = BIBL_CHARSET_UNICODE; + np->charsetin_src = BIBL_SRC_DEFAULT; + np->readformat = BIBL_INTERNALIN; + } + return status; } void bibl_freeparams( param *p ) { - list_free( &(p->asis) ); - list_free( &(p->corps) ); - if ( p->progname ) free( p->progname ); -} - -static void -bibl_readlist( list *pl, char *progname, char *filename ) -{ - if ( !list_fill( pl, filename ) ) { - fprintf( stderr, "%s: warning problems reading '%s' " - "obtained %d elements\n", progname, filename, - pl->n ); + if ( p ) { + list_free( &(p->asis) ); + list_free( &(p->corps) ); + if ( p->progname ) free( p->progname ); } } -void -bibl_readasis( param *p, char *filename ) +int +bibl_readasis( param *p, char *f ) { - bibl_readlist( &(p->asis), p->progname, filename ); -} + int status; -void -bibl_readcorps( param *p, char *filename ) -{ - bibl_readlist( &(p->corps), p->progname, filename ); + if ( !p ) return BIBL_ERR_BADINPUT; + if ( !f ) return BIBL_ERR_BADINPUT; + + status = list_fill( &(p->asis), f, 1 ); + + if ( status == LIST_ERR_CANNOTOPEN ) return BIBL_ERR_CANTOPEN; + else if ( status == 0 ) return BIBL_ERR_MEMERR; + return BIBL_OK; } -static void -bibl_addtolist( list *pl, char *entry ) +int +bibl_readcorps( param *p, char *f ) { - list_add( pl, entry ); + int status; + + if ( !p ) return BIBL_ERR_BADINPUT; + if ( !f ) return BIBL_ERR_BADINPUT; + + status = list_fill( &(p->corps), f, 1 ); + + if ( status == LIST_ERR_CANNOTOPEN ) return BIBL_ERR_CANTOPEN; + else if ( status == 0 ) return BIBL_ERR_MEMERR; + return BIBL_OK; } -void -bibl_addtoasis( param *p, char *entry ) +/* bibl_addtoasis() + * + * Returns BIBL_OK or BIBL_ERR_MEMERR + */ +int +bibl_addtoasis( param *p, char *d ) { - bibl_addtolist( &(p->asis), entry ); + newstr *s; + + if ( !p ) return BIBL_ERR_BADINPUT; + if ( !d ) return BIBL_ERR_BADINPUT; + + s = list_addc( &(p->asis), d ); + + return ( s==NULL )? BIBL_ERR_MEMERR : BIBL_OK; } -void -bibl_addtocorps( param *p, char *entry ) +/* bibl_addtocorps() + * + * Returns BIBL_OK or BIBL_ERR_MEMERR + */ +int +bibl_addtocorps( param *p, char *d ) { - bibl_addtolist( &(p->corps), entry ); + newstr *s; + + if ( !p ) return BIBL_ERR_BADINPUT; + if ( !d ) return BIBL_ERR_BADINPUT; + + s = list_addc( &(p->corps), d ); + + return ( s==NULL )? BIBL_ERR_MEMERR : BIBL_OK; } void @@ -240,7 +293,7 @@ else return 0; } -void +static void bibl_verbose2( fields *f, char *filename, long nrefs ) { int i, n; @@ -256,7 +309,8 @@ fflush( stderr ); } -void +#if 0 +static void bibl_verbose1( fields *f, fields *orig, char *filename, long nrefs ) { int i, n; @@ -270,8 +324,9 @@ } if ( f ) bibl_verbose2( f, filename, nrefs ); } +#endif -void +static void bibl_verbose0( bibl *bin ) { int i; @@ -287,7 +342,7 @@ * tag = "NGENRE" * value = "Masters thesis" */ -static void +static int extract_tag_value( newstr *tag, newstr *value, char *p ) { newstr_empty( tag ); @@ -295,12 +350,18 @@ newstr_addchar( tag, *p ); p++; } + if ( newstr_memerr( tag ) ) return BIBL_ERR_MEMERR; + if ( p && *p=='|' ) p++; + newstr_empty( value ); while ( p && *p ) { newstr_addchar( value, *p ); p++; } + if ( newstr_memerr( tag ) ) return BIBL_ERR_MEMERR; + + return BIBL_OK; } /* process_defaultadd() @@ -312,29 +373,40 @@ static int process_defaultadd( fields *f, int reftype, param *r ) { - int i, n, process, level, ok = 1; + int i, n, process, level, status, ret = BIBL_OK; newstr tag, value; char *p; newstrs_init( &tag, &value, NULL ); for ( i=0; iall[reftype].ntags; ++i ) { + process = ((r->all[reftype]).tags[i]).processingtype; if ( process!=DEFAULT ) continue; + level = ((r->all[reftype]).tags[i]).level; p = ((r->all[reftype]).tags[i]).newstr; - extract_tag_value( &tag, &value, p ); + + status = extract_tag_value( &tag, &value, p ); + if ( status!=BIBL_OK ) { + ret = status; + goto out; + } + n = fields_find( f, tag.data, level ); if ( n==-1 ) { - ok = fields_add( f, tag.data, value.data, level ); - if ( !ok ) goto out; + status = fields_add( f, tag.data, value.data, level ); + if ( status!=FIELDS_OK ) { + ret = BIBL_ERR_MEMERR; + goto out; + } } + } out: newstrs_free( &tag, &value, NULL ); - if ( ok ) return BIBL_OK; - else return BIBL_ERR_MEMERR; + return ret; } /* process_alwaysadd() @@ -346,27 +418,37 @@ static int process_alwaysadd( fields *f, int reftype, param *r ) { - int i, process, level, ok = 1; + int i, process, level, status, ret = BIBL_OK; newstr tag, value; char *p; newstrs_init( &tag, &value, NULL ); for ( i=0; iall[reftype].ntags; ++i ) { + process = ((r->all[reftype]).tags[i]).processingtype; if ( process!=ALWAYS ) continue; + level = ((r->all[reftype]).tags[i]).level; - p = ((r->all[reftype]).tags[i]).newstr; - extract_tag_value( &tag, &value, p ); - ok = fields_add( f, tag.data, value.data, level ); - if ( !ok ) goto out; + p = ((r->all[reftype]).tags[i]).newstr; + + status = extract_tag_value( &tag, &value, p ); + if ( status!=BIBL_OK ) { + ret = status; + goto out; + } + + status = fields_add( f, tag.data, value.data, level ); + if ( status!=FIELDS_OK ) { + ret = BIBL_ERR_MEMERR; + goto out; + } } out: newstrs_free( &tag, &value, NULL ); - if ( ok ) return BIBL_OK; - else return BIBL_ERR_MEMERR; + return ret; } static int @@ -384,7 +466,7 @@ if ( !ref ) { ret = BIBL_ERR_MEMERR; bibl_free( bin ); - goto out0; + goto out; } if ( p->processf( ref, reference.data, filename, nrefs+1 )){ ok = bibl_addref( bin, ref ); @@ -393,7 +475,7 @@ bibl_free( bin ); fields_free( ref ); free( ref ); - goto out0; + goto out; } } else { fields_free( ref ); @@ -411,7 +493,7 @@ } } if ( p->charsetin==CHARSET_UNICODE ) p->utf8in = 1; -out0: +out: newstr_free( &line ); newstr_free( &reference ); return ret; @@ -421,15 +503,19 @@ static int bibl_notexify( char *tag ) { - char *protected[] = { "DOI", "URL", "REFNUM" }; + char *protected[] = { "DOI", "URL", "REFNUM", "FILEATTACH" }; int i, nprotected = sizeof( protected ) / sizeof( protected[0] ); for ( i=0; icharsetout, p->latexout, p->utf8out, p->xmlout ); } - if ( !ok ) return 0; + if ( !ok ) return BIBL_ERR_MEMERR; } - return 1; + return BIBL_OK; } +/* bibl_fixcharsets() + * + * returns BIBL_OK or BIBL_ERR_MEMERR + */ static int bibl_fixcharsets( bibl *b, param *p ) { + int status = BIBL_OK; long i; - int ok; - for ( i=0; inrefs; ++i ) { - ok = bibl_fixcharsetfields( b->ref[i], p ); - if ( !ok ) return 0; - } - return 1; + for ( i=0; inrefs && status==BIBL_OK; ++i ) + status = bibl_fixcharsetdata( b->ref[i], p ); + return status; } static int -build_refnum( fields *f, long nrefs ) +build_refnum( fields *f, long nrefs, int *n ) { char *year, *author, *p, num[512]; + int status, ret = BIBL_OK; newstr refnum; + *n = -1; + newstr_init( &refnum ); year = fields_findv( f, LEVEL_MAIN, FIELDS_CHRP_NOUSE, "YEAR" ); @@ -500,38 +591,56 @@ sprintf( num, "%ld", nrefs ); newstr_mergestrs( &refnum, "ref", num, NULL ); } + if ( newstr_memerr( &refnum ) ) { + ret = BIBL_ERR_MEMERR; + goto out; + } - fields_add( f, "REFNUM", refnum.data, 0 ); + status = fields_add( f, "REFNUM", refnum.data, 0 ); + if ( status!=FIELDS_OK ) ret = BIBL_ERR_MEMERR; + else *n = fields_find( f, "REFNUM", 0 ); + +out: newstr_free( &refnum ); - return fields_find( f, "REFNUM", 0 ); + return ret; } -static void +static int bibl_checkrefid( bibl *b, param *p ) { + char buf[512]; + int n, status; fields *ref; long i; - char buf[512]; - int n; + for ( i=0; inrefs; ++i ) { ref = b->ref[i]; n = fields_find( ref, "REFNUM", 0 ); - if ( n==-1 ) n = build_refnum( ref, i+1 ); + if ( n==-1 ) { + status = build_refnum( ref, i+1, &n ); + if ( status!=BIBL_OK ) return status; + } if ( p->addcount ) { sprintf( buf, "_%ld", i+1 ); newstr_strcat( &(ref->data[n]), buf ); + if ( newstr_memerr( &(ref->data[n]) ) ) + return BIBL_ERR_MEMERR; } } + + return BIBL_OK; } static int generate_citekey( fields *f, int nref ) { - newstr citekey; - int n1, n2; + int n1, n2, status, ret; char *p, buf[100]; + newstr citekey; + newstr_init( &citekey ); + n1 = fields_find( f, "AUTHOR", 0 ); if ( n1==-1 ) n1 = fields_find( f, "AUTHOR", -1 ); n2 = fields_find( f, "YEAR", 0 ); @@ -549,21 +658,31 @@ if ( !is_ws( *p ) ) newstr_addchar( &citekey, *p ); p++; } - fields_add( f, "REFNUM", citekey.data, 0 ); + if ( newstr_memerr( &citekey ) ) { + ret = -1; + goto out; + } + status = fields_add( f, "REFNUM", citekey.data, 0 ); + if ( status!=FIELDS_OK ) { + ret = -1; + goto out; + } } else { sprintf( buf, "ref%d\n", nref ); newstr_strcpy( &citekey, buf ); } + ret = fields_find( f, "REFNUM", -1 ); +out: newstr_free( &citekey ); - return fields_find( f, "REFNUM", -1 ); + return ret; } -static void +static int resolve_citekeys( bibl *b, list *citekeys, int *dup ) { - char abc[]="abcdefghijklmnopqrstuvwxyz"; + const char abc[]="abcdefghijklmnopqrstuvwxyz"; + int nsame, ntmp, n, i, j, status = BIBL_OK; newstr tmp; - int nsame, ntmp, n, i, j; newstr_init( &tmp ); @@ -573,6 +692,10 @@ for ( j=i; jn; ++j ) { if ( dup[j]!=i ) continue; newstr_newstrcpy( &tmp, &(citekeys->str[j]) ); + if ( newstr_memerr( &tmp ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } ntmp = nsame; while ( ntmp >= 26 ) { newstr_addchar( &tmp, 'a' ); @@ -580,38 +703,56 @@ } if ( ntmp<26 && ntmp>=0 ) newstr_addchar( &tmp, abc[ntmp] ); + if ( newstr_memerr( &tmp ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } nsame++; dup[j] = -1; n = fields_find( b->ref[j], "REFNUM", -1 ); - if ( n!=-1 ) + if ( n!=-1 ) { newstr_newstrcpy(&((b->ref[j])->data[n]),&tmp); + if ( newstr_memerr( &((b->ref[j])->data[n]) ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } + } } } +out: newstr_free( &tmp ); + return status; } -static void +static int get_citekeys( bibl *b, list *citekeys ) { + newstr *s; fields *f; int i, n; 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 ) - list_add( citekeys, f->data[n].data ); - else - list_add( citekeys, "" ); + if ( n!=-1 && f->data[n].data ) { + s = list_add( citekeys, &(f->data[n]) ); + if ( !s ) return BIBL_ERR_MEMERR; + } else { + s = list_addc( citekeys, "" ); + if ( !s ) return BIBL_ERR_MEMERR; + } } + return BIBL_OK; } static int dup_citekeys( bibl *b, list *citekeys ) { - int i, j, *dup, ndup=0; + int i, j, status = BIBL_OK, *dup, ndup=0; + dup = ( int * ) malloc( sizeof( int ) * citekeys->n ); - if ( !dup ) return 0; + if ( !dup ) return BIBL_ERR_MEMERR; + for ( i=0; in; ++i ) dup[i] = -1; for ( i=0; in-1; ++i ) { if ( dup[i]!=-1 ) continue; @@ -624,32 +765,37 @@ } } } - if ( ndup ) resolve_citekeys( b, citekeys, dup ); + if ( ndup ) status = resolve_citekeys( b, citekeys, dup ); free( dup ); - return ndup; + return status; } -static void +static int uniqueify_citekeys( bibl *b ) { list citekeys; + int status; list_init( &citekeys ); - get_citekeys( b, &citekeys ); - dup_citekeys( b, &citekeys ); + status = get_citekeys( b, &citekeys ); + if ( status!=BIBL_OK ) goto out; + status = dup_citekeys( b, &citekeys ); +out: list_free( &citekeys ); + return status; } -static void +static int clean_ref( bibl *bin, param *p ) { - if ( p->cleanf ) p->cleanf( bin, p ); + if ( p->cleanf ) return p->cleanf( bin, p ); + else return BIBL_OK; } static int convert_ref( bibl *bin, char *fname, bibl *bout, param *p ) { fields *rin, *rout; - int reftype = 0, ok; + int reftype = 0, ok, status; long i; for ( i=0; inrefs; ++i ) { @@ -658,37 +804,41 @@ if ( !rout ) return BIBL_ERR_MEMERR; if ( p->typef ) reftype = p->typef( rin, fname, i+1, p, p->all, p->nall ); - ok = p->convertf( rin, rout, reftype, p, p->all, p->nall ); - if ( ok!=BIBL_OK ) return ok; + status = p->convertf( rin, rout, reftype, p, p->all, p->nall ); + if ( status!=BIBL_OK ) return status; if ( p->all ) { - ok = process_alwaysadd( rout, reftype, p ); - if ( ok!=BIBL_OK ) return ok; - ok = process_defaultadd( rout, reftype, p ); - if ( ok!=BIBL_OK ) return ok; + status = process_alwaysadd( rout, reftype, p ); + if ( status!=BIBL_OK ) return status; + status = process_defaultadd( rout, reftype, p ); + if ( status!=BIBL_OK ) return status; } - bibl_addref( bout, rout ); + ok = bibl_addref( bout, rout ); + if ( !ok ) return BIBL_ERR_MEMERR; } - uniqueify_citekeys( bout ); - return BIBL_OK; + status = uniqueify_citekeys( bout ); + return status; } int bibl_read( bibl *b, FILE *fp, char *filename, param *p ) { - int ret, ok; + int ok, status; param lp; bibl bin; - if ( !b ) return BIBL_ERR_BADINPUT; + if ( !b ) return BIBL_ERR_BADINPUT; if ( !fp ) return BIBL_ERR_BADINPUT; - if ( !p ) return BIBL_ERR_BADINPUT; + if ( !p ) return BIBL_ERR_BADINPUT; + if ( bibl_illegalinmode( p->readformat ) ) return BIBL_ERR_BADINPUT; - bibl_setreadparams( &lp, p ); + status = bibl_setreadparams( &lp, p ); + if ( status!=BIBL_OK ) return status; + bibl_init( &bin ); - ret = read_ref( fp, &bin, filename, &lp ); - if ( ret!=BIBL_OK ) return ret; + status = read_ref( fp, &bin, filename, &lp ); + if ( status!=BIBL_OK ) return status; if ( debug_set( p ) ) { fflush( stdout ); @@ -700,8 +850,8 @@ } if ( !lp.output_raw || ( lp.output_raw & BIBL_RAW_WITHCHARCONVERT ) ) { - ok = bibl_fixcharsets( &bin, &lp ); - if ( !ok ) return BIBL_ERR_MEMERR; + status = bibl_fixcharsets( &bin, &lp ); + if ( status!=BIBL_OK ) return status; if ( debug_set( p ) ) { fprintf( stderr, "-------------------post_fixcharsets start for bibl_read\n"); bibl_verbose0( &bin ); @@ -710,7 +860,8 @@ } } if ( !lp.output_raw ) { - clean_ref( &bin, &lp ); + status = clean_ref( &bin, &lp ); + if ( status!=BIBL_OK ) return status; if ( debug_set( p ) ) { fprintf( stderr, "-------------------post_clean_ref start for bibl_read\n"); bibl_verbose0( &bin ); @@ -779,48 +930,53 @@ } static int -output_bibl( FILE *fp, bibl *b, param *p ) +bibl_writeeachfp( FILE *fp, bibl *b, param *p ) { long i; - if ( !p->singlerefperfile && p->headerf ) p->headerf( fp, p ); for ( i=0; inrefs; ++i ) { - if ( p->singlerefperfile ) { - fp = singlerefname( b->ref[i], i, p->writeformat ); - if ( fp ) { - if ( p->headerf ) p->headerf( fp, p ); - } else return BIBL_ERR_CANTOPEN; - } + 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 ); - if ( p->singlerefperfile ) { - if ( p->footerf ) p->footerf( fp ); - fclose( fp ); - } + if ( p->footerf ) p->footerf( fp ); + fclose( fp ); } - if ( !p->singlerefperfile && p->footerf ) p->footerf( fp ); - return 1; + return BIBL_OK; } +static int +bibl_writefp( FILE *fp, bibl *b, param *p ) +{ + long i; + if ( p->headerf ) p->headerf( fp, p ); + for ( i=0; inrefs; ++i ) + p->writef( b->ref[i], fp, p, i ); + if ( p->footerf ) p->footerf( fp ); + return BIBL_OK; +} + int bibl_write( bibl *b, FILE *fp, param *p ) { + int status; param lp; - int ok; if ( !b ) return BIBL_ERR_BADINPUT; if ( !p ) return BIBL_ERR_BADINPUT; if ( bibl_illegaloutmode( p->writeformat ) ) return BIBL_ERR_BADINPUT; if ( !fp && ( !p || !p->singlerefperfile ) ) return BIBL_ERR_BADINPUT; - bibl_setwriteparams( &lp, p ); + status = bibl_setwriteparams( &lp, p ); + if ( status!=BIBL_OK ) return status; - ok = bibl_fixcharsets( b, &lp ); - if ( !ok ) return BIBL_ERR_MEMERR; + status = bibl_fixcharsets( b, &lp ); + if ( status!=BIBL_OK ) return status; if ( debug_set( p ) ) report_params( stderr, "bibl_write", &lp ); - ok = output_bibl( fp, b, &lp ); - if ( !ok ) return BIBL_ERR_MEMERR; + if ( p->singlerefperfile ) status = bibl_writeeachfp( fp, b, &lp ); + else status = bibl_writefp( fp, b, &lp ); - return BIBL_OK; + return status; } 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 2005-2013 + * Copyright (c) Chris Putnam 2005-2014 * * Source code released under the GPL version 2 * @@ -80,19 +80,20 @@ bibl_copy( bibl *bout, bibl *bin ) { fields *refin, *refout; - int i, j, n, ok, level; + int i, j, n, status, ok, level; char *tag, *value; for ( i=0; inrefs; ++i ) { refin = bin->ref[i]; refout = fields_new(); + if ( !refout ) return 0; n = fields_num( refin ); for ( j=0; j -#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" - -static list find = { 0, 0, 0, NULL }; -static list replace = { 0, 0, 0, NULL }; - -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 ); -} - -/* - * 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; -} - -static char * -biblatex_item( char *p, newstr *s ) -{ - int surrounding_quotes = 0; - int nbrackets = 0; - int nquotes = 0; - while ( *p ) { - if ( !nquotes && !nbrackets ) { - if ( *p==',' || *p=='=' || *p=='}' || *p==')' ) - goto out; - } - if ( *p=='\"' && *(p-1)!='\\' && nbrackets==0 ) { - if ( s->len == 0 ) surrounding_quotes = 1; - else { - if ( !surrounding_quotes ) newstr_addchar( s, *p ); - if ( nquotes ) surrounding_quotes = 0; - } - nquotes = ( nquotes==0 ); - } else if ( *p=='{' ) { - if ( nbrackets>0 || nquotes ) newstr_addchar( s, *p ); - nbrackets++; - } else if ( *p=='}' ) { - nbrackets--; - if ( nbrackets>0 || nquotes ) newstr_addchar( s, *p ); - } else { - if ( !is_ws( *p ) ) newstr_addchar( s, *p ); - else { - if ( s->len!=0 && *p!='\n' && *p!='\r' ) - newstr_addchar( s, *p ); - else if ( s->len!=0 && (*p=='\n' || *p=='\r')) { - newstr_addchar( s, ' ' ); - while ( is_ws( *(p+1) ) ) p++; - } - } - } - p++; - } -out: - newstr_trimendingws( s ); - return p; -} - -static char * -process_biblatexline( char *p, newstr *tag, newstr *data ) -{ - p = skip_ws( p ); - p = biblatex_item( p, tag ); - p = skip_ws( p ); - if ( *p=='=' ) { - p++; - p = skip_ws( p ); - p = biblatex_item( p, data ); - p = skip_ws( p ); - } - if ( *p==',' || *p=='}' || *p==')' ) p++; - p = skip_ws( p ); - return p; -} - -static void -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, "\\$", "$" ); - newstr_findreplace( s, "{", "" ); - newstr_findreplace( s, "}", "" ); - while ( newstr_findreplace( s, " ", " " ) ) {} - - /* 'textcomp' annotations that we don't want to substitute on output*/ - newstr_findreplace( s, "\\textdollar", "$" ); - newstr_findreplace( s, "\\textunderscore", "_" ); -} - -static void -biblatex_split( list *tokens, newstr *s ) -{ - int i, n = s->len, nbrackets = 0; - newstr currtok; - - newstr_init( &currtok ); - - for ( i=0; idata[i]=='{' ) { - nbrackets++; - newstr_addchar( &currtok, '{' ); - } else if ( s->data[i]=='}' ) { - nbrackets--; - newstr_addchar( &currtok, '}' ); - } else if ( s->data[i]=='#' && !nbrackets ) { - if ( currtok.len ) list_add( tokens, currtok.data ); - newstr_empty( &currtok ); - } else if ( !is_ws( s->data[i] ) || nbrackets ) { - newstr_addchar( &currtok, s->data[i] ); - } else if ( is_ws( s->data[i] ) ) { - if ( currtok.len ) list_add( tokens, currtok.data ); - newstr_empty( &currtok ); - } - } - if ( currtok.len ) list_add( tokens, currtok.data ); - for ( i=0; in; ++i ) { - newstr_trimstartingws( list_get( tokens, i ) ); - newstr_trimendingws( list_get( tokens, i ) ); - } - newstr_free( &currtok ); -} - -/* get reference type */ -static char* -process_biblatextype( char *p, newstr *data ) -{ - newstr tmp; - newstr_init( &tmp ); - - newstr_empty( data ); - - if ( *p=='@' ) p++; /* skip '@' character */ - while ( *p && *p!='{' && *p!='(' ) newstr_addchar( &tmp, *p++ ); - if ( *p=='{' || *p=='(' ) p++; - p = skip_ws( p ); - - if ( tmp.len ) { - /* add '{' and '}' to protect from string expansion */ - newstr_addchar( data, '{' ); - newstr_strcat( data, tmp.data ); - newstr_addchar( data, '}' ); - } - newstr_free( &tmp ); - return p; -} -/* get reference name */ -static char* -process_biblatexid( char *p, newstr *data ) -{ - newstr tmp; - char *start_p = p; - newstr_init( &tmp ); - newstr_empty( data ); - - while ( *p && *p!=',' ) newstr_addchar( &tmp, *p++ ); - if ( *p==',' ) p++; - p = skip_ws( p ); /* skip ending newline/carriage return */ - - 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; - } else { - /* add '{' and '}' to protect from string expansion */ - newstr_addchar( data, '{' ); - newstr_strcat( data, tmp.data ); - newstr_addchar( data, '}' ); - } - } - - newstr_free( &tmp ); - return p; -} - -static void -process_cite( fields *bibin, char *p, char *filename, long nref ) -{ - newstr tag, data; - newstrs_init( &tag, &data, NULL ); - p = process_biblatextype( p, &data ); - if ( data.len ) fields_add( bibin, "INTERNAL_TYPE", data.data, 0 ); - if ( *p ) p = process_biblatexid ( p, &data ); - if ( data.len ) fields_add( bibin, "REFNUM", data.data, 0 ); - newstr_empty( &data ); - while ( *p ) { - p = process_biblatexline( p, &tag, &data ); - /* no anonymous or empty fields allowed */ - if ( tag.len && data.len ) - fields_add( bibin, tag.data, data.data, 0 ); - newstrs_empty( &tag, &data, NULL ); - } - newstrs_free( &tag, &data, NULL ); -} - -static void -biblatex_addstring( char *p ) -{ - newstr s1, s2; - newstrs_init( &s1, &s2, NULL ); - p = skip_ws( p ); - if ( *p=='(' || *p=='{' ) p++; - p = process_biblatexline( p, &s1, &s2 ); - newstr_findreplace( &s2, "\\ ", " " ); - biblatex_cleantoken( &s2 ); - if ( s1.data ) { - list_add( &find, s1.data ); - if ( s2.data ) list_add( &replace, s2.data ); - else list_add( &replace, "" ); - } - newstrs_free( &s1, &s2, NULL ); -} - -static int -biblatex_usestrings( newstr *s ) -{ - int i; - for ( i=0; idata, (find.str[i]).data ) ) { - newstr_findreplace( s, (find.str[i]).data, - (replace.str[i]).data ); - return 1; - } - } - return 0; -} - -static void -process_string( char *p ) -{ - while ( *p && *p!='{' && *p!='(' ) p++; - biblatex_addstring( p ); -} - -int -biblatexin_processf( fields *bibin, char *data, char *filename, long nref ) -{ - if ( !strncasecmp( data, "@STRING", 7 ) ) { - process_string( data ); - return 0; - } else { - process_cite( bibin, data, filename, nref ); - return 1; - } -} - -static void -biblatex_addtitleurl( fields *info, newstr *in ) -{ - newstr s; - char *p,*q; - newstr_init( &s ); - q = p = in->data + 6; /*skip past \href{ */ - while ( *q && *q!='}' ) q++; - newstr_segcpy( &s, p, q ); - fields_add( info, "URL", s.data, 0 ); - newstr_empty( &s ); - if ( *q=='}' ) q++; - p = q; - while ( *q ) q++; - newstr_segcpy( &s, p, q ); - newstr_swapstrings( &s, in ); - newstr_free( &s ); -} - -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 void -biblatex_cleandata( newstr *tag, newstr *s, fields *info, param *p ) -{ - list tokens; - newstr *tok; - int i; - if ( !s->len ) return; - list_init( &tokens ); - biblatex_split( &tokens, s ); - for ( i=0; ilatexin && !is_name_tag( tag ) ) biblatex_cleantoken( &(tokens.str[i]) ); - } - newstr_empty( s ); - for ( i=0; i0 ) newstr_addchar( s, ' ' ); - newstr_newstrcat( s, tok ); - } - list_free( &tokens ); -} - -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 void -biblatexin_crossref( bibl *bin, param *p ) -{ - char booktitle[] = "booktitle"; - long i, j, ncross; - char *nt, *nd, *type; - int n, ntype, nl; - for ( i=0; inrefs; ++i ) { - n = fields_find( bin->ref[i], "CROSSREF", -1 ); - if ( n==-1 ) continue; - ncross = biblatexin_findref( bin, bin->ref[i]->data[n].data ); - if ( ncross==-1 ) { - biblatexin_nocrossref( bin, i, n, p ); -#if 0 - int n1 = fields_find( bin->ref[i], "REFNUM", -1 ); - fprintf( stderr, "%s: Cannot find cross-reference '%s'", - progname, bin->ref[i]->data[n].data); - if ( n1!=-1 ) - fprintf( stderr, " for reference '%s'\n", - bin->ref[i]->data[n1].data ); - fprintf( stderr, "\n" ); -#endif - continue; - } - ntype = fields_find( bin->ref[i], "INTERNAL_TYPE", -1 ); - type = bin->ref[i]->data[ntype].data; - fields_setused( bin->ref[i], n ); -/* bin->ref[i]->used[n] = 1; */ - for ( j=0; jref[ncross]->n; ++j ) { - nt = bin->ref[ncross]->tag[j].data; - 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 = bin->ref[ncross]->data[j].data; - nl = bin->ref[ncross]->level[j] + 1; - fields_add( bin->ref[i], nt, nd, nl ); - - } - } -} - -static void -biblatexin_cleanref( fields *bibin, param *p ) -{ - newstr *t, *d; - int i, n; - 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", "" ); - } - } -} - -void -biblatexin_cleanf( bibl *bin, param *p ) -{ - long i; - for ( i=0; inrefs; ++i ) - biblatexin_cleanref( bin->ref[i], p ); - biblatexin_crossref( bin, p ); -} - -/* 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 ) -{ - newstr page; - char *p; - int ok; - - newstr_findreplace( s, " ", "" ); - if ( s->len==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 ) { - ok = fields_add( info, "PAGESTART", page.data, level ); - if ( !ok ) return 0; - } - - 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 ) { - ok = fields_add( info, "PAGEEND", page.data, level ); - if ( !ok ) return 0; - } - - newstr_free( &page ); - return 1; -} - -static int -process_urlcore( fields *info, char *p, int level, char *default_tag ) -{ - if ( !strncasecmp( p, "\\urllink", 8 ) ) - return fields_add( info, "URL", p+8, level ); - else if ( !strncasecmp( p, "\\url", 4 ) ) - return fields_add( info, "URL", p+4, level ); - else if ( !strncasecmp( p, "arXiv:", 6 ) ) - return fields_add( info, "ARXIV", p+6, level ); - else if ( !strncasecmp( p, "http://arxiv.org/abs/", 21 ) ) - return fields_add( info, "ARXIV", p+21, level ); - else if ( !strncasecmp( p, "http:", 5 ) ) - return fields_add( info, "URL", p, level ); - else return fields_add( info, default_tag, p, level ); -} - -static int -process_url( fields *info, char *p, int level ) -{ - return process_urlcore( info, p, level, "URL" ); -} - -/* 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 ) -{ - if ( !strncasecmp( p, "Diplom", 6 ) ) - return fields_replace_or_add( info, "NGENRE", "Diploma thesis", level ); - else if ( !strncasecmp( p, "Habilitation", 13 ) ) - return fields_replace_or_add( info, "NGENRE", "Habilitation thesis", level ); - else - return fields_add( info, "PUBLISHER", p, level ); -} - -static int -process_thesistype( fields *info, char *p, int level ) -{ - /* type in the @thesis is used to distinguish Ph.D. and Master's thesis */ - if ( !strncasecmp( p, "phdthesis", 9 ) ) { - return fields_replace_or_add( info, "NGENRE", "Ph.D. thesis", level ); - } else if ( !strncasecmp( p, "mastersthesis", 13 ) || !strncasecmp( p, "masterthesis", 12 ) ) { - return fields_replace_or_add( info, "NGENRE", "Masters thesis", level ); - } else if ( !strncasecmp( p, "mathesis", 8 ) ) { - return fields_replace_or_add( info, "NGENRE", "Masters thesis", level ); - } else if ( !strncasecmp( p, "diploma", 7 ) ) { - return fields_replace_or_add( info, "NGENRE", "Diploma thesis", level ); - } else if ( !strncasecmp( p, "habilitation", 12 ) ) { - return fields_replace_or_add( info, "NGENRE", "Habilitation thesis", level ); - } - return 1; -} - -/* biblatex drops school field if institution is present */ -static int -process_school( fields *bibin, fields *info, char *tag, char *value, int level ) -{ - if ( fields_find( bibin, "institution", LEVEL_ANY ) != -1 ) - return 1; - else - return fields_add( info, tag, value, level ); -} - -/* biblatex drops school field if institution is present */ -static int -process_subtype( fields *bibin, fields *info, char *tag, char *value, int level ) -{ - int ok = 1; - if ( !strcasecmp( value, "magazine" ) ) { - ok = fields_add( info, "NGENRE", "magazine article", LEVEL_MAIN ); - if ( !ok ) return 0; - ok = fields_add( info, "NGENRE", "magazine", LEVEL_HOST ); - } else if ( !strcasecmp( value, "newspaper" ) ) { - ok = fields_add( info, "NGENRE", "newspaper article", LEVEL_MAIN ); - if ( !ok ) return 0; - ok = fields_add( info, "GENRE", "newspaper", LEVEL_HOST ); - } - return ok; -} - -static int -process_eprint( fields *bibin, fields *info, int level ) -{ - int neprint, netype, ok; - 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 ) ) { - ok = fields_add( info, "ARXIV", eprint, level ); - if ( !ok ) return 0; - } else if ( !strncasecmp( etype, "jstor", 5 ) ) { - ok = fields_add( info, "JSTOR", eprint, level ); - if ( !ok ) return 0; - } else if ( !strncasecmp( etype, "pubmed", 6 ) ) { - ok = fields_add( info, "PMID", eprint, level ); - if ( !ok ) return 0; - } else if ( !strncasecmp( etype, "medline", 7 ) ) { - ok = fields_add( info, "MEDLINE", eprint, level ); - if ( !ok ) return 0; - } else { - ok = fields_add( info, "EPRINT", eprint, level ); - if ( !ok ) return 0; - ok = fields_add( info, "EPRINTTYPE", etype, level ); - if ( !ok ) return 0; - } - fields_setused( bibin, neprint ); - fields_setused( bibin, netype ); - } else if ( eprint ) { - ok = fields_add( info, "EPRINT", eprint, level ); - if ( !ok ) return 0; - fields_setused( bibin, neprint ); - } else if ( etype ) { - ok = fields_add( info, "EPRINTTYPE", etype, level ); - if ( !ok ) return 0; - fields_setused( bibin, netype ); - } - return 1; -} - -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; -} - -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 ) -{ - newstr combined; - int ok, ret = 1; - 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 ); - ok = fields_add( info, "TITLE", combined.data, currlevel ); - if ( !ok ) ret = 0; - newstr_free( &combined ); - return ret; -} - -static int -process_separated_title( fields *info, newstr *ttl, newstr *subttl, newstr *ttladdon, int currlevel ) -{ - int ok; - if ( ttladdon->len ) { - if ( subttl->len ) attach_addon( subttl, ttladdon ); - else attach_addon( ttl, ttladdon ); - } - if ( ttl->len ) { - ok = fields_add( info, "TITLE", ttl->data, currlevel ); - if ( !ok ) return 0; - } - if ( subttl->len ) { - ok = fields_add( info, "SUBTITLE", subttl->data, currlevel ); - if ( !ok ) return 0; - } - return 1; -} - -static int -process_title_all( fields *bibin, fields *info, int reftype, param *p, - variants *all, int nall ) -{ - int currlevel, ok, found, ret=1; - newstr ttl, subttl, ttladdon; - newstrs_init( &ttl, &subttl, &ttladdon, NULL ); - for ( currlevel = 0; currlevelnosplittitle ) - ok = process_combined_title( info, &ttl, &subttl, &ttladdon, currlevel ); - else - ok = process_separated_title( info, &ttl, &subttl, &ttladdon, currlevel ); - if ( !ok ) { ret = 0; goto out; } - } -out: - newstrs_free( &ttl, &subttl, &ttladdon, NULL ); - return ret; -} - -static int -biblatex_matches_asis_corps( fields *info, char *tag, newstr *data, int level, - list *asis, list *corps ) -{ - newstr newtag; - int i; - for ( i=0; in; ++i ) { - if ( !strcmp( data->data, list_getc( asis, i ) ) ) { - newstr_initstr( &newtag, tag ); - newstr_strcat( &newtag, ":ASIS" ); - fields_add( info, newtag.data, data->data, level ); - newstr_free( &newtag ); - return 1; - } - } - for ( i=0; in; ++i ) { - if ( !strcmp( data->data, list_getc( corps, i ) ) ) { - newstr_initstr( &newtag, tag ); - newstr_strcat( &newtag, ":CORP" ); - fields_add( info, newtag.data, data->data, level ); - newstr_free( &newtag ); - return 1; - } - } - return 0; -} - -static int -biblatex_names( fields *info, char *tag, newstr *data, int level, list *asis, list *corps ) -{ - int begin, end, ok, n, etal, i, ret = 1; - list tokens; - - /* If we match the asis or corps list add and bail. */ - if ( biblatex_matches_asis_corps( info, tag, data, level, asis, corps ) ) - return 1; - - 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 ); -} - -int -biblatexin_convertf( fields *bibin, fields *info, int reftype, param *p, - variants *all, int nall ) -{ - int process, level, i, n, nfields, 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: - ok = fields_add( info, newtag, d->data, level ); - fields_setused( bibin, i ); - break; - - case PERSON: - ok = biblatex_names( info, newtag, d, level, &(p->asis), &(p->corps) ); - fields_setused( bibin, i ); - break; - - case BLT_EDITOR: - ok = process_editor( bibin, info, t, d, level, &(p->asis), &(p->corps) ); - fields_setused( bibin, i ); - break; - - case PAGES: - ok = process_pages( info, d, level); - fields_setused( bibin, i ); - break; - - case HOWPUBLISHED: - ok = process_howpublished( info, d->data, level ); - fields_setused( bibin, i ); - break; - - case BT_URL: - ok = process_url( info, d->data, level ); - fields_setused( bibin, i ); - break; - - case BT_GENRE: - ok = fields_add( info, "NGENRE", d->data, level ); - fields_setused( bibin, i ); - break; - - case BT_EPRINT: - ok = process_eprint( bibin, info, level ); - fields_setused( bibin, i ); - break; - - case BLT_THESIS_TYPE: - ok = process_thesistype( info, d->data, level ); - fields_setused( bibin, i ); - break; - - case BLT_SCHOOL: - ok = process_school( bibin, info, newtag, d->data, level ); - fields_setused( bibin, i ); - break; - - case BLT_SUBTYPE: - ok = process_subtype( bibin, info, newtag, d->data, level ); - fields_setused( bibin, i ); - break; - - case BLT_SKIP: - ok = 1; - fields_setused( bibin, i ); - break; - - case TITLE: - ok = 1; /* delay title processing until later */ - break; - - default: - ok = 1; - break; - - } - if ( !ok ) return BIBL_ERR_MEMERR; - - } - - ok = process_title_all( bibin, info, reftype, p, all, nall ); - if ( !ok ) return BIBL_ERR_MEMERR; - - if ( p->verbose ) report( info ); - - return BIBL_OK; + * 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 ); + + return status; } diff --git a/bibutils/biblatexin.h b/bibutils/biblatexin.h --- a/bibutils/biblatexin.h +++ b/bibutils/biblatexin.h @@ -1,7 +1,7 @@ /* * biblatexin.h * - * Copyright (c) Chris Putnam 2008-2013 + * Copyright (c) Chris Putnam 2008-2014 * * Source code released under the GPL version 2 * @@ -18,7 +18,7 @@ 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 void biblatexin_cleanf( bibl *bin, param *p ); +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 ); diff --git a/bibutils/bibtexin.c b/bibutils/bibtexin.c --- a/bibutils/bibtexin.c +++ b/bibutils/bibtexin.c @@ -1,1055 +1,1375 @@ /* * bibtexin.c * - * Copyright (c) Chris Putnam 2003-2013 - * - * 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, 0, NULL }; -static list replace = { 0, 0, 0, NULL }; - -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 ); -} - -/* - * 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; -} - -static char * -bibtex_item( char *p, newstr *s ) -{ - int surrounding_quotes = 0; - int nbrackets = 0; - int nquotes = 0; - while ( *p ) { - if ( !nquotes && !nbrackets ) { - if ( *p==',' || *p=='=' || *p=='}' || *p==')' ) - goto out; - } - if ( *p=='\"' && *(p-1)!='\\' && nbrackets==0 ) { - if ( s->len == 0 ) surrounding_quotes = 1; - else { - if ( !surrounding_quotes ) newstr_addchar( s, *p ); - if ( nquotes ) surrounding_quotes = 0; - } - nquotes = ( nquotes==0 ); - } else if ( *p=='{' ) { - if ( nbrackets>0 || nquotes ) newstr_addchar( s, *p ); - nbrackets++; - } else if ( *p=='}' ) { - nbrackets--; - if ( nbrackets>0 || nquotes ) newstr_addchar( s, *p ); - } else { - if ( !is_ws( *p ) ) newstr_addchar( s, *p ); - else { - if ( s->len!=0 && *p!='\n' && *p!='\r' ) - newstr_addchar( s, *p ); - else if ( s->len!=0 && (*p=='\n' || *p=='\r')) { - newstr_addchar( s, ' ' ); - while ( is_ws( *(p+1) ) ) p++; - } - } - } - p++; - } -out: - newstr_trimendingws( s ); - return p; -} - -static char * -process_bibtexline( char *p, newstr *tag, newstr *data ) -{ - p = skip_ws( p ); - p = bibtex_item( p, tag ); - p = skip_ws( p ); - if ( *p=='=' ) { - p++; - p = skip_ws( p ); - p = bibtex_item( p, data ); - p = skip_ws( p ); - } - if ( *p==',' || *p=='}' || *p==')' ) p++; - p = skip_ws( p ); - return p; -} - -static void -bibtex_process_tilde( newstr *s ) -{ - char *p, *q; - int n = 0; - - p = q = s->data; - 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_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, "\\$", "$" ); - newstr_findreplace( s, "{", "" ); - newstr_findreplace( s, "}", "" ); - while ( newstr_findreplace( s, " ", " " ) ) {} - - /* 'textcomp' annotations that we don't want to substitute on output*/ - newstr_findreplace( s, "\\textdollar", "$" ); - newstr_findreplace( s, "\\textunderscore", "_" ); - - bibtex_process_tilde( s ); - -} - -static void -bibtex_addstring( char *p ) -{ - newstr s1, s2; - newstrs_init( &s1, &s2, NULL ); - p = skip_ws( p ); - if ( *p=='(' || *p=='{' ) p++; - p = process_bibtexline( p, &s1, &s2 ); - newstr_findreplace( &s2, "\\ ", " " ); - bibtex_cleantoken( &s2 ); - if ( s1.data ) { - list_add( &find, s1.data ); - if ( s2.data ) list_add( &replace, s2.data ); - else list_add( &replace, "" ); - } - newstrs_free( &s1, &s2, NULL ); -} - -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 void -bibtex_split( list *tokens, newstr *s ) -{ - int i, n = s->len, nbrackets = 0; - newstr currtok; - - newstr_init( &currtok ); - - for ( i=0; idata[i]=='{' ) { - nbrackets++; - newstr_addchar( &currtok, '{' ); - } else if ( s->data[i]=='}' ) { - nbrackets--; - newstr_addchar( &currtok, '}' ); - } else if ( s->data[i]=='#' && !nbrackets ) { - if ( currtok.len ) list_add( tokens, currtok.data ); - newstr_empty( &currtok ); - } else if ( !is_ws( s->data[i] ) || nbrackets ) { - newstr_addchar( &currtok, s->data[i] ); - } else if ( is_ws( s->data[i] ) ) { - if ( currtok.len ) list_add( tokens, currtok.data ); - newstr_empty( &currtok ); - } - } - if ( currtok.len ) list_add( tokens, currtok.data ); - for ( i=0; in; ++i ) { - newstr_trimstartingws( list_get( tokens, i ) ); - newstr_trimendingws( list_get( tokens, i ) ); - } - newstr_free( &currtok ); -} - -static int -bibtex_usestrings( newstr *s ) -{ - char *p; - int i; - for ( i=0; idata, p ) ) { - newstr_findreplace( s, p, list_getc( &replace, i ) ); - return 1; - } - } - return 0; -} - -/* get reference type */ -static char* -process_bibtextype( char *p, newstr *data ) -{ - newstr tmp; - newstr_init( &tmp ); - - newstr_empty( data ); - - if ( *p=='@' ) p++; /* skip '@' character */ - while ( *p && *p!='{' && *p!='(' && !is_ws( *p ) ) newstr_addchar( &tmp, *p++ ); - p = skip_ws( p ); - if ( *p=='{' || *p=='(' ) p++; - p = skip_ws( p ); - - if ( tmp.len ) { - /* add '{' and '}' to protect from string expansion */ - newstr_addchar( data, '{' ); - newstr_strcat( data, tmp.data ); - newstr_addchar( data, '}' ); - } - newstr_free( &tmp ); - return p; -} -/* get reference name */ -static char* -process_bibtexid( char *p, newstr *data ) -{ - newstr tmp; - char *start_p = p; - newstr_init( &tmp ); - newstr_empty( data ); - - while ( *p && *p!=',' ) newstr_addchar( &tmp, *p++ ); - if ( *p==',' ) p++; - p = skip_ws( p ); /* skip ending newline/carriage return */ - - 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; - } else { - /* add '{' and '}' to protect from string expansion */ - newstr_addchar( data, '{' ); - newstr_strcat( data, tmp.data ); - newstr_addchar( data, '}' ); - } - } - - newstr_free( &tmp ); - return p; -} - -static void -process_cite( fields *bibin, char *p, char *filename, long nref ) -{ - newstr tag, data; - newstrs_init( &tag, &data, NULL ); - p = process_bibtextype( p, &data ); - if ( data.len ) fields_add( bibin, "INTERNAL_TYPE", data.data, 0 ); - if ( *p ) p = process_bibtexid ( p, &data ); - if ( data.len ) fields_add( bibin, "REFNUM", data.data, 0 ); - newstr_empty( &data ); - while ( *p ) { - p = process_bibtexline( p, &tag, &data ); - /* no anonymous or empty fields allowed */ - if ( tag.len && data.len ) - fields_add( bibin, tag.data, data.data, 0 ); - newstrs_empty( &tag, &data, NULL ); - } - newstrs_free( &tag, &data, NULL ); -} - -static void -process_string( char *p ) -{ - while ( *p && *p!='{' && *p!='(' ) p++; - bibtex_addstring( p ); -} - -int -bibtexin_processf( fields *bibin, char *data, char *filename, long nref ) -{ - if ( !strncasecmp( data, "@STRING", 7 ) ) { - process_string( data ); - 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; - } -} - -static void -bibtex_addtitleurl( fields *info, newstr *in ) -{ - newstr s; - char *p,*q; - newstr_init( &s ); - q = p = in->data + 6; /*skip past \href{ */ - while ( *q && *q!='}' ) q++; - newstr_segcpy( &s, p, q ); - fields_add( info, "URL", s.data, 0 ); - newstr_empty( &s ); - if ( *q=='}' ) q++; - p = q; - while ( *q ) q++; - newstr_segcpy( &s, p, q ); - newstr_swapstrings( &s, in ); - newstr_free( &s ); -} - -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_cleandata( newstr *tag, newstr *s, fields *info, param *p ) -{ - list tokens; - newstr *tok; - int i; - if ( !s->len ) return; - list_init( &tokens ); - bibtex_split( &tokens, s ); - 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 ); - } - list_free( &tokens ); -} - -static long -bibtexin_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 -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 void -bibtexin_crossref( bibl *bin, param *p ) -{ - char booktitle[] = "booktitle"; - long i, j, ncross; - char *nt, *nd, *type; - int n, ntype, nl; - for ( i=0; inrefs; ++i ) { - n = fields_find( bin->ref[i], "CROSSREF", -1 ); - if ( n==-1 ) continue; - ncross = bibtexin_findref( bin, bin->ref[i]->data[n].data ); - if ( ncross==-1 ) { - bibtexin_nocrossref( bin, i, n, p ); - continue; - } - ntype = fields_find( bin->ref[i], "INTERNAL_TYPE", -1 ); - type = bin->ref[i]->data[ntype].data; - fields_setused( bin->ref[i], n ); - for ( j=0; jref[ncross]->n; ++j ) { - nt = bin->ref[ncross]->tag[j].data; - 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 = bin->ref[ncross]->data[j].data; - nl = bin->ref[ncross]->level[j] + 1; - fields_add( bin->ref[i], nt, nd, nl ); - - } - } -} - -static void -bibtexin_cleanref( fields *bibin, param *p ) -{ - newstr *t, *d; - int i, n; - n = fields_num( bibin ); - for ( i=0; inrefs; ++i ) - bibtexin_cleanref( bin->ref[i], p ); - bibtexin_crossref( bin, p ); -} - -static int -bibtex_matches_asis_corps( fields *info, char *tag, newstr *data, int level, - list *asis, list *corps ) -{ - newstr newtag; - int i; - for ( i=0; in; ++i ) { - if ( !strcmp( data->data, list_getc( asis, i ) ) ) { - newstr_initstr( &newtag, tag ); - newstr_strcat( &newtag, ":ASIS" ); - fields_add( info, newtag.data, data->data, level ); - newstr_free( &newtag ); - return 1; - } - } - for ( i=0; in; ++i ) { - if ( !strcmp( data->data, list_getc( corps, i ) ) ) { - newstr_initstr( &newtag, tag ); - newstr_strcat( &newtag, ":CORP" ); - fields_add( info, newtag.data, data->data, level ); - newstr_free( &newtag ); - return 1; - } - } - return 0; -} - -/* - * bibtex_names( info, newtag, field, level); - * - * split names in author list separated by and's (use '|' character) - * and add names - */ -static int -bibtex_names( fields *info, char *tag, newstr *data, int level, list *asis, - list *corps ) -{ - int begin, end, ok, n, etal, i, ret = 1; - list tokens; - - /* If we match the asis or corps list add and bail. */ - if ( bibtex_matches_asis_corps( info, tag, data, level, asis, corps ) ) - return 1; - - 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 ) { - ok = fields_add( info, "PAGESTART", page.data, level ); - if ( !ok ) return 0; - } - - 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 ) { - ok = fields_add( info, "PAGEEND", page.data, level ); - if ( !ok ) return 0; - } - - newstr_free( &page ); - return 1; -} - -static int -process_urlcore( fields *info, newstr *d, int level, char *default_tag ) -{ - char *p = d->data; - if ( !strncasecmp( p, "\\urllink", 8 ) ) - return fields_add( info, "URL", p+8, level ); - else if ( !strncasecmp( p, "\\url", 4 ) ) - return fields_add( info, "URL", p+4, level ); - else if ( !strncasecmp( p, "arXiv:", 6 ) ) - return fields_add( info, "ARXIV", p+6, level ); - else if ( !strncasecmp( p, "http://arxiv.org/abs/", 21 ) ) - return fields_add( info, "ARXIV", p+21, level ); - else if ( !strncasecmp( p, "http:", 5 ) ) - return fields_add( info, "URL", p, level ); - else return fields_add( info, default_tag, p, level ); -} - -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" - */ -static int -process_keywords( fields *info, newstr *d, int level ) -{ - newstr keyword; - char *p; - int ok; - - if ( !d || d->len==0 ) return 1; - - p = d->data; - newstr_init( &keyword ); - - while ( *p ) { - p = skip_ws( p ); - while ( *p && *p!=';' ) newstr_addchar( &keyword, *p++ ); - newstr_trimendingws( &keyword ); - if ( keyword.len ) { - ok = fields_add( info, "KEYWORD", keyword.data, level ); - if ( !ok ) return 0; - newstr_empty( &keyword ); - } - if ( *p==';' ) p++; - } - newstr_free( &keyword ); - return 1; -} - -/* 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. - */ -static int -process_howpublished( fields *info, newstr *d, int level ) -{ - char *p = d->data; - if ( !strncasecmp( p, "Diplom", 6 ) ) - return fields_replace_or_add( info, "GENRE", "Diploma thesis", level ); - else if ( !strncasecmp( p, "Habilitation", 13 ) ) - return fields_replace_or_add( info, "GENRE", "Habilitation thesis", level ); - else if ( !strncasecmp( d->data, "http:", 5 ) ) - return process_url( info, d, level ); - else if ( !strncasecmp( d->data, "arXiv:", 6 ) ) - return process_url( info, d, level ); - else - return fields_add( info, "PUBLISHER", p, level ); -} - -/* - * sentelink = {file://localhost/full/path/to/file.pdf,Sente,PDF} - */ -static int -process_sente( fields *info, newstr *d, int level ) -{ - int ret = 1; - newstr link; - char *p = d->data; - newstr_init( &link ); - while ( *p && *p!=',' ) newstr_addchar( &link, *p++ ); - newstr_trimstartingws( &link ); - newstr_trimendingws( &link ); - if ( link.len ) ret = fields_add( info, "FILEATTACH", link.data, level ); - newstr_free( &link ); - return ret; -} - -/* - * 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; - n = fields_find( bibin, "publisher", LEVEL_ANY ); - if ( n==-1 ) - return fields_add( info, "PUBLISHER", d->data, level ); - else - return fields_add( info, "ORGANIZER:CORP", d->data, level ); -} - -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 ) -{ - char *p = d->data; - newstr link; - int i, n, n1, n2, ret = 1; - - 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 ) ) { - return process_url( info, d, level ); - } else { - return fields_add( info, "NOTES", d->data, level ); - } -} - -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; -} - -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; - if ( bibtexin_titleinbook_isbooktitle( intag, bibin ) ) level=LEVEL_MAIN; - title_process( info, outtag, indata, level, nosplittitle ); - return 1; -} -static int -bibtex_simple( fields *info, char *outtag, newstr *d, int level ) -{ - return fields_add( info, outtag, d->data, level ); -} - -int -bibtexin_convertf( fields *bibin, fields *info, int reftype, param *p, - variants *all, int nall ) -{ - int process, level, i, n, nfields, ok; - 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: - ok = bibtex_simple( info, outtag, d, level ); - break; - - case TITLE: - ok = bibtexin_title_process( info, "TITLE", bibin, t, d, level, p->nosplittitle ); - break; - - case PERSON: - ok = bibtex_names( info, outtag, d, level, &(p->asis), &(p->corps) ); - break; - - case PAGES: - ok = process_pages( info, d, level ); - break; - - case KEYWORD: - ok = process_keywords( info, d, level ); - break; - - case HOWPUBLISHED: - ok = process_howpublished( info, d, level ); - break; - - case LINKEDFILE: - ok = process_file( info, d, level ); - break; - - case BT_NOTE: - ok = process_note( info, d, level ); - break; - - case BT_SENTE: - ok = process_sente( info, d, level ); - break; - - case BT_URL: - ok = process_url( info, d, level ); - break; - - case BT_ORG: - ok = process_organization( bibin, info, d, level ); - break; - - default: - ok = 1; - break; - } - - if ( !ok ) return BIBL_ERR_MEMERR; - } - return BIBL_OK; + * 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; } diff --git a/bibutils/bibtexin.h b/bibutils/bibtexin.h --- a/bibutils/bibtexin.h +++ b/bibutils/bibtexin.h @@ -1,7 +1,7 @@ /* * bibtexin.h * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2014 * * Source code released under the GPL version 2 * @@ -18,7 +18,7 @@ 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 void bibtexin_cleanf( bibl *bin, param *p ); +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 ); 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 2003-2013 + * Copyright (c) Chris Putnam 2003-2014 * * Program and source code released under the GPL version 2 * @@ -30,7 +30,7 @@ p->latexout = 1; p->utf8out = BIBL_CHARSET_UTF8_DEFAULT; p->utf8bom = BIBL_CHARSET_BOM_DEFAULT; - p->xmlout = 0; + p->xmlout = BIBL_XMLOUT_FALSE; p->nosplittitle = 0; p->verbose = 0; p->addcount = 0; diff --git a/bibutils/bibtextypes.c b/bibutils/bibtextypes.c --- a/bibutils/bibtextypes.c +++ b/bibutils/bibtextypes.c @@ -664,6 +664,7 @@ REFTYPE( "manual", manual ), REFTYPE( "mastersthesis", masters ), REFTYPE( "misc", misc ), + REFTYPE( "online", misc ), REFTYPE( "patent", patent ), REFTYPE( "phdthesis", phds ), REFTYPE( "periodical", periodical ), 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 2005-2013 + * Copyright (c) Chris Putnam 2005-2014 * * Source code released under GPL version 2 * @@ -17,6 +17,7 @@ #include "bibl.h" #include "list.h" #include "charsets.h" +#include "newstr_conv.h" #define BIBL_OK (0) #define BIBL_ERR_BADINPUT (-1) @@ -63,6 +64,10 @@ #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 + typedef unsigned char uchar; typedef struct param { @@ -98,7 +103,7 @@ int (*readf)(FILE*,char*,int,int*,newstr*,newstr*,int*); int (*processf)(fields*,char*,char*,long); - void (*cleanf)(bibl*,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); void (*headerf)(FILE*,struct param*); @@ -113,12 +118,12 @@ extern void bibl_initparams( param *p, int readmode, int writemode, char *progname ); extern void bibl_freeparams( param *p ); -extern void bibl_readasis( param *p, char *filename ); -extern void bibl_addtoasis( param *p, char *entry ); -extern void bibl_readcorps( param *p, char *filename ); -extern void bibl_addtocorps( param *p, char *entry ); -extern int bibl_read( bibl *b, FILE *fp, char *filename, param *p ); -extern int bibl_write( bibl *b, FILE *fp, param *p ); +extern int bibl_readasis( param *p, char *filename ); +extern int bibl_addtoasis( param *p, char *entry ); +extern int bibl_readcorps( param *p, char *filename ); +extern int bibl_addtocorps( param *p, char *entry ); +extern int bibl_read( bibl *b, FILE *fp, char *filename, param *p ); +extern int bibl_write( bibl *b, FILE *fp, param *p ); extern void bibl_reporterr( int err ); #ifdef __cplusplus diff --git a/bibutils/bltypes.c b/bibutils/bltypes.c --- a/bibutils/bltypes.c +++ b/bibutils/bltypes.c @@ -18,1038 +18,1044 @@ * Article in a journal, newspaper, other periodical */ static lookups article[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editortype", "", BLT_SKIP, LEVEL_MAIN }, - { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, - { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, - { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, - { "redactor", "REDACTOR", PERSON, LEVEL_MAIN }, - { "annotator", "ANNOTATOR", PERSON, LEVEL_MAIN }, - { "commentator", "COMMENTATOR", PERSON, LEVEL_MAIN }, - { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, - { "shorttitle", "SHORTITLE", SIMPLE, LEVEL_MAIN }, - { "journal", "TITLE", TITLE, LEVEL_HOST }, - { "journaltitle", "TITLE", TITLE, LEVEL_HOST }, - { "journalsubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, - { "shortjournal", "SHORTTITLE", SIMPLE, LEVEL_HOST }, - { "issuetitle", "TITLE", TITLE, LEVEL_SERIES }, /*WRONG*/ - { "issuesubtitle", "SUBTITLE", TITLE, LEVEL_SERIES }, /*WRONG*/ - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, - { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, - { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, - { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, - { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, - { "series", "PARTTITLE", SIMPLE, LEVEL_HOST }, - { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, - { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "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 }, - { "pages", "PAGES", PAGES, LEVEL_MAIN }, - { "version", "EDITION", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "issn", "ISSN", 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "entrysubtype", "", BLT_SUBTYPE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|ARTICLE", ALWAYS, LEVEL_MAIN }, - { "", "ISSUANCE|continuing", ALWAYS, LEVEL_HOST }, - { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { "", "NGENRE|journal article", DEFAULT, LEVEL_MAIN }, - { "", "GENRE|periodical", DEFAULT, LEVEL_HOST } -}; - -/* Book */ - -static lookups book[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editortype", "", BLT_SKIP, LEVEL_MAIN }, - { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, - { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, - { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, - { "redactor", "REDACTOR", PERSON, LEVEL_MAIN }, - { "annotator", "ANNOTATOR", PERSON, LEVEL_MAIN }, - { "commentator", "COMMENTATOR", PERSON, LEVEL_MAIN }, - { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, - { "introduction", "INTROAUTHOR", PERSON, LEVEL_MAIN }, - { "foreword", "INTROAUTHOR", PERSON, LEVEL_MAIN }, - { "afterword", "AFTERAUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, - { "shorttitle", "SHORTITLE", SIMPLE, LEVEL_MAIN }, - { "maintitle", "TITLE", TITLE, LEVEL_HOST }, - { "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 }, - { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ - { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, - { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, - { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, - { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, - { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, - { "volume", "VOLUME", SIMPLE, LEVEL_HOST }, - { "part", "PART", SIMPLE, LEVEL_HOST }, - { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, - { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, - { "series", "TITLE", SIMPLE, LEVEL_HOST }, /* WRONG */ - { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, - { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, - { "pages", "?pages?", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "pagetotal", "?pagetotal?", 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|BOOK", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { "", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|book", ALWAYS, LEVEL_MAIN } -}; - -/* Booklet */ - -static lookups booklet[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editortype", "", BLT_SKIP, LEVEL_MAIN }, - { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, - { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, - { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, - { "shorttitle", "SHORTITLE", SIMPLE, LEVEL_MAIN }, - { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "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 }, - { "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?", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "pagetotal", "?pagetotal?", 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|BOOK", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text",ALWAYS, LEVEL_MAIN }, - { "", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|book", ALWAYS, LEVEL_MAIN } -}; - -static lookups collection[] = { - { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editortype", "", BLT_SKIP, LEVEL_MAIN }, - { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, - { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, - { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, - { "redactor", "REDACTOR", PERSON, LEVEL_MAIN }, - { "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 }, - { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ - { "introduction", "INTROAUTHOR", PERSON, LEVEL_MAIN }, - { "foreword", "INTROAUTHOR", PERSON, LEVEL_MAIN }, - { "afterword", "AFTERAUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, - { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, - { "maintitle", "TITLE", TITLE, LEVEL_HOST }, - { "mainsubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, - { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, - { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, - { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, - { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, - { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, - { "volume", "VOLUME", SIMPLE, LEVEL_HOST }, - { "part", "PART", SIMPLE, LEVEL_HOST }, - { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, - { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, - { "series", "?series?", SIMPLE, LEVEL_HOST }, /* WRONG */ - { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, - { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, - { "pages", "?pages?", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "pagetotal", "?pagetotal?", 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|BOOK", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text",ALWAYS, LEVEL_MAIN }, - { "", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|book", ALWAYS, LEVEL_MAIN } -}; - -/* Part of a book (e.g. chapter or section) */ - -static lookups inbook[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "editor", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editortype", "", BLT_SKIP, LEVEL_HOST }, - { "editoratype", "", BLT_SKIP, LEVEL_HOST }, - { "editorbtype", "", BLT_SKIP, LEVEL_HOST }, - { "editorctype", "", BLT_SKIP, LEVEL_HOST }, - { "director", "DIRECTOR", PERSON, LEVEL_HOST }, - { "producer", "PRODUCER", PERSON, LEVEL_HOST }, - { "execproducer", "PRODUCER", PERSON, LEVEL_HOST }, - { "writer", "AUTHOR", PERSON, LEVEL_HOST }, - { "redactor", "REDACTOR", PERSON, LEVEL_HOST }, - { "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 }, - { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ - { "introduction", "INTROAUTHOR", PERSON, LEVEL_HOST }, - { "foreword", "INTROAUTHOR", PERSON, LEVEL_HOST }, - { "afterword", "AFTERAUTHOR", PERSON, LEVEL_HOST }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, - { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, - { "booktitle", "TITLE", TITLE, LEVEL_HOST }, - { "booksubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, - { "booktitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, - { "bookauthor", "AUTHOR", PERSON, LEVEL_HOST }, - { "maintitle", "TITLE", TITLE, LEVEL_SERIES }, - { "mainsubtitle", "SUBTITLE", TITLE, LEVEL_SERIES }, - { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_SERIES }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, - { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, - { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, - { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, - { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, - { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, - { "pages", "PAGES", PAGES, LEVEL_MAIN }, - { "part", "PART", SIMPLE, LEVEL_HOST }, - { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, - { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, - { "series", "TITLE", SIMPLE, LEVEL_SERIES+1 }, /* WRONG */ - { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "isbn", "ISBN", SIMPLE, LEVEL_HOST }, - { "chapter", "CHAPTER", 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, 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 } -}; - -/* incollection */ - -static lookups incollection[] = { - - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "year", "YEAR", SIMPLE, LEVEL_MAIN }, - { "month", "MONTH", SIMPLE, LEVEL_MAIN }, - { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, - { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, - { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "introduction", "INTROAUTHOR", PERSON, LEVEL_HOST }, - { "foreword", "INTROAUTHOR", PERSON, LEVEL_HOST }, - { "afterword", "AFTERAUTHOR", PERSON, LEVEL_HOST }, - { "bookauthor", "AUTHOR", PERSON, LEVEL_HOST }, - { "booktitle", "TITLE", TITLE, LEVEL_HOST }, - { "booksubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, - { "booktitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, - { "editor", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editortype", "", BLT_SKIP, LEVEL_HOST }, - { "editoratype", "", BLT_SKIP, LEVEL_HOST }, - { "editorbtype", "", BLT_SKIP, LEVEL_HOST }, - { "editorctype", "", BLT_SKIP, LEVEL_HOST }, - { "director", "DIRECTOR", PERSON, LEVEL_HOST }, - { "producer", "PRODUCER", PERSON, LEVEL_HOST }, - { "execproducer", "PRODUCER", PERSON, LEVEL_HOST }, - { "writer", "AUTHOR", PERSON, LEVEL_HOST }, - { "redactor", "REDACTOR", PERSON, LEVEL_HOST }, - { "annotator", "ANNOTATOR", PERSON, LEVEL_HOST }, - { "commentator", "COMMENTATOR", PERSON, LEVEL_HOST }, - { "translator", "TRANSLATOR", PERSON, LEVEL_HOST }, - { "volume", "VOLUME", SIMPLE, LEVEL_HOST }, - { "part", "PART", SIMPLE, LEVEL_HOST }, - { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, - - { "maintitle", "TITLE", TITLE, LEVEL_SERIES }, - { "mainsubtitle", "SUBTITLE", TITLE, LEVEL_SERIES }, - { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_SERIES }, - - { "series", "TITLE", SIMPLE, LEVEL_SERIES+1 }, /* WRONG */ - - { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, - { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, - { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, - { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, - { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, - - { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, - { "location", "ADDRESS", SIMPLE, LEVEL_HOST }, - { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, - { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, - { "pages", "PAGES", PAGES, LEVEL_MAIN }, /* WRONG */ - { "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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|INCOLLECTION", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text",ALWAYS, LEVEL_MAIN }, - { "", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|collection", ALWAYS, LEVEL_HOST } -}; - -/* inproceedings */ - -static lookups inproceedings[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "editor", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_HOST }, - { "editortype", "", BLT_SKIP, LEVEL_HOST }, - { "editoratype", "", BLT_SKIP, LEVEL_HOST }, - { "editorbtype", "", BLT_SKIP, LEVEL_HOST }, - { "editorctype", "", BLT_SKIP, LEVEL_HOST }, - { "director", "DIRECTOR", PERSON, LEVEL_HOST }, - { "producer", "PRODUCER", PERSON, LEVEL_HOST }, - { "execproducer", "PRODUCER", PERSON, LEVEL_HOST }, - { "writer", "AUTHOR", PERSON, LEVEL_HOST }, - { "redactor", "REDACTOR", PERSON, LEVEL_HOST }, - { "annotator", "ANNOTATOR", PERSON, LEVEL_HOST }, - { "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 }, - { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ - { "introduction", "INTROAUTHOR", PERSON, LEVEL_HOST }, - { "foreword", "INTROAUTHOR", PERSON, LEVEL_HOST }, - { "afterword", "AFTERAUTHOR", PERSON, LEVEL_HOST }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, - { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, - - { "booktitle", "TITLE", TITLE, LEVEL_HOST }, - { "booksubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, - { "booktitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, - - { "maintitle", "TITLE", TITLE, LEVEL_SERIES }, - { "mainsubtitle", "SUBTITLE", TITLE, LEVEL_SERIES }, - { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_SERIES }, - - { "series", "TITLE", SIMPLE, LEVEL_HOST+2 }, - - { "venue", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, - { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, - { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, - { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, - { "volume", "VOLUME", SIMPLE, LEVEL_HOST }, - { "part", "PART", SIMPLE, LEVEL_HOST }, - { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, - { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, - { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, - { "location", "ADDRESS", SIMPLE, LEVEL_HOST }, - { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, - { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, - { "pages", "PAGES", PAGES, LEVEL_MAIN }, /* WRONG */ - { "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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|INPROCEEDINGS", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text",ALWAYS, LEVEL_MAIN }, - { "", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|conference publication", ALWAYS, LEVEL_HOST } -}; - -static lookups manual[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editortype", "", BLT_SKIP, LEVEL_MAIN }, - { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, - { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, - { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, - { "redactor", "REDACTOR", PERSON, LEVEL_MAIN }, - { "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 }, - { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ - { "introduction", "INTROAUTHOR", PERSON, LEVEL_MAIN }, - { "foreword", "INTROAUTHOR", PERSON, LEVEL_MAIN }, - { "afterword", "AFTERAUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, - { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, - { "version", "EDITION", SIMPLE, LEVEL_MAIN }, - { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, - { "series", "TITLE", SIMPLE, LEVEL_HOST }, - { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, - { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, - { "pages", "?????????", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "pagetotal", "?????????", 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|REPORT", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|instruction", ALWAYS, LEVEL_MAIN } -}; - -static lookups misc[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editortype", "", BLT_SKIP, LEVEL_MAIN }, - { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, - { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, - { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "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 }, - { "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 }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "organization", "ORGANIZER:CORP",SIMPLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|MISC", ALWAYS, LEVEL_MAIN }, -}; - -static lookups online[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editortype", "", BLT_SKIP, LEVEL_MAIN }, - { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, - { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, - { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "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 }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "version", "EDITION", SIMPLE, LEVEL_MAIN }, - { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "location", "ADDRESS", 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "RESOURCE|software, multimedia", ALWAYS, LEVEL_MAIN }, - { "", "NGENRE|web page", ALWAYS, LEVEL_MAIN }, -}; - -static lookups patent[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "holder", "ASSIGNEE", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "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 }, - { "version", "EDITION", SIMPLE, LEVEL_MAIN }, - { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|PATENT", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|patent", ALWAYS, LEVEL_MAIN }, -}; - -/* - * An entire issue of a periodical - * - * "The title of the periodical is given in the title field. If the issue has - * its own title in addition to the main title of the periodical, it goes in - * the issuetitle field. The editor is omissible..." - */ -static lookups periodical[] = { - { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editortype", "", BLT_SKIP, LEVEL_MAIN }, - { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, - { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, - { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_HOST }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_HOST }, - { "titleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, - { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_HOST }, - { "issuetitle", "TITLE", TITLE, LEVEL_MAIN }, - { "issuesubtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "issuetitleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, - { "series", "TITLE", SIMPLE, LEVEL_SERIES }, - { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, - { "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 }, - { "pages", "PAGES", PAGES, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "issn", "ISSN", 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?????", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "urlmonth", "?????", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "urlyear", "?????", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "ISSUANCE|continuing", ALWAYS, LEVEL_HOST }, - { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|issue", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|periodical", ALWAYS, LEVEL_HOST } -}; - -static lookups proceedings[] = { - { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, - { "editortype", "", BLT_SKIP, LEVEL_MAIN }, - { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, - { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, - { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, - { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, - { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, - { "redactor", "REDACTOR", PERSON, LEVEL_MAIN }, - { "annotator", "ANNOTATOR", PERSON, LEVEL_MAIN }, - { "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 }, - { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ - { "introduction", "INTROAUTHOR", PERSON, LEVEL_MAIN }, - { "foreword", "INTROAUTHOR", PERSON, LEVEL_MAIN }, - { "afterword", "AFTERAUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, - { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, - { "maintitle", "TITLE", TITLE, LEVEL_HOST }, - { "mainsubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, - { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, - { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, - { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, - { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, - { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, - { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, - { "volume", "VOLUME", SIMPLE, LEVEL_HOST }, - { "part", "PART", SIMPLE, LEVEL_HOST }, - { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, - { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, - { "series", "?????", SIMPLE, LEVEL_HOST }, /* WRONG */ - { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "organization", "ORGANIZER:CORP",SIMPLE, LEVEL_MAIN }, - { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, - { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, - { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, - { "pages", "?????????", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "pagetotal", "?????????", 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|BOOK", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|conference publication", ALWAYS, LEVEL_MAIN } -}; - -/* Technical reports */ -static lookups report[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, - { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, - { "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 }, - { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ - { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, - { "number", "REPORTNUMBER", SIMPLE, LEVEL_MAIN }, - { "note", "NOTES", SIMPLE, LEVEL_MAIN }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "version", "EDITION", SIMPLE, LEVEL_MAIN }, - { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "isrn", "ISRN", SIMPLE, LEVEL_MAIN }, - { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, - { "pages", "?????????", SIMPLE, LEVEL_MAIN }, /* WRONG */ - { "pagetotal", "?????????", 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 }, - { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, - { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, - { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|REPORT", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|report", ALWAYS, LEVEL_MAIN } -}; - -/* Unpublished */ -static lookups unpublished[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, - { "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 }, - { "date", "DATE", SIMPLE, LEVEL_MAIN }, - { "url", "", BT_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 }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|BOOK", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text",ALWAYS, LEVEL_MAIN }, - { "", "GENRE|unpublished",ALWAYS, LEVEL_MAIN } -}; - -static lookups thesis[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "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 }, - { "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 }, - { "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 }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|THESIS", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|thesis", ALWAYS, LEVEL_MAIN }, -}; - -static lookups phdthesis[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "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 }, - { "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 }, - { "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 }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|THESIS", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|thesis", ALWAYS, LEVEL_MAIN }, - { "", "NGENRE|Ph.D. thesis", DEFAULT, LEVEL_MAIN }, -}; - -static lookups mastersthesis[] = { - { "author", "AUTHOR", PERSON, LEVEL_MAIN }, - { "title", "TITLE", TITLE, LEVEL_MAIN }, - { "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 }, - { "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 }, - { "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 }, - { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, - { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, - { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, - { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, - { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, - { "", "INTERNAL_TYPE|THESIS", ALWAYS, LEVEL_MAIN }, - { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, - { "", "GENRE|thesis", ALWAYS, LEVEL_MAIN }, - { "", "NGENRE|Masters thesis", DEFAULT, LEVEL_MAIN }, -}; - -#define ORIG(a) ( &(a[0]) ) -#define SIZE(a) ( sizeof( a ) / sizeof( lookups ) ) -#define REFTYPE(a,b) { a, ORIG(b), SIZE(b) } - -variants biblatex_all[] = { - REFTYPE( "article", article ), - REFTYPE( "booklet", booklet ), - REFTYPE( "book", book ), - REFTYPE( "collection", collection ), - REFTYPE( "inbook", inbook ), - REFTYPE( "incollection", incollection ), - REFTYPE( "inproceedings", inproceedings ), - REFTYPE( "conference", inproceedings ), /* legacy */ - REFTYPE( "manual", manual ), - REFTYPE( "misc", misc ), - REFTYPE( "online", online ), - REFTYPE( "electronic", online ), /* legacy */ - REFTYPE( "www", online ), /* jurabib compatibility */ - REFTYPE( "patent", patent ), - REFTYPE( "periodical", periodical ), - REFTYPE( "proceedings", proceedings ), + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editortype", "", BLT_SKIP, LEVEL_MAIN }, + { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, + { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, + { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, + { "redactor", "REDACTOR", PERSON, LEVEL_MAIN }, + { "annotator", "ANNOTATOR", PERSON, LEVEL_MAIN }, + { "commentator", "COMMENTATOR", PERSON, LEVEL_MAIN }, + { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, + { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, + { "journal", "TITLE", TITLE, LEVEL_HOST }, + { "journaltitle", "TITLE", TITLE, LEVEL_HOST }, + { "journalsubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, + { "shortjournal", "SHORTTITLE", SIMPLE, LEVEL_HOST }, + { "issuetitle", "TITLE", TITLE, LEVEL_SERIES }, /*WRONG*/ + { "issuesubtitle", "SUBTITLE", TITLE, LEVEL_SERIES }, /*WRONG*/ + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, + { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, + { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, + { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, + { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, + { "series", "PARTTITLE", SIMPLE, LEVEL_HOST }, + { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, + { "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 }, + { "pages", "PAGES", PAGES, LEVEL_MAIN }, + { "version", "EDITION", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "issn", "ISSN", 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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, /* WRONG */ + { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, /* WRONG */ + { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, /* WRONG */ + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "entrysubtype", "", BLT_SUBTYPE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|ARTICLE", ALWAYS, LEVEL_MAIN }, + { "", "ISSUANCE|continuing", ALWAYS, LEVEL_HOST }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "NGENRE|journal article", DEFAULT, LEVEL_MAIN }, + { "", "GENRE|periodical", DEFAULT, LEVEL_HOST } +}; + +/* Book */ + +static lookups book[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editortype", "", BLT_SKIP, LEVEL_MAIN }, + { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, + { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, + { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, + { "redactor", "REDACTOR", PERSON, LEVEL_MAIN }, + { "annotator", "ANNOTATOR", PERSON, LEVEL_MAIN }, + { "commentator", "COMMENTATOR", PERSON, LEVEL_MAIN }, + { "translator", "TRANSLATOR", PERSON, LEVEL_MAIN }, + { "introduction", "INTROAUTHOR", PERSON, LEVEL_MAIN }, + { "foreword", "INTROAUTHOR", PERSON, LEVEL_MAIN }, + { "afterword", "AFTERAUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, + { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, + { "maintitle", "TITLE", TITLE, LEVEL_HOST }, + { "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 }, + { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ + { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, + { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, + { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, + { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, + { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, + { "volume", "VOLUME", SIMPLE, LEVEL_HOST }, + { "part", "PART", SIMPLE, LEVEL_HOST }, + { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, + { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, + { "series", "TITLE", SIMPLE, LEVEL_HOST }, /* WRONG */ + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, + { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, + { "pages", "PAGES", PAGES, LEVEL_MAIN }, /* WRONG */ + { "pagetotal", "TOTALPAGES", 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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|BOOK", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|book", ALWAYS, LEVEL_MAIN } +}; + +/* Booklet */ + +static lookups booklet[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editortype", "", BLT_SKIP, LEVEL_MAIN }, + { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, + { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, + { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, + { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, + { "howpublished", "", HOWPUBLISHED, LEVEL_MAIN }, + { "year", "YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "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 }, + { "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 }, + { "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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|BOOK", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|book", ALWAYS, LEVEL_MAIN } +}; + +static lookups collection[] = { + { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editortype", "", BLT_SKIP, LEVEL_MAIN }, + { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, + { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, + { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, + { "redactor", "REDACTOR", PERSON, LEVEL_MAIN }, + { "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 }, + { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ + { "introduction", "INTROAUTHOR", PERSON, LEVEL_MAIN }, + { "foreword", "INTROAUTHOR", PERSON, LEVEL_MAIN }, + { "afterword", "AFTERAUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, + { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, + { "maintitle", "TITLE", TITLE, LEVEL_HOST }, + { "mainsubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, + { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, + { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, + { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, + { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, + { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, + { "volume", "VOLUME", SIMPLE, LEVEL_HOST }, + { "part", "PART", SIMPLE, LEVEL_HOST }, + { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, + { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, + { "series", "TITLE", SIMPLE, LEVEL_HOST }, + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, + { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, + { "pages", "PAGES", PAGES, LEVEL_MAIN }, + { "pagetotal", "TOTALPAGES", 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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|BOOK", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|book", ALWAYS, LEVEL_MAIN } +}; + +/* Part of a book (e.g. chapter or section) */ + +static lookups inbook[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "editor", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editortype", "", BLT_SKIP, LEVEL_HOST }, + { "editoratype", "", BLT_SKIP, LEVEL_HOST }, + { "editorbtype", "", BLT_SKIP, LEVEL_HOST }, + { "editorctype", "", BLT_SKIP, LEVEL_HOST }, + { "director", "DIRECTOR", PERSON, LEVEL_HOST }, + { "producer", "PRODUCER", PERSON, LEVEL_HOST }, + { "execproducer", "PRODUCER", PERSON, LEVEL_HOST }, + { "writer", "AUTHOR", PERSON, LEVEL_HOST }, + { "redactor", "REDACTOR", PERSON, LEVEL_HOST }, + { "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 }, + { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ + { "introduction", "INTROAUTHOR", PERSON, LEVEL_HOST }, + { "foreword", "INTROAUTHOR", PERSON, LEVEL_HOST }, + { "afterword", "AFTERAUTHOR", PERSON, LEVEL_HOST }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, + { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, + { "booktitle", "TITLE", TITLE, LEVEL_HOST }, + { "booksubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, + { "booktitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, + { "bookauthor", "AUTHOR", PERSON, LEVEL_HOST }, + { "maintitle", "TITLE", TITLE, LEVEL_SERIES }, + { "mainsubtitle", "SUBTITLE", TITLE, LEVEL_SERIES }, + { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_SERIES }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, + { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, + { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, + { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, + { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, + { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, + { "pages", "PAGES", PAGES, LEVEL_MAIN }, + { "part", "PART", SIMPLE, LEVEL_HOST }, + { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, + { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, + { "series", "TITLE", SIMPLE, LEVEL_SERIES+1 }, /* WRONG */ + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "isbn", "ISBN", SIMPLE, LEVEL_HOST }, + { "chapter", "CHAPTER", 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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, 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 } +}; + +/* incollection */ + +static lookups incollection[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "year", "YEAR", SIMPLE, LEVEL_MAIN }, + { "month", "MONTH", SIMPLE, LEVEL_MAIN }, + { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, + { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "introduction", "INTROAUTHOR", PERSON, LEVEL_HOST }, + { "foreword", "INTROAUTHOR", PERSON, LEVEL_HOST }, + { "afterword", "AFTERAUTHOR", PERSON, LEVEL_HOST }, + { "bookauthor", "AUTHOR", PERSON, LEVEL_HOST }, + { "booktitle", "TITLE", TITLE, LEVEL_HOST }, + { "booksubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, + { "booktitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, + { "editor", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editortype", "", BLT_SKIP, LEVEL_HOST }, + { "editoratype", "", BLT_SKIP, LEVEL_HOST }, + { "editorbtype", "", BLT_SKIP, LEVEL_HOST }, + { "editorctype", "", BLT_SKIP, LEVEL_HOST }, + { "director", "DIRECTOR", PERSON, LEVEL_HOST }, + { "producer", "PRODUCER", PERSON, LEVEL_HOST }, + { "execproducer", "PRODUCER", PERSON, LEVEL_HOST }, + { "writer", "AUTHOR", PERSON, LEVEL_HOST }, + { "redactor", "REDACTOR", PERSON, LEVEL_HOST }, + { "annotator", "ANNOTATOR", PERSON, LEVEL_HOST }, + { "commentator", "COMMENTATOR", PERSON, LEVEL_HOST }, + { "translator", "TRANSLATOR", PERSON, LEVEL_HOST }, + { "volume", "VOLUME", SIMPLE, LEVEL_HOST }, + { "part", "PART", SIMPLE, LEVEL_HOST }, + { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, + + { "maintitle", "TITLE", TITLE, LEVEL_SERIES }, + { "mainsubtitle", "SUBTITLE", TITLE, LEVEL_SERIES }, + { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_SERIES }, + + { "series", "TITLE", SIMPLE, LEVEL_SERIES+1 }, /* WRONG */ + + { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, + { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, + { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, + { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, + { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, + + { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, + { "location", "ADDRESS", SIMPLE, LEVEL_HOST }, + { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, + { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, + { "pages", "PAGES", PAGES, LEVEL_MAIN }, /* WRONG */ + { "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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|INCOLLECTION", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|collection", ALWAYS, LEVEL_HOST } +}; + +/* inproceedings */ + +static lookups inproceedings[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "editor", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_HOST }, + { "editortype", "", BLT_SKIP, LEVEL_HOST }, + { "editoratype", "", BLT_SKIP, LEVEL_HOST }, + { "editorbtype", "", BLT_SKIP, LEVEL_HOST }, + { "editorctype", "", BLT_SKIP, LEVEL_HOST }, + { "director", "DIRECTOR", PERSON, LEVEL_HOST }, + { "producer", "PRODUCER", PERSON, LEVEL_HOST }, + { "execproducer", "PRODUCER", PERSON, LEVEL_HOST }, + { "writer", "AUTHOR", PERSON, LEVEL_HOST }, + { "redactor", "REDACTOR", PERSON, LEVEL_HOST }, + { "annotator", "ANNOTATOR", PERSON, LEVEL_HOST }, + { "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 }, + { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ + { "introduction", "INTROAUTHOR", PERSON, LEVEL_HOST }, + { "foreword", "INTROAUTHOR", PERSON, LEVEL_HOST }, + { "afterword", "AFTERAUTHOR", PERSON, LEVEL_HOST }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, + { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, + + { "booktitle", "TITLE", TITLE, LEVEL_HOST }, + { "booksubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, + { "booktitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, + + { "maintitle", "TITLE", TITLE, LEVEL_SERIES }, + { "mainsubtitle", "SUBTITLE", TITLE, LEVEL_SERIES }, + { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_SERIES }, + + { "series", "TITLE", SIMPLE, LEVEL_SERIES+1 }, + + { "venue", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, + { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, + { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, + { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, + { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, + { "volume", "VOLUME", SIMPLE, LEVEL_HOST }, + { "part", "PART", SIMPLE, LEVEL_HOST }, + { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, + { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_HOST }, + { "location", "ADDRESS", SIMPLE, LEVEL_HOST }, + { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, + { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, + { "pages", "PAGES", PAGES, LEVEL_MAIN }, /* WRONG */ + { "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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?urlday?", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?urlmonth?", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?urlyear?", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|INPROCEEDINGS", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "ISSUANCE|monographic", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|conference publication", ALWAYS, LEVEL_HOST } +}; + +static lookups manual[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editortype", "", BLT_SKIP, LEVEL_MAIN }, + { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, + { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, + { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, + { "redactor", "REDACTOR", PERSON, LEVEL_MAIN }, + { "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 }, + { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ + { "introduction", "INTROAUTHOR", PERSON, LEVEL_MAIN }, + { "foreword", "INTROAUTHOR", PERSON, LEVEL_MAIN }, + { "afterword", "AFTERAUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, + { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, + { "version", "EDITION", SIMPLE, LEVEL_MAIN }, + { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, + { "series", "TITLE", SIMPLE, LEVEL_HOST }, + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, + { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, + { "pages", "PAGES", PAGES, LEVEL_MAIN }, + { "pagetotal", "TOTALPAGES", 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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|REPORT", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|instruction", ALWAYS, LEVEL_MAIN } +}; + +static lookups misc[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editortype", "", BLT_SKIP, LEVEL_MAIN }, + { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, + { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, + { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "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 }, + { "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 }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", 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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|MISC", ALWAYS, LEVEL_MAIN }, +}; + +static lookups online[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editortype", "", BLT_SKIP, LEVEL_MAIN }, + { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, + { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, + { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "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 }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "version", "EDITION", SIMPLE, LEVEL_MAIN }, + { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "location", "ADDRESS", 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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "RESOURCE|software, multimedia", ALWAYS, LEVEL_MAIN }, + { "", "NGENRE|web page", ALWAYS, LEVEL_MAIN }, +}; + +static lookups patent[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "holder", "ASSIGNEE", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "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 }, + { "version", "EDITION", SIMPLE, LEVEL_MAIN }, + { "type", "GENRE", BT_GENRE, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, 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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|PATENT", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|patent", ALWAYS, LEVEL_MAIN }, +}; + +/* + * An entire issue of a periodical + * + * "The title of the periodical is given in the title field. If the issue has + * its own title in addition to the main title of the periodical, it goes in + * the issuetitle field. The editor is omissible..." + */ +static lookups periodical[] = { + { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editortype", "", BLT_SKIP, LEVEL_MAIN }, + { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, + { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, + { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_HOST }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_HOST }, + { "titleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, + { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_HOST }, + { "issuetitle", "TITLE", TITLE, LEVEL_MAIN }, + { "issuesubtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "issuetitleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, + { "series", "TITLE", SIMPLE, LEVEL_SERIES }, + { "volume", "VOLUME", SIMPLE, LEVEL_MAIN }, + { "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 }, + { "pages", "PAGES", PAGES, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "issn", "ISSN", 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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?????", SIMPLE, LEVEL_MAIN }, /* WRONG */ + { "urlmonth", "?????", SIMPLE, LEVEL_MAIN }, /* WRONG */ + { "urlyear", "?????", SIMPLE, LEVEL_MAIN }, /* WRONG */ + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "ISSUANCE|continuing", ALWAYS, LEVEL_HOST }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|issue", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|periodical", ALWAYS, LEVEL_HOST } +}; + +static lookups proceedings[] = { + { "editor", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editora", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorb", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editorc", "EDITOR", BLT_EDITOR, LEVEL_MAIN }, + { "editortype", "", BLT_SKIP, LEVEL_MAIN }, + { "editoratype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorbtype", "", BLT_SKIP, LEVEL_MAIN }, + { "editorctype", "", BLT_SKIP, LEVEL_MAIN }, + { "director", "DIRECTOR", PERSON, LEVEL_MAIN }, + { "producer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "execproducer", "PRODUCER", PERSON, LEVEL_MAIN }, + { "writer", "AUTHOR", PERSON, LEVEL_MAIN }, + { "redactor", "REDACTOR", PERSON, LEVEL_MAIN }, + { "annotator", "ANNOTATOR", PERSON, LEVEL_MAIN }, + { "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 }, + { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ + { "introduction", "INTROAUTHOR", PERSON, LEVEL_MAIN }, + { "foreword", "INTROAUTHOR", PERSON, LEVEL_MAIN }, + { "afterword", "AFTERAUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, + { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, + { "maintitle", "TITLE", TITLE, LEVEL_HOST }, + { "mainsubtitle", "SUBTITLE", TITLE, LEVEL_HOST }, + { "maintitleaddon", "TITLEADDON", TITLE, LEVEL_HOST }, + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "origlanguage", "LANGUAGE", SIMPLE, LEVEL_ORIG }, + { "origdate", "DATE", SIMPLE, LEVEL_ORIG }, + { "origyear", "YEAR", SIMPLE, LEVEL_ORIG }, + { "origtitle", "TITLE", SIMPLE, LEVEL_ORIG }, + { "origlocation", "ADDRESS", SIMPLE, LEVEL_ORIG }, + { "origpublisher", "PUBLISHER", SIMPLE, LEVEL_ORIG }, + { "volume", "VOLUME", SIMPLE, LEVEL_HOST }, + { "part", "PART", SIMPLE, LEVEL_HOST }, + { "edition", "EDITION", SIMPLE, LEVEL_MAIN }, + { "volumes", "NUMVOLUMES", SIMPLE, LEVEL_HOST }, + { "series", "TITLE", SIMPLE, LEVEL_SERIES }, + { "number", "NUMBER", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "organization", "ORGANIZER:CORP", SIMPLE, LEVEL_MAIN }, + { "publisher", "PUBLISHER", SIMPLE, LEVEL_MAIN }, + { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "isbn", "ISBN", SIMPLE, LEVEL_MAIN }, + { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, + { "pages", "PAGES", SIMPLE, LEVEL_MAIN }, + { "pagetotal", "TOTALPAGES", 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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|BOOK", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|conference publication", ALWAYS, LEVEL_MAIN } +}; + +/* Technical reports */ +static lookups report[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "titleaddon", "TITLEADDON", TITLE, LEVEL_MAIN }, + { "shorttitle", "SHORTTITLE", SIMPLE, LEVEL_MAIN }, + { "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 }, + { "date", "DATE", SIMPLE, LEVEL_MAIN }, /*WRONG*/ + { "language", "LANGUAGE", SIMPLE, LEVEL_MAIN }, + { "number", "REPORTNUMBER", SIMPLE, LEVEL_MAIN }, + { "note", "NOTES", SIMPLE, LEVEL_MAIN }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "version", "EDITION", SIMPLE, LEVEL_MAIN }, + { "location", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "isrn", "ISRN", SIMPLE, LEVEL_MAIN }, + { "chapter", "CHAPTER", SIMPLE, LEVEL_MAIN }, + { "pages", "PAGES", SIMPLE, LEVEL_MAIN }, + { "pagetotal", "TOTALPAGES", 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 }, + { "urldate", "URLDATE", SIMPLE, LEVEL_MAIN }, + { "urlday", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlmonth", "?????????", SIMPLE, LEVEL_MAIN }, + { "urlyear", "?????????", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|REPORT", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|report", ALWAYS, LEVEL_MAIN } +}; + +/* Unpublished */ +static lookups unpublished[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "subtitle", "SUBTITLE", TITLE, LEVEL_MAIN }, + { "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 }, + { "date", "DATE", SIMPLE, LEVEL_MAIN }, + { "url", "", BT_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 }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "addendum", "ADDENDUM", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|BOOK", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|unpublished", ALWAYS, LEVEL_MAIN } +}; + +static lookups thesis[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "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 }, + { "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 }, + { "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 }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|THESIS", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|thesis", ALWAYS, LEVEL_MAIN }, +}; + +static lookups phdthesis[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "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 }, + { "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 }, + { "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 }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|THESIS", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|thesis", ALWAYS, LEVEL_MAIN }, + { "", "NGENRE|Ph.D. thesis", DEFAULT, LEVEL_MAIN }, +}; + +static lookups mastersthesis[] = { + { "author", "AUTHOR", PERSON, LEVEL_MAIN }, + { "title", "TITLE", TITLE, LEVEL_MAIN }, + { "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 }, + { "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 }, + { "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 }, + { "annote", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "annotation", "ANNOTATION", SIMPLE, LEVEL_MAIN }, + { "address", "ADDRESS", SIMPLE, LEVEL_MAIN }, + { "hyphenation", "LANGCATALOG", SIMPLE, LEVEL_MAIN }, + { "pubstate", "PUBSTATE", SIMPLE, LEVEL_MAIN }, + { "refnum", "REFNUM", SIMPLE, LEVEL_MAIN }, + { "", "INTERNAL_TYPE|THESIS", ALWAYS, LEVEL_MAIN }, + { "", "RESOURCE|text", ALWAYS, LEVEL_MAIN }, + { "", "GENRE|thesis", ALWAYS, LEVEL_MAIN }, + { "", "NGENRE|Masters thesis", DEFAULT, LEVEL_MAIN }, +}; + +#define ORIG(a) ( &(a[0]) ) +#define SIZE(a) ( sizeof( a ) / sizeof( lookups ) ) +#define REFTYPE(a,b) { a, ORIG(b), SIZE(b) } + +variants biblatex_all[] = { + REFTYPE( "article", article ), + REFTYPE( "suppperiodical", article ), + REFTYPE( "booklet", booklet ), + REFTYPE( "book", book ), + REFTYPE( "collection", collection ), + REFTYPE( "reference", collection ), + REFTYPE( "mvreference", collection ), + REFTYPE( "inbook", inbook ), + REFTYPE( "suppbook", inbook ), + REFTYPE( "incollection", incollection ), + REFTYPE( "inreference", incollection ), + REFTYPE( "suppcollection", incollection ), + REFTYPE( "inproceedings", inproceedings ), + REFTYPE( "conference", inproceedings ), /* legacy */ + REFTYPE( "manual", manual ), + REFTYPE( "misc", misc ), + REFTYPE( "online", online ), + REFTYPE( "electronic", online ), /* legacy */ + REFTYPE( "www", online ), /* jurabib compatibility */ + REFTYPE( "patent", patent ), + REFTYPE( "periodical", periodical ), + REFTYPE( "proceedings", proceedings ), + REFTYPE( "mvproceedings", proceedings ), REFTYPE( "report", report ), REFTYPE( "techreport", report ), /* REFTYPE( "set", set ), */ 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 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Program and source code released under the GPL version 2 * @@ -20,6 +20,9 @@ #include "serialno.h" #include "copacin.h" +/***************************************************** + PUBLIC: void copacin_initparams() +*****************************************************/ void copacin_initparams( param *p, const char *progname ) { @@ -49,6 +52,10 @@ else p->progname = strdup( progname ); } +/***************************************************** + PUBLIC: int copacin_readf() +*****************************************************/ + /* Endnote-Refer/Copac tag definition: character 1 = alphabetic character character 2 = alphabetic character @@ -114,6 +121,10 @@ return haveref; } +/***************************************************** + PUBLIC: int copacin_processf() +*****************************************************/ + static char* copacin_addtag2( char *p, newstr *tag, newstr *data ) { @@ -145,6 +156,7 @@ copacin_processf( fields *copacin, char *p, char *filename, long nref ) { newstr tag, data; + int status; newstr_init( &tag ); newstr_init( &data ); while ( *p ) { @@ -152,8 +164,10 @@ if ( copacin_istag( p ) ) { p = copacin_addtag2( p, &tag, &data ); /* don't add empty strings */ - if ( tag.len && data.len ) - fields_add( copacin, tag.data, data.data, 0 ); + if ( tag.len && data.len ) { + status = fields_add( copacin, tag.data, data.data, 0 ); + if ( status!=FIELDS_OK ) return 0; + } newstr_empty( &tag ); newstr_empty( &data ); } @@ -164,6 +178,10 @@ return 1; } +/***************************************************** + PUBLIC: int copacin_convertf(), returns BIBL_OK or BIBL_ERR_MEMERR +*****************************************************/ + /* copac names appear to always start with last name first, but don't * always seem to have a comma after the name * @@ -176,17 +194,19 @@ char *usetag = tag, editor[]="EDITOR"; newstr usename, *s; list tokens; - int comma = 0, i; + int comma = 0, i, ok; if ( list_find( asis, name->data ) !=-1 || list_find( corps, name->data ) !=-1 ) { - return name_add( info, tag, name->data, level, asis, corps ); + ok = name_add( info, tag, name->data, level, asis, corps ); + if ( ok ) return BIBL_OK; + else return BIBL_ERR_MEMERR; } list_init( &tokens ); newstr_init( &usename ); - list_tokenize( &tokens, name, ' ', 1 ); + list_tokenize( &tokens, name, " ", 1 ); for ( i=0; idata, "[Editor]" ) ) { @@ -207,90 +227,11 @@ newstr_newstrcat( &usename, list_get( &tokens, i ) ); } - return name_add( info, usetag, usename.data, level, asis, corps ); -} - -static int -copacin_addpage( fields *info, char *p, int level ) -{ - newstr page; - int ok; - newstr_init( &page ); - p = skip_ws( p ); - while ( *p && !is_ws(*p) && *p!='-' && *p!='\r' && *p!='\n' ) - newstr_addchar( &page, *p++ ); - if ( page.len>0 ) { - ok = fields_add( info, "PAGESTART", page.data, level ); - if ( !ok ) return 0; - } - newstr_empty( &page ); - while ( *p && (is_ws(*p) || *p=='-' ) ) p++; - while ( *p && !is_ws(*p) && *p!='-' && *p!='\r' && *p!='\n' ) - newstr_addchar( &page, *p++ ); - if ( page.len>0 ) { - ok = fields_add( info, "PAGEEND", page.data, level ); - if ( !ok ) return 0; - } - newstr_free( &page ); - return 1; -} + list_free( &tokens ); -static int -copacin_adddate( fields *info, char *tag, char *newtag, char *p, int level ) -{ - char *months[12]={ "January", "February", "March", "April", - "May", "June", "July", "August", "September", - "October", "November", "December" }; - char month[10]; - int found,i,part,ok; - newstr date; - newstr_init( &date ); - part = (!strncasecmp(newtag,"PART",4)); - if ( !strcasecmp( tag, "%D" ) ) { - while ( *p ) newstr_addchar( &date, *p++ ); - if ( date.len>0 ) { - if ( part ) - ok = fields_add(info, "PARTYEAR", date.data, level); - else - ok = fields_add( info, "YEAR", date.data, level ); - if ( !ok ) return 0; - } - } else if ( !strcasecmp( tag, "%8" ) ) { - while ( *p && *p!=' ' && *p!=',' ) newstr_addchar( &date, *p++ ); - if ( date.len>0 ) { - found = -1; - for ( i=0; i<12 && found==-1; ++i ) - if ( !strncasecmp( date.data, months[i], 3 ) ) - found = i; - if ( found!=-1 ) { - if (found>8) sprintf( month, "%d", found+1 ); - else sprintf( month, "0%d", found+1 ); - if ( part ) - ok = fields_add( info, "PARTMONTH", month, level ); - else ok = fields_add( info, "MONTH", month, level ); - if ( !ok ) return 0; - } else { - if ( part ) - ok = fields_add( info, "PARTMONTH", date.data, level ); - else - ok = fields_add( info, "MONTH", date.data, level ); - if ( !ok ) return 0; - } - } - newstr_empty( &date ); - p = skip_ws( p ); - while ( *p && *p!='\n' && *p!=',' ) - newstr_addchar( &date, *p++ ); - if ( date.len>0 && date.len<3 ) { - if ( part ) - ok = fields_add( info, "PARTDAY", date.data, level ); - else - ok = fields_add( info, "DAY", date.data, level ); - if ( !ok ) return 0; - } - } - newstr_free( &date ); - return 1; + ok = name_add( info, usetag, usename.data, level, asis, corps ); + if ( ok ) return BIBL_OK; + else return BIBL_ERR_MEMERR; } static void @@ -302,10 +243,18 @@ } } +static int +copacin_simple( fields *out, char *tag, char *value, int level ) +{ + int fstatus = fields_add( out, tag, value, level ); + if ( fstatus==FIELDS_OK ) return BIBL_OK; + else return BIBL_ERR_MEMERR; +} + int copacin_convertf( fields *copacin, fields *out, int reftype, param *p, variants *all, int nall ) { - int process, level, i, n, nfields, ok; + int process, level, i, n, nfields, ok, status = BIBL_OK; newstr *tag, *data; char *newtag; @@ -326,39 +275,35 @@ switch ( process ) { case SIMPLE: - ok = fields_add( out, newtag, data->data, level ); + 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: - ok = copacin_addname( out, newtag, data, level, &(p->asis), &(p->corps) ); - break; - - case DATE: - ok = copacin_adddate(out,all[reftype]. tags[i].oldstr,newtag,data->data,level); - break; - - case PAGES: - ok = copacin_addpage( out, data->data, level ); + 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 ); - ok = 1; + status = BIBL_OK; break; } - if ( !ok ) return BIBL_ERR_MEMERR; + if ( status!=BIBL_OK ) return status; } - return BIBL_OK; + return status; } diff --git a/bibutils/copacin.h b/bibutils/copacin.h --- a/bibutils/copacin.h +++ b/bibutils/copacin.h @@ -1,7 +1,7 @@ /* * copacin.h * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Source code released under the GPL * 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 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Program and source code released under the GPL version 2 * diff --git a/bibutils/ebiin.c b/bibutils/ebiin.c --- a/bibutils/ebiin.c +++ b/bibutils/ebiin.c @@ -16,6 +16,9 @@ #include "xml_encoding.h" #include "ebiin.h" +/***************************************************** + PUBLIC: void ebiin_initparams() +*****************************************************/ void ebiin_initparams( param *p, const char *progname ) { @@ -46,6 +49,9 @@ else p->progname = strdup( progname ); } +/***************************************************** + PUBLIC: int ebiin_readf() +*****************************************************/ int ebiin_readf( FILE *fp, char *buf, int bufsize, int *bufpos, newstr *line, newstr *reference, int *fcharset ) { @@ -78,27 +84,9 @@ return haveref; } - -static inline int -xml_hasdata( xml *node ) -{ - if ( node && node->value && node->value->data ) return 1; - return 0; -} - -static inline char * -xml_data( xml *node ) -{ - return node->value->data; -} - - -static inline int -xml_tagwithdata( xml *node, char *tag ) -{ - if ( !xml_hasdata( node ) ) return 0; - return xml_tagexact( node, tag ); -} +/***************************************************** + PUBLIC: int ebiin_processf() +*****************************************************/ typedef struct xml_convert { char *in; /* The input tag */ @@ -108,72 +96,108 @@ } xml_convert; static int -ebiin_doconvert( xml *node, fields *info, xml_convert *c, int nc ) +ebiin_doconvert( xml *node, fields *info, xml_convert *c, int nc, int *found ) { - int i, found = 0; + int i, status; char *d; - if ( !xml_hasdata( node ) ) return 0; + + if ( !xml_hasdata( node ) ) goto out; + d = xml_data( node ); - for ( i=0; iMechanism and..... + * and * Mechanism and.... */ -static void +static int ebiin_title( xml *node, fields *info, int title_level ) { - if ( xml_hasdata( node ) ) - fields_add( info, "TITLE", xml_data( node ), title_level ); + int status; + if ( xml_hasdata( node ) ) { + status = fields_add( info, "TITLE", xml_data( node ), title_level ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + return BIBL_OK; } -/* 2003 Jan-Feb */ -static void -ebiin_medlinedate( fields *info, char *string, int level ) +/* ebiin_medlinedate() + * + * - extract medline information from entries like: + * 2003 Jan-Feb + */ +static int +ebiin_medlinedate_year( fields *info, char *p, newstr *s, int level, char **end ) { - newstr tmp; - char *p, *q; - newstr_init( &tmp ); - /* extract year */ - p = string; - q = skip_notws( string ); - newstr_segcpy( &tmp, p, q ); - fields_add( info, "PARTYEAR", tmp.data, level ); - q = skip_ws( q ); - /* extract month */ - if ( q ) { - p = q; - newstr_empty( &tmp ); - q = skip_notws( q ); - newstr_segcpy( &tmp, p, q ); - newstr_findreplace( &tmp, "-", "/" ); - fields_add( info, "PARTMONTH", tmp.data, level ); - q = skip_ws( q ); + 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 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - /* extract day */ - if ( q ) { - p = q; - newstr_empty( &tmp ); - q = skip_notws( q ); - newstr_segcpy( &tmp, p, q ); - fields_add( info, "PARTDAY", tmp.data, level ); + return BIBL_OK; +} +static int +ebiin_medlinedate_month( fields *info, char *p, newstr *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 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - newstr_free( &tmp ); + return BIBL_OK; } +static int +ebiin_medlinedate_day( fields *info, char *p, newstr *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 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + return BIBL_OK; +} +static int +ebiin_medlinedate( fields *info, char *p, int level ) +{ + int status; + newstr s; + newstr_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 ); + return status; +} /* * 0027-8424 @@ -203,7 +227,7 @@ * Alcohol Alcohol. * */ -static void +static int ebiin_journal1( xml *node, fields *info ) { xml_convert c[] = { @@ -215,59 +239,112 @@ { "Day", NULL, NULL, "PARTDAY", 1 }, { "Language", NULL, NULL, "LANGUAGE", 1 }, }; - int nc = sizeof( c ) / sizeof( c[0] );; - if ( xml_hasdata( node ) && !ebiin_doconvert( node, info, c, nc ) ) { - if ( xml_tagexact( node, "MedlineDate" ) ) - ebiin_medlinedate( info, xml_data( node ), 1 ); + int nc = sizeof( c ) / sizeof( c[0] ), status, found; + if ( xml_hasdata( 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 ); + if ( status!=BIBL_OK ) return status; + } + } } - if ( node->down ) ebiin_journal1( node->down, info ); - if ( node->next ) ebiin_journal1( node->next, info ); + if ( node->down ) { + status = ebiin_journal1( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) { + status = ebiin_journal1( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } - /* * 12111-6 * */ -static void +static int +ebiin_pages( fields *info, char *p ) +{ + int i, status, ret = BIBL_OK; + const int level = 1; + newstr sp, ep, *up; + + newstrs_init( &sp, &ep, NULL ); + + /* ...start page */ + p = newstr_cpytodelim( &sp, skip_ws( p ), "-", 1 ); + if ( newstr_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 ) ) { + ret = BIBL_ERR_MEMERR; + goto out; + } + + if ( sp.len ) { + status = fields_add( info, "PAGESTART", sp.data, level ); + if ( status!=FIELDS_OK ) { + ret = BIBL_ERR_MEMERR; + goto out; + } + } + if ( ep.len ) { + if ( sp.len > ep.len ) { + for ( i=sp.len-ep.len; idata, level ); + if ( status!=FIELDS_OK ) ret = BIBL_ERR_MEMERR; + } + +out: + newstrs_free( &sp, &ep, NULL ); + return ret; +} +static int ebiin_pagination( xml *node, fields *info ) { - newstr sp, ep; - char *p; - int i; + int status; if ( xml_tagexact( node, "Pages" ) && node->value ) { - newstrs_init( &sp, &ep, NULL ); - p = xml_data( node ); - while ( *p && *p!='-' ) - newstr_addchar( &sp, *p++ ); - if ( *p=='-' ) p++; - while ( *p ) - newstr_addchar( &ep, *p++ ); - if ( sp.len ) fields_add( info, "PAGESTART", sp.data, 1 ); - if ( ep.len ) { - if ( sp.len > ep.len ) { - for ( i=sp.len-ep.len; idown ) ebiin_pagination( node->down, info ); - if ( node->next ) ebiin_pagination( node->next, info ); + if ( node->down ) { + status = ebiin_pagination( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) { + status = ebiin_pagination( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } /* * ljwejrelr * */ -static void +static int ebiin_abstract( xml *node, fields *info ) { - if ( xml_hasdata( node ) && xml_tagexact( node, "AbstractText" ) ) - fields_add( info, "ABSTRACT", xml_data( node ), 0 ); - else if ( node->next ) ebiin_abstract( node->next, info ); + int status; + if ( xml_hasdata( node ) && xml_tagexact( node, "AbstractText" ) ) { + status = fields_add( info, "ABSTRACT", xml_data( node ), 0 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + else if ( node->next ) { + status = ebiin_abstract( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } /* @@ -279,9 +356,10 @@ * * */ -static void +static int ebiin_author( xml *node, newstr *name ) { + int status; char *p; if ( xml_tagexact( node, "LastName" ) ) { if ( name->len ) { @@ -304,28 +382,42 @@ if ( !is_ws(*p ) ) newstr_addchar( name, *p++ ); } } + if ( newstr_memerr( name ) ) return BIBL_ERR_MEMERR; - if ( node->down ) ebiin_author( node->down, name ); - if ( node->next ) ebiin_author( node->next, name ); -} + if ( node->down ) { + status = ebiin_author( node->down, name ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) { + status = ebiin_author( node->next, name ); + if ( status!=BIBL_OK ) return status; + } -static void + return BIBL_OK; +} +static int ebiin_authorlist( xml *node, fields *info, int level ) { + int fstatus, status = BIBL_OK; newstr name; + newstr_init( &name ); node = node->down; while ( node ) { if ( xml_tagexact( node, "Author" ) && node->down ) { - ebiin_author( node->down, &name ); + status = ebiin_author( node->down, &name ); + if ( status!=BIBL_OK ) goto out; if ( name.len ) { - fields_add(info,"AUTHOR",name.data,level); + fstatus = fields_add(info,"AUTHOR",name.data,level); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } newstr_empty( &name ); } } node = node->next; } +out: newstr_free( &name ); + return status; } /* @@ -340,13 +432,23 @@ * */ -static void +static int ebiin_journal2( xml *node, fields *info ) { - if ( xml_tagwithdata( node, "TitleAbbreviation" ) ) - fields_add( info, "TITLE", xml_data( node ), 1 ); - if ( node->down ) ebiin_journal2( node->down, info ); - if ( node->next ) ebiin_journal2( node->next, info ); + int status; + if ( xml_tagwithdata( node, "TitleAbbreviation" ) ) { + status = fields_add( info, "TITLE", xml_data( node ), 1 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + if ( node->down ) { + status = ebiin_journal2( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) { + status = ebiin_journal2( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } /* @@ -359,23 +461,37 @@ * * */ -static void +static int ebiin_meshheading( xml *node, fields *info ) { - if ( xml_tagwithdata( node, "DescriptorName" ) ) - fields_add( info, "KEYWORD", xml_data( node ), 0 ); - if ( node->next ) ebiin_meshheading( node->next, info ); + int status; + if ( xml_tagwithdata( node, "DescriptorName" ) ) { + status = fields_add( info, "KEYWORD", xml_data( node ), 0 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + if ( node->next ) { + status = ebiin_meshheading( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } -static void +static int ebiin_meshheadinglist( xml *node, fields *info ) { - if ( xml_tagexact( node, "MeshHeading" ) && node->down ) - ebiin_meshheading( node->down, info ); - if ( node->next ) ebiin_meshheadinglist( node->next, info ); + int status; + if ( xml_tagexact( node, "MeshHeading" ) && node->down ) { + status = ebiin_meshheading( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) { + status = ebiin_meshheadinglist( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } -static void +static int ebiin_book( xml *node, fields *info, int book_level ) { xml_convert book[] = { @@ -409,101 +525,175 @@ }; int ninbook = sizeof( inbook ) / sizeof( inbook[0] ); xml_convert *c; - int nc; + int nc, status, found; if ( book_level==0 ) { c = book; nc = nbook; } else { c = inbook; nc = ninbook; } - if ( xml_hasdata( node ) && !ebiin_doconvert( node, info, c, nc ) ) { - if ( xml_tagexact( node, "MedlineDate" ) ) - ebiin_medlinedate( info, xml_data( node ), book_level); - else if ( xml_tagexact( node, "Title" ) ) - ebiin_title( node, info, book_level ); - else if ( xml_tagexact( node, "Pagination" ) && node->down ) - ebiin_pagination( node->down, info ); - else if ( xml_tagexact( node, "Abstract" ) && node->down ) - ebiin_abstract( node->down, info ); - else if ( xml_tagexact( node, "AuthorList" ) ) - ebiin_authorlist( node, info, book_level ); - else if ( xml_tagexact( node, "PubDate" ) && node->down) - ebiin_book( node->down, info, book_level ); + if ( xml_hasdata( 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); + else if ( xml_tagexact( node, "Title" ) ) + status = ebiin_title( node, info, book_level ); + else if ( xml_tagexact( node, "Pagination" ) && node->down ) + status = ebiin_pagination( node->down, info ); + else if ( xml_tagexact( node, "Abstract" ) && node->down ) + status = ebiin_abstract( node->down, info ); + else if ( xml_tagexact( node, "AuthorList" ) ) + status = ebiin_authorlist( node, info, book_level ); + else if ( xml_tagexact( node, "PubDate" ) && node->down) + status = ebiin_book( node->down, info, book_level ); + if ( status!=BIBL_OK ) return status; + } } - if ( node->next ) ebiin_book( node->next, info, book_level ); + if ( node->next ) { + status = ebiin_book( node->next, info, book_level ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } -static void +static int ebiin_article( xml *node, fields *info ) { + int status = BIBL_OK; + if ( xml_tagexact( node, "Journal" ) ) - ebiin_journal1( node, info ); + status = ebiin_journal1( node, info ); else if ( node->down && ( xml_tagexact( node, "Book" ) || xml_tagexact(node, "Report") )) - ebiin_book( node->down, info, 1 ); + status = ebiin_book( node->down, info, 1 ); else if ( xml_tagexact( node, "ArticleTitle" ) ) - ebiin_title( node, info, 0 ); + status = ebiin_title( node, info, 0 ); else if ( xml_tagexact( node, "Pagination" ) && node->down ) - ebiin_pagination( node->down, info ); + status = ebiin_pagination( node->down, info ); else if ( xml_tagexact( node, "Abstract" ) && node->down ) - ebiin_abstract( node->down, info ); + status = ebiin_abstract( node->down, info ); else if ( xml_tagexact( node, "AuthorList" ) ) - ebiin_authorlist( node, info, 0 ); - if ( node->next ) ebiin_article( node->next, info ); + status = ebiin_authorlist( node, info, 0 ); + if ( status!=BIBL_OK ) return status; + + if ( node->next ) { + status = ebiin_article( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + + return BIBL_OK; } -static void +static int ebiin_publication( xml *node, fields *info ) { + int status; if ( node->down ) { if ( xml_tagexact( node, "Article" ) ) - ebiin_article( node->down, info ); + status = ebiin_article( node->down, info ); else if ( xml_tagexact( node, "Book" ) ) - ebiin_book( node->down, info, 0 ); + status = ebiin_book( node->down, info, 0 ); else if ( xml_tagexact( node, "Report" ) ) - ebiin_book( node->down, info, 0 ); + status = ebiin_book( node->down, info, 0 ); else if ( xml_tagexact( node, "JournalInfo" ) ) - ebiin_journal2( node->down, info ); + status = ebiin_journal2( node->down, info ); else if ( xml_tagexact( node, "MeshHeadingList" ) ) - ebiin_meshheadinglist( node->down, info ); + status = ebiin_meshheadinglist( node->down, info ); + if ( status!=BIBL_OK ) return status; } - if ( node->next ) ebiin_publication( node->next, info ); + if ( node->next ) { + status = ebiin_publication( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } /* Call with the "Publication" node */ -static void +static int ebiin_fixtype( xml *node, fields *info ) { + char *resource = NULL, *issuance = NULL, *genre1 = NULL, *genre2 = NULL; newstr *type; - fields_add( info, "RESOURCE", "text", 0 ); + int reslvl, isslvl, gen1lvl, gen2lvl; + int status; + type = xml_getattrib( node, "Type" ); - if ( !type || type->len==0 ) return; + if ( !type || type->len==0 ) return BIBL_OK; + if ( !strcmp( type->data, "JournalArticle" ) ) { - fields_add( info, "ISSUANCE", "continuing", 1 ); - fields_add( info, "GENRE", "periodical", 1 ); - fields_add( info, "GENRE", "academic journal", 1 ); + resource = "text"; + issuance = "continuing"; + genre1 = "periodical"; + genre2 = "academic journal"; + reslvl = 0; + isslvl = 1; + gen1lvl = 1; + gen2lvl = 1; } else if ( !strcmp( type->data, "Book" ) ) { - fields_add( info, "GENRE", "book", 0 ); - fields_add( info, "ISSUANCE", "monographic", 0 ); + resource = "text"; + issuance = "monographic"; + genre1 = "book"; + reslvl = 0; + isslvl = 0; + gen1lvl = 0; } else if ( !strcmp( type->data, "BookArticle" ) ) { - fields_add( info, "GENRE", "book", 1 ); - fields_add( info, "ISSUANCE", "monographic", 1 ); + resource = "text"; + issuance = "monographic"; + genre1 = "book"; + reslvl = 0; + isslvl = 1; + gen1lvl = 1; } + + if ( resource ) { + status = fields_add( info, "RESOURCE", resource, reslvl ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + if ( issuance ) { + status = fields_add( info, "ISSUANCE", issuance, isslvl ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + if ( genre1 ) { + status = fields_add( info, "GENRE", genre1, gen1lvl ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + if ( genre2 ) { + status = fields_add( info, "GENRE", genre2, gen2lvl ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + + return BIBL_OK; } -static void +static int ebiin_assembleref( xml *node, fields *info ) { - if ( xml_tagexact( node, "Publication" ) && node->down) { - ebiin_fixtype( node, info ); - ebiin_publication( node->down, info ); - } else if ( node->down ) ebiin_assembleref( node->down, info ); - if ( node->next ) ebiin_assembleref( node->next, info ); + int status; + if ( xml_tagexact( node, "Publication" ) && node->down ) { + status = ebiin_fixtype( node, info ); + if ( status!=BIBL_OK ) return status; + status = ebiin_publication( node->down, info ); + if ( status!=BIBL_OK ) return status; + } else if ( node->down ) { + status = ebiin_assembleref( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) { + status = ebiin_assembleref( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } int ebiin_processf( fields *ebiin, char *data, char *filename, long nref ) { + int status; xml top; + xml_init( &top ); xml_tree( data, &top ); - ebiin_assembleref( &top, ebiin ); + status = ebiin_assembleref( &top, ebiin ); xml_free( &top ); - return 1; + + return ( status==BIBL_OK ) ? 1 : 0; } 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 2003-2013 + * Copyright (c) Chris Putnam 2003-2014 * * Program and source code released under the GPL version 2 * @@ -21,6 +21,9 @@ #include "reftypes.h" #include "endin.h" +/***************************************************** + PUBLIC: void endin_initparams() +*****************************************************/ void endin_initparams( param *p, const char *progname ) { @@ -50,6 +53,11 @@ else p->progname = strdup( progname ); } + +/***************************************************** + PUBLIC: int endin_readf() +*****************************************************/ + /* Endnote tag definition: character 1 = '%' character 2 = alphabetic character or digit (or other characters) @@ -113,6 +121,9 @@ return haveref; } +/***************************************************** + PUBLIC: int endin_processf() +*****************************************************/ static char* process_endline( newstr *tag, newstr *data, char *p ) { @@ -149,159 +160,37 @@ endin_processf( fields *endin, char *p, char *filename, long nref ) { newstr tag, data; - int n; + int status, n; newstrs_init( &tag, &data, NULL ); while ( *p ) { + newstrs_empty( &tag, &data, NULL ); if ( endin_istag( p ) ) { p = process_endline( &tag, &data, p ); - /* no empty fields allowed */ - if ( data.len ) { - fields_add( endin, tag.data, data.data, 0 ); - } + if ( data.len==0 ) continue; + status = fields_add( endin, tag.data, data.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 ( !strncmp( endin->tag[n-1].data, "%K", 2 ) ) { - fields_add( endin, "%K", data.data, 0 ); + status = fields_add( endin, "%K", data.data, 0 ); + if ( status!=FIELDS_OK ) return 0; } else { newstr_addchar( &(endin->data[n-1]), ' ' ); newstr_strcat( &(endin->data[n-1]), data.data ); } } } - newstrs_empty( &tag, &data, NULL ); } newstrs_free( &tag, &data, NULL ); return 1; } -static int -endin_addtype( fields *info, char *data, int level ) -{ - lookups types[] = { - { "GENERIC", "ARTICLE" }, - { "BOOK", "BOOK" }, - { "MANUSCRIPT", "MANUSCRIPT" }, - { "CONFERENCE PROCEEDINGS", "INPROCEEDINGS"}, - { "REPORT", "REPORT" }, - { "COMPUTER PROGRAM", "BOOK" }, - { "AUDIOVISUAL MATERIAL", "AUDIOVISUAL" }, - { "ARTWORK", "BOOK" }, - { "PATENT", "BOOK" }, - { "BILL", "BILL" }, - { "CASE", "CASE" }, - { "JOURNAL ARTICLE", "ARTICLE" }, - { "MAGAZINE ARTICLE", "ARTICLE" }, - { "BOOK SECTION", "INBOOK" }, - { "EDITED BOOK", "BOOK" }, - { "NEWSPAPER ARTICLE", "NEWSARTICLE" }, - { "THESIS", "PHDTHESIS" }, - { "PERSONAL COMMUNICATION", "COMMUNICATION" }, - { "ELECTRONIC SOURCE", "TEXT" }, - { "FILM OR BROADCAST", "AUDIOVISUAL" }, - { "MAP", "MAP" }, - { "HEARING", "HEARING" }, - { "STATUTE", "STATUTE" }, - { "CHART OR TABLE", "CHART" }, - { "WEB PAGE", "WEBPAGE" }, - }; - int ntypes = sizeof( types ) / sizeof( lookups ); - int i, ok, found=0; - for ( i=0; i0 ) { - ok = fields_add( info, "PAGESTART", page.data, level ); - if ( !ok ) return 0; - } - newstr_empty( &page ); - while ( *p && (is_ws(*p) || *p=='-' ) ) p++; - while ( *p && !is_ws(*p) && *p!='-' && *p!='\r' && *p!='\n' ) - newstr_addchar( &page, *p++ ); - if ( page.len>0 ) { - ok = fields_add( info, "PAGEEND", page.data, level ); - if ( !ok ) return 0; - } - newstr_free( &page ); - return 1; -} - -static int -endin_adddate( fields *info, char *tag, char *newtag, char *p, int level ) -{ - char *months[12]={ "January", "February", "March", "April", - "May", "June", "July", "August", "September", - "October", "November", "December" }; - char month[10]; - int found,i,part, ok; - newstr date; - newstr_init( &date ); - part = (!strncasecmp(newtag,"PART",4)); - if ( !strcasecmp( tag, "%D" ) ) { - while ( *p ) newstr_addchar( &date, *p++ ); - if ( date.len>0 ) { - if ( part ) ok = fields_add( info, "PARTYEAR", date.data, level ); - else ok = fields_add( info, "YEAR", date.data, level ); - if ( !ok ) return 0; - } - } else if ( !strcasecmp( tag, "%8" ) ) { - while ( *p && *p!=' ' && *p!=',' ) newstr_addchar( &date, *p++ ); - if ( date.len>0 ) { - found = -1; - for ( i=0; i<12 && found==-1; ++i ) - if ( !strncasecmp( date.data, months[i], 3 ) ) - found = i; - if ( found!=-1 ) { - if (found>8) sprintf( month, "%d", found+1 ); - else sprintf( month, "0%d", found+1 ); - if ( part ) ok = fields_add( info, "PARTMONTH", month, level ); - else ok = fields_add( info, "MONTH", month, level ); - if ( !ok ) return 0; - } else { - if ( part ) - ok = fields_add( info, "PARTMONTH", date.data, level ); - else - ok = fields_add( info, "MONTH", date.data, level ); - if ( !ok ) return 0; - } - } - newstr_empty( &date ); - p = skip_ws( p ); - while ( *p && *p!='\n' && *p!=',' ) newstr_addchar( &date, *p++ ); - if ( date.len>0 && date.len<3 ) { - if ( part ) ok = fields_add( info, "PARTDAY", date.data, level ); - else ok = fields_add( info, "DAY", date.data, level ); - if ( !ok ) return 0; - } - } - newstr_free( &date ); - return 1; -} +/***************************************************** + PUBLIC: int endin_typef() +*****************************************************/ /* Endnote defaults if no %0 * @@ -353,6 +242,10 @@ return reftype; } +/***************************************************** + PUBLIC: void endin_cleanf() +*****************************************************/ + /* Wiley puts multiple authors separated by commas on the %A lines. * We can detect this by finding the terminal comma in the data. * @@ -370,51 +263,265 @@ return 1; } -static void +static int cleanup_wiley_author( fields *endin, int n ) { - newstr tmp, tmppart; - int i, nauthor = 0; - newstrs_init( &tmp, &tmppart, NULL ); - newstr_newstrcpy( &tmp, &( endin->data[n] ) ); - i = 0; - while ( idata[n]), &tmppart ); - else - fields_add( endin, endin->tag[n].data, - tmppart.data, endin->level[n] ); - newstr_empty( &tmppart ); + newstr *instring, copy, name; + int status, nauthor = 0; + char *p; + + newstrs_init( ©, &name, NULL ); + + instring = &( endin->data[n] ); + newstr_newstrcpy( ©, instring ); + + p = copy.data; + while ( *p ) { + if ( *p==',' ) { + if ( newstr_memerr( &name ) ) + return BIBL_ERR_MEMERR; + if ( nauthor==0 ) { + /* ...replace the first author in the field */ + newstr_newstrcpy( instring, &name ); + if ( newstr_memerr( instring ) ) + return BIBL_ERR_MEMERR; + } else { + status = fields_add( endin, endin->tag[n].data, + name.data, endin->level[n] ); + if ( status!=FIELDS_OK ) + return BIBL_ERR_MEMERR; + } + newstr_empty( &name ); nauthor++; - while ( inrefs; ++i ) endin_cleanref( bin->ref[i] ); + return BIBL_OK; } +/***************************************************** + 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 + * otherwise return 0 + */ +static int +month_convert( char *in, char *out ) +{ + char *month1[12]={ + "January", "February", + "March", "April", + "May", "June", + "July", "August", + "September", "October", + "November", "December" + }; + char *month2[12]={ + "Jan", "Feb", + "Mar", "Apr", + "May", "Jun", + "Jul", "Aug", + "Sep", "Oct", + "Nov", "Dec" + }; + int i, found = -1; + + for ( i=0; i<12 && found==-1; ++i ) { + if ( !strcasecmp( in, month1[i] ) ) found = i; + if ( !strcasecmp( in, month2[i] ) ) found = i; + } + + if ( found==-1 ) return 0; + + if ( found > 8 ) + sprintf( out, "%d", found+1 ); + else + sprintf( out, "0%d", found+1 ); + + return 1; +} + +static int +endin_adddate( fields *info, char *tag, char *newtag, char *p, int level ) +{ + char *tags[3][2] = { + { "YEAR", "PARTYEAR" }, + { "MONTH", "PARTMONTH" }, + { "DAY", "PARTDAY" } + }; + char month[10], *m; + int part, status; + newstr date; + + newstr_init( &date ); + + if ( !strncasecmp( newtag, "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 ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + } + + /* %8 MONTH DAY, YEAR */ + /* %8 MONTH, YEAR */ + /* %8 MONTH YEAR */ + else if ( !strcasecmp( tag, "%8" ) ) { + + /* ...get month */ + p = newstr_cpytodelim( &date, skip_ws( p ), " ,\n", 0 ); + if ( newstr_memerr( &date ) ) return BIBL_ERR_MEMERR; + if ( date.len>0 ) { + if ( month_convert( date.data, month ) ) m = month; + else m = date.data; + status = fields_add( info, tags[1][part], m, level ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + + p = skip_ws( p ); + if ( *p==',' ) p++; + + /* ...get days */ + p = newstr_cpytodelim( &date, skip_ws( p ), ",\n", 0 ); + if ( newstr_memerr( &date ) ) return BIBL_ERR_MEMERR; + if ( date.len>0 && date.len<3 ) { + status = fields_add( info, 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 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + + p = skip_ws( p ); + 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 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + } + newstr_free( &date ); + return BIBL_OK; +} + +static int +endin_addtype( fields *info, char *data, int level ) +{ + lookups types[] = { + { "GENERIC", "ARTICLE" }, + { "BOOK", "BOOK" }, + { "MANUSCRIPT", "MANUSCRIPT" }, + { "CONFERENCE PROCEEDINGS", "INPROCEEDINGS"}, + { "REPORT", "REPORT" }, + { "COMPUTER PROGRAM", "BOOK" }, + { "AUDIOVISUAL MATERIAL", "AUDIOVISUAL" }, + { "ARTWORK", "BOOK" }, + { "PATENT", "BOOK" }, + { "BILL", "BILL" }, + { "CASE", "CASE" }, + { "JOURNAL ARTICLE", "ARTICLE" }, + { "MAGAZINE ARTICLE", "ARTICLE" }, + { "BOOK SECTION", "INBOOK" }, + { "EDITED BOOK", "BOOK" }, + { "NEWSPAPER ARTICLE", "NEWSARTICLE" }, + { "THESIS", "PHDTHESIS" }, + { "PERSONAL COMMUNICATION", "COMMUNICATION" }, + { "ELECTRONIC SOURCE", "TEXT" }, + { "FILM OR BROADCAST", "AUDIOVISUAL" }, + { "MAP", "MAP" }, + { "HEARING", "HEARING" }, + { "STATUTE", "STATUTE" }, + { "CHART OR TABLE", "CHART" }, + { "WEB PAGE", "WEBPAGE" }, + }; + int ntypes = sizeof( types ) / sizeof( lookups ); + int i, status, found=0; + for ( i=0; idata, endin->level[i] ); + fstatus = fields_add( info, t, d->data, endin->level[i] ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; continue; } @@ -473,46 +592,52 @@ switch ( process ) { case SIMPLE: - ok = fields_add( info, newtag, d->data, level ); + status = endin_simple( info, newtag, d->data, level ); break; case TYPE: - ok = endin_addtype( info, d->data, level ); + 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: - ok = endin_adddate( info, t, newtag,d->data,level); + status = endin_adddate( info, t, newtag,d->data,level); break; case PAGES: - ok = endin_addpage( info, d->data, level ); + 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: - ok = endin_addnotes( info, newtag, d->data, level ); + status = endin_addnotes( info, newtag, d->data, level ); break; default: fprintf(stderr,"%s: internal error -- illegal process number %d\n", p->progname, process ); - ok = 1; + status = BIBL_OK; break; } - if ( !ok ) return BIBL_ERR_MEMERR; + if ( status!=BIBL_OK ) return status; } - return BIBL_OK; + return status; } diff --git a/bibutils/endin.h b/bibutils/endin.h --- a/bibutils/endin.h +++ b/bibutils/endin.h @@ -1,7 +1,7 @@ /* * endin.h * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2014 * * Source code released under the GPL version 2 * @@ -18,7 +18,7 @@ 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 void endin_cleanf( bibl *bin, param *p ); +extern int endin_cleanf( bibl *bin, param *p ); extern void endin_initparams( param *p, const char *progname ); diff --git a/bibutils/endout.c b/bibutils/endout.c --- a/bibutils/endout.c +++ b/bibutils/endout.c @@ -28,7 +28,7 @@ p->latexout = 0; p->utf8out = BIBL_CHARSET_UTF8_DEFAULT; p->utf8bom = BIBL_CHARSET_BOM_DEFAULT; - p->xmlout = 0; + p->xmlout = BIBL_XMLOUT_FALSE; p->nosplittitle = 0; p->verbose = 0; p->addcount = 0; @@ -87,13 +87,62 @@ TYPE_UNPUBLISHED, /* Unpublished Work */ }; +static void +write_type( FILE *fp, int type ) +{ + switch( type ) { + case TYPE_UNKNOWN: fprintf( fp, "TYPE_UNKNOWN" ); break; + case TYPE_GENERIC: fprintf( fp, "TYPE_GENERIC" ); break; + case TYPE_ARTWORK: fprintf( fp, "TYPE_ARTWORK" ); break; + case TYPE_AUDIOVISUAL: fprintf( fp, "TYPE_AUDIOVISUAL" ); break; + case TYPE_BILL: fprintf( fp, "TYPE_BILL" ); break; + case TYPE_BOOK: fprintf( fp, "TYPE_BOOK" ); break; + case TYPE_INBOOK: fprintf( fp, "TYPE_INBOOK" ); break; + case TYPE_CASE: fprintf( fp, "TYPE_CASE" ); break; + case TYPE_CHARTTABLE: fprintf( fp, "TYPE_CHARITABLE" ); break; + case TYPE_CLASSICALWORK: fprintf( fp, "TYPE_CLASSICALWORK" ); break; + case TYPE_PROGRAM: fprintf( fp, "TYPE_PROGRAM" ); break; + case TYPE_INPROCEEDINGS: fprintf( fp, "TYPE_INPROCEEDINGS" ); break; + case TYPE_PROCEEDINGS: fprintf( fp, "TYPE_PROCEEDINGS" ); break; + case TYPE_EDITEDBOOK: fprintf( fp, "TYPE_EDITEDBOOK" ); break; + case TYPE_EQUATION: fprintf( fp, "TYPE_EQUATION" ); break; + case TYPE_ELECTRONICARTICLE: fprintf( fp, "TYPE_ELECTRONICARTICLE" ); break; + case TYPE_ELECTRONICBOOK: fprintf( fp, "TYPE_ELECTRONICBOOK" ); break; + case TYPE_ELECTRONIC: fprintf( fp, "TYPE_ELECTRONIC" ); break; + case TYPE_FIGURE: fprintf( fp, "TYPE_FIGURE" ); break; + case TYPE_FILMBROADCAST: fprintf( fp, "TYPE_FILMBROADCAST" ); break; + case TYPE_GOVERNMENT: fprintf( fp, "TYPE_GOVERNMENT" ); break; + case TYPE_HEARING: fprintf( fp, "TYPE_HEARING" ); break; + case TYPE_ARTICLE: fprintf( fp, "TYPE_ARTICLE" ); break; + case TYPE_LEGALRULE: fprintf( fp, "TYPE_LEGALRULE" ); break; + case TYPE_MAGARTICLE: fprintf( fp, "TYPE_MAGARTICLE" ); break; + case TYPE_MANUSCRIPT: fprintf( fp, "TYPE_MANUSCRIPT" ); break; + case TYPE_MAP: fprintf( fp, "TYPE_MAP" ); break; + case TYPE_NEWSARTICLE: fprintf( fp, "TYPE_NEWSARTICLE" ); break; + case TYPE_ONLINEDATABASE: fprintf( fp, "TYPE_ONLINEDATABASE" ); break; + case TYPE_ONLINEMULTIMEDIA: fprintf( fp, "TYPE_ONLINEMULTIMEDIA" ); break; + case TYPE_PATENT: fprintf( fp, "TYPE_PATENT" ); break; + case TYPE_COMMUNICATION: fprintf( fp, "TYPE_COMMUNICATION" ); 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_UNPUBLISHED: fprintf( fp, "TYPE_UNPUBLISHED" ); break; + default: fprintf( fp, "Error - type not in enum" );break; + } +} + typedef struct match_type { char *name; int type; } match_type; static int -get_type( fields *info ) +get_type( fields *info, param *p, unsigned long refnum ) { /* Comment out TYPE_GENERIC entries as that is default, but * keep in source as record of mapping decision. */ @@ -107,8 +156,10 @@ /* { "bibliography", TYPE_GENERIC },*/ { "biography", TYPE_BOOK }, { "book", TYPE_BOOK }, +/* { "calendar", TYPE_GENERIC },*/ /* { "catalog", TYPE_GENERIC },*/ { "chart", TYPE_CHARTTABLE }, +/* { "comic or graphic novel", TYPE_GENERIC },*/ /* { "comic strip", TYPE_GENERIC },*/ { "conference publication", TYPE_PROCEEDINGS }, { "database", TYPE_ONLINEDATABASE }, @@ -175,6 +226,7 @@ /* { "slide", TYPE_GENERIC },*/ { "sound", TYPE_AUDIOVISUAL }, /* { "speech", TYPE_GENERIC },*/ +/* { "standard or specification", TYPE_GENERIC },*/ /* { "statistics", TYPE_GENERIC },*/ /* { "survey of literature", TYPE_GENERIC },*/ { "technical drawing", TYPE_ARTWORK }, @@ -201,9 +253,10 @@ }; int nmatch_genres = sizeof( match_genres ) / sizeof( match_genres[0] ); + int i, j, n, maxlevel, type = TYPE_UNKNOWN; char *tag, *data; - int i, j, type = TYPE_UNKNOWN; + /* Determine type from genre information */ for ( i=0; in; ++i ) { tag = info->tag[i].data; if ( strcasecmp( tag, "GENRE" )!=0 && @@ -215,6 +268,12 @@ fields_setused( info, i ); } } + if ( p->verbose ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Type from tag '%s' data '%s': ", info->tag[i].data, info->data[i].data ); + write_type( stderr, type ); + fprintf( stderr, "\n" ); + } if ( type==TYPE_UNKNOWN ) { if ( !strcasecmp( data, "periodical" ) ) type = TYPE_ARTICLE; @@ -231,10 +290,16 @@ if ( type!=TYPE_UNKNOWN ) fields_setused( info, i ); } /* the inbook type should be defined if 'book' in host */ - if ( type==TYPE_BOOK && info->level[i]!=0 ) type = TYPE_INBOOK; - /* the article types should be defined if it's the host */ - if ( ( type==TYPE_ARTICLE || type==TYPE_MAGARTICLE || type==TYPE_NEWSARTICLE ) && info->level[i]<1 ) type=TYPE_UNKNOWN; + if ( type==TYPE_BOOK && info->level[i]>0 ) type = TYPE_INBOOK; } + if ( p->verbose ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Type from genre element: " ); + write_type( stderr, type ); + fprintf( stderr, "\n" ); + } + + /* Determine from resource information */ if ( type==TYPE_UNKNOWN ) { for ( i=0; in; ++i ) { if ( strcasecmp( info->tag[i].data, "RESOURCE" ) ) @@ -246,10 +311,54 @@ type = TYPE_PROGRAM; if ( type!=TYPE_UNKNOWN ) fields_setused( info, i ); } + if ( p->verbose ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Type from resource element: " ); + write_type( stderr, type ); + fprintf( stderr, "\n" ); + } } - /* default to generic */ - if ( type==TYPE_UNKNOWN ) type = TYPE_GENERIC; + /* Determine from issuance information */ + if ( type==TYPE_UNKNOWN ) { + for ( i=0; in; ++i ) { + if ( strcasecmp( info->tag[i].data, "ISSUANCE" ) ) + continue; + data = info->data[i].data; + if ( !strcasecmp( data, "monographic" ) ) { + if ( info->level[i]==0 ) type = TYPE_BOOK; + else type = TYPE_INBOOK; + } + } + if ( p->verbose ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Type from issuance element: " ); + write_type( stderr, type ); + fprintf( stderr, "\n" ); + } + } + + /* default to generic or book chapter, depending on maxlevel */ + if ( type==TYPE_UNKNOWN ) { + maxlevel = fields_maxlevel( info ); + 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 ); + if ( n!=-1 ) + fprintf( stderr, " %s", info->data[n].data ); + fprintf( stderr, " (defaulting to generic)\n" ); + type = TYPE_GENERIC; + } + } + + if ( p->verbose ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Final type: " ); + write_type( stderr, type ); + fprintf( stderr, "\n" ); + } return type; } @@ -524,7 +633,7 @@ fields_clearused( info ); - type = get_type( info ); + type = get_type( info, p, refnum ); output_type( fp, type, p ); @@ -597,6 +706,7 @@ output_easyall( fp, info, "KEYWORD", "%K", LEVEL_ANY ); output_easyall( fp, info, "NGENRE", "%9", LEVEL_ANY ); output_thesishint( fp, type ); + output_easyall( fp, info, "DOI", "%R", LEVEL_ANY ); output_easyall( fp, info, "URL", "%U", LEVEL_ANY ); output_easyall( fp, info, "FILEATTACH", "%U", LEVEL_ANY ); output_doi( fp, info ); diff --git a/bibutils/endxmlin.c b/bibutils/endxmlin.c --- a/bibutils/endxmlin.c +++ b/bibutils/endxmlin.c @@ -1,7 +1,7 @@ /* * endxmlin.c * - * Copyright (c) Chris Putnam 2006-2013 + * Copyright (c) Chris Putnam 2006-2014 * * Program and source code released under the GPL version 2 * @@ -23,6 +23,9 @@ char *internal; } attribs; +/***************************************************** + PUBLIC: void endxmlin_initparams() +*****************************************************/ void endxmlin_initparams( param *p, const char *progname ) { @@ -52,6 +55,10 @@ else p->progname = strdup( progname ); } +/***************************************************** + PUBLIC: int endxmlin_readf() +*****************************************************/ + static int xml_readmore( FILE *fp, char *buf, int bufsize, int *bufpos ) { @@ -110,6 +117,10 @@ return haveref; } +/***************************************************** + PUBLIC: int endxmlin_processf() +*****************************************************/ + /* * add data to fields */ @@ -127,26 +138,39 @@ * * */ -void +static int endxmlin_datar( xml *node, newstr *s ) { - if ( node->value && node->value->len ) + int status; + if ( node->value && node->value->len ) { newstr_strcat( s, node->value->data ); - if ( node->down && xml_tagexact( node->down, "style" ) ) - endxmlin_datar( node->down, s ); - if ( xml_tagexact( node, "style" ) && node->next ) - endxmlin_datar( node->next, s ); + if ( newstr_memerr( s ) ) return BIBL_ERR_MEMERR; + } + if ( node->down && xml_tagexact( node->down, "style" ) ) { + status = endxmlin_datar( node->down, s ); + if ( status!=BIBL_OK ) return status; + } + if ( xml_tagexact( node, "style" ) && node->next ) { + status = endxmlin_datar( node->next, s ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } -void +static int endxmlin_data( xml *node, char *inttag, fields *info, int level ) { + int status; newstr s; newstr_init( &s ); - endxmlin_datar( node, &s ); - if ( s.len ) - fields_add( info, inttag, s.data, level ); + status = endxmlin_datar( node, &s ); + if ( status!=BIBL_OK ) return status; + if ( s.len ) { + status = fields_add( info, inttag, s.data, level ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } newstr_free( &s ); + return BIBL_OK; } /* @@ -155,7 +179,7 @@ * * */ -void +static int endxmlin_titles( xml *node, fields *info ) { attribs a[] = { @@ -165,20 +189,26 @@ { "alt-title", "%!" }, { "short-title", "SHORTTITLE" }, }; - int i, n = sizeof( a ) / sizeof ( a[0] ); + int i, status, n = sizeof( a ) / sizeof ( a[0] ); newstr title; newstr_init( &title ); for ( i=0; idown ) { newstr_empty( &title ); - endxmlin_datar( node, &title ); + status = endxmlin_datar( node, &title ); + if ( status!=BIBL_OK ) return BIBL_ERR_MEMERR; newstr_trimstartingws( &title ); newstr_trimendingws( &title ); - fields_add( info, a[i].internal, title.data, 0); + status = fields_add( info, a[i].internal, title.data, 0); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } } - if ( node->next ) endxmlin_titles( node->next, info ); + if ( node->next ) { + status = endxmlin_titles( node->next, info ); + if ( status!=BIBL_OK ) return status; + } newstr_free( &title ); + return BIBL_OK; } /* @@ -202,65 +232,84 @@ * > * */ -void +static int endxmlin_contributor( xml *node, fields *info, char *int_tag, int level ) { - endxmlin_data( node, int_tag, info, level ); - if ( node->next ) - endxmlin_contributor( node->next, info, int_tag, level ); + int status; + status = endxmlin_data( node, int_tag, info, level ); + if ( status!=BIBL_OK ) return status; + if ( node->next ) { + status = endxmlin_contributor( node->next, info, int_tag, level ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } -static void +static int endxmlin_contributors( xml *node, fields *info ) { - attribs contrib[] = { + attribs a[] = { { "authors", "%A" }, { "secondary-authors", "%E" }, { "tertiary-authors", "%Y" }, { "subsidiary-authors", "%?" }, { "translated-authors", "%?" }, }; - int i, n = sizeof( contrib ) / sizeof ( contrib[0] ); + int i, status, n = sizeof( a ) / sizeof ( a[0] ); for ( i=0; idown ) - endxmlin_contributor( node->down, info, contrib[i].internal, 0 ); + if ( xml_tagexact( node, a[i].attrib ) && node->down ) { + status = endxmlin_contributor( node->down, info, a[i].internal, 0 ); + if ( status!=BIBL_OK ) return status; + } } - if ( node->next ) - endxmlin_contributors( node->next, info ); + if ( node->next ) { + status = endxmlin_contributors( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } -static void +static int endxmlin_keyword( xml *node, fields *info ) { - if ( xml_tagexact( node, "keyword" ) ) - endxmlin_data( node, "%K", info, 0 ); - if ( node->next ) - endxmlin_keyword( node->next, info ); + int status; + if ( xml_tagexact( node, "keyword" ) ) { + status = endxmlin_data( node, "%K", info, 0 ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) { + status = endxmlin_keyword( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } -static void +static int endxmlin_keywords( xml *node, fields *info ) { if ( node->down && xml_tagexact( node->down, "keyword" ) ) - endxmlin_keyword( node->down, info ); + return endxmlin_keyword( node->down, info ); + return BIBL_OK; } /* * */ -static void +static int endxmlin_ern( xml *node, fields *info ) { if ( xml_tagexact( node, "electronic-resource-num" ) ) - endxmlin_data( node, "DOI", info, 0 ); + return endxmlin_data( node, "DOI", info, 0 ); + return BIBL_OK; } -static void +static int endxmlin_language( xml *node, fields *info ) { if ( xml_tagexact( node, "language" ) ) - endxmlin_data( node, "%G", info, 0 ); + return endxmlin_data( node, "%G", info, 0 ); + return BIBL_OK; } /* @@ -270,77 +319,108 @@ * * */ -static void +static int endxmlin_fileattach( xml *node, fields *info ) { - if ( xml_tagexact( node, "url" ) ) - endxmlin_data( node, "FILEATTACH", info, 0 ); - if ( node->down ) endxmlin_fileattach( node->down, info ); - if ( node->next ) endxmlin_fileattach( node->next, info ); + int status; + if ( xml_tagexact( node, "url" ) ) { + status = endxmlin_data( node, "FILEATTACH", info, 0 ); + if ( status!=BIBL_OK ) return status; + } + if ( node->down ) { + status = endxmlin_fileattach( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) { + status = endxmlin_fileattach( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } -static void +static int endxmlin_urls( xml *node, fields *info ) { - if ( xml_tagexact( node, "pdf-urls" ) && node->down ) - endxmlin_fileattach( node->down, info ); - else if ( xml_tagexact( node, "url" ) ) - endxmlin_data( node, "%U", info, 0 ); - else { + int status; + if ( xml_tagexact( node, "pdf-urls" ) && node->down ) { + status = endxmlin_fileattach( node->down, info ); + if ( status!=BIBL_OK ) return status; + } else if ( xml_tagexact( node, "url" ) ) { + status = endxmlin_data( node, "%U", info, 0 ); + if ( status!=BIBL_OK ) return status; + } else { if ( node->down ) { if ( xml_tagexact( node->down, "related-urls" ) || xml_tagexact( node->down, "pdf-urls" ) || - xml_tagexact( node->down, "url" ) ) - endxmlin_urls( node->down, info ); + xml_tagexact( node->down, "url" ) ) { + status = endxmlin_urls( node->down, info ); + if ( status!=BIBL_OK ) return status; + } } } - if ( node->next ) - endxmlin_urls( node->next, info ); + if ( node->next ) { + status = endxmlin_urls( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } -static void +static int endxmlin_pubdates( xml *node, fields *info ) { if ( xml_tagexact( node, "date" ) ) - endxmlin_data( node, "%8", info, 0 ); + return endxmlin_data( node, "%8", info, 0 ); else { if ( node->down && xml_tagexact( node->down, "date" ) ) - endxmlin_pubdates( node->down, info ); + return endxmlin_pubdates( node->down, info ); } + return BIBL_OK; } -static void +static int endxmlin_dates( xml *node, fields *info ) { - if ( xml_tagexact( node, "year" ) ) - endxmlin_data( node, "%D", info, 0 ); - else { + int status; + if ( xml_tagexact( node, "year" ) ) { + status = endxmlin_data( node, "%D", info, 0 ); + if ( status!=BIBL_OK ) return status; + } else { if ( node->down ) { - if ( xml_tagexact( node->down, "year" ) ) - endxmlin_dates( node->down, info ); - if ( xml_tagexact( node->down, "pub-dates" ) ) - endxmlin_pubdates( node->down, info ); + if ( xml_tagexact( node->down, "year" ) ) { + status = endxmlin_dates( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( xml_tagexact( node->down, "pub-dates" ) ) { + status = endxmlin_pubdates( node->down, info ); + if ( status!=BIBL_OK ); + } } } - if ( node->next ) - endxmlin_dates( node->next, info ); + if ( node->next ) { + status = endxmlin_dates( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } /* * 17 */ -static void +static int endxmlin_reftype( xml *node, fields *info ) { + int status; newstr *s; s = xml_getattrib( node, "name" ); - if ( s && s->dim ) { - fields_add( info, "%0", s->data, 0 ); + if ( s && s->len ) { + status = fields_add( info, "%0", s->data, 0 ); newstr_free( s ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } + return BIBL_OK; } -static void +static int endxmlin_record( xml *node, fields *info ) { attribs a[] = { @@ -369,28 +449,35 @@ { "custom5", "%#" }, { "custom6", "%$" }, }; - int i, n = sizeof ( a ) / sizeof( a[0] ); + int i, status, n = sizeof ( a ) / sizeof( a[0] ); if ( xml_tagexact( node, "DATABASE" ) ) { -/* endxmlin_database( node, info );*/ } else if ( xml_tagexact( node, "SOURCE-APP" ) ) { -/* endxmlin_sourceapp( node, info );*/ } else if ( xml_tagexact( node, "REC-NUMBER" ) ) { } else if ( xml_tagexact( node, "ref-type" ) ) { - endxmlin_reftype( node, info ); + status = endxmlin_reftype( node, info ); + if ( status!=BIBL_OK ) return status; } else if ( xml_tagexact( node, "contributors" ) ) { - if ( node->down ) endxmlin_contributors( node->down, info ); + if ( node->down ) { + status = endxmlin_contributors( node->down, info ); + if ( status!=BIBL_OK ) return status; + } } else if ( xml_tagexact( node, "titles" ) ) { if ( node->down ) endxmlin_titles( node->down, info ); } else if ( xml_tagexact( node, "keywords" ) ) { - endxmlin_keywords( node, info ); + status = endxmlin_keywords( node, info ); + if ( status!=BIBL_OK ) return status; } else if ( xml_tagexact( node, "urls" ) ) { - endxmlin_urls( node, info ); + status = endxmlin_urls( node, info ); + if ( status!=BIBL_OK ) return status; } else if ( xml_tagexact( node, "electronic-resource-num" ) ) { - endxmlin_ern( node, info ); + status = endxmlin_ern( node, info ); + if ( status!=BIBL_OK ) return status; } else if ( xml_tagexact( node, "dates" ) ) { - endxmlin_dates( node, info ); + status = endxmlin_dates( node, info ); + if ( status!=BIBL_OK ) return status; } else if ( xml_tagexact( node, "language" ) ) { - endxmlin_language( node, info ); + status = endxmlin_language( node, info ); + if ( status!=BIBL_OK ) return status; } else if ( xml_tagexact( node, "periodical" ) ) { } else if ( xml_tagexact( node, "secondary-volume" ) ) { } else if ( xml_tagexact( node, "secondary-issue" ) ) { @@ -419,22 +506,33 @@ } else if ( xml_tagexact( node, "misc3" ) ) { } else { for ( i=0; inext ) endxmlin_record( node->next, info ); + if ( node->next ) { + status = endxmlin_record( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } -static void +static int endxmlin_assembleref( xml *node, fields *info ) { + int status; if ( node->tag->len==0 ) { - if ( node->down ) endxmlin_assembleref( node->down, info ); - return; + if ( node->down ) + return endxmlin_assembleref( node->down, info ); } else if ( xml_tagexact( node, "RECORD" ) ) { - if ( node->down ) endxmlin_record( node->down, info ); + if ( node->down ) { + status = endxmlin_record( node->down, info ); + if ( status!=BIBL_OK ) return status; + } } + return BIBL_OK; } /* endxmlin_processf first operates by converting to endnote input @@ -446,10 +544,14 @@ int endxmlin_processf( fields *fin, char *data, char *filename, long nref ) { + int status; xml top; + xml_init( &top ); xml_tree( data, &top ); - endxmlin_assembleref( &top, fin ); + status = endxmlin_assembleref( &top, fin ); xml_free( &top ); - return 1; + + if ( status==BIBL_OK ) return 1; + return 0; } diff --git a/bibutils/endxmlin.h b/bibutils/endxmlin.h --- a/bibutils/endxmlin.h +++ b/bibutils/endxmlin.h @@ -1,7 +1,7 @@ /* * endxmlin.h * - * Copyright (c) Chris Putnam 2006-2013 + * Copyright (c) Chris Putnam 2006-2014 * * 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 @@ -10,7 +10,6 @@ #include #include #include -#include #include "fields.h" fields* @@ -24,8 +23,6 @@ void fields_init( fields *f ) { - assert( f ); - f->used = NULL; f->level = NULL; f->tag = NULL; @@ -38,8 +35,6 @@ { int i; - assert( f ); - for ( i=0; imax; ++i ) { newstr_free( &(f->tag[i]) ); newstr_free( &(f->data[i]) ); @@ -67,7 +62,7 @@ if ( f->used ) free( f->used ); if ( f->level ) free( f->level ); fields_init( f ); - return 0; + return FIELDS_ERR; } f->max = alloc; @@ -76,7 +71,7 @@ newstr_init( &(f->tag[i]) ); newstr_init( &(f->data[i]) ); } - return 1; + return FIELDS_OK; } static int @@ -97,7 +92,7 @@ if ( newlevel ) f->level = newlevel; if ( !newtags || !newdata || !newused || !newlevel ) - return 0; + return FIELDS_ERR; f->max = alloc; @@ -106,22 +101,22 @@ newstr_init( &(f->data[i]) ); } - return 1; + return FIELDS_OK; } int fields_add( fields *f, char *tag, char *data, int level ) { - int i, found; - - assert( f ); + int i, status, found; - if ( !tag || !data ) return 1; + if ( !tag || !data ) return FIELDS_OK; if ( f->max==0 ) { - if ( !fields_alloc( f ) ) return 0; + status = fields_alloc( f ); + if ( status!=FIELDS_OK ) return status; } else if ( f->n >= f->max ) { - if ( !fields_realloc( f ) ) return 0; + status = fields_realloc( f ); + if ( status!=FIELDS_OK ) return status; } /* Don't duplicate identical entries */ @@ -132,13 +127,16 @@ !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 ); - f->used[ f->n ] = 0; - f->level[ f->n ] = level; + if ( newstr_memerr( &(f->tag[f->n]) ) || + newstr_memerr( &(f->data[f->n] ) ) ) + return FIELDS_ERR; f->n++; } - return 1; + return FIELDS_OK; } int @@ -148,44 +146,26 @@ newstr newtag; int ret; - assert( f ); - assert( tag ); - assert( suffix ); - newstr_init( &newtag ); newstr_mergestrs( &newtag, tag, suffix, NULL ); - ret = fields_add( f, newtag.data, data, level ); + if ( newstr_memerr( &newtag ) ) ret = FIELDS_ERR; + else ret = fields_add( f, newtag.data, data, level ); newstr_free( &newtag ); return ret; } -/* fields_get_level() - * - */ -inline int -fields_get_level( fields *f, int n ) -{ - assert( f ); - assert( n>=0 ); - assert( nn ); - - return f->level[n]; -} - /* fields_match_level() * * returns 1 if level matched, 0 if not * - * level==-1 is a special flag meaning any level can match + * level==LEVEL_ANY is a special flag meaning any level can match */ inline int fields_match_level( fields *f, int n, int level ) { - assert( f ); - if ( level==LEVEL_ANY ) return 1; - if ( fields_get_level( f, n )==level ) return 1; + if ( fields_level( f, n )==level ) return 1; return 0; } @@ -232,9 +212,6 @@ { int i; - assert( f ); - assert( tag ); - for ( i=0; in; ++i ) { if ( !fields_match_casetag_level( f, i, tag, level ) ) continue; @@ -254,11 +231,12 @@ { int i, max = 0; - assert( f ); - - for ( i=0; in; ++i ) { - if ( f->level[i] > max ) - max = f->level[i]; + if ( f->n ) { + max = f->level[0]; + for ( i=1; in; ++i ) { + if ( f->level[i] > max ) + max = f->level[i]; + } } return max; @@ -269,8 +247,6 @@ { int i; - assert( f ); - for ( i=0; in; ++i ) f->used[i] = 0; } @@ -278,15 +254,13 @@ void fields_setused( fields *f, int n ) { - assert( f ); - - if ( n < f->n ) + if ( n >= 0 && n < f->n ) f->used[n] = 1; } /* fields_replace_or_add() * - * return 1 on success, 0 on memory error + * return FIELDS_OK on success, FIELDS_ERR on memory error */ int fields_replace_or_add( fields *f, char *tag, char *data, int level ) @@ -295,7 +269,8 @@ if ( n==-1 ) return fields_add( f, tag, data, level ); else { newstr_strcpy( &(f->data[n]), data ); - return 1; + if ( newstr_memerr( &(f->data[n]) ) ) return FIELDS_ERR; + return FIELDS_OK; } } @@ -304,7 +279,7 @@ inline int fields_used( fields *f, int n ) { - if ( n < f->n ) return f->used[n]; + if ( n >= 0 && n < f->n ) return f->used[n]; else return 0; } @@ -312,7 +287,7 @@ fields_nodata( fields *f, int n ) { newstr *d; - if ( n < f->n ) { + if ( n >= 0 && n < f->n ) { d = &( f->data[n] ); if ( d->len > 0 ) return 0; return 1; @@ -324,7 +299,6 @@ inline int fields_num( fields *f ) { - assert( f ); return f->n; } @@ -346,9 +320,7 @@ { intptr_t retn; - assert( f ); - assert( n >= 0 ); - assert( n < f->n ); + if ( n<0 || n>= f->n ) return NULL; if ( mode & FIELDS_SETUSE_FLAG ) fields_setused( f, n ); @@ -371,9 +343,7 @@ { intptr_t retn; - assert( f ); - assert( n >= 0 ); - assert( n < f->n ); + if ( n<0 || n>= f->n ) return NULL; if ( mode & FIELDS_STRP_FLAG ) return &(f->tag[n]); @@ -391,10 +361,7 @@ int fields_level( fields *f, int n ) { - assert( f ); - assert( n >= 0 ); - assert( n < f->n ); - + if ( n<0 || n>= f->n ) return 0; return f->level[n]; } @@ -404,9 +371,6 @@ int i, found = -1; intptr_t retn; - assert( f ); - assert( tag ); - for ( i=0; in && found==-1; ++i ) { if ( !fields_match_level( f, i, level ) ) continue; @@ -442,8 +406,6 @@ char *tag, *value; va_list argp; - assert( f ); - va_start( argp, mode ); while ( ( tag = ( char * ) va_arg( argp, char * ) ) ) { value = fields_findv( f, level, mode, tag ); @@ -462,10 +424,7 @@ { intptr_t retn; - assert( a ); - assert( f ); - assert( n >= 0 ); - assert( n < f->n ); + if ( n<0 || n>= f->n ) return; if ( mode & FIELDS_SETUSE_FLAG ) fields_setused( f, n ); @@ -485,10 +444,6 @@ { int i; - assert( a ); - assert( tag ); - assert( f ); - for ( i=0; in; ++i ) { if ( !fields_match_level( f, i, level ) ) continue; @@ -514,9 +469,6 @@ vplist tags; char *tag; int i, j, found; - - assert( f ); - assert( a ); vplist_init( &tags ); diff --git a/bibutils/fields.h b/bibutils/fields.h --- a/bibutils/fields.h +++ b/bibutils/fields.h @@ -1,7 +1,7 @@ /* * fields.h * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2014 * * Source code released under the GPL version 2 * @@ -9,6 +9,9 @@ #ifndef FIELDS_H #define FIELDS_H +#define FIELDS_OK (1) +#define FIELDS_ERR (0) + #define LEVEL_ANY (-1) #define LEVEL_MAIN (0) #define LEVEL_HOST (1) @@ -45,7 +48,6 @@ 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 ); -extern inline int fields_get_level( fields *f, int n ); extern inline int fields_match_level( fields *f, int n, int level ); extern inline int fields_match_tag( fields *f, int n, char *tag ); diff --git a/bibutils/intlist.c b/bibutils/intlist.c --- a/bibutils/intlist.c +++ b/bibutils/intlist.c @@ -3,6 +3,8 @@ * * Copyright (c) Chris Putnam 2007-2013 * + * Version 9/5/2013 + * * Source code released under the GPL version 2 * * Implements a simple managed array of ints @@ -10,55 +12,75 @@ */ #include "intlist.h" -static void -memerr( const char *f ) -{ - fprintf( stderr, "Memory error in %s\n", f ); - exit( EXIT_FAILURE ); -} - -static void +static int intlist_alloc( intlist *il ) { int alloc = 20, i; il->data = ( int * ) malloc( sizeof( int ) * alloc ); - if ( !(il->data) ) memerr( __FUNCTION__ ); + if ( !(il->data) ) return 0; for ( i=0; idata[i] = 0; il->max = alloc; il->n = 0; + return 1; } -static void +static int intlist_realloc( intlist *il ) { int *more; int alloc = il->max * 2, i; more = ( int * ) realloc( il->data, sizeof( int ) * alloc ); - if ( !more ) memerr( __FUNCTION__ ); + if ( !more ) return 0; il->data = more; for ( i=il->max; idata[i] = 0; il->max = alloc; + return 1; } +/* intlist_add() + * + * Returns position of newly added value in range [0,n), -1 on error + */ int intlist_add( intlist *il, int value ) { - if ( il->max==0 ) intlist_alloc( il ); - else if ( il->n >= il->max ) intlist_realloc( il ); + if ( il->max==0 ) { + if ( !intlist_alloc( il ) ) return -1; + } else if ( il->n >= il->max ) { + if ( !intlist_realloc( il ) ) return -1; + } il->data[ il->n ] = value; il->n++; return il->n - 1; } +/* intlist_add_unique() + * + * Returns position of newly added (or previously added) value + * Returns -1 on (memory) error + */ int intlist_add_unique( intlist *il, int value ) { - if ( intlist_find( il, value )!=-1 ) return il->n - 1; - else return intlist_add( il, value ); + int n; + n = intlist_find( il, value ); + if ( n==-1 ) + n = intlist_add( il, value ); + return n; } +int +intlist_find_or_add( intlist *il, int value ) +{ + return intlist_add_unique( il, value ); +} +/* intlist_find() + * + * Returns position of value in range [0,n), or -1 if + * value cannot be found + */ int intlist_find( intlist *il, int value ) { @@ -68,7 +90,6 @@ return -1; } -/* Here we know that pos is valid */ static void intlist_remove_pos_core( intlist *il, int pos ) { @@ -78,32 +99,30 @@ il->n -= 1; } -void +/* intlist_remove_pos() + * + * Returns 1 on success, 0 on failure. + */ +int intlist_remove_pos( intlist *il, int pos ) { - if ( pos < 0 || pos >= il->n ) return; + if ( pos < 0 || pos >= il->n ) return 0; intlist_remove_pos_core( il, pos ); + return 1; } -void +/* intlist_remove() + * + * Removes first instance of value from the intlist. + * Returns 1 on success, 0 on error. + */ +int intlist_remove( intlist *il, int value ) { int pos = intlist_find( il, value ); - if ( pos==-1 ) return; + if ( pos==-1 ) return 0; intlist_remove_pos_core( il, pos ); -} - -/* Return the index of searched-for string. - * If cannot find string, add to list and then - * return the index - */ -int -intlist_find_or_add( intlist *il, int value ) -{ - int n = intlist_find( il, value ); - if ( n==-1 ) - n = intlist_add( il, value ); - return n; + return 1; } /* don't actually free space, just reset counter */ @@ -121,6 +140,13 @@ } void +intlist_delete( intlist *il ) +{ + intlist_free( il ); + free( il ); +} + +void intlist_init( intlist *il ) { il->data = NULL; @@ -128,15 +154,28 @@ il->n = 0; } -void +/* intlist_init_range() + * + * Initializes intlist to values from [low,high) with step step. + * Returns -1 on failure, number of elements on success. + */ +int intlist_init_range( intlist *il, int low, int high, int step ) { - int i; + int i, n; intlist_init( il ); - for ( i=low; in; } +/* intlist_new() + * + * Allocates an empty intlist. + * Returns pointer to intlist on success, NULL on memory error. + */ intlist * intlist_new( void ) { @@ -145,11 +184,25 @@ 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; + */ intlist * intlist_new_range( int low, int high, int step ) { - intlist *il = ( intlist * ) malloc( sizeof( intlist ) ); - if ( il ) intlist_init_range( il, low, high, step ); + intlist *il; + int n; + il = ( intlist * ) malloc( sizeof( intlist ) ); + if ( il ) { + n = intlist_init_range( il, low, high, step ); + if ( n==-1 ) { + intlist_free( il ); + free( il ); + il = NULL; + } + } return il; } @@ -198,47 +251,66 @@ } } -void +/* Returns 1 on success, 0 on error */ +int intlist_copy( intlist *to, intlist *from ) { int i; intlist_free( to ); to->data = ( int* ) malloc( sizeof( int ) * from->n ); - if ( !to->data ) return; + if ( !to->data ) return 0; to->n = to->max = from->n; for ( i=0; in; ++i ) to->data[i] = from->data[i]; + return 1; } +/* Returns pointer on success, NULL on error */ intlist * intlist_dup( intlist *il ) { intlist *l; - l = ( intlist* ) malloc( sizeof( intlist ) ); - if ( !l ) goto err0; - intlist_copy( l, il ); - return l; - free( l ); -err0: + int n; + + l = intlist_new(); + if ( l ) { + n = intlist_copy( l, il ); + if ( !n ) { + intlist_delete( l ); + l = NULL; + } + } + return l; } -void +int intlist_append( intlist *to, intlist *from ) { - int i; - for ( i=0; in; ++i ) - intlist_add( to, from->data[i] ); + 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; + } + } + return to->n; } -void +int intlist_append_unique( intlist *to, intlist *from ) { - int i; + int i, n, nsave = to->n; for ( i=0; in; ++i ) { if ( intlist_find( to, from->data[i] )!=-1 ) continue; - intlist_add( to, from->data[i] ); + n = intlist_add( to, from->data[i] ); + if ( n==-1 ) { + to->n = nsave; + return -1; + } } + return to->n; } int @@ -248,3 +320,55 @@ else return il->data[pos]; } +/* intlist_set() + * + * Returns 1 on success, 0 on failure + */ +int +intlist_set( intlist *il, int pos, int value ) +{ + if ( pos<0 || pos>=il->n ) return 0; + il->data[pos] = value; + return 1; +} + +float +intlist_median( intlist *il ) +{ + intlist *tmp; + float median; + int m1, m2; + + if ( il->n==0 ) return 0.0; + + tmp = intlist_dup( il ); + if ( !tmp ) return 0.0; + + intlist_sort( tmp ); + + if ( tmp->n % 2 == 1 ) { + median = intlist_get( tmp, tmp->n / 2 ); + } else { + m1 = intlist_get( tmp, tmp->n / 2 ); + m2 = intlist_get( tmp, tmp->n / 2 + 1); + median = ( m1 + m2 ) / 2.0; + } + + intlist_delete( tmp ); + + return median; +} + +float +intlist_mean( intlist *il ) +{ + float sum = 0.0; + int i; + + if ( il->n==0 ) return 0.0; + + for ( i=0; in; ++i ) + sum += intlist_get( il, i ); + + return sum / il->n; +} diff --git a/bibutils/intlist.h b/bibutils/intlist.h --- a/bibutils/intlist.h +++ b/bibutils/intlist.h @@ -3,6 +3,8 @@ * * Copyright (c) Chris Putnam 2007-2013 * + * Version 9/5/2013 + * * Source code released under the GPL version 2 * */ @@ -18,23 +20,27 @@ int *data; } intlist; -extern void intlist_init( intlist *info ); -extern void intlist_init_range( intlist *info, 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_sort( intlist *info ); -extern void intlist_randomize( intlist *info ); -extern int intlist_add( intlist *info, int value ); -extern int intlist_add_unique( intlist *info, int value ); -extern int intlist_find( intlist *info, int searchvalue ); -extern int intlist_find_or_add( intlist *info, int searchvalue ); -extern void intlist_empty( intlist *info ); -extern void intlist_free( intlist *info ); -extern void intlist_copy( intlist *to, intlist *from ); -extern int intlist_get( intlist *info, int pos ); -extern void intlist_remove( intlist *info, int searchvalue ); -extern void intlist_remove_pos( intlist *info, int pos ); -extern void intlist_append( intlist *to, intlist *from ); -extern void intlist_append_unique( intlist *to, intlist *from ); +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 ); #endif diff --git a/bibutils/isiin.c b/bibutils/isiin.c --- a/bibutils/isiin.c +++ b/bibutils/isiin.c @@ -19,6 +19,9 @@ #include "reftypes.h" #include "isiin.h" +/***************************************************** + PUBLIC: void isiin_initparams() +*****************************************************/ void isiin_initparams( param *p, const char *progname ) { @@ -48,6 +51,10 @@ else p->progname = strdup( progname ); } +/***************************************************** + PUBLIC: int isiin_readf() +*****************************************************/ + /* ISI definition of a tag is strict: * char 1 = uppercase alphabetic character * char 2 = uppercase alphabetic character or digit @@ -116,6 +123,10 @@ return haveref; } +/***************************************************** + PUBLIC: int isiin_processf() +*****************************************************/ + static char * process_isiline( newstr *tag, newstr *data, char *p ) { @@ -138,56 +149,48 @@ int isiin_processf( fields *isiin, char *p, char *filename, long nref ) { + int status, n, ret = 1; newstr tag, data; - int n; newstrs_init( &tag, &data, 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 ) ) { - fields_add( isiin, tag.data, data.data, 0 ); + status = fields_add( isiin, tag.data, data.data, 0 ); + if ( status!=FIELDS_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") ){ - fields_add( isiin, "AU", data.data, 0); + status = fields_add( isiin, "AU", data.data, 0); + if ( status!=FIELDS_OK ) ret = 0; } else if ( !strcmp( isiin->tag[n-1].data,"AF") ){ - fields_add( isiin, "AF", data.data, 0); + 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; } } } +out: newstrs_free( &data, &tag, NULL ); - return 1; -} - -static int -keyword_process( fields *info, char *newtag, char *p, int level ) -{ - newstr keyword; - int ok; - newstr_init( &keyword ); - while ( *p ) { - p = skip_ws( p ); - while ( *p && *p!=';' ) newstr_addchar( &keyword, *p++ ); - if ( keyword.len ) { - ok = fields_add( info, newtag, keyword.data, level ); - if ( !ok ) return 0; - newstr_empty( &keyword ); - } - if ( *p==';' ) p++; - } - newstr_free( &keyword ); - return 1; + return ret; } +/***************************************************** + PUBLIC: int isiin_typef() +*****************************************************/ int isiin_typef( fields *isiin, char *filename, int nref, param *p, variants *all, int nall ) { @@ -203,6 +206,29 @@ return reftype; } +/***************************************************** + 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 ) @@ -228,9 +254,9 @@ level = ((all[reftype]).tags[n]).level; newtag = all[reftype].tags[n].newstr; ok = name_add( info, newtag, d->data, level, asis, corps ); - if ( !ok ) return 0; + if ( !ok ) return BIBL_ERR_MEMERR; } - return 1; + return BIBL_OK; } static void @@ -242,15 +268,23 @@ } } +static int +isiin_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 isiin_convertf( fields *isiin, fields *info, int reftype, param *p, variants *all, int nall ) { - int process, level, i, n, nfields, ok; + int process, level, i, n, nfields, ok, status; newstr *t, *d; char *newtag; - ok = isiin_addauthors( isiin, info, reftype, all, nall, &(p->asis), &(p->corps) ); - if ( !ok ) return BIBL_ERR_MEMERR; + status = isiin_addauthors( isiin, info, reftype, all, nall, &(p->asis), &(p->corps) ); + if ( status!=BIBL_OK ) return status; nfields = fields_num( isiin ); for ( i=0; idata, level ); - break; - case DATE: - ok = fields_add( info, newtag, d->data, level ); + 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: - ok = keyword_process( info, newtag, d->data, level ); + 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: - ok = 1; + status = BIBL_OK; break; } - /* do nothing if process==TYPE || process==ALWAYS */ - - if ( !ok ) return BIBL_ERR_MEMERR; + if ( status!=BIBL_OK ) return status; } - return BIBL_OK; + return status; } diff --git a/bibutils/isiout.c b/bibutils/isiout.c --- a/bibutils/isiout.c +++ b/bibutils/isiout.c @@ -27,7 +27,7 @@ p->latexout = 0; p->utf8out = BIBL_CHARSET_UTF8_DEFAULT; p->utf8bom = BIBL_CHARSET_BOM_DEFAULT; - p->xmlout = 0; + p->xmlout = BIBL_XMLOUT_FALSE; p->nosplittitle = 0; p->verbose = 0; p->addcount = 0; diff --git a/bibutils/iso639_1.c b/bibutils/iso639_1.c new file mode 100644 --- /dev/null +++ b/bibutils/iso639_1.c @@ -0,0 +1,211 @@ +/* + * iso639_1.c + */ +#include +#include "iso639_1.h" + +typedef struct { + char *code; + char *language; +} iso639_1_t; + +static iso639_1_t iso639_1[] = { + { "aa", "Afar" }, + { "ab", "Abkhazian" }, + { "ae", "Avestan" }, + { "af", "Afrikaans" }, + { "ak", "Akan" }, + { "am", "Amharic" }, + { "an", "Aragonese" }, + { "ar", "Arabic" }, + { "as", "Assamese" }, + { "av", "Avaric" }, + { "ay", "Aymara" }, + { "az", "Azerbaijani" }, + { "ba", "Bashkir" }, + { "be", "Belarusian" }, + { "bg", "Bulgarian" }, + { "bh", "Bihari languages" }, + { "bi", "Bislama" }, + { "bm", "Bambara" }, + { "bn", "Bengali" }, + { "bo", "Tibetan" }, + { "br", "Breton" }, + { "bs", "Bosnian" }, + { "ca", "Catalan" }, + { "ce", "Chechen" }, + { "ch", "Chamorro" }, + { "co", "Corsican" }, + { "cr", "Cree" }, + { "cs", "Czech" }, + { "cu", "Church Slavic" }, + { "cv", "Chuvash" }, + { "cy", "Welsh" }, + { "da", "Danish" }, + { "de", "German" }, + { "dv", "Dhivehi" }, + { "dz", "Dzongkha" }, + { "ee", "Ewe" }, + { "el", "Modern Greek" }, + { "en", "English" }, + { "eo", "Esperanto" }, + { "es", "Spanish" }, + { "et", "Estonian" }, + { "eu", "Basque" }, + { "fa", "Persian" }, + { "ff", "Fulah" }, + { "fi", "Finnish" }, + { "fj", "Fijian" }, + { "fo", "Faroese" }, + { "fr", "French" }, + { "fy", "Western Frisian" }, + { "ga", "Irish" }, + { "gd", "Scottish Gaelic" }, + { "gl", "Galician" }, + { "gn", "Guarani" }, + { "gu", "Gujarati" }, + { "gv", "Manx" }, + { "ha", "Hausa" }, + { "he", "Hebrew" }, + { "hi", "Hindi" }, + { "ho", "Hiri Motu" }, + { "hr", "Croatian" }, + { "ht", "Haitian" }, + { "hu", "Hungarian" }, + { "hy", "Armenian" }, + { "hz", "Herero" }, + { "ia", "Interlingua" }, + { "id", "Indonesian" }, + { "ie", "Interlingue" }, + { "ig", "Igbo" }, + { "ii", "Sichuan Yi" }, + { "ik", "Inupiaq" }, + { "io", "Ido" }, + { "is", "Icelandic" }, + { "it", "Italian" }, + { "iu", "Inuktitut" }, + { "ja", "Japanese" }, + { "jv", "Javanese" }, + { "ka", "Georgian" }, + { "kg", "Kongo" }, + { "ki", "Kikuyu" }, + { "kj", "Kuanyama" }, + { "kk", "Kazakh" }, + { "kl", "Kalaallisut" }, + { "km", "Central Khmer" }, + { "kn", "Kannada" }, + { "ko", "Korean" }, + { "kr", "Kanuri" }, + { "ks", "Kashmiri" }, + { "ku", "Kurdish" }, + { "kv", "Komi" }, + { "kw", "Cornish" }, + { "ky", "Kirghiz" }, + { "la", "Latin" }, + { "lb", "Luxembourgish" }, + { "lg", "Ganda" }, + { "li", "Limburgan" }, + { "ln", "Lingala" }, + { "lo", "Lao" }, + { "lt", "Lithuanian" }, + { "lu", "Luba-Katanga" }, + { "lv", "Latvian" }, + { "mg", "Malagasy" }, + { "mh", "Marshallese" }, + { "mi", "Maori" }, + { "mk", "Macedonian" }, + { "ml", "Malayalam" }, + { "mn", "Mongolian" }, + { "mr", "Marathi" }, + { "ms", "Malay" }, + { "mt", "Maltese" }, + { "my", "Burmese" }, + { "na", "Nauru" }, + { "nb", "Norwegian Bokmål" }, + { "nd", "North Ndebele" }, + { "ne", "Nepali" }, + { "ng", "Ndonga" }, + { "nl", "Dutch" }, + { "nn", "Norwegian Nynorsk" }, + { "no", "Norwegian" }, + { "nr", "South Ndebele" }, + { "nv", "Navajo" }, + { "ny", "Nyanja" }, + { "oc", "Occitan" }, + { "oj", "Ojibwa" }, + { "om", "Oromo" }, + { "or", "Oriya" }, + { "os", "Ossetian" }, + { "pa", "Panjabi" }, + { "pi", "Pali" }, + { "pl", "Polish" }, + { "ps", "Pushto" }, + { "pt", "Portuguese" }, + { "qu", "Quechua" }, + { "rm", "Romansh" }, + { "rn", "Rundi" }, + { "ro", "Romanian" }, + { "ru", "Russian" }, + { "rw", "Kinyarwanda" }, + { "sa", "Sanskrit" }, + { "sc", "Sardinian" }, + { "sd", "Sindhi" }, + { "se", "Northern Sami" }, + { "sg", "Sango" }, + { "sh", "Serbo-Croatian" }, + { "si", "Sinhala" }, + { "sk", "Slovak" }, + { "sl", "Slovenian" }, + { "sm", "Samoan" }, + { "sn", "Shona" }, + { "so", "Somali" }, + { "sq", "Albanian" }, + { "sr", "Serbian" }, + { "ss", "Swati" }, + { "st", "Southern Sotho" }, + { "su", "Sundanese" }, + { "sv", "Swedish" }, + { "sw", "Swahili" }, + { "ta", "Tamil" }, + { "te", "Telugu" }, + { "tg", "Tajik" }, + { "th", "Thai" }, + { "ti", "Tigrinya" }, + { "tk", "Turkmen" }, + { "tl", "Tagalog" }, + { "tn", "Tswana" }, + { "to", "Tonga" }, + { "tr", "Turkish" }, + { "ts", "Tsonga" }, + { "tt", "Tatar" }, + { "tw", "Twi" }, + { "ty", "Tahitian" }, + { "ug", "Uighur" }, + { "uk", "Ukrainian" }, + { "ur", "Urdu" }, + { "uz", "Uzbek" }, + { "ve", "Venda" }, + { "vi", "Vietnamese" }, + { "vo", "Volapük" }, + { "wa", "Walloon" }, + { "wo", "Wolof" }, + { "xh", "Xhosa" }, + { "yi", "Yiddish" }, + { "yo", "Yoruba" }, + { "za", "Zhuang" }, + { "zh", "Chinese" }, + { "zu", "Zulu" }, +}; +static int niso639_1= sizeof( iso639_1 ) / sizeof( iso639_1[0] ); + +char * +iso639_1_from_code( const char *code ) +{ + int i; + for ( i=0; i +#include "iso639_3.h" + +typedef struct { + char *code; + char *language; +} iso639_3_t; + +static iso639_3_t iso639_3[] = { + { "aaa", "Ghotuo" }, + { "aab", "Alumu-Tesu" }, + { "aac", "Ari" }, + { "aad", "Amal" }, + { "aae", "Arbëreshë Albanian" }, + { "aaf", "Aranadan" }, + { "aag", "Ambrak" }, + { "aah", "Abu' Arapesh" }, + { "aai", "Arifama-Miniafia" }, + { "aak", "Ankave" }, + { "aal", "Afade" }, + { "aam", "Aramanik" }, + { "aan", "Anambé" }, + { "aao", "Algerian Saharan Arabic" }, + { "aap", "Pará Arára" }, + { "aaq", "Eastern Abnaki" }, + { "aar", "Afar" }, + { "aas", "Aasáx" }, + { "aat", "Arvanitika Albanian" }, + { "aau", "Abau" }, + { "aaw", "Solong" }, + { "aax", "Mandobo Atas" }, + { "aaz", "Amarasi" }, + { "aba", "Abé" }, + { "abb", "Bankon" }, + { "abc", "Ambala Ayta" }, + { "abd", "Manide" }, + { "abe", "Western Abnaki" }, + { "abf", "Abai Sungai" }, + { "abg", "Abaga" }, + { "abh", "Tajiki Arabic" }, + { "abi", "Abidji" }, + { "abj", "Aka-Bea" }, + { "abk", "Abkhazian" }, + { "abl", "Lampung Nyo" }, + { "abm", "Abanyom" }, + { "abn", "Abua" }, + { "abo", "Abon" }, + { "abp", "Abellen Ayta" }, + { "abq", "Abaza" }, + { "abr", "Abron" }, + { "abs", "Ambonese Malay" }, + { "abt", "Ambulas" }, + { "abu", "Abure" }, + { "abv", "Baharna Arabic" }, + { "abw", "Pal" }, + { "abx", "Inabaknon" }, + { "aby", "Aneme Wake" }, + { "abz", "Abui" }, + { "aca", "Achagua" }, + { "acb", "Áncá" }, + { "acd", "Gikyode" }, + { "ace", "Achinese" }, + { "acf", "Saint Lucian Creole French" }, + { "ach", "Acoli" }, + { "aci", "Aka-Cari" }, + { "ack", "Aka-Kora" }, + { "acl", "Akar-Bale" }, + { "acm", "Mesopotamian Arabic" }, + { "acn", "Achang" }, + { "acp", "Eastern Acipa" }, + { "acq", "Ta'izzi-Adeni Arabic" }, + { "acr", "Achi" }, + { "acs", "Acroá" }, + { "act", "Achterhoeks" }, + { "acu", "Achuar-Shiwiar" }, + { "acv", "Achumawi" }, + { "acw", "Hijazi Arabic" }, + { "acx", "Omani Arabic" }, + { "acy", "Cypriot Arabic" }, + { "acz", "Acheron" }, + { "ada", "Adangme" }, + { "adb", "Adabe" }, + { "add", "Dzodinka" }, + { "ade", "Adele" }, + { "adf", "Dhofari Arabic" }, + { "adg", "Andegerebinha" }, + { "adh", "Adhola" }, + { "adi", "Adi" }, + { "adj", "Adioukrou" }, + { "adl", "Galo" }, + { "adn", "Adang" }, + { "ado", "Abu" }, + { "adp", "Adap" }, + { "adq", "Adangbe" }, + { "adr", "Adonara" }, + { "ads", "Adamorobe Sign Language" }, + { "adt", "Adnyamathanha" }, + { "adu", "Aduge" }, + { "adw", "Amundava" }, + { "adx", "Amdo Tibetan" }, + { "ady", "Adyghe" }, + { "adz", "Adzera" }, + { "aea", "Areba" }, + { "aeb", "Tunisian Arabic" }, + { "aec", "Saidi Arabic" }, + { "aed", "Argentine Sign Language" }, + { "aee", "Northeast Pashayi" }, + { "aek", "Haeke" }, + { "ael", "Ambele" }, + { "aem", "Arem" }, + { "aen", "Armenian Sign Language" }, + { "aeq", "Aer" }, + { "aer", "Eastern Arrernte" }, + { "aes", "Alsea" }, + { "aeu", "Akeu" }, + { "aew", "Ambakich" }, + { "aey", "Amele" }, + { "aez", "Aeka" }, + { "afb", "Gulf Arabic" }, + { "afd", "Andai" }, + { "afe", "Putukwam" }, + { "afg", "Afghan Sign Language" }, + { "afh", "Afrihili" }, + { "afi", "Akrukay" }, + { "afk", "Nanubae" }, + { "afn", "Defaka" }, + { "afo", "Eloyi" }, + { "afp", "Tapei" }, + { "afr", "Afrikaans" }, + { "afs", "Afro-Seminole Creole" }, + { "aft", "Afitti" }, + { "afu", "Awutu" }, + { "afz", "Obokuitai" }, + { "aga", "Aguano" }, + { "agb", "Legbo" }, + { "agc", "Agatu" }, + { "agd", "Agarabi" }, + { "age", "Angal" }, + { "agf", "Arguni" }, + { "agg", "Angor" }, + { "agh", "Ngelima" }, + { "agi", "Agariya" }, + { "agj", "Argobba" }, + { "agk", "Isarog Agta" }, + { "agl", "Fembe" }, + { "agm", "Angaataha" }, + { "agn", "Agutaynen" }, + { "ago", "Tainae" }, + { "agq", "Aghem" }, + { "agr", "Aguaruna" }, + { "ags", "Esimbi" }, + { "agt", "Central Cagayan Agta" }, + { "agu", "Aguacateco" }, + { "agv", "Remontado Dumagat" }, + { "agw", "Kahua" }, + { "agx", "Aghul" }, + { "agy", "Southern Alta" }, + { "agz", "Mt. Iriga Agta" }, + { "aha", "Ahanta" }, + { "ahb", "Axamb" }, + { "ahg", "Qimant" }, + { "ahh", "Aghu" }, + { "ahi", "Tiagbamrin Aizi" }, + { "ahk", "Akha" }, + { "ahl", "Igo" }, + { "ahm", "Mobumrin Aizi" }, + { "ahn", "Àhàn" }, + { "aho", "Ahom" }, + { "ahp", "Aproumu Aizi" }, + { "ahr", "Ahirani" }, + { "ahs", "Ashe" }, + { "aht", "Ahtena" }, + { "aia", "Arosi" }, + { "aib", "Ainu (China)" }, + { "aic", "Ainbai" }, + { "aid", "Alngith" }, + { "aie", "Amara" }, + { "aif", "Agi" }, + { "aig", "Antigua and Barbuda Creole English" }, + { "aih", "Ai-Cham" }, + { "aii", "Assyrian Neo-Aramaic" }, + { "aij", "Lishanid Noshan" }, + { "aik", "Ake" }, + { "ail", "Aimele" }, + { "aim", "Aimol" }, + { "ain", "Ainu (Japan)" }, + { "aio", "Aiton" }, + { "aip", "Burumakok" }, + { "aiq", "Aimaq" }, + { "air", "Airoran" }, + { "ais", "Nataoran Amis" }, + { "ait", "Arikem" }, + { "aiw", "Aari" }, + { "aix", "Aighon" }, + { "aiy", "Ali" }, + { "aja", "Aja (Sudan)" }, + { "ajg", "Aja (Benin)" }, + { "aji", "Ajië" }, + { "ajn", "Andajin" }, + { "ajp", "South Levantine Arabic" }, + { "ajt", "Judeo-Tunisian Arabic" }, + { "aju", "Judeo-Moroccan Arabic" }, + { "ajw", "Ajawa" }, + { "ajz", "Amri Karbi" }, + { "aka", "Akan" }, + { "akb", "Batak Angkola" }, + { "akc", "Mpur" }, + { "akd", "Ukpet-Ehom" }, + { "ake", "Akawaio" }, + { "akf", "Akpa" }, + { "akg", "Anakalangu" }, + { "akh", "Angal Heneng" }, + { "aki", "Aiome" }, + { "akj", "Aka-Jeru" }, + { "akk", "Akkadian" }, + { "akl", "Aklanon" }, + { "akm", "Aka-Bo" }, + { "ako", "Akurio" }, + { "akp", "Siwu" }, + { "akq", "Ak" }, + { "akr", "Araki" }, + { "aks", "Akaselem" }, + { "akt", "Akolet" }, + { "aku", "Akum" }, + { "akv", "Akhvakh" }, + { "akw", "Akwa" }, + { "akx", "Aka-Kede" }, + { "aky", "Aka-Kol" }, + { "akz", "Alabama" }, + { "ala", "Alago" }, + { "alc", "Qawasqar" }, + { "ald", "Alladian" }, + { "ale", "Aleut" }, + { "alf", "Alege" }, + { "alh", "Alawa" }, + { "ali", "Amaimon" }, + { "alj", "Alangan" }, + { "alk", "Alak" }, + { "all", "Allar" }, + { "alm", "Amblong" }, + { "aln", "Gheg Albanian" }, + { "alo", "Larike-Wakasihu" }, + { "alp", "Alune" }, + { "alq", "Algonquin" }, + { "alr", "Alutor" }, + { "als", "Tosk Albanian" }, + { "alt", "Southern Altai" }, + { "alu", "'Are'are" }, + { "alw", "Alaba-K’abeena" }, + { "alx", "Amol" }, + { "aly", "Alyawarr" }, + { "alz", "Alur" }, + { "ama", "Amanayé" }, + { "amb", "Ambo" }, + { "amc", "Amahuaca" }, + { "ame", "Yanesha'" }, + { "amf", "Hamer-Banna" }, + { "amg", "Amurdak" }, + { "amh", "Amharic" }, + { "ami", "Amis" }, + { "amj", "Amdang" }, + { "amk", "Ambai" }, + { "aml", "War-Jaintia" }, + { "amm", "Ama (Papua New Guinea)" }, + { "amn", "Amanab" }, + { "amo", "Amo" }, + { "amp", "Alamblak" }, + { "amq", "Amahai" }, + { "amr", "Amarakaeri" }, + { "ams", "Southern Amami-Oshima" }, + { "amt", "Amto" }, + { "amu", "Guerrero Amuzgo" }, + { "amv", "Ambelau" }, + { "amw", "Western Neo-Aramaic" }, + { "amx", "Anmatyerre" }, + { "amy", "Ami" }, + { "amz", "Atampaya" }, + { "ana", "Andaqui" }, + { "anb", "Andoa" }, + { "anc", "Ngas" }, + { "and", "Ansus" }, + { "ane", "Xârâcùù" }, + { "anf", "Animere" }, + { "ang", "Old English (ca. 450-1100)" }, + { "anh", "Nend" }, + { "ani", "Andi" }, + { "anj", "Anor" }, + { "ank", "Goemai" }, + { "anl", "Anu-Hkongso Chin" }, + { "anm", "Anal" }, + { "ann", "Obolo" }, + { "ano", "Andoque" }, + { "anp", "Angika" }, + { "anq", "Jarawa (India)" }, + { "anr", "Andh" }, + { "ans", "Anserma" }, + { "ant", "Antakarinya" }, + { "anu", "Anuak" }, + { "anv", "Denya" }, + { "anw", "Anaang" }, + { "anx", "Andra-Hus" }, + { "any", "Anyin" }, + { "anz", "Anem" }, + { "aoa", "Angolar" }, + { "aob", "Abom" }, + { "aoc", "Pemon" }, + { "aod", "Andarum" }, + { "aoe", "Angal Enen" }, + { "aof", "Bragat" }, + { "aog", "Angoram" }, + { "aoh", "Arma" }, + { "aoi", "Anindilyakwa" }, + { "aoj", "Mufian" }, + { "aok", "Arhö" }, + { "aol", "Alor" }, + { "aom", "Ömie" }, + { "aon", "Bumbita Arapesh" }, + { "aor", "Aore" }, + { "aos", "Taikat" }, + { "aot", "A'tong" }, + { "aou", "A'ou" }, + { "aox", "Atorada" }, + { "aoz", "Uab Meto" }, + { "apb", "Sa'a" }, + { "apc", "North Levantine Arabic" }, + { "apd", "Sudanese Arabic" }, + { "ape", "Bukiyip" }, + { "apf", "Pahanan Agta" }, + { "apg", "Ampanang" }, + { "aph", "Athpariya" }, + { "api", "Apiaká" }, + { "apj", "Jicarilla Apache" }, + { "apk", "Kiowa Apache" }, + { "apl", "Lipan Apache" }, + { "apm", "Mescalero-Chiricahua Apache" }, + { "apn", "Apinayé" }, + { "apo", "Ambul" }, + { "app", "Apma" }, + { "apq", "A-Pucikwar" }, + { "apr", "Arop-Lokep" }, + { "aps", "Arop-Sissano" }, + { "apt", "Apatani" }, + { "apu", "Apurinã" }, + { "apv", "Alapmunte" }, + { "apw", "Western Apache" }, + { "apx", "Aputai" }, + { "apy", "Apalaí" }, + { "apz", "Safeyoka" }, + { "aqc", "Archi" }, + { "aqd", "Ampari Dogon" }, + { "aqg", "Arigidi" }, + { "aqm", "Atohwaim" }, + { "aqn", "Northern Alta" }, + { "aqp", "Atakapa" }, + { "aqr", "Arhâ" }, + { "aqz", "Akuntsu" }, + { "ara", "Arabic" }, + { "arb", "Standard Arabic" }, + { "arc", "Official Aramaic (700-300 BCE)" }, + { "ard", "Arabana" }, + { "are", "Western Arrarnta" }, + { "arg", "Aragonese" }, + { "arh", "Arhuaco" }, + { "ari", "Arikara" }, + { "arj", "Arapaso" }, + { "ark", "Arikapú" }, + { "arl", "Arabela" }, + { "arn", "Mapudungun" }, + { "aro", "Araona" }, + { "arp", "Arapaho" }, + { "arq", "Algerian Arabic" }, + { "arr", "Karo (Brazil)" }, + { "ars", "Najdi Arabic" }, + { "aru", "Aruá (Amazonas State)" }, + { "arv", "Arbore" }, + { "arw", "Arawak" }, + { "arx", "Aruá (Rodonia State)" }, + { "ary", "Moroccan Arabic" }, + { "arz", "Egyptian Arabic" }, + { "asa", "Asu (Tanzania)" }, + { "asb", "Assiniboine" }, + { "asc", "Casuarina Coast Asmat" }, + { "asd", "Asas" }, + { "ase", "American Sign Language" }, + { "asf", "Australian Sign Language" }, + { "asg", "Cishingini" }, + { "ash", "Abishira" }, + { "asi", "Buruwai" }, + { "asj", "Sari" }, + { "ask", "Ashkun" }, + { "asl", "Asilulu" }, + { "asm", "Assamese" }, + { "asn", "Xingú Asuriní" }, + { "aso", "Dano" }, + { "asp", "Algerian Sign Language" }, + { "asq", "Austrian Sign Language" }, + { "asr", "Asuri" }, + { "ass", "Ipulo" }, + { "ast", "Asturian" }, + { "asu", "Tocantins Asurini" }, + { "asv", "Asoa" }, + { "asw", "Australian Aborigines Sign Language" }, + { "asx", "Muratayak" }, + { "asy", "Yaosakor Asmat" }, + { "asz", "As" }, + { "ata", "Pele-Ata" }, + { "atb", "Zaiwa" }, + { "atc", "Atsahuaca" }, + { "atd", "Ata Manobo" }, + { "ate", "Atemble" }, + { "atg", "Ivbie North-Okpela-Arhe" }, + { "ati", "Attié" }, + { "atj", "Atikamekw" }, + { "atk", "Ati" }, + { "atl", "Mt. Iraya Agta" }, + { "atm", "Ata" }, + { "atn", "Ashtiani" }, + { "ato", "Atong" }, + { "atp", "Pudtol Atta" }, + { "atq", "Aralle-Tabulahan" }, + { "atr", "Waimiri-Atroari" }, + { "ats", "Gros Ventre" }, + { "att", "Pamplona Atta" }, + { "atu", "Reel" }, + { "atv", "Northern Altai" }, + { "atw", "Atsugewi" }, + { "atx", "Arutani" }, + { "aty", "Aneityum" }, + { "atz", "Arta" }, + { "aua", "Asumboa" }, + { "aub", "Alugu" }, + { "auc", "Waorani" }, + { "aud", "Anuta" }, + { "aue", "=Kx'au'ein" }, + { "aug", "Aguna" }, + { "auh", "Aushi" }, + { "aui", "Anuki" }, + { "auj", "Awjilah" }, + { "auk", "Heyo" }, + { "aul", "Aulua" }, + { "aum", "Asu (Nigeria)" }, + { "aun", "Molmo One" }, + { "auo", "Auyokawa" }, + { "aup", "Makayam" }, + { "auq", "Anus" }, + { "aur", "Aruek" }, + { "aut", "Austral" }, + { "auu", "Auye" }, + { "auw", "Awyi" }, + { "aux", "Aurá" }, + { "auy", "Awiyaana" }, + { "auz", "Uzbeki Arabic" }, + { "ava", "Avaric" }, + { "avb", "Avau" }, + { "avd", "Alviri-Vidari" }, + { "ave", "Avestan" }, + { "avi", "Avikam" }, + { "avk", "Kotava" }, + { "avl", "Eastern Egyptian Bedawi Arabic" }, + { "avm", "Angkamuthi" }, + { "avn", "Avatime" }, + { "avo", "Agavotaguerra" }, + { "avs", "Aushiri" }, + { "avt", "Au" }, + { "avu", "Avokaya" }, + { "avv", "Avá-Canoeiro" }, + { "awa", "Awadhi" }, + { "awb", "Awa (Papua New Guinea)" }, + { "awc", "Cicipu" }, + { "awe", "Awetí" }, + { "awg", "Anguthimri" }, + { "awh", "Awbono" }, + { "awi", "Aekyom" }, + { "awk", "Awabakal" }, + { "awm", "Arawum" }, + { "awn", "Awngi" }, + { "awo", "Awak" }, + { "awr", "Awera" }, + { "aws", "South Awyu" }, + { "awt", "Araweté" }, + { "awu", "Central Awyu" }, + { "awv", "Jair Awyu" }, + { "aww", "Awun" }, + { "awx", "Awara" }, + { "awy", "Edera Awyu" }, + { "axb", "Abipon" }, + { "axe", "Ayerrerenge" }, + { "axg", "Mato Grosso Arára" }, + { "axk", "Yaka (Central African Republic)" }, + { "axl", "Lower Southern Aranda" }, + { "axm", "Middle Armenian" }, + { "axx", "Xârâgurè" }, + { "aya", "Awar" }, + { "ayb", "Ayizo Gbe" }, + { "ayc", "Southern Aymara" }, + { "ayd", "Ayabadhu" }, + { "aye", "Ayere" }, + { "ayg", "Ginyanga" }, + { "ayh", "Hadrami Arabic" }, + { "ayi", "Leyigha" }, + { "ayk", "Akuku" }, + { "ayl", "Libyan Arabic" }, + { "aym", "Aymara" }, + { "ayn", "Sanaani Arabic" }, + { "ayo", "Ayoreo" }, + { "ayp", "North Mesopotamian Arabic" }, + { "ayq", "Ayi (Papua New Guinea)" }, + { "ayr", "Central Aymara" }, + { "ays", "Sorsogon Ayta" }, + { "ayt", "Magbukun Ayta" }, + { "ayu", "Ayu" }, + { "ayy", "Tayabas Ayta" }, + { "ayz", "Mai Brat" }, + { "aza", "Azha" }, + { "azb", "South Azerbaijani" }, + { "azd", "Eastern Durango Nahuatl" }, + { "aze", "Azerbaijani" }, + { "azg", "San Pedro Amuzgos Amuzgo" }, + { "azj", "North Azerbaijani" }, + { "azm", "Ipalapa Amuzgo" }, + { "azn", "Western Durango Nahuatl" }, + { "azo", "Awing" }, + { "azt", "Faire Atta" }, + { "azz", "Highland Puebla Nahuatl" }, + { "baa", "Babatana" }, + { "bab", "Bainouk-Gunyuño" }, + { "bac", "Badui" }, + { "bae", "Baré" }, + { "baf", "Nubaca" }, + { "bag", "Tuki" }, + { "bah", "Bahamas Creole English" }, + { "baj", "Barakai" }, + { "bak", "Bashkir" }, + { "bal", "Baluchi" }, + { "bam", "Bambara" }, + { "ban", "Balinese" }, + { "bao", "Waimaha" }, + { "bap", "Bantawa" }, + { "bar", "Bavarian" }, + { "bas", "Basa (Cameroon)" }, + { "bau", "Bada (Nigeria)" }, + { "bav", "Vengo" }, + { "baw", "Bambili-Bambui" }, + { "bax", "Bamun" }, + { "bay", "Batuley" }, + { "bba", "Baatonum" }, + { "bbb", "Barai" }, + { "bbc", "Batak Toba" }, + { "bbd", "Bau" }, + { "bbe", "Bangba" }, + { "bbf", "Baibai" }, + { "bbg", "Barama" }, + { "bbh", "Bugan" }, + { "bbi", "Barombi" }, + { "bbj", "Ghomálá'" }, + { "bbk", "Babanki" }, + { "bbl", "Bats" }, + { "bbm", "Babango" }, + { "bbn", "Uneapa" }, + { "bbo", "Northern Bobo Madaré" }, + { "bbp", "West Central Banda" }, + { "bbq", "Bamali" }, + { "bbr", "Girawa" }, + { "bbs", "Bakpinka" }, + { "bbt", "Mburku" }, + { "bbu", "Kulung (Nigeria)" }, + { "bbv", "Karnai" }, + { "bbw", "Baba" }, + { "bbx", "Bubia" }, + { "bby", "Befang" }, + { "bbz", "Babalia Creole Arabic" }, + { "bca", "Central Bai" }, + { "bcb", "Bainouk-Samik" }, + { "bcc", "Southern Balochi" }, + { "bcd", "North Babar" }, + { "bce", "Bamenyam" }, + { "bcf", "Bamu" }, + { "bcg", "Baga Binari" }, + { "bch", "Bariai" }, + { "bci", "Baoulé" }, + { "bcj", "Bardi" }, + { "bck", "Bunaba" }, + { "bcl", "Central Bikol" }, + { "bcm", "Bannoni" }, + { "bcn", "Bali (Nigeria)" }, + { "bco", "Kaluli" }, + { "bcp", "Bali (Democratic Republic of Congo)" }, + { "bcq", "Bench" }, + { "bcr", "Babine" }, + { "bcs", "Kohumono" }, + { "bct", "Bendi" }, + { "bcu", "Awad Bing" }, + { "bcv", "Shoo-Minda-Nye" }, + { "bcw", "Bana" }, + { "bcy", "Bacama" }, + { "bcz", "Bainouk-Gunyaamolo" }, + { "bda", "Bayot" }, + { "bdb", "Basap" }, + { "bdc", "Emberá-Baudó" }, + { "bdd", "Bunama" }, + { "bde", "Bade" }, + { "bdf", "Biage" }, + { "bdg", "Bonggi" }, + { "bdh", "Baka (Sudan)" }, + { "bdi", "Burun" }, + { "bdj", "Bai" }, + { "bdk", "Budukh" }, + { "bdl", "Indonesian Bajau" }, + { "bdm", "Buduma" }, + { "bdn", "Baldemu" }, + { "bdo", "Morom" }, + { "bdp", "Bende" }, + { "bdq", "Bahnar" }, + { "bdr", "West Coast Bajau" }, + { "bds", "Burunge" }, + { "bdt", "Bokoto" }, + { "bdu", "Oroko" }, + { "bdv", "Bodo Parja" }, + { "bdw", "Baham" }, + { "bdx", "Budong-Budong" }, + { "bdy", "Bandjalang" }, + { "bdz", "Badeshi" }, + { "bea", "Beaver" }, + { "beb", "Bebele" }, + { "bec", "Iceve-Maci" }, + { "bed", "Bedoanas" }, + { "bee", "Byangsi" }, + { "bef", "Benabena" }, + { "beg", "Belait" }, + { "beh", "Biali" }, + { "bei", "Bekati'" }, + { "bej", "Beja" }, + { "bek", "Bebeli" }, + { "bel", "Belarusian" }, + { "bem", "Bemba (Zambia)" }, + { "ben", "Bengali" }, + { "beo", "Beami" }, + { "bep", "Besoa" }, + { "beq", "Beembe" }, + { "bes", "Besme" }, + { "bet", "Guiberoua Béte" }, + { "beu", "Blagar" }, + { "bev", "Daloa Bété" }, + { "bew", "Betawi" }, + { "bex", "Jur Modo" }, + { "bey", "Beli (Papua New Guinea)" }, + { "bez", "Bena (Tanzania)" }, + { "bfa", "Bari" }, + { "bfb", "Pauri Bareli" }, + { "bfc", "Northern Bai" }, + { "bfd", "Bafut" }, + { "bfe", "Betaf" }, + { "bff", "Bofi" }, + { "bfg", "Busang Kayan" }, + { "bfh", "Blafe" }, + { "bfi", "British Sign Language" }, + { "bfj", "Bafanji" }, + { "bfk", "Ban Khor Sign Language" }, + { "bfl", "Banda-Ndélé" }, + { "bfm", "Mmen" }, + { "bfn", "Bunak" }, + { "bfo", "Malba Birifor" }, + { "bfp", "Beba" }, + { "bfq", "Badaga" }, + { "bfr", "Bazigar" }, + { "bfs", "Southern Bai" }, + { "bft", "Balti" }, + { "bfu", "Gahri" }, + { "bfw", "Bondo" }, + { "bfx", "Bantayanon" }, + { "bfy", "Bagheli" }, + { "bfz", "Mahasu Pahari" }, + { "bga", "Gwamhi-Wuri" }, + { "bgb", "Bobongko" }, + { "bgc", "Haryanvi" }, + { "bgd", "Rathwi Bareli" }, + { "bge", "Bauria" }, + { "bgf", "Bangandu" }, + { "bgg", "Bugun" }, + { "bgi", "Giangan" }, + { "bgj", "Bangolan" }, + { "bgk", "Bit" }, + { "bgl", "Bo (Laos)" }, + { "bgm", "Baga Mboteni" }, + { "bgn", "Western Balochi" }, + { "bgo", "Baga Koga" }, + { "bgp", "Eastern Balochi" }, + { "bgq", "Bagri" }, + { "bgr", "Bawm Chin" }, + { "bgs", "Tagabawa" }, + { "bgt", "Bughotu" }, + { "bgu", "Mbongno" }, + { "bgv", "Warkay-Bipim" }, + { "bgw", "Bhatri" }, + { "bgx", "Balkan Gagauz Turkish" }, + { "bgy", "Benggoi" }, + { "bgz", "Banggai" }, + { "bha", "Bharia" }, + { "bhb", "Bhili" }, + { "bhc", "Biga" }, + { "bhd", "Bhadrawahi" }, + { "bhe", "Bhaya" }, + { "bhf", "Odiai" }, + { "bhg", "Binandere" }, + { "bhh", "Bukharic" }, + { "bhi", "Bhilali" }, + { "bhj", "Bahing" }, + { "bhl", "Bimin" }, + { "bhm", "Bathari" }, + { "bhn", "Bohtan Neo-Aramaic" }, + { "bho", "Bhojpuri" }, + { "bhp", "Bima" }, + { "bhq", "Tukang Besi South" }, + { "bhr", "Bara Malagasy" }, + { "bhs", "Buwal" }, + { "bht", "Bhattiyali" }, + { "bhu", "Bhunjia" }, + { "bhv", "Bahau" }, + { "bhw", "Biak" }, + { "bhx", "Bhalay" }, + { "bhy", "Bhele" }, + { "bhz", "Bada (Indonesia)" }, + { "bia", "Badimaya" }, + { "bib", "Bissa" }, + { "bic", "Bikaru" }, + { "bid", "Bidiyo" }, + { "bie", "Bepour" }, + { "bif", "Biafada" }, + { "big", "Biangai" }, + { "bij", "Vaghat-Ya-Bijim-Legeri" }, + { "bik", "Bikol" }, + { "bil", "Bile" }, + { "bim", "Bimoba" }, + { "bin", "Bini" }, + { "bio", "Nai" }, + { "bip", "Bila" }, + { "biq", "Bipi" }, + { "bir", "Bisorio" }, + { "bis", "Bislama" }, + { "bit", "Berinomo" }, + { "biu", "Biete" }, + { "biv", "Southern Birifor" }, + { "biw", "Kol (Cameroon)" }, + { "bix", "Bijori" }, + { "biy", "Birhor" }, + { "biz", "Baloi" }, + { "bja", "Budza" }, + { "bjb", "Banggarla" }, + { "bjc", "Bariji" }, + { "bje", "Biao-Jiao Mien" }, + { "bjf", "Barzani Jewish Neo-Aramaic" }, + { "bjg", "Bidyogo" }, + { "bjh", "Bahinemo" }, + { "bji", "Burji" }, + { "bjj", "Kanauji" }, + { "bjk", "Barok" }, + { "bjl", "Bulu (Papua New Guinea)" }, + { "bjm", "Bajelani" }, + { "bjn", "Banjar" }, + { "bjo", "Mid-Southern Banda" }, + { "bjp", "Fanamaket" }, + { "bjr", "Binumarien" }, + { "bjs", "Bajan" }, + { "bjt", "Balanta-Ganja" }, + { "bju", "Busuu" }, + { "bjv", "Bedjond" }, + { "bjw", "Bakwé" }, + { "bjx", "Banao Itneg" }, + { "bjy", "Bayali" }, + { "bjz", "Baruga" }, + { "bka", "Kyak" }, + { "bkc", "Baka (Cameroon)" }, + { "bkd", "Binukid" }, + { "bkf", "Beeke" }, + { "bkg", "Buraka" }, + { "bkh", "Bakoko" }, + { "bki", "Baki" }, + { "bkj", "Pande" }, + { "bkk", "Brokskat" }, + { "bkl", "Berik" }, + { "bkm", "Kom (Cameroon)" }, + { "bkn", "Bukitan" }, + { "bko", "Kwa'" }, + { "bkp", "Boko (Democratic Republic of Congo)" }, + { "bkq", "Bakairí" }, + { "bkr", "Bakumpai" }, + { "bks", "Northern Sorsoganon" }, + { "bkt", "Boloki" }, + { "bku", "Buhid" }, + { "bkv", "Bekwarra" }, + { "bkw", "Bekwel" }, + { "bkx", "Baikeno" }, + { "bky", "Bokyi" }, + { "bkz", "Bungku" }, + { "bla", "Siksika" }, + { "blb", "Bilua" }, + { "blc", "Bella Coola" }, + { "bld", "Bolango" }, + { "ble", "Balanta-Kentohe" }, + { "blf", "Buol" }, + { "blg", "Balau" }, + { "blh", "Kuwaa" }, + { "bli", "Bolia" }, + { "blj", "Bolongan" }, + { "blk", "Pa'o Karen" }, + { "bll", "Biloxi" }, + { "blm", "Beli (Sudan)" }, + { "bln", "Southern Catanduanes Bikol" }, + { "blo", "Anii" }, + { "blp", "Blablanga" }, + { "blq", "Baluan-Pam" }, + { "blr", "Blang" }, + { "bls", "Balaesang" }, + { "blt", "Tai Dam" }, + { "blv", "Bolo" }, + { "blw", "Balangao" }, + { "blx", "Mag-Indi Ayta" }, + { "bly", "Notre" }, + { "blz", "Balantak" }, + { "bma", "Lame" }, + { "bmb", "Bembe" }, + { "bmc", "Biem" }, + { "bmd", "Baga Manduri" }, + { "bme", "Limassa" }, + { "bmf", "Bom" }, + { "bmg", "Bamwe" }, + { "bmh", "Kein" }, + { "bmi", "Bagirmi" }, + { "bmj", "Bote-Majhi" }, + { "bmk", "Ghayavi" }, + { "bml", "Bomboli" }, + { "bmm", "Northern Betsimisaraka Malagasy" }, + { "bmn", "Bina (Papua New Guinea)" }, + { "bmo", "Bambalang" }, + { "bmp", "Bulgebi" }, + { "bmq", "Bomu" }, + { "bmr", "Muinane" }, + { "bms", "Bilma Kanuri" }, + { "bmt", "Biao Mon" }, + { "bmu", "Somba-Siawari" }, + { "bmv", "Bum" }, + { "bmw", "Bomwali" }, + { "bmx", "Baimak" }, + { "bmy", "Bemba (Democratic Republic of Congo)" }, + { "bmz", "Baramu" }, + { "bna", "Bonerate" }, + { "bnb", "Bookan" }, + { "bnc", "Bontok" }, + { "bnd", "Banda (Indonesia)" }, + { "bne", "Bintauna" }, + { "bnf", "Masiwang" }, + { "bng", "Benga" }, + { "bni", "Bangi" }, + { "bnj", "Eastern Tawbuid" }, + { "bnk", "Bierebo" }, + { "bnl", "Boon" }, + { "bnm", "Batanga" }, + { "bnn", "Bunun" }, + { "bno", "Bantoanon" }, + { "bnp", "Bola" }, + { "bnq", "Bantik" }, + { "bnr", "Butmas-Tur" }, + { "bns", "Bundeli" }, + { "bnu", "Bentong" }, + { "bnv", "Bonerif" }, + { "bnw", "Bisis" }, + { "bnx", "Bangubangu" }, + { "bny", "Bintulu" }, + { "bnz", "Beezen" }, + { "boa", "Bora" }, + { "bob", "Aweer" }, + { "bod", "Tibetan" }, + { "boe", "Mundabli" }, + { "bof", "Bolon" }, + { "bog", "Bamako Sign Language" }, + { "boh", "Boma" }, + { "boi", "Barbareño" }, + { "boj", "Anjam" }, + { "bok", "Bonjo" }, + { "bol", "Bole" }, + { "bom", "Berom" }, + { "bon", "Bine" }, + { "boo", "Tiemacèwè Bozo" }, + { "bop", "Bonkiman" }, + { "boq", "Bogaya" }, + { "bor", "Borôro" }, + { "bos", "Bosnian" }, + { "bot", "Bongo" }, + { "bou", "Bondei" }, + { "bov", "Tuwuli" }, + { "bow", "Rema" }, + { "box", "Buamu" }, + { "boy", "Bodo (Central African Republic)" }, + { "boz", "Tiéyaxo Bozo" }, + { "bpa", "Daakaka" }, + { "bpb", "Barbacoas" }, + { "bpd", "Banda-Banda" }, + { "bpg", "Bonggo" }, + { "bph", "Botlikh" }, + { "bpi", "Bagupi" }, + { "bpj", "Binji" }, + { "bpk", "Orowe" }, + { "bpl", "Broome Pearling Lugger Pidgin" }, + { "bpm", "Biyom" }, + { "bpn", "Dzao Min" }, + { "bpo", "Anasi" }, + { "bpp", "Kaure" }, + { "bpq", "Banda Malay" }, + { "bpr", "Koronadal Blaan" }, + { "bps", "Sarangani Blaan" }, + { "bpt", "Barrow Point" }, + { "bpu", "Bongu" }, + { "bpv", "Bian Marind" }, + { "bpw", "Bo (Papua New Guinea)" }, + { "bpx", "Palya Bareli" }, + { "bpy", "Bishnupriya" }, + { "bpz", "Bilba" }, + { "bqa", "Tchumbuli" }, + { "bqb", "Bagusa" }, + { "bqc", "Boko (Benin)" }, + { "bqd", "Bung" }, + { "bqf", "Baga Kaloum" }, + { "bqg", "Bago-Kusuntu" }, + { "bqh", "Baima" }, + { "bqi", "Bakhtiari" }, + { "bqj", "Bandial" }, + { "bqk", "Banda-Mbrès" }, + { "bql", "Bilakura" }, + { "bqm", "Wumboko" }, + { "bqn", "Bulgarian Sign Language" }, + { "bqo", "Balo" }, + { "bqp", "Busa" }, + { "bqq", "Biritai" }, + { "bqr", "Burusu" }, + { "bqs", "Bosngun" }, + { "bqt", "Bamukumbit" }, + { "bqu", "Boguru" }, + { "bqv", "Koro Wachi" }, + { "bqw", "Buru (Nigeria)" }, + { "bqx", "Baangi" }, + { "bqy", "Bengkala Sign Language" }, + { "bqz", "Bakaka" }, + { "bra", "Braj" }, + { "brb", "Lave" }, + { "brc", "Berbice Creole Dutch" }, + { "brd", "Baraamu" }, + { "bre", "Breton" }, + { "brf", "Bera" }, + { "brg", "Baure" }, + { "brh", "Brahui" }, + { "bri", "Mokpwe" }, + { "brj", "Bieria" }, + { "brk", "Birked" }, + { "brl", "Birwa" }, + { "brm", "Barambu" }, + { "brn", "Boruca" }, + { "bro", "Brokkat" }, + { "brp", "Barapasi" }, + { "brq", "Breri" }, + { "brr", "Birao" }, + { "brs", "Baras" }, + { "brt", "Bitare" }, + { "bru", "Eastern Bru" }, + { "brv", "Western Bru" }, + { "brw", "Bellari" }, + { "brx", "Bodo (India)" }, + { "bry", "Burui" }, + { "brz", "Bilbil" }, + { "bsa", "Abinomn" }, + { "bsb", "Brunei Bisaya" }, + { "bsc", "Bassari" }, + { "bse", "Wushi" }, + { "bsf", "Bauchi" }, + { "bsg", "Bashkardi" }, + { "bsh", "Kati" }, + { "bsi", "Bassossi" }, + { "bsj", "Bangwinji" }, + { "bsk", "Burushaski" }, + { "bsl", "Basa-Gumna" }, + { "bsm", "Busami" }, + { "bsn", "Barasana-Eduria" }, + { "bso", "Buso" }, + { "bsp", "Baga Sitemu" }, + { "bsq", "Bassa" }, + { "bsr", "Bassa-Kontagora" }, + { "bss", "Akoose" }, + { "bst", "Basketo" }, + { "bsu", "Bahonsuai" }, + { "bsv", "Baga Sobané" }, + { "bsw", "Baiso" }, + { "bsx", "Yangkam" }, + { "bsy", "Sabah Bisaya" }, + { "bta", "Bata" }, + { "btc", "Bati (Cameroon)" }, + { "btd", "Batak Dairi" }, + { "bte", "Gamo-Ningi" }, + { "btf", "Birgit" }, + { "btg", "Gagnoa Bété" }, + { "bth", "Biatah Bidayuh" }, + { "bti", "Burate" }, + { "btj", "Bacanese Malay" }, + { "btl", "Bhatola" }, + { "btm", "Batak Mandailing" }, + { "btn", "Ratagnon" }, + { "bto", "Rinconada Bikol" }, + { "btp", "Budibud" }, + { "btq", "Batek" }, + { "btr", "Baetora" }, + { "bts", "Batak Simalungun" }, + { "btt", "Bete-Bendi" }, + { "btu", "Batu" }, + { "btv", "Bateri" }, + { "btw", "Butuanon" }, + { "btx", "Batak Karo" }, + { "bty", "Bobot" }, + { "btz", "Batak Alas-Kluet" }, + { "bua", "Buriat" }, + { "bub", "Bua" }, + { "buc", "Bushi" }, + { "bud", "Ntcham" }, + { "bue", "Beothuk" }, + { "buf", "Bushoong" }, + { "bug", "Buginese" }, + { "buh", "Younuo Bunu" }, + { "bui", "Bongili" }, + { "buj", "Basa-Gurmana" }, + { "buk", "Bugawac" }, + { "bul", "Bulgarian" }, + { "bum", "Bulu (Cameroon)" }, + { "bun", "Sherbro" }, + { "buo", "Terei" }, + { "bup", "Busoa" }, + { "buq", "Brem" }, + { "bus", "Bokobaru" }, + { "but", "Bungain" }, + { "buu", "Budu" }, + { "buv", "Bun" }, + { "buw", "Bubi" }, + { "bux", "Boghom" }, + { "buy", "Bullom So" }, + { "buz", "Bukwen" }, + { "bva", "Barein" }, + { "bvb", "Bube" }, + { "bvc", "Baelelea" }, + { "bvd", "Baeggu" }, + { "bve", "Berau Malay" }, + { "bvf", "Boor" }, + { "bvg", "Bonkeng" }, + { "bvh", "Bure" }, + { "bvi", "Belanda Viri" }, + { "bvj", "Baan" }, + { "bvk", "Bukat" }, + { "bvl", "Bolivian Sign Language" }, + { "bvm", "Bamunka" }, + { "bvn", "Buna" }, + { "bvo", "Bolgo" }, + { "bvp", "Bumang" }, + { "bvq", "Birri" }, + { "bvr", "Burarra" }, + { "bvt", "Bati (Indonesia)" }, + { "bvu", "Bukit Malay" }, + { "bvv", "Baniva" }, + { "bvw", "Boga" }, + { "bvx", "Dibole" }, + { "bvy", "Baybayanon" }, + { "bvz", "Bauzi" }, + { "bwa", "Bwatoo" }, + { "bwb", "Namosi-Naitasiri-Serua" }, + { "bwc", "Bwile" }, + { "bwd", "Bwaidoka" }, + { "bwe", "Bwe Karen" }, + { "bwf", "Boselewa" }, + { "bwg", "Barwe" }, + { "bwh", "Bishuo" }, + { "bwi", "Baniwa" }, + { "bwj", "Láá Láá Bwamu" }, + { "bwk", "Bauwaki" }, + { "bwl", "Bwela" }, + { "bwm", "Biwat" }, + { "bwn", "Wunai Bunu" }, + { "bwo", "Boro (Ethiopia)" }, + { "bwp", "Mandobo Bawah" }, + { "bwq", "Southern Bobo Madaré" }, + { "bwr", "Bura-Pabir" }, + { "bws", "Bomboma" }, + { "bwt", "Bafaw-Balong" }, + { "bwu", "Buli (Ghana)" }, + { "bww", "Bwa" }, + { "bwx", "Bu-Nao Bunu" }, + { "bwy", "Cwi Bwamu" }, + { "bwz", "Bwisi" }, + { "bxa", "Tairaha" }, + { "bxb", "Belanda Bor" }, + { "bxc", "Molengue" }, + { "bxd", "Pela" }, + { "bxe", "Birale" }, + { "bxf", "Bilur" }, + { "bxg", "Bangala" }, + { "bxh", "Buhutu" }, + { "bxi", "Pirlatapa" }, + { "bxj", "Bayungu" }, + { "bxk", "Bukusu" }, + { "bxl", "Jalkunan" }, + { "bxm", "Mongolia Buriat" }, + { "bxn", "Burduna" }, + { "bxo", "Barikanchi" }, + { "bxp", "Bebil" }, + { "bxq", "Beele" }, + { "bxr", "Russia Buriat" }, + { "bxs", "Busam" }, + { "bxu", "China Buriat" }, + { "bxv", "Berakou" }, + { "bxw", "Bankagooma" }, + { "bxx", "Borna (Democratic Republic of Congo)" }, + { "bxz", "Binahari" }, + { "bya", "Batak" }, + { "byb", "Bikya" }, + { "byc", "Ubaghara" }, + { "byd", "Benyadu'" }, + { "bye", "Pouye" }, + { "byf", "Bete" }, + { "byg", "Baygo" }, + { "byh", "Bhujel" }, + { "byi", "Buyu" }, + { "byj", "Bina (Nigeria)" }, + { "byk", "Biao" }, + { "byl", "Bayono" }, + { "bym", "Bidyara" }, + { "byn", "Bilin" }, + { "byo", "Biyo" }, + { "byp", "Bumaji" }, + { "byq", "Basay" }, + { "byr", "Baruya" }, + { "bys", "Burak" }, + { "byt", "Berti" }, + { "byv", "Medumba" }, + { "byw", "Belhariya" }, + { "byx", "Qaqet" }, + { "byy", "Buya" }, + { "byz", "Banaro" }, + { "bza", "Bandi" }, + { "bzb", "Andio" }, + { "bzc", "Southern Betsimisaraka Malagasy" }, + { "bzd", "Bribri" }, + { "bze", "Jenaama Bozo" }, + { "bzf", "Boikin" }, + { "bzg", "Babuza" }, + { "bzh", "Mapos Buang" }, + { "bzi", "Bisu" }, + { "bzj", "Belize Kriol English" }, + { "bzk", "Nicaragua Creole English" }, + { "bzl", "Boano (Sulawesi)" }, + { "bzm", "Bolondo" }, + { "bzn", "Boano (Maluku)" }, + { "bzo", "Bozaba" }, + { "bzp", "Kemberano" }, + { "bzq", "Buli (Indonesia)" }, + { "bzr", "Biri" }, + { "bzs", "Brazilian Sign Language" }, + { "bzt", "Brithenig" }, + { "bzu", "Burmeso" }, + { "bzv", "Naami" }, + { "bzw", "Basa (Nigeria)" }, + { "bzx", "Kɛlɛngaxo Bozo" }, + { "bzy", "Obanliku" }, + { "bzz", "Evant" }, + { "caa", "Chortí" }, + { "cab", "Garifuna" }, + { "cac", "Chuj" }, + { "cad", "Caddo" }, + { "cae", "Lehar" }, + { "caf", "Southern Carrier" }, + { "cag", "Nivaclé" }, + { "cah", "Cahuarano" }, + { "caj", "Chané" }, + { "cak", "Kaqchikel" }, + { "cal", "Carolinian" }, + { "cam", "Cemuhî" }, + { "can", "Chambri" }, + { "cao", "Chácobo" }, + { "cap", "Chipaya" }, + { "caq", "Car Nicobarese" }, + { "car", "Galibi Carib" }, + { "cas", "Tsimané" }, + { "cat", "Catalan" }, + { "cav", "Cavineña" }, + { "caw", "Callawalla" }, + { "cax", "Chiquitano" }, + { "cay", "Cayuga" }, + { "caz", "Canichana" }, + { "cbb", "Cabiyarí" }, + { "cbc", "Carapana" }, + { "cbd", "Carijona" }, + { "cbe", "Chipiajes" }, + { "cbg", "Chimila" }, + { "cbh", "Cagua" }, + { "cbi", "Chachi" }, + { "cbj", "Ede Cabe" }, + { "cbk", "Chavacano" }, + { "cbl", "Bualkhaw Chin" }, + { "cbn", "Nyahkur" }, + { "cbo", "Izora" }, + { "cbr", "Cashibo-Cacataibo" }, + { "cbs", "Cashinahua" }, + { "cbt", "Chayahuita" }, + { "cbu", "Candoshi-Shapra" }, + { "cbv", "Cacua" }, + { "cbw", "Kinabalian" }, + { "cby", "Carabayo" }, + { "cca", "Cauca" }, + { "ccc", "Chamicuro" }, + { "ccd", "Cafundo Creole" }, + { "cce", "Chopi" }, + { "ccg", "Samba Daka" }, + { "cch", "Atsam" }, + { "ccj", "Kasanga" }, + { "ccl", "Cutchi-Swahili" }, + { "ccm", "Malaccan Creole Malay" }, + { "cco", "Comaltepec Chinantec" }, + { "ccp", "Chakma" }, + { "ccr", "Cacaopera" }, + { "cda", "Choni" }, + { "cde", "Chenchu" }, + { "cdf", "Chiru" }, + { "cdg", "Chamari" }, + { "cdh", "Chambeali" }, + { "cdi", "Chodri" }, + { "cdj", "Churahi" }, + { "cdm", "Chepang" }, + { "cdn", "Chaudangsi" }, + { "cdo", "Min Dong Chinese" }, + { "cdr", "Cinda-Regi-Tiyal" }, + { "cds", "Chadian Sign Language" }, + { "cdy", "Chadong" }, + { "cdz", "Koda" }, + { "cea", "Lower Chehalis" }, + { "ceb", "Cebuano" }, + { "ceg", "Chamacoco" }, + { "cek", "Eastern Khumi Chin" }, + { "cen", "Cen" }, + { "ces", "Czech" }, + { "cet", "Centúúm" }, + { "cfa", "Dijim-Bwilim" }, + { "cfd", "Cara" }, + { "cfg", "Como Karim" }, + { "cfm", "Falam Chin" }, + { "cga", "Changriwa" }, + { "cgc", "Kagayanen" }, + { "cgg", "Chiga" }, + { "cgk", "Chocangacakha" }, + { "cha", "Chamorro" }, + { "chb", "Chibcha" }, + { "chc", "Catawba" }, + { "chd", "Highland Oaxaca Chontal" }, + { "che", "Chechen" }, + { "chf", "Tabasco Chontal" }, + { "chg", "Chagatai" }, + { "chh", "Chinook" }, + { "chj", "Ojitlán Chinantec" }, + { "chk", "Chuukese" }, + { "chl", "Cahuilla" }, + { "chm", "Mari (Russia)" }, + { "chn", "Chinook jargon" }, + { "cho", "Choctaw" }, + { "chp", "Chipewyan" }, + { "chq", "Quiotepec Chinantec" }, + { "chr", "Cherokee" }, + { "cht", "Cholón" }, + { "chu", "Church Slavic" }, + { "chv", "Chuvash" }, + { "chw", "Chuwabu" }, + { "chx", "Chantyal" }, + { "chy", "Cheyenne" }, + { "chz", "Ozumacín Chinantec" }, + { "cia", "Cia-Cia" }, + { "cib", "Ci Gbe" }, + { "cic", "Chickasaw" }, + { "cid", "Chimariko" }, + { "cie", "Cineni" }, + { "cih", "Chinali" }, + { "cik", "Chitkuli Kinnauri" }, + { "cim", "Cimbrian" }, + { "cin", "Cinta Larga" }, + { "cip", "Chiapanec" }, + { "cir", "Tiri" }, + { "ciw", "Chippewa" }, + { "ciy", "Chaima" }, + { "cja", "Western Cham" }, + { "cje", "Chru" }, + { "cjh", "Upper Chehalis" }, + { "cji", "Chamalal" }, + { "cjk", "Chokwe" }, + { "cjm", "Eastern Cham" }, + { "cjn", "Chenapian" }, + { "cjo", "Ashéninka Pajonal" }, + { "cjp", "Cabécar" }, + { "cjs", "Shor" }, + { "cjv", "Chuave" }, + { "cjy", "Jinyu Chinese" }, + { "ckb", "Central Kurdish" }, + { "ckh", "Chak" }, + { "ckl", "Cibak" }, + { "ckn", "Kaang Chin" }, + { "cko", "Anufo" }, + { "ckq", "Kajakse" }, + { "ckr", "Kairak" }, + { "cks", "Tayo" }, + { "ckt", "Chukot" }, + { "cku", "Koasati" }, + { "ckv", "Kavalan" }, + { "ckx", "Caka" }, + { "cky", "Cakfem-Mushere" }, + { "ckz", "Cakchiquel-Quiché Mixed Language" }, + { "cla", "Ron" }, + { "clc", "Chilcotin" }, + { "cld", "Chaldean Neo-Aramaic" }, + { "cle", "Lealao Chinantec" }, + { "clh", "Chilisso" }, + { "cli", "Chakali" }, + { "clj", "Laitu Chin" }, + { "clk", "Idu-Mishmi" }, + { "cll", "Chala" }, + { "clm", "Clallam" }, + { "clo", "Lowland Oaxaca Chontal" }, + { "clt", "Lautu Chin" }, + { "clu", "Caluyanun" }, + { "clw", "Chulym" }, + { "cly", "Eastern Highland Chatino" }, + { "cma", "Maa" }, + { "cme", "Cerma" }, + { "cmg", "Classical Mongolian" }, + { "cmi", "Emberá-Chamí" }, + { "cml", "Campalagian" }, + { "cmm", "Michigamea" }, + { "cmn", "Mandarin Chinese" }, + { "cmo", "Central Mnong" }, + { "cmr", "Mro-Khimi Chin" }, + { "cms", "Messapic" }, + { "cmt", "Camtho" }, + { "cna", "Changthang" }, + { "cnb", "Chinbon Chin" }, + { "cnc", "Côông" }, + { "cng", "Northern Qiang" }, + { "cnh", "Haka Chin" }, + { "cni", "Asháninka" }, + { "cnk", "Khumi Chin" }, + { "cnl", "Lalana Chinantec" }, + { "cno", "Con" }, + { "cns", "Central Asmat" }, + { "cnt", "Tepetotutla Chinantec" }, + { "cnu", "Chenoua" }, + { "cnw", "Ngawn Chin" }, + { "cnx", "Middle Cornish" }, + { "coa", "Cocos Islands Malay" }, + { "cob", "Chicomuceltec" }, + { "coc", "Cocopa" }, + { "cod", "Cocama-Cocamilla" }, + { "coe", "Koreguaje" }, + { "cof", "Colorado" }, + { "cog", "Chong" }, + { "coh", "Chonyi-Dzihana-Kauma" }, + { "coj", "Cochimi" }, + { "cok", "Santa Teresa Cora" }, + { "col", "Columbia-Wenatchi" }, + { "com", "Comanche" }, + { "con", "Cofán" }, + { "coo", "Comox" }, + { "cop", "Coptic" }, + { "coq", "Coquille" }, + { "cor", "Cornish" }, + { "cos", "Corsican" }, + { "cot", "Caquinte" }, + { "cou", "Wamey" }, + { "cov", "Cao Miao" }, + { "cow", "Cowlitz" }, + { "cox", "Nanti" }, + { "coy", "Coyaima" }, + { "coz", "Chochotec" }, + { "cpa", "Palantla Chinantec" }, + { "cpb", "Ucayali-Yurúa Ashéninka" }, + { "cpc", "Ajyíninka Apurucayali" }, + { "cpg", "Cappadocian Greek" }, + { "cpi", "Chinese Pidgin English" }, + { "cpn", "Cherepon" }, + { "cpo", "Kpeego" }, + { "cps", "Capiznon" }, + { "cpu", "Pichis Ashéninka" }, + { "cpx", "Pu-Xian Chinese" }, + { "cpy", "South Ucayali Ashéninka" }, + { "cqd", "Chuanqiandian Cluster Miao" }, + { "cqu", "Chilean Quechua" }, + { "cra", "Chara" }, + { "crb", "Island Carib" }, + { "crc", "Lonwolwol" }, + { "crd", "Coeur d'Alene" }, + { "cre", "Cree" }, + { "crf", "Caramanta" }, + { "crg", "Michif" }, + { "crh", "Crimean Tatar" }, + { "cri", "Sãotomense" }, + { "crj", "Southern East Cree" }, + { "crk", "Plains Cree" }, + { "crl", "Northern East Cree" }, + { "crm", "Moose Cree" }, + { "crn", "El Nayar Cora" }, + { "cro", "Crow" }, + { "crq", "Iyo'wujwa Chorote" }, + { "crr", "Carolina Algonquian" }, + { "crs", "Seselwa Creole French" }, + { "crt", "Iyojwa'ja Chorote" }, + { "crv", "Chaura" }, + { "crw", "Chrau" }, + { "crx", "Carrier" }, + { "cry", "Cori" }, + { "crz", "Cruzeño" }, + { "csa", "Chiltepec Chinantec" }, + { "csb", "Kashubian" }, + { "csc", "Catalan Sign Language" }, + { "csd", "Chiangmai Sign Language" }, + { "cse", "Czech Sign Language" }, + { "csf", "Cuba Sign Language" }, + { "csg", "Chilean Sign Language" }, + { "csh", "Asho Chin" }, + { "csi", "Coast Miwok" }, + { "csj", "Songlai Chin" }, + { "csk", "Jola-Kasa" }, + { "csl", "Chinese Sign Language" }, + { "csm", "Central Sierra Miwok" }, + { "csn", "Colombian Sign Language" }, + { "cso", "Sochiapam Chinantec" }, + { "csq", "Croatia Sign Language" }, + { "csr", "Costa Rican Sign Language" }, + { "css", "Southern Ohlone" }, + { "cst", "Northern Ohlone" }, + { "csv", "Sumtu Chin" }, + { "csw", "Swampy Cree" }, + { "csy", "Siyin Chin" }, + { "csz", "Coos" }, + { "cta", "Tataltepec Chatino" }, + { "ctc", "Chetco" }, + { "ctd", "Tedim Chin" }, + { "cte", "Tepinapa Chinantec" }, + { "ctg", "Chittagonian" }, + { "cth", "Thaiphum Chin" }, + { "ctl", "Tlacoatzintepec Chinantec" }, + { "ctm", "Chitimacha" }, + { "ctn", "Chhintange" }, + { "cto", "Emberá-Catío" }, + { "ctp", "Western Highland Chatino" }, + { "cts", "Northern Catanduanes Bikol" }, + { "ctt", "Wayanad Chetti" }, + { "ctu", "Chol" }, + { "ctz", "Zacatepec Chatino" }, + { "cua", "Cua" }, + { "cub", "Cubeo" }, + { "cuc", "Usila Chinantec" }, + { "cug", "Cung" }, + { "cuh", "Chuka" }, + { "cui", "Cuiba" }, + { "cuj", "Mashco Piro" }, + { "cuk", "San Blas Kuna" }, + { "cul", "Culina" }, + { "cum", "Cumeral" }, + { "cuo", "Cumanagoto" }, + { "cup", "Cupeño" }, + { "cuq", "Cun" }, + { "cur", "Chhulung" }, + { "cut", "Teutila Cuicatec" }, + { "cuu", "Tai Ya" }, + { "cuv", "Cuvok" }, + { "cuw", "Chukwa" }, + { "cux", "Tepeuxila Cuicatec" }, + { "cvg", "Chug" }, + { "cvn", "Valle Nacional Chinantec" }, + { "cwa", "Kabwa" }, + { "cwb", "Maindo" }, + { "cwd", "Woods Cree" }, + { "cwe", "Kwere" }, + { "cwg", "Chewong" }, + { "cwt", "Kuwaataay" }, + { "cya", "Nopala Chatino" }, + { "cyb", "Cayubaba" }, + { "cym", "Welsh" }, + { "cyo", "Cuyonon" }, + { "czh", "Huizhou Chinese" }, + { "czk", "Knaanic" }, + { "czn", "Zenzontepec Chatino" }, + { "czo", "Min Zhong Chinese" }, + { "czt", "Zotung Chin" }, + { "daa", "Dangaléat" }, + { "dac", "Dambi" }, + { "dad", "Marik" }, + { "dae", "Duupa" }, + { "dag", "Dagbani" }, + { "dah", "Gwahatike" }, + { "dai", "Day" }, + { "daj", "Dar Fur Daju" }, + { "dak", "Dakota" }, + { "dal", "Dahalo" }, + { "dam", "Damakawa" }, + { "dan", "Danish" }, + { "dao", "Daai Chin" }, + { "daq", "Dandami Maria" }, + { "dar", "Dargwa" }, + { "das", "Daho-Doo" }, + { "dau", "Dar Sila Daju" }, + { "dav", "Taita" }, + { "daw", "Davawenyo" }, + { "dax", "Dayi" }, + { "daz", "Dao" }, + { "dba", "Bangime" }, + { "dbb", "Deno" }, + { "dbd", "Dadiya" }, + { "dbe", "Dabe" }, + { "dbf", "Edopi" }, + { "dbg", "Dogul Dom Dogon" }, + { "dbi", "Doka" }, + { "dbj", "Ida'an" }, + { "dbl", "Dyirbal" }, + { "dbm", "Duguri" }, + { "dbn", "Duriankere" }, + { "dbo", "Dulbu" }, + { "dbp", "Duwai" }, + { "dbq", "Daba" }, + { "dbr", "Dabarre" }, + { "dbt", "Ben Tey Dogon" }, + { "dbu", "Bondum Dom Dogon" }, + { "dbv", "Dungu" }, + { "dbw", "Bankan Tey Dogon" }, + { "dby", "Dibiyaso" }, + { "dcc", "Deccan" }, + { "dcr", "Negerhollands" }, + { "dda", "Dadi Dadi" }, + { "ddd", "Dongotono" }, + { "dde", "Doondo" }, + { "ddg", "Fataluku" }, + { "ddi", "West Goodenough" }, + { "ddj", "Jaru" }, + { "ddn", "Dendi (Benin)" }, + { "ddo", "Dido" }, + { "ddr", "Dhudhuroa" }, + { "dds", "Donno So Dogon" }, + { "ddw", "Dawera-Daweloor" }, + { "dec", "Dagik" }, + { "ded", "Dedua" }, + { "dee", "Dewoin" }, + { "def", "Dezfuli" }, + { "deg", "Degema" }, + { "deh", "Dehwari" }, + { "dei", "Demisa" }, + { "dek", "Dek" }, + { "del", "Delaware" }, + { "dem", "Dem" }, + { "den", "Slave (Athapascan)" }, + { "dep", "Pidgin Delaware" }, + { "deq", "Dendi (Central African Republic)" }, + { "der", "Deori" }, + { "des", "Desano" }, + { "deu", "German" }, + { "dev", "Domung" }, + { "dez", "Dengese" }, + { "dga", "Southern Dagaare" }, + { "dgb", "Bunoge Dogon" }, + { "dgc", "Casiguran Dumagat Agta" }, + { "dgd", "Dagaari Dioula" }, + { "dge", "Degenan" }, + { "dgg", "Doga" }, + { "dgh", "Dghwede" }, + { "dgi", "Northern Dagara" }, + { "dgk", "Dagba" }, + { "dgl", "Andaandi" }, + { "dgn", "Dagoman" }, + { "dgo", "Dogri (individual language)" }, + { "dgr", "Dogrib" }, + { "dgs", "Dogoso" }, + { "dgt", "Ndra'ngith" }, + { "dgu", "Degaru" }, + { "dgw", "Daungwurrung" }, + { "dgx", "Doghoro" }, + { "dgz", "Daga" }, + { "dhd", "Dhundari" }, + { "dhg", "Djangu" }, + { "dhi", "Dhimal" }, + { "dhl", "Dhalandji" }, + { "dhm", "Zemba" }, + { "dhn", "Dhanki" }, + { "dho", "Dhodia" }, + { "dhr", "Dhargari" }, + { "dhs", "Dhaiso" }, + { "dhu", "Dhurga" }, + { "dhv", "Dehu" }, + { "dhw", "Dhanwar (Nepal)" }, + { "dhx", "Dhungaloo" }, + { "dia", "Dia" }, + { "dib", "South Central Dinka" }, + { "dic", "Lakota Dida" }, + { "did", "Didinga" }, + { "dif", "Dieri" }, + { "dig", "Digo" }, + { "dih", "Kumiai" }, + { "dii", "Dimbong" }, + { "dij", "Dai" }, + { "dik", "Southwestern Dinka" }, + { "dil", "Dilling" }, + { "dim", "Dime" }, + { "din", "Dinka" }, + { "dio", "Dibo" }, + { "dip", "Northeastern Dinka" }, + { "diq", "Dimli (individual language)" }, + { "dir", "Dirim" }, + { "dis", "Dimasa" }, + { "dit", "Dirari" }, + { "diu", "Diriku" }, + { "div", "Dhivehi" }, + { "diw", "Northwestern Dinka" }, + { "dix", "Dixon Reef" }, + { "diy", "Diuwe" }, + { "diz", "Ding" }, + { "dja", "Djadjawurrung" }, + { "djb", "Djinba" }, + { "djc", "Dar Daju Daju" }, + { "djd", "Djamindjung" }, + { "dje", "Zarma" }, + { "djf", "Djangun" }, + { "dji", "Djinang" }, + { "djj", "Djeebbana" }, + { "djk", "Eastern Maroon Creole" }, + { "djm", "Jamsay Dogon" }, + { "djn", "Djauan" }, + { "djo", "Jangkang" }, + { "djr", "Djambarrpuyngu" }, + { "dju", "Kapriman" }, + { "djw", "Djawi" }, + { "dka", "Dakpakha" }, + { "dkk", "Dakka" }, + { "dkr", "Kuijau" }, + { "dks", "Southeastern Dinka" }, + { "dkx", "Mazagway" }, + { "dlg", "Dolgan" }, + { "dlk", "Dahalik" }, + { "dlm", "Dalmatian" }, + { "dln", "Darlong" }, + { "dma", "Duma" }, + { "dmb", "Mombo Dogon" }, + { "dmc", "Gavak" }, + { "dmd", "Madhi Madhi" }, + { "dme", "Dugwor" }, + { "dmg", "Upper Kinabatangan" }, + { "dmk", "Domaaki" }, + { "dml", "Dameli" }, + { "dmm", "Dama" }, + { "dmo", "Kemedzung" }, + { "dmr", "East Damar" }, + { "dms", "Dampelas" }, + { "dmu", "Dubu" }, + { "dmv", "Dumpas" }, + { "dmw", "Mudburra" }, + { "dmx", "Dema" }, + { "dmy", "Demta" }, + { "dna", "Upper Grand Valley Dani" }, + { "dnd", "Daonda" }, + { "dne", "Ndendeule" }, + { "dng", "Dungan" }, + { "dni", "Lower Grand Valley Dani" }, + { "dnj", "Dan" }, + { "dnk", "Dengka" }, + { "dnn", "Dzùùngoo" }, + { "dnr", "Danaru" }, + { "dnt", "Mid Grand Valley Dani" }, + { "dnu", "Danau" }, + { "dnv", "Danu" }, + { "dnw", "Western Dani" }, + { "dny", "Dení" }, + { "doa", "Dom" }, + { "dob", "Dobu" }, + { "doc", "Northern Dong" }, + { "doe", "Doe" }, + { "dof", "Domu" }, + { "doh", "Dong" }, + { "doi", "Dogri (macrolanguage)" }, + { "dok", "Dondo" }, + { "dol", "Doso" }, + { "don", "Toura (Papua New Guinea)" }, + { "doo", "Dongo" }, + { "dop", "Lukpa" }, + { "doq", "Dominican Sign Language" }, + { "dor", "Dori'o" }, + { "dos", "Dogosé" }, + { "dot", "Dass" }, + { "dov", "Dombe" }, + { "dow", "Doyayo" }, + { "dox", "Bussa" }, + { "doy", "Dompo" }, + { "doz", "Dorze" }, + { "dpp", "Papar" }, + { "drb", "Dair" }, + { "drc", "Minderico" }, + { "drd", "Darmiya" }, + { "dre", "Dolpo" }, + { "drg", "Rungus" }, + { "dri", "C'lela" }, + { "drl", "Paakantyi" }, + { "drn", "West Damar" }, + { "dro", "Daro-Matu Melanau" }, + { "drq", "Dura" }, + { "drr", "Dororo" }, + { "drs", "Gedeo" }, + { "drt", "Drents" }, + { "dru", "Rukai" }, + { "dry", "Darai" }, + { "dsb", "Lower Sorbian" }, + { "dse", "Dutch Sign Language" }, + { "dsh", "Daasanach" }, + { "dsi", "Disa" }, + { "dsl", "Danish Sign Language" }, + { "dsn", "Dusner" }, + { "dso", "Desiya" }, + { "dsq", "Tadaksahak" }, + { "dta", "Daur" }, + { "dtb", "Labuk-Kinabatangan Kadazan" }, + { "dtd", "Ditidaht" }, + { "dth", "Adithinngithigh" }, + { "dti", "Ana Tinga Dogon" }, + { "dtk", "Tene Kan Dogon" }, + { "dtm", "Tomo Kan Dogon" }, + { "dto", "Tommo So Dogon" }, + { "dtp", "Central Dusun" }, + { "dtr", "Lotud" }, + { "dts", "Toro So Dogon" }, + { "dtt", "Toro Tegu Dogon" }, + { "dtu", "Tebul Ure Dogon" }, + { "dty", "Dotyali" }, + { "dua", "Duala" }, + { "dub", "Dubli" }, + { "duc", "Duna" }, + { "dud", "Hun-Saare" }, + { "due", "Umiray Dumaget Agta" }, + { "duf", "Dumbea" }, + { "dug", "Duruma" }, + { "duh", "Dungra Bhil" }, + { "dui", "Dumun" }, + { "duj", "Dhuwal" }, + { "duk", "Uyajitaya" }, + { "dul", "Alabat Island Agta" }, + { "dum", "Middle Dutch (ca. 1050-1350)" }, + { "dun", "Dusun Deyah" }, + { "duo", "Dupaninan Agta" }, + { "dup", "Duano" }, + { "duq", "Dusun Malang" }, + { "dur", "Dii" }, + { "dus", "Dumi" }, + { "duu", "Drung" }, + { "duv", "Duvle" }, + { "duw", "Dusun Witu" }, + { "dux", "Duungooma" }, + { "duy", "Dicamay Agta" }, + { "duz", "Duli" }, + { "dva", "Duau" }, + { "dwa", "Diri" }, + { "dwr", "Dawro" }, + { "dws", "Dutton World Speedwords" }, + { "dww", "Dawawa" }, + { "dya", "Dyan" }, + { "dyb", "Dyaberdyaber" }, + { "dyd", "Dyugun" }, + { "dyg", "Villa Viciosa Agta" }, + { "dyi", "Djimini Senoufo" }, + { "dym", "Yanda Dom Dogon" }, + { "dyn", "Dyangadi" }, + { "dyo", "Jola-Fonyi" }, + { "dyu", "Dyula" }, + { "dyy", "Dyaabugay" }, + { "dza", "Tunzu" }, + { "dzd", "Daza" }, + { "dze", "Djiwarli" }, + { "dzg", "Dazaga" }, + { "dzl", "Dzalakha" }, + { "dzn", "Dzando" }, + { "dzo", "Dzongkha" }, + { "eaa", "Karenggapa" }, + { "ebg", "Ebughu" }, + { "ebk", "Eastern Bontok" }, + { "ebo", "Teke-Ebo" }, + { "ebr", "Ebrié" }, + { "ebu", "Embu" }, + { "ecr", "Eteocretan" }, + { "ecs", "Ecuadorian Sign Language" }, + { "ecy", "Eteocypriot" }, + { "eee", "E" }, + { "efa", "Efai" }, + { "efe", "Efe" }, + { "efi", "Efik" }, + { "ega", "Ega" }, + { "egl", "Emilian" }, + { "ego", "Eggon" }, + { "egy", "Egyptian (Ancient)" }, + { "ehu", "Ehueun" }, + { "eip", "Eipomek" }, + { "eit", "Eitiep" }, + { "eiv", "Askopan" }, + { "eja", "Ejamat" }, + { "eka", "Ekajuk" }, + { "ekc", "Eastern Karnic" }, + { "eke", "Ekit" }, + { "ekg", "Ekari" }, + { "eki", "Eki" }, + { "ekk", "Standard Estonian" }, + { "ekl", "Kol (Bangladesh)" }, + { "ekm", "Elip" }, + { "eko", "Koti" }, + { "ekp", "Ekpeye" }, + { "ekr", "Yace" }, + { "eky", "Eastern Kayah" }, + { "ele", "Elepi" }, + { "elh", "El Hugeirat" }, + { "eli", "Nding" }, + { "elk", "Elkei" }, + { "ell", "Modern Greek (1453-)" }, + { "elm", "Eleme" }, + { "elo", "El Molo" }, + { "elu", "Elu" }, + { "elx", "Elamite" }, + { "ema", "Emai-Iuleha-Ora" }, + { "emb", "Embaloh" }, + { "eme", "Emerillon" }, + { "emg", "Eastern Meohang" }, + { "emi", "Mussau-Emira" }, + { "emk", "Eastern Maninkakan" }, + { "emm", "Mamulique" }, + { "emn", "Eman" }, + { "emo", "Emok" }, + { "emp", "Northern Emberá" }, + { "ems", "Pacific Gulf Yupik" }, + { "emu", "Eastern Muria" }, + { "emw", "Emplawas" }, + { "emx", "Erromintxela" }, + { "emy", "Epigraphic Mayan" }, + { "ena", "Apali" }, + { "enb", "Markweeta" }, + { "enc", "En" }, + { "end", "Ende" }, + { "enf", "Forest Enets" }, + { "eng", "English" }, + { "enh", "Tundra Enets" }, + { "enm", "Middle English (1100-1500)" }, + { "enn", "Engenni" }, + { "eno", "Enggano" }, + { "enq", "Enga" }, + { "enr", "Emumu" }, + { "enu", "Enu" }, + { "env", "Enwan (Edu State)" }, + { "enw", "Enwan (Akwa Ibom State)" }, + { "eot", "Beti (Côte d'Ivoire)" }, + { "epi", "Epie" }, + { "epo", "Esperanto" }, + { "era", "Eravallan" }, + { "erg", "Sie" }, + { "erh", "Eruwa" }, + { "eri", "Ogea" }, + { "erk", "South Efate" }, + { "ero", "Horpa" }, + { "err", "Erre" }, + { "ers", "Ersu" }, + { "ert", "Eritai" }, + { "erw", "Erokwanas" }, + { "ese", "Ese Ejja" }, + { "esh", "Eshtehardi" }, + { "esi", "North Alaskan Inupiatun" }, + { "esk", "Northwest Alaska Inupiatun" }, + { "esl", "Egypt Sign Language" }, + { "esm", "Esuma" }, + { "esn", "Salvadoran Sign Language" }, + { "eso", "Estonian Sign Language" }, + { "esq", "Esselen" }, + { "ess", "Central Siberian Yupik" }, + { "est", "Estonian" }, + { "esu", "Central Yupik" }, + { "etb", "Etebi" }, + { "etc", "Etchemin" }, + { "eth", "Ethiopian Sign Language" }, + { "etn", "Eton (Vanuatu)" }, + { "eto", "Eton (Cameroon)" }, + { "etr", "Edolo" }, + { "ets", "Yekhee" }, + { "ett", "Etruscan" }, + { "etu", "Ejagham" }, + { "etx", "Eten" }, + { "etz", "Semimi" }, + { "eus", "Basque" }, + { "eve", "Even" }, + { "evh", "Uvbie" }, + { "evn", "Evenki" }, + { "ewe", "Ewe" }, + { "ewo", "Ewondo" }, + { "ext", "Extremaduran" }, + { "eya", "Eyak" }, + { "eyo", "Keiyo" }, + { "eza", "Ezaa" }, + { "eze", "Uzekwe" }, + { "faa", "Fasu" }, + { "fab", "Fa d'Ambu" }, + { "fad", "Wagi" }, + { "faf", "Fagani" }, + { "fag", "Finongan" }, + { "fah", "Baissa Fali" }, + { "fai", "Faiwol" }, + { "faj", "Faita" }, + { "fak", "Fang (Cameroon)" }, + { "fal", "South Fali" }, + { "fam", "Fam" }, + { "fan", "Fang (Equatorial Guinea)" }, + { "fao", "Faroese" }, + { "fap", "Palor" }, + { "far", "Fataleka" }, + { "fas", "Persian" }, + { "fat", "Fanti" }, + { "fau", "Fayu" }, + { "fax", "Fala" }, + { "fay", "Southwestern Fars" }, + { "faz", "Northwestern Fars" }, + { "fbl", "West Albay Bikol" }, + { "fcs", "Quebec Sign Language" }, + { "fer", "Feroge" }, + { "ffi", "Foia Foia" }, + { "ffm", "Maasina Fulfulde" }, + { "fgr", "Fongoro" }, + { "fia", "Nobiin" }, + { "fie", "Fyer" }, + { "fij", "Fijian" }, + { "fil", "Filipino" }, + { "fin", "Finnish" }, + { "fip", "Fipa" }, + { "fir", "Firan" }, + { "fit", "Tornedalen Finnish" }, + { "fiw", "Fiwaga" }, + { "fkk", "Kirya-Konzəl" }, + { "fkv", "Kven Finnish" }, + { "fla", "Kalispel-Pend d'Oreille" }, + { "flh", "Foau" }, + { "fli", "Fali" }, + { "fll", "North Fali" }, + { "fln", "Flinders Island" }, + { "flr", "Fuliiru" }, + { "fly", "Tsotsitaal" }, + { "fmp", "Fe'fe'" }, + { "fmu", "Far Western Muria" }, + { "fng", "Fanagalo" }, + { "fni", "Fania" }, + { "fod", "Foodo" }, + { "foi", "Foi" }, + { "fom", "Foma" }, + { "fon", "Fon" }, + { "for", "Fore" }, + { "fos", "Siraya" }, + { "fpe", "Fernando Po Creole English" }, + { "fqs", "Fas" }, + { "fra", "French" }, + { "frc", "Cajun French" }, + { "frd", "Fordata" }, + { "frk", "Frankish" }, + { "frm", "Middle French (ca. 1400-1600)" }, + { "fro", "Old French (842-ca. 1400)" }, + { "frp", "Arpitan" }, + { "frq", "Forak" }, + { "frr", "Northern Frisian" }, + { "frs", "Eastern Frisian" }, + { "frt", "Fortsenal" }, + { "fry", "Western Frisian" }, + { "fse", "Finnish Sign Language" }, + { "fsl", "French Sign Language" }, + { "fss", "Finland-Swedish Sign Language" }, + { "fub", "Adamawa Fulfulde" }, + { "fuc", "Pulaar" }, + { "fud", "East Futuna" }, + { "fue", "Borgu Fulfulde" }, + { "fuf", "Pular" }, + { "fuh", "Western Niger Fulfulde" }, + { "fui", "Bagirmi Fulfulde" }, + { "fuj", "Ko" }, + { "ful", "Fulah" }, + { "fum", "Fum" }, + { "fun", "Fulniô" }, + { "fuq", "Central-Eastern Niger Fulfulde" }, + { "fur", "Friulian" }, + { "fut", "Futuna-Aniwa" }, + { "fuu", "Furu" }, + { "fuv", "Nigerian Fulfulde" }, + { "fuy", "Fuyug" }, + { "fvr", "Fur" }, + { "fwa", "Fwâi" }, + { "fwe", "Fwe" }, + { "gaa", "Ga" }, + { "gab", "Gabri" }, + { "gac", "Mixed Great Andamanese" }, + { "gad", "Gaddang" }, + { "gae", "Guarequena" }, + { "gaf", "Gende" }, + { "gag", "Gagauz" }, + { "gah", "Alekano" }, + { "gai", "Borei" }, + { "gaj", "Gadsup" }, + { "gak", "Gamkonora" }, + { "gal", "Galolen" }, + { "gam", "Kandawo" }, + { "gan", "Gan Chinese" }, + { "gao", "Gants" }, + { "gap", "Gal" }, + { "gaq", "Gata'" }, + { "gar", "Galeya" }, + { "gas", "Adiwasi Garasia" }, + { "gat", "Kenati" }, + { "gau", "Mudhili Gadaba" }, + { "gaw", "Nobonob" }, + { "gax", "Borana-Arsi-Guji Oromo" }, + { "gay", "Gayo" }, + { "gaz", "West Central Oromo" }, + { "gba", "Gbaya (Central African Republic)" }, + { "gbb", "Kaytetye" }, + { "gbd", "Karadjeri" }, + { "gbe", "Niksek" }, + { "gbf", "Gaikundi" }, + { "gbg", "Gbanziri" }, + { "gbh", "Defi Gbe" }, + { "gbi", "Galela" }, + { "gbj", "Bodo Gadaba" }, + { "gbk", "Gaddi" }, + { "gbl", "Gamit" }, + { "gbm", "Garhwali" }, + { "gbn", "Mo'da" }, + { "gbo", "Northern Grebo" }, + { "gbp", "Gbaya-Bossangoa" }, + { "gbq", "Gbaya-Bozoum" }, + { "gbr", "Gbagyi" }, + { "gbs", "Gbesi Gbe" }, + { "gbu", "Gagadu" }, + { "gbv", "Gbanu" }, + { "gbw", "Gabi-Gabi" }, + { "gbx", "Eastern Xwla Gbe" }, + { "gby", "Gbari" }, + { "gbz", "Zoroastrian Dari" }, + { "gcc", "Mali" }, + { "gcd", "Ganggalida" }, + { "gce", "Galice" }, + { "gcf", "Guadeloupean Creole French" }, + { "gcl", "Grenadian Creole English" }, + { "gcn", "Gaina" }, + { "gcr", "Guianese Creole French" }, + { "gct", "Colonia Tovar German" }, + { "gda", "Gade Lohar" }, + { "gdb", "Pottangi Ollar Gadaba" }, + { "gdc", "Gugu Badhun" }, + { "gdd", "Gedaged" }, + { "gde", "Gude" }, + { "gdf", "Guduf-Gava" }, + { "gdg", "Ga'dang" }, + { "gdh", "Gadjerawang" }, + { "gdi", "Gundi" }, + { "gdj", "Gurdjar" }, + { "gdk", "Gadang" }, + { "gdl", "Dirasha" }, + { "gdm", "Laal" }, + { "gdn", "Umanakaina" }, + { "gdo", "Ghodoberi" }, + { "gdq", "Mehri" }, + { "gdr", "Wipi" }, + { "gds", "Ghandruk Sign Language" }, + { "gdt", "Kungardutyi" }, + { "gdu", "Gudu" }, + { "gdx", "Godwari" }, + { "gea", "Geruma" }, + { "geb", "Kire" }, + { "gec", "Gboloo Grebo" }, + { "ged", "Gade" }, + { "geg", "Gengle" }, + { "geh", "Hutterite German" }, + { "gei", "Gebe" }, + { "gej", "Gen" }, + { "gek", "Yiwom" }, + { "gel", "ut-Ma'in" }, + { "geq", "Geme" }, + { "ges", "Geser-Gorom" }, + { "gew", "Gera" }, + { "gex", "Garre" }, + { "gey", "Enya" }, + { "gez", "Geez" }, + { "gfk", "Patpatar" }, + { "gft", "Gafat" }, + { "gfx", "Mangetti Dune !Xung" }, + { "gga", "Gao" }, + { "ggb", "Gbii" }, + { "ggd", "Gugadj" }, + { "gge", "Guragone" }, + { "ggg", "Gurgula" }, + { "ggk", "Kungarakany" }, + { "ggl", "Ganglau" }, + { "ggm", "Gugu Mini" }, + { "ggn", "Eastern Gurung" }, + { "ggo", "Southern Gondi" }, + { "ggt", "Gitua" }, + { "ggu", "Gagu" }, + { "ggw", "Gogodala" }, + { "gha", "Ghadamès" }, + { "ghc", "Hiberno-Scottish Gaelic" }, + { "ghe", "Southern Ghale" }, + { "ghh", "Northern Ghale" }, + { "ghk", "Geko Karen" }, + { "ghl", "Ghulfan" }, + { "ghn", "Ghanongga" }, + { "gho", "Ghomara" }, + { "ghr", "Ghera" }, + { "ghs", "Guhu-Samane" }, + { "ght", "Kuke" }, + { "gia", "Kitja" }, + { "gib", "Gibanawa" }, + { "gic", "Gail" }, + { "gid", "Gidar" }, + { "gig", "Goaria" }, + { "gih", "Githabul" }, + { "gil", "Gilbertese" }, + { "gim", "Gimi (Eastern Highlands)" }, + { "gin", "Hinukh" }, + { "gip", "Gimi (West New Britain)" }, + { "giq", "Green Gelao" }, + { "gir", "Red Gelao" }, + { "gis", "North Giziga" }, + { "git", "Gitxsan" }, + { "giu", "Mulao" }, + { "giw", "White Gelao" }, + { "gix", "Gilima" }, + { "giy", "Giyug" }, + { "giz", "South Giziga" }, + { "gji", "Geji" }, + { "gjk", "Kachi Koli" }, + { "gjm", "Gunditjmara" }, + { "gjn", "Gonja" }, + { "gju", "Gujari" }, + { "gka", "Guya" }, + { "gke", "Ndai" }, + { "gkn", "Gokana" }, + { "gko", "Kok-Nar" }, + { "gkp", "Guinea Kpelle" }, + { "gla", "Scottish Gaelic" }, + { "glc", "Bon Gula" }, + { "gld", "Nanai" }, + { "gle", "Irish" }, + { "glg", "Galician" }, + { "glh", "Northwest Pashayi" }, + { "gli", "Guliguli" }, + { "glj", "Gula Iro" }, + { "glk", "Gilaki" }, + { "gll", "Garlali" }, + { "glo", "Galambu" }, + { "glr", "Glaro-Twabo" }, + { "glu", "Gula (Chad)" }, + { "glv", "Manx" }, + { "glw", "Glavda" }, + { "gly", "Gule" }, + { "gma", "Gambera" }, + { "gmb", "Gula'alaa" }, + { "gmd", "Mághdì" }, + { "gmh", "Middle High German (ca. 1050-1500)" }, + { "gml", "Middle Low German" }, + { "gmm", "Gbaya-Mbodomo" }, + { "gmn", "Gimnime" }, + { "gmu", "Gumalu" }, + { "gmv", "Gamo" }, + { "gmx", "Magoma" }, + { "gmy", "Mycenaean Greek" }, + { "gmz", "Mgbolizhia" }, + { "gna", "Kaansa" }, + { "gnb", "Gangte" }, + { "gnc", "Guanche" }, + { "gnd", "Zulgo-Gemzek" }, + { "gne", "Ganang" }, + { "gng", "Ngangam" }, + { "gnh", "Lere" }, + { "gni", "Gooniyandi" }, + { "gnk", "Gana" }, + { "gnl", "Gangulu" }, + { "gnm", "Ginuman" }, + { "gnn", "Gumatj" }, + { "gno", "Northern Gondi" }, + { "gnq", "Gana" }, + { "gnr", "Gureng Gureng" }, + { "gnt", "Guntai" }, + { "gnu", "Gnau" }, + { "gnw", "Western Bolivian Guaraní" }, + { "gnz", "Ganzi" }, + { "goa", "Guro" }, + { "gob", "Playero" }, + { "goc", "Gorakor" }, + { "god", "Godié" }, + { "goe", "Gongduk" }, + { "gof", "Gofa" }, + { "gog", "Gogo" }, + { "goh", "Old High German (ca. 750-1050)" }, + { "goi", "Gobasi" }, + { "goj", "Gowlan" }, + { "gok", "Gowli" }, + { "gol", "Gola" }, + { "gom", "Goan Konkani" }, + { "gon", "Gondi" }, + { "goo", "Gone Dau" }, + { "gop", "Yeretuar" }, + { "goq", "Gorap" }, + { "gor", "Gorontalo" }, + { "gos", "Gronings" }, + { "got", "Gothic" }, + { "gou", "Gavar" }, + { "gow", "Gorowa" }, + { "gox", "Gobu" }, + { "goy", "Goundo" }, + { "goz", "Gozarkhani" }, + { "gpa", "Gupa-Abawa" }, + { "gpe", "Ghanaian Pidgin English" }, + { "gpn", "Taiap" }, + { "gqa", "Ga'anda" }, + { "gqi", "Guiqiong" }, + { "gqn", "Guana (Brazil)" }, + { "gqr", "Gor" }, + { "gqu", "Qau" }, + { "gra", "Rajput Garasia" }, + { "grb", "Grebo" }, + { "grc", "Ancient Greek (to 1453)" }, + { "grd", "Guruntum-Mbaaru" }, + { "grg", "Madi" }, + { "grh", "Gbiri-Niragu" }, + { "gri", "Ghari" }, + { "grj", "Southern Grebo" }, + { "grm", "Kota Marudu Talantang" }, + { "grn", "Guarani" }, + { "gro", "Groma" }, + { "grq", "Gorovu" }, + { "grr", "Taznatit" }, + { "grs", "Gresi" }, + { "grt", "Garo" }, + { "gru", "Kistane" }, + { "grv", "Central Grebo" }, + { "grw", "Gweda" }, + { "grx", "Guriaso" }, + { "gry", "Barclayville Grebo" }, + { "grz", "Guramalum" }, + { "gse", "Ghanaian Sign Language" }, + { "gsg", "German Sign Language" }, + { "gsl", "Gusilay" }, + { "gsm", "Guatemalan Sign Language" }, + { "gsn", "Gusan" }, + { "gso", "Southwest Gbaya" }, + { "gsp", "Wasembo" }, + { "gss", "Greek Sign Language" }, + { "gsw", "Swiss German" }, + { "gta", "Guató" }, + { "gti", "Gbati-ri" }, + { "gtu", "Aghu-Tharnggala" }, + { "gua", "Shiki" }, + { "gub", "Guajajára" }, + { "guc", "Wayuu" }, + { "gud", "Yocoboué Dida" }, + { "gue", "Gurinji" }, + { "guf", "Gupapuyngu" }, + { "gug", "Paraguayan Guaraní" }, + { "guh", "Guahibo" }, + { "gui", "Eastern Bolivian Guaraní" }, + { "guj", "Gujarati" }, + { "guk", "Gumuz" }, + { "gul", "Sea Island Creole English" }, + { "gum", "Guambiano" }, + { "gun", "Mbyá Guaraní" }, + { "guo", "Guayabero" }, + { "gup", "Gunwinggu" }, + { "guq", "Aché" }, + { "gur", "Farefare" }, + { "gus", "Guinean Sign Language" }, + { "gut", "Maléku Jaíka" }, + { "guu", "Yanomamö" }, + { "guv", "Gey" }, + { "guw", "Gun" }, + { "gux", "Gourmanchéma" }, + { "guz", "Gusii" }, + { "gva", "Guana (Paraguay)" }, + { "gvc", "Guanano" }, + { "gve", "Duwet" }, + { "gvf", "Golin" }, + { "gvj", "Guajá" }, + { "gvl", "Gulay" }, + { "gvm", "Gurmana" }, + { "gvn", "Kuku-Yalanji" }, + { "gvo", "Gavião Do Jiparaná" }, + { "gvp", "Pará Gavião" }, + { "gvr", "Western Gurung" }, + { "gvs", "Gumawana" }, + { "gvy", "Guyani" }, + { "gwa", "Mbato" }, + { "gwb", "Gwa" }, + { "gwc", "Kalami" }, + { "gwd", "Gawwada" }, + { "gwe", "Gweno" }, + { "gwf", "Gowro" }, + { "gwg", "Moo" }, + { "gwi", "Gwichʼin" }, + { "gwj", "Gwi" }, + { "gwm", "Awngthim" }, + { "gwn", "Gwandara" }, + { "gwr", "Gwere" }, + { "gwt", "Gawar-Bati" }, + { "gwu", "Guwamu" }, + { "gww", "Kwini" }, + { "gwx", "Gua" }, + { "gxx", "Wè Southern" }, + { "gya", "Northwest Gbaya" }, + { "gyb", "Garus" }, + { "gyd", "Kayardild" }, + { "gye", "Gyem" }, + { "gyf", "Gungabula" }, + { "gyg", "Gbayi" }, + { "gyi", "Gyele" }, + { "gyl", "Gayil" }, + { "gym", "Ngäbere" }, + { "gyn", "Guyanese Creole English" }, + { "gyr", "Guarayu" }, + { "gyy", "Gunya" }, + { "gza", "Ganza" }, + { "gzi", "Gazi" }, + { "gzn", "Gane" }, + { "haa", "Han" }, + { "hab", "Hanoi Sign Language" }, + { "hac", "Gurani" }, + { "had", "Hatam" }, + { "hae", "Eastern Oromo" }, + { "haf", "Haiphong Sign Language" }, + { "hag", "Hanga" }, + { "hah", "Hahon" }, + { "hai", "Haida" }, + { "haj", "Hajong" }, + { "hak", "Hakka Chinese" }, + { "hal", "Halang" }, + { "ham", "Hewa" }, + { "han", "Hangaza" }, + { "hao", "Hakö" }, + { "hap", "Hupla" }, + { "haq", "Ha" }, + { "har", "Harari" }, + { "has", "Haisla" }, + { "hat", "Haitian" }, + { "hau", "Hausa" }, + { "hav", "Havu" }, + { "haw", "Hawaiian" }, + { "hax", "Southern Haida" }, + { "hay", "Haya" }, + { "haz", "Hazaragi" }, + { "hba", "Hamba" }, + { "hbb", "Huba" }, + { "hbn", "Heiban" }, + { "hbo", "Ancient Hebrew" }, + { "hbs", "Serbo-Croatian" }, + { "hbu", "Habu" }, + { "hca", "Andaman Creole Hindi" }, + { "hch", "Huichol" }, + { "hdn", "Northern Haida" }, + { "hds", "Honduras Sign Language" }, + { "hdy", "Hadiyya" }, + { "hea", "Northern Qiandong Miao" }, + { "heb", "Hebrew" }, + { "hed", "Herdé" }, + { "heg", "Helong" }, + { "heh", "Hehe" }, + { "hei", "Heiltsuk" }, + { "hem", "Hemba" }, + { "her", "Herero" }, + { "hgm", "Haiom" }, + { "hgw", "Haigwai" }, + { "hhi", "Hoia Hoia" }, + { "hhr", "Kerak" }, + { "hhy", "Hoyahoya" }, + { "hia", "Lamang" }, + { "hib", "Hibito" }, + { "hid", "Hidatsa" }, + { "hif", "Fiji Hindi" }, + { "hig", "Kamwe" }, + { "hih", "Pamosu" }, + { "hii", "Hinduri" }, + { "hij", "Hijuk" }, + { "hik", "Seit-Kaitetu" }, + { "hil", "Hiligaynon" }, + { "hin", "Hindi" }, + { "hio", "Tsoa" }, + { "hir", "Himarimã" }, + { "hit", "Hittite" }, + { "hiw", "Hiw" }, + { "hix", "Hixkaryána" }, + { "hji", "Haji" }, + { "hka", "Kahe" }, + { "hke", "Hunde" }, + { "hkk", "Hunjara-Kaina Ke" }, + { "hks", "Hong Kong Sign Language" }, + { "hla", "Halia" }, + { "hlb", "Halbi" }, + { "hld", "Halang Doan" }, + { "hle", "Hlersu" }, + { "hlt", "Matu Chin" }, + { "hlu", "Hieroglyphic Luwian" }, + { "hma", "Southern Mashan Hmong" }, + { "hmb", "Humburi Senni Songhay" }, + { "hmc", "Central Huishui Hmong" }, + { "hmd", "Large Flowery Miao" }, + { "hme", "Eastern Huishui Hmong" }, + { "hmf", "Hmong Don" }, + { "hmg", "Southwestern Guiyang Hmong" }, + { "hmh", "Southwestern Huishui Hmong" }, + { "hmi", "Northern Huishui Hmong" }, + { "hmj", "Ge" }, + { "hmk", "Maek" }, + { "hml", "Luopohe Hmong" }, + { "hmm", "Central Mashan Hmong" }, + { "hmn", "Hmong" }, + { "hmo", "Hiri Motu" }, + { "hmp", "Northern Mashan Hmong" }, + { "hmq", "Eastern Qiandong Miao" }, + { "hmr", "Hmar" }, + { "hms", "Southern Qiandong Miao" }, + { "hmt", "Hamtai" }, + { "hmu", "Hamap" }, + { "hmv", "Hmong Dô" }, + { "hmw", "Western Mashan Hmong" }, + { "hmy", "Southern Guiyang Hmong" }, + { "hmz", "Hmong Shua" }, + { "hna", "Mina (Cameroon)" }, + { "hnd", "Southern Hindko" }, + { "hne", "Chhattisgarhi" }, + { "hnh", "Ani" }, + { "hni", "Hani" }, + { "hnj", "Hmong Njua" }, + { "hnn", "Hanunoo" }, + { "hno", "Northern Hindko" }, + { "hns", "Caribbean Hindustani" }, + { "hnu", "Hung" }, + { "hoa", "Hoava" }, + { "hob", "Mari (Madang Province)" }, + { "hoc", "Ho" }, + { "hod", "Holma" }, + { "hoe", "Horom" }, + { "hoh", "Hobyót" }, + { "hoi", "Holikachuk" }, + { "hoj", "Hadothi" }, + { "hol", "Holu" }, + { "hom", "Homa" }, + { "hoo", "Holoholo" }, + { "hop", "Hopi" }, + { "hor", "Horo" }, + { "hos", "Ho Chi Minh City Sign Language" }, + { "hot", "Hote" }, + { "hov", "Hovongan" }, + { "how", "Honi" }, + { "hoy", "Holiya" }, + { "hoz", "Hozo" }, + { "hpo", "Hpon" }, + { "hps", "Hawai'i Pidgin Sign Language" }, + { "hra", "Hrangkhol" }, + { "hrc", "Niwer Mil" }, + { "hre", "Hre" }, + { "hrk", "Haruku" }, + { "hrm", "Horned Miao" }, + { "hro", "Haroi" }, + { "hrp", "Nhirrpi" }, + { "hrt", "Hértevin" }, + { "hru", "Hruso" }, + { "hrv", "Croatian" }, + { "hrw", "Warwar Feni" }, + { "hrx", "Hunsrik" }, + { "hrz", "Harzani" }, + { "hsb", "Upper Sorbian" }, + { "hsh", "Hungarian Sign Language" }, + { "hsl", "Hausa Sign Language" }, + { "hsn", "Xiang Chinese" }, + { "hss", "Harsusi" }, + { "hti", "Hoti" }, + { "hto", "Minica Huitoto" }, + { "hts", "Hadza" }, + { "htu", "Hitu" }, + { "htx", "Middle Hittite" }, + { "hub", "Huambisa" }, + { "huc", "=Hua" }, + { "hud", "Huaulu" }, + { "hue", "San Francisco Del Mar Huave" }, + { "huf", "Humene" }, + { "hug", "Huachipaeri" }, + { "huh", "Huilliche" }, + { "hui", "Huli" }, + { "huj", "Northern Guiyang Hmong" }, + { "huk", "Hulung" }, + { "hul", "Hula" }, + { "hum", "Hungana" }, + { "hun", "Hungarian" }, + { "huo", "Hu" }, + { "hup", "Hupa" }, + { "huq", "Tsat" }, + { "hur", "Halkomelem" }, + { "hus", "Huastec" }, + { "hut", "Humla" }, + { "huu", "Murui Huitoto" }, + { "huv", "San Mateo Del Mar Huave" }, + { "huw", "Hukumina" }, + { "hux", "Nüpode Huitoto" }, + { "huy", "Hulaulá" }, + { "huz", "Hunzib" }, + { "hvc", "Haitian Vodoun Culture Language" }, + { "hve", "San Dionisio Del Mar Huave" }, + { "hvk", "Haveke" }, + { "hvn", "Sabu" }, + { "hvv", "Santa María Del Mar Huave" }, + { "hwa", "Wané" }, + { "hwc", "Hawai'i Creole English" }, + { "hwo", "Hwana" }, + { "hya", "Hya" }, + { "hye", "Armenian" }, + { "iai", "Iaai" }, + { "ian", "Iatmul" }, + { "iap", "Iapama" }, + { "iar", "Purari" }, + { "iba", "Iban" }, + { "ibb", "Ibibio" }, + { "ibd", "Iwaidja" }, + { "ibe", "Akpes" }, + { "ibg", "Ibanag" }, + { "ibl", "Ibaloi" }, + { "ibm", "Agoi" }, + { "ibn", "Ibino" }, + { "ibo", "Igbo" }, + { "ibr", "Ibuoro" }, + { "ibu", "Ibu" }, + { "iby", "Ibani" }, + { "ica", "Ede Ica" }, + { "ich", "Etkywan" }, + { "icl", "Icelandic Sign Language" }, + { "icr", "Islander Creole English" }, + { "ida", "Idakho-Isukha-Tiriki" }, + { "idb", "Indo-Portuguese" }, + { "idc", "Idon" }, + { "idd", "Ede Idaca" }, + { "ide", "Idere" }, + { "idi", "Idi" }, + { "ido", "Ido" }, + { "idr", "Indri" }, + { "ids", "Idesa" }, + { "idt", "Idaté" }, + { "idu", "Idoma" }, + { "ifa", "Amganad Ifugao" }, + { "ifb", "Batad Ifugao" }, + { "ife", "Ifè" }, + { "iff", "Ifo" }, + { "ifk", "Tuwali Ifugao" }, + { "ifm", "Teke-Fuumu" }, + { "ifu", "Mayoyao Ifugao" }, + { "ify", "Keley-I Kallahan" }, + { "igb", "Ebira" }, + { "ige", "Igede" }, + { "igg", "Igana" }, + { "igl", "Igala" }, + { "igm", "Kanggape" }, + { "ign", "Ignaciano" }, + { "igo", "Isebe" }, + { "igs", "Interglossa" }, + { "igw", "Igwe" }, + { "ihb", "Iha Based Pidgin" }, + { "ihi", "Ihievbe" }, + { "ihp", "Iha" }, + { "ihw", "Bidhawal" }, + { "iii", "Sichuan Yi" }, + { "iin", "Thiin" }, + { "ijc", "Izon" }, + { "ije", "Biseni" }, + { "ijj", "Ede Ije" }, + { "ijn", "Kalabari" }, + { "ijs", "Southeast Ijo" }, + { "ike", "Eastern Canadian Inuktitut" }, + { "iki", "Iko" }, + { "ikk", "Ika" }, + { "ikl", "Ikulu" }, + { "iko", "Olulumo-Ikom" }, + { "ikp", "Ikpeshi" }, + { "ikr", "Ikaranggal" }, + { "ikt", "Inuinnaqtun" }, + { "iku", "Inuktitut" }, + { "ikv", "Iku-Gora-Ankwa" }, + { "ikw", "Ikwere" }, + { "ikx", "Ik" }, + { "ikz", "Ikizu" }, + { "ila", "Ile Ape" }, + { "ilb", "Ila" }, + { "ile", "Interlingue" }, + { "ilg", "Garig-Ilgar" }, + { "ili", "Ili Turki" }, + { "ilk", "Ilongot" }, + { "ill", "Iranun" }, + { "ilo", "Iloko" }, + { "ils", "International Sign" }, + { "ilu", "Ili'uun" }, + { "ilv", "Ilue" }, + { "ima", "Mala Malasar" }, + { "ime", "Imeraguen" }, + { "imi", "Anamgura" }, + { "iml", "Miluk" }, + { "imn", "Imonda" }, + { "imo", "Imbongu" }, + { "imr", "Imroing" }, + { "ims", "Marsian" }, + { "imy", "Milyan" }, + { "ina", "Interlingua (International Auxiliary Language Association)" }, + { "inb", "Inga" }, + { "ind", "Indonesian" }, + { "ing", "Degexit'an" }, + { "inh", "Ingush" }, + { "inj", "Jungle Inga" }, + { "inl", "Indonesian Sign Language" }, + { "inm", "Minaean" }, + { "inn", "Isinai" }, + { "ino", "Inoke-Yate" }, + { "inp", "Iñapari" }, + { "ins", "Indian Sign Language" }, + { "int", "Intha" }, + { "inz", "Ineseño" }, + { "ior", "Inor" }, + { "iou", "Tuma-Irumu" }, + { "iow", "Iowa-Oto" }, + { "ipi", "Ipili" }, + { "ipk", "Inupiaq" }, + { "ipo", "Ipiko" }, + { "iqu", "Iquito" }, + { "iqw", "Ikwo" }, + { "ire", "Iresim" }, + { "irh", "Irarutu" }, + { "iri", "Irigwe" }, + { "irk", "Iraqw" }, + { "irn", "Irántxe" }, + { "irr", "Ir" }, + { "iru", "Irula" }, + { "irx", "Kamberau" }, + { "iry", "Iraya" }, + { "isa", "Isabi" }, + { "isc", "Isconahua" }, + { "isd", "Isnag" }, + { "ise", "Italian Sign Language" }, + { "isg", "Irish Sign Language" }, + { "ish", "Esan" }, + { "isi", "Nkem-Nkum" }, + { "isk", "Ishkashimi" }, + { "isl", "Icelandic" }, + { "ism", "Masimasi" }, + { "isn", "Isanzu" }, + { "iso", "Isoko" }, + { "isr", "Israeli Sign Language" }, + { "ist", "Istriot" }, + { "isu", "Isu (Menchum Division)" }, + { "ita", "Italian" }, + { "itb", "Binongan Itneg" }, + { "ite", "Itene" }, + { "iti", "Inlaod Itneg" }, + { "itk", "Judeo-Italian" }, + { "itl", "Itelmen" }, + { "itm", "Itu Mbon Uzo" }, + { "ito", "Itonama" }, + { "itr", "Iteri" }, + { "its", "Isekiri" }, + { "itt", "Maeng Itneg" }, + { "itv", "Itawit" }, + { "itw", "Ito" }, + { "itx", "Itik" }, + { "ity", "Moyadan Itneg" }, + { "itz", "Itzá" }, + { "ium", "Iu Mien" }, + { "ivb", "Ibatan" }, + { "ivv", "Ivatan" }, + { "iwk", "I-Wak" }, + { "iwm", "Iwam" }, + { "iwo", "Iwur" }, + { "iws", "Sepik Iwam" }, + { "ixc", "Ixcatec" }, + { "ixl", "Ixil" }, + { "iya", "Iyayu" }, + { "iyo", "Mesaka" }, + { "iyx", "Yaka (Congo)" }, + { "izh", "Ingrian" }, + { "izr", "Izere" }, + { "izz", "Izii" }, + { "jaa", "Jamamadí" }, + { "jab", "Hyam" }, + { "jac", "Popti'" }, + { "jad", "Jahanka" }, + { "jae", "Yabem" }, + { "jaf", "Jara" }, + { "jah", "Jah Hut" }, + { "jaj", "Zazao" }, + { "jak", "Jakun" }, + { "jal", "Yalahatan" }, + { "jam", "Jamaican Creole English" }, + { "jan", "Jandai" }, + { "jao", "Yanyuwa" }, + { "jaq", "Yaqay" }, + { "jas", "New Caledonian Javanese" }, + { "jat", "Jakati" }, + { "jau", "Yaur" }, + { "jav", "Javanese" }, + { "jax", "Jambi Malay" }, + { "jay", "Yan-nhangu" }, + { "jaz", "Jawe" }, + { "jbe", "Judeo-Berber" }, + { "jbi", "Badjiri" }, + { "jbj", "Arandai" }, + { "jbk", "Barikewa" }, + { "jbn", "Nafusi" }, + { "jbo", "Lojban" }, + { "jbr", "Jofotek-Bromnya" }, + { "jbt", "Jabutí" }, + { "jbu", "Jukun Takum" }, + { "jbw", "Yawijibaya" }, + { "jcs", "Jamaican Country Sign Language" }, + { "jct", "Krymchak" }, + { "jda", "Jad" }, + { "jdg", "Jadgali" }, + { "jdt", "Judeo-Tat" }, + { "jeb", "Jebero" }, + { "jee", "Jerung" }, + { "jeg", "Jeng" }, + { "jeh", "Jeh" }, + { "jei", "Yei" }, + { "jek", "Jeri Kuo" }, + { "jel", "Yelmek" }, + { "jen", "Dza" }, + { "jer", "Jere" }, + { "jet", "Manem" }, + { "jeu", "Jonkor Bourmataguil" }, + { "jgb", "Ngbee" }, + { "jge", "Judeo-Georgian" }, + { "jgk", "Gwak" }, + { "jgo", "Ngomba" }, + { "jhi", "Jehai" }, + { "jhs", "Jhankot Sign Language" }, + { "jia", "Jina" }, + { "jib", "Jibu" }, + { "jic", "Tol" }, + { "jid", "Bu" }, + { "jie", "Jilbe" }, + { "jig", "Djingili" }, + { "jih", "sTodsde" }, + { "jii", "Jiiddu" }, + { "jil", "Jilim" }, + { "jim", "Jimi (Cameroon)" }, + { "jio", "Jiamao" }, + { "jiq", "Guanyinqiao" }, + { "jit", "Jita" }, + { "jiu", "Youle Jinuo" }, + { "jiv", "Shuar" }, + { "jiy", "Buyuan Jinuo" }, + { "jjr", "Bankal" }, + { "jkm", "Mobwa Karen" }, + { "jko", "Kubo" }, + { "jkp", "Paku Karen" }, + { "jkr", "Koro (India)" }, + { "jku", "Labir" }, + { "jle", "Ngile" }, + { "jls", "Jamaican Sign Language" }, + { "jma", "Dima" }, + { "jmb", "Zumbun" }, + { "jmc", "Machame" }, + { "jmd", "Yamdena" }, + { "jmi", "Jimi (Nigeria)" }, + { "jml", "Jumli" }, + { "jmn", "Makuri Naga" }, + { "jmr", "Kamara" }, + { "jms", "Mashi (Nigeria)" }, + { "jmw", "Mouwase" }, + { "jmx", "Western Juxtlahuaca Mixtec" }, + { "jna", "Jangshung" }, + { "jnd", "Jandavra" }, + { "jng", "Yangman" }, + { "jni", "Janji" }, + { "jnj", "Yemsa" }, + { "jnl", "Rawat" }, + { "jns", "Jaunsari" }, + { "job", "Joba" }, + { "jod", "Wojenaka" }, + { "jor", "Jorá" }, + { "jos", "Jordanian Sign Language" }, + { "jow", "Jowulu" }, + { "jpa", "Jewish Palestinian Aramaic" }, + { "jpn", "Japanese" }, + { "jpr", "Judeo-Persian" }, + { "jqr", "Jaqaru" }, + { "jra", "Jarai" }, + { "jrb", "Judeo-Arabic" }, + { "jrr", "Jiru" }, + { "jrt", "Jorto" }, + { "jru", "Japrería" }, + { "jsl", "Japanese Sign Language" }, + { "jua", "Júma" }, + { "jub", "Wannu" }, + { "juc", "Jurchen" }, + { "jud", "Worodougou" }, + { "juh", "Hõne" }, + { "jui", "Ngadjuri" }, + { "juk", "Wapan" }, + { "jul", "Jirel" }, + { "jum", "Jumjum" }, + { "jun", "Juang" }, + { "juo", "Jiba" }, + { "jup", "Hupdë" }, + { "jur", "Jurúna" }, + { "jus", "Jumla Sign Language" }, + { "jut", "Jutish" }, + { "juu", "Ju" }, + { "juw", "Wãpha" }, + { "juy", "Juray" }, + { "jvd", "Javindo" }, + { "jvn", "Caribbean Javanese" }, + { "jwi", "Jwira-Pepesa" }, + { "jya", "Jiarong" }, + { "jye", "Judeo-Yemeni Arabic" }, + { "jyy", "Jaya" }, + { "kaa", "Kara-Kalpak" }, + { "kab", "Kabyle" }, + { "kac", "Kachin" }, + { "kad", "Adara" }, + { "kae", "Ketangalan" }, + { "kaf", "Katso" }, + { "kag", "Kajaman" }, + { "kah", "Kara (Central African Republic)" }, + { "kai", "Karekare" }, + { "kaj", "Jju" }, + { "kak", "Kayapa Kallahan" }, + { "kal", "Kalaallisut" }, + { "kam", "Kamba (Kenya)" }, + { "kan", "Kannada" }, + { "kao", "Xaasongaxango" }, + { "kap", "Bezhta" }, + { "kaq", "Capanahua" }, + { "kas", "Kashmiri" }, + { "kat", "Georgian" }, + { "kau", "Kanuri" }, + { "kav", "Katukína" }, + { "kaw", "Kawi" }, + { "kax", "Kao" }, + { "kay", "Kamayurá" }, + { "kaz", "Kazakh" }, + { "kba", "Kalarko" }, + { "kbb", "Kaxuiâna" }, + { "kbc", "Kadiwéu" }, + { "kbd", "Kabardian" }, + { "kbe", "Kanju" }, + { "kbf", "Kakauhua" }, + { "kbg", "Khamba" }, + { "kbh", "Camsá" }, + { "kbi", "Kaptiau" }, + { "kbj", "Kari" }, + { "kbk", "Grass Koiari" }, + { "kbl", "Kanembu" }, + { "kbm", "Iwal" }, + { "kbn", "Kare (Central African Republic)" }, + { "kbo", "Keliko" }, + { "kbp", "Kabiyè" }, + { "kbq", "Kamano" }, + { "kbr", "Kafa" }, + { "kbs", "Kande" }, + { "kbt", "Abadi" }, + { "kbu", "Kabutra" }, + { "kbv", "Dera (Indonesia)" }, + { "kbw", "Kaiep" }, + { "kbx", "Ap Ma" }, + { "kby", "Manga Kanuri" }, + { "kbz", "Duhwa" }, + { "kca", "Khanty" }, + { "kcb", "Kawacha" }, + { "kcc", "Lubila" }, + { "kcd", "Ngkâlmpw Kanum" }, + { "kce", "Kaivi" }, + { "kcf", "Ukaan" }, + { "kcg", "Tyap" }, + { "kch", "Vono" }, + { "kci", "Kamantan" }, + { "kcj", "Kobiana" }, + { "kck", "Kalanga" }, + { "kcl", "Kela (Papua New Guinea)" }, + { "kcm", "Gula (Central African Republic)" }, + { "kcn", "Nubi" }, + { "kco", "Kinalakna" }, + { "kcp", "Kanga" }, + { "kcq", "Kamo" }, + { "kcr", "Katla" }, + { "kcs", "Koenoem" }, + { "kct", "Kaian" }, + { "kcu", "Kami (Tanzania)" }, + { "kcv", "Kete" }, + { "kcw", "Kabwari" }, + { "kcx", "Kachama-Ganjule" }, + { "kcy", "Korandje" }, + { "kcz", "Konongo" }, + { "kda", "Worimi" }, + { "kdc", "Kutu" }, + { "kdd", "Yankunytjatjara" }, + { "kde", "Makonde" }, + { "kdf", "Mamusi" }, + { "kdg", "Seba" }, + { "kdh", "Tem" }, + { "kdi", "Kumam" }, + { "kdj", "Karamojong" }, + { "kdk", "Numèè" }, + { "kdl", "Tsikimba" }, + { "kdm", "Kagoma" }, + { "kdn", "Kunda" }, + { "kdp", "Kaningdon-Nindem" }, + { "kdq", "Koch" }, + { "kdr", "Karaim" }, + { "kdt", "Kuy" }, + { "kdu", "Kadaru" }, + { "kdw", "Koneraw" }, + { "kdx", "Kam" }, + { "kdy", "Keder" }, + { "kdz", "Kwaja" }, + { "kea", "Kabuverdianu" }, + { "keb", "Kélé" }, + { "kec", "Keiga" }, + { "ked", "Kerewe" }, + { "kee", "Eastern Keres" }, + { "kef", "Kpessi" }, + { "keg", "Tese" }, + { "keh", "Keak" }, + { "kei", "Kei" }, + { "kej", "Kadar" }, + { "kek", "Kekchí" }, + { "kel", "Kela (Democratic Republic of Congo)" }, + { "kem", "Kemak" }, + { "ken", "Kenyang" }, + { "keo", "Kakwa" }, + { "kep", "Kaikadi" }, + { "keq", "Kamar" }, + { "ker", "Kera" }, + { "kes", "Kugbo" }, + { "ket", "Ket" }, + { "keu", "Akebu" }, + { "kev", "Kanikkaran" }, + { "kew", "West Kewa" }, + { "kex", "Kukna" }, + { "key", "Kupia" }, + { "kez", "Kukele" }, + { "kfa", "Kodava" }, + { "kfb", "Northwestern Kolami" }, + { "kfc", "Konda-Dora" }, + { "kfd", "Korra Koraga" }, + { "kfe", "Kota (India)" }, + { "kff", "Koya" }, + { "kfg", "Kudiya" }, + { "kfh", "Kurichiya" }, + { "kfi", "Kannada Kurumba" }, + { "kfj", "Kemiehua" }, + { "kfk", "Kinnauri" }, + { "kfl", "Kung" }, + { "kfm", "Khunsari" }, + { "kfn", "Kuk" }, + { "kfo", "Koro (Côte d'Ivoire)" }, + { "kfp", "Korwa" }, + { "kfq", "Korku" }, + { "kfr", "Kachchi" }, + { "kfs", "Bilaspuri" }, + { "kft", "Kanjari" }, + { "kfu", "Katkari" }, + { "kfv", "Kurmukar" }, + { "kfw", "Kharam Naga" }, + { "kfx", "Kullu Pahari" }, + { "kfy", "Kumaoni" }, + { "kfz", "Koromfé" }, + { "kga", "Koyaga" }, + { "kgb", "Kawe" }, + { "kgc", "Kasseng" }, + { "kgd", "Kataang" }, + { "kge", "Komering" }, + { "kgf", "Kube" }, + { "kgg", "Kusunda" }, + { "kgi", "Selangor Sign Language" }, + { "kgj", "Gamale Kham" }, + { "kgk", "Kaiwá" }, + { "kgl", "Kunggari" }, + { "kgm", "Karipúna" }, + { "kgn", "Karingani" }, + { "kgo", "Krongo" }, + { "kgp", "Kaingang" }, + { "kgq", "Kamoro" }, + { "kgr", "Abun" }, + { "kgs", "Kumbainggar" }, + { "kgt", "Somyev" }, + { "kgu", "Kobol" }, + { "kgv", "Karas" }, + { "kgw", "Karon Dori" }, + { "kgx", "Kamaru" }, + { "kgy", "Kyerung" }, + { "kha", "Khasi" }, + { "khb", "Lü" }, + { "khc", "Tukang Besi North" }, + { "khd", "Bädi Kanum" }, + { "khe", "Korowai" }, + { "khf", "Khuen" }, + { "khg", "Khams Tibetan" }, + { "khh", "Kehu" }, + { "khj", "Kuturmi" }, + { "khk", "Halh Mongolian" }, + { "khl", "Lusi" }, + { "khm", "Central Khmer" }, + { "khn", "Khandesi" }, + { "kho", "Khotanese" }, + { "khp", "Kapori" }, + { "khq", "Koyra Chiini Songhay" }, + { "khr", "Kharia" }, + { "khs", "Kasua" }, + { "kht", "Khamti" }, + { "khu", "Nkhumbi" }, + { "khv", "Khvarshi" }, + { "khw", "Khowar" }, + { "khx", "Kanu" }, + { "khy", "Kele (Democratic Republic of Congo)" }, + { "khz", "Keapara" }, + { "kia", "Kim" }, + { "kib", "Koalib" }, + { "kic", "Kickapoo" }, + { "kid", "Koshin" }, + { "kie", "Kibet" }, + { "kif", "Eastern Parbate Kham" }, + { "kig", "Kimaama" }, + { "kih", "Kilmeri" }, + { "kii", "Kitsai" }, + { "kij", "Kilivila" }, + { "kik", "Kikuyu" }, + { "kil", "Kariya" }, + { "kim", "Karagas" }, + { "kin", "Kinyarwanda" }, + { "kio", "Kiowa" }, + { "kip", "Sheshi Kham" }, + { "kiq", "Kosadle" }, + { "kir", "Kirghiz" }, + { "kis", "Kis" }, + { "kit", "Agob" }, + { "kiu", "Kirmanjki (individual language)" }, + { "kiv", "Kimbu" }, + { "kiw", "Northeast Kiwai" }, + { "kix", "Khiamniungan Naga" }, + { "kiy", "Kirikiri" }, + { "kiz", "Kisi" }, + { "kja", "Mlap" }, + { "kjb", "Q'anjob'al" }, + { "kjc", "Coastal Konjo" }, + { "kjd", "Southern Kiwai" }, + { "kje", "Kisar" }, + { "kjf", "Khalaj" }, + { "kjg", "Khmu" }, + { "kjh", "Khakas" }, + { "kji", "Zabana" }, + { "kjj", "Khinalugh" }, + { "kjk", "Highland Konjo" }, + { "kjl", "Western Parbate Kham" }, + { "kjm", "Kháng" }, + { "kjn", "Kunjen" }, + { "kjo", "Harijan Kinnauri" }, + { "kjp", "Pwo Eastern Karen" }, + { "kjq", "Western Keres" }, + { "kjr", "Kurudu" }, + { "kjs", "East Kewa" }, + { "kjt", "Phrae Pwo Karen" }, + { "kju", "Kashaya" }, + { "kjx", "Ramopa" }, + { "kjy", "Erave" }, + { "kjz", "Bumthangkha" }, + { "kka", "Kakanda" }, + { "kkb", "Kwerisa" }, + { "kkc", "Odoodee" }, + { "kkd", "Kinuku" }, + { "kke", "Kakabe" }, + { "kkf", "Kalaktang Monpa" }, + { "kkg", "Mabaka Valley Kalinga" }, + { "kkh", "Khün" }, + { "kki", "Kagulu" }, + { "kkj", "Kako" }, + { "kkk", "Kokota" }, + { "kkl", "Kosarek Yale" }, + { "kkm", "Kiong" }, + { "kkn", "Kon Keu" }, + { "kko", "Karko" }, + { "kkp", "Gugubera" }, + { "kkq", "Kaiku" }, + { "kkr", "Kir-Balar" }, + { "kks", "Giiwo" }, + { "kkt", "Koi" }, + { "kku", "Tumi" }, + { "kkv", "Kangean" }, + { "kkw", "Teke-Kukuya" }, + { "kkx", "Kohin" }, + { "kky", "Guguyimidjir" }, + { "kkz", "Kaska" }, + { "kla", "Klamath-Modoc" }, + { "klb", "Kiliwa" }, + { "klc", "Kolbila" }, + { "kld", "Gamilaraay" }, + { "kle", "Kulung (Nepal)" }, + { "klf", "Kendeje" }, + { "klg", "Tagakaulo" }, + { "klh", "Weliki" }, + { "kli", "Kalumpang" }, + { "klj", "Turkic Khalaj" }, + { "klk", "Kono (Nigeria)" }, + { "kll", "Kagan Kalagan" }, + { "klm", "Migum" }, + { "kln", "Kalenjin" }, + { "klo", "Kapya" }, + { "klp", "Kamasa" }, + { "klq", "Rumu" }, + { "klr", "Khaling" }, + { "kls", "Kalasha" }, + { "klt", "Nukna" }, + { "klu", "Klao" }, + { "klv", "Maskelynes" }, + { "klw", "Lindu" }, + { "klx", "Koluwawa" }, + { "kly", "Kalao" }, + { "klz", "Kabola" }, + { "kma", "Konni" }, + { "kmb", "Kimbundu" }, + { "kmc", "Southern Dong" }, + { "kmd", "Majukayang Kalinga" }, + { "kme", "Bakole" }, + { "kmf", "Kare (Papua New Guinea)" }, + { "kmg", "Kâte" }, + { "kmh", "Kalam" }, + { "kmi", "Kami (Nigeria)" }, + { "kmj", "Kumarbhag Paharia" }, + { "kmk", "Limos Kalinga" }, + { "kml", "Tanudan Kalinga" }, + { "kmm", "Kom (India)" }, + { "kmn", "Awtuw" }, + { "kmo", "Kwoma" }, + { "kmp", "Gimme" }, + { "kmq", "Kwama" }, + { "kmr", "Northern Kurdish" }, + { "kms", "Kamasau" }, + { "kmt", "Kemtuik" }, + { "kmu", "Kanite" }, + { "kmv", "Karipúna Creole French" }, + { "kmw", "Komo (Democratic Republic of Congo)" }, + { "kmx", "Waboda" }, + { "kmy", "Koma" }, + { "kmz", "Khorasani Turkish" }, + { "kna", "Dera (Nigeria)" }, + { "knb", "Lubuagan Kalinga" }, + { "knc", "Central Kanuri" }, + { "knd", "Konda" }, + { "kne", "Kankanaey" }, + { "knf", "Mankanya" }, + { "kng", "Koongo" }, + { "kni", "Kanufi" }, + { "knj", "Western Kanjobal" }, + { "knk", "Kuranko" }, + { "knl", "Keninjal" }, + { "knm", "Kanamarí" }, + { "knn", "Konkani (individual language)" }, + { "kno", "Kono (Sierra Leone)" }, + { "knp", "Kwanja" }, + { "knq", "Kintaq" }, + { "knr", "Kaningra" }, + { "kns", "Kensiu" }, + { "knt", "Panoan Katukína" }, + { "knu", "Kono (Guinea)" }, + { "knv", "Tabo" }, + { "knw", "Kung-Ekoka" }, + { "knx", "Kendayan" }, + { "kny", "Kanyok" }, + { "knz", "Kalamsé" }, + { "koa", "Konomala" }, + { "koc", "Kpati" }, + { "kod", "Kodi" }, + { "koe", "Kacipo-Balesi" }, + { "kof", "Kubi" }, + { "kog", "Cogui" }, + { "koh", "Koyo" }, + { "koi", "Komi-Permyak" }, + { "koj", "Sara Dunjo" }, + { "kok", "Konkani (macrolanguage)" }, + { "kol", "Kol (Papua New Guinea)" }, + { "kom", "Komi" }, + { "kon", "Kongo" }, + { "koo", "Konzo" }, + { "kop", "Waube" }, + { "koq", "Kota (Gabon)" }, + { "kor", "Korean" }, + { "kos", "Kosraean" }, + { "kot", "Lagwan" }, + { "kou", "Koke" }, + { "kov", "Kudu-Camo" }, + { "kow", "Kugama" }, + { "kox", "Coxima" }, + { "koy", "Koyukon" }, + { "koz", "Korak" }, + { "kpa", "Kutto" }, + { "kpb", "Mullu Kurumba" }, + { "kpc", "Curripaco" }, + { "kpd", "Koba" }, + { "kpe", "Kpelle" }, + { "kpf", "Komba" }, + { "kpg", "Kapingamarangi" }, + { "kph", "Kplang" }, + { "kpi", "Kofei" }, + { "kpj", "Karajá" }, + { "kpk", "Kpan" }, + { "kpl", "Kpala" }, + { "kpm", "Koho" }, + { "kpn", "Kepkiriwát" }, + { "kpo", "Ikposo" }, + { "kpq", "Korupun-Sela" }, + { "kpr", "Korafe-Yegha" }, + { "kps", "Tehit" }, + { "kpt", "Karata" }, + { "kpu", "Kafoa" }, + { "kpv", "Komi-Zyrian" }, + { "kpw", "Kobon" }, + { "kpx", "Mountain Koiali" }, + { "kpy", "Koryak" }, + { "kpz", "Kupsabiny" }, + { "kqa", "Mum" }, + { "kqb", "Kovai" }, + { "kqc", "Doromu-Koki" }, + { "kqd", "Koy Sanjaq Surat" }, + { "kqe", "Kalagan" }, + { "kqf", "Kakabai" }, + { "kqg", "Khe" }, + { "kqh", "Kisankasa" }, + { "kqi", "Koitabu" }, + { "kqj", "Koromira" }, + { "kqk", "Kotafon Gbe" }, + { "kql", "Kyenele" }, + { "kqm", "Khisa" }, + { "kqn", "Kaonde" }, + { "kqo", "Eastern Krahn" }, + { "kqp", "Kimré" }, + { "kqq", "Krenak" }, + { "kqr", "Kimaragang" }, + { "kqs", "Northern Kissi" }, + { "kqt", "Klias River Kadazan" }, + { "kqu", "Seroa" }, + { "kqv", "Okolod" }, + { "kqw", "Kandas" }, + { "kqx", "Mser" }, + { "kqy", "Koorete" }, + { "kqz", "Korana" }, + { "kra", "Kumhali" }, + { "krb", "Karkin" }, + { "krc", "Karachay-Balkar" }, + { "krd", "Kairui-Midiki" }, + { "kre", "Panará" }, + { "krf", "Koro (Vanuatu)" }, + { "krh", "Kurama" }, + { "kri", "Krio" }, + { "krj", "Kinaray-A" }, + { "krk", "Kerek" }, + { "krl", "Karelian" }, + { "krm", "Krim" }, + { "krn", "Sapo" }, + { "krp", "Korop" }, + { "krr", "Kru'ng 2" }, + { "krs", "Gbaya (Sudan)" }, + { "krt", "Tumari Kanuri" }, + { "kru", "Kurukh" }, + { "krv", "Kavet" }, + { "krw", "Western Krahn" }, + { "krx", "Karon" }, + { "kry", "Kryts" }, + { "krz", "Sota Kanum" }, + { "ksa", "Shuwa-Zamani" }, + { "ksb", "Shambala" }, + { "ksc", "Southern Kalinga" }, + { "ksd", "Kuanua" }, + { "kse", "Kuni" }, + { "ksf", "Bafia" }, + { "ksg", "Kusaghe" }, + { "ksh", "Kölsch" }, + { "ksi", "Krisa" }, + { "ksj", "Uare" }, + { "ksk", "Kansa" }, + { "ksl", "Kumalu" }, + { "ksm", "Kumba" }, + { "ksn", "Kasiguranin" }, + { "kso", "Kofa" }, + { "ksp", "Kaba" }, + { "ksq", "Kwaami" }, + { "ksr", "Borong" }, + { "kss", "Southern Kisi" }, + { "kst", "Winyé" }, + { "ksu", "Khamyang" }, + { "ksv", "Kusu" }, + { "ksw", "S'gaw Karen" }, + { "ksx", "Kedang" }, + { "ksy", "Kharia Thar" }, + { "ksz", "Kodaku" }, + { "kta", "Katua" }, + { "ktb", "Kambaata" }, + { "ktc", "Kholok" }, + { "ktd", "Kokata" }, + { "kte", "Nubri" }, + { "ktf", "Kwami" }, + { "ktg", "Kalkutung" }, + { "kth", "Karanga" }, + { "kti", "North Muyu" }, + { "ktj", "Plapo Krumen" }, + { "ktk", "Kaniet" }, + { "ktl", "Koroshi" }, + { "ktm", "Kurti" }, + { "ktn", "Karitiâna" }, + { "kto", "Kuot" }, + { "ktp", "Kaduo" }, + { "ktq", "Katabaga" }, + { "ktr", "Kota Marudu Tinagas" }, + { "kts", "South Muyu" }, + { "ktt", "Ketum" }, + { "ktu", "Kituba (Democratic Republic of Congo)" }, + { "ktv", "Eastern Katu" }, + { "ktw", "Kato" }, + { "ktx", "Kaxararí" }, + { "kty", "Kango (Bas-Uélé District)" }, + { "ktz", "Ju'hoan" }, + { "kua", "Kuanyama" }, + { "kub", "Kutep" }, + { "kuc", "Kwinsu" }, + { "kud", "'Auhelawa" }, + { "kue", "Kuman" }, + { "kuf", "Western Katu" }, + { "kug", "Kupa" }, + { "kuh", "Kushi" }, + { "kui", "Kuikúro-Kalapálo" }, + { "kuj", "Kuria" }, + { "kuk", "Kepo'" }, + { "kul", "Kulere" }, + { "kum", "Kumyk" }, + { "kun", "Kunama" }, + { "kuo", "Kumukio" }, + { "kup", "Kunimaipa" }, + { "kuq", "Karipuna" }, + { "kur", "Kurdish" }, + { "kus", "Kusaal" }, + { "kut", "Kutenai" }, + { "kuu", "Upper Kuskokwim" }, + { "kuv", "Kur" }, + { "kuw", "Kpagua" }, + { "kux", "Kukatja" }, + { "kuy", "Kuuku-Ya'u" }, + { "kuz", "Kunza" }, + { "kva", "Bagvalal" }, + { "kvb", "Kubu" }, + { "kvc", "Kove" }, + { "kvd", "Kui (Indonesia)" }, + { "kve", "Kalabakan" }, + { "kvf", "Kabalai" }, + { "kvg", "Kuni-Boazi" }, + { "kvh", "Komodo" }, + { "kvi", "Kwang" }, + { "kvj", "Psikye" }, + { "kvk", "Korean Sign Language" }, + { "kvl", "Kayaw" }, + { "kvm", "Kendem" }, + { "kvn", "Border Kuna" }, + { "kvo", "Dobel" }, + { "kvp", "Kompane" }, + { "kvq", "Geba Karen" }, + { "kvr", "Kerinci" }, + { "kvs", "Kunggara" }, + { "kvt", "Lahta Karen" }, + { "kvu", "Yinbaw Karen" }, + { "kvv", "Kola" }, + { "kvw", "Wersing" }, + { "kvx", "Parkari Koli" }, + { "kvy", "Yintale Karen" }, + { "kvz", "Tsakwambo" }, + { "kwa", "Dâw" }, + { "kwb", "Kwa" }, + { "kwc", "Likwala" }, + { "kwd", "Kwaio" }, + { "kwe", "Kwerba" }, + { "kwf", "Kwara'ae" }, + { "kwg", "Sara Kaba Deme" }, + { "kwh", "Kowiai" }, + { "kwi", "Awa-Cuaiquer" }, + { "kwj", "Kwanga" }, + { "kwk", "Kwakiutl" }, + { "kwl", "Kofyar" }, + { "kwm", "Kwambi" }, + { "kwn", "Kwangali" }, + { "kwo", "Kwomtari" }, + { "kwp", "Kodia" }, + { "kwq", "Kwak" }, + { "kwr", "Kwer" }, + { "kws", "Kwese" }, + { "kwt", "Kwesten" }, + { "kwu", "Kwakum" }, + { "kwv", "Sara Kaba Náà" }, + { "kww", "Kwinti" }, + { "kwx", "Khirwar" }, + { "kwy", "San Salvador Kongo" }, + { "kwz", "Kwadi" }, + { "kxa", "Kairiru" }, + { "kxb", "Krobu" }, + { "kxc", "Konso" }, + { "kxd", "Brunei" }, + { "kxe", "Kakihum" }, + { "kxf", "Manumanaw Karen" }, + { "kxh", "Karo (Ethiopia)" }, + { "kxi", "Keningau Murut" }, + { "kxj", "Kulfa" }, + { "kxk", "Zayein Karen" }, + { "kxl", "Nepali Kurux" }, + { "kxm", "Northern Khmer" }, + { "kxn", "Kanowit-Tanjong Melanau" }, + { "kxo", "Kanoé" }, + { "kxp", "Wadiyara Koli" }, + { "kxq", "Smärky Kanum" }, + { "kxr", "Koro (Papua New Guinea)" }, + { "kxs", "Kangjia" }, + { "kxt", "Koiwat" }, + { "kxu", "Kui (India)" }, + { "kxv", "Kuvi" }, + { "kxw", "Konai" }, + { "kxx", "Likuba" }, + { "kxy", "Kayong" }, + { "kxz", "Kerewo" }, + { "kya", "Kwaya" }, + { "kyb", "Butbut Kalinga" }, + { "kyc", "Kyaka" }, + { "kyd", "Karey" }, + { "kye", "Krache" }, + { "kyf", "Kouya" }, + { "kyg", "Keyagana" }, + { "kyh", "Karok" }, + { "kyi", "Kiput" }, + { "kyj", "Karao" }, + { "kyk", "Kamayo" }, + { "kyl", "Kalapuya" }, + { "kym", "Kpatili" }, + { "kyn", "Northern Binukidnon" }, + { "kyo", "Kelon" }, + { "kyp", "Kang" }, + { "kyq", "Kenga" }, + { "kyr", "Kuruáya" }, + { "kys", "Baram Kayan" }, + { "kyt", "Kayagar" }, + { "kyu", "Western Kayah" }, + { "kyv", "Kayort" }, + { "kyw", "Kudmali" }, + { "kyx", "Rapoisi" }, + { "kyy", "Kambaira" }, + { "kyz", "Kayabí" }, + { "kza", "Western Karaboro" }, + { "kzb", "Kaibobo" }, + { "kzc", "Bondoukou Kulango" }, + { "kzd", "Kadai" }, + { "kze", "Kosena" }, + { "kzf", "Da'a Kaili" }, + { "kzg", "Kikai" }, + { "kzi", "Kelabit" }, + { "kzj", "Coastal Kadazan" }, + { "kzk", "Kazukuru" }, + { "kzl", "Kayeli" }, + { "kzm", "Kais" }, + { "kzn", "Kokola" }, + { "kzo", "Kaningi" }, + { "kzp", "Kaidipang" }, + { "kzq", "Kaike" }, + { "kzr", "Karang" }, + { "kzs", "Sugut Dusun" }, + { "kzt", "Tambunan Dusun" }, + { "kzu", "Kayupulau" }, + { "kzv", "Komyandaret" }, + { "kzw", "Karirí-Xocó" }, + { "kzx", "Kamarian" }, + { "kzy", "Kango (Tshopo District)" }, + { "kzz", "Kalabra" }, + { "laa", "Southern Subanen" }, + { "lab", "Linear A" }, + { "lac", "Lacandon" }, + { "lad", "Ladino" }, + { "lae", "Pattani" }, + { "laf", "Lafofa" }, + { "lag", "Langi" }, + { "lah", "Lahnda" }, + { "lai", "Lambya" }, + { "laj", "Lango (Uganda)" }, + { "lak", "Laka (Nigeria)" }, + { "lal", "Lalia" }, + { "lam", "Lamba" }, + { "lan", "Laru" }, + { "lao", "Lao" }, + { "lap", "Laka (Chad)" }, + { "laq", "Qabiao" }, + { "lar", "Larteh" }, + { "las", "Lama (Togo)" }, + { "lat", "Latin" }, + { "lau", "Laba" }, + { "lav", "Latvian" }, + { "law", "Lauje" }, + { "lax", "Tiwa" }, + { "lay", "Lama (Myanmar)" }, + { "laz", "Aribwatsa" }, + { "lba", "Lui" }, + { "lbb", "Label" }, + { "lbc", "Lakkia" }, + { "lbe", "Lak" }, + { "lbf", "Tinani" }, + { "lbg", "Laopang" }, + { "lbi", "La'bi" }, + { "lbj", "Ladakhi" }, + { "lbk", "Central Bontok" }, + { "lbl", "Libon Bikol" }, + { "lbm", "Lodhi" }, + { "lbn", "Lamet" }, + { "lbo", "Laven" }, + { "lbq", "Wampar" }, + { "lbr", "Lohorung" }, + { "lbs", "Libyan Sign Language" }, + { "lbt", "Lachi" }, + { "lbu", "Labu" }, + { "lbv", "Lavatbura-Lamusong" }, + { "lbw", "Tolaki" }, + { "lbx", "Lawangan" }, + { "lby", "Lamu-Lamu" }, + { "lbz", "Lardil" }, + { "lcc", "Legenyem" }, + { "lcd", "Lola" }, + { "lce", "Loncong" }, + { "lcf", "Lubu" }, + { "lch", "Luchazi" }, + { "lcl", "Lisela" }, + { "lcm", "Tungag" }, + { "lcp", "Western Lawa" }, + { "lcq", "Luhu" }, + { "lcs", "Lisabata-Nuniali" }, + { "lda", "Kla-Dan" }, + { "ldb", "Dũya" }, + { "ldd", "Luri" }, + { "ldg", "Lenyima" }, + { "ldh", "Lamja-Dengsa-Tola" }, + { "ldi", "Laari" }, + { "ldj", "Lemoro" }, + { "ldk", "Leelau" }, + { "ldl", "Kaan" }, + { "ldm", "Landoma" }, + { "ldn", "Láadan" }, + { "ldo", "Loo" }, + { "ldp", "Tso" }, + { "ldq", "Lufu" }, + { "lea", "Lega-Shabunda" }, + { "leb", "Lala-Bisa" }, + { "lec", "Leco" }, + { "led", "Lendu" }, + { "lee", "Lyélé" }, + { "lef", "Lelemi" }, + { "leg", "Lengua" }, + { "leh", "Lenje" }, + { "lei", "Lemio" }, + { "lej", "Lengola" }, + { "lek", "Leipon" }, + { "lel", "Lele (Democratic Republic of Congo)" }, + { "lem", "Nomaande" }, + { "len", "Lenca" }, + { "leo", "Leti (Cameroon)" }, + { "lep", "Lepcha" }, + { "leq", "Lembena" }, + { "ler", "Lenkau" }, + { "les", "Lese" }, + { "let", "Lesing-Gelimi" }, + { "leu", "Kara (Papua New Guinea)" }, + { "lev", "Lamma" }, + { "lew", "Ledo Kaili" }, + { "lex", "Luang" }, + { "ley", "Lemolang" }, + { "lez", "Lezghian" }, + { "lfa", "Lefa" }, + { "lfn", "Lingua Franca Nova" }, + { "lga", "Lungga" }, + { "lgb", "Laghu" }, + { "lgg", "Lugbara" }, + { "lgh", "Laghuu" }, + { "lgi", "Lengilu" }, + { "lgk", "Lingarak" }, + { "lgl", "Wala" }, + { "lgm", "Lega-Mwenga" }, + { "lgn", "Opuuo" }, + { "lgq", "Logba" }, + { "lgr", "Lengo" }, + { "lgt", "Pahi" }, + { "lgu", "Longgu" }, + { "lgz", "Ligenza" }, + { "lha", "Laha (Viet Nam)" }, + { "lhh", "Laha (Indonesia)" }, + { "lhi", "Lahu Shi" }, + { "lhl", "Lahul Lohar" }, + { "lhm", "Lhomi" }, + { "lhn", "Lahanan" }, + { "lhp", "Lhokpu" }, + { "lhs", "Mlahsö" }, + { "lht", "Lo-Toga" }, + { "lhu", "Lahu" }, + { "lia", "West-Central Limba" }, + { "lib", "Likum" }, + { "lic", "Hlai" }, + { "lid", "Nyindrou" }, + { "lie", "Likila" }, + { "lif", "Limbu" }, + { "lig", "Ligbi" }, + { "lih", "Lihir" }, + { "lii", "Lingkhim" }, + { "lij", "Ligurian" }, + { "lik", "Lika" }, + { "lil", "Lillooet" }, + { "lim", "Limburgan" }, + { "lin", "Lingala" }, + { "lio", "Liki" }, + { "lip", "Sekpele" }, + { "liq", "Libido" }, + { "lir", "Liberian English" }, + { "lis", "Lisu" }, + { "lit", "Lithuanian" }, + { "liu", "Logorik" }, + { "liv", "Liv" }, + { "liw", "Col" }, + { "lix", "Liabuku" }, + { "liy", "Banda-Bambari" }, + { "liz", "Libinza" }, + { "lja", "Golpa" }, + { "lje", "Rampi" }, + { "lji", "Laiyolo" }, + { "ljl", "Li'o" }, + { "ljp", "Lampung Api" }, + { "ljw", "Yirandali" }, + { "ljx", "Yuru" }, + { "lka", "Lakalei" }, + { "lkb", "Kabras" }, + { "lkc", "Kucong" }, + { "lkd", "Lakondê" }, + { "lke", "Kenyi" }, + { "lkh", "Lakha" }, + { "lki", "Laki" }, + { "lkj", "Remun" }, + { "lkl", "Laeko-Libuat" }, + { "lkm", "Kalaamaya" }, + { "lkn", "Lakon" }, + { "lko", "Khayo" }, + { "lkr", "Päri" }, + { "lks", "Kisa" }, + { "lkt", "Lakota" }, + { "lku", "Kungkari" }, + { "lky", "Lokoya" }, + { "lla", "Lala-Roba" }, + { "llb", "Lolo" }, + { "llc", "Lele (Guinea)" }, + { "lld", "Ladin" }, + { "lle", "Lele (Papua New Guinea)" }, + { "llf", "Hermit" }, + { "llg", "Lole" }, + { "llh", "Lamu" }, + { "lli", "Teke-Laali" }, + { "llj", "Ladji Ladji" }, + { "llk", "Lelak" }, + { "lll", "Lilau" }, + { "llm", "Lasalimu" }, + { "lln", "Lele (Chad)" }, + { "llo", "Khlor" }, + { "llp", "North Efate" }, + { "llq", "Lolak" }, + { "lls", "Lithuanian Sign Language" }, + { "llu", "Lau" }, + { "llx", "Lauan" }, + { "lma", "East Limba" }, + { "lmb", "Merei" }, + { "lmc", "Limilngan" }, + { "lmd", "Lumun" }, + { "lme", "Pévé" }, + { "lmf", "South Lembata" }, + { "lmg", "Lamogai" }, + { "lmh", "Lambichhong" }, + { "lmi", "Lombi" }, + { "lmj", "West Lembata" }, + { "lmk", "Lamkang" }, + { "lml", "Hano" }, + { "lmm", "Lamam" }, + { "lmn", "Lambadi" }, + { "lmo", "Lombard" }, + { "lmp", "Limbum" }, + { "lmq", "Lamatuka" }, + { "lmr", "Lamalera" }, + { "lmu", "Lamenu" }, + { "lmv", "Lomaiviti" }, + { "lmw", "Lake Miwok" }, + { "lmx", "Laimbue" }, + { "lmy", "Lamboya" }, + { "lmz", "Lumbee" }, + { "lna", "Langbashe" }, + { "lnb", "Mbalanhu" }, + { "lnd", "Lundayeh" }, + { "lng", "Langobardic" }, + { "lnh", "Lanoh" }, + { "lni", "Daantanai'" }, + { "lnj", "Leningitij" }, + { "lnl", "South Central Banda" }, + { "lnm", "Langam" }, + { "lnn", "Lorediakarkar" }, + { "lno", "Lango (Sudan)" }, + { "lns", "Lamnso'" }, + { "lnu", "Longuda" }, + { "lnw", "Lanima" }, + { "lnz", "Lonzo" }, + { "loa", "Loloda" }, + { "lob", "Lobi" }, + { "loc", "Inonhan" }, + { "loe", "Saluan" }, + { "lof", "Logol" }, + { "log", "Logo" }, + { "loh", "Narim" }, + { "loi", "Loma (Côte d'Ivoire)" }, + { "loj", "Lou" }, + { "lok", "Loko" }, + { "lol", "Mongo" }, + { "lom", "Loma (Liberia)" }, + { "lon", "Malawi Lomwe" }, + { "loo", "Lombo" }, + { "lop", "Lopa" }, + { "loq", "Lobala" }, + { "lor", "Téén" }, + { "los", "Loniu" }, + { "lot", "Otuho" }, + { "lou", "Louisiana Creole French" }, + { "lov", "Lopi" }, + { "low", "Tampias Lobu" }, + { "lox", "Loun" }, + { "loy", "Loke" }, + { "loz", "Lozi" }, + { "lpa", "Lelepa" }, + { "lpe", "Lepki" }, + { "lpn", "Long Phuri Naga" }, + { "lpo", "Lipo" }, + { "lpx", "Lopit" }, + { "lra", "Rara Bakati'" }, + { "lrc", "Northern Luri" }, + { "lre", "Laurentian" }, + { "lrg", "Laragia" }, + { "lri", "Marachi" }, + { "lrk", "Loarki" }, + { "lrl", "Lari" }, + { "lrm", "Marama" }, + { "lrn", "Lorang" }, + { "lro", "Laro" }, + { "lrr", "Southern Yamphu" }, + { "lrt", "Larantuka Malay" }, + { "lrv", "Larevat" }, + { "lrz", "Lemerig" }, + { "lsa", "Lasgerdi" }, + { "lsd", "Lishana Deni" }, + { "lse", "Lusengo" }, + { "lsg", "Lyons Sign Language" }, + { "lsh", "Lish" }, + { "lsi", "Lashi" }, + { "lsl", "Latvian Sign Language" }, + { "lsm", "Saamia" }, + { "lso", "Laos Sign Language" }, + { "lsp", "Panamanian Sign Language" }, + { "lsr", "Aruop" }, + { "lss", "Lasi" }, + { "lst", "Trinidad and Tobago Sign Language" }, + { "lsy", "Mauritian Sign Language" }, + { "ltc", "Late Middle Chinese" }, + { "ltg", "Latgalian" }, + { "lti", "Leti (Indonesia)" }, + { "ltn", "Latundê" }, + { "lto", "Tsotso" }, + { "lts", "Tachoni" }, + { "ltu", "Latu" }, + { "ltz", "Luxembourgish" }, + { "lua", "Luba-Lulua" }, + { "lub", "Luba-Katanga" }, + { "luc", "Aringa" }, + { "lud", "Ludian" }, + { "lue", "Luvale" }, + { "luf", "Laua" }, + { "lug", "Ganda" }, + { "lui", "Luiseno" }, + { "luj", "Luna" }, + { "luk", "Lunanakha" }, + { "lul", "Olu'bo" }, + { "lum", "Luimbi" }, + { "lun", "Lunda" }, + { "luo", "Luo (Kenya and Tanzania)" }, + { "lup", "Lumbu" }, + { "luq", "Lucumi" }, + { "lur", "Laura" }, + { "lus", "Lushai" }, + { "lut", "Lushootseed" }, + { "luu", "Lumba-Yakkha" }, + { "luv", "Luwati" }, + { "luw", "Luo (Cameroon)" }, + { "luy", "Luyia" }, + { "luz", "Southern Luri" }, + { "lva", "Maku'a" }, + { "lvk", "Lavukaleve" }, + { "lvs", "Standard Latvian" }, + { "lvu", "Levuka" }, + { "lwa", "Lwalu" }, + { "lwe", "Lewo Eleng" }, + { "lwg", "Wanga" }, + { "lwh", "White Lachi" }, + { "lwl", "Eastern Lawa" }, + { "lwm", "Laomian" }, + { "lwo", "Luwo" }, + { "lwt", "Lewotobi" }, + { "lwu", "Lawu" }, + { "lww", "Lewo" }, + { "lya", "Layakha" }, + { "lyg", "Lyngngam" }, + { "lyn", "Luyana" }, + { "lzh", "Literary Chinese" }, + { "lzl", "Litzlitz" }, + { "lzn", "Leinong Naga" }, + { "lzz", "Laz" }, + { "maa", "San Jerónimo Tecóatl Mazatec" }, + { "mab", "Yutanduchi Mixtec" }, + { "mad", "Madurese" }, + { "mae", "Bo-Rukul" }, + { "maf", "Mafa" }, + { "mag", "Magahi" }, + { "mah", "Marshallese" }, + { "mai", "Maithili" }, + { "maj", "Jalapa De Díaz Mazatec" }, + { "mak", "Makasar" }, + { "mal", "Malayalam" }, + { "mam", "Mam" }, + { "man", "Mandingo" }, + { "maq", "Chiquihuitlán Mazatec" }, + { "mar", "Marathi" }, + { "mas", "Masai" }, + { "mat", "San Francisco Matlatzinca" }, + { "mau", "Huautla Mazatec" }, + { "mav", "Sateré-Mawé" }, + { "maw", "Mampruli" }, + { "max", "North Moluccan Malay" }, + { "maz", "Central Mazahua" }, + { "mba", "Higaonon" }, + { "mbb", "Western Bukidnon Manobo" }, + { "mbc", "Macushi" }, + { "mbd", "Dibabawon Manobo" }, + { "mbe", "Molale" }, + { "mbf", "Baba Malay" }, + { "mbh", "Mangseng" }, + { "mbi", "Ilianen Manobo" }, + { "mbj", "Nadëb" }, + { "mbk", "Malol" }, + { "mbl", "Maxakalí" }, + { "mbm", "Ombamba" }, + { "mbn", "Macaguán" }, + { "mbo", "Mbo (Cameroon)" }, + { "mbp", "Malayo" }, + { "mbq", "Maisin" }, + { "mbr", "Nukak Makú" }, + { "mbs", "Sarangani Manobo" }, + { "mbt", "Matigsalug Manobo" }, + { "mbu", "Mbula-Bwazza" }, + { "mbv", "Mbulungish" }, + { "mbw", "Maring" }, + { "mbx", "Mari (East Sepik Province)" }, + { "mby", "Memoni" }, + { "mbz", "Amoltepec Mixtec" }, + { "mca", "Maca" }, + { "mcb", "Machiguenga" }, + { "mcc", "Bitur" }, + { "mcd", "Sharanahua" }, + { "mce", "Itundujia Mixtec" }, + { "mcf", "Matsés" }, + { "mcg", "Mapoyo" }, + { "mch", "Maquiritari" }, + { "mci", "Mese" }, + { "mcj", "Mvanip" }, + { "mck", "Mbunda" }, + { "mcl", "Macaguaje" }, + { "mcm", "Malaccan Creole Portuguese" }, + { "mcn", "Masana" }, + { "mco", "Coatlán Mixe" }, + { "mcp", "Makaa" }, + { "mcq", "Ese" }, + { "mcr", "Menya" }, + { "mcs", "Mambai" }, + { "mct", "Mengisa" }, + { "mcu", "Cameroon Mambila" }, + { "mcv", "Minanibai" }, + { "mcw", "Mawa (Chad)" }, + { "mcx", "Mpiemo" }, + { "mcy", "South Watut" }, + { "mcz", "Mawan" }, + { "mda", "Mada (Nigeria)" }, + { "mdb", "Morigi" }, + { "mdc", "Male (Papua New Guinea)" }, + { "mdd", "Mbum" }, + { "mde", "Maba (Chad)" }, + { "mdf", "Moksha" }, + { "mdg", "Massalat" }, + { "mdh", "Maguindanaon" }, + { "mdi", "Mamvu" }, + { "mdj", "Mangbetu" }, + { "mdk", "Mangbutu" }, + { "mdl", "Maltese Sign Language" }, + { "mdm", "Mayogo" }, + { "mdn", "Mbati" }, + { "mdp", "Mbala" }, + { "mdq", "Mbole" }, + { "mdr", "Mandar" }, + { "mds", "Maria (Papua New Guinea)" }, + { "mdt", "Mbere" }, + { "mdu", "Mboko" }, + { "mdv", "Santa Lucía Monteverde Mixtec" }, + { "mdw", "Mbosi" }, + { "mdx", "Dizin" }, + { "mdy", "Male (Ethiopia)" }, + { "mdz", "Suruí Do Pará" }, + { "mea", "Menka" }, + { "meb", "Ikobi" }, + { "mec", "Mara" }, + { "med", "Melpa" }, + { "mee", "Mengen" }, + { "mef", "Megam" }, + { "meh", "Southwestern Tlaxiaco Mixtec" }, + { "mei", "Midob" }, + { "mej", "Meyah" }, + { "mek", "Mekeo" }, + { "mel", "Central Melanau" }, + { "mem", "Mangala" }, + { "men", "Mende (Sierra Leone)" }, + { "meo", "Kedah Malay" }, + { "mep", "Miriwung" }, + { "meq", "Merey" }, + { "mer", "Meru" }, + { "mes", "Masmaje" }, + { "met", "Mato" }, + { "meu", "Motu" }, + { "mev", "Mano" }, + { "mew", "Maaka" }, + { "mey", "Hassaniyya" }, + { "mez", "Menominee" }, + { "mfa", "Pattani Malay" }, + { "mfb", "Bangka" }, + { "mfc", "Mba" }, + { "mfd", "Mendankwe-Nkwen" }, + { "mfe", "Morisyen" }, + { "mff", "Naki" }, + { "mfg", "Mogofin" }, + { "mfh", "Matal" }, + { "mfi", "Wandala" }, + { "mfj", "Mefele" }, + { "mfk", "North Mofu" }, + { "mfl", "Putai" }, + { "mfm", "Marghi South" }, + { "mfn", "Cross River Mbembe" }, + { "mfo", "Mbe" }, + { "mfp", "Makassar Malay" }, + { "mfq", "Moba" }, + { "mfr", "Marithiel" }, + { "mfs", "Mexican Sign Language" }, + { "mft", "Mokerang" }, + { "mfu", "Mbwela" }, + { "mfv", "Mandjak" }, + { "mfw", "Mulaha" }, + { "mfx", "Melo" }, + { "mfy", "Mayo" }, + { "mfz", "Mabaan" }, + { "mga", "Middle Irish (900-1200)" }, + { "mgb", "Mararit" }, + { "mgc", "Morokodo" }, + { "mgd", "Moru" }, + { "mge", "Mango" }, + { "mgf", "Maklew" }, + { "mgg", "Mpumpong" }, + { "mgh", "Makhuwa-Meetto" }, + { "mgi", "Lijili" }, + { "mgj", "Abureni" }, + { "mgk", "Mawes" }, + { "mgl", "Maleu-Kilenge" }, + { "mgm", "Mambae" }, + { "mgn", "Mbangi" }, + { "mgo", "Meta'" }, + { "mgp", "Eastern Magar" }, + { "mgq", "Malila" }, + { "mgr", "Mambwe-Lungu" }, + { "mgs", "Manda (Tanzania)" }, + { "mgt", "Mongol" }, + { "mgu", "Mailu" }, + { "mgv", "Matengo" }, + { "mgw", "Matumbi" }, + { "mgy", "Mbunga" }, + { "mgz", "Mbugwe" }, + { "mha", "Manda (India)" }, + { "mhb", "Mahongwe" }, + { "mhc", "Mocho" }, + { "mhd", "Mbugu" }, + { "mhe", "Besisi" }, + { "mhf", "Mamaa" }, + { "mhg", "Margu" }, + { "mhh", "Maskoy Pidgin" }, + { "mhi", "Ma'di" }, + { "mhj", "Mogholi" }, + { "mhk", "Mungaka" }, + { "mhl", "Mauwake" }, + { "mhm", "Makhuwa-Moniga" }, + { "mhn", "Mócheno" }, + { "mho", "Mashi (Zambia)" }, + { "mhp", "Balinese Malay" }, + { "mhq", "Mandan" }, + { "mhr", "Eastern Mari" }, + { "mhs", "Buru (Indonesia)" }, + { "mht", "Mandahuaca" }, + { "mhu", "Digaro-Mishmi" }, + { "mhw", "Mbukushu" }, + { "mhx", "Maru" }, + { "mhy", "Ma'anyan" }, + { "mhz", "Mor (Mor Islands)" }, + { "mia", "Miami" }, + { "mib", "Atatláhuca Mixtec" }, + { "mic", "Mi'kmaq" }, + { "mid", "Mandaic" }, + { "mie", "Ocotepec Mixtec" }, + { "mif", "Mofu-Gudur" }, + { "mig", "San Miguel El Grande Mixtec" }, + { "mih", "Chayuco Mixtec" }, + { "mii", "Chigmecatitlán Mixtec" }, + { "mij", "Abar" }, + { "mik", "Mikasuki" }, + { "mil", "Peñoles Mixtec" }, + { "mim", "Alacatlatzala Mixtec" }, + { "min", "Minangkabau" }, + { "mio", "Pinotepa Nacional Mixtec" }, + { "mip", "Apasco-Apoala Mixtec" }, + { "miq", "Mískito" }, + { "mir", "Isthmus Mixe" }, + { "mis", "Uncoded languages" }, + { "mit", "Southern Puebla Mixtec" }, + { "miu", "Cacaloxtepec Mixtec" }, + { "miw", "Akoye" }, + { "mix", "Mixtepec Mixtec" }, + { "miy", "Ayutla Mixtec" }, + { "miz", "Coatzospan Mixtec" }, + { "mjc", "San Juan Colorado Mixtec" }, + { "mjd", "Northwest Maidu" }, + { "mje", "Muskum" }, + { "mjg", "Tu" }, + { "mjh", "Mwera (Nyasa)" }, + { "mji", "Kim Mun" }, + { "mjj", "Mawak" }, + { "mjk", "Matukar" }, + { "mjl", "Mandeali" }, + { "mjm", "Medebur" }, + { "mjn", "Ma (Papua New Guinea)" }, + { "mjo", "Malankuravan" }, + { "mjp", "Malapandaram" }, + { "mjq", "Malaryan" }, + { "mjr", "Malavedan" }, + { "mjs", "Miship" }, + { "mjt", "Sauria Paharia" }, + { "mju", "Manna-Dora" }, + { "mjv", "Mannan" }, + { "mjw", "Karbi" }, + { "mjx", "Mahali" }, + { "mjy", "Mahican" }, + { "mjz", "Majhi" }, + { "mka", "Mbre" }, + { "mkb", "Mal Paharia" }, + { "mkc", "Siliput" }, + { "mkd", "Macedonian" }, + { "mke", "Mawchi" }, + { "mkf", "Miya" }, + { "mkg", "Mak (China)" }, + { "mki", "Dhatki" }, + { "mkj", "Mokilese" }, + { "mkk", "Byep" }, + { "mkl", "Mokole" }, + { "mkm", "Moklen" }, + { "mkn", "Kupang Malay" }, + { "mko", "Mingang Doso" }, + { "mkp", "Moikodi" }, + { "mkq", "Bay Miwok" }, + { "mkr", "Malas" }, + { "mks", "Silacayoapan Mixtec" }, + { "mkt", "Vamale" }, + { "mku", "Konyanka Maninka" }, + { "mkv", "Mafea" }, + { "mkw", "Kituba (Congo)" }, + { "mkx", "Kinamiging Manobo" }, + { "mky", "East Makian" }, + { "mkz", "Makasae" }, + { "mla", "Malo" }, + { "mlb", "Mbule" }, + { "mlc", "Cao Lan" }, + { "mle", "Manambu" }, + { "mlf", "Mal" }, + { "mlg", "Malagasy" }, + { "mlh", "Mape" }, + { "mli", "Malimpung" }, + { "mlj", "Miltu" }, + { "mlk", "Ilwana" }, + { "mll", "Malua Bay" }, + { "mlm", "Mulam" }, + { "mln", "Malango" }, + { "mlo", "Mlomp" }, + { "mlp", "Bargam" }, + { "mlq", "Western Maninkakan" }, + { "mlr", "Vame" }, + { "mls", "Masalit" }, + { "mlt", "Maltese" }, + { "mlu", "To'abaita" }, + { "mlv", "Motlav" }, + { "mlw", "Moloko" }, + { "mlx", "Malfaxal" }, + { "mlz", "Malaynon" }, + { "mma", "Mama" }, + { "mmb", "Momina" }, + { "mmc", "Michoacán Mazahua" }, + { "mmd", "Maonan" }, + { "mme", "Mae" }, + { "mmf", "Mundat" }, + { "mmg", "North Ambrym" }, + { "mmh", "Mehináku" }, + { "mmi", "Musar" }, + { "mmj", "Majhwar" }, + { "mmk", "Mukha-Dora" }, + { "mml", "Man Met" }, + { "mmm", "Maii" }, + { "mmn", "Mamanwa" }, + { "mmo", "Mangga Buang" }, + { "mmp", "Siawi" }, + { "mmq", "Musak" }, + { "mmr", "Western Xiangxi Miao" }, + { "mmt", "Malalamai" }, + { "mmu", "Mmaala" }, + { "mmv", "Miriti" }, + { "mmw", "Emae" }, + { "mmx", "Madak" }, + { "mmy", "Migaama" }, + { "mmz", "Mabaale" }, + { "mna", "Mbula" }, + { "mnb", "Muna" }, + { "mnc", "Manchu" }, + { "mnd", "Mondé" }, + { "mne", "Naba" }, + { "mnf", "Mundani" }, + { "mng", "Eastern Mnong" }, + { "mnh", "Mono (Democratic Republic of Congo)" }, + { "mni", "Manipuri" }, + { "mnj", "Munji" }, + { "mnk", "Mandinka" }, + { "mnl", "Tiale" }, + { "mnm", "Mapena" }, + { "mnn", "Southern Mnong" }, + { "mnp", "Min Bei Chinese" }, + { "mnq", "Minriq" }, + { "mnr", "Mono (USA)" }, + { "mns", "Mansi" }, + { "mnu", "Mer" }, + { "mnv", "Rennell-Bellona" }, + { "mnw", "Mon" }, + { "mnx", "Manikion" }, + { "mny", "Manyawa" }, + { "mnz", "Moni" }, + { "moa", "Mwan" }, + { "moc", "Mocoví" }, + { "mod", "Mobilian" }, + { "moe", "Montagnais" }, + { "mog", "Mongondow" }, + { "moh", "Mohawk" }, + { "moi", "Mboi" }, + { "moj", "Monzombo" }, + { "mok", "Morori" }, + { "mom", "Mangue" }, + { "mon", "Mongolian" }, + { "moo", "Monom" }, + { "mop", "Mopán Maya" }, + { "moq", "Mor (Bomberai Peninsula)" }, + { "mor", "Moro" }, + { "mos", "Mossi" }, + { "mot", "Barí" }, + { "mou", "Mogum" }, + { "mov", "Mohave" }, + { "mow", "Moi (Congo)" }, + { "mox", "Molima" }, + { "moy", "Shekkacho" }, + { "moz", "Mukulu" }, + { "mpa", "Mpoto" }, + { "mpb", "Mullukmulluk" }, + { "mpc", "Mangarayi" }, + { "mpd", "Machinere" }, + { "mpe", "Majang" }, + { "mpg", "Marba" }, + { "mph", "Maung" }, + { "mpi", "Mpade" }, + { "mpj", "Martu Wangka" }, + { "mpk", "Mbara (Chad)" }, + { "mpl", "Middle Watut" }, + { "mpm", "Yosondúa Mixtec" }, + { "mpn", "Mindiri" }, + { "mpo", "Miu" }, + { "mpp", "Migabac" }, + { "mpq", "Matís" }, + { "mpr", "Vangunu" }, + { "mps", "Dadibi" }, + { "mpt", "Mian" }, + { "mpu", "Makuráp" }, + { "mpv", "Mungkip" }, + { "mpw", "Mapidian" }, + { "mpx", "Misima-Panaeati" }, + { "mpy", "Mapia" }, + { "mpz", "Mpi" }, + { "mqa", "Maba (Indonesia)" }, + { "mqb", "Mbuko" }, + { "mqc", "Mangole" }, + { "mqe", "Matepi" }, + { "mqf", "Momuna" }, + { "mqg", "Kota Bangun Kutai Malay" }, + { "mqh", "Tlazoyaltepec Mixtec" }, + { "mqi", "Mariri" }, + { "mqj", "Mamasa" }, + { "mqk", "Rajah Kabunsuwan Manobo" }, + { "mql", "Mbelime" }, + { "mqm", "South Marquesan" }, + { "mqn", "Moronene" }, + { "mqo", "Modole" }, + { "mqp", "Manipa" }, + { "mqq", "Minokok" }, + { "mqr", "Mander" }, + { "mqs", "West Makian" }, + { "mqt", "Mok" }, + { "mqu", "Mandari" }, + { "mqv", "Mosimo" }, + { "mqw", "Murupi" }, + { "mqx", "Mamuju" }, + { "mqy", "Manggarai" }, + { "mqz", "Pano" }, + { "mra", "Mlabri" }, + { "mrb", "Marino" }, + { "mrc", "Maricopa" }, + { "mrd", "Western Magar" }, + { "mre", "Martha's Vineyard Sign Language" }, + { "mrf", "Elseng" }, + { "mrg", "Mising" }, + { "mrh", "Mara Chin" }, + { "mri", "Maori" }, + { "mrj", "Western Mari" }, + { "mrk", "Hmwaveke" }, + { "mrl", "Mortlockese" }, + { "mrm", "Merlav" }, + { "mrn", "Cheke Holo" }, + { "mro", "Mru" }, + { "mrp", "Morouas" }, + { "mrq", "North Marquesan" }, + { "mrr", "Maria (India)" }, + { "mrs", "Maragus" }, + { "mrt", "Marghi Central" }, + { "mru", "Mono (Cameroon)" }, + { "mrv", "Mangareva" }, + { "mrw", "Maranao" }, + { "mrx", "Maremgi" }, + { "mry", "Mandaya" }, + { "mrz", "Marind" }, + { "msa", "Malay (macrolanguage)" }, + { "msb", "Masbatenyo" }, + { "msc", "Sankaran Maninka" }, + { "msd", "Yucatec Maya Sign Language" }, + { "mse", "Musey" }, + { "msf", "Mekwei" }, + { "msg", "Moraid" }, + { "msh", "Masikoro Malagasy" }, + { "msi", "Sabah Malay" }, + { "msj", "Ma (Democratic Republic of Congo)" }, + { "msk", "Mansaka" }, + { "msl", "Molof" }, + { "msm", "Agusan Manobo" }, + { "msn", "Vurës" }, + { "mso", "Mombum" }, + { "msp", "Maritsauá" }, + { "msq", "Caac" }, + { "msr", "Mongolian Sign Language" }, + { "mss", "West Masela" }, + { "msu", "Musom" }, + { "msv", "Maslam" }, + { "msw", "Mansoanka" }, + { "msx", "Moresada" }, + { "msy", "Aruamu" }, + { "msz", "Momare" }, + { "mta", "Cotabato Manobo" }, + { "mtb", "Anyin Morofo" }, + { "mtc", "Munit" }, + { "mtd", "Mualang" }, + { "mte", "Mono (Solomon Islands)" }, + { "mtf", "Murik (Papua New Guinea)" }, + { "mtg", "Una" }, + { "mth", "Munggui" }, + { "mti", "Maiwa (Papua New Guinea)" }, + { "mtj", "Moskona" }, + { "mtk", "Mbe'" }, + { "mtl", "Montol" }, + { "mtm", "Mator" }, + { "mtn", "Matagalpa" }, + { "mto", "Totontepec Mixe" }, + { "mtp", "Wichí Lhamtés Nocten" }, + { "mtq", "Muong" }, + { "mtr", "Mewari" }, + { "mts", "Yora" }, + { "mtt", "Mota" }, + { "mtu", "Tututepec Mixtec" }, + { "mtv", "Asaro'o" }, + { "mtw", "Southern Binukidnon" }, + { "mtx", "Tidaá Mixtec" }, + { "mty", "Nabi" }, + { "mua", "Mundang" }, + { "mub", "Mubi" }, + { "muc", "Ajumbu" }, + { "mud", "Mednyj Aleut" }, + { "mue", "Media Lengua" }, + { "mug", "Musgu" }, + { "muh", "Mündü" }, + { "mui", "Musi" }, + { "muj", "Mabire" }, + { "muk", "Mugom" }, + { "mul", "Multiple languages" }, + { "mum", "Maiwala" }, + { "muo", "Nyong" }, + { "mup", "Malvi" }, + { "muq", "Eastern Xiangxi Miao" }, + { "mur", "Murle" }, + { "mus", "Creek" }, + { "mut", "Western Muria" }, + { "muu", "Yaaku" }, + { "muv", "Muthuvan" }, + { "mux", "Bo-Ung" }, + { "muy", "Muyang" }, + { "muz", "Mursi" }, + { "mva", "Manam" }, + { "mvb", "Mattole" }, + { "mvd", "Mamboru" }, + { "mve", "Marwari (Pakistan)" }, + { "mvf", "Peripheral Mongolian" }, + { "mvg", "Yucuañe Mixtec" }, + { "mvh", "Mulgi" }, + { "mvi", "Miyako" }, + { "mvk", "Mekmek" }, + { "mvl", "Mbara (Australia)" }, + { "mvm", "Muya" }, + { "mvn", "Minaveha" }, + { "mvo", "Marovo" }, + { "mvp", "Duri" }, + { "mvq", "Moere" }, + { "mvr", "Marau" }, + { "mvs", "Massep" }, + { "mvt", "Mpotovoro" }, + { "mvu", "Marfa" }, + { "mvv", "Tagal Murut" }, + { "mvw", "Machinga" }, + { "mvx", "Meoswar" }, + { "mvy", "Indus Kohistani" }, + { "mvz", "Mesqan" }, + { "mwa", "Mwatebu" }, + { "mwb", "Juwal" }, + { "mwc", "Are" }, + { "mwe", "Mwera (Chimwera)" }, + { "mwf", "Murrinh-Patha" }, + { "mwg", "Aiklep" }, + { "mwh", "Mouk-Aria" }, + { "mwi", "Labo" }, + { "mwj", "Maligo" }, + { "mwk", "Kita Maninkakan" }, + { "mwl", "Mirandese" }, + { "mwm", "Sar" }, + { "mwn", "Nyamwanga" }, + { "mwo", "Central Maewo" }, + { "mwp", "Kala Lagaw Ya" }, + { "mwq", "Mün Chin" }, + { "mwr", "Marwari" }, + { "mws", "Mwimbi-Muthambi" }, + { "mwt", "Moken" }, + { "mwu", "Mittu" }, + { "mwv", "Mentawai" }, + { "mww", "Hmong Daw" }, + { "mwx", "Mediak" }, + { "mwy", "Mosiro" }, + { "mwz", "Moingi" }, + { "mxa", "Northwest Oaxaca Mixtec" }, + { "mxb", "Tezoatlán Mixtec" }, + { "mxc", "Manyika" }, + { "mxd", "Modang" }, + { "mxe", "Mele-Fila" }, + { "mxf", "Malgbe" }, + { "mxg", "Mbangala" }, + { "mxh", "Mvuba" }, + { "mxi", "Mozarabic" }, + { "mxj", "Miju-Mishmi" }, + { "mxk", "Monumbo" }, + { "mxl", "Maxi Gbe" }, + { "mxm", "Meramera" }, + { "mxn", "Moi (Indonesia)" }, + { "mxo", "Mbowe" }, + { "mxp", "Tlahuitoltepec Mixe" }, + { "mxq", "Juquila Mixe" }, + { "mxr", "Murik (Malaysia)" }, + { "mxs", "Huitepec Mixtec" }, + { "mxt", "Jamiltepec Mixtec" }, + { "mxu", "Mada (Cameroon)" }, + { "mxv", "Metlatónoc Mixtec" }, + { "mxw", "Namo" }, + { "mxx", "Mahou" }, + { "mxy", "Southeastern Nochixtlán Mixtec" }, + { "mxz", "Central Masela" }, + { "mya", "Burmese" }, + { "myb", "Mbay" }, + { "myc", "Mayeka" }, + { "myd", "Maramba" }, + { "mye", "Myene" }, + { "myf", "Bambassi" }, + { "myg", "Manta" }, + { "myh", "Makah" }, + { "myi", "Mina (India)" }, + { "myj", "Mangayat" }, + { "myk", "Mamara Senoufo" }, + { "myl", "Moma" }, + { "mym", "Me'en" }, + { "myo", "Anfillo" }, + { "myp", "Pirahã" }, + { "myr", "Muniche" }, + { "mys", "Mesmes" }, + { "myu", "Mundurukú" }, + { "myv", "Erzya" }, + { "myw", "Muyuw" }, + { "myx", "Masaaba" }, + { "myy", "Macuna" }, + { "myz", "Classical Mandaic" }, + { "mza", "Santa María Zacatepec Mixtec" }, + { "mzb", "Tumzabt" }, + { "mzc", "Madagascar Sign Language" }, + { "mzd", "Malimba" }, + { "mze", "Morawa" }, + { "mzg", "Monastic Sign Language" }, + { "mzh", "Wichí Lhamtés Güisnay" }, + { "mzi", "Ixcatlán Mazatec" }, + { "mzj", "Manya" }, + { "mzk", "Nigeria Mambila" }, + { "mzl", "Mazatlán Mixe" }, + { "mzm", "Mumuye" }, + { "mzn", "Mazanderani" }, + { "mzo", "Matipuhy" }, + { "mzp", "Movima" }, + { "mzq", "Mori Atas" }, + { "mzr", "Marúbo" }, + { "mzs", "Macanese" }, + { "mzt", "Mintil" }, + { "mzu", "Inapang" }, + { "mzv", "Manza" }, + { "mzw", "Deg" }, + { "mzx", "Mawayana" }, + { "mzy", "Mozambican Sign Language" }, + { "mzz", "Maiadomu" }, + { "naa", "Namla" }, + { "nab", "Southern Nambikuára" }, + { "nac", "Narak" }, + { "nad", "Nijadali" }, + { "nae", "Naka'ela" }, + { "naf", "Nabak" }, + { "nag", "Naga Pidgin" }, + { "naj", "Nalu" }, + { "nak", "Nakanai" }, + { "nal", "Nalik" }, + { "nam", "Ngan'gityemerri" }, + { "nan", "Min Nan Chinese" }, + { "nao", "Naaba" }, + { "nap", "Neapolitan" }, + { "naq", "Nama (Namibia)" }, + { "nar", "Iguta" }, + { "nas", "Naasioi" }, + { "nat", "Hungworo" }, + { "nau", "Nauru" }, + { "nav", "Navajo" }, + { "naw", "Nawuri" }, + { "nax", "Nakwi" }, + { "nay", "Narrinyeri" }, + { "naz", "Coatepec Nahuatl" }, + { "nba", "Nyemba" }, + { "nbb", "Ndoe" }, + { "nbc", "Chang Naga" }, + { "nbd", "Ngbinda" }, + { "nbe", "Konyak Naga" }, + { "nbg", "Nagarchal" }, + { "nbh", "Ngamo" }, + { "nbi", "Mao Naga" }, + { "nbj", "Ngarinman" }, + { "nbk", "Nake" }, + { "nbl", "South Ndebele" }, + { "nbm", "Ngbaka Ma'bo" }, + { "nbn", "Kuri" }, + { "nbo", "Nkukoli" }, + { "nbp", "Nnam" }, + { "nbq", "Nggem" }, + { "nbr", "Numana-Nunku-Gbantu-Numbu" }, + { "nbs", "Namibian Sign Language" }, + { "nbt", "Na" }, + { "nbu", "Rongmei Naga" }, + { "nbv", "Ngamambo" }, + { "nbw", "Southern Ngbandi" }, + { "nby", "Ningera" }, + { "nca", "Iyo" }, + { "ncb", "Central Nicobarese" }, + { "ncc", "Ponam" }, + { "ncd", "Nachering" }, + { "nce", "Yale" }, + { "ncf", "Notsi" }, + { "ncg", "Nisga'a" }, + { "nch", "Central Huasteca Nahuatl" }, + { "nci", "Classical Nahuatl" }, + { "ncj", "Northern Puebla Nahuatl" }, + { "nck", "Nakara" }, + { "ncl", "Michoacán Nahuatl" }, + { "ncm", "Nambo" }, + { "ncn", "Nauna" }, + { "nco", "Sibe" }, + { "ncp", "Ndaktup" }, + { "ncr", "Ncane" }, + { "ncs", "Nicaraguan Sign Language" }, + { "nct", "Chothe Naga" }, + { "ncu", "Chumburung" }, + { "ncx", "Central Puebla Nahuatl" }, + { "ncz", "Natchez" }, + { "nda", "Ndasa" }, + { "ndb", "Kenswei Nsei" }, + { "ndc", "Ndau" }, + { "ndd", "Nde-Nsele-Nta" }, + { "nde", "North Ndebele" }, + { "ndf", "Nadruvian" }, + { "ndg", "Ndengereko" }, + { "ndh", "Ndali" }, + { "ndi", "Samba Leko" }, + { "ndj", "Ndamba" }, + { "ndk", "Ndaka" }, + { "ndl", "Ndolo" }, + { "ndm", "Ndam" }, + { "ndn", "Ngundi" }, + { "ndo", "Ndonga" }, + { "ndp", "Ndo" }, + { "ndq", "Ndombe" }, + { "ndr", "Ndoola" }, + { "nds", "Low German" }, + { "ndt", "Ndunga" }, + { "ndu", "Dugun" }, + { "ndv", "Ndut" }, + { "ndw", "Ndobo" }, + { "ndx", "Nduga" }, + { "ndy", "Lutos" }, + { "ndz", "Ndogo" }, + { "nea", "Eastern Ngad'a" }, + { "neb", "Toura (Côte d'Ivoire)" }, + { "nec", "Nedebang" }, + { "ned", "Nde-Gbite" }, + { "nee", "Nêlêmwa-Nixumwak" }, + { "nef", "Nefamese" }, + { "neg", "Negidal" }, + { "neh", "Nyenkha" }, + { "nei", "Neo-Hittite" }, + { "nej", "Neko" }, + { "nek", "Neku" }, + { "nem", "Nemi" }, + { "nen", "Nengone" }, + { "neo", "Ná-Meo" }, + { "nep", "Nepali (macrolanguage)" }, + { "neq", "North Central Mixe" }, + { "ner", "Yahadian" }, + { "nes", "Bhoti Kinnauri" }, + { "net", "Nete" }, + { "neu", "Neo" }, + { "nev", "Nyaheun" }, + { "new", "Newari" }, + { "nex", "Neme" }, + { "ney", "Neyo" }, + { "nez", "Nez Perce" }, + { "nfa", "Dhao" }, + { "nfd", "Ahwai" }, + { "nfl", "Ayiwo" }, + { "nfr", "Nafaanra" }, + { "nfu", "Mfumte" }, + { "nga", "Ngbaka" }, + { "ngb", "Northern Ngbandi" }, + { "ngc", "Ngombe (Democratic Republic of Congo)" }, + { "ngd", "Ngando (Central African Republic)" }, + { "nge", "Ngemba" }, + { "ngg", "Ngbaka Manza" }, + { "ngh", "Nu" }, + { "ngi", "Ngizim" }, + { "ngj", "Ngie" }, + { "ngk", "Dalabon" }, + { "ngl", "Lomwe" }, + { "ngm", "Ngatik Men's Creole" }, + { "ngn", "Ngwo" }, + { "ngo", "Ngoni" }, + { "ngp", "Ngulu" }, + { "ngq", "Ngurimi" }, + { "ngr", "Engdewu" }, + { "ngs", "Gvoko" }, + { "ngt", "Ngeq" }, + { "ngu", "Guerrero Nahuatl" }, + { "ngv", "Nagumi" }, + { "ngw", "Ngwaba" }, + { "ngx", "Nggwahyi" }, + { "ngy", "Tibea" }, + { "ngz", "Ngungwel" }, + { "nha", "Nhanda" }, + { "nhb", "Beng" }, + { "nhc", "Tabasco Nahuatl" }, + { "nhd", "Chiripá" }, + { "nhe", "Eastern Huasteca Nahuatl" }, + { "nhf", "Nhuwala" }, + { "nhg", "Tetelcingo Nahuatl" }, + { "nhh", "Nahari" }, + { "nhi", "Zacatlán-Ahuacatlán-Tepetzintla Nahuatl" }, + { "nhk", "Isthmus-Cosoleacaque Nahuatl" }, + { "nhm", "Morelos Nahuatl" }, + { "nhn", "Central Nahuatl" }, + { "nho", "Takuu" }, + { "nhp", "Isthmus-Pajapan Nahuatl" }, + { "nhq", "Huaxcaleca Nahuatl" }, + { "nhr", "Naro" }, + { "nht", "Ometepec Nahuatl" }, + { "nhu", "Noone" }, + { "nhv", "Temascaltepec Nahuatl" }, + { "nhw", "Western Huasteca Nahuatl" }, + { "nhx", "Isthmus-Mecayapan Nahuatl" }, + { "nhy", "Northern Oaxaca Nahuatl" }, + { "nhz", "Santa María La Alta Nahuatl" }, + { "nia", "Nias" }, + { "nib", "Nakame" }, + { "nid", "Ngandi" }, + { "nie", "Niellim" }, + { "nif", "Nek" }, + { "nig", "Ngalakan" }, + { "nih", "Nyiha (Tanzania)" }, + { "nii", "Nii" }, + { "nij", "Ngaju" }, + { "nik", "Southern Nicobarese" }, + { "nil", "Nila" }, + { "nim", "Nilamba" }, + { "nin", "Ninzo" }, + { "nio", "Nganasan" }, + { "niq", "Nandi" }, + { "nir", "Nimboran" }, + { "nis", "Nimi" }, + { "nit", "Southeastern Kolami" }, + { "niu", "Niuean" }, + { "niv", "Gilyak" }, + { "niw", "Nimo" }, + { "nix", "Hema" }, + { "niy", "Ngiti" }, + { "niz", "Ningil" }, + { "nja", "Nzanyi" }, + { "njb", "Nocte Naga" }, + { "njd", "Ndonde Hamba" }, + { "njh", "Lotha Naga" }, + { "nji", "Gudanji" }, + { "njj", "Njen" }, + { "njl", "Njalgulgule" }, + { "njm", "Angami Naga" }, + { "njn", "Liangmai Naga" }, + { "njo", "Ao Naga" }, + { "njr", "Njerep" }, + { "njs", "Nisa" }, + { "njt", "Ndyuka-Trio Pidgin" }, + { "nju", "Ngadjunmaya" }, + { "njx", "Kunyi" }, + { "njy", "Njyem" }, + { "njz", "Nyishi" }, + { "nka", "Nkoya" }, + { "nkb", "Khoibu Naga" }, + { "nkc", "Nkongho" }, + { "nkd", "Koireng" }, + { "nke", "Duke" }, + { "nkf", "Inpui Naga" }, + { "nkg", "Nekgini" }, + { "nkh", "Khezha Naga" }, + { "nki", "Thangal Naga" }, + { "nkj", "Nakai" }, + { "nkk", "Nokuku" }, + { "nkm", "Namat" }, + { "nkn", "Nkangala" }, + { "nko", "Nkonya" }, + { "nkp", "Niuatoputapu" }, + { "nkq", "Nkami" }, + { "nkr", "Nukuoro" }, + { "nks", "North Asmat" }, + { "nkt", "Nyika (Tanzania)" }, + { "nku", "Bouna Kulango" }, + { "nkv", "Nyika (Malawi and Zambia)" }, + { "nkw", "Nkutu" }, + { "nkx", "Nkoroo" }, + { "nkz", "Nkari" }, + { "nla", "Ngombale" }, + { "nlc", "Nalca" }, + { "nld", "Dutch" }, + { "nle", "East Nyala" }, + { "nlg", "Gela" }, + { "nli", "Grangali" }, + { "nlj", "Nyali" }, + { "nlk", "Ninia Yali" }, + { "nll", "Nihali" }, + { "nlo", "Ngul" }, + { "nlq", "Lao Naga" }, + { "nlu", "Nchumbulu" }, + { "nlv", "Orizaba Nahuatl" }, + { "nlw", "Walangama" }, + { "nlx", "Nahali" }, + { "nly", "Nyamal" }, + { "nlz", "Nalögo" }, + { "nma", "Maram Naga" }, + { "nmb", "Big Nambas" }, + { "nmc", "Ngam" }, + { "nmd", "Ndumu" }, + { "nme", "Mzieme Naga" }, + { "nmf", "Tangkhul Naga (India)" }, + { "nmg", "Kwasio" }, + { "nmh", "Monsang Naga" }, + { "nmi", "Nyam" }, + { "nmj", "Ngombe (Central African Republic)" }, + { "nmk", "Namakura" }, + { "nml", "Ndemli" }, + { "nmm", "Manangba" }, + { "nmn", "!Xóõ" }, + { "nmo", "Moyon Naga" }, + { "nmp", "Nimanbur" }, + { "nmq", "Nambya" }, + { "nmr", "Nimbari" }, + { "nms", "Letemboi" }, + { "nmt", "Namonuito" }, + { "nmu", "Northeast Maidu" }, + { "nmv", "Ngamini" }, + { "nmw", "Nimoa" }, + { "nmx", "Nama (Papua New Guinea)" }, + { "nmy", "Namuyi" }, + { "nmz", "Nawdm" }, + { "nna", "Nyangumarta" }, + { "nnb", "Nande" }, + { "nnc", "Nancere" }, + { "nnd", "West Ambae" }, + { "nne", "Ngandyera" }, + { "nnf", "Ngaing" }, + { "nng", "Maring Naga" }, + { "nnh", "Ngiemboon" }, + { "nni", "North Nuaulu" }, + { "nnj", "Nyangatom" }, + { "nnk", "Nankina" }, + { "nnl", "Northern Rengma Naga" }, + { "nnm", "Namia" }, + { "nnn", "Ngete" }, + { "nno", "Norwegian Nynorsk" }, + { "nnp", "Wancho Naga" }, + { "nnq", "Ngindo" }, + { "nnr", "Narungga" }, + { "nns", "Ningye" }, + { "nnt", "Nanticoke" }, + { "nnu", "Dwang" }, + { "nnv", "Nugunu (Australia)" }, + { "nnw", "Southern Nuni" }, + { "nnx", "Ngong" }, + { "nny", "Nyangga" }, + { "nnz", "Nda'nda'" }, + { "noa", "Woun Meu" }, + { "nob", "Norwegian Bokmål" }, + { "noc", "Nuk" }, + { "nod", "Northern Thai" }, + { "noe", "Nimadi" }, + { "nof", "Nomane" }, + { "nog", "Nogai" }, + { "noh", "Nomu" }, + { "noi", "Noiri" }, + { "noj", "Nonuya" }, + { "nok", "Nooksack" }, + { "nol", "Nomlaki" }, + { "nom", "Nocamán" }, + { "non", "Old Norse" }, + { "nop", "Numanggang" }, + { "noq", "Ngongo" }, + { "nor", "Norwegian" }, + { "nos", "Eastern Nisu" }, + { "not", "Nomatsiguenga" }, + { "nou", "Ewage-Notu" }, + { "nov", "Novial" }, + { "now", "Nyambo" }, + { "noy", "Noy" }, + { "noz", "Nayi" }, + { "npa", "Nar Phu" }, + { "npb", "Nupbikha" }, + { "npg", "Ponyo-Gongwang Naga" }, + { "nph", "Phom Naga" }, + { "npi", "Nepali (individual language)" }, + { "npl", "Southeastern Puebla Nahuatl" }, + { "npn", "Mondropolon" }, + { "npo", "Pochuri Naga" }, + { "nps", "Nipsan" }, + { "npu", "Puimei Naga" }, + { "npy", "Napu" }, + { "nqg", "Southern Nago" }, + { "nqk", "Kura Ede Nago" }, + { "nqm", "Ndom" }, + { "nqn", "Nen" }, + { "nqo", "N'Ko" }, + { "nqq", "Kyan-Karyaw Naga" }, + { "nqy", "Akyaung Ari Naga" }, + { "nra", "Ngom" }, + { "nrb", "Nara" }, + { "nrc", "Noric" }, + { "nre", "Southern Rengma Naga" }, + { "nrg", "Narango" }, + { "nri", "Chokri Naga" }, + { "nrk", "Ngarla" }, + { "nrl", "Ngarluma" }, + { "nrm", "Narom" }, + { "nrn", "Norn" }, + { "nrp", "North Picene" }, + { "nrr", "Norra" }, + { "nrt", "Northern Kalapuya" }, + { "nru", "Narua" }, + { "nrx", "Ngurmbur" }, + { "nrz", "Lala" }, + { "nsa", "Sangtam Naga" }, + { "nsc", "Nshi" }, + { "nsd", "Southern Nisu" }, + { "nse", "Nsenga" }, + { "nsf", "Northwestern Nisu" }, + { "nsg", "Ngasa" }, + { "nsh", "Ngoshie" }, + { "nsi", "Nigerian Sign Language" }, + { "nsk", "Naskapi" }, + { "nsl", "Norwegian Sign Language" }, + { "nsm", "Sumi Naga" }, + { "nsn", "Nehan" }, + { "nso", "Pedi" }, + { "nsp", "Nepalese Sign Language" }, + { "nsq", "Northern Sierra Miwok" }, + { "nsr", "Maritime Sign Language" }, + { "nss", "Nali" }, + { "nst", "Tase Naga" }, + { "nsu", "Sierra Negra Nahuatl" }, + { "nsv", "Southwestern Nisu" }, + { "nsw", "Navut" }, + { "nsx", "Nsongo" }, + { "nsy", "Nasal" }, + { "nsz", "Nisenan" }, + { "nte", "Nathembo" }, + { "ntg", "Ngantangarra" }, + { "nti", "Natioro" }, + { "ntj", "Ngaanyatjarra" }, + { "ntk", "Ikoma-Nata-Isenye" }, + { "ntm", "Nateni" }, + { "nto", "Ntomba" }, + { "ntp", "Northern Tepehuan" }, + { "ntr", "Delo" }, + { "nts", "Natagaimas" }, + { "ntu", "Natügu" }, + { "ntw", "Nottoway" }, + { "ntx", "Tangkhul Naga (Myanmar)" }, + { "nty", "Mantsi" }, + { "ntz", "Natanzi" }, + { "nua", "Yuanga" }, + { "nuc", "Nukuini" }, + { "nud", "Ngala" }, + { "nue", "Ngundu" }, + { "nuf", "Nusu" }, + { "nug", "Nungali" }, + { "nuh", "Ndunda" }, + { "nui", "Ngumbi" }, + { "nuj", "Nyole" }, + { "nuk", "Nuu-chah-nulth" }, + { "nul", "Nusa Laut" }, + { "num", "Niuafo'ou" }, + { "nun", "Anong" }, + { "nuo", "Nguôn" }, + { "nup", "Nupe-Nupe-Tako" }, + { "nuq", "Nukumanu" }, + { "nur", "Nukuria" }, + { "nus", "Nuer" }, + { "nut", "Nung (Viet Nam)" }, + { "nuu", "Ngbundu" }, + { "nuv", "Northern Nuni" }, + { "nuw", "Nguluwan" }, + { "nux", "Mehek" }, + { "nuy", "Nunggubuyu" }, + { "nuz", "Tlamacazapa Nahuatl" }, + { "nvh", "Nasarian" }, + { "nvm", "Namiae" }, + { "nvo", "Nyokon" }, + { "nwa", "Nawathinehena" }, + { "nwb", "Nyabwa" }, + { "nwc", "Classical Newari" }, + { "nwe", "Ngwe" }, + { "nwg", "Ngayawung" }, + { "nwi", "Southwest Tanna" }, + { "nwm", "Nyamusa-Molo" }, + { "nwo", "Nauo" }, + { "nwr", "Nawaru" }, + { "nwx", "Middle Newar" }, + { "nwy", "Nottoway-Meherrin" }, + { "nxa", "Nauete" }, + { "nxd", "Ngando (Democratic Republic of Congo)" }, + { "nxe", "Nage" }, + { "nxg", "Ngad'a" }, + { "nxi", "Nindi" }, + { "nxk", "Koki Naga" }, + { "nxl", "South Nuaulu" }, + { "nxm", "Numidian" }, + { "nxn", "Ngawun" }, + { "nxq", "Naxi" }, + { "nxr", "Ninggerum" }, + { "nxu", "Narau" }, + { "nxx", "Nafri" }, + { "nya", "Nyanja" }, + { "nyb", "Nyangbo" }, + { "nyc", "Nyanga-li" }, + { "nyd", "Nyore" }, + { "nye", "Nyengo" }, + { "nyf", "Giryama" }, + { "nyg", "Nyindu" }, + { "nyh", "Nyigina" }, + { "nyi", "Ama (Sudan)" }, + { "nyj", "Nyanga" }, + { "nyk", "Nyaneka" }, + { "nyl", "Nyeu" }, + { "nym", "Nyamwezi" }, + { "nyn", "Nyankole" }, + { "nyo", "Nyoro" }, + { "nyp", "Nyang'i" }, + { "nyq", "Nayini" }, + { "nyr", "Nyiha (Malawi)" }, + { "nys", "Nyunga" }, + { "nyt", "Nyawaygi" }, + { "nyu", "Nyungwe" }, + { "nyv", "Nyulnyul" }, + { "nyw", "Nyaw" }, + { "nyx", "Nganyaywana" }, + { "nyy", "Nyakyusa-Ngonde" }, + { "nza", "Tigon Mbembe" }, + { "nzb", "Njebi" }, + { "nzi", "Nzima" }, + { "nzk", "Nzakara" }, + { "nzm", "Zeme Naga" }, + { "nzs", "New Zealand Sign Language" }, + { "nzu", "Teke-Nzikou" }, + { "nzy", "Nzakambay" }, + { "nzz", "Nanga Dama Dogon" }, + { "oaa", "Orok" }, + { "oac", "Oroch" }, + { "oar", "Old Aramaic (up to 700 BCE)" }, + { "oav", "Old Avar" }, + { "obi", "Obispeño" }, + { "obk", "Southern Bontok" }, + { "obl", "Oblo" }, + { "obm", "Moabite" }, + { "obo", "Obo Manobo" }, + { "obr", "Old Burmese" }, + { "obt", "Old Breton" }, + { "obu", "Obulom" }, + { "oca", "Ocaina" }, + { "och", "Old Chinese" }, + { "oci", "Occitan (post 1500)" }, + { "oco", "Old Cornish" }, + { "ocu", "Atzingo Matlatzinca" }, + { "oda", "Odut" }, + { "odk", "Od" }, + { "odt", "Old Dutch" }, + { "odu", "Odual" }, + { "ofo", "Ofo" }, + { "ofs", "Old Frisian" }, + { "ofu", "Efutop" }, + { "ogb", "Ogbia" }, + { "ogc", "Ogbah" }, + { "oge", "Old Georgian" }, + { "ogg", "Ogbogolo" }, + { "ogo", "Khana" }, + { "ogu", "Ogbronuagum" }, + { "oht", "Old Hittite" }, + { "ohu", "Old Hungarian" }, + { "oia", "Oirata" }, + { "oin", "Inebu One" }, + { "ojb", "Northwestern Ojibwa" }, + { "ojc", "Central Ojibwa" }, + { "ojg", "Eastern Ojibwa" }, + { "oji", "Ojibwa" }, + { "ojp", "Old Japanese" }, + { "ojs", "Severn Ojibwa" }, + { "ojv", "Ontong Java" }, + { "ojw", "Western Ojibwa" }, + { "oka", "Okanagan" }, + { "okb", "Okobo" }, + { "okd", "Okodia" }, + { "oke", "Okpe (Southwestern Edo)" }, + { "okg", "Koko Babangk" }, + { "okh", "Koresh-e Rostam" }, + { "oki", "Okiek" }, + { "okj", "Oko-Juwoi" }, + { "okk", "Kwamtim One" }, + { "okl", "Old Kentish Sign Language" }, + { "okm", "Middle Korean (10th-16th cent.)" }, + { "okn", "Oki-No-Erabu" }, + { "oko", "Old Korean (3rd-9th cent.)" }, + { "okr", "Kirike" }, + { "oks", "Oko-Eni-Osayen" }, + { "oku", "Oku" }, + { "okv", "Orokaiva" }, + { "okx", "Okpe (Northwestern Edo)" }, + { "ola", "Walungge" }, + { "old", "Mochi" }, + { "ole", "Olekha" }, + { "olk", "Olkol" }, + { "olm", "Oloma" }, + { "olo", "Livvi" }, + { "olr", "Olrat" }, + { "oma", "Omaha-Ponca" }, + { "omb", "East Ambae" }, + { "omc", "Mochica" }, + { "ome", "Omejes" }, + { "omg", "Omagua" }, + { "omi", "Omi" }, + { "omk", "Omok" }, + { "oml", "Ombo" }, + { "omn", "Minoan" }, + { "omo", "Utarmbung" }, + { "omp", "Old Manipuri" }, + { "omr", "Old Marathi" }, + { "omt", "Omotik" }, + { "omu", "Omurano" }, + { "omw", "South Tairora" }, + { "omx", "Old Mon" }, + { "ona", "Ona" }, + { "onb", "Lingao" }, + { "one", "Oneida" }, + { "ong", "Olo" }, + { "oni", "Onin" }, + { "onj", "Onjob" }, + { "onk", "Kabore One" }, + { "onn", "Onobasulu" }, + { "ono", "Onondaga" }, + { "onp", "Sartang" }, + { "onr", "Northern One" }, + { "ons", "Ono" }, + { "ont", "Ontenu" }, + { "onu", "Unua" }, + { "onw", "Old Nubian" }, + { "onx", "Onin Based Pidgin" }, + { "ood", "Tohono O'odham" }, + { "oog", "Ong" }, + { "oon", "Önge" }, + { "oor", "Oorlams" }, + { "oos", "Old Ossetic" }, + { "opa", "Okpamheri" }, + { "opk", "Kopkaka" }, + { "opm", "Oksapmin" }, + { "opo", "Opao" }, + { "opt", "Opata" }, + { "opy", "Ofayé" }, + { "ora", "Oroha" }, + { "orc", "Orma" }, + { "ore", "Orejón" }, + { "org", "Oring" }, + { "orh", "Oroqen" }, + { "ori", "Oriya (macrolanguage)" }, + { "orm", "Oromo" }, + { "orn", "Orang Kanaq" }, + { "oro", "Orokolo" }, + { "orr", "Oruma" }, + { "ors", "Orang Seletar" }, + { "ort", "Adivasi Oriya" }, + { "oru", "Ormuri" }, + { "orv", "Old Russian" }, + { "orw", "Oro Win" }, + { "orx", "Oro" }, + { "ory", "Oriya (individual language)" }, + { "orz", "Ormu" }, + { "osa", "Osage" }, + { "osc", "Oscan" }, + { "osi", "Osing" }, + { "oso", "Ososo" }, + { "osp", "Old Spanish" }, + { "oss", "Ossetian" }, + { "ost", "Osatu" }, + { "osu", "Southern One" }, + { "osx", "Old Saxon" }, + { "ota", "Ottoman Turkish (1500-1928)" }, + { "otb", "Old Tibetan" }, + { "otd", "Ot Danum" }, + { "ote", "Mezquital Otomi" }, + { "oti", "Oti" }, + { "otk", "Old Turkish" }, + { "otl", "Tilapa Otomi" }, + { "otm", "Eastern Highland Otomi" }, + { "otn", "Tenango Otomi" }, + { "otq", "Querétaro Otomi" }, + { "otr", "Otoro" }, + { "ots", "Estado de México Otomi" }, + { "ott", "Temoaya Otomi" }, + { "otu", "Otuke" }, + { "otw", "Ottawa" }, + { "otx", "Texcatepec Otomi" }, + { "oty", "Old Tamil" }, + { "otz", "Ixtenco Otomi" }, + { "oua", "Tagargrent" }, + { "oub", "Glio-Oubi" }, + { "oue", "Oune" }, + { "oui", "Old Uighur" }, + { "oum", "Ouma" }, + { "oun", "!O!ung" }, + { "owi", "Owiniga" }, + { "owl", "Old Welsh" }, + { "oyb", "Oy" }, + { "oyd", "Oyda" }, + { "oym", "Wayampi" }, + { "oyy", "Oya'oya" }, + { "ozm", "Koonzime" }, + { "pab", "Parecís" }, + { "pac", "Pacoh" }, + { "pad", "Paumarí" }, + { "pae", "Pagibete" }, + { "paf", "Paranawát" }, + { "pag", "Pangasinan" }, + { "pah", "Tenharim" }, + { "pai", "Pe" }, + { "pak", "Parakanã" }, + { "pal", "Pahlavi" }, + { "pam", "Pampanga" }, + { "pan", "Panjabi" }, + { "pao", "Northern Paiute" }, + { "pap", "Papiamento" }, + { "paq", "Parya" }, + { "par", "Panamint" }, + { "pas", "Papasena" }, + { "pat", "Papitalai" }, + { "pau", "Palauan" }, + { "pav", "Pakaásnovos" }, + { "paw", "Pawnee" }, + { "pax", "Pankararé" }, + { "pay", "Pech" }, + { "paz", "Pankararú" }, + { "pbb", "Páez" }, + { "pbc", "Patamona" }, + { "pbe", "Mezontla Popoloca" }, + { "pbf", "Coyotepec Popoloca" }, + { "pbg", "Paraujano" }, + { "pbh", "E'ñapa Woromaipu" }, + { "pbi", "Parkwa" }, + { "pbl", "Mak (Nigeria)" }, + { "pbn", "Kpasam" }, + { "pbo", "Papel" }, + { "pbp", "Badyara" }, + { "pbr", "Pangwa" }, + { "pbs", "Central Pame" }, + { "pbt", "Southern Pashto" }, + { "pbu", "Northern Pashto" }, + { "pbv", "Pnar" }, + { "pby", "Pyu" }, + { "pca", "Santa Inés Ahuatempan Popoloca" }, + { "pcb", "Pear" }, + { "pcc", "Bouyei" }, + { "pcd", "Picard" }, + { "pce", "Ruching Palaung" }, + { "pcf", "Paliyan" }, + { "pcg", "Paniya" }, + { "pch", "Pardhan" }, + { "pci", "Duruwa" }, + { "pcj", "Parenga" }, + { "pck", "Paite Chin" }, + { "pcl", "Pardhi" }, + { "pcm", "Nigerian Pidgin" }, + { "pcn", "Piti" }, + { "pcp", "Pacahuara" }, + { "pcw", "Pyapun" }, + { "pda", "Anam" }, + { "pdc", "Pennsylvania German" }, + { "pdi", "Pa Di" }, + { "pdn", "Podena" }, + { "pdo", "Padoe" }, + { "pdt", "Plautdietsch" }, + { "pdu", "Kayan" }, + { "pea", "Peranakan Indonesian" }, + { "peb", "Eastern Pomo" }, + { "ped", "Mala (Papua New Guinea)" }, + { "pee", "Taje" }, + { "pef", "Northeastern Pomo" }, + { "peg", "Pengo" }, + { "peh", "Bonan" }, + { "pei", "Chichimeca-Jonaz" }, + { "pej", "Northern Pomo" }, + { "pek", "Penchal" }, + { "pel", "Pekal" }, + { "pem", "Phende" }, + { "peo", "Old Persian (ca. 600-400 B.C.)" }, + { "pep", "Kunja" }, + { "peq", "Southern Pomo" }, + { "pes", "Iranian Persian" }, + { "pev", "Pémono" }, + { "pex", "Petats" }, + { "pey", "Petjo" }, + { "pez", "Eastern Penan" }, + { "pfa", "Pááfang" }, + { "pfe", "Peere" }, + { "pfl", "Pfaelzisch" }, + { "pga", "Sudanese Creole Arabic" }, + { "pgg", "Pangwali" }, + { "pgi", "Pagi" }, + { "pgk", "Rerep" }, + { "pgl", "Primitive Irish" }, + { "pgn", "Paelignian" }, + { "pgs", "Pangseng" }, + { "pgu", "Pagu" }, + { "pha", "Pa-Hng" }, + { "phd", "Phudagi" }, + { "phg", "Phuong" }, + { "phh", "Phukha" }, + { "phk", "Phake" }, + { "phl", "Phalura" }, + { "phm", "Phimbi" }, + { "phn", "Phoenician" }, + { "pho", "Phunoi" }, + { "phq", "Phana'" }, + { "phr", "Pahari-Potwari" }, + { "pht", "Phu Thai" }, + { "phu", "Phuan" }, + { "phv", "Pahlavani" }, + { "phw", "Phangduwali" }, + { "pia", "Pima Bajo" }, + { "pib", "Yine" }, + { "pic", "Pinji" }, + { "pid", "Piaroa" }, + { "pie", "Piro" }, + { "pif", "Pingelapese" }, + { "pig", "Pisabo" }, + { "pih", "Pitcairn-Norfolk" }, + { "pii", "Pini" }, + { "pij", "Pijao" }, + { "pil", "Yom" }, + { "pim", "Powhatan" }, + { "pin", "Piame" }, + { "pio", "Piapoco" }, + { "pip", "Pero" }, + { "pir", "Piratapuyo" }, + { "pis", "Pijin" }, + { "pit", "Pitta Pitta" }, + { "piu", "Pintupi-Luritja" }, + { "piv", "Pileni" }, + { "piw", "Pimbwe" }, + { "pix", "Piu" }, + { "piy", "Piya-Kwonci" }, + { "piz", "Pije" }, + { "pjt", "Pitjantjatjara" }, + { "pka", "Ardhamāgadhī Prākrit" }, + { "pkb", "Pokomo" }, + { "pkc", "Paekche" }, + { "pkg", "Pak-Tong" }, + { "pkh", "Pankhu" }, + { "pkn", "Pakanha" }, + { "pko", "Pökoot" }, + { "pkp", "Pukapuka" }, + { "pkr", "Attapady Kurumba" }, + { "pks", "Pakistan Sign Language" }, + { "pkt", "Maleng" }, + { "pku", "Paku" }, + { "pla", "Miani" }, + { "plb", "Polonombauk" }, + { "plc", "Central Palawano" }, + { "pld", "Polari" }, + { "ple", "Palu'e" }, + { "plg", "Pilagá" }, + { "plh", "Paulohi" }, + { "pli", "Pali" }, + { "plj", "Polci" }, + { "plk", "Kohistani Shina" }, + { "pll", "Shwe Palaung" }, + { "pln", "Palenquero" }, + { "plo", "Oluta Popoluca" }, + { "plp", "Palpa" }, + { "plq", "Palaic" }, + { "plr", "Palaka Senoufo" }, + { "pls", "San Marcos Tlalcoyalco Popoloca" }, + { "plt", "Plateau Malagasy" }, + { "plu", "Palikúr" }, + { "plv", "Southwest Palawano" }, + { "plw", "Brooke's Point Palawano" }, + { "ply", "Bolyu" }, + { "plz", "Paluan" }, + { "pma", "Paama" }, + { "pmb", "Pambia" }, + { "pmc", "Palumata" }, + { "pmd", "Pallanganmiddang" }, + { "pme", "Pwaamei" }, + { "pmf", "Pamona" }, + { "pmh", "Māhārāṣṭri Prākrit" }, + { "pmi", "Northern Pumi" }, + { "pmj", "Southern Pumi" }, + { "pmk", "Pamlico" }, + { "pml", "Lingua Franca" }, + { "pmm", "Pomo" }, + { "pmn", "Pam" }, + { "pmo", "Pom" }, + { "pmq", "Northern Pame" }, + { "pmr", "Paynamar" }, + { "pms", "Piemontese" }, + { "pmt", "Tuamotuan" }, + { "pmu", "Mirpur Panjabi" }, + { "pmw", "Plains Miwok" }, + { "pmx", "Poumei Naga" }, + { "pmy", "Papuan Malay" }, + { "pmz", "Southern Pame" }, + { "pna", "Punan Bah-Biau" }, + { "pnb", "Western Panjabi" }, + { "pnc", "Pannei" }, + { "pne", "Western Penan" }, + { "png", "Pongu" }, + { "pnh", "Penrhyn" }, + { "pni", "Aoheng" }, + { "pnj", "Pinjarup" }, + { "pnk", "Paunaka" }, + { "pnl", "Paleni" }, + { "pnm", "Punan Batu 1" }, + { "pnn", "Pinai-Hagahai" }, + { "pno", "Panobo" }, + { "pnp", "Pancana" }, + { "pnq", "Pana (Burkina Faso)" }, + { "pnr", "Panim" }, + { "pns", "Ponosakan" }, + { "pnt", "Pontic" }, + { "pnu", "Jiongnai Bunu" }, + { "pnv", "Pinigura" }, + { "pnw", "Panytyima" }, + { "pnx", "Phong-Kniang" }, + { "pny", "Pinyin" }, + { "pnz", "Pana (Central African Republic)" }, + { "poc", "Poqomam" }, + { "pod", "Ponares" }, + { "poe", "San Juan Atzingo Popoloca" }, + { "pof", "Poke" }, + { "pog", "Potiguára" }, + { "poh", "Poqomchi'" }, + { "poi", "Highland Popoluca" }, + { "pok", "Pokangá" }, + { "pol", "Polish" }, + { "pom", "Southeastern Pomo" }, + { "pon", "Pohnpeian" }, + { "poo", "Central Pomo" }, + { "pop", "Pwapwâ" }, + { "poq", "Texistepec Popoluca" }, + { "por", "Portuguese" }, + { "pos", "Sayula Popoluca" }, + { "pot", "Potawatomi" }, + { "pov", "Upper Guinea Crioulo" }, + { "pow", "San Felipe Otlaltepec Popoloca" }, + { "pox", "Polabian" }, + { "poy", "Pogolo" }, + { "ppa", "Pao" }, + { "ppe", "Papi" }, + { "ppi", "Paipai" }, + { "ppk", "Uma" }, + { "ppl", "Pipil" }, + { "ppm", "Papuma" }, + { "ppn", "Papapana" }, + { "ppo", "Folopa" }, + { "ppp", "Pelende" }, + { "ppq", "Pei" }, + { "pps", "San Luís Temalacayuca Popoloca" }, + { "ppt", "Pare" }, + { "ppu", "Papora" }, + { "pqa", "Pa'a" }, + { "pqm", "Malecite-Passamaquoddy" }, + { "prb", "Lua'" }, + { "prc", "Parachi" }, + { "prd", "Parsi-Dari" }, + { "pre", "Principense" }, + { "prf", "Paranan" }, + { "prg", "Prussian" }, + { "prh", "Porohanon" }, + { "pri", "Paicî" }, + { "prk", "Parauk" }, + { "prl", "Peruvian Sign Language" }, + { "prm", "Kibiri" }, + { "prn", "Prasuni" }, + { "pro", "Old Provençal (to 1500)" }, + { "prp", "Parsi" }, + { "prq", "Ashéninka Perené" }, + { "prr", "Puri" }, + { "prs", "Dari" }, + { "prt", "Phai" }, + { "pru", "Puragi" }, + { "prw", "Parawen" }, + { "prx", "Purik" }, + { "pry", "Pray 3" }, + { "prz", "Providencia Sign Language" }, + { "psa", "Asue Awyu" }, + { "psc", "Persian Sign Language" }, + { "psd", "Plains Indian Sign Language" }, + { "pse", "Central Malay" }, + { "psg", "Penang Sign Language" }, + { "psh", "Southwest Pashayi" }, + { "psi", "Southeast Pashayi" }, + { "psl", "Puerto Rican Sign Language" }, + { "psm", "Pauserna" }, + { "psn", "Panasuan" }, + { "pso", "Polish Sign Language" }, + { "psp", "Philippine Sign Language" }, + { "psq", "Pasi" }, + { "psr", "Portuguese Sign Language" }, + { "pss", "Kaulong" }, + { "pst", "Central Pashto" }, + { "psu", "Sauraseni Prākrit" }, + { "psw", "Port Sandwich" }, + { "psy", "Piscataway" }, + { "pta", "Pai Tavytera" }, + { "pth", "Pataxó Hã-Ha-Hãe" }, + { "pti", "Pintiini" }, + { "ptn", "Patani" }, + { "pto", "Zo'é" }, + { "ptp", "Patep" }, + { "ptr", "Piamatsina" }, + { "ptt", "Enrekang" }, + { "ptu", "Bambam" }, + { "ptv", "Port Vato" }, + { "ptw", "Pentlatch" }, + { "pty", "Pathiya" }, + { "pua", "Western Highland Purepecha" }, + { "pub", "Purum" }, + { "puc", "Punan Merap" }, + { "pud", "Punan Aput" }, + { "pue", "Puelche" }, + { "puf", "Punan Merah" }, + { "pug", "Phuie" }, + { "pui", "Puinave" }, + { "puj", "Punan Tubu" }, + { "puk", "Pu Ko" }, + { "pum", "Puma" }, + { "puo", "Puoc" }, + { "pup", "Pulabu" }, + { "puq", "Puquina" }, + { "pur", "Puruborá" }, + { "pus", "Pushto" }, + { "put", "Putoh" }, + { "puu", "Punu" }, + { "puw", "Puluwatese" }, + { "pux", "Puare" }, + { "puy", "Purisimeño" }, + { "puz", "Purum Naga" }, + { "pwa", "Pawaia" }, + { "pwb", "Panawa" }, + { "pwg", "Gapapaiwa" }, + { "pwi", "Patwin" }, + { "pwm", "Molbog" }, + { "pwn", "Paiwan" }, + { "pwo", "Pwo Western Karen" }, + { "pwr", "Powari" }, + { "pww", "Pwo Northern Karen" }, + { "pxm", "Quetzaltepec Mixe" }, + { "pye", "Pye Krumen" }, + { "pym", "Fyam" }, + { "pyn", "Poyanáwa" }, + { "pys", "Paraguayan Sign Language" }, + { "pyu", "Puyuma" }, + { "pyx", "Pyu (Myanmar)" }, + { "pyy", "Pyen" }, + { "pzn", "Para Naga" }, + { "qaa", "Reserved for local use" }, + { "qab", "Reserved for local use" }, + { "qac", "Reserved for local use" }, + { "qad", "Reserved for local use" }, + { "qae", "Reserved for local use" }, + { "qaf", "Reserved for local use" }, + { "qag", "Reserved for local use" }, + { "qah", "Reserved for local use" }, + { "qai", "Reserved for local use" }, + { "qaj", "Reserved for local use" }, + { "qak", "Reserved for local use" }, + { "qal", "Reserved for local use" }, + { "qam", "Reserved for local use" }, + { "qan", "Reserved for local use" }, + { "qao", "Reserved for local use" }, + { "qap", "Reserved for local use" }, + { "qaq", "Reserved for local use" }, + { "qar", "Reserved for local use" }, + { "qas", "Reserved for local use" }, + { "qat", "Reserved for local use" }, + { "qau", "Reserved for local use" }, + { "qav", "Reserved for local use" }, + { "qaw", "Reserved for local use" }, + { "qax", "Reserved for local use" }, + { "qay", "Reserved for local use" }, + { "qaz", "Reserved for local use" }, + { "qba", "Reserved for local use" }, + { "qbb", "Reserved for local use" }, + { "qbc", "Reserved for local use" }, + { "qbd", "Reserved for local use" }, + { "qbe", "Reserved for local use" }, + { "qbf", "Reserved for local use" }, + { "qbg", "Reserved for local use" }, + { "qbh", "Reserved for local use" }, + { "qbi", "Reserved for local use" }, + { "qbj", "Reserved for local use" }, + { "qbk", "Reserved for local use" }, + { "qbl", "Reserved for local use" }, + { "qbm", "Reserved for local use" }, + { "qbn", "Reserved for local use" }, + { "qbo", "Reserved for local use" }, + { "qbp", "Reserved for local use" }, + { "qbq", "Reserved for local use" }, + { "qbr", "Reserved for local use" }, + { "qbs", "Reserved for local use" }, + { "qbt", "Reserved for local use" }, + { "qbu", "Reserved for local use" }, + { "qbv", "Reserved for local use" }, + { "qbw", "Reserved for local use" }, + { "qbx", "Reserved for local use" }, + { "qby", "Reserved for local use" }, + { "qbz", "Reserved for local use" }, + { "qca", "Reserved for local use" }, + { "qcb", "Reserved for local use" }, + { "qcc", "Reserved for local use" }, + { "qcd", "Reserved for local use" }, + { "qce", "Reserved for local use" }, + { "qcf", "Reserved for local use" }, + { "qcg", "Reserved for local use" }, + { "qch", "Reserved for local use" }, + { "qci", "Reserved for local use" }, + { "qcj", "Reserved for local use" }, + { "qck", "Reserved for local use" }, + { "qcl", "Reserved for local use" }, + { "qcm", "Reserved for local use" }, + { "qcn", "Reserved for local use" }, + { "qco", "Reserved for local use" }, + { "qcp", "Reserved for local use" }, + { "qcq", "Reserved for local use" }, + { "qcr", "Reserved for local use" }, + { "qcs", "Reserved for local use" }, + { "qct", "Reserved for local use" }, + { "qcu", "Reserved for local use" }, + { "qcv", "Reserved for local use" }, + { "qcw", "Reserved for local use" }, + { "qcx", "Reserved for local use" }, + { "qcy", "Reserved for local use" }, + { "qcz", "Reserved for local use" }, + { "qda", "Reserved for local use" }, + { "qdb", "Reserved for local use" }, + { "qdc", "Reserved for local use" }, + { "qdd", "Reserved for local use" }, + { "qde", "Reserved for local use" }, + { "qdf", "Reserved for local use" }, + { "qdg", "Reserved for local use" }, + { "qdh", "Reserved for local use" }, + { "qdi", "Reserved for local use" }, + { "qdj", "Reserved for local use" }, + { "qdk", "Reserved for local use" }, + { "qdl", "Reserved for local use" }, + { "qdm", "Reserved for local use" }, + { "qdn", "Reserved for local use" }, + { "qdo", "Reserved for local use" }, + { "qdp", "Reserved for local use" }, + { "qdq", "Reserved for local use" }, + { "qdr", "Reserved for local use" }, + { "qds", "Reserved for local use" }, + { "qdt", "Reserved for local use" }, + { "qdu", "Reserved for local use" }, + { "qdv", "Reserved for local use" }, + { "qdw", "Reserved for local use" }, + { "qdx", "Reserved for local use" }, + { "qdy", "Reserved for local use" }, + { "qdz", "Reserved for local use" }, + { "qea", "Reserved for local use" }, + { "qeb", "Reserved for local use" }, + { "qec", "Reserved for local use" }, + { "qed", "Reserved for local use" }, + { "qee", "Reserved for local use" }, + { "qef", "Reserved for local use" }, + { "qeg", "Reserved for local use" }, + { "qeh", "Reserved for local use" }, + { "qei", "Reserved for local use" }, + { "qej", "Reserved for local use" }, + { "qek", "Reserved for local use" }, + { "qel", "Reserved for local use" }, + { "qem", "Reserved for local use" }, + { "qen", "Reserved for local use" }, + { "qeo", "Reserved for local use" }, + { "qep", "Reserved for local use" }, + { "qeq", "Reserved for local use" }, + { "qer", "Reserved for local use" }, + { "qes", "Reserved for local use" }, + { "qet", "Reserved for local use" }, + { "qeu", "Reserved for local use" }, + { "qev", "Reserved for local use" }, + { "qew", "Reserved for local use" }, + { "qex", "Reserved for local use" }, + { "qey", "Reserved for local use" }, + { "qez", "Reserved for local use" }, + { "qfa", "Reserved for local use" }, + { "qfb", "Reserved for local use" }, + { "qfc", "Reserved for local use" }, + { "qfd", "Reserved for local use" }, + { "qfe", "Reserved for local use" }, + { "qff", "Reserved for local use" }, + { "qfg", "Reserved for local use" }, + { "qfh", "Reserved for local use" }, + { "qfi", "Reserved for local use" }, + { "qfj", "Reserved for local use" }, + { "qfk", "Reserved for local use" }, + { "qfl", "Reserved for local use" }, + { "qfm", "Reserved for local use" }, + { "qfn", "Reserved for local use" }, + { "qfo", "Reserved for local use" }, + { "qfp", "Reserved for local use" }, + { "qfq", "Reserved for local use" }, + { "qfr", "Reserved for local use" }, + { "qfs", "Reserved for local use" }, + { "qft", "Reserved for local use" }, + { "qfu", "Reserved for local use" }, + { "qfv", "Reserved for local use" }, + { "qfw", "Reserved for local use" }, + { "qfx", "Reserved for local use" }, + { "qfy", "Reserved for local use" }, + { "qfz", "Reserved for local use" }, + { "qga", "Reserved for local use" }, + { "qgb", "Reserved for local use" }, + { "qgc", "Reserved for local use" }, + { "qgd", "Reserved for local use" }, + { "qge", "Reserved for local use" }, + { "qgf", "Reserved for local use" }, + { "qgg", "Reserved for local use" }, + { "qgh", "Reserved for local use" }, + { "qgi", "Reserved for local use" }, + { "qgj", "Reserved for local use" }, + { "qgk", "Reserved for local use" }, + { "qgl", "Reserved for local use" }, + { "qgm", "Reserved for local use" }, + { "qgn", "Reserved for local use" }, + { "qgo", "Reserved for local use" }, + { "qgp", "Reserved for local use" }, + { "qgq", "Reserved for local use" }, + { "qgr", "Reserved for local use" }, + { "qgs", "Reserved for local use" }, + { "qgt", "Reserved for local use" }, + { "qgu", "Reserved for local use" }, + { "qgv", "Reserved for local use" }, + { "qgw", "Reserved for local use" }, + { "qgx", "Reserved for local use" }, + { "qgy", "Reserved for local use" }, + { "qgz", "Reserved for local use" }, + { "qha", "Reserved for local use" }, + { "qhb", "Reserved for local use" }, + { "qhc", "Reserved for local use" }, + { "qhd", "Reserved for local use" }, + { "qhe", "Reserved for local use" }, + { "qhf", "Reserved for local use" }, + { "qhg", "Reserved for local use" }, + { "qhh", "Reserved for local use" }, + { "qhi", "Reserved for local use" }, + { "qhj", "Reserved for local use" }, + { "qhk", "Reserved for local use" }, + { "qhl", "Reserved for local use" }, + { "qhm", "Reserved for local use" }, + { "qhn", "Reserved for local use" }, + { "qho", "Reserved for local use" }, + { "qhp", "Reserved for local use" }, + { "qhq", "Reserved for local use" }, + { "qhr", "Reserved for local use" }, + { "qhs", "Reserved for local use" }, + { "qht", "Reserved for local use" }, + { "qhu", "Reserved for local use" }, + { "qhv", "Reserved for local use" }, + { "qhw", "Reserved for local use" }, + { "qhx", "Reserved for local use" }, + { "qhy", "Reserved for local use" }, + { "qhz", "Reserved for local use" }, + { "qia", "Reserved for local use" }, + { "qib", "Reserved for local use" }, + { "qic", "Reserved for local use" }, + { "qid", "Reserved for local use" }, + { "qie", "Reserved for local use" }, + { "qif", "Reserved for local use" }, + { "qig", "Reserved for local use" }, + { "qih", "Reserved for local use" }, + { "qii", "Reserved for local use" }, + { "qij", "Reserved for local use" }, + { "qik", "Reserved for local use" }, + { "qil", "Reserved for local use" }, + { "qim", "Reserved for local use" }, + { "qin", "Reserved for local use" }, + { "qio", "Reserved for local use" }, + { "qip", "Reserved for local use" }, + { "qiq", "Reserved for local use" }, + { "qir", "Reserved for local use" }, + { "qis", "Reserved for local use" }, + { "qit", "Reserved for local use" }, + { "qiu", "Reserved for local use" }, + { "qiv", "Reserved for local use" }, + { "qiw", "Reserved for local use" }, + { "qix", "Reserved for local use" }, + { "qiy", "Reserved for local use" }, + { "qiz", "Reserved for local use" }, + { "qja", "Reserved for local use" }, + { "qjb", "Reserved for local use" }, + { "qjc", "Reserved for local use" }, + { "qjd", "Reserved for local use" }, + { "qje", "Reserved for local use" }, + { "qjf", "Reserved for local use" }, + { "qjg", "Reserved for local use" }, + { "qjh", "Reserved for local use" }, + { "qji", "Reserved for local use" }, + { "qjj", "Reserved for local use" }, + { "qjk", "Reserved for local use" }, + { "qjl", "Reserved for local use" }, + { "qjm", "Reserved for local use" }, + { "qjn", "Reserved for local use" }, + { "qjo", "Reserved for local use" }, + { "qjp", "Reserved for local use" }, + { "qjq", "Reserved for local use" }, + { "qjr", "Reserved for local use" }, + { "qjs", "Reserved for local use" }, + { "qjt", "Reserved for local use" }, + { "qju", "Reserved for local use" }, + { "qjv", "Reserved for local use" }, + { "qjw", "Reserved for local use" }, + { "qjx", "Reserved for local use" }, + { "qjy", "Reserved for local use" }, + { "qjz", "Reserved for local use" }, + { "qka", "Reserved for local use" }, + { "qkb", "Reserved for local use" }, + { "qkc", "Reserved for local use" }, + { "qkd", "Reserved for local use" }, + { "qke", "Reserved for local use" }, + { "qkf", "Reserved for local use" }, + { "qkg", "Reserved for local use" }, + { "qkh", "Reserved for local use" }, + { "qki", "Reserved for local use" }, + { "qkj", "Reserved for local use" }, + { "qkk", "Reserved for local use" }, + { "qkl", "Reserved for local use" }, + { "qkm", "Reserved for local use" }, + { "qkn", "Reserved for local use" }, + { "qko", "Reserved for local use" }, + { "qkp", "Reserved for local use" }, + { "qkq", "Reserved for local use" }, + { "qkr", "Reserved for local use" }, + { "qks", "Reserved for local use" }, + { "qkt", "Reserved for local use" }, + { "qku", "Reserved for local use" }, + { "qkv", "Reserved for local use" }, + { "qkw", "Reserved for local use" }, + { "qkx", "Reserved for local use" }, + { "qky", "Reserved for local use" }, + { "qkz", "Reserved for local use" }, + { "qla", "Reserved for local use" }, + { "qlb", "Reserved for local use" }, + { "qlc", "Reserved for local use" }, + { "qld", "Reserved for local use" }, + { "qle", "Reserved for local use" }, + { "qlf", "Reserved for local use" }, + { "qlg", "Reserved for local use" }, + { "qlh", "Reserved for local use" }, + { "qli", "Reserved for local use" }, + { "qlj", "Reserved for local use" }, + { "qlk", "Reserved for local use" }, + { "qll", "Reserved for local use" }, + { "qlm", "Reserved for local use" }, + { "qln", "Reserved for local use" }, + { "qlo", "Reserved for local use" }, + { "qlp", "Reserved for local use" }, + { "qlq", "Reserved for local use" }, + { "qlr", "Reserved for local use" }, + { "qls", "Reserved for local use" }, + { "qlt", "Reserved for local use" }, + { "qlu", "Reserved for local use" }, + { "qlv", "Reserved for local use" }, + { "qlw", "Reserved for local use" }, + { "qlx", "Reserved for local use" }, + { "qly", "Reserved for local use" }, + { "qlz", "Reserved for local use" }, + { "qma", "Reserved for local use" }, + { "qmb", "Reserved for local use" }, + { "qmc", "Reserved for local use" }, + { "qmd", "Reserved for local use" }, + { "qme", "Reserved for local use" }, + { "qmf", "Reserved for local use" }, + { "qmg", "Reserved for local use" }, + { "qmh", "Reserved for local use" }, + { "qmi", "Reserved for local use" }, + { "qmj", "Reserved for local use" }, + { "qmk", "Reserved for local use" }, + { "qml", "Reserved for local use" }, + { "qmm", "Reserved for local use" }, + { "qmn", "Reserved for local use" }, + { "qmo", "Reserved for local use" }, + { "qmp", "Reserved for local use" }, + { "qmq", "Reserved for local use" }, + { "qmr", "Reserved for local use" }, + { "qms", "Reserved for local use" }, + { "qmt", "Reserved for local use" }, + { "qmu", "Reserved for local use" }, + { "qmv", "Reserved for local use" }, + { "qmw", "Reserved for local use" }, + { "qmx", "Reserved for local use" }, + { "qmy", "Reserved for local use" }, + { "qmz", "Reserved for local use" }, + { "qna", "Reserved for local use" }, + { "qnb", "Reserved for local use" }, + { "qnc", "Reserved for local use" }, + { "qnd", "Reserved for local use" }, + { "qne", "Reserved for local use" }, + { "qnf", "Reserved for local use" }, + { "qng", "Reserved for local use" }, + { "qnh", "Reserved for local use" }, + { "qni", "Reserved for local use" }, + { "qnj", "Reserved for local use" }, + { "qnk", "Reserved for local use" }, + { "qnl", "Reserved for local use" }, + { "qnm", "Reserved for local use" }, + { "qnn", "Reserved for local use" }, + { "qno", "Reserved for local use" }, + { "qnp", "Reserved for local use" }, + { "qnq", "Reserved for local use" }, + { "qnr", "Reserved for local use" }, + { "qns", "Reserved for local use" }, + { "qnt", "Reserved for local use" }, + { "qnu", "Reserved for local use" }, + { "qnv", "Reserved for local use" }, + { "qnw", "Reserved for local use" }, + { "qnx", "Reserved for local use" }, + { "qny", "Reserved for local use" }, + { "qnz", "Reserved for local use" }, + { "qoa", "Reserved for local use" }, + { "qob", "Reserved for local use" }, + { "qoc", "Reserved for local use" }, + { "qod", "Reserved for local use" }, + { "qoe", "Reserved for local use" }, + { "qof", "Reserved for local use" }, + { "qog", "Reserved for local use" }, + { "qoh", "Reserved for local use" }, + { "qoi", "Reserved for local use" }, + { "qoj", "Reserved for local use" }, + { "qok", "Reserved for local use" }, + { "qol", "Reserved for local use" }, + { "qom", "Reserved for local use" }, + { "qon", "Reserved for local use" }, + { "qoo", "Reserved for local use" }, + { "qop", "Reserved for local use" }, + { "qoq", "Reserved for local use" }, + { "qor", "Reserved for local use" }, + { "qos", "Reserved for local use" }, + { "qot", "Reserved for local use" }, + { "qou", "Reserved for local use" }, + { "qov", "Reserved for local use" }, + { "qow", "Reserved for local use" }, + { "qox", "Reserved for local use" }, + { "qoy", "Reserved for local use" }, + { "qoz", "Reserved for local use" }, + { "qpa", "Reserved for local use" }, + { "qpb", "Reserved for local use" }, + { "qpc", "Reserved for local use" }, + { "qpd", "Reserved for local use" }, + { "qpe", "Reserved for local use" }, + { "qpf", "Reserved for local use" }, + { "qpg", "Reserved for local use" }, + { "qph", "Reserved for local use" }, + { "qpi", "Reserved for local use" }, + { "qpj", "Reserved for local use" }, + { "qpk", "Reserved for local use" }, + { "qpl", "Reserved for local use" }, + { "qpm", "Reserved for local use" }, + { "qpn", "Reserved for local use" }, + { "qpo", "Reserved for local use" }, + { "qpp", "Reserved for local use" }, + { "qpq", "Reserved for local use" }, + { "qpr", "Reserved for local use" }, + { "qps", "Reserved for local use" }, + { "qpt", "Reserved for local use" }, + { "qpu", "Reserved for local use" }, + { "qpv", "Reserved for local use" }, + { "qpw", "Reserved for local use" }, + { "qpx", "Reserved for local use" }, + { "qpy", "Reserved for local use" }, + { "qpz", "Reserved for local use" }, + { "qqa", "Reserved for local use" }, + { "qqb", "Reserved for local use" }, + { "qqc", "Reserved for local use" }, + { "qqd", "Reserved for local use" }, + { "qqe", "Reserved for local use" }, + { "qqf", "Reserved for local use" }, + { "qqg", "Reserved for local use" }, + { "qqh", "Reserved for local use" }, + { "qqi", "Reserved for local use" }, + { "qqj", "Reserved for local use" }, + { "qqk", "Reserved for local use" }, + { "qql", "Reserved for local use" }, + { "qqm", "Reserved for local use" }, + { "qqn", "Reserved for local use" }, + { "qqo", "Reserved for local use" }, + { "qqp", "Reserved for local use" }, + { "qqq", "Reserved for local use" }, + { "qqr", "Reserved for local use" }, + { "qqs", "Reserved for local use" }, + { "qqt", "Reserved for local use" }, + { "qqu", "Reserved for local use" }, + { "qqv", "Reserved for local use" }, + { "qqw", "Reserved for local use" }, + { "qqx", "Reserved for local use" }, + { "qqy", "Reserved for local use" }, + { "qqz", "Reserved for local use" }, + { "qra", "Reserved for local use" }, + { "qrb", "Reserved for local use" }, + { "qrc", "Reserved for local use" }, + { "qrd", "Reserved for local use" }, + { "qre", "Reserved for local use" }, + { "qrf", "Reserved for local use" }, + { "qrg", "Reserved for local use" }, + { "qrh", "Reserved for local use" }, + { "qri", "Reserved for local use" }, + { "qrj", "Reserved for local use" }, + { "qrk", "Reserved for local use" }, + { "qrl", "Reserved for local use" }, + { "qrm", "Reserved for local use" }, + { "qrn", "Reserved for local use" }, + { "qro", "Reserved for local use" }, + { "qrp", "Reserved for local use" }, + { "qrq", "Reserved for local use" }, + { "qrr", "Reserved for local use" }, + { "qrs", "Reserved for local use" }, + { "qrt", "Reserved for local use" }, + { "qru", "Reserved for local use" }, + { "qrv", "Reserved for local use" }, + { "qrw", "Reserved for local use" }, + { "qrx", "Reserved for local use" }, + { "qry", "Reserved for local use" }, + { "qrz", "Reserved for local use" }, + { "qsa", "Reserved for local use" }, + { "qsb", "Reserved for local use" }, + { "qsc", "Reserved for local use" }, + { "qsd", "Reserved for local use" }, + { "qse", "Reserved for local use" }, + { "qsf", "Reserved for local use" }, + { "qsg", "Reserved for local use" }, + { "qsh", "Reserved for local use" }, + { "qsi", "Reserved for local use" }, + { "qsj", "Reserved for local use" }, + { "qsk", "Reserved for local use" }, + { "qsl", "Reserved for local use" }, + { "qsm", "Reserved for local use" }, + { "qsn", "Reserved for local use" }, + { "qso", "Reserved for local use" }, + { "qsp", "Reserved for local use" }, + { "qsq", "Reserved for local use" }, + { "qsr", "Reserved for local use" }, + { "qss", "Reserved for local use" }, + { "qst", "Reserved for local use" }, + { "qsu", "Reserved for local use" }, + { "qsv", "Reserved for local use" }, + { "qsw", "Reserved for local use" }, + { "qsx", "Reserved for local use" }, + { "qsy", "Reserved for local use" }, + { "qsz", "Reserved for local use" }, + { "qta", "Reserved for local use" }, + { "qtb", "Reserved for local use" }, + { "qtc", "Reserved for local use" }, + { "qtd", "Reserved for local use" }, + { "qte", "Reserved for local use" }, + { "qtf", "Reserved for local use" }, + { "qtg", "Reserved for local use" }, + { "qth", "Reserved for local use" }, + { "qti", "Reserved for local use" }, + { "qtj", "Reserved for local use" }, + { "qtk", "Reserved for local use" }, + { "qtl", "Reserved for local use" }, + { "qtm", "Reserved for local use" }, + { "qtn", "Reserved for local use" }, + { "qto", "Reserved for local use" }, + { "qtp", "Reserved for local use" }, + { "qtq", "Reserved for local use" }, + { "qtr", "Reserved for local use" }, + { "qts", "Reserved for local use" }, + { "qtt", "Reserved for local use" }, + { "qtu", "Reserved for local use" }, + { "qtv", "Reserved for local use" }, + { "qtw", "Reserved for local use" }, + { "qtx", "Reserved for local use" }, + { "qty", "Reserved for local use" }, + { "qtz", "Reserved for local use" }, + { "qua", "Quapaw" }, + { "qub", "Huallaga Huánuco Quechua" }, + { "quc", "K'iche'" }, + { "qud", "Calderón Highland Quichua" }, + { "que", "Quechua" }, + { "quf", "Lambayeque Quechua" }, + { "qug", "Chimborazo Highland Quichua" }, + { "quh", "South Bolivian Quechua" }, + { "qui", "Quileute" }, + { "quk", "Chachapoyas Quechua" }, + { "qul", "North Bolivian Quechua" }, + { "qum", "Sipacapense" }, + { "qun", "Quinault" }, + { "qup", "Southern Pastaza Quechua" }, + { "quq", "Quinqui" }, + { "qur", "Yanahuanca Pasco Quechua" }, + { "qus", "Santiago del Estero Quichua" }, + { "quv", "Sacapulteco" }, + { "quw", "Tena Lowland Quichua" }, + { "qux", "Yauyos Quechua" }, + { "quy", "Ayacucho Quechua" }, + { "quz", "Cusco Quechua" }, + { "qva", "Ambo-Pasco Quechua" }, + { "qvc", "Cajamarca Quechua" }, + { "qve", "Eastern Apurímac Quechua" }, + { "qvh", "Huamalíes-Dos de Mayo Huánuco Quechua" }, + { "qvi", "Imbabura Highland Quichua" }, + { "qvj", "Loja Highland Quichua" }, + { "qvl", "Cajatambo North Lima Quechua" }, + { "qvm", "Margos-Yarowilca-Lauricocha Quechua" }, + { "qvn", "North Junín Quechua" }, + { "qvo", "Napo Lowland Quechua" }, + { "qvp", "Pacaraos Quechua" }, + { "qvs", "San Martín Quechua" }, + { "qvw", "Huaylla Wanca Quechua" }, + { "qvy", "Queyu" }, + { "qvz", "Northern Pastaza Quichua" }, + { "qwa", "Corongo Ancash Quechua" }, + { "qwc", "Classical Quechua" }, + { "qwh", "Huaylas Ancash Quechua" }, + { "qwm", "Kuman (Russia)" }, + { "qws", "Sihuas Ancash Quechua" }, + { "qwt", "Kwalhioqua-Tlatskanai" }, + { "qxa", "Chiquián Ancash Quechua" }, + { "qxc", "Chincha Quechua" }, + { "qxh", "Panao Huánuco Quechua" }, + { "qxl", "Salasaca Highland Quichua" }, + { "qxn", "Northern Conchucos Ancash Quechua" }, + { "qxo", "Southern Conchucos Ancash Quechua" }, + { "qxp", "Puno Quechua" }, + { "qxq", "Qashqa'i" }, + { "qxr", "Cañar Highland Quichua" }, + { "qxs", "Southern Qiang" }, + { "qxt", "Santa Ana de Tusi Pasco Quechua" }, + { "qxu", "Arequipa-La Unión Quechua" }, + { "qxw", "Jauja Wanca Quechua" }, + { "qya", "Quenya" }, + { "qyp", "Quiripi" }, + { "raa", "Dungmali" }, + { "rab", "Camling" }, + { "rac", "Rasawa" }, + { "rad", "Rade" }, + { "raf", "Western Meohang" }, + { "rag", "Logooli" }, + { "rah", "Rabha" }, + { "rai", "Ramoaaina" }, + { "raj", "Rajasthani" }, + { "rak", "Tulu-Bohuai" }, + { "ral", "Ralte" }, + { "ram", "Canela" }, + { "ran", "Riantana" }, + { "rao", "Rao" }, + { "rap", "Rapanui" }, + { "raq", "Saam" }, + { "rar", "Rarotongan" }, + { "ras", "Tegali" }, + { "rat", "Razajerdi" }, + { "rau", "Raute" }, + { "rav", "Sampang" }, + { "raw", "Rawang" }, + { "rax", "Rang" }, + { "ray", "Rapa" }, + { "raz", "Rahambuu" }, + { "rbb", "Rumai Palaung" }, + { "rbk", "Northern Bontok" }, + { "rbl", "Miraya Bikol" }, + { "rbp", "Barababaraba" }, + { "rcf", "Réunion Creole French" }, + { "rdb", "Rudbari" }, + { "rea", "Rerau" }, + { "reb", "Rembong" }, + { "ree", "Rejang Kayan" }, + { "reg", "Kara (Tanzania)" }, + { "rei", "Reli" }, + { "rej", "Rejang" }, + { "rel", "Rendille" }, + { "rem", "Remo" }, + { "ren", "Rengao" }, + { "rer", "Rer Bare" }, + { "res", "Reshe" }, + { "ret", "Retta" }, + { "rey", "Reyesano" }, + { "rga", "Roria" }, + { "rge", "Romano-Greek" }, + { "rgk", "Rangkas" }, + { "rgn", "Romagnol" }, + { "rgr", "Resígaro" }, + { "rgs", "Southern Roglai" }, + { "rgu", "Ringgou" }, + { "rhg", "Rohingya" }, + { "rhp", "Yahang" }, + { "ria", "Riang (India)" }, + { "rie", "Rien" }, + { "rif", "Tarifit" }, + { "ril", "Riang (Myanmar)" }, + { "rim", "Nyaturu" }, + { "rin", "Nungu" }, + { "rir", "Ribun" }, + { "rit", "Ritarungo" }, + { "riu", "Riung" }, + { "rjg", "Rajong" }, + { "rji", "Raji" }, + { "rjs", "Rajbanshi" }, + { "rka", "Kraol" }, + { "rkb", "Rikbaktsa" }, + { "rkh", "Rakahanga-Manihiki" }, + { "rki", "Rakhine" }, + { "rkm", "Marka" }, + { "rkt", "Rangpuri" }, + { "rkw", "Arakwal" }, + { "rma", "Rama" }, + { "rmb", "Rembarunga" }, + { "rmc", "Carpathian Romani" }, + { "rmd", "Traveller Danish" }, + { "rme", "Angloromani" }, + { "rmf", "Kalo Finnish Romani" }, + { "rmg", "Traveller Norwegian" }, + { "rmh", "Murkim" }, + { "rmi", "Lomavren" }, + { "rmk", "Romkun" }, + { "rml", "Baltic Romani" }, + { "rmm", "Roma" }, + { "rmn", "Balkan Romani" }, + { "rmo", "Sinte Romani" }, + { "rmp", "Rempi" }, + { "rmq", "Caló" }, + { "rms", "Romanian Sign Language" }, + { "rmt", "Domari" }, + { "rmu", "Tavringer Romani" }, + { "rmv", "Romanova" }, + { "rmw", "Welsh Romani" }, + { "rmx", "Romam" }, + { "rmy", "Vlax Romani" }, + { "rmz", "Marma" }, + { "rna", "Runa" }, + { "rnd", "Ruund" }, + { "rng", "Ronga" }, + { "rnl", "Ranglong" }, + { "rnn", "Roon" }, + { "rnp", "Rongpo" }, + { "rnr", "Nari Nari" }, + { "rnw", "Rungwa" }, + { "rob", "Tae'" }, + { "roc", "Cacgia Roglai" }, + { "rod", "Rogo" }, + { "roe", "Ronji" }, + { "rof", "Rombo" }, + { "rog", "Northern Roglai" }, + { "roh", "Romansh" }, + { "rol", "Romblomanon" }, + { "rom", "Romany" }, + { "ron", "Romanian" }, + { "roo", "Rotokas" }, + { "rop", "Kriol" }, + { "ror", "Rongga" }, + { "rou", "Runga" }, + { "row", "Dela-Oenale" }, + { "rpn", "Repanbitip" }, + { "rpt", "Rapting" }, + { "rri", "Ririo" }, + { "rro", "Waima" }, + { "rrt", "Arritinngithigh" }, + { "rsb", "Romano-Serbian" }, + { "rsi", "Rennellese Sign Language" }, + { "rsl", "Russian Sign Language" }, + { "rtc", "Rungtu Chin" }, + { "rth", "Ratahan" }, + { "rtm", "Rotuman" }, + { "rtw", "Rathawi" }, + { "rub", "Gungu" }, + { "ruc", "Ruuli" }, + { "rue", "Rusyn" }, + { "ruf", "Luguru" }, + { "rug", "Roviana" }, + { "ruh", "Ruga" }, + { "rui", "Rufiji" }, + { "ruk", "Che" }, + { "run", "Rundi" }, + { "ruo", "Istro Romanian" }, + { "rup", "Macedo-Romanian" }, + { "ruq", "Megleno Romanian" }, + { "rus", "Russian" }, + { "rut", "Rutul" }, + { "ruu", "Lanas Lobu" }, + { "ruy", "Mala (Nigeria)" }, + { "ruz", "Ruma" }, + { "rwa", "Rawo" }, + { "rwk", "Rwa" }, + { "rwm", "Amba (Uganda)" }, + { "rwo", "Rawa" }, + { "rwr", "Marwari (India)" }, + { "rxd", "Ngardi" }, + { "rxw", "Karuwali" }, + { "ryn", "Northern Amami-Oshima" }, + { "rys", "Yaeyama" }, + { "ryu", "Central Okinawan" }, + { "saa", "Saba" }, + { "sab", "Buglere" }, + { "sac", "Meskwaki" }, + { "sad", "Sandawe" }, + { "sae", "Sabanê" }, + { "saf", "Safaliba" }, + { "sag", "Sango" }, + { "sah", "Yakut" }, + { "saj", "Sahu" }, + { "sak", "Sake" }, + { "sam", "Samaritan Aramaic" }, + { "san", "Sanskrit" }, + { "sao", "Sause" }, + { "sap", "Sanapaná" }, + { "saq", "Samburu" }, + { "sar", "Saraveca" }, + { "sas", "Sasak" }, + { "sat", "Santali" }, + { "sau", "Saleman" }, + { "sav", "Saafi-Saafi" }, + { "saw", "Sawi" }, + { "sax", "Sa" }, + { "say", "Saya" }, + { "saz", "Saurashtra" }, + { "sba", "Ngambay" }, + { "sbb", "Simbo" }, + { "sbc", "Kele (Papua New Guinea)" }, + { "sbd", "Southern Samo" }, + { "sbe", "Saliba" }, + { "sbf", "Shabo" }, + { "sbg", "Seget" }, + { "sbh", "Sori-Harengan" }, + { "sbi", "Seti" }, + { "sbj", "Surbakhal" }, + { "sbk", "Safwa" }, + { "sbl", "Botolan Sambal" }, + { "sbm", "Sagala" }, + { "sbn", "Sindhi Bhil" }, + { "sbo", "Sabüm" }, + { "sbp", "Sangu (Tanzania)" }, + { "sbq", "Sileibi" }, + { "sbr", "Sembakung Murut" }, + { "sbs", "Subiya" }, + { "sbt", "Kimki" }, + { "sbu", "Stod Bhoti" }, + { "sbv", "Sabine" }, + { "sbw", "Simba" }, + { "sbx", "Seberuang" }, + { "sby", "Soli" }, + { "sbz", "Sara Kaba" }, + { "scb", "Chut" }, + { "sce", "Dongxiang" }, + { "scf", "San Miguel Creole French" }, + { "scg", "Sanggau" }, + { "sch", "Sakachep" }, + { "sci", "Sri Lankan Creole Malay" }, + { "sck", "Sadri" }, + { "scl", "Shina" }, + { "scn", "Sicilian" }, + { "sco", "Scots" }, + { "scp", "Helambu Sherpa" }, + { "scq", "Sa'och" }, + { "scs", "North Slavey" }, + { "scu", "Shumcho" }, + { "scv", "Sheni" }, + { "scw", "Sha" }, + { "scx", "Sicel" }, + { "sda", "Toraja-Sa'dan" }, + { "sdb", "Shabak" }, + { "sdc", "Sassarese Sardinian" }, + { "sde", "Surubu" }, + { "sdf", "Sarli" }, + { "sdg", "Savi" }, + { "sdh", "Southern Kurdish" }, + { "sdj", "Suundi" }, + { "sdk", "Sos Kundi" }, + { "sdl", "Saudi Arabian Sign Language" }, + { "sdm", "Semandang" }, + { "sdn", "Gallurese Sardinian" }, + { "sdo", "Bukar-Sadung Bidayuh" }, + { "sdp", "Sherdukpen" }, + { "sdr", "Oraon Sadri" }, + { "sds", "Sened" }, + { "sdt", "Shuadit" }, + { "sdu", "Sarudu" }, + { "sdx", "Sibu Melanau" }, + { "sdz", "Sallands" }, + { "sea", "Semai" }, + { "seb", "Shempire Senoufo" }, + { "sec", "Sechelt" }, + { "sed", "Sedang" }, + { "see", "Seneca" }, + { "sef", "Cebaara Senoufo" }, + { "seg", "Segeju" }, + { "seh", "Sena" }, + { "sei", "Seri" }, + { "sej", "Sene" }, + { "sek", "Sekani" }, + { "sel", "Selkup" }, + { "sen", "Nanerigé Sénoufo" }, + { "seo", "Suarmin" }, + { "sep", "Sìcìté Sénoufo" }, + { "seq", "Senara Sénoufo" }, + { "ser", "Serrano" }, + { "ses", "Koyraboro Senni Songhai" }, + { "set", "Sentani" }, + { "seu", "Serui-Laut" }, + { "sev", "Nyarafolo Senoufo" }, + { "sew", "Sewa Bay" }, + { "sey", "Secoya" }, + { "sez", "Senthang Chin" }, + { "sfb", "Langue des signes de Belgique Francophone" }, + { "sfe", "Eastern Subanen" }, + { "sfm", "Small Flowery Miao" }, + { "sfs", "South African Sign Language" }, + { "sfw", "Sehwi" }, + { "sga", "Old Irish (to 900)" }, + { "sgb", "Mag-antsi Ayta" }, + { "sgc", "Kipsigis" }, + { "sgd", "Surigaonon" }, + { "sge", "Segai" }, + { "sgg", "Swiss-German Sign Language" }, + { "sgh", "Shughni" }, + { "sgi", "Suga" }, + { "sgj", "Surgujia" }, + { "sgk", "Sangkong" }, + { "sgm", "Singa" }, + { "sgo", "Songa" }, + { "sgp", "Singpho" }, + { "sgr", "Sangisari" }, + { "sgs", "Samogitian" }, + { "sgt", "Brokpake" }, + { "sgu", "Salas" }, + { "sgw", "Sebat Bet Gurage" }, + { "sgx", "Sierra Leone Sign Language" }, + { "sgy", "Sanglechi" }, + { "sgz", "Sursurunga" }, + { "sha", "Shall-Zwall" }, + { "shb", "Ninam" }, + { "shc", "Sonde" }, + { "shd", "Kundal Shahi" }, + { "she", "Sheko" }, + { "shg", "Shua" }, + { "shh", "Shoshoni" }, + { "shi", "Tachelhit" }, + { "shj", "Shatt" }, + { "shk", "Shilluk" }, + { "shl", "Shendu" }, + { "shm", "Shahrudi" }, + { "shn", "Shan" }, + { "sho", "Shanga" }, + { "shp", "Shipibo-Conibo" }, + { "shq", "Sala" }, + { "shr", "Shi" }, + { "shs", "Shuswap" }, + { "sht", "Shasta" }, + { "shu", "Chadian Arabic" }, + { "shv", "Shehri" }, + { "shw", "Shwai" }, + { "shx", "She" }, + { "shy", "Tachawit" }, + { "shz", "Syenara Senoufo" }, + { "sia", "Akkala Sami" }, + { "sib", "Sebop" }, + { "sid", "Sidamo" }, + { "sie", "Simaa" }, + { "sif", "Siamou" }, + { "sig", "Paasaal" }, + { "sih", "Zire" }, + { "sii", "Shom Peng" }, + { "sij", "Numbami" }, + { "sik", "Sikiana" }, + { "sil", "Tumulung Sisaala" }, + { "sim", "Mende (Papua New Guinea)" }, + { "sin", "Sinhala" }, + { "sip", "Sikkimese" }, + { "siq", "Sonia" }, + { "sir", "Siri" }, + { "sis", "Siuslaw" }, + { "siu", "Sinagen" }, + { "siv", "Sumariup" }, + { "siw", "Siwai" }, + { "six", "Sumau" }, + { "siy", "Sivandi" }, + { "siz", "Siwi" }, + { "sja", "Epena" }, + { "sjb", "Sajau Basap" }, + { "sjd", "Kildin Sami" }, + { "sje", "Pite Sami" }, + { "sjg", "Assangori" }, + { "sjk", "Kemi Sami" }, + { "sjl", "Sajalong" }, + { "sjm", "Mapun" }, + { "sjn", "Sindarin" }, + { "sjo", "Xibe" }, + { "sjp", "Surjapuri" }, + { "sjr", "Siar-Lak" }, + { "sjs", "Senhaja De Srair" }, + { "sjt", "Ter Sami" }, + { "sju", "Ume Sami" }, + { "sjw", "Shawnee" }, + { "ska", "Skagit" }, + { "skb", "Saek" }, + { "skc", "Ma Manda" }, + { "skd", "Southern Sierra Miwok" }, + { "ske", "Seke (Vanuatu)" }, + { "skf", "Sakirabiá" }, + { "skg", "Sakalava Malagasy" }, + { "skh", "Sikule" }, + { "ski", "Sika" }, + { "skj", "Seke (Nepal)" }, + { "skk", "Sok" }, + { "skm", "Kutong" }, + { "skn", "Kolibugan Subanon" }, + { "sko", "Seko Tengah" }, + { "skp", "Sekapan" }, + { "skq", "Sininkere" }, + { "skr", "Seraiki" }, + { "sks", "Maia" }, + { "skt", "Sakata" }, + { "sku", "Sakao" }, + { "skv", "Skou" }, + { "skw", "Skepi Creole Dutch" }, + { "skx", "Seko Padang" }, + { "sky", "Sikaiana" }, + { "skz", "Sekar" }, + { "slc", "Sáliba" }, + { "sld", "Sissala" }, + { "sle", "Sholaga" }, + { "slf", "Swiss-Italian Sign Language" }, + { "slg", "Selungai Murut" }, + { "slh", "Southern Puget Sound Salish" }, + { "sli", "Lower Silesian" }, + { "slj", "Salumá" }, + { "slk", "Slovak" }, + { "sll", "Salt-Yui" }, + { "slm", "Pangutaran Sama" }, + { "sln", "Salinan" }, + { "slp", "Lamaholot" }, + { "slq", "Salchuq" }, + { "slr", "Salar" }, + { "sls", "Singapore Sign Language" }, + { "slt", "Sila" }, + { "slu", "Selaru" }, + { "slv", "Slovenian" }, + { "slw", "Sialum" }, + { "slx", "Salampasu" }, + { "sly", "Selayar" }, + { "slz", "Ma'ya" }, + { "sma", "Southern Sami" }, + { "smb", "Simbari" }, + { "smc", "Som" }, + { "smd", "Sama" }, + { "sme", "Northern Sami" }, + { "smf", "Auwe" }, + { "smg", "Simbali" }, + { "smh", "Samei" }, + { "smj", "Lule Sami" }, + { "smk", "Bolinao" }, + { "sml", "Central Sama" }, + { "smm", "Musasa" }, + { "smn", "Inari Sami" }, + { "smo", "Samoan" }, + { "smp", "Samaritan" }, + { "smq", "Samo" }, + { "smr", "Simeulue" }, + { "sms", "Skolt Sami" }, + { "smt", "Simte" }, + { "smu", "Somray" }, + { "smv", "Samvedi" }, + { "smw", "Sumbawa" }, + { "smx", "Samba" }, + { "smy", "Semnani" }, + { "smz", "Simeku" }, + { "sna", "Shona" }, + { "snb", "Sebuyau" }, + { "snc", "Sinaugoro" }, + { "snd", "Sindhi" }, + { "sne", "Bau Bidayuh" }, + { "snf", "Noon" }, + { "sng", "Sanga (Democratic Republic of Congo)" }, + { "snh", "Shinabo" }, + { "sni", "Sensi" }, + { "snj", "Riverain Sango" }, + { "snk", "Soninke" }, + { "snl", "Sangil" }, + { "snm", "Southern Ma'di" }, + { "snn", "Siona" }, + { "sno", "Snohomish" }, + { "snp", "Siane" }, + { "snq", "Sangu (Gabon)" }, + { "snr", "Sihan" }, + { "sns", "South West Bay" }, + { "snu", "Senggi" }, + { "snv", "Sa'ban" }, + { "snw", "Selee" }, + { "snx", "Sam" }, + { "sny", "Saniyo-Hiyewe" }, + { "snz", "Sinsauru" }, + { "soa", "Thai Song" }, + { "sob", "Sobei" }, + { "soc", "So (Democratic Republic of Congo)" }, + { "sod", "Songoora" }, + { "soe", "Songomeno" }, + { "sog", "Sogdian" }, + { "soh", "Aka" }, + { "soi", "Sonha" }, + { "soj", "Soi" }, + { "sok", "Sokoro" }, + { "sol", "Solos" }, + { "som", "Somali" }, + { "soo", "Songo" }, + { "sop", "Songe" }, + { "soq", "Kanasi" }, + { "sor", "Somrai" }, + { "sos", "Seeku" }, + { "sot", "Southern Sotho" }, + { "sou", "Southern Thai" }, + { "sov", "Sonsorol" }, + { "sow", "Sowanda" }, + { "sox", "Swo" }, + { "soy", "Miyobe" }, + { "soz", "Temi" }, + { "spa", "Spanish" }, + { "spb", "Sepa (Indonesia)" }, + { "spc", "Sapé" }, + { "spd", "Saep" }, + { "spe", "Sepa (Papua New Guinea)" }, + { "spg", "Sian" }, + { "spi", "Saponi" }, + { "spk", "Sengo" }, + { "spl", "Selepet" }, + { "spm", "Akukem" }, + { "spo", "Spokane" }, + { "spp", "Supyire Senoufo" }, + { "spq", "Loreto-Ucayali Spanish" }, + { "spr", "Saparua" }, + { "sps", "Saposa" }, + { "spt", "Spiti Bhoti" }, + { "spu", "Sapuan" }, + { "spv", "Sambalpuri" }, + { "spx", "South Picene" }, + { "spy", "Sabaot" }, + { "sqa", "Shama-Sambuga" }, + { "sqh", "Shau" }, + { "sqi", "Albanian" }, + { "sqk", "Albanian Sign Language" }, + { "sqm", "Suma" }, + { "sqn", "Susquehannock" }, + { "sqo", "Sorkhei" }, + { "sqq", "Sou" }, + { "sqr", "Siculo Arabic" }, + { "sqs", "Sri Lankan Sign Language" }, + { "sqt", "Soqotri" }, + { "squ", "Squamish" }, + { "sra", "Saruga" }, + { "srb", "Sora" }, + { "src", "Logudorese Sardinian" }, + { "srd", "Sardinian" }, + { "sre", "Sara" }, + { "srf", "Nafi" }, + { "srg", "Sulod" }, + { "srh", "Sarikoli" }, + { "sri", "Siriano" }, + { "srk", "Serudung Murut" }, + { "srl", "Isirawa" }, + { "srm", "Saramaccan" }, + { "srn", "Sranan Tongo" }, + { "sro", "Campidanese Sardinian" }, + { "srp", "Serbian" }, + { "srq", "Sirionó" }, + { "srr", "Serer" }, + { "srs", "Sarsi" }, + { "srt", "Sauri" }, + { "sru", "Suruí" }, + { "srv", "Southern Sorsoganon" }, + { "srw", "Serua" }, + { "srx", "Sirmauri" }, + { "sry", "Sera" }, + { "srz", "Shahmirzadi" }, + { "ssb", "Southern Sama" }, + { "ssc", "Suba-Simbiti" }, + { "ssd", "Siroi" }, + { "sse", "Balangingi" }, + { "ssf", "Thao" }, + { "ssg", "Seimat" }, + { "ssh", "Shihhi Arabic" }, + { "ssi", "Sansi" }, + { "ssj", "Sausi" }, + { "ssk", "Sunam" }, + { "ssl", "Western Sisaala" }, + { "ssm", "Semnam" }, + { "ssn", "Waata" }, + { "sso", "Sissano" }, + { "ssp", "Spanish Sign Language" }, + { "ssq", "So'a" }, + { "ssr", "Swiss-French Sign Language" }, + { "sss", "Sô" }, + { "sst", "Sinasina" }, + { "ssu", "Susuami" }, + { "ssv", "Shark Bay" }, + { "ssw", "Swati" }, + { "ssx", "Samberigi" }, + { "ssy", "Saho" }, + { "ssz", "Sengseng" }, + { "sta", "Settla" }, + { "stb", "Northern Subanen" }, + { "std", "Sentinel" }, + { "ste", "Liana-Seti" }, + { "stf", "Seta" }, + { "stg", "Trieng" }, + { "sth", "Shelta" }, + { "sti", "Bulo Stieng" }, + { "stj", "Matya Samo" }, + { "stk", "Arammba" }, + { "stl", "Stellingwerfs" }, + { "stm", "Setaman" }, + { "stn", "Owa" }, + { "sto", "Stoney" }, + { "stp", "Southeastern Tepehuan" }, + { "stq", "Saterfriesisch" }, + { "str", "Straits Salish" }, + { "sts", "Shumashti" }, + { "stt", "Budeh Stieng" }, + { "stu", "Samtao" }, + { "stv", "Silt'e" }, + { "stw", "Satawalese" }, + { "sty", "Siberian Tatar" }, + { "sua", "Sulka" }, + { "sub", "Suku" }, + { "suc", "Western Subanon" }, + { "sue", "Suena" }, + { "sug", "Suganga" }, + { "sui", "Suki" }, + { "suj", "Shubi" }, + { "suk", "Sukuma" }, + { "sun", "Sundanese" }, + { "suq", "Suri" }, + { "sur", "Mwaghavul" }, + { "sus", "Susu" }, + { "sut", "Subtiaba" }, + { "suv", "Puroik" }, + { "suw", "Sumbwa" }, + { "sux", "Sumerian" }, + { "suy", "Suyá" }, + { "suz", "Sunwar" }, + { "sva", "Svan" }, + { "svb", "Ulau-Suain" }, + { "svc", "Vincentian Creole English" }, + { "sve", "Serili" }, + { "svk", "Slovakian Sign Language" }, + { "svm", "Slavomolisano" }, + { "svr", "Savara" }, + { "svs", "Savosavo" }, + { "svx", "Skalvian" }, + { "swa", "Swahili (macrolanguage)" }, + { "swb", "Maore Comorian" }, + { "swc", "Congo Swahili" }, + { "swe", "Swedish" }, + { "swf", "Sere" }, + { "swg", "Swabian" }, + { "swh", "Swahili (individual language)" }, + { "swi", "Sui" }, + { "swj", "Sira" }, + { "swk", "Malawi Sena" }, + { "swl", "Swedish Sign Language" }, + { "swm", "Samosa" }, + { "swn", "Sawknah" }, + { "swo", "Shanenawa" }, + { "swp", "Suau" }, + { "swq", "Sharwa" }, + { "swr", "Saweru" }, + { "sws", "Seluwasan" }, + { "swt", "Sawila" }, + { "swu", "Suwawa" }, + { "swv", "Shekhawati" }, + { "sww", "Sowa" }, + { "swx", "Suruahá" }, + { "swy", "Sarua" }, + { "sxb", "Suba" }, + { "sxc", "Sicanian" }, + { "sxe", "Sighu" }, + { "sxg", "Shixing" }, + { "sxk", "Southern Kalapuya" }, + { "sxl", "Selian" }, + { "sxm", "Samre" }, + { "sxn", "Sangir" }, + { "sxo", "Sorothaptic" }, + { "sxr", "Saaroa" }, + { "sxs", "Sasaru" }, + { "sxu", "Upper Saxon" }, + { "sxw", "Saxwe Gbe" }, + { "sya", "Siang" }, + { "syb", "Central Subanen" }, + { "syc", "Classical Syriac" }, + { "syi", "Seki" }, + { "syk", "Sukur" }, + { "syl", "Sylheti" }, + { "sym", "Maya Samo" }, + { "syn", "Senaya" }, + { "syo", "Suoy" }, + { "syr", "Syriac" }, + { "sys", "Sinyar" }, + { "syw", "Kagate" }, + { "syy", "Al-Sayyid Bedouin Sign Language" }, + { "sza", "Semelai" }, + { "szb", "Ngalum" }, + { "szc", "Semaq Beri" }, + { "szd", "Seru" }, + { "sze", "Seze" }, + { "szg", "Sengele" }, + { "szl", "Silesian" }, + { "szn", "Sula" }, + { "szp", "Suabo" }, + { "szv", "Isu (Fako Division)" }, + { "szw", "Sawai" }, + { "taa", "Lower Tanana" }, + { "tab", "Tabassaran" }, + { "tac", "Lowland Tarahumara" }, + { "tad", "Tause" }, + { "tae", "Tariana" }, + { "taf", "Tapirapé" }, + { "tag", "Tagoi" }, + { "tah", "Tahitian" }, + { "taj", "Eastern Tamang" }, + { "tak", "Tala" }, + { "tal", "Tal" }, + { "tam", "Tamil" }, + { "tan", "Tangale" }, + { "tao", "Yami" }, + { "tap", "Taabwa" }, + { "taq", "Tamasheq" }, + { "tar", "Central Tarahumara" }, + { "tas", "Tay Boi" }, + { "tat", "Tatar" }, + { "tau", "Upper Tanana" }, + { "tav", "Tatuyo" }, + { "taw", "Tai" }, + { "tax", "Tamki" }, + { "tay", "Atayal" }, + { "taz", "Tocho" }, + { "tba", "Aikanã" }, + { "tbb", "Tapeba" }, + { "tbc", "Takia" }, + { "tbd", "Kaki Ae" }, + { "tbe", "Tanimbili" }, + { "tbf", "Mandara" }, + { "tbg", "North Tairora" }, + { "tbh", "Thurawal" }, + { "tbi", "Gaam" }, + { "tbj", "Tiang" }, + { "tbk", "Calamian Tagbanwa" }, + { "tbl", "Tboli" }, + { "tbm", "Tagbu" }, + { "tbn", "Barro Negro Tunebo" }, + { "tbo", "Tawala" }, + { "tbp", "Taworta" }, + { "tbr", "Tumtum" }, + { "tbs", "Tanguat" }, + { "tbt", "Tembo (Kitembo)" }, + { "tbu", "Tubar" }, + { "tbv", "Tobo" }, + { "tbw", "Tagbanwa" }, + { "tbx", "Kapin" }, + { "tby", "Tabaru" }, + { "tbz", "Ditammari" }, + { "tca", "Ticuna" }, + { "tcb", "Tanacross" }, + { "tcc", "Datooga" }, + { "tcd", "Tafi" }, + { "tce", "Southern Tutchone" }, + { "tcf", "Malinaltepec Me'phaa" }, + { "tcg", "Tamagario" }, + { "tch", "Turks And Caicos Creole English" }, + { "tci", "Wára" }, + { "tck", "Tchitchege" }, + { "tcl", "Taman (Myanmar)" }, + { "tcm", "Tanahmerah" }, + { "tcn", "Tichurong" }, + { "tco", "Taungyo" }, + { "tcp", "Tawr Chin" }, + { "tcq", "Kaiy" }, + { "tcs", "Torres Strait Creole" }, + { "tct", "T'en" }, + { "tcu", "Southeastern Tarahumara" }, + { "tcw", "Tecpatlán Totonac" }, + { "tcx", "Toda" }, + { "tcy", "Tulu" }, + { "tcz", "Thado Chin" }, + { "tda", "Tagdal" }, + { "tdb", "Panchpargania" }, + { "tdc", "Emberá-Tadó" }, + { "tdd", "Tai Nüa" }, + { "tde", "Tiranige Diga Dogon" }, + { "tdf", "Talieng" }, + { "tdg", "Western Tamang" }, + { "tdh", "Thulung" }, + { "tdi", "Tomadino" }, + { "tdj", "Tajio" }, + { "tdk", "Tambas" }, + { "tdl", "Sur" }, + { "tdn", "Tondano" }, + { "tdo", "Teme" }, + { "tdq", "Tita" }, + { "tdr", "Todrah" }, + { "tds", "Doutai" }, + { "tdt", "Tetun Dili" }, + { "tdu", "Tempasuk Dusun" }, + { "tdv", "Toro" }, + { "tdx", "Tandroy-Mahafaly Malagasy" }, + { "tdy", "Tadyawan" }, + { "tea", "Temiar" }, + { "teb", "Tetete" }, + { "tec", "Terik" }, + { "ted", "Tepo Krumen" }, + { "tee", "Huehuetla Tepehua" }, + { "tef", "Teressa" }, + { "teg", "Teke-Tege" }, + { "teh", "Tehuelche" }, + { "tei", "Torricelli" }, + { "tek", "Ibali Teke" }, + { "tel", "Telugu" }, + { "tem", "Timne" }, + { "ten", "Tama (Colombia)" }, + { "teo", "Teso" }, + { "tep", "Tepecano" }, + { "teq", "Temein" }, + { "ter", "Tereno" }, + { "tes", "Tengger" }, + { "tet", "Tetum" }, + { "teu", "Soo" }, + { "tev", "Teor" }, + { "tew", "Tewa (USA)" }, + { "tex", "Tennet" }, + { "tey", "Tulishi" }, + { "tfi", "Tofin Gbe" }, + { "tfn", "Tanaina" }, + { "tfo", "Tefaro" }, + { "tfr", "Teribe" }, + { "tft", "Ternate" }, + { "tga", "Sagalla" }, + { "tgb", "Tobilung" }, + { "tgc", "Tigak" }, + { "tgd", "Ciwogai" }, + { "tge", "Eastern Gorkha Tamang" }, + { "tgf", "Chalikha" }, + { "tgh", "Tobagonian Creole English" }, + { "tgi", "Lawunuia" }, + { "tgj", "Tagin" }, + { "tgk", "Tajik" }, + { "tgl", "Tagalog" }, + { "tgn", "Tandaganon" }, + { "tgo", "Sudest" }, + { "tgp", "Tangoa" }, + { "tgq", "Tring" }, + { "tgr", "Tareng" }, + { "tgs", "Nume" }, + { "tgt", "Central Tagbanwa" }, + { "tgu", "Tanggu" }, + { "tgv", "Tingui-Boto" }, + { "tgw", "Tagwana Senoufo" }, + { "tgx", "Tagish" }, + { "tgy", "Togoyo" }, + { "tgz", "Tagalaka" }, + { "tha", "Thai" }, + { "thc", "Tai Hang Tong" }, + { "thd", "Thayore" }, + { "the", "Chitwania Tharu" }, + { "thf", "Thangmi" }, + { "thh", "Northern Tarahumara" }, + { "thi", "Tai Long" }, + { "thk", "Tharaka" }, + { "thl", "Dangaura Tharu" }, + { "thm", "Aheu" }, + { "thn", "Thachanadan" }, + { "thp", "Thompson" }, + { "thq", "Kochila Tharu" }, + { "thr", "Rana Tharu" }, + { "ths", "Thakali" }, + { "tht", "Tahltan" }, + { "thu", "Thuri" }, + { "thv", "Tahaggart Tamahaq" }, + { "thw", "Thudam" }, + { "thx", "The" }, + { "thy", "Tha" }, + { "thz", "Tayart Tamajeq" }, + { "tia", "Tidikelt Tamazight" }, + { "tic", "Tira" }, + { "tid", "Tidong" }, + { "tif", "Tifal" }, + { "tig", "Tigre" }, + { "tih", "Timugon Murut" }, + { "tii", "Tiene" }, + { "tij", "Tilung" }, + { "tik", "Tikar" }, + { "til", "Tillamook" }, + { "tim", "Timbe" }, + { "tin", "Tindi" }, + { "tio", "Teop" }, + { "tip", "Trimuris" }, + { "tiq", "Tiéfo" }, + { "tir", "Tigrinya" }, + { "tis", "Masadiit Itneg" }, + { "tit", "Tinigua" }, + { "tiu", "Adasen" }, + { "tiv", "Tiv" }, + { "tiw", "Tiwi" }, + { "tix", "Southern Tiwa" }, + { "tiy", "Tiruray" }, + { "tiz", "Tai Hongjin" }, + { "tja", "Tajuasohn" }, + { "tjg", "Tunjung" }, + { "tji", "Northern Tujia" }, + { "tjl", "Tai Laing" }, + { "tjm", "Timucua" }, + { "tjn", "Tonjon" }, + { "tjo", "Temacine Tamazight" }, + { "tjs", "Southern Tujia" }, + { "tju", "Tjurruru" }, + { "tjw", "Djabwurrung" }, + { "tka", "Truká" }, + { "tkb", "Buksa" }, + { "tkd", "Tukudede" }, + { "tke", "Takwane" }, + { "tkf", "Tukumanféd" }, + { "tkg", "Tesaka Malagasy" }, + { "tkl", "Tokelau" }, + { "tkm", "Takelma" }, + { "tkn", "Toku-No-Shima" }, + { "tkp", "Tikopia" }, + { "tkq", "Tee" }, + { "tkr", "Tsakhur" }, + { "tks", "Takestani" }, + { "tkt", "Kathoriya Tharu" }, + { "tku", "Upper Necaxa Totonac" }, + { "tkw", "Teanu" }, + { "tkx", "Tangko" }, + { "tkz", "Takua" }, + { "tla", "Southwestern Tepehuan" }, + { "tlb", "Tobelo" }, + { "tlc", "Yecuatla Totonac" }, + { "tld", "Talaud" }, + { "tlf", "Telefol" }, + { "tlg", "Tofanma" }, + { "tlh", "Klingon" }, + { "tli", "Tlingit" }, + { "tlj", "Talinga-Bwisi" }, + { "tlk", "Taloki" }, + { "tll", "Tetela" }, + { "tlm", "Tolomako" }, + { "tln", "Talondo'" }, + { "tlo", "Talodi" }, + { "tlp", "Filomena Mata-Coahuitlán Totonac" }, + { "tlq", "Tai Loi" }, + { "tlr", "Talise" }, + { "tls", "Tambotalo" }, + { "tlt", "Teluti" }, + { "tlu", "Tulehu" }, + { "tlv", "Taliabu" }, + { "tlx", "Khehek" }, + { "tly", "Talysh" }, + { "tma", "Tama (Chad)" }, + { "tmb", "Katbol" }, + { "tmc", "Tumak" }, + { "tmd", "Haruai" }, + { "tme", "Tremembé" }, + { "tmf", "Toba-Maskoy" }, + { "tmg", "Ternateño" }, + { "tmh", "Tamashek" }, + { "tmi", "Tutuba" }, + { "tmj", "Samarokena" }, + { "tmk", "Northwestern Tamang" }, + { "tml", "Tamnim Citak" }, + { "tmm", "Tai Thanh" }, + { "tmn", "Taman (Indonesia)" }, + { "tmo", "Temoq" }, + { "tmp", "Tai Mène" }, + { "tmq", "Tumleo" }, + { "tmr", "Jewish Babylonian Aramaic (ca. 200-1200 CE)" }, + { "tms", "Tima" }, + { "tmt", "Tasmate" }, + { "tmu", "Iau" }, + { "tmv", "Tembo (Motembo)" }, + { "tmw", "Temuan" }, + { "tmy", "Tami" }, + { "tmz", "Tamanaku" }, + { "tna", "Tacana" }, + { "tnb", "Western Tunebo" }, + { "tnc", "Tanimuca-Retuarã" }, + { "tnd", "Angosturas Tunebo" }, + { "tne", "Tinoc Kallahan" }, + { "tng", "Tobanga" }, + { "tnh", "Maiani" }, + { "tni", "Tandia" }, + { "tnk", "Kwamera" }, + { "tnl", "Lenakel" }, + { "tnm", "Tabla" }, + { "tnn", "North Tanna" }, + { "tno", "Toromono" }, + { "tnp", "Whitesands" }, + { "tnq", "Taino" }, + { "tnr", "Ménik" }, + { "tns", "Tenis" }, + { "tnt", "Tontemboan" }, + { "tnu", "Tay Khang" }, + { "tnv", "Tangchangya" }, + { "tnw", "Tonsawang" }, + { "tnx", "Tanema" }, + { "tny", "Tongwe" }, + { "tnz", "Tonga (Thailand)" }, + { "tob", "Toba" }, + { "toc", "Coyutla Totonac" }, + { "tod", "Toma" }, + { "toe", "Tomedes" }, + { "tof", "Gizrra" }, + { "tog", "Tonga (Nyasa)" }, + { "toh", "Gitonga" }, + { "toi", "Tonga (Zambia)" }, + { "toj", "Tojolabal" }, + { "tol", "Tolowa" }, + { "tom", "Tombulu" }, + { "ton", "Tonga (Tonga Islands)" }, + { "too", "Xicotepec De Juárez Totonac" }, + { "top", "Papantla Totonac" }, + { "toq", "Toposa" }, + { "tor", "Togbo-Vara Banda" }, + { "tos", "Highland Totonac" }, + { "tou", "Tho" }, + { "tov", "Upper Taromi" }, + { "tow", "Jemez" }, + { "tox", "Tobian" }, + { "toy", "Topoiyo" }, + { "toz", "To" }, + { "tpa", "Taupota" }, + { "tpc", "Azoyú Me'phaa" }, + { "tpe", "Tippera" }, + { "tpf", "Tarpia" }, + { "tpg", "Kula" }, + { "tpi", "Tok Pisin" }, + { "tpj", "Tapieté" }, + { "tpk", "Tupinikin" }, + { "tpl", "Tlacoapa Me'phaa" }, + { "tpm", "Tampulma" }, + { "tpn", "Tupinambá" }, + { "tpo", "Tai Pao" }, + { "tpp", "Pisaflores Tepehua" }, + { "tpq", "Tukpa" }, + { "tpr", "Tuparí" }, + { "tpt", "Tlachichilco Tepehua" }, + { "tpu", "Tampuan" }, + { "tpv", "Tanapag" }, + { "tpw", "Tupí" }, + { "tpx", "Acatepec Me'phaa" }, + { "tpy", "Trumai" }, + { "tpz", "Tinputz" }, + { "tqb", "Tembé" }, + { "tql", "Lehali" }, + { "tqm", "Turumsa" }, + { "tqn", "Tenino" }, + { "tqo", "Toaripi" }, + { "tqp", "Tomoip" }, + { "tqq", "Tunni" }, + { "tqr", "Torona" }, + { "tqt", "Western Totonac" }, + { "tqu", "Touo" }, + { "tqw", "Tonkawa" }, + { "tra", "Tirahi" }, + { "trb", "Terebu" }, + { "trc", "Copala Triqui" }, + { "trd", "Turi" }, + { "tre", "East Tarangan" }, + { "trf", "Trinidadian Creole English" }, + { "trg", "Lishán Didán" }, + { "trh", "Turaka" }, + { "tri", "Trió" }, + { "trj", "Toram" }, + { "trl", "Traveller Scottish" }, + { "trm", "Tregami" }, + { "trn", "Trinitario" }, + { "tro", "Tarao Naga" }, + { "trp", "Kok Borok" }, + { "trq", "San Martín Itunyoso Triqui" }, + { "trr", "Taushiro" }, + { "trs", "Chicahuaxtla Triqui" }, + { "trt", "Tunggare" }, + { "tru", "Turoyo" }, + { "trv", "Taroko" }, + { "trw", "Torwali" }, + { "trx", "Tringgus-Sembaan Bidayuh" }, + { "try", "Turung" }, + { "trz", "Torá" }, + { "tsa", "Tsaangi" }, + { "tsb", "Tsamai" }, + { "tsc", "Tswa" }, + { "tsd", "Tsakonian" }, + { "tse", "Tunisian Sign Language" }, + { "tsf", "Southwestern Tamang" }, + { "tsg", "Tausug" }, + { "tsh", "Tsuvan" }, + { "tsi", "Tsimshian" }, + { "tsj", "Tshangla" }, + { "tsk", "Tseku" }, + { "tsl", "Ts'ün-Lao" }, + { "tsm", "Turkish Sign Language" }, + { "tsn", "Tswana" }, + { "tso", "Tsonga" }, + { "tsp", "Northern Toussian" }, + { "tsq", "Thai Sign Language" }, + { "tsr", "Akei" }, + { "tss", "Taiwan Sign Language" }, + { "tst", "Tondi Songway Kiini" }, + { "tsu", "Tsou" }, + { "tsv", "Tsogo" }, + { "tsw", "Tsishingini" }, + { "tsx", "Mubami" }, + { "tsy", "Tebul Sign Language" }, + { "tsz", "Purepecha" }, + { "tta", "Tutelo" }, + { "ttb", "Gaa" }, + { "ttc", "Tektiteko" }, + { "ttd", "Tauade" }, + { "tte", "Bwanabwana" }, + { "ttf", "Tuotomb" }, + { "ttg", "Tutong" }, + { "tth", "Upper Ta'oih" }, + { "tti", "Tobati" }, + { "ttj", "Tooro" }, + { "ttk", "Totoro" }, + { "ttl", "Totela" }, + { "ttm", "Northern Tutchone" }, + { "ttn", "Towei" }, + { "tto", "Lower Ta'oih" }, + { "ttp", "Tombelala" }, + { "ttq", "Tawallammat Tamajaq" }, + { "ttr", "Tera" }, + { "tts", "Northeastern Thai" }, + { "ttt", "Muslim Tat" }, + { "ttu", "Torau" }, + { "ttv", "Titan" }, + { "ttw", "Long Wat" }, + { "tty", "Sikaritai" }, + { "ttz", "Tsum" }, + { "tua", "Wiarumus" }, + { "tub", "Tübatulabal" }, + { "tuc", "Mutu" }, + { "tud", "Tuxá" }, + { "tue", "Tuyuca" }, + { "tuf", "Central Tunebo" }, + { "tug", "Tunia" }, + { "tuh", "Taulil" }, + { "tui", "Tupuri" }, + { "tuj", "Tugutil" }, + { "tuk", "Turkmen" }, + { "tul", "Tula" }, + { "tum", "Tumbuka" }, + { "tun", "Tunica" }, + { "tuo", "Tucano" }, + { "tuq", "Tedaga" }, + { "tur", "Turkish" }, + { "tus", "Tuscarora" }, + { "tuu", "Tututni" }, + { "tuv", "Turkana" }, + { "tux", "Tuxináwa" }, + { "tuy", "Tugen" }, + { "tuz", "Turka" }, + { "tva", "Vaghua" }, + { "tvd", "Tsuvadi" }, + { "tve", "Te'un" }, + { "tvk", "Southeast Ambrym" }, + { "tvl", "Tuvalu" }, + { "tvm", "Tela-Masbuar" }, + { "tvn", "Tavoyan" }, + { "tvo", "Tidore" }, + { "tvs", "Taveta" }, + { "tvt", "Tutsa Naga" }, + { "tvu", "Tunen" }, + { "tvw", "Sedoa" }, + { "tvy", "Timor Pidgin" }, + { "twa", "Twana" }, + { "twb", "Western Tawbuid" }, + { "twc", "Teshenawa" }, + { "twd", "Twents" }, + { "twe", "Tewa (Indonesia)" }, + { "twf", "Northern Tiwa" }, + { "twg", "Tereweng" }, + { "twh", "Tai Dón" }, + { "twi", "Twi" }, + { "twl", "Tawara" }, + { "twm", "Tawang Monpa" }, + { "twn", "Twendi" }, + { "two", "Tswapong" }, + { "twp", "Ere" }, + { "twq", "Tasawaq" }, + { "twr", "Southwestern Tarahumara" }, + { "twt", "Turiwára" }, + { "twu", "Termanu" }, + { "tww", "Tuwari" }, + { "twx", "Tewe" }, + { "twy", "Tawoyan" }, + { "txa", "Tombonuo" }, + { "txb", "Tokharian B" }, + { "txc", "Tsetsaut" }, + { "txe", "Totoli" }, + { "txg", "Tangut" }, + { "txh", "Thracian" }, + { "txi", "Ikpeng" }, + { "txm", "Tomini" }, + { "txn", "West Tarangan" }, + { "txo", "Toto" }, + { "txq", "Tii" }, + { "txr", "Tartessian" }, + { "txs", "Tonsea" }, + { "txt", "Citak" }, + { "txu", "Kayapó" }, + { "txx", "Tatana" }, + { "txy", "Tanosy Malagasy" }, + { "tya", "Tauya" }, + { "tye", "Kyanga" }, + { "tyh", "O'du" }, + { "tyi", "Teke-Tsaayi" }, + { "tyj", "Tai Do" }, + { "tyl", "Thu Lao" }, + { "tyn", "Kombai" }, + { "typ", "Thaypan" }, + { "tyr", "Tai Daeng" }, + { "tys", "Tày Sa Pa" }, + { "tyt", "Tày Tac" }, + { "tyu", "Kua" }, + { "tyv", "Tuvinian" }, + { "tyx", "Teke-Tyee" }, + { "tyz", "Tày" }, + { "tza", "Tanzanian Sign Language" }, + { "tzh", "Tzeltal" }, + { "tzj", "Tz'utujil" }, + { "tzl", "Talossan" }, + { "tzm", "Central Atlas Tamazight" }, + { "tzn", "Tugun" }, + { "tzo", "Tzotzil" }, + { "tzx", "Tabriak" }, + { "uam", "Uamué" }, + { "uan", "Kuan" }, + { "uar", "Tairuma" }, + { "uba", "Ubang" }, + { "ubi", "Ubi" }, + { "ubl", "Buhi'non Bikol" }, + { "ubr", "Ubir" }, + { "ubu", "Umbu-Ungu" }, + { "uby", "Ubykh" }, + { "uda", "Uda" }, + { "ude", "Udihe" }, + { "udg", "Muduga" }, + { "udi", "Udi" }, + { "udj", "Ujir" }, + { "udl", "Wuzlam" }, + { "udm", "Udmurt" }, + { "udu", "Uduk" }, + { "ues", "Kioko" }, + { "ufi", "Ufim" }, + { "uga", "Ugaritic" }, + { "ugb", "Kuku-Ugbanh" }, + { "uge", "Ughele" }, + { "ugn", "Ugandan Sign Language" }, + { "ugo", "Ugong" }, + { "ugy", "Uruguayan Sign Language" }, + { "uha", "Uhami" }, + { "uhn", "Damal" }, + { "uig", "Uighur" }, + { "uis", "Uisai" }, + { "uiv", "Iyive" }, + { "uji", "Tanjijili" }, + { "uka", "Kaburi" }, + { "ukg", "Ukuriguma" }, + { "ukh", "Ukhwejo" }, + { "ukl", "Ukrainian Sign Language" }, + { "ukp", "Ukpe-Bayobiri" }, + { "ukq", "Ukwa" }, + { "ukr", "Ukrainian" }, + { "uks", "Urubú-Kaapor Sign Language" }, + { "uku", "Ukue" }, + { "ukw", "Ukwuani-Aboh-Ndoni" }, + { "uky", "Kuuk-Yak" }, + { "ula", "Fungwa" }, + { "ulb", "Ulukwumi" }, + { "ulc", "Ulch" }, + { "ule", "Lule" }, + { "ulf", "Usku" }, + { "uli", "Ulithian" }, + { "ulk", "Meriam" }, + { "ull", "Ullatan" }, + { "ulm", "Ulumanda'" }, + { "uln", "Unserdeutsch" }, + { "ulu", "Uma' Lung" }, + { "ulw", "Ulwa" }, + { "uma", "Umatilla" }, + { "umb", "Umbundu" }, + { "umc", "Marrucinian" }, + { "umd", "Umbindhamu" }, + { "umg", "Umbuygamu" }, + { "umi", "Ukit" }, + { "umm", "Umon" }, + { "umn", "Makyan Naga" }, + { "umo", "Umotína" }, + { "ump", "Umpila" }, + { "umr", "Umbugarla" }, + { "ums", "Pendau" }, + { "umu", "Munsee" }, + { "una", "North Watut" }, + { "und", "Undetermined" }, + { "une", "Uneme" }, + { "ung", "Ngarinyin" }, + { "unk", "Enawené-Nawé" }, + { "unm", "Unami" }, + { "unn", "Kurnai" }, + { "unr", "Mundari" }, + { "unu", "Unubahe" }, + { "unx", "Munda" }, + { "unz", "Unde Kaili" }, + { "uok", "Uokha" }, + { "upi", "Umeda" }, + { "upv", "Uripiv-Wala-Rano-Atchin" }, + { "ura", "Urarina" }, + { "urb", "Urubú-Kaapor" }, + { "urc", "Urningangg" }, + { "urd", "Urdu" }, + { "ure", "Uru" }, + { "urf", "Uradhi" }, + { "urg", "Urigina" }, + { "urh", "Urhobo" }, + { "uri", "Urim" }, + { "urk", "Urak Lawoi'" }, + { "url", "Urali" }, + { "urm", "Urapmin" }, + { "urn", "Uruangnirin" }, + { "uro", "Ura (Papua New Guinea)" }, + { "urp", "Uru-Pa-In" }, + { "urr", "Lehalurup" }, + { "urt", "Urat" }, + { "uru", "Urumi" }, + { "urv", "Uruava" }, + { "urw", "Sop" }, + { "urx", "Urimo" }, + { "ury", "Orya" }, + { "urz", "Uru-Eu-Wau-Wau" }, + { "usa", "Usarufa" }, + { "ush", "Ushojo" }, + { "usi", "Usui" }, + { "usk", "Usaghade" }, + { "usp", "Uspanteco" }, + { "usu", "Uya" }, + { "uta", "Otank" }, + { "ute", "Ute-Southern Paiute" }, + { "utp", "Amba (Solomon Islands)" }, + { "utr", "Etulo" }, + { "utu", "Utu" }, + { "uum", "Urum" }, + { "uun", "Kulon-Pazeh" }, + { "uur", "Ura (Vanuatu)" }, + { "uuu", "U" }, + { "uve", "West Uvean" }, + { "uvh", "Uri" }, + { "uvl", "Lote" }, + { "uwa", "Kuku-Uwanh" }, + { "uya", "Doko-Uyanga" }, + { "uzb", "Uzbek" }, + { "uzn", "Northern Uzbek" }, + { "uzs", "Southern Uzbek" }, + { "vaa", "Vaagri Booli" }, + { "vae", "Vale" }, + { "vaf", "Vafsi" }, + { "vag", "Vagla" }, + { "vah", "Varhadi-Nagpuri" }, + { "vai", "Vai" }, + { "vaj", "Vasekela Bushman" }, + { "val", "Vehes" }, + { "vam", "Vanimo" }, + { "van", "Valman" }, + { "vao", "Vao" }, + { "vap", "Vaiphei" }, + { "var", "Huarijio" }, + { "vas", "Vasavi" }, + { "vau", "Vanuma" }, + { "vav", "Varli" }, + { "vay", "Wayu" }, + { "vbb", "Southeast Babar" }, + { "vbk", "Southwestern Bontok" }, + { "vec", "Venetian" }, + { "ved", "Veddah" }, + { "vel", "Veluws" }, + { "vem", "Vemgo-Mabas" }, + { "ven", "Venda" }, + { "veo", "Ventureño" }, + { "vep", "Veps" }, + { "ver", "Mom Jango" }, + { "vgr", "Vaghri" }, + { "vgt", "Vlaamse Gebarentaal" }, + { "vic", "Virgin Islands Creole English" }, + { "vid", "Vidunda" }, + { "vie", "Vietnamese" }, + { "vif", "Vili" }, + { "vig", "Viemo" }, + { "vil", "Vilela" }, + { "vin", "Vinza" }, + { "vis", "Vishavan" }, + { "vit", "Viti" }, + { "viv", "Iduna" }, + { "vka", "Kariyarra" }, + { "vki", "Ija-Zuba" }, + { "vkj", "Kujarge" }, + { "vkk", "Kaur" }, + { "vkl", "Kulisusu" }, + { "vkm", "Kamakan" }, + { "vko", "Kodeoha" }, + { "vkp", "Korlai Creole Portuguese" }, + { "vkt", "Tenggarong Kutai Malay" }, + { "vku", "Kurrama" }, + { "vlp", "Valpei" }, + { "vls", "Vlaams" }, + { "vma", "Martuyhunira" }, + { "vmb", "Barbaram" }, + { "vmc", "Juxtlahuaca Mixtec" }, + { "vmd", "Mudu Koraga" }, + { "vme", "East Masela" }, + { "vmf", "Mainfränkisch" }, + { "vmg", "Lungalunga" }, + { "vmh", "Maraghei" }, + { "vmi", "Miwa" }, + { "vmj", "Ixtayutla Mixtec" }, + { "vmk", "Makhuwa-Shirima" }, + { "vml", "Malgana" }, + { "vmm", "Mitlatongo Mixtec" }, + { "vmp", "Soyaltepec Mazatec" }, + { "vmq", "Soyaltepec Mixtec" }, + { "vmr", "Marenje" }, + { "vms", "Moksela" }, + { "vmu", "Muluridyi" }, + { "vmv", "Valley Maidu" }, + { "vmw", "Makhuwa" }, + { "vmx", "Tamazola Mixtec" }, + { "vmy", "Ayautla Mazatec" }, + { "vmz", "Mazatlán Mazatec" }, + { "vnk", "Vano" }, + { "vnm", "Vinmavis" }, + { "vnp", "Vunapu" }, + { "vol", "Volapük" }, + { "vor", "Voro" }, + { "vot", "Votic" }, + { "vra", "Vera'a" }, + { "vro", "Võro" }, + { "vrs", "Varisi" }, + { "vrt", "Burmbar" }, + { "vsi", "Moldova Sign Language" }, + { "vsl", "Venezuelan Sign Language" }, + { "vsv", "Valencian Sign Language" }, + { "vto", "Vitou" }, + { "vum", "Vumbu" }, + { "vun", "Vunjo" }, + { "vut", "Vute" }, + { "vwa", "Awa (China)" }, + { "waa", "Walla Walla" }, + { "wab", "Wab" }, + { "wac", "Wasco-Wishram" }, + { "wad", "Wandamen" }, + { "wae", "Walser" }, + { "waf", "Wakoná" }, + { "wag", "Wa'ema" }, + { "wah", "Watubela" }, + { "wai", "Wares" }, + { "waj", "Waffa" }, + { "wal", "Wolaytta" }, + { "wam", "Wampanoag" }, + { "wan", "Wan" }, + { "wao", "Wappo" }, + { "wap", "Wapishana" }, + { "waq", "Wageman" }, + { "war", "Waray (Philippines)" }, + { "was", "Washo" }, + { "wat", "Kaninuwa" }, + { "wau", "Waurá" }, + { "wav", "Waka" }, + { "waw", "Waiwai" }, + { "wax", "Watam" }, + { "way", "Wayana" }, + { "waz", "Wampur" }, + { "wba", "Warao" }, + { "wbb", "Wabo" }, + { "wbe", "Waritai" }, + { "wbf", "Wara" }, + { "wbh", "Wanda" }, + { "wbi", "Vwanji" }, + { "wbj", "Alagwa" }, + { "wbk", "Waigali" }, + { "wbl", "Wakhi" }, + { "wbm", "Wa" }, + { "wbp", "Warlpiri" }, + { "wbq", "Waddar" }, + { "wbr", "Wagdi" }, + { "wbt", "Wanman" }, + { "wbv", "Wajarri" }, + { "wbw", "Woi" }, + { "wca", "Yanomámi" }, + { "wci", "Waci Gbe" }, + { "wdd", "Wandji" }, + { "wdg", "Wadaginam" }, + { "wdj", "Wadjiginy" }, + { "wdk", "Wadikali" }, + { "wdu", "Wadjigu" }, + { "wdy", "Wadjabangayi" }, + { "wea", "Wewaw" }, + { "wec", "Wè Western" }, + { "wed", "Wedau" }, + { "weg", "Wergaia" }, + { "weh", "Weh" }, + { "wei", "Kiunum" }, + { "wem", "Weme Gbe" }, + { "weo", "Wemale" }, + { "wep", "Westphalien" }, + { "wer", "Weri" }, + { "wes", "Cameroon Pidgin" }, + { "wet", "Perai" }, + { "weu", "Rawngtu Chin" }, + { "wew", "Wejewa" }, + { "wfg", "Yafi" }, + { "wga", "Wagaya" }, + { "wgb", "Wagawaga" }, + { "wgg", "Wangganguru" }, + { "wgi", "Wahgi" }, + { "wgo", "Waigeo" }, + { "wgu", "Wirangu" }, + { "wgy", "Warrgamay" }, + { "wha", "Manusela" }, + { "whg", "North Wahgi" }, + { "whk", "Wahau Kenyah" }, + { "whu", "Wahau Kayan" }, + { "wib", "Southern Toussian" }, + { "wic", "Wichita" }, + { "wie", "Wik-Epa" }, + { "wif", "Wik-Keyangan" }, + { "wig", "Wik-Ngathana" }, + { "wih", "Wik-Me'anha" }, + { "wii", "Minidien" }, + { "wij", "Wik-Iiyanh" }, + { "wik", "Wikalkan" }, + { "wil", "Wilawila" }, + { "wim", "Wik-Mungkan" }, + { "win", "Ho-Chunk" }, + { "wir", "Wiraféd" }, + { "wiu", "Wiru" }, + { "wiv", "Vitu" }, + { "wiy", "Wiyot" }, + { "wja", "Waja" }, + { "wji", "Warji" }, + { "wka", "Kw'adza" }, + { "wkb", "Kumbaran" }, + { "wkd", "Wakde" }, + { "wkl", "Kalanadi" }, + { "wku", "Kunduvadi" }, + { "wkw", "Wakawaka" }, + { "wky", "Wangkayutyuru" }, + { "wla", "Walio" }, + { "wlc", "Mwali Comorian" }, + { "wle", "Wolane" }, + { "wlg", "Kunbarlang" }, + { "wli", "Waioli" }, + { "wlk", "Wailaki" }, + { "wll", "Wali (Sudan)" }, + { "wlm", "Middle Welsh" }, + { "wln", "Walloon" }, + { "wlo", "Wolio" }, + { "wlr", "Wailapa" }, + { "wls", "Wallisian" }, + { "wlu", "Wuliwuli" }, + { "wlv", "Wichí Lhamtés Vejoz" }, + { "wlw", "Walak" }, + { "wlx", "Wali (Ghana)" }, + { "wly", "Waling" }, + { "wma", "Mawa (Nigeria)" }, + { "wmb", "Wambaya" }, + { "wmc", "Wamas" }, + { "wmd", "Mamaindé" }, + { "wme", "Wambule" }, + { "wmh", "Waima'a" }, + { "wmi", "Wamin" }, + { "wmm", "Maiwa (Indonesia)" }, + { "wmn", "Waamwang" }, + { "wmo", "Wom (Papua New Guinea)" }, + { "wms", "Wambon" }, + { "wmt", "Walmajarri" }, + { "wmw", "Mwani" }, + { "wmx", "Womo" }, + { "wnb", "Wanambre" }, + { "wnc", "Wantoat" }, + { "wnd", "Wandarang" }, + { "wne", "Waneci" }, + { "wng", "Wanggom" }, + { "wni", "Ndzwani Comorian" }, + { "wnk", "Wanukaka" }, + { "wnm", "Wanggamala" }, + { "wnn", "Wunumara" }, + { "wno", "Wano" }, + { "wnp", "Wanap" }, + { "wnu", "Usan" }, + { "wnw", "Wintu" }, + { "wny", "Wanyi" }, + { "woa", "Tyaraity" }, + { "wob", "Wè Northern" }, + { "woc", "Wogeo" }, + { "wod", "Wolani" }, + { "woe", "Woleaian" }, + { "wof", "Gambian Wolof" }, + { "wog", "Wogamusin" }, + { "woi", "Kamang" }, + { "wok", "Longto" }, + { "wol", "Wolof" }, + { "wom", "Wom (Nigeria)" }, + { "won", "Wongo" }, + { "woo", "Manombai" }, + { "wor", "Woria" }, + { "wos", "Hanga Hundi" }, + { "wow", "Wawonii" }, + { "woy", "Weyto" }, + { "wpc", "Maco" }, + { "wra", "Warapu" }, + { "wrb", "Warluwara" }, + { "wrd", "Warduji" }, + { "wrg", "Warungu" }, + { "wrh", "Wiradhuri" }, + { "wri", "Wariyangga" }, + { "wrk", "Garrwa" }, + { "wrl", "Warlmanpa" }, + { "wrm", "Warumungu" }, + { "wrn", "Warnang" }, + { "wro", "Worrorra" }, + { "wrp", "Waropen" }, + { "wrr", "Wardaman" }, + { "wrs", "Waris" }, + { "wru", "Waru" }, + { "wrv", "Waruna" }, + { "wrw", "Gugu Warra" }, + { "wrx", "Wae Rana" }, + { "wry", "Merwari" }, + { "wrz", "Waray (Australia)" }, + { "wsa", "Warembori" }, + { "wsi", "Wusi" }, + { "wsk", "Waskia" }, + { "wsr", "Owenia" }, + { "wss", "Wasa" }, + { "wsu", "Wasu" }, + { "wsv", "Wotapuri-Katarqalai" }, + { "wtf", "Watiwa" }, + { "wth", "Wathawurrung" }, + { "wti", "Berta" }, + { "wtk", "Watakataui" }, + { "wtm", "Mewati" }, + { "wtw", "Wotu" }, + { "wua", "Wikngenchera" }, + { "wub", "Wunambal" }, + { "wud", "Wudu" }, + { "wuh", "Wutunhua" }, + { "wul", "Silimo" }, + { "wum", "Wumbvu" }, + { "wun", "Bungu" }, + { "wur", "Wurrugu" }, + { "wut", "Wutung" }, + { "wuu", "Wu Chinese" }, + { "wuv", "Wuvulu-Aua" }, + { "wux", "Wulna" }, + { "wuy", "Wauyai" }, + { "wwa", "Waama" }, + { "wwb", "Wakabunga" }, + { "wwo", "Wetamut" }, + { "wwr", "Warrwa" }, + { "www", "Wawa" }, + { "wxa", "Waxianghua" }, + { "wxw", "Wardandi" }, + { "wya", "Wyandot" }, + { "wyb", "Wangaaybuwan-Ngiyambaa" }, + { "wyi", "Woiwurrung" }, + { "wym", "Wymysorys" }, + { "wyr", "Wayoró" }, + { "wyy", "Western Fijian" }, + { "xaa", "Andalusian Arabic" }, + { "xab", "Sambe" }, + { "xac", "Kachari" }, + { "xad", "Adai" }, + { "xae", "Aequian" }, + { "xag", "Aghwan" }, + { "xai", "Kaimbé" }, + { "xal", "Kalmyk" }, + { "xam", "Xam" }, + { "xan", "Xamtanga" }, + { "xao", "Khao" }, + { "xap", "Apalachee" }, + { "xaq", "Aquitanian" }, + { "xar", "Karami" }, + { "xas", "Kamas" }, + { "xat", "Katawixi" }, + { "xau", "Kauwera" }, + { "xav", "Xavánte" }, + { "xaw", "Kawaiisu" }, + { "xay", "Kayan Mahakam" }, + { "xba", "Kamba (Brazil)" }, + { "xbb", "Lower Burdekin" }, + { "xbc", "Bactrian" }, + { "xbd", "Bindal" }, + { "xbe", "Bigambal" }, + { "xbg", "Bunganditj" }, + { "xbi", "Kombio" }, + { "xbj", "Birrpayi" }, + { "xbm", "Middle Breton" }, + { "xbn", "Kenaboi" }, + { "xbo", "Bolgarian" }, + { "xbp", "Bibbulman" }, + { "xbr", "Kambera" }, + { "xbw", "Kambiwá" }, + { "xbx", "Kabixí" }, + { "xby", "Batyala" }, + { "xcb", "Cumbric" }, + { "xcc", "Camunic" }, + { "xce", "Celtiberian" }, + { "xcg", "Cisalpine Gaulish" }, + { "xch", "Chemakum" }, + { "xcl", "Classical Armenian" }, + { "xcm", "Comecrudo" }, + { "xcn", "Cotoname" }, + { "xco", "Chorasmian" }, + { "xcr", "Carian" }, + { "xct", "Classical Tibetan" }, + { "xcu", "Curonian" }, + { "xcv", "Chuvantsy" }, + { "xcw", "Coahuilteco" }, + { "xcy", "Cayuse" }, + { "xda", "Darkinyung" }, + { "xdc", "Dacian" }, + { "xdk", "Dharuk" }, + { "xdm", "Edomite" }, + { "xdy", "Malayic Dayak" }, + { "xeb", "Eblan" }, + { "xed", "Hdi" }, + { "xeg", "Xegwi" }, + { "xel", "Kelo" }, + { "xem", "Kembayan" }, + { "xep", "Epi-Olmec" }, + { "xer", "Xerénte" }, + { "xes", "Kesawai" }, + { "xet", "Xetá" }, + { "xeu", "Keoru-Ahia" }, + { "xfa", "Faliscan" }, + { "xga", "Galatian" }, + { "xgb", "Gbin" }, + { "xgd", "Gudang" }, + { "xgf", "Gabrielino-Fernandeño" }, + { "xgg", "Goreng" }, + { "xgi", "Garingbal" }, + { "xgl", "Galindan" }, + { "xgm", "Guwinmal" }, + { "xgr", "Garza" }, + { "xgu", "Unggumi" }, + { "xgw", "Guwa" }, + { "xha", "Harami" }, + { "xhc", "Hunnic" }, + { "xhd", "Hadrami" }, + { "xhe", "Khetrani" }, + { "xho", "Xhosa" }, + { "xhr", "Hernican" }, + { "xht", "Hattic" }, + { "xhu", "Hurrian" }, + { "xhv", "Khua" }, + { "xib", "Iberian" }, + { "xii", "Xiri" }, + { "xil", "Illyrian" }, + { "xin", "Xinca" }, + { "xip", "Xipináwa" }, + { "xir", "Xiriâna" }, + { "xiv", "Indus Valley Language" }, + { "xiy", "Xipaya" }, + { "xjb", "Minjungbal" }, + { "xjt", "Jaitmatang" }, + { "xka", "Kalkoti" }, + { "xkb", "Northern Nago" }, + { "xkc", "Kho'ini" }, + { "xkd", "Mendalam Kayan" }, + { "xke", "Kereho" }, + { "xkf", "Khengkha" }, + { "xkg", "Kagoro" }, + { "xkh", "Karahawyana" }, + { "xki", "Kenyan Sign Language" }, + { "xkj", "Kajali" }, + { "xkk", "Kaco'" }, + { "xkl", "Mainstream Kenyah" }, + { "xkn", "Kayan River Kayan" }, + { "xko", "Kiorr" }, + { "xkp", "Kabatei" }, + { "xkq", "Koroni" }, + { "xkr", "Xakriabá" }, + { "xks", "Kumbewaha" }, + { "xkt", "Kantosi" }, + { "xku", "Kaamba" }, + { "xkv", "Kgalagadi" }, + { "xkw", "Kembra" }, + { "xkx", "Karore" }, + { "xky", "Uma' Lasan" }, + { "xkz", "Kurtokha" }, + { "xla", "Kamula" }, + { "xlb", "Loup B" }, + { "xlc", "Lycian" }, + { "xld", "Lydian" }, + { "xle", "Lemnian" }, + { "xlg", "Ligurian (Ancient)" }, + { "xli", "Liburnian" }, + { "xln", "Alanic" }, + { "xlo", "Loup A" }, + { "xlp", "Lepontic" }, + { "xls", "Lusitanian" }, + { "xlu", "Cuneiform Luwian" }, + { "xly", "Elymian" }, + { "xma", "Mushungulu" }, + { "xmb", "Mbonga" }, + { "xmc", "Makhuwa-Marrevone" }, + { "xmd", "Mbudum" }, + { "xme", "Median" }, + { "xmf", "Mingrelian" }, + { "xmg", "Mengaka" }, + { "xmh", "Kuku-Muminh" }, + { "xmj", "Majera" }, + { "xmk", "Ancient Macedonian" }, + { "xml", "Malaysian Sign Language" }, + { "xmm", "Manado Malay" }, + { "xmn", "Manichaean Middle Persian" }, + { "xmo", "Morerebi" }, + { "xmp", "Kuku-Mu'inh" }, + { "xmq", "Kuku-Mangk" }, + { "xmr", "Meroitic" }, + { "xms", "Moroccan Sign Language" }, + { "xmt", "Matbat" }, + { "xmu", "Kamu" }, + { "xmv", "Antankarana Malagasy" }, + { "xmw", "Tsimihety Malagasy" }, + { "xmx", "Maden" }, + { "xmy", "Mayaguduna" }, + { "xmz", "Mori Bawah" }, + { "xna", "Ancient North Arabian" }, + { "xnb", "Kanakanabu" }, + { "xng", "Middle Mongolian" }, + { "xnh", "Kuanhua" }, + { "xni", "Ngarigu" }, + { "xnk", "Nganakarti" }, + { "xnn", "Northern Kankanay" }, + { "xno", "Anglo-Norman" }, + { "xnr", "Kangri" }, + { "xns", "Kanashi" }, + { "xnt", "Narragansett" }, + { "xnu", "Nukunul" }, + { "xny", "Nyiyaparli" }, + { "xnz", "Kenzi" }, + { "xoc", "O'chi'chi'" }, + { "xod", "Kokoda" }, + { "xog", "Soga" }, + { "xoi", "Kominimung" }, + { "xok", "Xokleng" }, + { "xom", "Komo (Sudan)" }, + { "xon", "Konkomba" }, + { "xoo", "Xukurú" }, + { "xop", "Kopar" }, + { "xor", "Korubo" }, + { "xow", "Kowaki" }, + { "xpa", "Pirriya" }, + { "xpc", "Pecheneg" }, + { "xpe", "Liberia Kpelle" }, + { "xpg", "Phrygian" }, + { "xpi", "Pictish" }, + { "xpj", "Mpalitjanh" }, + { "xpk", "Kulina Pano" }, + { "xpm", "Pumpokol" }, + { "xpn", "Kapinawá" }, + { "xpo", "Pochutec" }, + { "xpp", "Puyo-Paekche" }, + { "xpq", "Mohegan-Pequot" }, + { "xpr", "Parthian" }, + { "xps", "Pisidian" }, + { "xpt", "Punthamara" }, + { "xpu", "Punic" }, + { "xpy", "Puyo" }, + { "xqa", "Karakhanid" }, + { "xqt", "Qatabanian" }, + { "xra", "Krahô" }, + { "xrb", "Eastern Karaboro" }, + { "xrd", "Gundungurra" }, + { "xre", "Kreye" }, + { "xrg", "Minang" }, + { "xri", "Krikati-Timbira" }, + { "xrm", "Armazic" }, + { "xrn", "Arin" }, + { "xrq", "Karranga" }, + { "xrr", "Raetic" }, + { "xrt", "Aranama-Tamique" }, + { "xru", "Marriammu" }, + { "xrw", "Karawa" }, + { "xsa", "Sabaean" }, + { "xsb", "Sambal" }, + { "xsc", "Scythian" }, + { "xsd", "Sidetic" }, + { "xse", "Sempan" }, + { "xsh", "Shamang" }, + { "xsi", "Sio" }, + { "xsj", "Subi" }, + { "xsl", "South Slavey" }, + { "xsm", "Kasem" }, + { "xsn", "Sanga (Nigeria)" }, + { "xso", "Solano" }, + { "xsp", "Silopi" }, + { "xsq", "Makhuwa-Saka" }, + { "xsr", "Sherpa" }, + { "xss", "Assan" }, + { "xsu", "Sanumá" }, + { "xsv", "Sudovian" }, + { "xsy", "Saisiyat" }, + { "xta", "Alcozauca Mixtec" }, + { "xtb", "Chazumba Mixtec" }, + { "xtc", "Katcha-Kadugli-Miri" }, + { "xtd", "Diuxi-Tilantongo Mixtec" }, + { "xte", "Ketengban" }, + { "xtg", "Transalpine Gaulish" }, + { "xth", "Yitha Yitha" }, + { "xti", "Sinicahua Mixtec" }, + { "xtj", "San Juan Teita Mixtec" }, + { "xtl", "Tijaltepec Mixtec" }, + { "xtm", "Magdalena Peñasco Mixtec" }, + { "xtn", "Northern Tlaxiaco Mixtec" }, + { "xto", "Tokharian A" }, + { "xtp", "San Miguel Piedras Mixtec" }, + { "xtq", "Tumshuqese" }, + { "xtr", "Early Tripuri" }, + { "xts", "Sindihui Mixtec" }, + { "xtt", "Tacahua Mixtec" }, + { "xtu", "Cuyamecalco Mixtec" }, + { "xtv", "Thawa" }, + { "xtw", "Tawandê" }, + { "xty", "Yoloxochitl Mixtec" }, + { "xtz", "Tasmanian" }, + { "xua", "Alu Kurumba" }, + { "xub", "Betta Kurumba" }, + { "xud", "Umiida" }, + { "xug", "Kunigami" }, + { "xuj", "Jennu Kurumba" }, + { "xul", "Ngunawal" }, + { "xum", "Umbrian" }, + { "xun", "Unggaranggu" }, + { "xuo", "Kuo" }, + { "xup", "Upper Umpqua" }, + { "xur", "Urartian" }, + { "xut", "Kuthant" }, + { "xuu", "Kxoe" }, + { "xve", "Venetic" }, + { "xvi", "Kamviri" }, + { "xvn", "Vandalic" }, + { "xvo", "Volscian" }, + { "xvs", "Vestinian" }, + { "xwa", "Kwaza" }, + { "xwc", "Woccon" }, + { "xwd", "Wadi Wadi" }, + { "xwe", "Xwela Gbe" }, + { "xwg", "Kwegu" }, + { "xwj", "Wajuk" }, + { "xwk", "Wangkumara" }, + { "xwl", "Western Xwla Gbe" }, + { "xwo", "Written Oirat" }, + { "xwr", "Kwerba Mamberamo" }, + { "xwt", "Wotjobaluk" }, + { "xww", "Wemba Wemba" }, + { "xxb", "Boro (Ghana)" }, + { "xxk", "Ke'o" }, + { "xxm", "Minkin" }, + { "xxr", "Koropó" }, + { "xxt", "Tambora" }, + { "xya", "Yaygir" }, + { "xyb", "Yandjibara" }, + { "xyj", "Mayi-Yapi" }, + { "xyk", "Mayi-Kulan" }, + { "xyl", "Yalakalore" }, + { "xyt", "Mayi-Thakurti" }, + { "xyy", "Yorta Yorta" }, + { "xzh", "Zhang-Zhung" }, + { "xzm", "Zemgalian" }, + { "xzp", "Ancient Zapotec" }, + { "yaa", "Yaminahua" }, + { "yab", "Yuhup" }, + { "yac", "Pass Valley Yali" }, + { "yad", "Yagua" }, + { "yae", "Pumé" }, + { "yaf", "Yaka (Democratic Republic of Congo)" }, + { "yag", "Yámana" }, + { "yah", "Yazgulyam" }, + { "yai", "Yagnobi" }, + { "yaj", "Banda-Yangere" }, + { "yak", "Yakama" }, + { "yal", "Yalunka" }, + { "yam", "Yamba" }, + { "yan", "Mayangna" }, + { "yao", "Yao" }, + { "yap", "Yapese" }, + { "yaq", "Yaqui" }, + { "yar", "Yabarana" }, + { "yas", "Nugunu (Cameroon)" }, + { "yat", "Yambeta" }, + { "yau", "Yuwana" }, + { "yav", "Yangben" }, + { "yaw", "Yawalapití" }, + { "yax", "Yauma" }, + { "yay", "Agwagwune" }, + { "yaz", "Lokaa" }, + { "yba", "Yala" }, + { "ybb", "Yemba" }, + { "ybe", "West Yugur" }, + { "ybh", "Yakha" }, + { "ybi", "Yamphu" }, + { "ybj", "Hasha" }, + { "ybk", "Bokha" }, + { "ybl", "Yukuben" }, + { "ybm", "Yaben" }, + { "ybn", "Yabaâna" }, + { "ybo", "Yabong" }, + { "ybx", "Yawiyo" }, + { "yby", "Yaweyuha" }, + { "ych", "Chesu" }, + { "ycl", "Lolopo" }, + { "ycn", "Yucuna" }, + { "ycp", "Chepya" }, + { "yda", "Yanda" }, + { "ydd", "Eastern Yiddish" }, + { "yde", "Yangum Dey" }, + { "ydg", "Yidgha" }, + { "ydk", "Yoidik" }, + { "yds", "Yiddish Sign Language" }, + { "yea", "Ravula" }, + { "yec", "Yeniche" }, + { "yee", "Yimas" }, + { "yei", "Yeni" }, + { "yej", "Yevanic" }, + { "yel", "Yela" }, + { "yer", "Tarok" }, + { "yes", "Nyankpa" }, + { "yet", "Yetfa" }, + { "yeu", "Yerukula" }, + { "yev", "Yapunda" }, + { "yey", "Yeyi" }, + { "yga", "Malyangapa" }, + { "ygi", "Yiningayi" }, + { "ygl", "Yangum Gel" }, + { "ygm", "Yagomi" }, + { "ygp", "Gepo" }, + { "ygr", "Yagaria" }, + { "ygu", "Yugul" }, + { "ygw", "Yagwoia" }, + { "yha", "Baha Buyang" }, + { "yhd", "Judeo-Iraqi Arabic" }, + { "yhl", "Hlepho Phowa" }, + { "yia", "Yinggarda" }, + { "yid", "Yiddish" }, + { "yif", "Ache" }, + { "yig", "Wusa Nasu" }, + { "yih", "Western Yiddish" }, + { "yii", "Yidiny" }, + { "yij", "Yindjibarndi" }, + { "yik", "Dongshanba Lalo" }, + { "yil", "Yindjilandji" }, + { "yim", "Yimchungru Naga" }, + { "yin", "Yinchia" }, + { "yip", "Pholo" }, + { "yiq", "Miqie" }, + { "yir", "North Awyu" }, + { "yis", "Yis" }, + { "yit", "Eastern Lalu" }, + { "yiu", "Awu" }, + { "yiv", "Northern Nisu" }, + { "yix", "Axi Yi" }, + { "yiz", "Azhe" }, + { "yka", "Yakan" }, + { "ykg", "Northern Yukaghir" }, + { "yki", "Yoke" }, + { "ykk", "Yakaikeke" }, + { "ykl", "Khlula" }, + { "ykm", "Kap" }, + { "ykn", "Kua-nsi" }, + { "yko", "Yasa" }, + { "ykr", "Yekora" }, + { "ykt", "Kathu" }, + { "yku", "Kuamasi" }, + { "yky", "Yakoma" }, + { "yla", "Yaul" }, + { "ylb", "Yaleba" }, + { "yle", "Yele" }, + { "ylg", "Yelogu" }, + { "yli", "Angguruk Yali" }, + { "yll", "Yil" }, + { "ylm", "Limi" }, + { "yln", "Langnian Buyang" }, + { "ylo", "Naluo Yi" }, + { "ylr", "Yalarnnga" }, + { "ylu", "Aribwaung" }, + { "yly", "Nyâlayu" }, + { "ymb", "Yambes" }, + { "ymc", "Southern Muji" }, + { "ymd", "Muda" }, + { "yme", "Yameo" }, + { "ymg", "Yamongeri" }, + { "ymh", "Mili" }, + { "ymi", "Moji" }, + { "ymk", "Makwe" }, + { "yml", "Iamalele" }, + { "ymm", "Maay" }, + { "ymn", "Yamna" }, + { "ymo", "Yangum Mon" }, + { "ymp", "Yamap" }, + { "ymq", "Qila Muji" }, + { "ymr", "Malasar" }, + { "yms", "Mysian" }, + { "ymt", "Mator-Taygi-Karagas" }, + { "ymx", "Northern Muji" }, + { "ymz", "Muzi" }, + { "yna", "Aluo" }, + { "ynd", "Yandruwandha" }, + { "yne", "Lang'e" }, + { "yng", "Yango" }, + { "ynh", "Yangho" }, + { "ynk", "Naukan Yupik" }, + { "ynl", "Yangulam" }, + { "ynn", "Yana" }, + { "yno", "Yong" }, + { "ynq", "Yendang" }, + { "yns", "Yansi" }, + { "ynu", "Yahuna" }, + { "yob", "Yoba" }, + { "yog", "Yogad" }, + { "yoi", "Yonaguni" }, + { "yok", "Yokuts" }, + { "yol", "Yola" }, + { "yom", "Yombe" }, + { "yon", "Yongkom" }, + { "yor", "Yoruba" }, + { "yot", "Yotti" }, + { "yox", "Yoron" }, + { "yoy", "Yoy" }, + { "ypa", "Phala" }, + { "ypb", "Labo Phowa" }, + { "ypg", "Phola" }, + { "yph", "Phupha" }, + { "ypm", "Phuma" }, + { "ypn", "Ani Phowa" }, + { "ypo", "Alo Phola" }, + { "ypp", "Phupa" }, + { "ypz", "Phuza" }, + { "yra", "Yerakai" }, + { "yrb", "Yareba" }, + { "yre", "Yaouré" }, + { "yri", "Yarí" }, + { "yrk", "Nenets" }, + { "yrl", "Nhengatu" }, + { "yrm", "Yirrk-Mel" }, + { "yrn", "Yerong" }, + { "yrs", "Yarsun" }, + { "yrw", "Yarawata" }, + { "yry", "Yarluyandi" }, + { "ysc", "Yassic" }, + { "ysd", "Samatao" }, + { "ysg", "Sonaga" }, + { "ysl", "Yugoslavian Sign Language" }, + { "ysn", "Sani" }, + { "yso", "Nisi (China)" }, + { "ysp", "Southern Lolopo" }, + { "ysr", "Sirenik Yupik" }, + { "yss", "Yessan-Mayo" }, + { "ysy", "Sanie" }, + { "yta", "Talu" }, + { "ytl", "Tanglang" }, + { "ytp", "Thopho" }, + { "ytw", "Yout Wam" }, + { "yty", "Yatay" }, + { "yua", "Yucateco" }, + { "yub", "Yugambal" }, + { "yuc", "Yuchi" }, + { "yud", "Judeo-Tripolitanian Arabic" }, + { "yue", "Yue Chinese" }, + { "yuf", "Havasupai-Walapai-Yavapai" }, + { "yug", "Yug" }, + { "yui", "Yurutí" }, + { "yuj", "Karkar-Yuri" }, + { "yuk", "Yuki" }, + { "yul", "Yulu" }, + { "yum", "Quechan" }, + { "yun", "Bena (Nigeria)" }, + { "yup", "Yukpa" }, + { "yuq", "Yuqui" }, + { "yur", "Yurok" }, + { "yut", "Yopno" }, + { "yuu", "Yugh" }, + { "yuw", "Yau (Morobe Province)" }, + { "yux", "Southern Yukaghir" }, + { "yuy", "East Yugur" }, + { "yuz", "Yuracare" }, + { "yva", "Yawa" }, + { "yvt", "Yavitero" }, + { "ywa", "Kalou" }, + { "ywg", "Yinhawangka" }, + { "ywl", "Western Lalu" }, + { "ywn", "Yawanawa" }, + { "ywq", "Wuding-Luquan Yi" }, + { "ywr", "Yawuru" }, + { "ywt", "Xishanba Lalo" }, + { "ywu", "Wumeng Nasu" }, + { "yww", "Yawarawarga" }, + { "yxa", "Mayawali" }, + { "yxg", "Yagara" }, + { "yxl", "Yardliyawarra" }, + { "yxm", "Yinwum" }, + { "yxu", "Yuyu" }, + { "yxy", "Yabula Yabula" }, + { "yyr", "Yir Yoront" }, + { "yyu", "Yau (Sandaun Province)" }, + { "yyz", "Ayizi" }, + { "yzg", "E'ma Buyang" }, + { "yzk", "Zokhuo" }, + { "zaa", "Sierra de Juárez Zapotec" }, + { "zab", "San Juan Guelavía Zapotec" }, + { "zac", "Ocotlán Zapotec" }, + { "zad", "Cajonos Zapotec" }, + { "zae", "Yareni Zapotec" }, + { "zaf", "Ayoquesco Zapotec" }, + { "zag", "Zaghawa" }, + { "zah", "Zangwal" }, + { "zai", "Isthmus Zapotec" }, + { "zaj", "Zaramo" }, + { "zak", "Zanaki" }, + { "zal", "Zauzou" }, + { "zam", "Miahuatlán Zapotec" }, + { "zao", "Ozolotepec Zapotec" }, + { "zap", "Zapotec" }, + { "zaq", "Aloápam Zapotec" }, + { "zar", "Rincón Zapotec" }, + { "zas", "Santo Domingo Albarradas Zapotec" }, + { "zat", "Tabaa Zapotec" }, + { "zau", "Zangskari" }, + { "zav", "Yatzachi Zapotec" }, + { "zaw", "Mitla Zapotec" }, + { "zax", "Xadani Zapotec" }, + { "zay", "Zayse-Zergulla" }, + { "zaz", "Zari" }, + { "zbc", "Central Berawan" }, + { "zbe", "East Berawan" }, + { "zbl", "Blissymbols" }, + { "zbt", "Batui" }, + { "zbw", "West Berawan" }, + { "zca", "Coatecas Altas Zapotec" }, + { "zch", "Central Hongshuihe Zhuang" }, + { "zdj", "Ngazidja Comorian" }, + { "zea", "Zeeuws" }, + { "zeg", "Zenag" }, + { "zeh", "Eastern Hongshuihe Zhuang" }, + { "zen", "Zenaga" }, + { "zga", "Kinga" }, + { "zgb", "Guibei Zhuang" }, + { "zgh", "Standard Moroccan Tamazight" }, + { "zgm", "Minz Zhuang" }, + { "zgn", "Guibian Zhuang" }, + { "zgr", "Magori" }, + { "zha", "Zhuang" }, + { "zhb", "Zhaba" }, + { "zhd", "Dai Zhuang" }, + { "zhi", "Zhire" }, + { "zhn", "Nong Zhuang" }, + { "zho", "Chinese" }, + { "zhw", "Zhoa" }, + { "zia", "Zia" }, + { "zib", "Zimbabwe Sign Language" }, + { "zik", "Zimakani" }, + { "zil", "Zialo" }, + { "zim", "Mesme" }, + { "zin", "Zinza" }, + { "zir", "Ziriya" }, + { "ziw", "Zigula" }, + { "ziz", "Zizilivakan" }, + { "zka", "Kaimbulawa" }, + { "zkb", "Koibal" }, + { "zkd", "Kadu" }, + { "zkg", "Koguryo" }, + { "zkh", "Khorezmian" }, + { "zkk", "Karankawa" }, + { "zkn", "Kanan" }, + { "zko", "Kott" }, + { "zkp", "São Paulo Kaingáng" }, + { "zkr", "Zakhring" }, + { "zkt", "Kitan" }, + { "zku", "Kaurna" }, + { "zkv", "Krevinian" }, + { "zkz", "Khazar" }, + { "zlj", "Liujiang Zhuang" }, + { "zlm", "Malay (individual language)" }, + { "zln", "Lianshan Zhuang" }, + { "zlq", "Liuqian Zhuang" }, + { "zma", "Manda (Australia)" }, + { "zmb", "Zimba" }, + { "zmc", "Margany" }, + { "zmd", "Maridan" }, + { "zme", "Mangerr" }, + { "zmf", "Mfinu" }, + { "zmg", "Marti Ke" }, + { "zmh", "Makolkol" }, + { "zmi", "Negeri Sembilan Malay" }, + { "zmj", "Maridjabin" }, + { "zmk", "Mandandanyi" }, + { "zml", "Madngele" }, + { "zmm", "Marimanindji" }, + { "zmn", "Mbangwe" }, + { "zmo", "Molo" }, + { "zmp", "Mpuono" }, + { "zmq", "Mituku" }, + { "zmr", "Maranunggu" }, + { "zms", "Mbesa" }, + { "zmt", "Maringarr" }, + { "zmu", "Muruwari" }, + { "zmv", "Mbariman-Gudhinma" }, + { "zmw", "Mbo (Democratic Republic of Congo)" }, + { "zmx", "Bomitaba" }, + { "zmy", "Mariyedi" }, + { "zmz", "Mbandja" }, + { "zna", "Zan Gula" }, + { "zne", "Zande (individual language)" }, + { "zng", "Mang" }, + { "znk", "Manangkari" }, + { "zns", "Mangas" }, + { "zoc", "Copainalá Zoque" }, + { "zoh", "Chimalapa Zoque" }, + { "zom", "Zou" }, + { "zoo", "Asunción Mixtepec Zapotec" }, + { "zoq", "Tabasco Zoque" }, + { "zor", "Rayón Zoque" }, + { "zos", "Francisco León Zoque" }, + { "zpa", "Lachiguiri Zapotec" }, + { "zpb", "Yautepec Zapotec" }, + { "zpc", "Choapan Zapotec" }, + { "zpd", "Southeastern Ixtlán Zapotec" }, + { "zpe", "Petapa Zapotec" }, + { "zpf", "San Pedro Quiatoni Zapotec" }, + { "zpg", "Guevea De Humboldt Zapotec" }, + { "zph", "Totomachapan Zapotec" }, + { "zpi", "Santa María Quiegolani Zapotec" }, + { "zpj", "Quiavicuzas Zapotec" }, + { "zpk", "Tlacolulita Zapotec" }, + { "zpl", "Lachixío Zapotec" }, + { "zpm", "Mixtepec Zapotec" }, + { "zpn", "Santa Inés Yatzechi Zapotec" }, + { "zpo", "Amatlán Zapotec" }, + { "zpp", "El Alto Zapotec" }, + { "zpq", "Zoogocho Zapotec" }, + { "zpr", "Santiago Xanica Zapotec" }, + { "zps", "Coatlán Zapotec" }, + { "zpt", "San Vicente Coatlán Zapotec" }, + { "zpu", "Yalálag Zapotec" }, + { "zpv", "Chichicapan Zapotec" }, + { "zpw", "Zaniza Zapotec" }, + { "zpx", "San Baltazar Loxicha Zapotec" }, + { "zpy", "Mazaltepec Zapotec" }, + { "zpz", "Texmelucan Zapotec" }, + { "zqe", "Qiubei Zhuang" }, + { "zra", "Kara (Korea)" }, + { "zrg", "Mirgan" }, + { "zrn", "Zerenkel" }, + { "zro", "Záparo" }, + { "zrp", "Zarphatic" }, + { "zrs", "Mairasi" }, + { "zsa", "Sarasira" }, + { "zsk", "Kaskean" }, + { "zsl", "Zambian Sign Language" }, + { "zsm", "Standard Malay" }, + { "zsr", "Southern Rincon Zapotec" }, + { "zsu", "Sukurum" }, + { "zte", "Elotepec Zapotec" }, + { "ztg", "Xanaguía Zapotec" }, + { "ztl", "Lapaguía-Guivini Zapotec" }, + { "ztm", "San Agustín Mixtepec Zapotec" }, + { "ztn", "Santa Catarina Albarradas Zapotec" }, + { "ztp", "Loxicha Zapotec" }, + { "ztq", "Quioquitani-Quierí Zapotec" }, + { "zts", "Tilquiapan Zapotec" }, + { "ztt", "Tejalapan Zapotec" }, + { "ztu", "Güilá Zapotec" }, + { "ztx", "Zaachila Zapotec" }, + { "zty", "Yatee Zapotec" }, + { "zua", "Zeem" }, + { "zuh", "Tokano" }, + { "zul", "Zulu" }, + { "zum", "Kumzari" }, + { "zun", "Zuni" }, + { "zuy", "Zumaya" }, + { "zwa", "Zay" }, + { "zxx", "No linguistic content" }, + { "zyb", "Yongbei Zhuang" }, + { "zyg", "Yang Zhuang" }, + { "zyj", "Youjiang Zhuang" }, + { "zyn", "Yongnan Zhuang" }, + { "zyp", "Zyphe Chin" }, + { "zza", "Zaza" }, + { "zzj", "Zuojiang Zhuang" }, +}; +static int niso639_3= sizeof( iso639_3 ) / sizeof( iso639_3[0] ); + +char * +iso639_3_from_code( const char *code ) +{ + int i; + for ( i=0; istr = NULL; a->max = 0; a->n = 0; - a->sorted = 0; + a->sorted = 1; } void @@ -66,27 +66,71 @@ return 1; } -/* - * return pointer to newstr 'n', list_getstr() is deprecated - */ +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_get( list *a, int n ) +list_set( list *a, int n, newstr *s ) { if ( !list_valid_num( a, n ) ) return NULL; - else return &(a->str[n]); + newstr_newstrcpy( &(a->str[n]), s ); + return list_set_cleanup( a, n ); } + newstr * -list_getstr( list *a, int n ) +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', list_getstr_char() is deprecated + * return pointer to C string 'n' * - * Ensure that a pointer is returned even if the newstr doesn't - * point to data. Thus we can convert loops like: + * 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 ); @@ -113,23 +157,18 @@ if ( p ) return p; else return empty; } -char * -list_getstr_char( list *a, int n ) -{ - return list_getc( a, n ); -} static int list_alloc( list *a ) { int i, alloc = 20; a->str = ( newstr* ) malloc( sizeof( newstr ) * alloc ); - if ( !(a->str) ) return 0; + if ( !(a->str) ) return LIST_ERR; a->max = alloc; a->n = 0; for ( i=0; istr[i]) ); - return 1; + return LIST_OK; } static int @@ -138,94 +177,122 @@ newstr *more; int i, alloc = a->max * 2; more = ( newstr* ) realloc( a->str, sizeof( newstr ) * alloc ); - if ( !more ) return 0; + if ( !more ) return LIST_ERR; a->str = more; for ( i=a->max; istr[i]) ); a->max = alloc; - return 1; + return LIST_OK; } + static int list_ensure_space( list *a ) { - int ok = 1; - if ( a->max==0 ) ok = list_alloc( a ); - else if ( a->n >= a->max ) ok = list_realloc( a ); - return ok; + 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, void *vp, unsigned char mode ) +list_addvp( list *a, unsigned char mode, void *vp ) { newstr *s = NULL; - int ok; - ok = list_ensure_space( a ); - if ( ok ) { + int status; + status = list_ensure_space( a ); + if ( status==LIST_OK ) { s = &( a->str[a->n] ); if ( mode==LIST_CHR ) - newstr_strcpy( s, (char*) vp ); + newstr_strcpy( s, (const char*) vp ); else if ( mode==LIST_STR ) newstr_newstrcpy( s, (newstr*) vp ); else return NULL; - a->sorted = 0; + 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_add( list *a, char *s ) +list_addc( list *a, const char *s ) { - return list_addvp( a, (void*)s, LIST_CHR ); + return list_addvp( a, LIST_CHR, (void*)s ); } newstr * -list_addstr( list *a, newstr *s ) +list_add( list *a, newstr *s ) { - return list_addvp( a, (void*)s, LIST_STR ); + return list_addvp( a, LIST_STR, (void*)s ); } newstr * -list_addvp_unique( list *a, void *vp, unsigned char mode ) +list_addvp_unique( list *a, unsigned char mode, void *vp ) { newstr *s; int n; if ( mode==LIST_CHR ) - n = list_find( a, (char*) vp ); + 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, vp, mode ); + else { + s = list_addvp( a, mode, vp ); + } return s; } newstr * -list_add_unique( list *a, char *s ) +list_addc_unique( list *a, const char *s ) { - return list_addvp_unique( a, (void*) s, LIST_CHR ); + return list_addvp_unique( a, LIST_CHR, (void*)s ); } newstr * -list_addstr_unique( list *a, newstr *s ) +list_add_unique( list *a, newstr *s ) { - return list_addvp_unique( a, (void*) s, LIST_STR ); + return list_addvp_unique( a, LIST_STR, (void*)s ); } int -list_adds( list *a, ... ) +list_addvp_all( list *a, unsigned char mode, ... ) { - int ret = 1; + int ret = LIST_OK; va_list ap; newstr *s; - char *v; + 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, char * ); + v = va_arg( ap, newstr * ); if ( v ) { - s = list_addvp( a, (void*) v, LIST_CHR ); - if ( s==NULL ) { ret = 0; goto out; } + s = list_addvp( a, LIST_STR, (void*)v ); + if ( s==NULL ) { ret = LIST_ERR; goto out; } } } while ( v ); out: @@ -233,43 +300,67 @@ return ret; } -void +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 ) { - list_addstr( a, &(toadd->str[i]) ); + s = list_add( a, &(toadd->str[i]) ); + if ( !s ) return LIST_ERR; } + return LIST_OK; } -void +int list_append_unique( list *a, list *toadd ) { + newstr *s; int i; for ( i=0; in; ++i ) { - list_addstr_unique( a, &(toadd->str[i]) ); + s = list_add_unique( a, &(toadd->str[i]) ); + if ( !s ) return LIST_ERR; } + return LIST_OK; } -void +int list_remove( list *a, int n ) { int i; - if ( !list_valid_num( a, n ) ) return; - for ( i=n+1; in; ++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; } -static int -list_comp( const void *v1, const void *v2 ) +void +list_swap( list *a, int n1, int n2 ) { - 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 ); + newstr_swapstrings( &(a->str[n1]), &(a->str[n2]) ); } void @@ -280,11 +371,10 @@ } static int -list_find_sorted( list *a, char *searchstr ) +list_find_sorted( list *a, const char *searchstr ) { int min, max, mid, comp; newstr s, *cs; - if ( a->n==0 ) return -1; newstr_init( &s ); newstr_strcpy( &s, searchstr ); min = 0; @@ -293,7 +383,10 @@ mid = ( min + max ) / 2; cs = list_get( a, mid ); comp = list_comp( (void*)cs, (void*) (&s) ); - if ( comp==0 ) return mid; + if ( comp==0 ) { + newstr_free( &s ); + return mid; + } else if ( comp > 0 ) max = mid - 1; else if ( comp < 0 ) min = mid + 1; } @@ -302,7 +395,7 @@ } static int -list_find_simple( list *a, char *searchstr, int nocase ) +list_find_simple( list *a, const char *searchstr, int nocase ) { int i; if ( nocase ) { @@ -311,15 +404,16 @@ return i; } else { for ( i=0; in; ++i ) - if ( !strcmp(a->str[i].data,searchstr) ) + if ( !strcmp(a->str[i].data,searchstr) ) return i; } return -1; } int -list_find( list *a, char *searchstr ) +list_find( list *a, const char *searchstr ) { + if ( a->n==0 ) return -1; if ( a->sorted ) return list_find_sorted( a, searchstr ); else @@ -327,86 +421,90 @@ } int -list_findnocase( list *a, char *searchstr ) +list_findnocase( list *a, const char *searchstr ) { return list_find_simple( a, searchstr, 1 ); } -/* Return the index of searched-for string. - * If cannot find string, add to list and then - * return the index - */ int -list_find_or_add( list *a, char *searchstr ) -{ - int n = list_find( a, searchstr ); - if ( n==-1 ) { - list_add( a, searchstr ); - n = a->n - 1; - } - return n; -} - -void -list_fillfp( list *a, FILE *fp ) +list_fillfp( list *a, FILE *fp, unsigned char skip_blank_lines ) { + int bufpos = 0, ret = LIST_OK; + char buf[512]=""; newstr line; - char *p, buf[512]=""; - int bufpos = 0; - list_init( a ); + list_empty( a ); newstr_init( &line ); while ( newstr_fget( fp, buf, sizeof(buf), &bufpos, &line ) ) { - p = &(line.data[0]); - if ( *p=='\0' ) continue; - if ( !list_add( a, line.data ) ) return; + 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, char *filename ) +list_fill( list *a, const char *filename, unsigned char skip_blank_lines ) { - FILE *fp = fopen( filename, "r" ); - if ( !fp ) return 0; - list_fillfp( a, fp ); + 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 1; + + return ret; } -void +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 ) return; - to->n = to->max = from->n; - for ( i=0; in; ++i ) { + 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]) ); - newstr_strcpy( &(to->str[i]), from->str[i].data ); + + 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 *aold ) +list_dup( list *from ) { - list *anew; - int i; - anew = ( list* ) malloc( sizeof( list ) ); - if ( !anew ) goto err0; - anew->str = ( newstr* ) malloc( sizeof( newstr ) * aold->n ); - if ( !anew->str ) goto err1; - anew->n = anew->max = aold->n; - for ( i=0; in; ++i ) { - newstr_init( &(anew->str[i]) ); - newstr_strcpy( &(anew->str[i]), aold->str[i].data ); + list *to; + int ok; + + to = list_new(); + if ( to ) { + ok = list_copy( to, from ); + if ( !ok ) { + list_delete( to ); + to = NULL; + } } - return anew; -err1: - free( anew ); -err0: - return NULL; + + return to; } int @@ -431,44 +529,38 @@ } } -void -list_tokenize( list *tokens, newstr *in, char delim, int merge_delim ) +int +list_tokenizec( list *tokens, char *p, const char *delim, int merge_delim ) { - newstr s; - char *p; + int ret = LIST_OK; + newstr s, *t; + char *q; list_empty( tokens ); - p = in->data; newstr_init( &s ); while ( p && *p ) { - while ( *p && *p!=delim ) newstr_addchar( &s, *p++ ); - if ( s.len ) list_add( tokens, s.data ); - else if ( !merge_delim ) list_add( tokens, "" ); - newstr_empty( &s ); - if ( *p==delim ) 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; } -void -list_newstrtok( list *t, newstr *s, char *sep ) +int +list_tokenize( list *tokens, newstr *in, const char *delim, int merge_delim ) { - newstr tmp; - char *p; - list_empty( t ); - if ( !s->len ) return; - newstr_init( &tmp ); - p = s->data; - while ( *p ) { - if ( strchr( sep, *p ) ) { - if ( tmp.len ) { - list_add( t, tmp.data ); - newstr_empty( &tmp ); - } - } else newstr_addchar( &tmp, *p ); - p++; - } - if ( tmp.len ) list_add( t, tmp.data ); - newstr_free( &tmp ); + return list_tokenizec( tokens, in->data, delim, merge_delim ); } void diff --git a/bibutils/list.h b/bibutils/list.h --- a/bibutils/list.h +++ b/bibutils/list.h @@ -1,9 +1,9 @@ /* * list.h * - * version: 2013-04-02 + * version: 2014-11-15 * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Source code released under the GPL version 2 * @@ -18,13 +18,17 @@ #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; - int sorted; newstr *str; + unsigned char sorted; } list; @@ -41,40 +45,43 @@ extern void list_delete( list * ); extern list* list_dup( list *a ); -extern void list_copy( list *to, list *from ); +extern int list_copy( list *to, list *from ); -extern newstr * list_add( list *a, char *value ); -extern newstr * list_addstr( list *a, newstr *value ); -extern newstr * list_addvp( list *a, void *vp, unsigned char mode ); +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_adds( list *a, ... ); +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_add_unique( list *a, char *value ); -extern newstr * list_addstr_unique( list *a, newstr *value ); -extern newstr * list_addvp_unique( list *a, void *vp, unsigned char mode ); +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 void list_append( list *a, list *toadd ); -extern void list_append_unique( list *a, list *toadd ); +extern int list_append( list *a, list *toadd ); +extern int list_append_unique( list *a, list *toadd ); -extern void list_remove( list *a, int n ); +extern int list_remove( list *a, int n ); extern newstr* list_get( list *a, int n ); -extern newstr* list_getstr( list *a, int n ); extern char* list_getc( list *a, int n ); -extern char* list_getstr_char( 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 int list_find( list *a, char *searchstr ); -extern int list_findnocase( list *a, char *searchstr ); -extern int list_find_or_add( list *a, char *searchstr ); +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, char *filename ); -extern void list_fillfp( list *a, FILE *fp ); -extern void list_tokenize( list *tokens, newstr *in, char delim, int merge_delim ); -extern void list_newstrtok( list *t, newstr *s, char *sep ); - +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 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Source code released under the GPL version 2 * @@ -22,8 +22,10 @@ "bibliography", "biography", "book", + "calendar", "catalog", "chart", + "comic or graphic novel", "comic strip", "conference publication", "database", @@ -49,9 +51,12 @@ "handbook", "history", "humor, satire", + "hymnal", "index", "instruction", "interview", + "issue", + "journal", "kit", "language instruction", "law report or digest", @@ -86,6 +91,7 @@ "slide", "sound", "speech", + "standard or specification", "statistics", "survey of literature", "technical drawing", @@ -95,7 +101,8 @@ "transparency", "treaty", "videorecording", - "web site" + "web site", + "yearbook", }; int nmarc = sizeof( marc ) / sizeof( char* ); int i; @@ -110,11 +117,14 @@ { char *marc[] = { "cartographic", + "kit", "mixed material", "moving image", "notated music", "software, multimedia", "sound recording", + "sound recording - musical", + "sound recording - nonmusical", "still image", "text", "three dimensional object" 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 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Source code released under the GPL version 2 * @@ -18,6 +18,9 @@ #include "iso639_2.h" #include "bibutils.h" +/***************************************************** + PUBLIC: void medin_initparams() +*****************************************************/ void medin_initparams( param *p, const char *progname ) { @@ -48,6 +51,10 @@ else p->progname = strdup( progname ); } +/***************************************************** + PUBLIC: int medin_readf() +*****************************************************/ + /* * The only difference between MEDLINE and PUBMED in format is * that the entire library is wrapped in @@ -108,25 +115,9 @@ return haveref; } -static inline int -xml_hasdata( xml *node ) -{ - if ( node && node->value && node->value->data ) return 1; - return 0; -} - -static inline char * -xml_data( xml *node ) -{ - return node->value->data; -} - -static inline int -xml_tagwithdata( xml *node, char *tag ) -{ - if ( !xml_hasdata( node ) ) return 0; - return xml_tagexact( node, tag ); -} +/***************************************************** + PUBLIC: int medin_processf() +*****************************************************/ typedef struct xml_convert { char *in; /* The input tag */ @@ -136,75 +127,79 @@ } xml_convert; static int -medin_doconvert( xml *node, fields *info, xml_convert *c, int nc ) +medin_doconvert( xml *node, fields *info, xml_convert *c, int nc, int *found ) { - int i, found = 0; + int i, fstatus; char *d; - if ( !xml_hasdata( node ) ) return 0; + *found = 0; + if ( !xml_hasdata( node ) ) return BIBL_OK; d = xml_data( node ); - for ( i=0; iMechanism and..... */ -static void +static int medin_articletitle( xml *node, fields *info ) { - if ( xml_hasdata( node ) ) - fields_add( info, "TITLE", xml_data( node ), 0 ); + int fstatus, status = BIBL_OK; + if ( xml_hasdata( node ) ) { + fstatus = fields_add( info, "TITLE", xml_data( node ), 0 ); + if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; + } + return status; } /* 2003 Jan-Feb */ -static void -medin_medlinedate( fields *info, char *string, int level ) +static int +medin_medlinedate( fields *info, char *p, int level ) { + int fstatus; newstr tmp; - char *p, *q; newstr_init( &tmp ); - /* extract year */ - p = string; - q = skip_notws( string ); - newstr_segcpy( &tmp, p, q ); - fields_add( info, "PARTYEAR", tmp.data, level ); - q = skip_ws( q ); + 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, "PARTYEAR", tmp.data, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } - /* extract month */ - if ( q ) { - p = q; - newstr_empty( &tmp ); - q = skip_notws( q ); - newstr_segcpy( &tmp, p, q ); + 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, "-", "/" ); - fields_add( info, "PARTMONTH", tmp.data, level ); - q = skip_ws( q ); + fstatus = fields_add( info, "PARTMONTH", tmp.data, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - /* extract day */ - if ( q ) { - p = q; - newstr_empty( &tmp ); - q = skip_notws( q ); - newstr_segcpy( &tmp, p, q ); - fields_add( info, "PARTDAY", tmp.data, level ); + 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 ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } newstr_free( &tmp ); + + return BIBL_OK; } /* eng @@ -213,13 +208,16 @@ medin_language( xml *node, fields *info, int level ) { char *code, *language; - int ok; + int fstatus; code = xml_data( node ); - if ( !code ) return 1; + if ( !code ) return BIBL_OK; language = iso639_2_from_code( code ); - if ( language ) ok = fields_add( info, "LANGUAGE", language, level ); - else ok = fields_add( info, "LANGUAGE", code, level ); - return ok; + if ( language ) + fstatus = fields_add( info, "LANGUAGE", language, level ); + else + fstatus = fields_add( info, "LANGUAGE", code, level ); + if ( fstatus==FIELDS_OK ) return BIBL_OK; + else return BIBL_ERR_MEMERR; } /* @@ -250,7 +248,7 @@ * Alcohol Alcohol. * */ -static void +static int medin_journal1( xml *node, fields *info ) { xml_convert c[] = { @@ -263,60 +261,87 @@ { "Month", NULL, NULL, "PARTMONTH", 1 }, { "Day", NULL, NULL, "PARTDAY", 1 }, }; - int nc = sizeof( c ) / sizeof( c[0] );; - if ( xml_hasdata( node ) && !medin_doconvert( node, info, c, nc ) ) { - if ( xml_tagexact( node, "MedlineDate" ) ) - medin_medlinedate( info, xml_data( node ), 1 ); - if ( xml_tagexact( node, "Language" ) ) - medin_language( node, info, 1 ); + int nc = sizeof( c ) / sizeof( c[0] ), status, found; + if ( xml_hasdata( 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 ); + if ( status!=BIBL_OK ) return status; + } + if ( xml_tagexact( node, "Language" ) ) { + status = medin_language( node, info, 1 ); + if ( status!=BIBL_OK ) return status; + } + } } - if ( node->down ) medin_journal1( node->down, info ); - if ( node->next ) medin_journal1( node->next, info ); + if ( node->down ) { + status = medin_journal1( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) { + status = medin_journal1( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } /* * 12111-6 * */ -static void +static int medin_pagination( xml *node, fields *info ) { + int i, fstatus, status; newstr sp, ep; - char *p; - int i; + char *p, *pp; if ( xml_tagexact( node, "MedlinePgn" ) && node->value ) { newstrs_init( &sp, &ep, NULL ); - p = xml_data( node ); - while ( *p && *p!='-' ) - newstr_addchar( &sp, *p++ ); - if ( *p=='-' ) p++; - while ( *p ) - newstr_addchar( &ep, *p++ ); - if ( sp.len ) fields_add( info, "PAGESTART", sp.data, 1 ); + 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 ); + 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 ) { if ( sp.len > ep.len ) { for ( i=sp.len-ep.len; idown ) medin_pagination( node->down, info ); - if ( node->next ) medin_pagination( node->next, info ); + if ( node->down ) { + status = medin_pagination( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) { + status = medin_pagination( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } /* * ljwejrelr * */ -static void +static int medin_abstract( xml *node, fields *info ) { - if ( xml_tagwithdata( node, "AbstractText" ) ) - fields_add( info, "ABSTRACT", xml_data( node ), 0 ); - else if ( node->next ) medin_abstract( node->next, info ); + int fstatus; + if ( xml_tagwithdata( node, "AbstractText" ) ) { + fstatus = fields_add( info, "ABSTRACT", xml_data( node ), 0 ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } else if ( node->next ) return medin_abstract( node->next, info ); + return BIBL_OK; } /* @@ -331,7 +356,7 @@ * * */ -static void +static int medin_author( xml *node, newstr *name ) { char *p; @@ -357,37 +382,45 @@ } } if ( node->next ) medin_author( node->next, name ); + return BIBL_OK; } -static void +static int medin_corpauthor( xml *node, newstr *name ) { if ( xml_tagexact( node, "CollectiveName" ) ) { newstr_strcpy( name, xml_data( node ) ); } else if ( node->next ) medin_corpauthor( node->next, name ); + return BIBL_OK; } -static void +static int medin_authorlist( xml *node, fields *info ) { + int fstatus, status; newstr name; + char *tag; newstr_init( &name ); node = node->down; while ( node ) { if ( xml_tagexact( node, "Author" ) && node->down ) { - medin_author( node->down, &name ); + status = medin_author( node->down, &name ); + tag = "AUTHOR"; + if ( !name.len ) { + status = medin_corpauthor( node->down, &name ); + tag = "AUTHOR:CORP"; + } + if ( newstr_memerr( &name ) || status!=BIBL_OK ) return BIBL_ERR_MEMERR; if ( name.len ) { - fields_add(info,"AUTHOR",name.data,0); - } else { - medin_corpauthor( node->down, &name ); - if ( name.len ) - fields_add(info,"AUTHOR:CORP",name.data,0); + fstatus = fields_add(info,tag,name.data,0); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } newstr_empty( &name ); } node = node->next; } newstr_free( &name ); + return BIBL_OK; } /* @@ -402,13 +435,20 @@ * */ -static void +static int medin_journal2( xml *node, fields *info ) { - if ( xml_tagwithdata( node, "MedlineTA" ) && fields_find( info, "TITLE", 1 )==-1 ) - fields_add( info, "TITLE", xml_data( node ), 1 ); - if ( node->down ) medin_journal2( node->down, info ); - if ( node->next ) medin_journal2( node->next, 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 ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + if ( node->down ) { + status = medin_journal2( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) status = medin_journal2( node->next, info ); + return status; } /* @@ -421,20 +461,28 @@ */ -static void +static int medin_meshheading( xml *node, fields *info ) { - if ( xml_tagwithdata( node, "DescriptorName" ) ) - fields_add( info, "KEYWORD", xml_data( node ), 0 ); - if ( node->next ) medin_meshheading( node->next, info ); + int fstatus, status = BIBL_OK; + if ( xml_tagwithdata( node, "DescriptorName" ) ) { + fstatus = fields_add( info, "KEYWORD", xml_data( node ), 0 ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + if ( node->next ) status = medin_meshheading( node->next, info ); + return status; } -static void +static int medin_meshheadinglist( xml *node, fields *info ) { - if ( xml_tagexact( node, "MeshHeading" ) && node->down ) - medin_meshheading( node->down, info ); - if ( node->next ) medin_meshheadinglist( node->next, info ); + int status = BIBL_OK; + if ( xml_tagexact( node, "MeshHeading" ) && node->down ) { + status = medin_meshheading( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) status = medin_meshheadinglist( node->next, info ); + return status; } /* @@ -449,8 +497,7 @@ * * I think "pii" is "Publisher Item Identifier" */ - -static void +static int medin_pubmeddata( xml *node, fields *info ) { xml_convert c[] = { @@ -459,88 +506,127 @@ { "ArticleId", "IdType", "medline", "MEDLINE", 0 }, { "ArticleId", "IdType", "pii", "PII", 0 }, }; - int nc = sizeof( c ) / sizeof( c[0] ); - medin_doconvert( node, info, c, nc ); - if ( node->next ) medin_pubmeddata( node->next, info ); - if ( node->down ) medin_pubmeddata( node->down, info ); + int nc = sizeof( c ) / sizeof( c[0] ), found, status; + status = medin_doconvert( node, info, c, nc, &found ); + if ( status!=BIBL_OK ) return status; + if ( node->next ) { + status = medin_pubmeddata( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->down ) { + medin_pubmeddata( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + return BIBL_OK; } -static void +static int medin_article( xml *node, fields *info ) { - if ( xml_tagexact( node, "Journal" ) ) - medin_journal1( node, info ); + int fstatus, status = BIBL_OK; + if ( xml_tagexact( node, "Journal" ) ) + status = medin_journal1( node, info ); else if ( xml_tagexact( node, "ArticleTitle" ) ) - medin_articletitle( node, info ); + status = medin_articletitle( node, info ); else if ( xml_tagexact( node, "Pagination" ) && node->down ) - medin_pagination( node->down, info ); + status = medin_pagination( node->down, info ); else if ( xml_tagexact( node, "Abstract" ) && node->down ) - medin_abstract( node->down, info ); + status = medin_abstract( node->down, info ); else if ( xml_tagexact( node, "AuthorList" ) ) - medin_authorlist( node, info ); + status = medin_authorlist( node, info ); else if ( xml_tagexact( node, "Language" ) ) - medin_language( node, info, 0 ); - else if ( xml_tagexact( node, "Affiliation" ) ) - fields_add( info, "ADDRESS", xml_data( node ), 0 ); - if ( node->next ) medin_article( node->next, info ); + status = medin_language( node, info, 0 ); + else if ( xml_tagexact( node, "Affiliation" ) ) { + fstatus = fields_add( info, "ADDRESS", xml_data( 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; } -static void +static int medin_medlinecitation( xml *node, fields *info ) { - if ( xml_tagexact( node, "PMID" ) && node->value->data ) - fields_add( info, "PMID", node->value->data, 0 ); + int fstatus, status = BIBL_OK; + if ( xml_tagexact( node, "PMID" ) && node->value->data ) { + fstatus = fields_add( info, "PMID", node->value->data, 0 ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } if ( node->down ) { - if ( xml_tagexact( node, "Article" ) ) - medin_article( node->down, info ); - else if ( xml_tagexact( node, "MedlineJournalInfo" ) ) - medin_journal2( node->down, info ); - else if ( xml_tagexact( node, "MeshHeadingList" ) ) - medin_meshheadinglist( node->down, info ); + if ( xml_tagexact( node, "Article" ) ) { + status = medin_article( node->down, info ); + } else if ( xml_tagexact( node, "MedlineJournalInfo" ) ) { + status = medin_journal2( node->down, info ); + } else if ( xml_tagexact( node, "MeshHeadingList" ) ) + status = medin_meshheadinglist( node->down, info ); + if ( status!=BIBL_OK ) return status; } - if ( node->next ) medin_medlinecitation( node->next, info ); + if ( node->next ) status = medin_medlinecitation( node->next, info ); + return status; } -static void +static int medin_pubmedarticle( xml *node, fields *info ) { + int status = BIBL_OK; if ( node->down ) { if ( xml_tagexact( node, "MedlineCitation" ) ) - medin_medlinecitation( node->down, info ); + status = medin_medlinecitation( node->down, info ); else if ( xml_tagexact( node, "PubmedData" ) ) - medin_pubmeddata( node->down, info ); + status = medin_pubmeddata( node->down, info ); + if ( status!=BIBL_OK ) return status; } - if ( node->next ) medin_pubmedarticle( node->next, info ); + if ( node->next ) status = medin_pubmedarticle( node->next, info ); + return status; } -static void +static int medin_assembleref( xml *node, fields *info ) { + int status = BIBL_OK; if ( node->down ) { if ( xml_tagexact( node, "PubmedArticle" ) ) - medin_pubmedarticle( node->down, info ); + status = medin_pubmedarticle( node->down, info ); else if ( xml_tagexact( node, "MedlineCitation" ) ) - medin_medlinecitation( node->down, info ); - else medin_assembleref( node->down, info ); + status = medin_medlinecitation( node->down, info ); + else + status = medin_assembleref( node->down, info ); } + if ( status!=BIBL_OK ) return status; - if ( node->next ) medin_assembleref( node->next, info ); + if ( node->next ) { + status = medin_assembleref( node->next, info ); + if ( status!=BIBL_OK ) return status; + } + /* assume everything is a journal article */ if ( fields_num( info ) ) { - fields_add( info, "RESOURCE", "text", 0 ); - fields_add( info, "ISSUANCE", "continuing", 1 ); - fields_add( info, "GENRE", "periodical", 1 ); - fields_add( info, "GENRE", "academic journal", 1 ); + status = fields_add( info, "RESOURCE", "text", 0 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + status = fields_add( info, "ISSUANCE", "continuing", 1 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + status = fields_add( info, "GENRE", "periodical", 1 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + status = fields_add( info, "GENRE", "academic journal", 1 ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; + status = BIBL_OK; } + + return status; } int medin_processf( fields *medin, char *data, char *filename, long nref ) { + int status; xml top; + xml_init( &top ); xml_tree( data, &top ); - medin_assembleref( &top, medin ); + status = medin_assembleref( &top, medin ); xml_free( &top ); - return 1; + + if ( status==BIBL_OK ) return 1; + return 0; } diff --git a/bibutils/medin.h b/bibutils/medin.h --- a/bibutils/medin.h +++ b/bibutils/medin.h @@ -1,7 +1,7 @@ /* * medin.h * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Source code released under the GPL version 2 * 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 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Source code released under the GPL version 2 * @@ -10,6 +10,7 @@ #include #include #include +#include "is_ws.h" #include "newstr.h" #include "newstr_conv.h" #include "xml.h" @@ -19,9 +20,15 @@ #include "reftypes.h" #include "modstypes.h" #include "marc.h" +#include "iso639_1.h" +#include "iso639_2.h" +#include "iso639_3.h" #include "bibutils.h" #include "modsin.h" +/***************************************************** + PUBLIC: void modsin_initparams() +*****************************************************/ void modsin_initparams( param *p, const char *progname ) { @@ -55,113 +62,162 @@ else p->progname = strdup( progname ); } +/***************************************************** + PUBLIC: int modsin_processf() +*****************************************************/ + static char modsns[]="mods"; -static void +static int modsin_detailr( xml *node, newstr *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 ( node->down ) modsin_detailr( node->down, value ); - if ( node->next ) modsin_detailr( node->next, value ); + if ( node->down ) { + status = modsin_detailr( node->down, value ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) + status = modsin_detailr( node->next, value ); + return status; } -static void +static int modsin_detail( xml *node, fields *info, int level ) { newstr type, value, *tp; + int fstatus, status = BIBL_OK; if ( node->down ) { newstrs_init( &type, &value, NULL ); tp = xml_getattrib( node, "type" ); if ( tp ) { newstr_newstrcpy( &type, tp ); newstr_toupper( &type ); + if ( newstr_memerr( &type ) ) goto out; } - modsin_detailr( node->down, &value ); + status = modsin_detailr( node->down, &value ); + if ( status!=BIBL_OK ) goto out; if ( type.data && !strcasecmp( type.data, "PAGE" ) ) { - fields_add( info, "PAGESTART", value.data, level ); - } else fields_add( info, type.data, value.data, level ); + fstatus = fields_add( info, "PAGESTART", 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 ); } + return status; } -static void +static int modsin_date( xml *node, fields *info, int level, int part ) { -/* char *month[12] = { "January", "February", "March", "April", - "May", "June", "July", "August", "September", "October", - "November", "December" };*/ + int fstatus, status = BIBL_OK; + char *tag, *p = NULL; newstr s; - char *p = NULL; -/* int m;*/ if ( node->value ) p = node->value->data; if ( p ) { newstr_init( &s ); - while ( *p && *p!='-' ) newstr_addchar( &s, *p++ ); - if ( !part ) fields_add( info, "YEAR", s.data, level ); - else fields_add( info, "PARTYEAR", s.data, level ); - if ( *p=='-' ) p++; - newstr_empty( &s ); - while ( *p && *p!='-' ) newstr_addchar( &s, *p++ ); -/* m = atoi( s.data );*/ -/* if ( m > 0 && m < 13 ) { - if ( !part ) fields_add( info, "MONTH", month[m-1], level ); - else fields_add( info, "PARTMONTH", month[m-1], level ); - } else {*/ - if ( !part ) fields_add( info, "MONTH", s.data, level ); - else fields_add( info, "PARTMONTH", s.data, level ); -/* }*/ - if ( *p=='-' ) p++; - newstr_empty( &s ); - while ( *p ) newstr_addchar( &s, *p++ ); - if ( !part ) fields_add( info, "DAY", s.data, level ); - else fields_add( info, "PARTDAY", s.data, level ); + + 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 ); + 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 ); + 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 ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + } +out: newstr_free( &s ); } + return status; } -static void +static int modsin_pager( xml *node, newstr *sp, newstr *ep, newstr *tp, newstr *lp ) { + int status = BIBL_OK; if ( xml_tagexact( node, "start" ) ) { newstr_newstrcpy( sp, node->value ); + if ( newstr_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; } else if ( xml_tagexact( node, "total" ) ) { newstr_newstrcpy( tp, node->value ); + if ( newstr_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; } - if ( node->down ) modsin_pager( node->down, sp, ep, tp, lp ); - if ( node->next ) modsin_pager( node->next, sp, ep, tp, lp ); + if ( node->down ) { + status = modsin_pager( node->down, sp, ep, tp, lp ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) + status = modsin_pager( node->next, sp, ep, tp, lp ); + return status; } -static void +static int modsin_page( xml *node, fields *info, int level ) { + int fstatus, status = BIBL_OK; newstr sp, ep, tp, lp; - if ( node->down ) { - newstrs_init( &sp, &ep, &tp, &lp, NULL ); - modsin_pager( node->down, &sp, &ep, &tp, &lp ); - if ( sp.len || ep.len ) { - if ( sp.len ) - fields_add( info, "PAGESTART", sp.data, level ); - if ( ep.len ) - fields_add( info, "PAGEEND", ep.data, level ); - } else if ( lp.len ) { - fields_add( info, "PAGESTART", lp.data, level ); + xml *dnode = node->down; + + if ( !dnode ) return BIBL_OK; + + newstrs_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 ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } - if ( tp.len ) - fields_add( info, "TOTALPAGES", tp.data, level ); - newstrs_free( &sp, &ep, &tp, &lp, NULL ); + if ( ep.len ) { + fstatus = fields_add( info, "PAGEEND", ep.data, level ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + } + } else if ( lp.len ) { + fstatus = fields_add( info, "PAGESTART", lp.data, level ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } + if ( tp.len ) { + fstatus = fields_add( info, "TOTALPAGES", tp.data, level ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + } +out: + newstrs_free( &sp, &ep, &tp, &lp, NULL ); + return BIBL_OK; } -static void +static int modsin_titler( xml *node, newstr *title, newstr *subtitle ) { + int status = BIBL_OK; if ( xml_tagexact( node, "title" ) ) { if ( title->len ) { newstr_strcat( title, " : " ); @@ -169,34 +225,54 @@ } else { newstr_newstrcat( title, node->value ); } - } else if ( xml_tagexact( node, "subTitle" ) ) + if ( newstr_memerr( title ) ) return BIBL_ERR_MEMERR; + } else if ( xml_tagexact( node, "subTitle" ) ) { newstr_newstrcat( subtitle, node->value ); - if ( node->down ) modsin_titler( node->down, title, subtitle ); - if ( node->next ) modsin_titler( node->next, title, subtitle ); + if ( newstr_memerr( subtitle ) ) return BIBL_ERR_MEMERR; + } + if ( node->down ) { + status = modsin_titler( node->down, title, subtitle ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) + status = modsin_titler( node->next, title, subtitle ); + return status; } -static void +static int modsin_title( xml *node, fields *info, int level ) { + char *titletag[2][2] = { + { "TITLE", "SHORTTITLE" }, + { "SUBTITLE", "SHORTSUBTITLE" }, + }; + int fstatus, status = BIBL_OK; newstr title, subtitle; - int abbr = xml_tag_attrib( node, "titleInfo", "type", "abbreviated" ); - if ( node->down ) { - newstrs_init( &title, &subtitle, NULL ); - modsin_titler( node->down, &title, &subtitle ); - if ( title.len ) { - if ( abbr ) - fields_add( info, "SHORTTITLE", title.data, level ); - else - fields_add( info, "TITLE", title.data, level ); - } - if ( subtitle.len ) { - if ( abbr ) - fields_add( info, "SHORTSUBTITLE", subtitle.data, level ); - else - fields_add( info, "SUBTITLE", subtitle.data, level ); - } - newstrs_free( &title, &subtitle, NULL ); + xml *dnode = node->down; + int abbr; + + dnode = node->down; + if ( !dnode ) return status; + + newstrs_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 ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } } + + if ( subtitle.len ) { + fstatus = fields_add( info, titletag[1][abbr], subtitle.data, level ); + if ( fstatus!=FIELDS_OK ) { status = BIBL_ERR_MEMERR; goto out; } + } + +out: + newstrs_free( &title, &subtitle, NULL ); + return status; } /* modsin_marcrole_convert() @@ -207,7 +283,7 @@ * Take input strings with roles separated by '|' characters, e.g. * "author" or "author|creator" or "edt" or "editor|edt". */ -static void +static int modsin_marcrole_convert( newstr *s, char *suffix, newstr *out ) { convert roles[] = { @@ -228,7 +304,7 @@ { "pth", "ASSIGNEE" } }; int nroles = sizeof( roles ) / sizeof( roles[0] ); - int i, nmismatch, n = -1; + int i, nmismatch, n = -1, status = BIBL_OK; char *p, *q; if ( s->len == 0 ) { @@ -259,25 +335,36 @@ } else { newstr_strcpy( out, s->data ); } + if ( newstr_memerr( out ) ) status = BIBL_ERR_MEMERR; + return status; } -static void +static int modsin_asis_corp_r( xml *node, newstr *name, newstr *role ) { - if ( xml_tagexact( node, "namePart" ) ) + int status = BIBL_OK; + if ( xml_tagexact( node, "namePart" ) ) { newstr_newstrcpy( name, node->value ); - else if ( xml_tagexact( node, "roleTerm" ) ) { + if ( newstr_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 ( node->down ) modsin_asis_corp_r( node->down, name, role ); - if ( node->next ) modsin_asis_corp_r( node->next, name, role ); + if ( node->down ) { + status = modsin_asis_corp_r( node->down, name, role ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) + status = modsin_asis_corp_r( node->next, name, role ); + return status; } -static void +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" ) ) { @@ -297,150 +384,242 @@ if ( roles->len ) newstr_addchar( roles, '|' ); newstr_newstrcat( roles, node->value ); } - if ( node->down ) modsin_personr( node->down, name, suffix, roles ); - if ( node->next ) modsin_personr( node->next, name, suffix, roles ); + 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 void +static int modsin_asis_corp( xml *node, fields *info, int level, char *suffix ) { + int fstatus, status = BIBL_OK; newstr name, roles, role_out; xml *dnode = node->down; if ( dnode ) { newstrs_init( &name, &roles, &role_out, NULL ); - modsin_asis_corp_r( dnode, &name, &roles ); - modsin_marcrole_convert( &roles, suffix, &role_out ); - fields_add( info, role_out.data, name.data, level ); + 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 ); + if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; +out: newstrs_free( &name, &roles, &role_out, NULL ); } + return status; } -static void +static int modsin_person( xml *node, fields *info, int level ) { - newstr name, suffix, roles, role, role_out; + newstr name, suffix, roles, role_out; + int fstatus, status = BIBL_OK; xml *dnode = node->down; if ( dnode ) { - newstrs_init( &name, &suffix, &role, &roles, &role_out, NULL ); - modsin_personr( dnode, &name, &suffix, &roles ); - modsin_marcrole_convert( &roles, NULL, &role_out ); + newstrs_init( &name, &suffix, &roles, &role_out, NULL ); + + 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; } } - fields_add( info, role_out.data, name.data, level ); - newstrs_free( &name, &suffix, &role, &roles, NULL ); + + status = modsin_marcrole_convert( &roles, NULL, &role_out ); + if ( status!=BIBL_OK ) goto out; + + 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 ); } + return status; } -static void -modsin_placeterm( xml *node, fields *info, int level, int school ) +static int +modsin_placeterm_text( xml *node, fields *info, int level, int school ) { - char address_tag[] = "ADDRESS", - addresscode_tag[] = "CODEDADDRESS", - school_tag[] = "SCHOOL", - *newtag; - newstr *type, s; + char address_tag[] = "ADDRESS"; + char school_tag[] = "SCHOOL"; + char *tag; + int fstatus; - newtag = ( school ) ? school_tag : address_tag; + tag = ( school ) ? school_tag : address_tag; + fstatus = fields_add( info, tag, xml_data( node ), level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + + return BIBL_OK; +} + +static int +modsin_placeterm_code( xml *node, fields *info, int level ) +{ + int fstatus, status = BIBL_OK; + newstr s, *auth; + + newstr_init( &s ); + + auth = xml_getattrib( node, "authority" ); + if ( auth && auth->len ) { + newstr_newstrcpy( &s, auth ); + newstr_addchar( &s, '|' ); + } + newstr_newstrcat( &s, node->value ); + + if ( newstr_memerr( &s ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } + + fstatus = fields_add( info, "CODEDADDRESS", s.data, level ); + if ( fstatus!=FIELDS_OK ) status = BIBL_ERR_MEMERR; +out: + newstr_free( &s ); + return status; +} + +static int +modsin_placeterm( xml *node, fields *info, int level, int school ) +{ + int status = BIBL_OK; + newstr *type; + type = xml_getattrib( node, "type" ); if ( type && type->len ) { - if ( !strcmp( type->data, "text" ) ) { - fields_add( info, newtag, node->value->data, level ); - } else if ( !strcmp( type->data, "code" ) ) { - newstr_init( &s ); - type = xml_getattrib( node, "authority" ); - if ( type && type->len ) newstr_newstrcpy(&s, type); - newstr_addchar( &s, '|' ); - newstr_newstrcat( &s, node->value ); - fields_add( info, addresscode_tag, s.data, level ); - newstr_free( &s ); - } + if ( !strcmp( type->data, "text" ) ) + status = modsin_placeterm_text( node, info, level, school ); + else if ( !strcmp( type->data, "code" ) ) + status = modsin_placeterm_code( node, info, level ); } + + return status; } -static void +static int modsin_placer( xml *node, fields *info, int level, int school ) { + int status = BIBL_OK; if ( xml_tag_attrib( node, "place", "type", "school" ) ) { school = 1; } else if ( xml_tagexact( node, "placeTerm" ) ) { - modsin_placeterm( node, info, level, school ); + status = modsin_placeterm( node, info, level, school ); } - if ( node->down ) modsin_placer( node->down, info, level, school ); - if ( node->next ) modsin_placer( node->next, info, level, school ); + if ( node->down ) { + status = modsin_placer( node->down, info, level, school ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) status = modsin_placer( node->next, info, level, school ); + return status; } -static void +static int modsin_origininfor( xml *node, fields *info, int level, newstr *pub, newstr *add, newstr *addc, newstr *ed, newstr *iss ) { + int status = BIBL_OK; if ( xml_tagexact( node, "dateIssued" ) ) - modsin_date( node, info, level, 0 ); - else if ( xml_tagexact( node, "publisher" ) ) + status = modsin_date( node, info, level, 0 ); + else if ( xml_tagexact( node, "publisher" ) && xml_hasdata( node ) ) { newstr_newstrcat( pub, node->value ); - else if ( xml_tagexact( node, "edition" ) ) + if ( newstr_memerr( pub ) ) return BIBL_ERR_MEMERR; + } else if ( xml_tagexact( node, "edition" ) && xml_hasdata( node ) ) { newstr_newstrcat( ed, node->value ); - else if ( xml_tagexact( node, "issuance" ) ) + if( newstr_memerr( ed ) ) return BIBL_ERR_MEMERR; + } else if ( xml_tagexact( node, "issuance" ) && xml_hasdata( node ) ) { newstr_newstrcat( iss, node->value ); - else if ( xml_tagexact( node, "place" ) ) - modsin_placer( node, info, level, 0 ); - if ( node->down ) - modsin_origininfor( node->down, info, level, pub, add, - addc, ed, iss ); - if ( node->next ) modsin_origininfor( node->next, info, level, pub, add, addc, ed, iss ); + if ( newstr_memerr( iss ) ) return BIBL_ERR_MEMERR; + } else if ( xml_tagexact( node, "place" ) && xml_hasdata( node ) ) + status = modsin_placer( node, info, level, 0 ); + if ( status!=BIBL_OK ) return status; + if ( node->down ) { + status = modsin_origininfor( node->down, info, level, pub, add, addc, ed, iss ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) + status = modsin_origininfor( node->next, info, level, pub, add, addc, ed, iss ); + return status; } -static void +static int modsin_origininfo( xml *node, fields *info, int level ) { newstr publisher, address, addcode, edition, issuance; + int fstatus, status = BIBL_OK; if ( node->down ) { newstrs_init( &publisher, &address, &addcode, &edition, &issuance, NULL ); - modsin_origininfor( node->down, info, level, &publisher, + status = modsin_origininfor( node->down, info, level, &publisher, &address, &addcode, &edition, &issuance ); - if ( publisher.len ) - fields_add( info, "PUBLISHER", publisher.data, level ); - if ( address.len ) - fields_add( info, "ADDRESS", address.data, level ); - if ( addcode.len ) - fields_add( info, "CODEDADDRESS", addcode.data, level ); - if ( edition.len ) - fields_add( info, "EDITION", edition.data, level ); - if ( issuance.len ) - fields_add( info, "ISSUANCE", issuance.data, level ); + if ( status!=BIBL_OK ) goto out; + if ( publisher.len ) { + fstatus = fields_add( info, "PUBLISHER", publisher.data, level ); + if ( fstatus!=FIELDS_OK ) { status=BIBL_ERR_MEMERR; goto out; } + } + if ( address.len ) { + fstatus = fields_add( info, "ADDRESS", address.data, level ); + if ( fstatus!=FIELDS_OK ) { status=BIBL_ERR_MEMERR; goto out; } + } + if ( addcode.len ) { + fstatus = fields_add( info, "CODEDADDRESS", addcode.data, level ); + if ( fstatus!=FIELDS_OK ) { status=BIBL_ERR_MEMERR; goto out; } + } + if ( edition.len ) { + fstatus = fields_add( info, "EDITION", edition.data, level ); + if ( fstatus!=FIELDS_OK ) { status=BIBL_ERR_MEMERR; goto out; } + } + if ( issuance.len ) { + fstatus = fields_add( info, "ISSUANCE", issuance.data, level ); + if ( fstatus!=FIELDS_OK ) { status=BIBL_ERR_MEMERR; goto out; } + } +out: newstrs_free( &publisher, &address, &addcode, &edition, &issuance, NULL ); } + return status; } -static void +static int modsin_subjectr( xml *node, fields *info, int level ) { + int fstatus, status = BIBL_OK; if ( xml_tagexact( node, "topic" ) || xml_tagexact( node, "geographic" )) { - fields_add( info, "KEYWORD", node->value->data, level ); + fstatus = fields_add( info, "KEYWORD", node->value->data, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - if ( node->down ) modsin_subjectr( node->down, info, level ); - if ( node->next ) modsin_subjectr( node->next, info, level ); + if ( node->down ) { + status = modsin_subjectr( node->down, info, level ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) status = modsin_subjectr( node->next, info, level ); + return status; } -static void +static int modsin_subject( xml *node, fields *info, int level ) { - if ( node->down ) modsin_subjectr( node->down, info, level ); + int status = BIBL_OK; + if ( node->down ) status = modsin_subjectr( node->down, info, level ); + return status; } -static void +static int modsin_id1( xml *node, fields *info, int level ) { + int fstatus; newstr *ns; ns = xml_getattrib( node, "ID" ); - if ( ns ) { - fields_add( info, "REFNUM", ns->data, level ); + if ( ns && ns->len ) { + fstatus = fields_add( info, "REFNUM", ns->data, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } + return BIBL_OK; } -static void +static int modsin_genre( xml *node, fields *info, int level ) { char *added[] = { "manuscript", "academic journal", "magazine", @@ -451,181 +630,234 @@ "press release", "television broadcast", "electronic" }; int nadded = sizeof( added ) /sizeof( char *); - int j, ismarc = 0, isadded = 0; - if ( node->value && node->value->len ) { - if ( marc_findgenre( node->value->data )!=-1 ) ismarc = 1; - for ( j=0; jvalue->data, added[j] ) ) - isadded = 1; - } - if ( ismarc || isadded ) - fields_add( info, "GENRE", node->value->data, level ); - else - fields_add( info, "NGENRE", node->value->data, level ); + int i, ismarc = 0, isadded = 0, fstatus; + char *d; + + if ( !xml_hasdata( node ) ) return BIBL_OK; + d = xml_data( node ); + if ( marc_findgenre( d )!=-1 ) ismarc = 1; + if ( !ismarc ) { + for ( i=0; ivalue && node->value->len ) - fields_add( info, "RESOURCE", node->value->data, level ); + if ( ismarc || isadded ) + fstatus = fields_add( info, "GENRE", d, level ); + else + fstatus = fields_add( info, "NGENRE", d, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + + return BIBL_OK; } -static void +/* in MODS version 3.5 + * .... + * ... + * xxx = rfc3066 + * xxx = iso639-2b + * xxx = iso639-3 + * xxx = rfc4646 + * xxx = rfc5646 + */ +static int modsin_languager( xml *node, fields *info, int level ) { - if ( xml_tag_attrib( node, "languageTerm", "type", "text" ) ) { - if ( node->value && node->value->len ) - fields_add( info, "LANGUAGE", node->value->data, level ); + int fstatus, status = BIBL_OK; + char *d = NULL; + if ( xml_tagexact( node, "languageTerm" ) ) { + if ( xml_hasdata( node ) ) { + if ( xml_hasattrib( node, "type", "code" ) ) { + if ( xml_hasattrib( node, "authority", "iso639-1" ) ) + d = iso639_1_from_code( xml_data( node ) ); + else if ( xml_hasattrib( node, "authority", "iso639-2b" ) ) + d = iso639_2_from_code( xml_data( node ) ); + else if ( xml_hasattrib( node, "authority", "iso639-3" )) + d = iso639_3_from_code( xml_data( node ) ); + } + if ( !d ) d = xml_data( node ); + fstatus = fields_add( info, "LANGUAGE", d, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } } - if ( node->next ) modsin_languager( node->next, info, level ); + if ( node->next ) status = modsin_languager( node->next, info, level ); + return status; } -static void +static int modsin_language( xml *node, fields *info, int level ) { + int fstatus, status = BIBL_OK; /* Old versions of MODS had English */ - if ( node->value && node->value->len ) - fields_add( info, "LANGUAGE", node->value->data, level ); + if ( xml_hasdata( node ) ) { + fstatus = fields_add( info, "LANGUAGE", xml_data( node ), level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } /* New versions of MODS have English */ - if ( node->down ) modsin_languager( node->down, info, level ); -} - -static void -modsin_toc( xml *node, fields *info, int level ) -{ - if ( node->value && node->value->len ) - fields_add( info, "CONTENTS", node->value->data, level ); -} - -static void -modsin_note( xml *node, fields *info, int level ) -{ - if ( node->value && node->value->len ) - fields_add( info, "NOTES", node->value->data, level ); -} - -static void -modsin_annote( xml *node, fields *info, int level ) -{ - if ( node->value && node->value->len ) - fields_add( info, "ANNOTE", node->value->data, level ); + if ( node->down ) status = modsin_languager( node->down, info, level ); + return status; } -static void -modsin_abstract( xml *node, fields *info, int level ) +static int +modsin_simple( xml *node, fields *info, char *tag, int level ) { - if ( node->value && node->value->len ) - fields_add( info, "ABSTRACT", node->value->data, level ); + int fstatus; + if ( xml_hasdata( node ) ) { + fstatus = fields_add( info, tag, xml_data( node ), level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } + return BIBL_OK; } -static void +static int modsin_locationr( xml *node, fields *info, int level ) { - char url[]="URL", school[]="SCHOOL", loc[]="LOCATION"; - char fileattach[]="FILEATTACH", *tag=NULL; - - if ( xml_tag_attrib( node, "url", "access", "raw object" ) ) { - tag = fileattach; - } else if ( xml_tagexact( node, "url" ) ) { - tag = url; - } + int fstatus, status = BIBL_OK; + char *tag=NULL; - if ( xml_tag_attrib( node, "physicalLocation", "type", "school" ) ) { - tag = school; + if ( xml_tagexact( node, "url" ) ) { + if ( xml_hasattrib( node, "access", "raw object" ) ) + tag = "FILEATTACH"; + else + tag = "URL"; } else if ( xml_tagexact( node, "physicalLocation" ) ) { - tag = loc; + if ( xml_hasattrib( node, "type", "school" ) ) + tag = "SCHOOL"; + else + tag = "LOCATION"; } - if ( tag ) fields_add( info, tag, node->value->data, level ); + if ( tag ) { + fstatus = fields_add( info, tag, node->value->data, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } - if ( node->down ) modsin_locationr( node->down, info, level ); - if ( node->next ) modsin_locationr( node->next, info, level ); + if ( node->down ) { + status = modsin_locationr( node->down, info, level ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) status = modsin_locationr( node->next, info, level ); + return status; } -static void +static int modsin_location( xml *node, fields *info, int level ) { - if ( node->down ) modsin_locationr( node->down, info, level ); + int status = BIBL_OK; + if ( node->down ) status = modsin_locationr( node->down, info, level ); + return status; } -static void +static int modsin_descriptionr( xml *node, newstr *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; } - if ( node->down ) modsin_descriptionr( node->down, s ); - if ( node->next ) modsin_descriptionr( node->next, s ); + if ( node->down ) { + status = modsin_descriptionr( node->down, s ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) status = modsin_descriptionr( node->next, s ); + return status; } -static void +static int modsin_description( xml *node, fields *info, int level ) { + int fstatus, status = BIBL_OK; newstr s; newstr_init( &s ); - if ( node->down ) modsin_descriptionr( node->down, &s ); - else { - if ( node->value && node->value->data ); - newstr_newstrcpy( &s, node->value ); + 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 ) ) { + status = BIBL_ERR_MEMERR; + goto out; + } } - if ( s.len ) fields_add( info, "DESCRIPTION", s.data, level ); + if ( s.len ) { + fstatus = fields_add( info, "DESCRIPTION", s.data, level ); + if ( fstatus!=FIELDS_OK ) { + status = BIBL_ERR_MEMERR; + goto out; + } + } +out: newstr_free( &s ); + return BIBL_OK; } -static void +static int modsin_partr( xml *node, fields *info, int level ) { + int status = BIBL_OK; if ( xml_tagexact( node, "detail" ) ) - modsin_detail( node, info, level ); + status = modsin_detail( node, info, level ); else if ( xml_tag_attrib( node, "extent", "unit", "page" ) ) - modsin_page( node, info, level ); + status = modsin_page( node, info, level ); else if ( xml_tag_attrib( node, "extent", "unit", "pages" ) ) - modsin_page( node, info, level ); + status = modsin_page( node, info, level ); else if ( xml_tagexact( node, "date" ) ) - modsin_date( node, info, level, 1 ); - if ( node->next ) modsin_partr( node->next, info, level ); + status = modsin_date( node, info, level, 1 ); + if ( status!=BIBL_OK ) return status; + if ( node->next ) status = modsin_partr( node->next, info, level ); + return status; } -static void +static int modsin_part( xml *node, fields *info, int level ) { - if ( node->down ) modsin_partr( node->down, info, level ); + if ( node->down ) return modsin_partr( node->down, info, level ); + return BIBL_OK; } /* Q3 .A65 */ -static void +static int modsin_classification( xml *node, fields *info, int level ) { - if ( node->value && node->value->len ) { - if (xml_tag_attrib(node, "classification", "authority", "lcc")){ - fields_add( info, "LCC", node->value->data, level ); - } else - fields_add( info, "CLASSIFICATION", node->value->data, level ); + int fstatus, status = BIBL_OK; + char *tag, *d; + if ( xml_hasdata( node ) ) { + d = xml_data( node ); + if ( xml_tag_attrib( node, "classification", "authority", "lcc" ) ) + tag = "LCC"; + else + tag = "CLASSIFICATION"; + fstatus = fields_add( info, tag, d, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } - if ( node->down ) modsin_classification( node->down, info, level ); + if ( node->down ) status = modsin_classification( node->down, info, level ); + return status; } -static void +static int modsin_recordinfo( xml *node, fields *info, int level ) { + int fstatus; xml *curr; + char *d; /* extract recordIdentifier */ curr = node; while ( curr ) { - if ( xml_tagexact( curr, "recordIdentifier" ) ) { - fields_add( info, "REFNUM", curr->value->data, level ); + if ( xml_tagexact( curr, "recordIdentifier" ) && xml_hasdata( curr ) ) { + d = xml_data( curr ); + fstatus = fields_add( info, "REFNUM", d, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } curr = curr->next; } - + return BIBL_OK; } -static void +static int modsin_identifier( xml *node, fields *info, int level ) { convert ids[] = { @@ -645,87 +877,118 @@ { "accessnum", "ACCESSNUM" }, { "jstor", "JSTOR" }, }; - int i , n = sizeof( ids ) / sizeof( ids[0] ); - if ( !node->value || !node->value->data ) return; + int i, fstatus, n = sizeof( ids ) / sizeof( ids[0] ); + if ( !node->value || node->value->len==0 ) return BIBL_OK; for ( i=0; ivalue->data, level ); + if ( xml_tag_attrib( node, "identifier", "type", ids[i].mods ) ) { + fstatus = fields_add( info, ids[i].internal, node->value->data, level ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; + } } + return BIBL_OK; } -static void +static int modsin_mods( xml *node, fields *info, int level ) { - if ( xml_tagexact( node, "titleInfo" ) ) - modsin_title( node, info, level ); - else if ( xml_tag_attrib( node, "name", "type", "personal" ) ) - modsin_person( node, info, level ); - else if ( xml_tag_attrib( node, "name", "type", "corporate" ) ) - modsin_asis_corp( node, info, level, ":CORP" ); - else if ( xml_tagexact( node, "name" ) ) - modsin_asis_corp( node, info, level, ":ASIS" ); - else if ( xml_tagexact( node, "recordInfo" ) && node->down ) - modsin_recordinfo( node->down, info, level ); - else if ( xml_tagexact( node, "part" ) ) - modsin_part( node, info, level ); - else if ( xml_tagexact( node, "identifier" ) ) - modsin_identifier( node, info, level ); - else if ( xml_tagexact( node, "originInfo" ) ) - modsin_origininfo( node, info, level ); - else if ( xml_tagexact( node, "typeOfResource" ) ) - modsin_resource( node, info, level ); - else if ( xml_tagexact( node, "language" ) ) - modsin_language( node, info, level ); - else if ( xml_tagexact( node, "tableOfContents" ) ) - modsin_toc( node, info, level ); - else if ( xml_tagexact( node, "genre" ) ) - modsin_genre( node, info, level ); - else if ( xml_tagexact( node, "date" ) ) - modsin_date( node, info, level, 0 ); - else if ( xml_tagexact( node, "note" ) ) - modsin_note( node, info, level ); - else if ( xml_tagexact( node, "bibtex-annote" ) ) - modsin_annote( node, info, level ); - else if ( xml_tagexact( node, "abstract" ) ) - modsin_abstract( node, info, level ); - else if ( xml_tagexact( node, "subject" ) ) - modsin_subject( node, info, level ); - else if ( xml_tagexact( node, "classification" ) ) - modsin_classification( node, info, level ); - else if ( xml_tagexact( node, "location" ) ) - modsin_location( node, info, level ); - else if ( xml_tagexact( node, "physicalDescription" ) ) - modsin_description( node, info, level ); - else if ( xml_tag_attrib( node, "relatedItem", "type", "host" ) || - xml_tag_attrib( node, "relatedItem", "type", "series" ) ) { - if ( node->down ) modsin_mods( node->down, info, level+1 ); + convert simple[] = { + { "note", "NOTES" }, + { "abstract", "ABSTRACT" }, + { "bibtex-annote", "ANNOTE" }, + { "typeOfResource", "RESOURCE" }, + { "tableOfContents", "CONTENTS" }, + }; + int nsimple = sizeof( simple ) / sizeof( simple[0] ); + int i, found = 0, status = BIBL_OK; + + for ( i=0; inext ) modsin_mods( node->next, info, level ); + if ( !found ) { + if ( xml_tagexact( node, "titleInfo" ) ) + modsin_title( node, info, level ); + else if ( xml_tag_attrib( node, "name", "type", "personal" ) ) + status = modsin_person( node, info, level ); + else if ( xml_tag_attrib( node, "name", "type", "corporate" ) ) + status = modsin_asis_corp( node, info, level, ":CORP" ); + else if ( xml_tagexact( node, "name" ) ) + status = modsin_asis_corp( node, info, level, ":ASIS" ); + else if ( xml_tagexact( node, "recordInfo" ) && node->down ) + status = modsin_recordinfo( node->down, info, level ); + else if ( xml_tagexact( node, "part" ) ) + modsin_part( node, info, level ); + else if ( xml_tagexact( node, "identifier" ) ) + status = modsin_identifier( node, info, level ); + else if ( xml_tagexact( node, "originInfo" ) ) + status = modsin_origininfo( node, info, level ); + else if ( xml_tagexact( node, "language" ) ) + status = modsin_language( node, info, level ); + else if ( xml_tagexact( node, "genre" ) ) + status = modsin_genre( node, info, level ); + else if ( xml_tagexact( node, "date" ) ) + status = modsin_date( node, info, level, 0 ); + else if ( xml_tagexact( node, "subject" ) ) + status = modsin_subject( node, info, level ); + else if ( xml_tagexact( node, "classification" ) ) + status = modsin_classification( node, info, level ); + else if ( xml_tagexact( node, "location" ) ) + status = modsin_location( node, info, level ); + else if ( xml_tagexact( node, "physicalDescription" ) ) + status = modsin_description( node, info, level ); + else if ( xml_tag_attrib( node, "relatedItem", "type", "host" ) || + xml_tag_attrib( node, "relatedItem", "type", "series" ) ) { + if ( node->down ) status = modsin_mods( node->down, info, level+1 ); + } + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) status = modsin_mods( node->next, info, level ); + + return status; } -static void +static int modsin_assembleref( xml *node, fields *info ) { + int status = BIBL_OK; if ( xml_tagexact( node, "mods" ) ) { - modsin_id1( node, info, 0 ); - if ( node->down ) modsin_mods( node->down, info, 0 ); - } else if ( node->down ) modsin_assembleref( node->down, info ); - if ( node->next ) modsin_assembleref( node->next, info ); + status = modsin_id1( node, info, 0 ); + if ( status!=BIBL_OK ) return status; + if ( node->down ) { + status = modsin_mods( node->down, info, 0 ); + if ( status!=BIBL_OK ) return status; + } + } else if ( node->down ) { + status = modsin_assembleref( node->down, info ); + if ( status!=BIBL_OK ) return status; + } + if ( node->next ) status = modsin_assembleref( node->next, info ); + return status; } int modsin_processf( fields *modsin, char *data, char *filename, long nref ) { + int status; xml top; + xml_init( &top ); xml_tree( data, &top ); - modsin_assembleref( &top, modsin ); + status = modsin_assembleref( &top, modsin ); xml_free( &top ); - return 1; + + if ( status==BIBL_OK ) return 1; + else return 0; } +/***************************************************** + PUBLIC: int modsin_readf() +*****************************************************/ static char * modsin_startptr( char *p ) diff --git a/bibutils/modsin.h b/bibutils/modsin.h --- a/bibutils/modsin.h +++ b/bibutils/modsin.h @@ -1,7 +1,7 @@ /* * modsin.h * - * Copyright (c) Chris Putnam 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Source code released under the GPL version 2 * diff --git a/bibutils/modsout.c b/bibutils/modsout.c --- a/bibutils/modsout.c +++ b/bibutils/modsout.c @@ -1,7 +1,7 @@ /* * modsout.c * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2014 * * Source code released under the GPL version 2 * @@ -30,7 +30,7 @@ p->latexout = 0; p->utf8out = 1; p->utf8bom = 1; - p->xmlout = 1; + p->xmlout = BIBL_XMLOUT_TRUE; p->nosplittitle = 0; p->verbose = 0; p->addcount = 0; @@ -386,6 +386,7 @@ { "issuance", "ISSUANCE", 0 }, { "publisher", "PUBLISHER", 0 }, { "place", "ADDRESS", 1 }, + { "place", "AUTHORADDRESS", 0 }, { "edition", "EDITION", 0 }, { "dateCaptured", "URLDATE", 0 } }; @@ -571,9 +572,10 @@ static int output_partpages( fields *f, FILE *outptr, int level, int wrote_header ) { - convert parts[3] = { + convert parts[4] = { { "", "PAGESTART", -1 }, { "", "PAGEEND", -1 }, + { "", "PAGES", -1 }, { "", "TOTALPAGES", -1 } }; int nparts = sizeof(parts)/sizeof(parts[0]); @@ -591,13 +593,16 @@ 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[2].code, "page", level ); + parts[3].code, "page", level ); } /* If both PAGESTART and PAGEEND are defined */ else { mods_output_extents( f, outptr, parts[0].code, - parts[1].code, parts[2].code, "page", level ); + parts[1].code, parts[3].code, "page", level ); } return 1; @@ -763,6 +768,7 @@ { convert sn_types[] = { { "isbn", "ISBN", 0 }, + { "isbn", "ISBN13", 0 }, { "lccn", "LCCN", 0 }, { "issn", "ISSN", 0 }, { "citekey", "REFNUM", 0 }, diff --git a/bibutils/modsout.h b/bibutils/modsout.h --- a/bibutils/modsout.h +++ b/bibutils/modsout.h @@ -1,7 +1,7 @@ /* * modsout.h * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2014 * * Source code released under the GPL version 2 * 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 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Source code released under the GPL version 2 * @@ -363,13 +363,14 @@ int name_addmultielement( fields *info, char *tag, list *tokens, int begin, int end, int level ) { + int status, ok = 1; newstr name; - int ok; newstr_init( &name ); name_construct_multi( &name, tokens, begin, end ); - ok = fields_add( info, tag, name.data, level ); + status = fields_add( info, tag, name.data, level ); + if ( status!=FIELDS_OK ) ok = 0; newstr_free( &name ); @@ -386,13 +387,14 @@ int name_addsingleelement( fields *info, char *tag, char *name, int level, int corp ) { + int status, ok = 1; newstr outtag; - int ok; newstr_init( &outtag ); newstr_strcpy( &outtag, tag ); if ( !corp ) newstr_strcat( &outtag, ":ASIS" ); else newstr_strcat( &outtag, ":CORP" ); - ok = fields_add( info, outtag.data, name, level ); + status = fields_add( info, outtag.data, name, level ); + if ( status!=FIELDS_OK ) ok = 0; newstr_free( &outtag ); return ok; } @@ -428,7 +430,7 @@ } newstr_findreplace( inname, ",", ", " ); - list_tokenize( &tokens, inname, ' ', 1 ); + list_tokenize( &tokens, inname, " ", 1 ); if ( tokens.n==1 ) { newstr_newstrcpy( outname, inname ); @@ -486,7 +488,7 @@ int name_add( fields *info, char *tag, char *q, int level, list *asis, list *corps ) { - int ok, nametype, ret = 1; + int ok, status, nametype, ret = 1; newstr inname, outname; list tokens; @@ -500,10 +502,12 @@ q = name_copy( &inname, q ); nametype = name_parse( &outname, &inname, asis, corps ); - if ( !nametype ) return 0; + if ( !nametype ) { ret = 0; goto out; } - if ( nametype==1 ) - ok = fields_add( info, tag, outname.data, level ); + if ( nametype==1 ) { + status = fields_add( info, tag, outname.data, level ); + ok = ( status==FIELDS_OK ) ? 1 : 0; + } else if ( nametype==2 ) ok = name_addsingleelement( info, tag, outname.data, level, 0 ); else @@ -515,7 +519,7 @@ out: newstrs_free( &inname, &outname, NULL ); - newstr_free( &outname ); + list_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 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Source code released under the GPL version 2 * diff --git a/bibutils/newstr.c b/bibutils/newstr.c --- a/bibutils/newstr.c +++ b/bibutils/newstr.c @@ -1,9 +1,9 @@ /* * newstr.c * - * Version: 04/21/13 + * Version: 04/27/14 * - * Copyright (c) Chris Putnam 1999-2013 + * Copyright (c) Chris Putnam 1999-2014 * * Source code released under the GPL version 2 * @@ -20,10 +20,17 @@ #include "newstr.h" #include "is_ws.h" +/* Do not use asserts in NEWSTR_NOASSERT defined */ +#ifdef NEWSTR_NOASSERT +#define NDEBUG +#endif #include #define newstr_initlen (64) + +/* Clear memory in resize/free if NEWSTR_PARANOIA defined */ + #ifndef NEWSTR_PARANOIA static void @@ -43,11 +50,8 @@ s->dim = size; } -/* define as no-op */ -static inline void -newstr_nullify( newstr *s ) -{ -} +/* define as a no-op */ +#define newstr_nullify( s ) #else @@ -91,7 +95,7 @@ } void -newstr_initstr( newstr *s, char *initstr ) +newstr_initstr( newstr *s, const char *initstr ) { assert( s ); assert( initstr ); @@ -113,15 +117,27 @@ 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; - char *cp; + const char *cp; newstr_empty( s ); va_start( ap, s ); do { - cp = va_arg( ap, char * ); + cp = va_arg( ap, const char * ); if ( cp ) newstr_strcat( s, cp ); } while ( cp ); va_end( ap ); @@ -180,6 +196,14 @@ } void +newstr_delete( newstr *s ) +{ + assert( s ); + newstr_free( s ); + free( s ); +} + +void newstr_empty( newstr *s ) { assert( s ); @@ -208,10 +232,11 @@ 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 ); + newstr_realloc( s, s->len*2 ); s->data[s->len++] = newchar; s->data[s->len] = '\0'; } @@ -224,8 +249,8 @@ * Since we can progress more than one byte at p, return the * properly updated pointer p. */ -char * -newstr_addutf8( newstr *s, char *p ) +const char * +newstr_addutf8( newstr *s, const char *p ) { if ( ! ((*p) & 128 ) ) { newstr_addchar( s, *p ); @@ -247,11 +272,12 @@ } void -newstr_prepend( newstr *s, char *addstr ) +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 { @@ -276,7 +302,7 @@ } static inline void -newstr_strcat_internal( newstr *s, char *addstr, unsigned long n ) +newstr_strcat_internal( newstr *s, const char *addstr, unsigned long n ) { newstr_strcat_ensurespace( s, n ); strncat( &(s->data[s->len]), addstr, n ); @@ -293,7 +319,7 @@ } void -newstr_strcat( newstr *s, char *addstr ) +newstr_strcat( newstr *s, const char *addstr ) { unsigned long n; assert( s && addstr ); @@ -304,41 +330,78 @@ void newstr_segcat( newstr *s, char *startat, char *endat ) { - size_t seglength; - char *p, *q; + unsigned long n; + char *p; assert( s && startat && endat ); assert( (size_t) startat < (size_t) endat ); - seglength=(size_t) endat - (size_t) startat; - if ( !s->data || !s->dim ) - newstr_initalloc( s, seglength+1 ); - else { - if ( s->len + seglength + 1 > s->dim ) - newstr_realloc( s, s->len + seglength+1 ); - } - q = &(s->data[s->len]); + if ( startat==endat ) return; + + n = 0; p = startat; - while ( *p && p!=endat ) *q++ = *p++; - *q = '\0'; - s->len += seglength; + 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; idata || !s->dim ) newstr_initalloc( s, m ); - else if ( n+1 > s->dim ) + else if ( m > s->dim ) newstr_realloc( s, m ); } static inline void -newstr_strcpy_internal( newstr *s, char *p, unsigned long n ) +newstr_strcpy_internal( newstr *s, const char *p, unsigned long n ) { newstr_strcpy_ensurespace( s, n ); - strcpy( s->data, p ); + strncpy( s->data, p, n ); + s->data[n] = '\0'; s->len = n; } @@ -352,7 +415,7 @@ } void -newstr_strcpy( newstr *s, char *addstr ) +newstr_strcpy( newstr *s, const char *addstr ) { unsigned long n; assert( s && addstr ); @@ -360,65 +423,63 @@ newstr_strcpy_internal( s, addstr, n ); } -newstr * -newstr_strdup( char *s1 ) +/* newstr_segcpy( s, start, end ); + * + * copies [start,end) into s + */ +void +newstr_segcpy( newstr *s, char *startat, char *endat ) { - newstr *s2 = newstr_new(); - if ( s2 ) - newstr_strcpy( s2, s1 ); - return s2; + 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] to in[stop] (includes stop) into s + * copies in[start,stop) (excludes stop) into s */ void -newstr_indxcpy( newstr *s, char *p, int start, int stop ) +newstr_indxcpy( newstr *s, char *p, unsigned long start, unsigned long stop ) { - int i; - assert( s ); - assert( p ); + 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 ) + for ( i=start; idata[i-start] = p[i]; - s->data[i] = '\0'; - s->len = stop-start+1; -} - -void -newstr_indxcat( newstr *s, char *p, int start, int stop ) -{ - int i; - assert( s ); - assert( p ); - assert( start <= stop ); - for ( i=start; i<=stop; ++i ) - newstr_addchar( s, p[i] ); + s->len = stop-start; + s->data[s->len] = '\0'; } -/* newstr_segcpy( s, start, end ); - * - * copies [start,end) into s - */ -void -newstr_segcpy( newstr *s, char *startat, char *endat ) +newstr * +newstr_strdup( const char *s1 ) { - size_t n; - char *p, *q; - - assert( s && startat && endat ); - assert( ((size_t) startat) <= ((size_t) endat) ); - - n = (size_t) endat - (size_t) startat; - newstr_strcpy_ensurespace( s, n ); - q = s->data; - p = startat; - while ( *p && p!=endat ) *q++ = *p++; - *q = '\0'; - s->len = n; + newstr *s2 = newstr_new(); + if ( s2 ) + newstr_strcpy( s2, s1 ); + return s2; } void @@ -446,7 +507,7 @@ */ int -newstr_findreplace( newstr *s, char *find, char *replace ) +newstr_findreplace( newstr *s, const char *find, const char *replace ) { long diff; size_t findstart, searchstart; @@ -503,6 +564,7 @@ { int bufpos = *pbufpos, done = 0; char *ok; + assert( fp && outs ); newstr_empty( outs ); while ( !done ) { while ( buf[bufpos] && buf[bufpos]!='\r' && buf[bufpos]!='\n' ) @@ -573,29 +635,26 @@ void newstr_trimstartingws( newstr *s ) { - unsigned char still_ws; - unsigned long n, m; + char *p, *q; + int n; assert( s ); if ( s->len==0 || !is_ws( s->data[0] ) ) return; - m = n = 0; - still_ws = 1; - while ( m <= s->len ) { - if ( still_ws && !is_ws( s->data[ m ] ) ) { - still_ws = 0; - } - if ( !still_ws ) { - s->data[ n ] = s->data[ m ]; - n++; - } - m++; + 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 ) @@ -610,6 +669,7 @@ int newstr_match_first( newstr *s, char ch ) { + assert( s ); if ( !s->len ) return 0; if ( s->data[0] == ch ) return 1; return 0; @@ -618,37 +678,81 @@ 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, int n ) +newstr_trimbegin( newstr *s, unsigned long n ) { - int i; + char *p, *q; + assert( s ); - if ( s->len - n < 1 ) newstr_empty( s ); - for ( i=1; i<=s->len; ++i ) /* pick up '\0' with '<=' */ - s->data[i-1] = s->data[i]; - s->len -= n; + + 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, int n ) +newstr_trimend( newstr *s, unsigned long n ) { assert( s ); - if ( s->len - n < 1 ) newstr_empty( s ); - else { - s->len -= n; - s->data[ s->len ] = '\0'; + + 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 in->len ) max = in->len; + for ( i=pos; idata[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; @@ -709,31 +813,28 @@ } int -newstr_newstrcmp( newstr *s, newstr *t ) +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 ) { - newstr ns; - unsigned long i; - + unsigned long i, max; + char tmp; assert( s ); - - if ( s->len==0 ) return; - newstr_init( &ns ); - i = s->len; - do { - i--; - newstr_addchar( &ns, s->data[i] ); - } while ( i>0 ); - newstr_swapstrings( s, &ns ); - newstr_free( &ns ); + max = s->len / 2; + for ( i=0; idata[ i ]; + s->data[ i ] = s->data[ s->len - 1 - i ]; + s->data[ s->len - 1 - i ] = tmp; + } } int @@ -741,11 +842,15 @@ { 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 ) eol = 1; + if ( ch == EOF ) { + if ( s->len ) return 1; + else return 0; + } else if ( ch == '\n' ) eol = 1; else if ( ch == '\r' ) { ch = fgetc( fp ); @@ -761,14 +866,15 @@ /* * s = "Hi!\0", s.len = 3 * - * newstr_char( s, 0 ) = 'H' newstr_revchar( s, 0 ) = '\0' - * newstr_char( s, 1 ) = 'i' newstr_revchar( s, 1 ) = '!' - * newstr_char( s, 2 ) = '!' newstr_revchar( s, 2 ) = 'i' - * newstr_char( s, 3 ) = '\0' newstr_revchar( s, 3 ) = 'H' + * 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 ]; } @@ -776,6 +882,20 @@ 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 ]; + 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 --- a/bibutils/newstr.h +++ b/bibutils/newstr.h @@ -1,9 +1,9 @@ /* * newstr.h * - * Version: 04/21/13 + * Version: 04/27/14 * - * Copyright (c) Chris Putnam 1999-2013 + * Copyright (c) Chris Putnam 1999-2014 * * Source code released under the GPL version 2 * @@ -20,9 +20,10 @@ } newstr; newstr *newstr_new ( void ); +void newstr_delete ( newstr *s ); void newstr_init ( newstr *s ); -void newstr_initstr ( newstr *s, char *initstr ); +void newstr_initstr ( newstr *s, const char *initstr ); void newstr_empty ( newstr *s ); void newstr_free ( newstr *s ); @@ -31,52 +32,70 @@ void newstrs_free ( newstr *s, ... ); void newstr_mergestrs ( newstr *s, ... ); -newstr *newstr_strdup ( char *buf ); +newstr *newstr_strdup ( const char *p ); void newstr_addchar ( newstr *s, char newchar ); void newstr_reverse ( newstr *s ); -char *newstr_addutf8 ( newstr *s, char *p ); -void newstr_strcat ( newstr *s, char *addstr ); +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 ); -void newstr_prepend ( newstr *s, char *addstr ); -void newstr_strcpy ( newstr *s, char *addstr ); +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, int start, int stop ); -void newstr_indxcat ( newstr *s, char *p, int start, int stop ); +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, char *find, char *replace ); +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, int n ); -void newstr_trimend ( newstr *s, int n ); +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 ( newstr *s, newstr *t ); +int newstr_newstrcmp ( const newstr *s, const newstr *t ); -/* NEWSTR_PARANOIA +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 */ -#undef NEWSTR_PARANOIA +/* #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 --- a/bibutils/newstr_conv.c +++ b/bibutils/newstr_conv.c @@ -1,7 +1,7 @@ /* * newstr_conv.c * - * Copyright (c) Chris Putnam 1999-2013 + * Copyright (c) Chris Putnam 1999-2014 * * Source code released under the GPL version 2 * @@ -50,13 +50,13 @@ } static void -addutf8char( newstr *s, unsigned int ch, int xmlout, int utf8out ) +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 > 1 ) + if ( ch > 127 && xmlout == NEWSTR_CONV_XMLOUT_ENTITIES ) { addentity( s, ch ); return; } } nc = utf8_encode( ch, code ); @@ -65,13 +65,13 @@ } static void -addgb18030char( newstr *s, unsigned int ch, int xmlout, int utf8out ) +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 > 1 ) + if ( ch > 127 && xmlout == NEWSTR_CONV_XMLOUT_ENTITIES ) { addentity( s, ch ); return; } } nc = gb18030_encode( ch, code ); @@ -89,7 +89,7 @@ * output the unicode. */ if ( utf8out && !strcmp( buf, "?" ) ) { - addutf8char( s, ch, xmlout, utf8out ); + addutf8char( s, ch, xmlout ); } else { newstr_strcat( s, buf ); } @@ -151,9 +151,9 @@ if ( latexout ) { addlatexchar( s, ch, xmlout, utf8out ); } else if ( utf8out ) { - addutf8char( s, ch, xmlout, utf8out ); + addutf8char( s, ch, xmlout ); } else if ( charsetout==CHARSET_GB18030 ) { - addgb18030char( s, ch, xmlout, utf8out ); + addgb18030char( s, ch, xmlout ); } else { c = charset_lookupuni( charsetout, ch ); if ( xmlout ) addxmlchar( s, c ); @@ -173,9 +173,9 @@ unsigned int pos = 0; unsigned int ch; newstr ns; - int ok; + int ok = 1; - if ( !s || s->len==0 ) return 1; + if ( !s || s->len==0 ) return ok; newstr_init( &ns ); @@ -185,13 +185,13 @@ while ( s->data[pos] ) { ch = get_unicode( s, &pos, charsetin, latexin, utf8in, xmlin ); ok = write_unicode( &ns, ch, charsetout, latexout, utf8out, xmlout ); - if ( !ok ) return 0; + if ( !ok ) goto out; } newstr_swapstrings( s, &ns ); - +out: newstr_free( &ns ); - return 1; + return ok; } diff --git a/bibutils/newstr_conv.h b/bibutils/newstr_conv.h --- a/bibutils/newstr_conv.h +++ b/bibutils/newstr_conv.h @@ -1,13 +1,17 @@ /* * newstring_conv.h * - * Copyright (c) Chris Putnam 1999-2013 + * 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" 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 2003-2013 + * Copyright (c) Chris Putnam 2003-2014 * * Source code released under the GPL version 2 * @@ -20,6 +20,9 @@ #include "doi.h" #include "risin.h" +/***************************************************** + PUBLIC: void risin_initparams() +*****************************************************/ void risin_initparams( param *p, const char *progname ) { @@ -49,6 +52,10 @@ else p->progname = strdup( progname ); } +/***************************************************** + PUBLIC: int risin_readf() +*****************************************************/ + /* RIS definition of a tag is strict: character 1 = uppercase alphabetic character character 2 = uppercase alphabetic character or digit @@ -130,6 +137,10 @@ return haveref; } +/***************************************************** + PUBLIC: int risin_processf() +*****************************************************/ + static char* process_line2( newstr *tag, newstr *data, char *p ) { @@ -161,7 +172,7 @@ risin_processf( fields *risin, char *p, char *filename, long nref ) { newstr tag, data; - int n; + int status, n; newstrs_init( &tag, &data, NULL ); @@ -170,7 +181,8 @@ p = process_line( &tag, &data, p ); /* no anonymous fields allowed */ if ( tag.len ) - fields_add( risin, tag.data, data.data, 0 ); + 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 ); @@ -188,15 +200,42 @@ return 1; } +/***************************************************** + PUBLIC: int risin_typef() +*****************************************************/ + +int +risin_typef( fields *risin, char *filename, int nref, param *p, variants *all, int nall ) +{ + 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; +} + +/***************************************************** + 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 = is_doi( s->data ); + int doi, status; + doi = is_doi( s->data ); if ( doi!=-1 ) - return fields_add( f, "DOI", &(s->data[doi]), level ); + status = fields_add( f, "DOI", &(s->data[doi]), level ); else - return fields_add( f, tag, s->data, level ); + status = fields_add( f, tag, s->data, level ); + if ( status==FIELDS_OK ) return BIBL_OK; + else return BIBL_ERR_MEMERR; } static int @@ -221,35 +260,45 @@ static int risin_addfile( fields *f, char *tag, newstr *s, int level ) { + int status, n; char *p; - int n; /* if URL is file:///path/to/xyz.pdf, only store "///path/to/xyz.pdf" */ n = is_uri_file_scheme( s->data ); if ( n ) { /* skip past "file:" and store only actual path */ p = s->data + n; - return fields_add( f, tag, p, level ); + status = fields_add( f, tag, p, level ); + if ( status==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 ) { - return fields_add( f, "URL", s->data, level ); + status = fields_add( f, "URL", s->data, level ); + if ( status==FIELDS_OK ) return BIBL_OK; + else return BIBL_ERR_MEMERR; } /* badly formed, RIS wants URI, but store value anyway */ - return fields_add( f, tag, s->data, level ); + status = fields_add( f, tag, s->data, level ); + if ( status==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 ) { - int doi = is_doi( s->data ); - if ( doi!=-1 ) - return fields_add( f, "DOI", &(s->data[doi]), level ); - else return 1; + int status, doi; + doi = is_doi( s->data ); + if ( doi!=-1 ) { + status = fields_add( f, "DOI", &(s->data[doi]), level ); + if ( status==FIELDS_OK ) return BIBL_OK; + else return BIBL_ERR_MEMERR; + } + else return BIBL_OK; } static int @@ -257,60 +306,46 @@ { char *p = d->data; newstr date; - int part = ( !strncasecmp( tag, "PART", 4 ) ), ok; + int part, status; + part = ( !strncasecmp( tag, "PART", 4 ) ); + newstr_init( &date ); while ( *p && *p!='/' ) newstr_addchar( &date, *p++ ); if ( *p=='/' ) p++; if ( date.len>0 ) { - if ( part ) ok = fields_add( f, "PARTYEAR", date.data, level ); - else ok = fields_add( f, "YEAR", date.data, level ); - if ( !ok ) return 0; + if ( part ) status = fields_add( f, "PARTYEAR", date.data, level ); + else status = fields_add( f, "YEAR", date.data, level ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } newstr_empty( &date ); while ( *p && *p!='/' ) newstr_addchar( &date, *p++ ); if ( *p=='/' ) p++; if ( date.len>0 ) { - if ( part ) ok = fields_add( f, "PARTMONTH", date.data, level ); - else ok = fields_add( f, "MONTH", date.data, level ); - if ( !ok ) return 0; + if ( part ) status = fields_add( f, "PARTMONTH", date.data, level ); + else status = fields_add( f, "MONTH", date.data, level ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } newstr_empty( &date ); while ( *p && *p!='/' ) newstr_addchar( &date, *p++ ); if ( *p=='/' ) p++; if ( date.len>0 ) { - if ( part ) ok = fields_add( f, "PARTDAY", date.data, level ); - else ok = fields_add( f, "DAY", date.data, level ); - if ( !ok ) return 0; + if ( part ) status = fields_add( f, "PARTDAY", date.data, level ); + else status = fields_add( f, "DAY", date.data, level ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } newstr_empty( &date ); while ( *p ) newstr_addchar( &date, *p++ ); if ( date.len>0 ) { - if ( part ) ok = fields_add( f, "PARTDATEOTHER", date.data,level); - else ok = fields_add( f, "DATEOTHER", date.data, level ); - if ( !ok ) return 0; + if ( part ) status = fields_add( f, "PARTDATEOTHER", date.data,level); + else status = fields_add( f, "DATEOTHER", date.data, level ); + if ( status!=FIELDS_OK ) return BIBL_ERR_MEMERR; } newstr_free( &date ); - return 1; -} - -int -risin_typef( fields *risin, char *filename, int nref, param *p, variants *all, int nall ) -{ - 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; + return BIBL_OK; } static void @@ -322,10 +357,18 @@ } } +static int +risin_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 risin_convertf( fields *risin, fields *f, int reftype, param *p, variants *all, int nall ) { - int process, level, i, n, nfields, ok; + int process, level, i, n, nfields, ok, fstatus, status = BIBL_OK; char *outtag, *tag, *value; newstr *t, *d; @@ -345,43 +388,49 @@ switch ( process ) { case SIMPLE: - ok = fields_add( f, outtag, d->data, level ); + status = risin_simple( f, outtag, d->data, level ); break; 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; case SERIALNO: ok = addsn( f, d->data, level ); + if ( ok ) status = BIBL_OK; + else status = BIBL_ERR_MEMERR; break; case DATE: - ok = risin_adddate( f, outtag, d, level ); + status = risin_adddate( f, outtag, d, level ); break; case NOTES: - ok = risin_addnotes( f, outtag, d, level ); + status = risin_addnotes( f, outtag, d, level ); break; case DOI: - ok = risin_adddoi( f, outtag, d, level ); + status = risin_adddoi( f, outtag, d, level ); break; case LINKEDFILE: - ok = risin_addfile( f, outtag, d, level ); + status = risin_addfile( f, outtag, d, level ); break; default: - ok = 1; + status = BIBL_OK; break; } - if ( !ok ) return BIBL_ERR_MEMERR; + if ( status!=BIBL_OK ) return status; } /* look for thesis-type hint */ @@ -395,11 +444,11 @@ !strcasecmp(value,"Diploma Thesis")|| !strcasecmp(value,"Doctoral Thesis")|| !strcasecmp(value,"Habilitation Thesis")) { - ok = fields_add( f, "GENRE", value, 0 ); - if ( !ok ) return BIBL_ERR_MEMERR; + fstatus = fields_add( f, "GENRE", value, 0 ); + if ( fstatus!=FIELDS_OK ) return BIBL_ERR_MEMERR; } } } - return BIBL_OK; + return status; } diff --git a/bibutils/risin.h b/bibutils/risin.h --- a/bibutils/risin.h +++ b/bibutils/risin.h @@ -1,7 +1,7 @@ /* * risin.h * - * Copyright (c) Chris Putnam 2003-2013 + * Copyright (c) Chris Putnam 2003-2014 * * Source code released under the GPL version 2 * diff --git a/bibutils/risout.c b/bibutils/risout.c --- a/bibutils/risout.c +++ b/bibutils/risout.c @@ -28,7 +28,7 @@ p->latexout = 0; p->utf8out = BIBL_CHARSET_UTF8_DEFAULT; p->utf8bom = BIBL_CHARSET_BOM_DEFAULT; - p->xmlout = 0; + p->xmlout = BIBL_XMLOUT_FALSE; p->nosplittitle = 0; p->verbose = 0; p->addcount = 0; @@ -73,6 +73,41 @@ TYPE_UNPUBLISHED, /* unpublished */ }; +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; + } +} + typedef struct match_type { char *name; int type; @@ -82,10 +117,11 @@ * */ static int -get_type_genre( fields *f ) +get_type_genre( fields *f, param *p ) { match_type match_genres[] = { { "academic journal", TYPE_ARTICLE }, + { "article", TYPE_ARTICLE }, { "journal article", TYPE_ARTICLE }, { "magazine", TYPE_MAGARTICLE }, { "conference publication", TYPE_CONF }, @@ -109,18 +145,25 @@ }; int nmatch_genres = sizeof( match_genres ) / sizeof( match_genres[0] ); int type, i, j; - char *value; + char *tag, *value; type = TYPE_UNKNOWN; for ( i=0; iverbose ) { + 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 ( type==TYPE_UNKNOWN ) { if ( !strcasecmp( value, "periodical" ) ) type = TYPE_ARTICLE; @@ -138,6 +181,13 @@ } + if ( p->verbose ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Type from genre element: " ); + write_type( stderr, type ); + fprintf( stderr, "\n" ); + } + return type; } @@ -145,7 +195,7 @@ * */ static int -get_type_resource( fields *f ) +get_type_resource( fields *f, param *p ) { match_type match_res[] = { { "software, multimedia", TYPE_PROGRAM }, @@ -167,8 +217,21 @@ 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 ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Type from resource element: " ); + write_type( stderr, type ); + fprintf( stderr, "\n" ); + } + vplist_free( &a ); return type; } @@ -176,36 +239,58 @@ /* Try to determine type of reference from and */ /* */ static int -get_type_issuance( fields *f ) +get_type_issuance( fields *f, param *p ) { int type = TYPE_UNKNOWN; - int i, monographic = 0, text = 0, monographic_level = 0; + int i, monographic = 0, monographic_level = 0; +// int text = 0; for ( i=0; in; ++i ) { if ( !strcasecmp( f->tag[i].data, "issuance" ) && !strcasecmp( f->data[i].data, "MONOGRAPHIC" ) ){ monographic = 1; monographic_level = f->level[i]; } - if ( !strcasecmp( f->tag[i].data, "typeOfResource" ) && - !strcasecmp( f->data[i].data,"text") ) { - text = 1; - } +// if ( !strcasecmp( f->tag[i].data, "typeOfResource" ) && +// !strcasecmp( f->data[i].data,"text") ) { +// text = 1; +// } } - if ( monographic && text ) { +// if ( monographic && text ) { + if ( monographic ) { if ( monographic_level==0 ) type=TYPE_BOOK; else if ( monographic_level>0 ) type=TYPE_INBOOK; } + + if ( p->verbose ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Type from issuance/typeOfReference elements: " ); + write_type( stderr, type ); + fprintf( stderr, "\n" ); + } + return type; } static int -get_type( fields *f ) +get_type( fields *f, param *p ) { int type; - type = get_type_genre( f ); - if ( type==TYPE_UNKNOWN ) type = get_type_resource( f ); - if ( type==TYPE_UNKNOWN ) type = get_type_issuance( f ); - if ( type==TYPE_UNKNOWN ) type = TYPE_STD; + type = get_type_genre( f, p ); + if ( type==TYPE_UNKNOWN ) type = get_type_resource( f, p ); + if ( type==TYPE_UNKNOWN ) type = get_type_issuance( f, p ); + if ( type==TYPE_UNKNOWN ) { + if ( fields_maxlevel( f ) > 0 ) type = TYPE_INBOOK; + else type = TYPE_STD; + } + + if ( p->verbose ) { + if ( p->progname ) fprintf( stderr, "%s: ", p->progname ); + fprintf( stderr, "Final type: " ); + write_type( stderr, type ); + fprintf( stderr, "\n" ); + } + + return type; } @@ -525,7 +610,7 @@ risout_write( fields *f, FILE *fp, param *p, unsigned long refnum ) { int type; - type = get_type( f ); + type = get_type( f, p ); output_type( fp, type, p ); output_allpeople( fp, f, type ); 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 2005-2013 + * Copyright (c) Chris Putnam 2005-2014 * * Source code released under the GPL version 2 * @@ -12,25 +12,44 @@ int addsn( fields *info, char *buf, int level ) { - int ndigits=0, issn=0, isbn=0; - char *p = buf; + int ndigits, issn=0, isbn=0, isbn10=0, isbn13=0, status; + char *p = buf, *tag; if ( !strncasecmp( p, "ISSN", 4 ) ) issn=1; else if ( !strncasecmp( p, "ISBN", 4 ) ) isbn=1; + if ( isbn ) { + ndigits = 0; + while ( *p && !(ndigits && (*p==';'||*p==':')) ) { + if ( ( *p>='0' && *p<='9' ) || *p=='x' || *p=='X' ) + ndigits++; + p++; + } + if ( ndigits==13 ) isbn13 = 1; + else /* ( ndigits==10) */ isbn10 = 1; + } + if ( !issn && !isbn ) { /* a lot have semicolons between multiple ISBN's for paperbacks and hardbacks with different numbers */ + ndigits = 0; while ( *p && !(ndigits && (*p==';'||*p==':')) ) { - if ( ( *p>='0' && *p<='9' ) || *p=='x' || *p=='X' ) + if ( ( *p>='0' && *p<='9' ) || *p=='x' || *p=='X' ) ndigits++; p++; } if ( ndigits==8 ) issn = 1; - else if ( ndigits==10 || ndigits==13 ) isbn = 1; + else if ( ndigits==10 ) isbn10 = 1; + else if ( ndigits==13 ) isbn13 = 1; } - if ( issn ) return fields_add( info, "ISSN", buf, level ); - else if ( isbn ) return fields_add( info, "ISBN", buf, level ); - else return fields_add( info, "SERIALNUMBER", buf, level ); + if ( issn ) tag = "ISSN"; + else if ( isbn10 ) tag = "ISBN"; + else if ( isbn13 ) tag = "ISBN13"; + else tag = "SERIALNUMBER"; + + status = fields_add( info, tag, buf, level ); + + if ( status==FIELDS_OK ) return 1; + else return 0; } 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 2005-2013 + * Copyright (c) Chris Putnam 2005-2014 * * 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 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Source code released under the GPL version 2 * @@ -22,7 +22,7 @@ { newstr title, subtitle; char *p, *q; - int ok; + int status; newstr_init( &title ); newstr_init( &subtitle ); @@ -45,17 +45,17 @@ if ( strncasecmp( "SHORT", tag, 5 ) ) { if ( title.len>0 ) { - ok = fields_add( info, "TITLE", title.data, level ); - if ( !ok ) return 0; + status = fields_add( info, "TITLE", title.data, level ); + if ( status!=FIELDS_OK ) return 0; } if ( subtitle.len>0 ) { - ok = fields_add( info, "SUBTITLE", subtitle.data, level ); - if ( !ok ) return 0; + status = fields_add( info, "SUBTITLE", subtitle.data, level ); + if ( status!=FIELDS_OK ) return 0; } } else { if ( title.len>0 ) { - ok = fields_add( info, "SHORTTITLE", title.data, level ); - if ( !ok ) return 0; + status = fields_add( info, "SHORTTITLE", title.data, level ); + if ( status!=FIELDS_OK ) return 0; } /* no SHORT-SUBTITLE! */ } 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 2004-2013 + * Copyright (c) Chris Putnam 2004-2014 * * Source code released under the GPL verison 2 * diff --git a/bibutils/wordin.c b/bibutils/wordin.c --- a/bibutils/wordin.c +++ b/bibutils/wordin.c @@ -16,6 +16,10 @@ #include "xml_encoding.h" #include "wordin.h" +/***************************************************** + PUBLIC: void wordin_initparams() +*****************************************************/ + void wordin_initparams( param *p, const char *progname ) { @@ -46,6 +50,10 @@ else p->progname = strdup( progname ); } +/***************************************************** + PUBLIC: int wordin_readf() +*****************************************************/ + static char * wordin_findstartwrapper( char *buf, int *ntype ) { @@ -93,25 +101,9 @@ return haveref; } -static inline int -xml_hasdata( xml *node ) -{ - if ( node && node->value && node->value->data ) return 1; - return 0; -} - -static inline char * -xml_data( xml *node ) -{ - return node->value->data; -} - -static inline int -xml_tagwithdata( xml *node, char *tag ) -{ - if ( !xml_hasdata( node ) ) return 0; - return xml_tagexact( node, tag ); -} +/***************************************************** + PUBLIC: int wordin_processf() +*****************************************************/ typedef struct xml_convert { char *in; /* The input tag */ @@ -120,126 +112,204 @@ int level; } xml_convert; -static void +/* wordin_person_last() + * + * From an xml list, extract the value from the first entry + * of xxxx and copy into name + * + * Additional yyyyy will be ignored. + * + * Returns BIBL_ERR_MEMERR on memory error, BIBL_OK otherwise. + */ +static int +wordin_person_last( xml *node, newstr *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; + } + return BIBL_OK; +} + +/* wordin_person_first() + * + * From an xml list, extract the value of any + * xxxx and append "|xxxx" to name. + * + * Returns BIBL_ERR_MEMERR on memory error, BIBL_OK otherwise + */ +static int +wordin_person_first( xml *node, newstr *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; + } + } + return BIBL_OK; +} + +static int wordin_person( xml *node, fields *info, char *type ) { - xml *last, *first; + int status, ret = BIBL_OK; newstr name; newstr_init( &name ); - last = node; - while ( last && !xml_tagexact( last, "b:Last" ) ) - last = last->next; - if ( last ) newstr_strcpy( &name, last->value->data ); - - first = node; - while ( first ) { - if ( xml_tagexact( first, "b:First" ) ) { - if ( name.len ) newstr_addchar( &name, '|' ); - newstr_strcat( &name, first->value->data ); - } - first = first->next; + status = wordin_person_last( node, &name ); + if ( status!=BIBL_OK ) { + ret = status; + goto out; } - fields_add( info, type, name.data, 0 ); + status = wordin_person_first( node, &name ); + if ( status!=BIBL_OK ) { + ret = status; + goto out; + } + status = fields_add( info, type, name.data, 0 ); + if ( status != FIELDS_OK ) ret = BIBL_ERR_MEMERR; +out: newstr_free( &name ); + return ret; } -static void +static int wordin_people( xml *node, fields *info, char *type ) { + int ret = BIBL_OK; if ( xml_tagexact( node, "b:Author" ) && node->down ) { - wordin_people( node->down, info, type ); + ret = wordin_people( node->down, info, type ); } else if ( xml_tagexact( node, "b:NameList" ) && node->down ) { - wordin_people( node->down, info, type ); + ret = wordin_people( node->down, info, type ); } else if ( xml_tagexact( node, "b:Person" ) ) { - if ( node->down ) wordin_person( node->down, info, type ); - if ( node->next ) wordin_people( node->next, info, type ); + if ( node->down ) ret = wordin_person( node->down, info, type ); + if ( ret!=BIBL_OK ) return ret; + if ( node->next ) ret = wordin_people( node->next, info, type ); } + return ret; } -static void +static int wordin_pages( xml *node, fields *info ) { + int i, status, ret = BIBL_OK; newstr sp, ep; char *p; - int i; + newstrs_init( &sp, &ep, NULL ); -/* - newstr_init( &sp ); - newstr_init( &ep ); -*/ + p = xml_data( node ); while ( *p && *p!='-' ) newstr_addchar( &sp, *p++ ); + if ( newstr_memerr( &sp ) ) { + ret = BIBL_ERR_MEMERR; + goto out; + } + if ( *p=='-' ) p++; while ( *p ) newstr_addchar( &ep, *p++ ); - if ( sp.len ) fields_add( info, "PAGESTART", sp.data, 1 ); + if ( newstr_memerr( &ep ) ) { + ret = BIBL_ERR_MEMERR; + goto out; + } + + if ( sp.len ) { + status = fields_add( info, "PAGESTART", sp.data, 1 ); + if ( status!=FIELDS_OK ) { + ret = BIBL_ERR_MEMERR; + goto out; + } + } + if ( ep.len ) { if ( sp.len > ep.len ) { for ( i=sp.len-ep.len; idown ) { - wordin_people( node->down, info, "AUTHOR" ); + ret = wordin_people( node->down, info, "AUTHOR" ); } else if ( xml_tagexact( node, "b:Editor" ) && node->down ) { - wordin_people( node->down, info, "EDITOR" ); + ret = wordin_people( node->down, info, "EDITOR" ); } } - if ( node->next ) wordin_reference( node->next, info ); + if ( ret==BIBL_OK && node->next ) wordin_reference( node->next, info ); + return ret; } -static void +static int wordin_assembleref( xml *node, fields *info ) { + int ret = BIBL_OK; if ( xml_tagexact( node, "b:Source" ) ) { - if ( node->down ) wordin_reference( node->down, info ); + if ( node->down ) ret = wordin_reference( node->down, info ); } else if ( node->tag->len==0 && node->down ) { - wordin_assembleref( node->down, info ); + ret = wordin_assembleref( node->down, info ); } + return ret; } int wordin_processf( fields *wordin, char *data, char *filename, long nref ) { + int status, ret = 1; xml top; + xml_init( &top ); xml_tree( data, &top ); - wordin_assembleref( &top, wordin ); + status = wordin_assembleref( &top, wordin ); xml_free( &top ); - return 1; + + if ( status==BIBL_ERR_MEMERR ) ret = 0; + return ret; } 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 2007-2013 + * Copyright (c) Chris Putnam 2007-2014 * * Source code released under the GPL version 2 * @@ -26,8 +26,10 @@ p->latexout = 0; p->utf8out = BIBL_CHARSET_UTF8_DEFAULT; p->utf8bom = BIBL_CHARSET_BOM_DEFAULT; - if ( !p->utf8out ) p->xmlout = 3; - else p->xmlout = 1; + if ( !p->utf8out ) + p->xmlout = BIBL_XMLOUT_ENTITIES; + else + p->xmlout = BIBL_XMLOUT_TRUE; p->nosplittitle = 0; p->verbose = 0; p->addcount = 0; @@ -575,6 +577,7 @@ { "NUMBER", "b:Issue", LEVEL_ANY }, { "PUBLICLAWNUMBER", "b:Volume", LEVEL_ANY }, { "SESSION", "b:Issue", LEVEL_ANY }, + { "URL", "b:Url", LEVEL_ANY }, }; int nparts=sizeof(parts)/sizeof(convert); diff --git a/bibutils/xml.c b/bibutils/xml.c --- a/bibutils/xml.c +++ b/bibutils/xml.c @@ -30,10 +30,10 @@ static void xmlattrib_add( xml_attrib *a, char *attrib, char *value ) { - if ( attrib ) list_add( &(a->attrib), attrib ); - else list_add( &(a->attrib), "" ); - if ( value ) list_add( &(a->value), value ); - else list_add( &(a->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), "" ); } static void @@ -238,10 +238,11 @@ p = xml_tree( p, nnode ); } else if ( type==XML_CLOSE ) { /*check to see if it's closing for this one*/ - return p; /* assume it's right for now*/ + goto out; /* assume it's right for now */ } } } +out: newstr_free( &tag ); return p; } @@ -335,24 +336,33 @@ } int -xml_tag_attrib( xml *node, char *s, char *attrib, char *value ) +xml_hasattrib( xml *node, char *attrib, char *value ) { xml_attrib *na = node->a; int i; - if ( !na || !xml_tagexact( node, s ) ) return 0; + if ( na ) { - for ( i=0; iattrib.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 ) ) - return 1; + for ( i=0; iattrib.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 ) ) + return 1; + } + } return 0; } +int +xml_tag_attrib( xml *node, char *s, char *attrib, char *value ) +{ + if ( !xml_tagexact( node, s ) ) return 0; + return xml_hasattrib( node, attrib, value ); +} + newstr * xml_getattrib( xml *node, char *attrib ) { @@ -366,5 +376,25 @@ ns = &(na->value.str[i]); } return ns; +} + +int +xml_hasdata( xml *node ) +{ + if ( node && node->value && node->value->data ) return 1; + return 0; +} + +char * +xml_data( xml *node ) +{ + return node->value->data; +} + +int +xml_tagwithdata( xml *node, char *tag ) +{ + if ( !xml_hasdata( 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 @@ -31,8 +31,12 @@ 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 ); extern char *xml_pns; /* global Namespace */ diff --git a/cbits/stub.c b/cbits/stub.c --- a/cbits/stub.c +++ b/cbits/stub.c @@ -9,3 +9,5 @@ { return stdin; } + +const char progname[] = "hs-bibutils"; 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: 5.0 -homepage: http://gorgias.mine.nu/repos/hs-bibutils/ +version: 5.5 +homepage: http://istitutocolli.org/repos/hs-bibutils/ synopsis: Haskell bindings to bibutils, the bibliography conversion utilities. @@ -30,38 +30,41 @@ cabal-version: >= 1.4 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/fields.c bibutils/fields.h bibutils/gb18030.c - bibutils/gb18030.h bibutils/gb18030_enumeration.c bibutils/is_ws.c - bibutils/intlis.h bibutils/intlis.c bibutils/is_ws.h - bibutils/isiin.c bibutils/isiin.h bibutils/isiout.c - bibutils/iso639_2.c bibutils/iso639_2.h bibutils/isiout.h - bibutils/isitypes.c 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/mycvout.c - 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/ristypes.c bibutils/vplist.c bibutils/vplist.h - bibutils/serialno.c bibutils/serialno.h bibutils/strsearch.c - bibutils/strsearch.h bibutils/title.c bibutils/title.h - bibutils/unicode. bibutils/unicode.c bibutils/utf8.c - bibutils/utf8.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/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/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/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/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 library exposed-modules: Text.Bibutils @@ -71,7 +74,7 @@ hs-source-dirs: src extensions: ForeignFunctionInterface include-dirs: bibutils - includes: bibutils.h + includes: bibutils.h c-sources: cbits/stub.c bibutils/adsout.c bibutils/adsout_journals.c @@ -83,15 +86,16 @@ 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_2.c - bibutils/latex.c bibutils/list.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/vplist.c - bibutils/serialno.c bibutils/strsearch.c bibutils/title.c - bibutils/unicode.c bibutils/utf8.c bibutils/wordin.c - bibutils/wordout.c bibutils/xml.c bibutils/xml_encoding.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/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 if impl(ghc >= 6.10) build-depends: base >= 4, syb