diff --git a/INSTALL b/INSTALL --- a/INSTALL +++ b/INSTALL @@ -169,27 +169,13 @@ on MacOS X computers. If you don't already have MacPorts, follow [these instructions for installing it](http://trac.macosforge.org/projects/macports/wiki/InstallingMacPorts). -Note that you'll need OSX 10.4 and the latest version of XCode Tools. -Once you've installed MacPorts, you'll need to create a local ports -repository and copy the [pandoc `Portfile`](Portfile) into it: - - mkdir -p ~/ports/textproc/pandoc - cp Portfile ~/ports/textproc/pandoc/ - -Then (as root) open `/opt/local/etc/macports/sources.conf` in an editor -and insert the line - - file:///Users/yourusername/ports - -before the line beginning `rsync:`, so MacPorts will know about your -local repository. - -Now you should be able to install pandoc by typing +Once you've installed MacPorts, you can install pandoc by typing: + sudo port sync # to get the most recent ports sudo port install pandoc -Since pandoc requires GHC to build, the process may take a long time. +Since pandoc depends on GHC, the process may take a long time. Installing the Windows binary ============================= @@ -205,18 +191,14 @@ Installing pandoc on Debian =========================== -This method will work on Debian linux and derivatives (including Ubuntu). -Download the latest debian package from the [pandoc home page]. -To install it, just type - - sudo dpkg -i pandoc_0.xx_i386.deb - -where `pandoc_0.xx_i386.deb` is the filename of the debian package. -To uninstall later, use +Pandoc is now in the debian unstable archive, and can be installed +using `apt-get` (as root): - sudo apt-get remove pandoc + apt-get install pandoc # the program, shell scripts, and docs + apt-get install libghc6-pandoc-dev # the libraries + apt-get install pandoc-doc # library documentation -[pandoc home page]: http://sophos.berkeley.edu/macfarlane/pandoc/ +Thanks to Recai Oktaş for setting up the debian packages. Installing pandoc on FreeBSD ============================ diff --git a/Makefile b/Makefile --- a/Makefile +++ b/Makefile @@ -18,7 +18,7 @@ #------------------------------------------------------------------------------- NAME := $(shell sed -ne 's/^[Nn]ame:[[:space:]]*//p' $(CABAL)) THIS := $(shell echo $(NAME) | tr A-Z a-z) -VERSION := $(shell sed -ne 's/^version[[:space:]]*=[[:space:]]*"\([^"]*\)"/\1/p' $(SRCDIR)/Main.hs) +VERSION := $(shell sed -ne 's/^[Vv]ersion:[[:space:]]*//p' $(CABAL)) RELNAME := $(THIS)-$(VERSION) EXECSBASE := $(shell sed -ne 's/^[Ee]xecutable:[[:space:]]*//p' $(CABAL)) @@ -239,17 +239,12 @@ # FreeBSD port .PHONY: freebsd freebsd_dest:=freebsd -freebsd_distinfo:=$(freebsd_dest)/distinfo freebsd_makefile:=$(freebsd_dest)/Makefile freebsd_template:=$(freebsd_makefile).in -cleanup_files+=$(freebsd_makefile) $(freebsd_distinfo) -freebsd : $(freebsd_makefile) $(freebsd_distinfo) +cleanup_files+=$(freebsd_makefile) +freebsd : $(freebsd_makefile) $(freebsd_makefile) : $(freebsd_template) sed -e 's/@VERSION@/$(VERSION)/' $< > $@ -$(freebsd_distinfo) : tarball - echo "MD5 ($(tarball)) = $(word 1, $(shell md5sum $(tarball)))" > $@ ; \ - echo "SHA256 ($(tarball)) = $(word 1, $(shell sha256sum $(tarball)))" >> $@ ; \ - echo "SIZE ($(tarball)) = $(word 5, $(shell ls -l $(tarball)))" >> $@ # MacPort .PHONY: macport @@ -348,8 +343,6 @@ cp changelog $(web_dest)/ ; \ cp README $(web_dest)/ ; \ cp INSTALL $(web_dest)/ ; \ - cp $(portfile) $(web_dest)/ ; \ - cp ../$(deb_main) $(web_dest)/ ; \ cp $(MANDIR)/man1/pandoc.1.md $(web_dest)/ ; \ cp $(MANDIR)/man1/*.1 $(web_dest)/ ; \ ) || { rm -rf $(web_dest); exit 1; } diff --git a/debian/changelog b/debian/changelog --- a/debian/changelog +++ b/debian/changelog @@ -1,3 +1,141 @@ +pandoc (0.43) unstable; urgency=low + + [ John MacFarlane ] + + * The focus of this release is performance. The markdown parser + is about five times faster than in 0.42, based on benchmarks + with the TextMate manual. + + * Main.hs: Replaced CRFilter and tabFilter with single function + tabFilter, which operates on the whole string rather than breaking + it into lines, and handles dos-style line-endings as well as tabs. + + * Added separate LaTeX reader and native reader tests; removed + round-trip tests. + + * Text.Pandoc.Shared: + + + Removed tabsToSpaces and tabsInLine (they were used only in Main.hs.) + + General code cleanup (to elimante warnings when compiling with -Wall.) + + Added 'wrapped' function, which helps wrap text into paragraphs, + using the prettyprinting library. + + Rewrote charsInBalanced and charsInBalanced'. + - Documented restriction: open and close must be distinct characters. + - Rearranged options for greater efficiency. + - Bug fix: Changed inner call to charsInBalanced inside + charsInBalanced' to charsInBalanced'. + + anyLine now requires that the line end with a newline (not eof). + This is a harmless assumption, since we always add newlines to the + end of a block before parsing with anyLine, and it yields a 10% speed + boost. + + Removed unnecessary 'try' in anyLine. + + Removed unneeded 'try' from romanNumeral parser. + + Use notFollowedBy instead of notFollowedBy' in charsInBalanced. + + Removed unneeded 'try' in parseFromString. + + Removed unneeded 'try' from stringAnyCase. (Now it behaves + like 'string'.) + + Changed definition of 'enclosed' in Text.Pandoc.Shared so that + 'try' is not automatically applied to the 'end' parser. Added + 'try' in calls to 'enclosed' where needed. Slight speed increase. + + * Writers: + + + Replaced individual wrapping routines in RST, Man, and Markdown + writers with 'wrapped' from Text.Pandoc.Shared. + + Rewrote LaTeX writer to use the prettyprinting library, + so we get word wrapping, etc. + + Modified latex writer tests for new latex writer using prettyprinter. + + Fixed bug in LaTeX writer: autolinks would not cause + '\usepackage{url}' to be put in the document header. Also, changes + to state in enumerated list items would be overwritten. + + In Markdown writer, escape paragraphs that begin with ordered list + markers, so they don't get interpreted as ordered lists. + + * Text.Pandoc.Reades.LaTeX: + + + Fixed bug in LaTeX reader, which wrongly assumed that the roman + numeral after "enum" in "setcounter" would consist entirely of + "i"s. 'enumiv' is legitimate. + + LaTeX command and environment names can't contain numbers. + + Rearranged order of parsers in inline for slight speed improvement. + + Added '`' to special characters and 'unescapedChar'. + + * Text.Pandoc.Readers.RST: + + + Removed unneeded try's in RST reader; also minor code cleanup. + + Removed tabchar. + + Rearranged parsers in inline (doubled speed). + + * Text.Pandoc.Readers.Markdown: + + + Skip notes parsing if running in strict mode. (This yields a nice + speed improvement in strict mode.) + + Simplify autolink parsing code, using Network.URI to test for + URIs. Added dependency on network library to debian/control and + pandoc.cabal. + + More perspicuous definition of nonindentSpaces. + + Removed unneeded 'try' in 'rawLine'. + + Combined linebreak and whitespace into a new whitespace parser, to + avoid unnecessary reparsing of space characters. + + Removed unnecessary 'try' in 'codeBlock', 'ellipses', 'noteMarker', + 'multilineRow', 'dashedLine', 'rawHtmlBlocks'. + + Use lookAhead in parsers for setext headers and definition lists + to see if the next line begins appropriately; if not, don't waste + any more time parsing. + + Don't require blank lines after code block. (It's sufficient to + end code block with a nonindented line.) + + Changed definition of 'emph': italics with '_' must not + be followed by an alphanumeric character. This is to help + prevent interpretation of e.g. [LC_TYPE]: my_type as + '[LCTYPE]:mytype'. + + Improved Markdown.pl-compatibility in referenceLink: the two parts + of a reference-style link may be separated by one space, but not + more... [a] [link], [not] [a link]. + + Fixed markdown inline code parsing so it better accords with + Markdown.pl: the marker for the end of the code section is a clump + of the same number of `'s with which the section began, followed + by a non-` character. So, for example, + ` h ``` i ` -> h ``` i. + + Split 'title' into 'linkTitle' and 'referenceTitle', since the + rules are slightly different. + + Rewrote 'para' for greater efficiency. + + Rewrote link parsers for greater efficiency. + + Removed redundant 'referenceLink' in definition of inline (it's + already in 'link'). + + Refactored escapeChar so it doesn't need 'try'. + + Refactored hrule for performance in Markdown reader. + + More intelligent rearranging of 'inline' so that most frequently + used parsers are tried first. + + Removed tabchar parser, as whitespace handles tabs anyway. + + * Text.Pandoc.CharacterReferences: + + + Refactored. + + Removed unnecessary 'try's for a speed improvement. + + Removed unnecessary '&' and ';' from the entity table. + + * Build process: + + + Makefile: Get VERSION from cabal file, not Main.hs. + + Modified MacPorts Portfile: + - Depend on haddock + - Build and install libraries and library documentation in + addition to pandoc executable + - Added template item for md5 sum in Portfile.in. + - Incorporated changes from MacPorts repository (r28278). + + FreeBSD port: Don't try to generate distinfo in Makefile. + It can be made using 'make makesum' in FreeBSD. + + Make both freebsd and macports targets depend on tarball. + + * Website and documentation: + + + Updated INSTALL instructions. + + Added pandocwiki demo to website. + + Removed local references to Portfile, since pandoc is now in the + MacPorts repository. + + -- Recai Oktaş Sun, 02 Sep 2007 15:50:11 +0300 + pandoc (0.42) unstable; urgency=low [ John MacFarlane ] @@ -53,6 +191,11 @@ * Website: + Added a programming demo, pandocwiki. + [ Recai Oktaş ] + + * Do not forget to close pandoc's ITP. Closes: #391666 + + -- Recai Oktaş Sun, 26 Aug 2007 22:51:32 +0300 pandoc (0.41) unstable; urgency=low diff --git a/debian/control b/debian/control --- a/debian/control +++ b/debian/control @@ -2,7 +2,7 @@ Section: text Priority: optional Maintainer: Recai Oktaş -Build-Depends: debhelper (>= 4.0.0), haskell-devscripts (>=0.5.12), ghc6 (>= 6.6-1), libghc6-xhtml-dev, libghc6-mtl-dev, perl +Build-Depends: debhelper (>= 4.0.0), haskell-devscripts (>=0.5.12), ghc6 (>= 6.6-1), libghc6-xhtml-dev, libghc6-mtl-dev, libghc6-network-dev, perl Build-Depends-Indep: haddock Standards-Version: 3.7.2.0 XS-Vcs-Svn: http://pandoc.googlecode.com/svn/trunk diff --git a/macports/Portfile.in b/macports/Portfile.in --- a/macports/Portfile.in +++ b/macports/Portfile.in @@ -1,6 +1,7 @@ -# ID$ +# $Id$ PortSystem 1.0 + name pandoc version @VERSION@ categories textproc @@ -16,8 +17,10 @@ platforms darwin master_sites http://pandoc.googlecode.com/files/ checksums md5 @TARBALLMD5SUM@ -depends_lib port:ghc - -configure {} -build.cmd PREFIX=${prefix} make +depends_build port:ghc port:haddock +depends_lib port:gmp +use_configure no +build.args PREFIX=${prefix} +build.target build-all +destroot.target install-all diff --git a/pandoc.cabal b/pandoc.cabal --- a/pandoc.cabal +++ b/pandoc.cabal @@ -1,5 +1,5 @@ Name: pandoc -Version: 0.42 +Version: 0.43 License: GPL License-File: COPYING Copyright: (c) 2006-2007 John MacFarlane @@ -31,7 +31,7 @@ which convert this native representation into a target format. Thus, adding an input or output format requires only adding a reader or writer. -Build-Depends: base, parsec, xhtml, mtl, regex-compat +Build-Depends: base, parsec, xhtml, mtl, regex-compat, network Hs-Source-Dirs: src Exposed-Modules: Text.Pandoc, Text.Pandoc.Blocks, diff --git a/src/Main.hs b/src/Main.hs --- a/src/Main.hs +++ b/src/Main.hs @@ -31,7 +31,7 @@ module Main where import Text.Pandoc import Text.Pandoc.UTF8 -import Text.Pandoc.Shared ( joinWithSep, tabsToSpaces ) +import Text.Pandoc.Shared ( joinWithSep ) import Text.Regex ( mkRegex, matchRegex ) import System.Environment ( getArgs, getProgName, getEnvironment ) import System.Exit ( exitWith, ExitCode (..) ) @@ -43,7 +43,7 @@ import Control.Monad ( (>>=) ) version :: String -version = "0.42" +version = "0.43" copyrightMessage :: String copyrightMessage = "\nCopyright (C) 2006-7 John MacFarlane\n\ @@ -445,8 +445,19 @@ Just cols -> read cols Nothing -> stateColumns defaultParserState - let tabFilter = if preserveTabs then id else (tabsToSpaces tabStop) - let removeCRs str = filter (/= '\r') str -- remove DOS-style line endings + let tabFilter _ [] = "" + tabFilter _ ('\n':xs) = '\n':(tabFilter tabStop xs) + tabFilter _ ('\r':'\n':xs) = '\n':(tabFilter tabStop xs) + -- remove DOS line endings + tabFilter spsToNextStop ('\t':xs) = + if preserveTabs + then '\t':(tabFilter tabStop xs) + else replicate spsToNextStop ' ' ++ tabFilter tabStop xs + tabFilter 1 (x:xs) = + x:(tabFilter tabStop xs) + tabFilter spsToNextStop (x:xs) = + x:(tabFilter (spsToNextStop - 1) xs) + let startParserState = defaultParserState { stateParseRaw = parseRaw, stateTabStop = tabStop, @@ -483,8 +494,8 @@ (readSources sources) >>= (hPutStrLn output . toUTF8 . (writer writerOptions) . - (reader startParserState) . tabFilter . - removeCRs . fromUTF8 . (joinWithSep "\n")) >> + (reader startParserState) . tabFilter tabStop . + fromUTF8 . (joinWithSep "\n")) >> hClose output where diff --git a/src/Text/Pandoc/CharacterReferences.hs b/src/Text/Pandoc/CharacterReferences.hs --- a/src/Text/Pandoc/CharacterReferences.hs +++ b/src/Text/Pandoc/CharacterReferences.hs @@ -37,37 +37,29 @@ -- | Parse character entity. characterReference :: GenParser Char st Char -characterReference = characterEntity <|> - hexadecimalCharacterReference <|> - decimalCharacterReference - "character entity" - --- | Parse character entity. -characterEntity :: GenParser Char st Char -characterEntity = try $ do +characterReference = try $ do st <- char '&' - body <- many1 alphaNum - end <- char ';' - let entity = "&" ++ body ++ ";" - return $ Map.findWithDefault '?' entity entityTable - --- | Parse hexadecimal entity. -hexadecimalCharacterReference :: GenParser Char st Char -hexadecimalCharacterReference = try $ do - st <- string "&#" - hex <- oneOf "Xx" - body <- many1 (oneOf "0123456789ABCDEFabcdef") + character <- numRef <|> entity end <- char ';' - return $ chr $ read ('0':'x':body) + return character --- | Parse decimal entity. -decimalCharacterReference :: GenParser Char st Char -decimalCharacterReference = try $ do - st <- string "&#" - body <- many1 digit - end <- char ';' - return $ chr $ read body +numRef :: GenParser Char st Char +numRef = do + char '#' + num <- hexNum <|> decNum + return $ chr $ num +hexNum :: GenParser Char st Int +hexNum = oneOf "Xx" >> many1 hexDigit >>= return . read . ("0x" ++) + +decNum :: GenParser Char st Int +decNum = many1 digit >>= return . read + +entity :: GenParser Char st Char +entity = do + body <- many1 alphaNum + return $ Map.findWithDefault '?' body entityTable + -- | Convert entities in a string to characters. decodeCharacterReferences :: String -> String decodeCharacterReferences str = @@ -80,256 +72,256 @@ entityTableList :: [(String, Char)] entityTableList = [ - (""", chr 34), - ("&", chr 38), - ("<", chr 60), - (">", chr 62), - (" ", chr 160), - ("¡", chr 161), - ("¢", chr 162), - ("£", chr 163), - ("¤", chr 164), - ("¥", chr 165), - ("¦", chr 166), - ("§", chr 167), - ("¨", chr 168), - ("©", chr 169), - ("ª", chr 170), - ("«", chr 171), - ("¬", chr 172), - ("­", chr 173), - ("®", chr 174), - ("¯", chr 175), - ("°", chr 176), - ("±", chr 177), - ("²", chr 178), - ("³", chr 179), - ("´", chr 180), - ("µ", chr 181), - ("¶", chr 182), - ("·", chr 183), - ("¸", chr 184), - ("¹", chr 185), - ("º", chr 186), - ("»", chr 187), - ("¼", chr 188), - ("½", chr 189), - ("¾", chr 190), - ("¿", chr 191), - ("À", chr 192), - ("Á", chr 193), - ("Â", chr 194), - ("Ã", chr 195), - ("Ä", chr 196), - ("Å", chr 197), - ("Æ", chr 198), - ("Ç", chr 199), - ("È", chr 200), - ("É", chr 201), - ("Ê", chr 202), - ("Ë", chr 203), - ("Ì", chr 204), - ("Í", chr 205), - ("Î", chr 206), - ("Ï", chr 207), - ("Ð", chr 208), - ("Ñ", chr 209), - ("Ò", chr 210), - ("Ó", chr 211), - ("Ô", chr 212), - ("Õ", chr 213), - ("Ö", chr 214), - ("×", chr 215), - ("Ø", chr 216), - ("Ù", chr 217), - ("Ú", chr 218), - ("Û", chr 219), - ("Ü", chr 220), - ("Ý", chr 221), - ("Þ", chr 222), - ("ß", chr 223), - ("à", chr 224), - ("á", chr 225), - ("â", chr 226), - ("ã", chr 227), - ("ä", chr 228), - ("å", chr 229), - ("æ", chr 230), - ("ç", chr 231), - ("è", chr 232), - ("é", chr 233), - ("ê", chr 234), - ("ë", chr 235), - ("ì", chr 236), - ("í", chr 237), - ("î", chr 238), - ("ï", chr 239), - ("ð", chr 240), - ("ñ", chr 241), - ("ò", chr 242), - ("ó", chr 243), - ("ô", chr 244), - ("õ", chr 245), - ("ö", chr 246), - ("÷", chr 247), - ("ø", chr 248), - ("ù", chr 249), - ("ú", chr 250), - ("û", chr 251), - ("ü", chr 252), - ("ý", chr 253), - ("þ", chr 254), - ("ÿ", chr 255), - ("Œ", chr 338), - ("œ", chr 339), - ("Š", chr 352), - ("š", chr 353), - ("Ÿ", chr 376), - ("ƒ", chr 402), - ("ˆ", chr 710), - ("˜", chr 732), - ("Α", chr 913), - ("Β", chr 914), - ("Γ", chr 915), - ("Δ", chr 916), - ("Ε", chr 917), - ("Ζ", chr 918), - ("Η", chr 919), - ("Θ", chr 920), - ("Ι", chr 921), - ("Κ", chr 922), - ("Λ", chr 923), - ("Μ", chr 924), - ("Ν", chr 925), - ("Ξ", chr 926), - ("Ο", chr 927), - ("Π", chr 928), - ("Ρ", chr 929), - ("Σ", chr 931), - ("Τ", chr 932), - ("Υ", chr 933), - ("Φ", chr 934), - ("Χ", chr 935), - ("Ψ", chr 936), - ("Ω", chr 937), - ("α", chr 945), - ("β", chr 946), - ("γ", chr 947), - ("δ", chr 948), - ("ε", chr 949), - ("ζ", chr 950), - ("η", chr 951), - ("θ", chr 952), - ("ι", chr 953), - ("κ", chr 954), - ("λ", chr 955), - ("μ", chr 956), - ("ν", chr 957), - ("ξ", chr 958), - ("ο", chr 959), - ("π", chr 960), - ("ρ", chr 961), - ("ς", chr 962), - ("σ", chr 963), - ("τ", chr 964), - ("υ", chr 965), - ("φ", chr 966), - ("χ", chr 967), - ("ψ", chr 968), - ("ω", chr 969), - ("ϑ", chr 977), - ("ϒ", chr 978), - ("ϖ", chr 982), - (" ", chr 8194), - (" ", chr 8195), - (" ", chr 8201), - ("‌", chr 8204), - ("‍", chr 8205), - ("‎", chr 8206), - ("‏", chr 8207), - ("–", chr 8211), - ("—", chr 8212), - ("‘", chr 8216), - ("’", chr 8217), - ("‚", chr 8218), - ("“", chr 8220), - ("”", chr 8221), - ("„", chr 8222), - ("†", chr 8224), - ("‡", chr 8225), - ("•", chr 8226), - ("…", chr 8230), - ("‰", chr 8240), - ("′", chr 8242), - ("″", chr 8243), - ("‹", chr 8249), - ("›", chr 8250), - ("‾", chr 8254), - ("⁄", chr 8260), - ("€", chr 8364), - ("ℑ", chr 8465), - ("℘", chr 8472), - ("ℜ", chr 8476), - ("™", chr 8482), - ("ℵ", chr 8501), - ("←", chr 8592), - ("↑", chr 8593), - ("→", chr 8594), - ("↓", chr 8595), - ("↔", chr 8596), - ("↵", chr 8629), - ("⇐", chr 8656), - ("⇑", chr 8657), - ("⇒", chr 8658), - ("⇓", chr 8659), - ("⇔", chr 8660), - ("∀", chr 8704), - ("∂", chr 8706), - ("∃", chr 8707), - ("∅", chr 8709), - ("∇", chr 8711), - ("∈", chr 8712), - ("∉", chr 8713), - ("∋", chr 8715), - ("∏", chr 8719), - ("∑", chr 8721), - ("−", chr 8722), - ("∗", chr 8727), - ("√", chr 8730), - ("∝", chr 8733), - ("∞", chr 8734), - ("∠", chr 8736), - ("∧", chr 8743), - ("∨", chr 8744), - ("∩", chr 8745), - ("∪", chr 8746), - ("∫", chr 8747), - ("∴", chr 8756), - ("∼", chr 8764), - ("≅", chr 8773), - ("≈", chr 8776), - ("≠", chr 8800), - ("≡", chr 8801), - ("≤", chr 8804), - ("≥", chr 8805), - ("⊂", chr 8834), - ("⊃", chr 8835), - ("⊄", chr 8836), - ("⊆", chr 8838), - ("⊇", chr 8839), - ("⊕", chr 8853), - ("⊗", chr 8855), - ("⊥", chr 8869), - ("⋅", chr 8901), - ("⌈", chr 8968), - ("⌉", chr 8969), - ("⌊", chr 8970), - ("⌋", chr 8971), - ("⟨", chr 9001), - ("⟩", chr 9002), - ("◊", chr 9674), - ("♠", chr 9824), - ("♣", chr 9827), - ("♥", chr 9829), - ("♦", chr 9830) + ("quot", chr 34), + ("amp", chr 38), + ("lt", chr 60), + ("gt", chr 62), + ("nbsp", chr 160), + ("iexcl", chr 161), + ("cent", chr 162), + ("pound", chr 163), + ("curren", chr 164), + ("yen", chr 165), + ("brvbar", chr 166), + ("sect", chr 167), + ("uml", chr 168), + ("copy", chr 169), + ("ordf", chr 170), + ("laquo", chr 171), + ("not", chr 172), + ("shy", chr 173), + ("reg", chr 174), + ("macr", chr 175), + ("deg", chr 176), + ("plusmn", chr 177), + ("sup2", chr 178), + ("sup3", chr 179), + ("acute", chr 180), + ("micro", chr 181), + ("para", chr 182), + ("middot", chr 183), + ("cedil", chr 184), + ("sup1", chr 185), + ("ordm", chr 186), + ("raquo", chr 187), + ("frac14", chr 188), + ("frac12", chr 189), + ("frac34", chr 190), + ("iquest", chr 191), + ("Agrave", chr 192), + ("Aacute", chr 193), + ("Acirc", chr 194), + ("Atilde", chr 195), + ("Auml", chr 196), + ("Aring", chr 197), + ("AElig", chr 198), + ("Ccedil", chr 199), + ("Egrave", chr 200), + ("Eacute", chr 201), + ("Ecirc", chr 202), + ("Euml", chr 203), + ("Igrave", chr 204), + ("Iacute", chr 205), + ("Icirc", chr 206), + ("Iuml", chr 207), + ("ETH", chr 208), + ("Ntilde", chr 209), + ("Ograve", chr 210), + ("Oacute", chr 211), + ("Ocirc", chr 212), + ("Otilde", chr 213), + ("Ouml", chr 214), + ("times", chr 215), + ("Oslash", chr 216), + ("Ugrave", chr 217), + ("Uacute", chr 218), + ("Ucirc", chr 219), + ("Uuml", chr 220), + ("Yacute", chr 221), + ("THORN", chr 222), + ("szlig", chr 223), + ("agrave", chr 224), + ("aacute", chr 225), + ("acirc", chr 226), + ("atilde", chr 227), + ("auml", chr 228), + ("aring", chr 229), + ("aelig", chr 230), + ("ccedil", chr 231), + ("egrave", chr 232), + ("eacute", chr 233), + ("ecirc", chr 234), + ("euml", chr 235), + ("igrave", chr 236), + ("iacute", chr 237), + ("icirc", chr 238), + ("iuml", chr 239), + ("eth", chr 240), + ("ntilde", chr 241), + ("ograve", chr 242), + ("oacute", chr 243), + ("ocirc", chr 244), + ("otilde", chr 245), + ("ouml", chr 246), + ("divide", chr 247), + ("oslash", chr 248), + ("ugrave", chr 249), + ("uacute", chr 250), + ("ucirc", chr 251), + ("uuml", chr 252), + ("yacute", chr 253), + ("thorn", chr 254), + ("yuml", chr 255), + ("OElig", chr 338), + ("oelig", chr 339), + ("Scaron", chr 352), + ("scaron", chr 353), + ("Yuml", chr 376), + ("fnof", chr 402), + ("circ", chr 710), + ("tilde", chr 732), + ("Alpha", chr 913), + ("Beta", chr 914), + ("Gamma", chr 915), + ("Delta", chr 916), + ("Epsilon", chr 917), + ("Zeta", chr 918), + ("Eta", chr 919), + ("Theta", chr 920), + ("Iota", chr 921), + ("Kappa", chr 922), + ("Lambda", chr 923), + ("Mu", chr 924), + ("Nu", chr 925), + ("Xi", chr 926), + ("Omicron", chr 927), + ("Pi", chr 928), + ("Rho", chr 929), + ("Sigma", chr 931), + ("Tau", chr 932), + ("Upsilon", chr 933), + ("Phi", chr 934), + ("Chi", chr 935), + ("Psi", chr 936), + ("Omega", chr 937), + ("alpha", chr 945), + ("beta", chr 946), + ("gamma", chr 947), + ("delta", chr 948), + ("epsilon", chr 949), + ("zeta", chr 950), + ("eta", chr 951), + ("theta", chr 952), + ("iota", chr 953), + ("kappa", chr 954), + ("lambda", chr 955), + ("mu", chr 956), + ("nu", chr 957), + ("xi", chr 958), + ("omicron", chr 959), + ("pi", chr 960), + ("rho", chr 961), + ("sigmaf", chr 962), + ("sigma", chr 963), + ("tau", chr 964), + ("upsilon", chr 965), + ("phi", chr 966), + ("chi", chr 967), + ("psi", chr 968), + ("omega", chr 969), + ("thetasym", chr 977), + ("upsih", chr 978), + ("piv", chr 982), + ("ensp", chr 8194), + ("emsp", chr 8195), + ("thinsp", chr 8201), + ("zwnj", chr 8204), + ("zwj", chr 8205), + ("lrm", chr 8206), + ("rlm", chr 8207), + ("ndash", chr 8211), + ("mdash", chr 8212), + ("lsquo", chr 8216), + ("rsquo", chr 8217), + ("sbquo", chr 8218), + ("ldquo", chr 8220), + ("rdquo", chr 8221), + ("bdquo", chr 8222), + ("dagger", chr 8224), + ("Dagger", chr 8225), + ("bull", chr 8226), + ("hellip", chr 8230), + ("permil", chr 8240), + ("prime", chr 8242), + ("Prime", chr 8243), + ("lsaquo", chr 8249), + ("rsaquo", chr 8250), + ("oline", chr 8254), + ("frasl", chr 8260), + ("euro", chr 8364), + ("image", chr 8465), + ("weierp", chr 8472), + ("real", chr 8476), + ("trade", chr 8482), + ("alefsym", chr 8501), + ("larr", chr 8592), + ("uarr", chr 8593), + ("rarr", chr 8594), + ("darr", chr 8595), + ("harr", chr 8596), + ("crarr", chr 8629), + ("lArr", chr 8656), + ("uArr", chr 8657), + ("rArr", chr 8658), + ("dArr", chr 8659), + ("hArr", chr 8660), + ("forall", chr 8704), + ("part", chr 8706), + ("exist", chr 8707), + ("empty", chr 8709), + ("nabla", chr 8711), + ("isin", chr 8712), + ("notin", chr 8713), + ("ni", chr 8715), + ("prod", chr 8719), + ("sum", chr 8721), + ("minus", chr 8722), + ("lowast", chr 8727), + ("radic", chr 8730), + ("prop", chr 8733), + ("infin", chr 8734), + ("ang", chr 8736), + ("and", chr 8743), + ("or", chr 8744), + ("cap", chr 8745), + ("cup", chr 8746), + ("int", chr 8747), + ("there4", chr 8756), + ("sim", chr 8764), + ("cong", chr 8773), + ("asymp", chr 8776), + ("ne", chr 8800), + ("equiv", chr 8801), + ("le", chr 8804), + ("ge", chr 8805), + ("sub", chr 8834), + ("sup", chr 8835), + ("nsub", chr 8836), + ("sube", chr 8838), + ("supe", chr 8839), + ("oplus", chr 8853), + ("otimes", chr 8855), + ("perp", chr 8869), + ("sdot", chr 8901), + ("lceil", chr 8968), + ("rceil", chr 8969), + ("lfloor", chr 8970), + ("rfloor", chr 8971), + ("lang", chr 9001), + ("rang", chr 9002), + ("loz", chr 9674), + ("spades", chr 9824), + ("clubs", chr 9827), + ("hearts", chr 9829), + ("diams", chr 9830) ] diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -47,7 +47,7 @@ readLaTeX = readWith parseLaTeX -- characters with special meaning -specialChars = "\\$%^&_~#{}\n \t|<>'\"-" +specialChars = "\\`$%^&_~#{}\n \t|<>'\"-" -- -- utility functions @@ -69,9 +69,9 @@ commandArgs = many optOrArg -- | Parses LaTeX command, returns (name, star, list of options or arguments). -command = try $ do +command = do char '\\' - name <- many1 alphaNum + name <- many1 letter star <- option "" (string "*") -- some commands have starred versions args <- commandArgs return (name, star, args) @@ -93,7 +93,7 @@ anyEnvironment = try $ do string "\\begin{" - name <- many alphaNum + name <- many letter star <- option "" (string "*") -- some environments have starred variants char '}' optional commandArgs @@ -152,16 +152,15 @@ -- header blocks -- -header = choice (map headerLevel (enumFromTo 1 5)) "header" - -headerLevel n = try $ do - let subs = concat $ replicate (n - 1) "sub" - string ("\\" ++ subs ++ "section") +header = try $ do + char '\\' + subs <- many (try (string "sub")) + string "section" optional (char '*') char '{' title <- manyTill inline (char '}') spaces - return $ Header n (normalizeSpaces title) + return $ Header (length subs + 1) (normalizeSpaces title) -- -- hrule block @@ -249,7 +248,7 @@ spaces start <- option 1 $ try $ do failIfStrict string "\\setcounter{enum" - many1 (char 'i') + many1 (oneOf "iv") string "}{" num <- many1 digit char '}' @@ -342,7 +341,7 @@ rawLaTeXEnvironment :: GenParser Char st Block rawLaTeXEnvironment = try $ do string "\\begin{" - name <- many1 alphaNum + name <- many1 letter star <- option "" (string "*") -- for starred variants let name' = name ++ star char '}' @@ -386,7 +385,18 @@ -- inline -- -inline = choice [ strong +inline = choice [ str + , endline + , whitespace + , quoted + , apostrophe + , spacer + , strong + , math + , ellipses + , emDash + , enDash + , hyphen , emph , strikeout , superscript @@ -394,34 +404,24 @@ , ref , lab , code - , linebreak - , spacer - , math - , ellipses - , emDash - , enDash - , hyphen - , quoted - , apostrophe - , accentedChar - , specialChar , url , link , image , footnote + , linebreak + , accentedChar + , specialChar , rawLaTeXInline , escapedChar , unescapedChar - , str - , endline - , whitespace ] "inline" + ] "inline" accentedChar = normalAccentedChar <|> specialAccentedChar normalAccentedChar = try $ do char '\\' accent <- oneOf "'`^\"~" - character <- (try $ char '{' >> alphaNum >>~ char '}') <|> alphaNum + character <- (try $ char '{' >> letter >>~ char '}') <|> letter let table = fromMaybe [] $ lookup character accentTable let result = case lookup accent table of Just num -> chr num @@ -492,7 +492,7 @@ return $ if result == Str "\n" then Str " " else result -- ignore standalone, nonescaped special characters -unescapedChar = oneOf "$^&_#{}|<>" >> return (Str "") +unescapedChar = oneOf "`$^&_#{}|<>" >> return (Str "") specialChar = choice [ backslash, tilde, caret, bar, lt, gt ] @@ -551,7 +551,7 @@ doubleQuoteStart = string "``" -doubleQuoteEnd = string "''" +doubleQuoteEnd = try $ string "''" ellipses = try $ string "\\ldots" >> optional (try (string "{}")) >> return Ellipses diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -31,9 +31,10 @@ readMarkdown ) where -import Data.List ( transpose, isSuffixOf, lookup, sortBy ) +import Data.List ( transpose, isPrefixOf, isSuffixOf, lookup, sortBy ) import Data.Ord ( comparing ) import Data.Char ( isAlphaNum ) +import Network.URI ( isURI ) import Text.Pandoc.Definition import Text.Pandoc.Shared import Text.Pandoc.Readers.LaTeX ( rawLaTeXInline, rawLaTeXEnvironment ) @@ -74,7 +75,10 @@ nonindentSpaces = do state <- getState let tabStop = stateTabStop state - choice $ map (\n -> (try (count n (char ' ')))) $ reverse [0..(tabStop - 1)] + sps <- many (char ' ') + if length sps < tabStop + then return sps + else unexpected "indented line" -- | Fail unless we're at beginning of a line. failUnlessBeginningOfLine = do @@ -139,22 +143,25 @@ (title, author, date) <- option ([],[],"") titleBlock -- go through once just to get list of reference keys refs <- manyTill (referenceKey <|> (lineClump >>= return . LineClump)) eof - let keys = map (\(KeyBlock label target) -> (label, target)) $ + let keys = map (\(KeyBlock label target) -> (label, target)) $ filter isKeyBlock refs - let rawlines = map (\(LineClump ln) -> ln) $ filter isLineClump refs - setInput $ concat rawlines -- with keys stripped out + -- strip out keys + setInput $ concatMap (\(LineClump ln) -> ln) $ filter isLineClump refs updateState (\state -> state { stateKeys = keys }) - -- now go through for notes (which may contain references - hence 2nd pass) - refs <- manyTill (noteBlock <|> (lineClump >>= return . LineClump)) eof - let notes = map (\(NoteBlock label blocks) -> (label, blocks)) $ - filter isNoteBlock refs - let rawlines = map (\(LineClump ln) -> ln) $ filter isLineClump refs - -- go through a 3rd time, with note blocks and keys stripped out - setInput $ concat rawlines - updateState (\state -> state { stateNotes = notes }) + st <- getState + if stateStrict st + then return () + else do -- go through for notes (which may contain refs - hence 2nd pass) + refs' <- manyTill (noteBlock <|> + (lineClump >>= return . LineClump)) eof + let notes = map (\(NoteBlock label blocks) -> (label, blocks)) $ + filter isNoteBlock refs' + updateState (\state -> state { stateNotes = notes }) + setInput $ concatMap (\(LineClump ln) -> ln) $ + filter isLineClump refs' + -- go through again, with note blocks and keys stripped out blocks <- parseBlocks - let blocks' = filter (/= Null) blocks - return $ Pandoc (Meta title author date) blocks' + return $ Pandoc (Meta title author date) $ filter (/= Null) blocks -- -- initial pass for references and notes @@ -168,16 +175,23 @@ optional (char '<') src <- many (noneOf "> \n\t") optional (char '>') - tit <- option "" title - blanklines + tit <- option "" referenceTitle + blanklines return $ KeyBlock label (removeTrailingSpace src, tit) -noteMarker = try $ do - char '[' - char '^' - manyTill (noneOf " \t\n") (char ']') +referenceTitle = try $ do + skipSpaces + optional newline + skipSpaces + tit <- (charsInBalanced '(' ')' >>= return . unwords . words) + <|> do delim <- char '\'' <|> char '"' + manyTill anyChar (try (char delim >> skipSpaces >> + notFollowedBy (noneOf ")\n"))) + return $ decodeCharacterReferences tit -rawLine = try $ do +noteMarker = string "[^" >> manyTill (noneOf " \t\n") (char ']') + +rawLine = do notFollowedBy blankline notFollowedBy' noteMarker contents <- many1 nonEndline @@ -187,7 +201,6 @@ rawLines = many1 rawLine >>= return . concat noteBlock = try $ do - failIfStrict ref <- noteMarker char ':' optional blankline @@ -220,7 +233,7 @@ -- header blocks -- -header = setextHeader <|> atxHeader "header" +header = atxHeader <|> setextHeader "header" atxHeader = try $ do level <- many1 (char '#') >>= return . length @@ -231,39 +244,40 @@ atxClosing = try $ skipMany (char '#') >> blanklines -setextHeader = choice $ map setextH $ enumFromTo 1 (length setextHChars) - -setextH level = try $ do +setextHeader = try $ do + -- first, see if this block has any chance of being a setextHeader: + lookAhead (anyLine >> oneOf setextHChars) text <- many1Till inline newline >>= return . normalizeSpaces - many1 $ char (setextHChars !! (level - 1)) - blanklines + level <- choice $ zipWith + (\ch lev -> try (many1 $ char ch) >> blanklines >> return lev) + setextHChars [1..(length setextHChars)] return $ Header level text -- -- hrule block -- -hruleWith chr = try $ do - count 3 (skipSpaces >> char chr) - skipMany (skipSpaces >> char chr) +hrule = try $ do + skipSpaces + start <- oneOf hruleChars + count 2 (skipSpaces >> char start) + skipMany (skipSpaces >> char start) newline optional blanklines return HorizontalRule -hrule = choice (map hruleWith hruleChars) "hrule" - -- -- code blocks -- indentedLine = indentSpaces >> manyTill anyChar newline >>= return . (++ "\n") -codeBlock = try $ do +codeBlock = do contents <- many1 (indentedLine <|> try (do b <- blanklines l <- indentedLine return $ b ++ l)) - blanklines + optional blanklines return $ CodeBlock $ stripTrailingNewlines $ concat contents -- @@ -307,7 +321,7 @@ bulletListStart = try $ do optional newline -- if preceded by a Plain block in a list context nonindentSpaces - notFollowedBy' hrule -- because hrules start out just like lists + notFollowedBy' hrule -- because hrules start out just like lists oneOf bulletListMarkers spaceChar skipSpaces @@ -400,6 +414,8 @@ definitionListItem = try $ do notFollowedBy blankline notFollowedBy' indentSpaces + -- first, see if this has any chance of being a definition list: + lookAhead (anyLine >> char ':') term <- manyTill inline newline raw <- many1 defRawBlock state <- getState @@ -434,12 +450,10 @@ para = try $ do result <- many1 inline newline - st <- getState - if stateStrict st - then choice [ lookAhead blockQuote, lookAhead header, - (blanklines >> return Null) ] - else choice [ lookAhead emacsBoxQuote >> return Null, - (blanklines >> return Null) ] + blanklines <|> do st <- getState + if stateStrict st + then lookAhead (blockQuote <|> header) >> return "" + else lookAhead emacsBoxQuote >> return "" return $ Para $ normalizeSpaces result plain = many1 inline >>= return . Plain . normalizeSpaces @@ -462,7 +476,7 @@ -- True if tag is self-closing isSelfClosing tag = - isSuffixOf "/>" $ filter (\c -> (not (c `elem` " \n\t"))) tag + isSuffixOf "/>" $ filter (not . (`elem` " \n\t")) tag strictHtmlBlock = try $ do tag <- anyHtmlBlockTag @@ -474,7 +488,7 @@ end <- htmlEndTag tag' return $ tag ++ concat contents ++ end -rawHtmlBlocks = try $ do +rawHtmlBlocks = do htmlBlocks <- many1 rawHtmlBlock let combined = concatMap (\(RawHtml str) -> str) htmlBlocks let combined' = if not (null combined) && last combined == '\n' @@ -494,7 +508,7 @@ -- Parse a dashed line with optional trailing spaces; return its length -- and the length including trailing space. -dashedLine ch = try $ do +dashedLine ch = do dashes <- many1 (char ch) sp <- many spaceChar return $ (length dashes, length $ dashes ++ sp) @@ -529,7 +543,7 @@ tableLine indices = rawTableLine indices >>= mapM (parseFromString (many plain)) -- Parse a multiline table row and return a list of blocks (columns). -multilineRow indices = try $ do +multilineRow indices = do colLines <- many1 (rawTableLine indices) optional blanklines let cols = map unlines $ transpose colLines @@ -615,44 +629,42 @@ -- inline -- -inline = choice [ rawLaTeXInline' - , escapedChar +inline = choice [ str + , smartPunctuation + , whitespace + , endline + , code , charRef + , strong + , emph , note , inlineNote , link - , referenceLink - , rawHtmlInline' - , autoLink , image , math - , strong - , emph , strikeout , superscript , subscript - , smartPunctuation - , code - , ltSign + , autoLink + , rawHtmlInline' + , rawLaTeXInline' + , escapedChar , symbol - , str - , linebreak - , tabchar - , whitespace - , endline ] "inline" + , ltSign ] "inline" -escapedChar = try $ do +escapedChar = do char '\\' state <- getState - result <- if stateStrict state - then oneOf "\\`*_{}[]()>#+-.!~" - else satisfy (not . isAlphaNum) + result <- option '\\' $ if stateStrict state + then oneOf "\\`*_{}[]()>#+-.!~" + else satisfy (not . isAlphaNum) return $ Str [result] -ltSign = try $ do - notFollowedBy (noneOf "<") -- continue only if it's a < - notFollowedBy' rawHtmlBlocks -- don't return < if it starts html - char '<' +ltSign = do + st <- getState + if stateStrict st + then char '<' + else notFollowedBy' rawHtmlBlocks >> char '<' -- unless it starts html return $ Str ['<'] specialCharsMinusLt = filter (/= '<') specialChars @@ -664,10 +676,12 @@ -- parses inline code, between n `s and n `s code = try $ do starts <- many1 (char '`') - let num = length starts - result <- many1Till anyChar (try (count num (char '`'))) - -- get rid of any internal newlines - return $ Code $ removeLeadingTrailingSpace $ joinWithSep " " $ lines result + skipSpaces + result <- many1Till (many1 (noneOf "`\n") <|> many1 (char '`') <|> + (char '\n' >> return " ")) + (try (skipSpaces >> count (length starts) (char '`') >> + notFollowedBy (char '`'))) + return $ Code $ removeLeadingTrailingSpace $ concat result mathWord = many1 ((noneOf " \t\n\\$") <|> (try (char '\\') >>~ notFollowedBy (char '$'))) @@ -681,14 +695,14 @@ return $ TeX ("$" ++ (joinWithSep " " words) ++ "$") emph = ((enclosed (char '*') (char '*') inline) <|> - (enclosed (char '_') (char '_') inline)) >>= + (enclosed (char '_') (char '_' >> notFollowedBy alphaNum) inline)) >>= return . Emph . normalizeSpaces -strong = ((enclosed (string "**") (string "**") inline) <|> - (enclosed (string "__") (string "__") inline)) >>= +strong = ((enclosed (string "**") (try $ string "**") inline) <|> + (enclosed (string "__") (try $ string "__") inline)) >>= return . Strong . normalizeSpaces -strikeout = failIfStrict >> enclosed (string "~~") (string "~~") inline >>= +strikeout = failIfStrict >> enclosed (string "~~") (try $ string "~~") inline >>= return . Strikeout . normalizeSpaces superscript = failIfStrict >> enclosed (char '^') (char '^') @@ -727,9 +741,9 @@ failIfInQuoteContext context = do st <- getState - if (stateQuoteContext st == context) - then fail "already inside quotes" - else return () + if stateQuoteContext st == context + then fail "already inside quotes" + else return () singleQuoteStart = do failIfInQuoteContext InSingleQuote @@ -748,8 +762,7 @@ doubleQuoteEnd = char '"' <|> char '\8221' -ellipses = try $ oneOfStrings ["...", " . . . ", ". . .", " . . ."] >> - return Ellipses +ellipses = oneOfStrings ["...", " . . . ", ". . .", " . . ."] >> return Ellipses dash = enDash <|> emDash @@ -758,13 +771,11 @@ emDash = try $ skipSpaces >> oneOfStrings ["---", "--"] >> skipSpaces >> return EmDash -whitespace = (many1 (oneOf spaceChars) >> return Space) "whitespace" - -tabchar = tab >> return (Str "\t") - --- hard line break -linebreak = try $ oneOf spaceChars >> many1 (oneOf spaceChars) >> - endline >> return LineBreak +whitespace = do + sps <- many1 (oneOf spaceChars) + if length sps >= 2 + then option Space (endline >> return LineBreak) + else return Space "whitespace" nonEndline = satisfy (/='\n') @@ -778,9 +789,8 @@ notFollowedBy blankline st <- getState if stateStrict st - then do - notFollowedBy emailBlockQuoteStart - notFollowedBy (char '#') -- atx header + then do notFollowedBy emailBlockQuoteStart + notFollowedBy (char '#') -- atx header else return () -- parse potential list-starts differently if in a list: if stateParserContext st == ListItemState @@ -803,69 +813,59 @@ optional (char '<') src <- many (noneOf ")> \t\n") optional (char '>') - tit <- option "" title + tit <- option "" linkTitle skipSpaces char ')' return (removeTrailingSpace src, tit) -titleWith startChar endChar = try $ do - leadingSpace <- many1 (oneOf " \t\n") - if length (filter (=='\n') leadingSpace) > 1 - then fail "title must be separated by space and on same or next line" - else return () - char startChar - tit <- manyTill anyChar (try (char endChar >> skipSpaces >> - notFollowedBy (noneOf ")\n"))) +linkTitle = try $ do + skipSpaces + optional newline + skipSpaces + delim <- char '\'' <|> char '"' + tit <- manyTill anyChar (try (char delim >> skipSpaces >> + notFollowedBy (noneOf ")\n"))) return $ decodeCharacterReferences tit -title = choice [ titleWith '(' ')', - titleWith '"' '"', - titleWith '\'' '\''] "title" - -link = choice [explicitLink, referenceLink] "link" - -explicitLink = try $ do +link = try $ do label <- reference - src <- source + src <- source <|> referenceLink label return $ Link label src -- a link like [this][ref] or [this][] or [this] -referenceLink = try $ do - label <- reference - ref <- option [] (try (skipSpaces >> optional newline >> - skipSpaces >> reference)) +referenceLink label = do + ref <- option [] (try (optional (char ' ') >> + optional (newline >> skipSpaces) >> reference)) let ref' = if null ref then label else ref state <- getState case lookupKeySrc (stateKeys state) ref' of Nothing -> fail "no corresponding key" - Just target -> return (Link label target) + Just target -> return target -autoLink = autoLinkEmail <|> autoLinkRegular +emailAddress = try $ do + name <- many1 (alphaNum <|> char '+') + char '@' + first <- many1 alphaNum + rest <- many1 (char '.' >> many1 alphaNum) + return $ "mailto:" ++ name ++ "@" ++ joinWithSep "." (first:rest) --- a link -autoLinkEmail = try $ do - char '<' - name <- many1Till (noneOf "/:<> \t\n") (char '@') - domain <- sepBy1 (many1 (noneOf "/:.@<> \t\n")) (char '.') - char '>' - let src = name ++ "@" ++ (joinWithSep "." domain) - txt <- autoLinkText src - return $ Link txt (("mailto:" ++ src), "") +uri = try $ do + str <- many1 (noneOf "\n\t >") + if isURI str + then return str + else fail "not a URI" --- a link -autoLinkRegular = try $ do +autoLink = try $ do char '<' - prot <- oneOfStrings ["http:", "ftp:", "mailto:"] - rest <- many1Till (noneOf " \t\n<>") (char '>') - let src = prot ++ rest - txt <- autoLinkText src - return $ Link txt (src, "") - -autoLinkText src = do + src <- uri <|> emailAddress + char '>' + let src' = if "mailto:" `isPrefixOf` src + then drop 7 src + else src st <- getState return $ if stateStrict st - then [Str src] - else [Code src] + then Link [Str src'] (src, "") + else Link [Code src'] (src, "") image = try $ do char '!' diff --git a/src/Text/Pandoc/Readers/RST.hs b/src/Text/Pandoc/Readers/RST.hs --- a/src/Text/Pandoc/Readers/RST.hs +++ b/src/Text/Pandoc/Readers/RST.hs @@ -179,7 +179,7 @@ para = paraBeforeCodeBlock <|> paraNormal "paragraph" -codeBlockStart = try $ string "::" >> blankline >> blankline +codeBlockStart = string "::" >> blankline >> blankline -- paragraph that ends in a :: starting a code block paraBeforeCodeBlock = try $ do @@ -260,16 +260,14 @@ -- hrule block -- -hruleWith chr = try $ do - count 4 (char chr) +hrule = try $ do + chr <- oneOf underlineChars + count 3 (char chr) skipMany (char chr) - skipSpaces - newline + blankline blanklines return HorizontalRule -hrule = choice (map hruleWith underlineChars) "hrule" - -- -- code blocks -- @@ -325,7 +323,7 @@ -- block quotes -- -blockQuote = try $ do +blockQuote = do raw <- indentedBlock True -- parse the extracted block, which may contain various block elements: contents <- parseFromString parseBlocks $ raw ++ "\n\n" @@ -344,9 +342,7 @@ contents <- parseFromString parseBlocks $ raw ++ "\n\n" return (normalizeSpaces term, contents) -definitionList = try $ do - items <- many1 definitionListItem - return $ DefinitionList items +definitionList = many1 definitionListItem >>= return . DefinitionList -- parses bullet list start and returns its length (inc. following whitespace) bulletListStart = try $ do @@ -378,7 +374,7 @@ (try (char '\t' >> count (num - tabStop) (char ' '))) ] -- parse raw text for one list item, excluding start marker and continuations -rawListItem start = try $ do +rawListItem start = do markerLength <- start firstLine <- manyTill anyChar newline restLines <- many (listLine markerLength) @@ -408,16 +404,14 @@ updateState (\st -> st {stateParserContext = oldContext}) return parsed -orderedList = try $ do +orderedList = do (start, style, delim) <- lookAhead (anyOrderedListMarker >>~ spaceChar) items <- many1 (listItem (orderedListStart style delim)) let items' = compactify items return $ OrderedList (start, style, delim) items' -bulletList = try $ do - items <- many1 (listItem bulletListStart) - let items' = compactify items - return $ BulletList items' +bulletList = many1 (listItem bulletListStart) >>= + return . BulletList . compactify -- -- unknown directive (e.g. comment) @@ -439,7 +433,7 @@ choice [imageKey, anonymousKey, regularKeyQuoted, regularKey] >>~ optional blanklines -targetURI = try $ do +targetURI = do skipSpaces optional newline contents <- many1 (try (many spaceChar >> newline >> @@ -478,22 +472,21 @@ -- inline -- -inline = choice [ superscript - , subscript - , escapedChar - , link - , image - , hyphens - , strong - , emph - , code +inline = choice [ link , str - , tabchar , whitespace , endline + , strong + , emph + , code + , image + , hyphens + , superscript + , subscript + , escapedChar , symbol ] "inline" -hyphens = try $ do +hyphens = do result <- many1 (char '-') option Space endline -- don't want to treat endline after hyphen or dash as a space @@ -514,7 +507,7 @@ emph = enclosed (char '*') (char '*') inline >>= return . Emph . normalizeSpaces -strong = enclosed (string "**") (string "**") inline >>= +strong = enclosed (string "**") (try $ string "**") inline >>= return . Strong . normalizeSpaces interpreted role = try $ do @@ -530,8 +523,6 @@ whitespace = many1 spaceChar >> return Space "whitespace" -tabchar = tab >> return (Str "\t") - str = notFollowedBy' oneWordReference >> many1 (noneOf (specialChars ++ "\t\n ")) >>= return . Str @@ -541,7 +532,7 @@ notFollowedBy blankline -- parse potential list-starts at beginning of line differently in a list: st <- getState - if ((stateParserContext st) == ListItemState) + if (stateParserContext st) == ListItemState then notFollowedBy (anyOrderedListMarker >> spaceChar) >> notFollowedBy' bulletListStart else return () @@ -598,7 +589,7 @@ identifier <- many1 (noneOf " \t\n") return $ scheme ++ identifier -autoURI = try $ do +autoURI = do src <- uri return $ Link [Str src] (src, "") @@ -614,12 +605,12 @@ domainChar = alphaNum <|> char '-' -domain = try $ do +domain = do first <- many1 domainChar dom <- many1 (try (do{ char '.'; many1 domainChar })) return $ joinWithSep "." (first:dom) -autoEmail = try $ do +autoEmail = do src <- emailAddress return $ Link [Str src] ("mailto:" ++ src, "") diff --git a/src/Text/Pandoc/Shared.hs b/src/Text/Pandoc/Shared.hs --- a/src/Text/Pandoc/Shared.hs +++ b/src/Text/Pandoc/Shared.hs @@ -34,7 +34,6 @@ substitute, joinWithSep, -- * Text processing - tabsToSpaces, backslashEscapes, escapeStringUsing, stripTrailingNewlines, @@ -44,6 +43,7 @@ stripFirstAndLast, camelCaseToHyphenated, toRomanNumeral, + wrapped, -- * Parsing (>>~), anyLine, @@ -99,9 +99,11 @@ import Text.Pandoc.Definition import Text.ParserCombinators.Parsec +import Text.PrettyPrint.HughesPJ ( Doc, fsep ) import Text.Pandoc.CharacterReferences ( characterReference ) -import Data.Char ( toLower, toUpper, ord, chr, isLower, isUpper ) -import Data.List ( find, groupBy, isPrefixOf, isSuffixOf ) +import Data.Char ( toLower, toUpper, ord, isLower, isUpper ) +import Data.List ( find, isPrefixOf ) +import Control.Monad ( join ) -- -- List processing @@ -135,34 +137,13 @@ joinWithSep :: [a] -- ^ List to use as separator -> [[a]] -- ^ Lists to join -> [a] -joinWithSep sep [] = [] +joinWithSep _ [] = [] joinWithSep sep lst = foldr1 (\a b -> a ++ sep ++ b) lst -- -- Text processing -- --- | Convert tabs to spaces (with adjustable tab stop). -tabsToSpaces :: Int -- ^ Tabstop - -> String -- ^ String to convert - -> String -tabsToSpaces tabstop str = - unlines $ map (tabsInLine tabstop tabstop) (lines str) - --- | Convert tabs to spaces in one line. -tabsInLine :: Int -- ^ Number of spaces to next tab stop - -> Int -- ^ Tabstop - -> String -- ^ Line to convert - -> String -tabsInLine num tabstop [] = "" -tabsInLine num tabstop (c:cs) = - let (replacement, nextnum) = if c == '\t' - then (replicate num ' ', tabstop) - else if num > 1 - then ([c], num - 1) - else ([c], tabstop) - in replacement ++ tabsInLine nextnum tabstop cs - -- | Returns an association list of backslash escapes for the -- designated characters. backslashEscapes :: [Char] -- ^ list of special characters to escape @@ -172,7 +153,7 @@ -- | Escape a string of characters, using an association list of -- characters and strings. escapeStringUsing :: [(Char, String)] -> String -> String -escapeStringUsing escapeTable [] = "" +escapeStringUsing _ [] = "" escapeStringUsing escapeTable (x:xs) = case (lookup x escapeTable) of Just str -> str ++ rest @@ -213,21 +194,26 @@ if x >= 4000 || x < 0 then "?" else case x of - x | x >= 1000 -> "M" ++ toRomanNumeral (x - 1000) - x | x >= 900 -> "CM" ++ toRomanNumeral (x - 900) - x | x >= 500 -> "D" ++ toRomanNumeral (x - 500) - x | x >= 400 -> "CD" ++ toRomanNumeral (x - 400) - x | x >= 100 -> "C" ++ toRomanNumeral (x - 100) - x | x >= 90 -> "XC" ++ toRomanNumeral (x - 90) - x | x >= 50 -> "L" ++ toRomanNumeral (x - 50) - x | x >= 40 -> "XL" ++ toRomanNumeral (x - 40) - x | x >= 10 -> "X" ++ toRomanNumeral (x - 10) - x | x >= 9 -> "IX" ++ toRomanNumeral (x - 5) - x | x >= 5 -> "V" ++ toRomanNumeral (x - 5) - x | x >= 4 -> "IV" ++ toRomanNumeral (x - 4) - x | x >= 1 -> "I" ++ toRomanNumeral (x - 1) - 0 -> "" + _ | x >= 1000 -> "M" ++ toRomanNumeral (x - 1000) + _ | x >= 900 -> "CM" ++ toRomanNumeral (x - 900) + _ | x >= 500 -> "D" ++ toRomanNumeral (x - 500) + _ | x >= 400 -> "CD" ++ toRomanNumeral (x - 400) + _ | x >= 100 -> "C" ++ toRomanNumeral (x - 100) + _ | x >= 90 -> "XC" ++ toRomanNumeral (x - 90) + _ | x >= 50 -> "L" ++ toRomanNumeral (x - 50) + _ | x >= 40 -> "XL" ++ toRomanNumeral (x - 40) + _ | x >= 10 -> "X" ++ toRomanNumeral (x - 10) + _ | x >= 9 -> "IX" ++ toRomanNumeral (x - 5) + _ | x >= 5 -> "V" ++ toRomanNumeral (x - 5) + _ | x >= 4 -> "IV" ++ toRomanNumeral (x - 4) + _ | x >= 1 -> "I" ++ toRomanNumeral (x - 1) + _ -> "" +-- | Wrap inlines to line length. +wrapped :: Monad m => ([Inline] -> m Doc) -> [Inline] -> m Doc +wrapped listWriter sect = (mapM listWriter $ splitBy Space sect) >>= + return . fsep + -- -- Parsing -- @@ -239,8 +225,7 @@ -- | Parse any line of text anyLine :: GenParser Char st [Char] -anyLine = try (manyTill anyChar newline) <|> many1 anyChar - -- second alternative is for a line ending with eof +anyLine = manyTill anyChar newline -- | Like @manyTill@, but reads at least one item. many1Till :: GenParser tok st a @@ -255,9 +240,11 @@ -- type of parser to be specified, and succeeds only if that parser fails. -- It does not consume any input. notFollowedBy' :: Show b => GenParser a st b -> GenParser a st () -notFollowedBy' parser = try $ (do result <- try parser - unexpected (show result)) - <|> return () +notFollowedBy' p = try $ join $ do a <- try p + return (unexpected (show a)) + <|> + return (return ()) +-- (This version due to Andrew Pimlott on the Haskell mailing list.) -- | Parses one of a list of strings (tried in order). oneOfStrings :: [String] -> GenParser Char st String @@ -265,7 +252,7 @@ -- | Parses a space or tab. spaceChar :: CharParser st Char -spaceChar = oneOf " \t" +spaceChar = char ' ' <|> char '\t' -- | Skips zero or more spaces or tabs. skipSpaces :: GenParser Char st () @@ -285,19 +272,19 @@ -> GenParser Char st a -- ^ content parser (to be used repeatedly) -> GenParser Char st [a] enclosed start end parser = try $ - start >> notFollowedBy space >> many1Till parser (try end) - + start >> notFollowedBy space >> many1Till parser end + -- | Parse string, case insensitive. stringAnyCase :: [Char] -> CharParser st String stringAnyCase [] = string "" -stringAnyCase (x:xs) = try $ do - firstChar <- choice [ char (toUpper x), char (toLower x) ] +stringAnyCase (x:xs) = do + firstChar <- char (toUpper x) <|> char (toLower x) rest <- stringAnyCase xs return (firstChar:rest) -- | Parse contents of 'str' using 'parser' and return result. parseFromString :: GenParser tok st a -> [tok] -> GenParser tok st a -parseFromString parser str = try $ do +parseFromString parser str = do oldInput <- getInput setInput str result <- parser @@ -307,41 +294,41 @@ -- | Parse raw line block up to and including blank lines. lineClump :: GenParser Char st String lineClump = do - lines <- many1 (notFollowedBy blankline >> anyLine) + lns <- many1 (notFollowedBy blankline >> anyLine) blanks <- blanklines <|> (eof >> return "\n") - return $ (unlines lines) ++ blanks + return $ (unlines lns) ++ blanks -- | Parse a string of characters between an open character -- and a close character, including text between balanced --- pairs of open and close. For example, +-- pairs of open and close, which must be different. For example, -- @charsInBalanced '(' ')'@ will parse "(hello (there))" -- and return "hello (there)". Stop if a blank line is -- encountered. charsInBalanced :: Char -> Char -> GenParser Char st String charsInBalanced open close = try $ do char open - raw <- manyTill ( (do res <- charsInBalanced open close - return $ [open] ++ res ++ [close]) - <|> (do notFollowedBy' (blankline >> blanklines) - count 1 anyChar)) - (char close) + raw <- many $ (many1 (noneOf [open, close, '\n'])) + <|> (do res <- charsInBalanced open close + return $ [open] ++ res ++ [close]) + <|> try (string "\n" >>~ notFollowedBy' blanklines) + char close return $ concat raw -- | Like @charsInBalanced@, but allow blank lines in the content. charsInBalanced' :: Char -> Char -> GenParser Char st String charsInBalanced' open close = try $ do char open - raw <- manyTill ( (do res <- charsInBalanced open close + raw <- many $ (many1 (noneOf [open, close])) + <|> (do res <- charsInBalanced' open close return $ [open] ++ res ++ [close]) - <|> count 1 anyChar) - (char close) + char close return $ concat raw -- | Parses a roman numeral (uppercase or lowercase), returns number. romanNumeral :: Bool -- ^ Uppercase if true -> GenParser Char st Int -romanNumeral upper = try $ do - let charAnyCase c = char (if upper then toUpper c else c) +romanNumeral upperCase = do + let charAnyCase c = char (if upperCase then toUpper c else c) let one = charAnyCase 'i' let five = charAnyCase 'v' let ten = charAnyCase 'x' @@ -389,8 +376,8 @@ -- | Fail if reader is in strict markdown syntax mode. failIfStrict :: GenParser Char ParserState () failIfStrict = do - state <- getState - if stateStrict state then fail "strict mode" else return () + state <- getState + if stateStrict state then fail "strict mode" else return () -- | Parses backslash, then applies character parser. escaped :: GenParser Char st Char -- ^ Parser for character to escape @@ -494,7 +481,7 @@ Period -> inPeriod OneParen -> inOneParen TwoParens -> inTwoParens - (start, style, delim) <- context num + (start, _, _) <- context num return start -- | Parses a character reference and returns a Str element. @@ -639,7 +626,7 @@ -> Int -- ^ Number of spaces (rel to block) to indent first line -> String -- ^ Contents of block to indent -> String -indentBy num first [] = "" +indentBy _ _ [] = "" indentBy num first str = let (firstLine:restLines) = lines str firstLineIndent = num + first @@ -692,21 +679,21 @@ orderedListMarkers :: (Int, ListNumberStyle, ListNumberDelim) -> [String] orderedListMarkers (start, numstyle, numdelim) = let singleton c = [c] - seq = case numstyle of - DefaultStyle -> map show [start..] - Decimal -> map show [start..] - UpperAlpha -> drop (start - 1) $ cycle $ - map singleton ['A'..'Z'] - LowerAlpha -> drop (start - 1) $ cycle $ - map singleton ['a'..'z'] - UpperRoman -> map toRomanNumeral [start..] - LowerRoman -> map (map toLower . toRomanNumeral) [start..] + nums = case numstyle of + DefaultStyle -> map show [start..] + Decimal -> map show [start..] + UpperAlpha -> drop (start - 1) $ cycle $ + map singleton ['A'..'Z'] + LowerAlpha -> drop (start - 1) $ cycle $ + map singleton ['a'..'z'] + UpperRoman -> map toRomanNumeral [start..] + LowerRoman -> map (map toLower . toRomanNumeral) [start..] inDelim str = case numdelim of DefaultDelim -> str ++ "." Period -> str ++ "." OneParen -> str ++ ")" TwoParens -> "(" ++ str ++ ")" - in map inDelim seq + in map inDelim nums -- | Normalize a list of inline elements: remove leading and trailing -- @Space@ elements, collapse double @Space@s into singles, and @@ -739,18 +726,18 @@ [Para a] -> if any containsPara others then items else others ++ [[Plain a]] - otherwise -> items + _ -> items containsPara :: [Block] -> Bool containsPara [] = False -containsPara ((Para a):rest) = True +containsPara ((Para _):_) = True containsPara ((BulletList items):rest) = any containsPara items || containsPara rest containsPara ((OrderedList _ items):rest) = any containsPara items || containsPara rest containsPara ((DefinitionList items):rest) = any containsPara (map snd items) || containsPara rest -containsPara (x:rest) = containsPara rest +containsPara (_:rest) = containsPara rest -- | Data structure for defining hierarchical Pandoc documents data Element = Blk Block @@ -759,7 +746,7 @@ -- | Returns @True@ on Header block with at least the specified level headerAtLeast :: Int -> Block -> Bool headerAtLeast level (Header x _) = x <= level -headerAtLeast level _ = False +headerAtLeast _ _ = False -- | Convert list of Pandoc blocks into (hierarchical) list of Elements hierarchicalize :: [Block] -> [Element] @@ -800,6 +787,7 @@ } deriving Show -- | Default writer options. +defaultWriterOptions :: WriterOptions defaultWriterOptions = WriterOptions { writerStandalone = False, writerHeader = "", diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs --- a/src/Text/Pandoc/Writers/LaTeX.hs +++ b/src/Text/Pandoc/Writers/LaTeX.hs @@ -31,10 +31,11 @@ import Text.Pandoc.Definition import Text.Pandoc.Shared import Text.Printf ( printf ) -import Data.List ( (\\), isInfixOf ) +import Data.List ( (\\), isInfixOf, intersperse ) import Data.Char ( toLower ) import qualified Data.Set as S import Control.Monad.State +import Text.PrettyPrint.HughesPJ hiding ( Str ) data WriterState = WriterState { stIncludes :: S.Set String -- strings to include in header @@ -51,51 +52,56 @@ -- | Convert Pandoc to LaTeX. writeLaTeX :: WriterOptions -> Pandoc -> String writeLaTeX options document = - evalState (pandocToLaTeX options document) $ + render $ evalState (pandocToLaTeX options document) $ WriterState { stIncludes = S.empty, stInNote = False, stOLLevel = 1 } -pandocToLaTeX :: WriterOptions -> Pandoc -> State WriterState String +pandocToLaTeX :: WriterOptions -> Pandoc -> State WriterState Doc pandocToLaTeX options (Pandoc meta blocks) = do main <- blockListToLaTeX blocks head <- if writerStandalone options then latexHeader options meta - else return "" - let body = writerIncludeBefore options ++ main ++ - writerIncludeAfter options + else return empty + let before = if null (writerIncludeBefore options) + then empty + else text (writerIncludeBefore options) + let after = if null (writerIncludeAfter options) + then empty + else text (writerIncludeAfter options) + let body = before $$ main $$ after let toc = if writerTableOfContents options - then "\\tableofcontents\n\n" - else "" + then text "\\tableofcontents\n" + else empty let foot = if writerStandalone options - then "\n\\end{document}\n" - else "" - return $ head ++ toc ++ body ++ foot + then text "\\end{document}" + else empty + return $ head $$ toc $$ body $$ foot -- | Insert bibliographic information into LaTeX header. latexHeader :: WriterOptions -- ^ Options, including LaTeX header -> Meta -- ^ Meta with bibliographic information - -> State WriterState String + -> State WriterState Doc latexHeader options (Meta title authors date) = do titletext <- if null title - then return "" - else do title' <- inlineListToLaTeX title - return $ "\\title{" ++ title' ++ "}\n" - extras <- get >>= (return . unlines . S.toList. stIncludes) - let verbatim = if "\\usepackage{fancyvrb}" `isInfixOf` extras - then "\\VerbatimFootnotes % allows verbatim text in footnotes\n" - else "" - let authorstext = "\\author{" ++ - joinWithSep "\\\\" (map stringToLaTeX authors) ++ "}\n" + then return empty + else inlineListToLaTeX title >>= return . inCmd "title" + headerIncludes <- get >>= return . S.toList . stIncludes + let extras = text $ unlines headerIncludes + let verbatim = if "\\usepackage{fancyvrb}" `elem` headerIncludes + then text "\\VerbatimFootnotes % allows verbatim text in footnotes" + else empty + let authorstext = text $ "\\author{" ++ + joinWithSep "\\\\" (map stringToLaTeX authors) ++ "}" let datetext = if date == "" - then "" - else "\\date{" ++ stringToLaTeX date ++ "}\n" - let maketitle = if null title then "" else "\\maketitle\n" + then empty + else text $ "\\date{" ++ stringToLaTeX date ++ "}" + let maketitle = if null title then empty else text "\\maketitle" let secnumline = if (writerNumberSections options) - then "" - else "\\setcounter{secnumdepth}{0}\n" - let baseHeader = writerHeader options - let header = baseHeader ++ extras - return $ header ++ secnumline ++ verbatim ++ titletext ++ authorstext ++ - datetext ++ "\\begin{document}\n" ++ maketitle ++ "\n" + then empty + else text "\\setcounter{secnumdepth}{0}" + let baseHeader = text $ writerHeader options + let header = baseHeader $$ extras + return $ header $$ secnumline $$ verbatim $$ titletext $$ authorstext $$ + datetext $$ text "\\begin{document}" $$ maketitle $$ text "" -- escape things as needed for LaTeX @@ -110,6 +116,10 @@ , ('>', "\\textgreater{}") ] +-- | Puts contents into LaTeX command. +inCmd :: String -> Doc -> Doc +inCmd cmd contents = char '\\' <> text cmd <> braces contents + -- | Remove all code elements from list of inline elements -- (because it's illegal to have verbatim inside some command arguments) deVerb :: [Inline] -> [Inline] @@ -120,51 +130,57 @@ -- | Convert Pandoc block element to LaTeX. blockToLaTeX :: Block -- ^ Block to convert - -> State WriterState String -blockToLaTeX Null = return "" -blockToLaTeX (Plain lst) = inlineListToLaTeX lst >>= return . (++ "\n") -blockToLaTeX (Para lst) = inlineListToLaTeX lst >>= return . (++ "\n\n") + -> State WriterState Doc +blockToLaTeX Null = return empty +blockToLaTeX (Plain lst) = wrapped inlineListToLaTeX lst >>= return +blockToLaTeX (Para lst) = + wrapped inlineListToLaTeX lst >>= return . (<> char '\n') blockToLaTeX (BlockQuote lst) = do contents <- blockListToLaTeX lst - return $ "\\begin{quote}\n" ++ contents ++ "\\end{quote}\n" + return $ text "\\begin{quote}" $$ contents $$ text "\\end{quote}" blockToLaTeX (CodeBlock str) = do st <- get - if stInNote st - then do addToHeader "\\usepackage{fancyvrb}" - return $ "\\begin{Verbatim}\n" ++ str ++ "\n\\end{Verbatim}\n" - else return $ "\\begin{verbatim}\n" ++ str ++ "\n\\end{verbatim}\n" -blockToLaTeX (RawHtml str) = return "" + env <- if stInNote st + then do addToHeader "\\usepackage{fancyvrb}" + return "Verbatim" + else return "verbatim" + return $ text ("\\begin{" ++ env ++ "}\n") <> text str <> + text ("\n\\end{" ++ env ++ "}") +blockToLaTeX (RawHtml str) = return empty blockToLaTeX (BulletList lst) = do items <- mapM listItemToLaTeX lst - return $ "\\begin{itemize}\n" ++ concat items ++ "\\end{itemize}\n" + return $ text "\\begin{itemize}" $$ vcat items $$ text "\\end{itemize}" blockToLaTeX (OrderedList (start, numstyle, numdelim) lst) = do st <- get let oldlevel = stOLLevel st put $ st {stOLLevel = oldlevel + 1} items <- mapM listItemToLaTeX lst - put $ st {stOLLevel = oldlevel} + modify (\st -> st {stOLLevel = oldlevel}) exemplar <- if numstyle /= DefaultStyle || numdelim /= DefaultDelim then do addToHeader "\\usepackage{enumerate}" - return $ "[" ++ head (orderedListMarkers (1, numstyle, numdelim)) ++ "]" - else return "" + return $ char '[' <> + text (head (orderedListMarkers (1, numstyle, + numdelim))) <> char ']' + else return empty let resetcounter = if start /= 1 && oldlevel <= 4 - then "\\setcounter{enum" ++ + then text $ "\\setcounter{enum" ++ map toLower (toRomanNumeral oldlevel) ++ - "}{" ++ show (start - 1) ++ "}\n" - else "" - return $ "\\begin{enumerate}" ++ exemplar ++ "\n" ++ - resetcounter ++ concat items ++ "\\end{enumerate}\n" + "}{" ++ show (start - 1) ++ "}" + else empty + return $ text "\\begin{enumerate}" <> exemplar $$ resetcounter $$ + vcat items $$ text "\\end{enumerate}" blockToLaTeX (DefinitionList lst) = do items <- mapM defListItemToLaTeX lst - return $ "\\begin{description}\n" ++ concat items ++ "\\end{description}\n" -blockToLaTeX HorizontalRule = return $ - "\\begin{center}\\rule{3in}{0.4pt}\\end{center}\n\n" + return $ text "\\begin{description}" $$ vcat items $$ + text "\\end{description}" +blockToLaTeX HorizontalRule = return $ text $ + "\\begin{center}\\rule{3in}{0.4pt}\\end{center}\n" blockToLaTeX (Header level lst) = do - text <- inlineListToLaTeX (deVerb lst) + txt <- inlineListToLaTeX (deVerb lst) return $ if (level > 0) && (level <= 3) - then "\\" ++ (concat (replicate (level - 1) "sub")) ++ - "section{" ++ text ++ "}\n\n" - else text ++ "\n\n" + then text ("\\" ++ (concat (replicate (level - 1) "sub")) ++ + "section{") <> txt <> text "}\n" + else txt <> char '\n' blockToLaTeX (Table caption aligns widths heads rows) = do headers <- tableRowToLaTeX heads captionText <- inlineListToLaTeX caption @@ -180,34 +196,37 @@ "\\hspace{0pt}}p{" ++ width ++ "\\columnwidth}") colWidths aligns - let tableBody = "\\begin{tabular}{" ++ colDescriptors ++ "}\n" ++ - headers ++ "\\hline\n" ++ concat rows' ++ "\\end{tabular}\n" - let centered str = "\\begin{center}\n" ++ str ++ "\\end{center}\n" + let tableBody = text ("\\begin{tabular}{" ++ colDescriptors ++ "}") $$ + headers $$ text "\\hline" $$ vcat rows' $$ + text "\\end{tabular}" + let centered txt = text "\\begin{center}" $$ txt $$ text "\\end{center}" addToHeader "\\usepackage{array}\n\ \% This is needed because raggedright in table elements redefines \\\\:\n\ \\\newcommand{\\PreserveBackslash}[1]{\\let\\temp=\\\\#1\\let\\\\=\\temp}\n\ \\\let\\PBS=\\PreserveBackslash" - return $ if null captionText - then centered tableBody ++ "\n" - else "\\begin{table}[h]\n" ++ centered tableBody ++ - "\\caption{" ++ captionText ++ "}\n" ++ "\\end{table}\n\n" + return $ if isEmpty captionText + then centered tableBody <> char '\n' + else text "\\begin{table}[h]" $$ centered tableBody $$ + inCmd "caption" captionText $$ text "\\end{table}\n" -blockListToLaTeX lst = mapM blockToLaTeX lst >>= return . concat +blockListToLaTeX lst = mapM blockToLaTeX lst >>= return . vcat -tableRowToLaTeX cols = - mapM blockListToLaTeX cols >>= return . (++ "\\\\\n") . (joinWithSep " & ") +tableRowToLaTeX cols = mapM blockListToLaTeX cols >>= + return . ($$ text "\\\\") . foldl (\row item -> row $$ + (if isEmpty row then empty else text " & ") <> item) empty -listItemToLaTeX lst = blockListToLaTeX lst >>= return . ("\\item "++) +listItemToLaTeX lst = blockListToLaTeX lst >>= return . (text "\\item " $$) . + (nest 2) defListItemToLaTeX (term, def) = do term' <- inlineListToLaTeX $ deVerb term def' <- blockListToLaTeX def - return $ "\\item[" ++ term' ++ "] " ++ def' + return $ text "\\item[" <> term' <> text "]" $$ def' -- | Convert list of inline elements to LaTeX. inlineListToLaTeX :: [Inline] -- ^ Inlines to convert - -> State WriterState String -inlineListToLaTeX lst = mapM inlineToLaTeX lst >>= return . concat + -> State WriterState Doc +inlineListToLaTeX lst = mapM inlineToLaTeX lst >>= return . hcat isQuoted :: Inline -> Bool isQuoted (Quoted _ _) = True @@ -216,68 +235,75 @@ -- | Convert inline element to LaTeX inlineToLaTeX :: Inline -- ^ Inline to convert - -> State WriterState String -inlineToLaTeX (Emph lst) = do - contents <- inlineListToLaTeX $ deVerb lst - return $ "\\emph{" ++ contents ++ "}" -inlineToLaTeX (Strong lst) = do - contents <- inlineListToLaTeX $ deVerb lst - return $ "\\textbf{" ++ contents ++ "}" + -> State WriterState Doc +inlineToLaTeX (Emph lst) = + inlineListToLaTeX (deVerb lst) >>= return . inCmd "emph" +inlineToLaTeX (Strong lst) = + inlineListToLaTeX (deVerb lst) >>= return . inCmd "textbf" inlineToLaTeX (Strikeout lst) = do contents <- inlineListToLaTeX $ deVerb lst addToHeader "\\usepackage[normalem]{ulem}" - return $ "\\sout{" ++ contents ++ "}" -inlineToLaTeX (Superscript lst) = do - contents <- inlineListToLaTeX $ deVerb lst - return $ "\\textsuperscript{" ++ contents ++ "}" + return $ inCmd "sout" contents +inlineToLaTeX (Superscript lst) = + inlineListToLaTeX (deVerb lst) >>= return . inCmd "textsuperscript" inlineToLaTeX (Subscript lst) = do contents <- inlineListToLaTeX $ deVerb lst -- oddly, latex includes \textsuperscript but not \textsubscript -- so we have to define it: addToHeader "\\newcommand{\\textsubscript}[1]{\\ensuremath{_{\\scriptsize\\textrm{#1}}}}" - return $ "\\textsubscript{" ++ contents ++ "}" + return $ inCmd "textsubscript" contents inlineToLaTeX (Code str) = do st <- get if stInNote st then do addToHeader "\\usepackage{fancyvrb}" else return () let chr = ((enumFromTo '!' '~') \\ str) !! 0 - return $ "\\verb" ++ [chr] ++ str ++ [chr] + return $ text $ "\\verb" ++ [chr] ++ str ++ [chr] inlineToLaTeX (Quoted SingleQuote lst) = do contents <- inlineListToLaTeX lst - let s1 = if (not (null lst)) && (isQuoted (head lst)) then "\\," else "" - let s2 = if (not (null lst)) && (isQuoted (last lst)) then "\\," else "" - return $ "`" ++ s1 ++ contents ++ s2 ++ "'" + let s1 = if (not (null lst)) && (isQuoted (head lst)) + then text "\\," + else empty + let s2 = if (not (null lst)) && (isQuoted (last lst)) + then text "\\," + else empty + return $ char '`' <> s1 <> contents <> s2 <> char '\'' inlineToLaTeX (Quoted DoubleQuote lst) = do contents <- inlineListToLaTeX lst - let s1 = if (not (null lst)) && (isQuoted (head lst)) then "\\," else "" - let s2 = if (not (null lst)) && (isQuoted (last lst)) then "\\," else "" - return $ "``" ++ s1 ++ contents ++ s2 ++ "''" -inlineToLaTeX Apostrophe = return "'" -inlineToLaTeX EmDash = return "---" -inlineToLaTeX EnDash = return "--" -inlineToLaTeX Ellipses = return "\\ldots{}" -inlineToLaTeX (Str str) = return $ stringToLaTeX str -inlineToLaTeX (TeX str) = return str -inlineToLaTeX (HtmlInline str) = return "" -inlineToLaTeX (LineBreak) = return "\\\\\n" -inlineToLaTeX Space = return " " -inlineToLaTeX (Link text (src, tit)) = do + let s1 = if (not (null lst)) && (isQuoted (head lst)) + then text "\\," + else empty + let s2 = if (not (null lst)) && (isQuoted (last lst)) + then text "\\," + else empty + return $ text "``" <> s1 <> contents <> s2 <> text "''" +inlineToLaTeX Apostrophe = return $ char '\'' +inlineToLaTeX EmDash = return $ text "---" +inlineToLaTeX EnDash = return $ text "--" +inlineToLaTeX Ellipses = return $ text "\\ldots{}" +inlineToLaTeX (Str str) = return $ text $ stringToLaTeX str +inlineToLaTeX (TeX str) = return $ text str +inlineToLaTeX (HtmlInline str) = return empty +inlineToLaTeX (LineBreak) = return $ text "\\\\" +inlineToLaTeX Space = return $ char ' ' +inlineToLaTeX (Link txt (src, _)) = do addToHeader "\\usepackage[breaklinks=true]{hyperref}" - case text of + case txt of [Code x] | x == src -> -- autolink - return $ "\\url{" ++ x ++ "}" - _ -> do contents <- inlineListToLaTeX $ deVerb text - return $ "\\href{" ++ src ++ "}{" ++ contents ++ "}" + do addToHeader "\\usepackage{url}" + return $ text $ "\\url{" ++ x ++ "}" + _ -> do contents <- inlineListToLaTeX $ deVerb txt + return $ text ("\\href{" ++ src ++ "}{") <> contents <> + char '}' inlineToLaTeX (Image alternate (source, tit)) = do addToHeader "\\usepackage{graphicx}" - return $ "\\includegraphics{" ++ source ++ "}" + return $ text $ "\\includegraphics{" ++ source ++ "}" inlineToLaTeX (Note contents) = do st <- get put (st {stInNote = True}) contents' <- blockListToLaTeX contents - st <- get - put (st {stInNote = False}) - return $ "\\footnote{" ++ stripTrailingNewlines contents' ++ "\n}" + modify (\st -> st {stInNote = False}) + return $ text "\\footnote{" $$ + (nest 11 $ text (stripTrailingNewlines $ render contents') <> text "\n}") -- note: the \n before } is important; removing it causes problems -- if a Verbatim environment occurs at the end of the footnote. diff --git a/src/Text/Pandoc/Writers/Man.hs b/src/Text/Pandoc/Writers/Man.hs --- a/src/Text/Pandoc/Writers/Man.hs +++ b/src/Text/Pandoc/Writers/Man.hs @@ -98,12 +98,6 @@ let marker = text "\n.SS [" <> text (show num) <> char ']' return $ marker $$ contents -wrappedMan :: WriterOptions -> [Inline] -> State WriterState Doc -wrappedMan opts sect = do - let chunks = splitBy Space sect - chunks' <- mapM (inlineListToMan opts) chunks - return $ fsep chunks' - -- | Association list of characters to escape. manEscapes :: [(Char, String)] manEscapes = [('\160', "\\ "), ('\'', "\\[aq]")] ++ backslashEscapes "\".@\\" @@ -121,9 +115,9 @@ -> Block -- ^ Block element -> State WriterState Doc blockToMan opts Null = return empty -blockToMan opts (Plain inlines) = wrappedMan opts inlines +blockToMan opts (Plain inlines) = wrapped (inlineListToMan opts) inlines blockToMan opts (Para inlines) = do - contents <- wrappedMan opts inlines + contents <- wrapped (inlineListToMan opts) inlines return $ text ".PP" $$ contents blockToMan opts (RawHtml str) = return $ text str blockToMan opts HorizontalRule = return $ text $ ".PP\n * * * * *" diff --git a/src/Text/Pandoc/Writers/Markdown.hs b/src/Text/Pandoc/Writers/Markdown.hs --- a/src/Text/Pandoc/Writers/Markdown.hs +++ b/src/Text/Pandoc/Writers/Markdown.hs @@ -33,6 +33,7 @@ import Text.Pandoc.Definition import Text.Pandoc.Shared import Text.Pandoc.Blocks +import Text.ParserCombinators.Parsec ( parse, (<|>), GenParser ) import Data.List ( group, isPrefixOf, drop, find, intersperse ) import Text.PrettyPrint.HughesPJ hiding ( Str ) import Control.Monad.State @@ -96,12 +97,6 @@ let marker = text "[^" <> text (show num) <> text "]:" return $ hang marker (writerTabStop opts) contents -wrappedMarkdown :: WriterOptions -> [Inline] -> State WriterState Doc -wrappedMarkdown opts sect = do - let chunks = splitBy Space sect - chunks' <- mapM (inlineListToMarkdown opts) chunks - return $ fsep chunks' - -- | Escape special characters for Markdown. escapeString :: String -> String escapeString = escapeStringUsing markdownEscapes @@ -145,15 +140,37 @@ then [] else [BulletList $ map elementToListItem subsecs] +-- | Ordered list start parser for use in Para below. +olMarker :: GenParser Char st Char +olMarker = do (start, style, delim) <- anyOrderedListMarker + if delim == Period && + (style == UpperAlpha || (style == UpperRoman && + start `elem` [1, 5, 10, 50, 100, 500, 1000])) + then spaceChar >> spaceChar + else spaceChar + +-- | True if string begins with an ordered list marker +beginsWithOrderedListMarker :: String -> Bool +beginsWithOrderedListMarker str = + case parse olMarker "para start" str of + Left _ -> False + Right _ -> True + -- | Convert Pandoc block element to markdown. blockToMarkdown :: WriterOptions -- ^ Options -> Block -- ^ Block element -> State WriterState Doc blockToMarkdown opts Null = return empty -blockToMarkdown opts (Plain inlines) = wrappedMarkdown opts inlines +blockToMarkdown opts (Plain inlines) = + wrapped (inlineListToMarkdown opts) inlines blockToMarkdown opts (Para inlines) = do - contents <- wrappedMarkdown opts inlines - return $ contents <> text "\n" + contents <- wrapped (inlineListToMarkdown opts) inlines + -- escape if para starts with ordered list marker + let esc = if (not (writerStrictMarkdown opts)) && + beginsWithOrderedListMarker (render contents) + then char '\\' + else empty + return $ esc <> contents <> text "\n" blockToMarkdown opts (RawHtml str) = return $ text str blockToMarkdown opts HorizontalRule = return $ text "\n* * * * *\n" blockToMarkdown opts (Header level inlines) = do diff --git a/src/Text/Pandoc/Writers/RST.hs b/src/Text/Pandoc/Writers/RST.hs --- a/src/Text/Pandoc/Writers/RST.hs +++ b/src/Text/Pandoc/Writers/RST.hs @@ -107,14 +107,8 @@ -- | Take list of inline elements and return wrapped doc. wrappedRST :: WriterOptions -> [Inline] -> State WriterState Doc wrappedRST opts inlines = - mapM (wrappedRSTSection opts) (splitBy LineBreak inlines) >>= + mapM (wrapped (inlineListToRST opts)) (splitBy LineBreak inlines) >>= return . vcat - -wrappedRSTSection :: WriterOptions -> [Inline] -> State WriterState Doc -wrappedRSTSection opts sect = do - let chunks = splitBy Space sect - chunks' <- mapM (inlineListToRST opts) chunks - return $ fsep chunks' -- | Escape special characters for RST. escapeString :: String -> String diff --git a/tests/latex-reader.latex b/tests/latex-reader.latex new file mode 100644 --- /dev/null +++ b/tests/latex-reader.latex @@ -0,0 +1,830 @@ +\documentclass{article} +\usepackage[mathletters]{ucs} +\usepackage[utf8x]{inputenc} +\setlength{\parindent}{0pt} +\setlength{\parskip}{6pt plus 2pt minus 1pt} + +\newcommand{\textsubscript}[1]{\ensuremath{_{\scriptsize\textrm{#1}}}} +\usepackage[breaklinks=true]{hyperref} +\usepackage[normalem]{ulem} +\usepackage{enumerate} +\usepackage{fancyvrb} +\usepackage{graphicx} +\usepackage{url} + +\setcounter{secnumdepth}{0} +\VerbatimFootnotes % allows verbatim text in footnotes +\title{Pandoc Test Suite} +\author{John MacFarlane\\Anonymous} +\date{July 17, 2006} +\begin{document} +\maketitle + +This is a set of tests for pandoc. Most of them are adapted from +John Gruber's markdown test suite. + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Headers} + +\subsection{Level 2 with an \href{/url}{embedded link}} + +\subsubsection{Level 3 with \emph{emphasis}} + +Level 4 + +Level 5 + +\section{Level 1} + +\subsection{Level 2 with \emph{emphasis}} + +\subsubsection{Level 3} + +with no blank line + +\subsection{Level 2} + +with no blank line + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Paragraphs} + +Here's a regular paragraph. + +In Markdown 1.0.0 and earlier. Version 8. This line turns into a +list item. Because a hard-wrapped line in the middle of a paragraph +looked like a list item. + +Here's one with a bullet. * criminey. + +There should be a hard line break\\here. + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Block Quotes} + +E-mail style: + +\begin{quote} +This is a block quote. It is pretty short. + +\end{quote} +\begin{quote} +Code in a block quote: + +\begin{verbatim} +sub status { + print "working"; +} +\end{verbatim} +A list: + +\begin{enumerate}[1.] +\item + item one +\item + item two +\end{enumerate} +Nested block quotes: + +\begin{quote} +nested + +\end{quote} +\begin{quote} +nested + +\end{quote} +\end{quote} +This should not be a block quote: 2 \textgreater{} 1. + +Box-style: + +\begin{quote} +Example: + +\begin{verbatim} +sub status { + print "working"; +} +\end{verbatim} +\end{quote} +\begin{quote} +\begin{enumerate}[1.] +\item + do laundry +\item + take out the trash +\end{enumerate} +\end{quote} +Here's a nested one: + +\begin{quote} +Joe said: + +\begin{quote} +Don't quote me. + +\end{quote} +\end{quote} +And a following paragraph. + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Code Blocks} + +Code: + +\begin{verbatim} +---- (should be four hyphens) + +sub status { + print "working"; +} + +this code block is indented by one tab +\end{verbatim} +And: + +\begin{verbatim} + this code block is indented by two tabs + +These should not be escaped: \$ \\ \> \[ \{ +\end{verbatim} +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Lists} + +\subsection{Unordered} + +Asterisks tight: + +\begin{itemize} +\item + asterisk 1 +\item + asterisk 2 +\item + asterisk 3 +\end{itemize} +Asterisks loose: + +\begin{itemize} +\item + asterisk 1 + +\item + asterisk 2 + +\item + asterisk 3 + +\end{itemize} +Pluses tight: + +\begin{itemize} +\item + Plus 1 +\item + Plus 2 +\item + Plus 3 +\end{itemize} +Pluses loose: + +\begin{itemize} +\item + Plus 1 + +\item + Plus 2 + +\item + Plus 3 + +\end{itemize} +Minuses tight: + +\begin{itemize} +\item + Minus 1 +\item + Minus 2 +\item + Minus 3 +\end{itemize} +Minuses loose: + +\begin{itemize} +\item + Minus 1 + +\item + Minus 2 + +\item + Minus 3 + +\end{itemize} +\subsection{Ordered} + +Tight: + +\begin{enumerate}[1.] +\item + First +\item + Second +\item + Third +\end{enumerate} +and: + +\begin{enumerate}[1.] +\item + One +\item + Two +\item + Three +\end{enumerate} +Loose using tabs: + +\begin{enumerate}[1.] +\item + First + +\item + Second + +\item + Third + +\end{enumerate} +and using spaces: + +\begin{enumerate}[1.] +\item + One + +\item + Two + +\item + Three + +\end{enumerate} +Multiple paragraphs: + +\begin{enumerate}[1.] +\item + Item 1, graf one. + + Item 1. graf two. The quick brown fox jumped over the lazy dog's + back. + +\item + Item 2. + +\item + Item 3. + +\end{enumerate} +\subsection{Nested} + +\begin{itemize} +\item + Tab + \begin{itemize} + \item + Tab + \begin{itemize} + \item + Tab + \end{itemize} + \end{itemize} +\end{itemize} +Here's another: + +\begin{enumerate}[1.] +\item + First +\item + Second: + \begin{itemize} + \item + Fee + \item + Fie + \item + Foe + \end{itemize} +\item + Third +\end{enumerate} +Same thing but with paragraphs: + +\begin{enumerate}[1.] +\item + First + +\item + Second: + + \begin{itemize} + \item + Fee + \item + Fie + \item + Foe + \end{itemize} +\item + Third + +\end{enumerate} +\subsection{Tabs and spaces} + +\begin{itemize} +\item + this is a list item indented with tabs + +\item + this is a list item indented with spaces + + \begin{itemize} + \item + this is an example list item indented with tabs + + \item + this is an example list item indented with spaces + + \end{itemize} +\end{itemize} +\subsection{Fancy list markers} + +\begin{enumerate}[(1)] +\setcounter{enumi}{1} +\item + begins with 2 +\item + and now 3 + + with a continuation + + \begin{enumerate}[i.] + \setcounter{enumii}{3} + \item + sublist with roman numerals, starting with 4 + \item + more items + \begin{enumerate}[(A)] + \item + a subsublist + \item + a subsublist + \end{enumerate} + \end{enumerate} +\end{enumerate} +Nesting: + +\begin{enumerate}[A.] +\item + Upper Alpha + \begin{enumerate}[I.] + \item + Upper Roman. + \begin{enumerate}[(1)] + \setcounter{enumiii}{5} + \item + Decimal start with 6 + \begin{enumerate}[a)] + \setcounter{enumiv}{2} + \item + Lower alpha with paren + \end{enumerate} + \end{enumerate} + \end{enumerate} +\end{enumerate} +Autonumbering: + +\begin{enumerate} +\item + Autonumber. +\item + More. + \begin{enumerate} + \item + Nested. + \end{enumerate} +\end{enumerate} +Should not be a list item: + +M.A. 2007 + +B. Williams + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Definition Lists} + +Tight using spaces: + +\begin{description} +\item[apple] +red fruit +\item[orange] +orange fruit +\item[banana] +yellow fruit +\end{description} +Tight using tabs: + +\begin{description} +\item[apple] +red fruit +\item[orange] +orange fruit +\item[banana] +yellow fruit +\end{description} +Loose: + +\begin{description} +\item[apple] +red fruit + +\item[orange] +orange fruit + +\item[banana] +yellow fruit + +\end{description} +Multiple blocks with italics: + +\begin{description} +\item[\emph{apple}] +red fruit + +contains seeds, crisp, pleasant to taste + +\item[\emph{orange}] +orange fruit + +\begin{verbatim} +{ orange code block } +\end{verbatim} +\begin{quote} +orange block quote + +\end{quote} +\end{description} +\section{HTML Blocks} + +Simple block on one line: + +foo +And nested without indentation: + +foo +bar +Interpreted markdown in a table: + +This is \emph{emphasized} +And this is \textbf{strong} +Here's a simple block: + +foo +This should be a code block, though: + +\begin{verbatim} +
+ foo +
+\end{verbatim} +As should this: + +\begin{verbatim} +
foo
+\end{verbatim} +Now, nested: + +foo +This should just be an HTML comment: + +Multiline: + +Code block: + +\begin{verbatim} + +\end{verbatim} +Just plain comment, with trailing spaces on the line: + +Code: + +\begin{verbatim} +
+\end{verbatim} +Hr's: + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Inline Markup} + +This is \emph{emphasized}, and so \emph{is this}. + +This is \textbf{strong}, and so \textbf{is this}. + +An \emph{\href{/url}{emphasized link}}. + +\textbf{\emph{This is strong and em.}} + +So is \textbf{\emph{this}} word. + +\textbf{\emph{This is strong and em.}} + +So is \textbf{\emph{this}} word. + +This is code: \verb!>!, \verb!$!, \verb!\!, \verb!\$!, +\verb!!. + +\sout{This is \emph{strikeout}.} + +Superscripts: a\textsuperscript{bc}d +a\textsuperscript{\emph{hello}} a\textsuperscript{hello there}. + +Subscripts: H\textsubscript{2}O, H\textsubscript{23}O, +H\textsubscript{many of them}O. + +These should not be superscripts or subscripts, because of the +unescaped spaces: a\^{}b c\^{}d, a\ensuremath{\sim}b +c\ensuremath{\sim}d. + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Smart quotes, ellipses, dashes} + +``Hello,'' said the spider. ``\,`Shelob' is my name.'' + +`A', `B', and `C' are letters. + +`Oak,' `elm,' and `beech' are names of trees. So is `pine.' + +`He said, ``I want to go.''\,' Were you alive in the 70's? + +Here is some quoted `\verb!code!' and a +``\href{http://example.com/?foo=1&bar=2}{quoted link}''. + +Some dashes: one---two---three---four---five. + +Dashes between numbers: 5--7, 255--66, 1987--1999. + +Ellipses\ldots{}and\ldots{}and\ldots{}. + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{LaTeX} + +\begin{itemize} +\item + \cite[22-23]{smith.1899} +\item + \doublespacing +\item + $2+2=4$ +\item + $x \in y$ +\item + $\alpha \wedge \omega$ +\item + $223$ +\item + $p$-Tree +\item + $\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$ +\item + Here's one that has a line break in it: + $\alpha + \omega \times x^2$. +\end{itemize} +These shouldn't be math: + +\begin{itemize} +\item + To get the famous equation, write \verb!$e = mc^2$!. +\item + \$22,000 is a \emph{lot} of money. So is \$34,000. (It worked if + ``lot'' is emphasized.) +\item + Escaped \verb!$!: \$73 \emph{this should be emphasized} 23\$. +\end{itemize} +Here's a LaTeX table: + +\begin{tabular}{|l|l|}\hline +Animal & Number \\ \hline +Dog & 2 \\ +Cat & 1 \\ \hline +\end{tabular} + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Special Characters} + +Here is some unicode: + +\begin{itemize} +\item + I hat: Î +\item + o umlaut: ö +\item + section: § +\item + set membership: ∈ +\item + copyright: © +\end{itemize} +AT\&T has an ampersand in their name. + +AT\&T is another way to write it. + +This \& that. + +4 \textless{} 5. + +6 \textgreater{} 5. + +Backslash: \textbackslash{} + +Backtick: ` + +Asterisk: * + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: [ + +Right bracket: ] + +Left paren: ( + +Right paren: ) + +Greater-than: \textgreater{} + +Hash: \# + +Period: . + +Bang: ! + +Plus: + + +Minus: - + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Links} + +\subsection{Explicit} + +Just a \href{/url/}{URL}. + +\href{/url/}{URL and title}. + +\href{/url/}{URL and title}. + +\href{/url/}{URL and title}. + +\href{/url/}{URL and title} + +\href{/url/}{URL and title} + +\href{/url/with_underscore}{with\_underscore} + +\href{mailto:nobody@nowhere.net}{Email link} + +\href{}{Empty}. + +\subsection{Reference} + +Foo \href{/url/}{bar}. + +Foo \href{/url/}{bar}. + +Foo \href{/url/}{bar}. + +With \href{/url/}{embedded [brackets]}. + +\href{/url/}{b} by itself should be a link. + +Indented \href{/url}{once}. + +Indented \href{/url}{twice}. + +Indented \href{/url}{thrice}. + +This should [not][] be a link. + +\begin{verbatim} +[not]: /url +\end{verbatim} +Foo \href{/url/}{bar}. + +Foo \href{/url/}{biz}. + +\subsection{With ampersands} + +Here's a +\href{http://example.com/?foo=1&bar=2}{link with an ampersand in the URL}. + +Here's a link with an amersand in the link text: +\href{http://att.com/}{AT\&T}. + +Here's an \href{/script?foo=1&bar=2}{inline link}. + +Here's an +\href{/script?foo=1&bar=2}{inline link in pointy braces}. + +\subsection{Autolinks} + +With an ampersand: \url{http://example.com/?foo=1&bar=2} + +\begin{itemize} +\item + In a list? +\item + \url{http://example.com/} +\item + It should. +\end{itemize} +An e-mail address: +\href{mailto:nobody@nowhere.net}{\texttt{nobody@nowhere.net}} + +\begin{quote} +Blockquoted: \url{http://example.com/} + +\end{quote} +Auto-links should not occur here: \verb!! + +\begin{verbatim} +or here: +\end{verbatim} +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Images} + +From ``Voyage dans la Lune'' by Georges Melies (1902): + +\includegraphics{lalune.jpg} + +Here is a movie \includegraphics{movie.jpg} icon. + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Footnotes} + +Here is a footnote +reference,\footnote{ Here is the footnote. It can go anywhere after the footnote +reference. It need not be placed at the end of the document. +} +and +another.\footnote{ Here's the long note. This one contains multiple blocks. + +Subsequent blocks are indented to show that they belong to the +footnote (as with list items). + +\begin{Verbatim} + { } +\end{Verbatim} +If you want, you can indent every line, but you can also be lazy +and just indent the first line of each block. +} +This should \emph{not} be a footnote reference, because it contains +a space.[\^{}my note] Here is an inline +note.\footnote{ This is \emph{easier} to type. Inline notes may contain +\href{http://google.com}{links} and \verb!]! verbatim characters, +as well as [bracketed text]. +} + +\begin{quote} +Notes can go in quotes.\footnote{ In quote. +} + +\end{quote} +\begin{enumerate}[1.] +\item + And in list items.\footnote{ In list. +} +\end{enumerate} +This paragraph should not be part of the note, as it is not +indented. + +\end{document} diff --git a/tests/latex-reader.native b/tests/latex-reader.native new file mode 100644 --- /dev/null +++ b/tests/latex-reader.native @@ -0,0 +1,378 @@ +Pandoc (Meta [Str "Pandoc",Space,Str "Test",Space,Str "Suite"] ["John MacFarlane","Anonymous"] "July 17, 2006") +[ Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber",Apostrophe,Str "s",Space,Str "markdown",Space,Str "test",Space,Str "suite."] +, HorizontalRule +, Header 1 [Str "Headers"] +, Header 2 [Str "Level",Space,Str "2",Space,Str "with",Space,Str "an",Space,Link [Str "embedded",Space,Str "link"] ("/url","")] +, Header 3 [Str "Level",Space,Str "3",Space,Str "with",Space,Emph [Str "emphasis"]] +, Para [Str "Level",Space,Str "4"] +, Para [Str "Level",Space,Str "5"] +, Header 1 [Str "Level",Space,Str "1"] +, Header 2 [Str "Level",Space,Str "2",Space,Str "with",Space,Emph [Str "emphasis"]] +, Header 3 [Str "Level",Space,Str "3"] +, Para [Str "with",Space,Str "no",Space,Str "blank",Space,Str "line"] +, Header 2 [Str "Level",Space,Str "2"] +, Para [Str "with",Space,Str "no",Space,Str "blank",Space,Str "line"] +, HorizontalRule +, Header 1 [Str "Paragraphs"] +, Para [Str "Here",Apostrophe,Str "s",Space,Str "a",Space,Str "regular",Space,Str "paragraph."] +, Para [Str "In",Space,Str "Markdown",Space,Str "1.0.0",Space,Str "and",Space,Str "earlier.",Space,Str "Version",Space,Str "8.",Space,Str "This",Space,Str "line",Space,Str "turns",Space,Str "into",Space,Str "a",Space,Str "list",Space,Str "item.",Space,Str "Because",Space,Str "a",Space,Str "hard",Str "-",Str "wrapped",Space,Str "line",Space,Str "in",Space,Str "the",Space,Str "middle",Space,Str "of",Space,Str "a",Space,Str "paragraph",Space,Str "looked",Space,Str "like",Space,Str "a",Space,Str "list",Space,Str "item."] +, Para [Str "Here",Apostrophe,Str "s",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet.",Space,Str "*",Space,Str "criminey."] +, Para [Str "There",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "hard",Space,Str "line",Space,Str "break",LineBreak,Str "here."] +, HorizontalRule +, Header 1 [Str "Block",Space,Str "Quotes"] +, Para [Str "E",Str "-",Str "mail",Space,Str "style:"] +, BlockQuote + [ Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "block",Space,Str "quote.",Space,Str "It",Space,Str "is",Space,Str "pretty",Space,Str "short."] ] + +, BlockQuote + [ Para [Str "Code",Space,Str "in",Space,Str "a",Space,Str "block",Space,Str "quote:"] + , CodeBlock "sub status {\n print \"working\";\n}" + , Para [Str "A",Space,Str "list:"] + , OrderedList (1,Decimal,Period) + [ [ Para [Str "item",Space,Str "one"] ] + , [ Para [Str "item",Space,Str "two"] ] ] + , Para [Str "Nested",Space,Str "block",Space,Str "quotes:"] + , BlockQuote + [ Para [Str "nested"] ] + + , BlockQuote + [ Para [Str "nested"] ] + ] +, Para [Str "This",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "block",Space,Str "quote:",Space,Str "2",Space,Str ">",Space,Str "1."] +, Para [Str "Box",Str "-",Str "style:"] +, BlockQuote + [ Para [Str "Example:"] + , CodeBlock "sub status {\n print \"working\";\n}" ] +, BlockQuote + [ OrderedList (1,Decimal,Period) + [ [ Para [Str "do",Space,Str "laundry"] ] + , [ Para [Str "take",Space,Str "out",Space,Str "the",Space,Str "trash"] ] ] ] +, Para [Str "Here",Apostrophe,Str "s",Space,Str "a",Space,Str "nested",Space,Str "one:"] +, BlockQuote + [ Para [Str "Joe",Space,Str "said:"] + , BlockQuote + [ Para [Str "Don",Apostrophe,Str "t",Space,Str "quote",Space,Str "me."] ] + ] +, Para [Str "And",Space,Str "a",Space,Str "following",Space,Str "paragraph."] +, HorizontalRule +, Header 1 [Str "Code",Space,Str "Blocks"] +, Para [Str "Code:"] +, CodeBlock "---- (should be four hyphens)\n\nsub status {\n print \"working\";\n}\n\nthis code block is indented by one tab" +, Para [Str "And:"] +, CodeBlock " this code block is indented by two tabs\n\nThese should not be escaped: \\$ \\\\ \\> \\[ \\{" +, HorizontalRule +, Header 1 [Str "Lists"] +, Header 2 [Str "Unordered"] +, Para [Str "Asterisks",Space,Str "tight:"] +, BulletList + [ [ Para [Str "asterisk",Space,Str "1"] ] + , [ Para [Str "asterisk",Space,Str "2"] ] + , [ Para [Str "asterisk",Space,Str "3"] ] ] +, Para [Str "Asterisks",Space,Str "loose:"] +, BulletList + [ [ Para [Str "asterisk",Space,Str "1"] ] + , [ Para [Str "asterisk",Space,Str "2"] ] + , [ Para [Str "asterisk",Space,Str "3"] ] ] +, Para [Str "Pluses",Space,Str "tight:"] +, BulletList + [ [ Para [Str "Plus",Space,Str "1"] ] + , [ Para [Str "Plus",Space,Str "2"] ] + , [ Para [Str "Plus",Space,Str "3"] ] ] +, Para [Str "Pluses",Space,Str "loose:"] +, BulletList + [ [ Para [Str "Plus",Space,Str "1"] ] + , [ Para [Str "Plus",Space,Str "2"] ] + , [ Para [Str "Plus",Space,Str "3"] ] ] +, Para [Str "Minuses",Space,Str "tight:"] +, BulletList + [ [ Para [Str "Minus",Space,Str "1"] ] + , [ Para [Str "Minus",Space,Str "2"] ] + , [ Para [Str "Minus",Space,Str "3"] ] ] +, Para [Str "Minuses",Space,Str "loose:"] +, BulletList + [ [ Para [Str "Minus",Space,Str "1"] ] + , [ Para [Str "Minus",Space,Str "2"] ] + , [ Para [Str "Minus",Space,Str "3"] ] ] +, Header 2 [Str "Ordered"] +, Para [Str "Tight:"] +, OrderedList (1,Decimal,Period) + [ [ Para [Str "First"] ] + , [ Para [Str "Second"] ] + , [ Para [Str "Third"] ] ] +, Para [Str "and:"] +, OrderedList (1,Decimal,Period) + [ [ Para [Str "One"] ] + , [ Para [Str "Two"] ] + , [ Para [Str "Three"] ] ] +, Para [Str "Loose",Space,Str "using",Space,Str "tabs:"] +, OrderedList (1,Decimal,Period) + [ [ Para [Str "First"] ] + , [ Para [Str "Second"] ] + , [ Para [Str "Third"] ] ] +, Para [Str "and",Space,Str "using",Space,Str "spaces:"] +, OrderedList (1,Decimal,Period) + [ [ Para [Str "One"] ] + , [ Para [Str "Two"] ] + , [ Para [Str "Three"] ] ] +, Para [Str "Multiple",Space,Str "paragraphs:"] +, OrderedList (1,Decimal,Period) + [ [ Para [Str "Item",Space,Str "1,",Space,Str "graf",Space,Str "one."] + , Para [Str "Item",Space,Str "1.",Space,Str "graf",Space,Str "two.",Space,Str "The",Space,Str "quick",Space,Str "brown",Space,Str "fox",Space,Str "jumped",Space,Str "over",Space,Str "the",Space,Str "lazy",Space,Str "dog",Apostrophe,Str "s",Space,Str "back."] ], [ Para [Str "Item",Space,Str "2."] ] + , [ Para [Str "Item",Space,Str "3."] ] ] +, Header 2 [Str "Nested"] +, BulletList + [ [ Para [Str "Tab"] + , BulletList + [ [ Para [Str "Tab"] + , BulletList + [ [ Para [Str "Tab"] ] + ] ] ] ] ] +, Para [Str "Here",Apostrophe,Str "s",Space,Str "another:"] +, OrderedList (1,Decimal,Period) + [ [ Para [Str "First"] ] + , [ Para [Str "Second:"] + , BulletList + [ [ Para [Str "Fee"] ] + , [ Para [Str "Fie"] ] + , [ Para [Str "Foe"] ] ] ], [ Para [Str "Third"] ] ] +, Para [Str "Same",Space,Str "thing",Space,Str "but",Space,Str "with",Space,Str "paragraphs:"] +, OrderedList (1,Decimal,Period) + [ [ Para [Str "First"] ] + , [ Para [Str "Second:"] + , BulletList + [ [ Para [Str "Fee"] ] + , [ Para [Str "Fie"] ] + , [ Para [Str "Foe"] ] ] ], [ Para [Str "Third"] ] ] +, Header 2 [Str "Tabs",Space,Str "and",Space,Str "spaces"] +, BulletList + [ [ Para [Str "this",Space,Str "is",Space,Str "a",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "tabs"] ] + , [ Para [Str "this",Space,Str "is",Space,Str "a",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "spaces"] + , BulletList + [ [ Para [Str "this",Space,Str "is",Space,Str "an",Space,Str "example",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "tabs"] ] + , [ Para [Str "this",Space,Str "is",Space,Str "an",Space,Str "example",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "spaces"] ] ] ] ] +, Header 2 [Str "Fancy",Space,Str "list",Space,Str "markers"] +, OrderedList (2,Decimal,TwoParens) + [ [ Para [Str "begins",Space,Str "with",Space,Str "2"] ] + , [ Para [Str "and",Space,Str "now",Space,Str "3"] + , Para [Str "with",Space,Str "a",Space,Str "continuation"] + , OrderedList (4,LowerRoman,Period) + [ [ Para [Str "sublist",Space,Str "with",Space,Str "roman",Space,Str "numerals,",Space,Str "starting",Space,Str "with",Space,Str "4"] ] + , [ Para [Str "more",Space,Str "items"] + , OrderedList (1,UpperAlpha,TwoParens) + [ [ Para [Str "a",Space,Str "subsublist"] ] + , [ Para [Str "a",Space,Str "subsublist"] ] ] ] ] ] ] +, Para [Str "Nesting:"] +, OrderedList (1,UpperAlpha,Period) + [ [ Para [Str "Upper",Space,Str "Alpha"] + , OrderedList (1,UpperRoman,Period) + [ [ Para [Str "Upper",Space,Str "Roman."] + , OrderedList (6,Decimal,TwoParens) + [ [ Para [Str "Decimal",Space,Str "start",Space,Str "with",Space,Str "6"] + , OrderedList (3,LowerAlpha,OneParen) + [ [ Para [Str "Lower",Space,Str "alpha",Space,Str "with",Space,Str "paren"] ] + ] ] ] ] ] ] ] +, Para [Str "Autonumbering:"] +, OrderedList (1,DefaultStyle,DefaultDelim) + [ [ Para [Str "Autonumber."] ] + , [ Para [Str "More."] + , OrderedList (1,DefaultStyle,DefaultDelim) + [ [ Para [Str "Nested."] ] + ] ] ] +, Para [Str "Should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "list",Space,Str "item:"] +, Para [Str "M.A.",Space,Str "2007"] +, Para [Str "B.",Space,Str "Williams"] +, HorizontalRule +, Header 1 [Str "Definition",Space,Str "Lists"] +, Para [Str "Tight",Space,Str "using",Space,Str "spaces:"] +, DefinitionList + [ ([Str "apple"], + [ Para [Str "red",Space,Str "fruit"] ] + ), + ([Str "orange"], + [ Para [Str "orange",Space,Str "fruit"] ] + ), + ([Str "banana"], + [ Para [Str "yellow",Space,Str "fruit"] ] + ) ] +, Para [Str "Tight",Space,Str "using",Space,Str "tabs:"] +, DefinitionList + [ ([Str "apple"], + [ Para [Str "red",Space,Str "fruit"] ] + ), + ([Str "orange"], + [ Para [Str "orange",Space,Str "fruit"] ] + ), + ([Str "banana"], + [ Para [Str "yellow",Space,Str "fruit"] ] + ) ] +, Para [Str "Loose:"] +, DefinitionList + [ ([Str "apple"], + [ Para [Str "red",Space,Str "fruit"] ] + ), + ([Str "orange"], + [ Para [Str "orange",Space,Str "fruit"] ] + ), + ([Str "banana"], + [ Para [Str "yellow",Space,Str "fruit"] ] + ) ] +, Para [Str "Multiple",Space,Str "blocks",Space,Str "with",Space,Str "italics:"] +, DefinitionList + [ ([Emph [Str "apple"]], + [ Para [Str "red",Space,Str "fruit"] + , Para [Str "contains",Space,Str "seeds,",Space,Str "crisp,",Space,Str "pleasant",Space,Str "to",Space,Str "taste"] ] ), + ([Emph [Str "orange"]], + [ Para [Str "orange",Space,Str "fruit"] + , CodeBlock "{ orange code block }" + , BlockQuote + [ Para [Str "orange",Space,Str "block",Space,Str "quote"] ] + ] ) ] +, Header 1 [Str "HTML",Space,Str "Blocks"] +, Para [Str "Simple",Space,Str "block",Space,Str "on",Space,Str "one",Space,Str "line:"] +, Para [Str "foo",Space,Str "And",Space,Str "nested",Space,Str "without",Space,Str "indentation:"] +, Para [Str "foo",Space,Str "bar",Space,Str "Interpreted",Space,Str "markdown",Space,Str "in",Space,Str "a",Space,Str "table:"] +, Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Space,Str "And",Space,Str "this",Space,Str "is",Space,Strong [Str "strong"],Space,Str "Here",Apostrophe,Str "s",Space,Str "a",Space,Str "simple",Space,Str "block:"] +, Para [Str "foo",Space,Str "This",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "code",Space,Str "block,",Space,Str "though:"] +, CodeBlock "
\n foo\n
" +, Para [Str "As",Space,Str "should",Space,Str "this:"] +, CodeBlock "
foo
" +, Para [Str "Now,",Space,Str "nested:"] +, Para [Str "foo",Space,Str "This",Space,Str "should",Space,Str "just",Space,Str "be",Space,Str "an",Space,Str "HTML",Space,Str "comment:"] +, Para [Str "Multiline:"] +, Para [Str "Code",Space,Str "block:"] +, CodeBlock "" +, Para [Str "Just",Space,Str "plain",Space,Str "comment,",Space,Str "with",Space,Str "trailing",Space,Str "spaces",Space,Str "on",Space,Str "the",Space,Str "line:"] +, Para [Str "Code:"] +, CodeBlock "
" +, Para [Str "Hr",Apostrophe,Str "s:"] +, HorizontalRule +, Header 1 [Str "Inline",Space,Str "Markup"] +, Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ",",Space,Str "and",Space,Str "so",Space,Emph [Str "is",Space,Str "this"],Str "."] +, Para [Str "This",Space,Str "is",Space,Strong [Str "strong"],Str ",",Space,Str "and",Space,Str "so",Space,Strong [Str "is",Space,Str "this"],Str "."] +, Para [Str "An",Space,Emph [Link [Str "emphasized",Space,Str "link"] ("/url","")],Str "."] +, Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]]] +, Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word."] +, Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]]] +, Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word."] +, Para [Str "This",Space,Str "is",Space,Str "code:",Space,Code ">",Str ",",Space,Code "$",Str ",",Space,Code "\\",Str ",",Space,Code "\\$",Str ",",Space,Code "",Str "."] +, Para [Strikeout [Str "This",Space,Str "is",Space,Emph [Str "strikeout"],Str "."]] +, Para [Str "Superscripts:",Space,Str "a",Superscript [Str "bc"],Str "d",Space,Str "a",Superscript [Emph [Str "hello"]],Space,Str "a",Superscript [Str "hello",Space,Str "there"],Str "."] +, Para [Str "Subscripts:",Space,Str "H",Subscript [Str "2"],Str "O,",Space,Str "H",Subscript [Str "23"],Str "O,",Space,Str "H",Subscript [Str "many",Space,Str "of",Space,Str "them"],Str "O."] +, Para [Str "These",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "superscripts",Space,Str "or",Space,Str "subscripts,",Space,Str "because",Space,Str "of",Space,Str "the",Space,Str "unescaped",Space,Str "spaces:",Space,Str "a",Str "^",Str "b",Space,Str "c",Str "^",Str "d,",Space,Str "a",Str "~",Str "b",Space,Str "c",Str "~",Str "d."] +, HorizontalRule +, Header 1 [Str "Smart",Space,Str "quotes,",Space,Str "ellipses,",Space,Str "dashes"] +, Para [Quoted DoubleQuote [Str "Hello,"],Space,Str "said",Space,Str "the",Space,Str "spider.",Space,Quoted DoubleQuote [Quoted SingleQuote [Str "Shelob"],Space,Str "is",Space,Str "my",Space,Str "name."]] +, Para [Quoted SingleQuote [Str "A"],Str ",",Space,Quoted SingleQuote [Str "B"],Str ",",Space,Str "and",Space,Quoted SingleQuote [Str "C"],Space,Str "are",Space,Str "letters."] +, Para [Quoted SingleQuote [Str "Oak,"],Space,Quoted SingleQuote [Str "elm,"],Space,Str "and",Space,Quoted SingleQuote [Str "beech"],Space,Str "are",Space,Str "names",Space,Str "of",Space,Str "trees.",Space,Str "So",Space,Str "is",Space,Quoted SingleQuote [Str "pine."]] +, Para [Quoted SingleQuote [Str "He",Space,Str "said,",Space,Quoted DoubleQuote [Str "I",Space,Str "want",Space,Str "to",Space,Str "go."]],Space,Str "Were",Space,Str "you",Space,Str "alive",Space,Str "in",Space,Str "the",Space,Str "70",Apostrophe,Str "s?"] +, Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "quoted",Space,Quoted SingleQuote [Code "code"],Space,Str "and",Space,Str "a",Space,Quoted DoubleQuote [Link [Str "quoted",Space,Str "link"] ("http://example.com/?foo=1&bar=2","")],Str "."] +, Para [Str "Some",Space,Str "dashes:",Space,Str "one",EmDash,Str "two",EmDash,Str "three",EmDash,Str "four",EmDash,Str "five."] +, Para [Str "Dashes",Space,Str "between",Space,Str "numbers:",Space,Str "5",EnDash,Str "7,",Space,Str "255",EnDash,Str "66,",Space,Str "1987",EnDash,Str "1999."] +, Para [Str "Ellipses",Ellipses,Str "and",Ellipses,Str "and",Ellipses,Str "."] +, HorizontalRule +, Header 1 [Str "LaTeX"] +, BulletList + [ [ Para [TeX "\\cite[22-23]{smith.1899}"] ] + , [ Para [TeX "\\doublespacing"] ] + , [ Para [TeX "$2+2=4$"] ] + , [ Para [TeX "$x \\in y$"] ] + , [ Para [TeX "$\\alpha \\wedge \\omega$"] ] + , [ Para [TeX "$223$"] ] + , [ Para [TeX "$p$",Str "-",Str "Tree"] ] + , [ Para [TeX "$\\frac{d}{dx}f(x)=\\lim_{h\\to 0}\\frac{f(x+h)-f(x)}{h}$"] ] + , [ Para [Str "Here",Apostrophe,Str "s",Space,Str "one",Space,Str "that",Space,Str "has",Space,Str "a",Space,Str "line",Space,Str "break",Space,Str "in",Space,Str "it:",Space,TeX "$\\alpha + \\omega \\times x^2$",Str "."] ] ] +, Para [Str "These",Space,Str "shouldn",Apostrophe,Str "t",Space,Str "be",Space,Str "math:"] +, BulletList + [ [ Para [Str "To",Space,Str "get",Space,Str "the",Space,Str "famous",Space,Str "equation,",Space,Str "write",Space,Code "$e = mc^2$",Str "."] ] + , [ Para [Str "$",Str "22,000",Space,Str "is",Space,Str "a",Space,Emph [Str "lot"],Space,Str "of",Space,Str "money.",Space,Str "So",Space,Str "is",Space,Str "$",Str "34,000.",Space,Str "(It",Space,Str "worked",Space,Str "if",Space,Quoted DoubleQuote [Str "lot"],Space,Str "is",Space,Str "emphasized.)"] ] + , [ Para [Str "Escaped",Space,Code "$",Str ":",Space,Str "$",Str "73",Space,Emph [Str "this",Space,Str "should",Space,Str "be",Space,Str "emphasized"],Space,Str "23",Str "$",Str "."] ] ] +, Para [Str "Here",Apostrophe,Str "s",Space,Str "a",Space,Str "LaTeX",Space,Str "table:"] +, Para [TeX "\\begin{tabular}{|l|l|}\\hline\nAnimal & Number \\\\ \\hline\nDog & 2 \\\\\nCat & 1 \\\\ \\hline\n\\end{tabular}"] +, HorizontalRule +, Header 1 [Str "Special",Space,Str "Characters"] +, Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "unicode:"] +, BulletList + [ [ Para [Str "I",Space,Str "hat:",Space,Str "\206"] ] + , [ Para [Str "o",Space,Str "umlaut:",Space,Str "\246"] ] + , [ Para [Str "section:",Space,Str "\167"] ] + , [ Para [Str "set",Space,Str "membership:",Space,Str "\8712"] ] + , [ Para [Str "copyright:",Space,Str "\169"] ] ] +, Para [Str "AT",Str "&",Str "T",Space,Str "has",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "their",Space,Str "name."] +, Para [Str "AT",Str "&",Str "T",Space,Str "is",Space,Str "another",Space,Str "way",Space,Str "to",Space,Str "write",Space,Str "it."] +, Para [Str "This",Space,Str "&",Space,Str "that."] +, Para [Str "4",Space,Str "<",Space,Str "5."] +, Para [Str "6",Space,Str ">",Space,Str "5."] +, Para [Str "Backslash:",Space,Str "\\"] +, Para [Str "Backtick:"] +, Para [Str "Asterisk:",Space,Str "*"] +, Para [Str "Underscore:",Space,Str "_"] +, Para [Str "Left",Space,Str "brace:",Space,Str "{"] +, Para [Str "Right",Space,Str "brace:",Space,Str "}"] +, Para [Str "Left",Space,Str "bracket:",Space,Str "["] +, Para [Str "Right",Space,Str "bracket:",Space,Str "]"] +, Para [Str "Left",Space,Str "paren:",Space,Str "("] +, Para [Str "Right",Space,Str "paren:",Space,Str ")"] +, Para [Str "Greater",Str "-",Str "than:",Space,Str ">"] +, Para [Str "Hash:",Space,Str "#"] +, Para [Str "Period:",Space,Str "."] +, Para [Str "Bang:",Space,Str "!"] +, Para [Str "Plus:",Space,Str "+"] +, Para [Str "Minus:",Space,Str "-"] +, HorizontalRule +, Header 1 [Str "Links"] +, Header 2 [Str "Explicit"] +, Para [Str "Just",Space,Str "a",Space,Link [Str "URL"] ("/url/",""),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] ("/url/",""),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] ("/url/",""),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] ("/url/",""),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] ("/url/","")] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] ("/url/","")] +, Para [Link [Str "with",Str "_",Str "underscore"] ("/url/with_underscore","")] +, Para [Link [Str "Email",Space,Str "link"] ("mailto:nobody@nowhere.net","")] +, Para [Link [Str "Empty"] ("",""),Str "."] +, Header 2 [Str "Reference"] +, Para [Str "Foo",Space,Link [Str "bar"] ("/url/",""),Str "."] +, Para [Str "Foo",Space,Link [Str "bar"] ("/url/",""),Str "."] +, Para [Str "Foo",Space,Link [Str "bar"] ("/url/",""),Str "."] +, Para [Str "With",Space,Link [Str "embedded",Space,Str "[brackets]"] ("/url/",""),Str "."] +, Para [Link [Str "b"] ("/url/",""),Space,Str "by",Space,Str "itself",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "link."] +, Para [Str "Indented",Space,Link [Str "once"] ("/url",""),Str "."] +, Para [Str "Indented",Space,Link [Str "twice"] ("/url",""),Str "."] +, Para [Str "Indented",Space,Link [Str "thrice"] ("/url",""),Str "."] +, Para [Str "This",Space,Str "should",Space,Str "[not][]",Space,Str "be",Space,Str "a",Space,Str "link."] +, CodeBlock "[not]: /url" +, Para [Str "Foo",Space,Link [Str "bar"] ("/url/",""),Str "."] +, Para [Str "Foo",Space,Link [Str "biz"] ("/url/",""),Str "."] +, Header 2 [Str "With",Space,Str "ampersands"] +, Para [Str "Here",Apostrophe,Str "s",Space,Str "a",Space,Link [Str "link",Space,Str "with",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "the",Space,Str "URL"] ("http://example.com/?foo=1&bar=2",""),Str "."] +, Para [Str "Here",Apostrophe,Str "s",Space,Str "a",Space,Str "link",Space,Str "with",Space,Str "an",Space,Str "amersand",Space,Str "in",Space,Str "the",Space,Str "link",Space,Str "text:",Space,Link [Str "AT",Str "&",Str "T"] ("http://att.com/",""),Str "."] +, Para [Str "Here",Apostrophe,Str "s",Space,Str "an",Space,Link [Str "inline",Space,Str "link"] ("/script?foo=1&bar=2",""),Str "."] +, Para [Str "Here",Apostrophe,Str "s",Space,Str "an",Space,Link [Str "inline",Space,Str "link",Space,Str "in",Space,Str "pointy",Space,Str "braces"] ("/script?foo=1&bar=2",""),Str "."] +, Header 2 [Str "Autolinks"] +, Para [Str "With",Space,Str "an",Space,Str "ampersand:",Space,Link [Code "http://example.com/?foo=1&bar=2"] ("http://example.com/?foo=1&bar=2","")] +, BulletList + [ [ Para [Str "In",Space,Str "a",Space,Str "list?"] ] + , [ Para [Link [Code "http://example.com/"] ("http://example.com/","")] ] + , [ Para [Str "It",Space,Str "should."] ] ] +, Para [Str "An",Space,Str "e",Str "-",Str "mail",Space,Str "address:",Space,Link [Code "nobody@nowhere.net"] ("mailto:nobody@nowhere.net","")] +, BlockQuote + [ Para [Str "Blockquoted:",Space,Link [Code "http://example.com/"] ("http://example.com/","")] ] + +, Para [Str "Auto",Str "-",Str "links",Space,Str "should",Space,Str "not",Space,Str "occur",Space,Str "here:",Space,Code ""] +, CodeBlock "or here: " +, HorizontalRule +, Header 1 [Str "Images"] +, Para [Str "From",Space,Quoted DoubleQuote [Str "Voyage",Space,Str "dans",Space,Str "la",Space,Str "Lune"],Space,Str "by",Space,Str "Georges",Space,Str "Melies",Space,Str "(1902):"] +, Para [Image [Str "image"] ("lalune.jpg","")] +, Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "movie",Space,Image [Str "image"] ("movie.jpg",""),Space,Str "icon."] +, HorizontalRule +, Header 1 [Str "Footnotes"] +, Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "footnote",Space,Str "reference,",Note [Para [Str "Here",Space,Str "is",Space,Str "the",Space,Str "footnote.",Space,Str "It",Space,Str "can",Space,Str "go",Space,Str "anywhere",Space,Str "after",Space,Str "the",Space,Str "footnote",Space,Str "reference.",Space,Str "It",Space,Str "need",Space,Str "not",Space,Str "be",Space,Str "placed",Space,Str "at",Space,Str "the",Space,Str "end",Space,Str "of",Space,Str "the",Space,Str "document."]],Space,Str "and",Space,Str "another.",Note [Para [Str "Here",Apostrophe,Str "s",Space,Str "the",Space,Str "long",Space,Str "note.",Space,Str "This",Space,Str "one",Space,Str "contains",Space,Str "multiple",Space,Str "blocks."],Para [Str "Subsequent",Space,Str "blocks",Space,Str "are",Space,Str "indented",Space,Str "to",Space,Str "show",Space,Str "that",Space,Str "they",Space,Str "belong",Space,Str "to",Space,Str "the",Space,Str "footnote",Space,Str "(as",Space,Str "with",Space,Str "list",Space,Str "items)."],CodeBlock " { }",Para [Str "If",Space,Str "you",Space,Str "want,",Space,Str "you",Space,Str "can",Space,Str "indent",Space,Str "every",Space,Str "line,",Space,Str "but",Space,Str "you",Space,Str "can",Space,Str "also",Space,Str "be",Space,Str "lazy",Space,Str "and",Space,Str "just",Space,Str "indent",Space,Str "the",Space,Str "first",Space,Str "line",Space,Str "of",Space,Str "each",Space,Str "block."]],Space,Str "This",Space,Str "should",Space,Emph [Str "not"],Space,Str "be",Space,Str "a",Space,Str "footnote",Space,Str "reference,",Space,Str "because",Space,Str "it",Space,Str "contains",Space,Str "a",Space,Str "space.[",Str "^",Str "my",Space,Str "note]",Space,Str "Here",Space,Str "is",Space,Str "an",Space,Str "inline",Space,Str "note.",Note [Para [Str "This",Space,Str "is",Space,Emph [Str "easier"],Space,Str "to",Space,Str "type.",Space,Str "Inline",Space,Str "notes",Space,Str "may",Space,Str "contain",Space,Link [Str "links"] ("http://google.com",""),Space,Str "and",Space,Code "]",Space,Str "verbatim",Space,Str "characters,",Space,Str "as",Space,Str "well",Space,Str "as",Space,Str "[bracketed",Space,Str "text]."]]] +, BlockQuote + [ Para [Str "Notes",Space,Str "can",Space,Str "go",Space,Str "in",Space,Str "quotes.",Note [Para [Str "In",Space,Str "quote."]]] ] + +, OrderedList (1,Decimal,Period) + [ [ Para [Str "And",Space,Str "in",Space,Str "list",Space,Str "items.",Note [Para [Str "In",Space,Str "list."]]] ] + ] +, Para [Str "This",Space,Str "paragraph",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "part",Space,Str "of",Space,Str "the",Space,Str "note,",Space,Str "as",Space,Str "it",Space,Str "is",Space,Str "not",Space,Str "indented."] ] + diff --git a/tests/runtests.pl b/tests/runtests.pl --- a/tests/runtests.pl +++ b/tests/runtests.pl @@ -15,7 +15,6 @@ print "Writer tests:\n"; my @writeformats = ("html", "latex", "rst", "rtf", "markdown", "man", "native"); # docbook, context, and s5 handled separately -my @readformats = ("latex", "native"); # handle html,markdown & rst separately my $source = "testsuite.native"; sub test_results @@ -99,16 +98,13 @@ `$script -r html -w native -s html-reader.html > tmp.native`; test_results("html reader", "tmp.native", "html-reader.native"); -print "\nReader tests (roundtrip: X -> native -> X -> native):\n"; +print "Testing latex reader..."; +`$script -r latex -w native -s latex-reader.latex > tmp.native`; +test_results("latex reader", "tmp.native", "latex-reader.native"); -foreach my $format (@readformats) -{ - print "Testing $format reader..."; - `$script -r $format -w native -s -R writer.$format > tmp1.native`; - `$script -r native -w $format -s -R tmp1.native | $script -r $format -w native -s -R - > tmp2.native`; - test_results("$format reader", "tmp1.native", "tmp2.native"); -} +print "Testing native reader..."; +`$script -r native -w native -s testsuite.native > tmp.native`; +test_results("native reader", "tmp.native", "testsuite.native"); -`rm tmp?.*`; `rm tmp.*`; diff --git a/tests/tables.latex b/tests/tables.latex --- a/tests/tables.latex +++ b/tests/tables.latex @@ -137,4 +137,3 @@ \end{tabular} \end{center} - diff --git a/tests/writer.latex b/tests/writer.latex --- a/tests/writer.latex +++ b/tests/writer.latex @@ -3,12 +3,15 @@ \usepackage[utf8x]{inputenc} \setlength{\parindent}{0pt} \setlength{\parskip}{6pt plus 2pt minus 1pt} + \newcommand{\textsubscript}[1]{\ensuremath{_{\scriptsize\textrm{#1}}}} \usepackage[breaklinks=true]{hyperref} \usepackage[normalem]{ulem} \usepackage{enumerate} \usepackage{fancyvrb} \usepackage{graphicx} +\usepackage{url} + \setcounter{secnumdepth}{0} \VerbatimFootnotes % allows verbatim text in footnotes \title{Pandoc Test Suite} @@ -17,7 +20,8 @@ \begin{document} \maketitle -This is a set of tests for pandoc. Most of them are adapted from John Gruber's markdown test suite. +This is a set of tests for pandoc. Most of them are adapted from +John Gruber's markdown test suite. \begin{center}\rule{3in}{0.4pt}\end{center} @@ -49,12 +53,13 @@ Here's a regular paragraph. -In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item. +In Markdown 1.0.0 and earlier. Version 8. This line turns into a +list item. Because a hard-wrapped line in the middle of a paragraph +looked like a list item. Here's one with a bullet. * criminey. -There should be a hard line break\\ -here. +There should be a hard line break\\here. \begin{center}\rule{3in}{0.4pt}\end{center} @@ -77,8 +82,10 @@ A list: \begin{enumerate}[1.] -\item item one -\item item two +\item + item one +\item + item two \end{enumerate} Nested block quotes: @@ -106,8 +113,10 @@ \end{quote} \begin{quote} \begin{enumerate}[1.] -\item do laundry -\item take out the trash +\item + do laundry +\item + take out the trash \end{enumerate} \end{quote} Here's a nested one: @@ -153,52 +162,70 @@ Asterisks tight: \begin{itemize} -\item asterisk 1 -\item asterisk 2 -\item asterisk 3 +\item + asterisk 1 +\item + asterisk 2 +\item + asterisk 3 \end{itemize} Asterisks loose: \begin{itemize} -\item asterisk 1 +\item + asterisk 1 -\item asterisk 2 +\item + asterisk 2 -\item asterisk 3 +\item + asterisk 3 \end{itemize} Pluses tight: \begin{itemize} -\item Plus 1 -\item Plus 2 -\item Plus 3 +\item + Plus 1 +\item + Plus 2 +\item + Plus 3 \end{itemize} Pluses loose: \begin{itemize} -\item Plus 1 +\item + Plus 1 -\item Plus 2 +\item + Plus 2 -\item Plus 3 +\item + Plus 3 \end{itemize} Minuses tight: \begin{itemize} -\item Minus 1 -\item Minus 2 -\item Minus 3 +\item + Minus 1 +\item + Minus 2 +\item + Minus 3 \end{itemize} Minuses loose: \begin{itemize} -\item Minus 1 +\item + Minus 1 -\item Minus 2 +\item + Minus 2 -\item Minus 3 +\item + Minus 3 \end{itemize} \subsection{Ordered} @@ -206,144 +233,192 @@ Tight: \begin{enumerate}[1.] -\item First -\item Second -\item Third +\item + First +\item + Second +\item + Third \end{enumerate} and: \begin{enumerate}[1.] -\item One -\item Two -\item Three +\item + One +\item + Two +\item + Three \end{enumerate} Loose using tabs: \begin{enumerate}[1.] -\item First +\item + First -\item Second +\item + Second -\item Third +\item + Third \end{enumerate} and using spaces: \begin{enumerate}[1.] -\item One +\item + One -\item Two +\item + Two -\item Three +\item + Three \end{enumerate} Multiple paragraphs: \begin{enumerate}[1.] -\item Item 1, graf one. +\item + Item 1, graf one. -Item 1. graf two. The quick brown fox jumped over the lazy dog's back. + Item 1. graf two. The quick brown fox jumped over the lazy dog's + back. -\item Item 2. +\item + Item 2. -\item Item 3. +\item + Item 3. \end{enumerate} \subsection{Nested} \begin{itemize} -\item Tab -\begin{itemize} -\item Tab -\begin{itemize} -\item Tab -\end{itemize} -\end{itemize} +\item + Tab + \begin{itemize} + \item + Tab + \begin{itemize} + \item + Tab + \end{itemize} + \end{itemize} \end{itemize} Here's another: \begin{enumerate}[1.] -\item First -\item Second: -\begin{itemize} -\item Fee -\item Fie -\item Foe -\end{itemize} -\item Third +\item + First +\item + Second: + \begin{itemize} + \item + Fee + \item + Fie + \item + Foe + \end{itemize} +\item + Third \end{enumerate} Same thing but with paragraphs: \begin{enumerate}[1.] -\item First +\item + First -\item Second: +\item + Second: -\begin{itemize} -\item Fee -\item Fie -\item Foe -\end{itemize} -\item Third + \begin{itemize} + \item + Fee + \item + Fie + \item + Foe + \end{itemize} +\item + Third \end{enumerate} \subsection{Tabs and spaces} \begin{itemize} -\item this is a list item indented with tabs +\item + this is a list item indented with tabs -\item this is a list item indented with spaces +\item + this is a list item indented with spaces -\begin{itemize} -\item this is an example list item indented with tabs + \begin{itemize} + \item + this is an example list item indented with tabs -\item this is an example list item indented with spaces + \item + this is an example list item indented with spaces -\end{itemize} + \end{itemize} \end{itemize} \subsection{Fancy list markers} \begin{enumerate}[(1)] \setcounter{enumi}{1} -\item begins with 2 -\item and now 3 +\item + begins with 2 +\item + and now 3 -with a continuation + with a continuation -\begin{enumerate}[i.] -\setcounter{enumii}{3} -\item sublist with roman numerals, starting with 4 -\item more items -\begin{enumerate}[(A)] -\item a subsublist -\item a subsublist -\end{enumerate} -\end{enumerate} + \begin{enumerate}[i.] + \setcounter{enumii}{3} + \item + sublist with roman numerals, starting with 4 + \item + more items + \begin{enumerate}[(A)] + \item + a subsublist + \item + a subsublist + \end{enumerate} + \end{enumerate} \end{enumerate} Nesting: \begin{enumerate}[A.] -\item Upper Alpha -\begin{enumerate}[I.] -\item Upper Roman. -\begin{enumerate}[(1)] -\setcounter{enumiii}{5} -\item Decimal start with 6 -\begin{enumerate}[a)] -\setcounter{enumiv}{2} -\item Lower alpha with paren -\end{enumerate} -\end{enumerate} -\end{enumerate} +\item + Upper Alpha + \begin{enumerate}[I.] + \item + Upper Roman. + \begin{enumerate}[(1)] + \setcounter{enumiii}{5} + \item + Decimal start with 6 + \begin{enumerate}[a)] + \setcounter{enumiv}{2} + \item + Lower alpha with paren + \end{enumerate} + \end{enumerate} + \end{enumerate} \end{enumerate} Autonumbering: \begin{enumerate} -\item Autonumber. -\item More. -\begin{enumerate} -\item Nested. -\end{enumerate} +\item + Autonumber. +\item + More. + \begin{enumerate} + \item + Nested. + \end{enumerate} \end{enumerate} Should not be a list item: @@ -358,35 +433,46 @@ Tight using spaces: \begin{description} -\item[apple] red fruit -\item[orange] orange fruit -\item[banana] yellow fruit +\item[apple] +red fruit +\item[orange] +orange fruit +\item[banana] +yellow fruit \end{description} Tight using tabs: \begin{description} -\item[apple] red fruit -\item[orange] orange fruit -\item[banana] yellow fruit +\item[apple] +red fruit +\item[orange] +orange fruit +\item[banana] +yellow fruit \end{description} Loose: \begin{description} -\item[apple] red fruit +\item[apple] +red fruit -\item[orange] orange fruit +\item[orange] +orange fruit -\item[banana] yellow fruit +\item[banana] +yellow fruit \end{description} Multiple blocks with italics: \begin{description} -\item[\emph{apple}] red fruit +\item[\emph{apple}] +red fruit contains seeds, crisp, pleasant to taste -\item[\emph{orange}] orange fruit +\item[\emph{orange}] +orange fruit \begin{verbatim} { orange code block } @@ -463,15 +549,20 @@ So is \textbf{\emph{this}} word. -This is code: \verb!>!, \verb!$!, \verb!\!, \verb!\$!, \verb!!. +This is code: \verb!>!, \verb!$!, \verb!\!, \verb!\$!, +\verb!!. \sout{This is \emph{strikeout}.} -Superscripts: a\textsuperscript{bc}d a\textsuperscript{\emph{hello}} a\textsuperscript{hello there}. +Superscripts: a\textsuperscript{bc}d +a\textsuperscript{\emph{hello}} a\textsuperscript{hello there}. -Subscripts: H\textsubscript{2}O, H\textsubscript{23}O, H\textsubscript{many of them}O. +Subscripts: H\textsubscript{2}O, H\textsubscript{23}O, +H\textsubscript{many of them}O. -These should not be superscripts or subscripts, because of the unescaped spaces: a\^{}b c\^{}d, a\ensuremath{\sim}b c\ensuremath{\sim}d. +These should not be superscripts or subscripts, because of the +unescaped spaces: a\^{}b c\^{}d, a\ensuremath{\sim}b +c\ensuremath{\sim}d. \begin{center}\rule{3in}{0.4pt}\end{center} @@ -485,7 +576,8 @@ `He said, ``I want to go.''\,' Were you alive in the 70's? -Here is some quoted `\verb!code!' and a ``\href{http://example.com/?foo=1&bar=2}{quoted link}''. +Here is some quoted `\verb!code!' and a +``\href{http://example.com/?foo=1&bar=2}{quoted link}''. Some dashes: one---two---three---four---five. @@ -498,22 +590,36 @@ \section{LaTeX} \begin{itemize} -\item \cite[22-23]{smith.1899} -\item \doublespacing -\item $2+2=4$ -\item $x \in y$ -\item $\alpha \wedge \omega$ -\item $223$ -\item $p$-Tree -\item $\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$ -\item Here's one that has a line break in it: $\alpha + \omega \times x^2$. +\item + \cite[22-23]{smith.1899} +\item + \doublespacing +\item + $2+2=4$ +\item + $x \in y$ +\item + $\alpha \wedge \omega$ +\item + $223$ +\item + $p$-Tree +\item + $\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$ +\item + Here's one that has a line break in it: + $\alpha + \omega \times x^2$. \end{itemize} These shouldn't be math: \begin{itemize} -\item To get the famous equation, write \verb!$e = mc^2$!. -\item \$22,000 is a \emph{lot} of money. So is \$34,000. (It worked if ``lot'' is emphasized.) -\item Escaped \verb!$!: \$73 \emph{this should be emphasized} 23\$. +\item + To get the famous equation, write \verb!$e = mc^2$!. +\item + \$22,000 is a \emph{lot} of money. So is \$34,000. (It worked if + ``lot'' is emphasized.) +\item + Escaped \verb!$!: \$73 \emph{this should be emphasized} 23\$. \end{itemize} Here's a LaTeX table: @@ -530,11 +636,16 @@ Here is some unicode: \begin{itemize} -\item I hat: Î -\item o umlaut: ö -\item section: § -\item set membership: ∈ -\item copyright: © +\item + I hat: Î +\item + o umlaut: ö +\item + section: § +\item + set membership: ∈ +\item + copyright: © \end{itemize} AT\&T has an ampersand in their name. @@ -631,24 +742,31 @@ \subsection{With ampersands} -Here's a \href{http://example.com/?foo=1&bar=2}{link with an ampersand in the URL}. +Here's a +\href{http://example.com/?foo=1&bar=2}{link with an ampersand in the URL}. -Here's a link with an amersand in the link text: \href{http://att.com/}{AT\&T}. +Here's a link with an amersand in the link text: +\href{http://att.com/}{AT\&T}. Here's an \href{/script?foo=1&bar=2}{inline link}. -Here's an \href{/script?foo=1&bar=2}{inline link in pointy braces}. +Here's an +\href{/script?foo=1&bar=2}{inline link in pointy braces}. \subsection{Autolinks} With an ampersand: \url{http://example.com/?foo=1&bar=2} \begin{itemize} -\item In a list? -\item \url{http://example.com/} -\item It should. +\item + In a list? +\item + \url{http://example.com/} +\item + It should. \end{itemize} -An e-mail address: \href{mailto:nobody@nowhere.net}{\texttt{nobody@nowhere.net}} +An e-mail address: +\href{mailto:nobody@nowhere.net}{\texttt{nobody@nowhere.net}} \begin{quote} Blockquoted: \url{http://example.com/} @@ -673,29 +791,40 @@ \section{Footnotes} -Here is a footnote reference,\footnote{Here is the footnote. It can go anywhere after the footnote reference. It need not be placed at the end of the document. -} and another.\footnote{Here's the long note. This one contains multiple blocks. +Here is a footnote +reference,\footnote{ Here is the footnote. It can go anywhere after the footnote +reference. It need not be placed at the end of the document. +} +and +another.\footnote{ Here's the long note. This one contains multiple blocks. -Subsequent blocks are indented to show that they belong to the footnote (as with list items). +Subsequent blocks are indented to show that they belong to the +footnote (as with list items). \begin{Verbatim} { } \end{Verbatim} -If you want, you can indent every line, but you can also be lazy and just indent the first line of each block. -} This should \emph{not} be a footnote reference, because it contains a space.[\^{}my note] Here is an inline note.\footnote{This is \emph{easier} to type. Inline notes may contain \href{http://google.com}{links} and \verb!]! verbatim characters, as well as [bracketed text]. +If you want, you can indent every line, but you can also be lazy +and just indent the first line of each block. } +This should \emph{not} be a footnote reference, because it contains +a space.[\^{}my note] Here is an inline +note.\footnote{ This is \emph{easier} to type. Inline notes may contain +\href{http://google.com}{links} and \verb!]! verbatim characters, +as well as [bracketed text]. +} \begin{quote} -Notes can go in quotes.\footnote{In quote. +Notes can go in quotes.\footnote{ In quote. } \end{quote} \begin{enumerate}[1.] -\item And in list items.\footnote{In list. +\item + And in list items.\footnote{ In list. } \end{enumerate} -This paragraph should not be part of the note, as it is not indented. - +This paragraph should not be part of the note, as it is not +indented. \end{document} - diff --git a/web/Makefile b/web/Makefile --- a/web/Makefile +++ b/web/Makefile @@ -1,7 +1,7 @@ ALL := index.html README.html INSTALL.html examples.html pandoc1.html markdown2pdf1.html html2markdown1.html hsmarkdown1.html PANDOC_PATH ?= $(dir $(shell which pandoc)) MAKEPAGE = $(PANDOC_PATH)/pandoc -s -S -c pandoc.css -A footer.html -all : $(ALL) +all : $(ALL) .PHONY: clean clean: @@ -12,7 +12,7 @@ PATH=$(PANDOC_PATH):$$PATH ./mkdemos.pl demos $@ perl -pi -e 's!(href="(main|(my)?header|footer|example\d+)\.(html|tex|xml|css))"!\1.html"!g' $@ for file in $$(ls | egrep '(main|(my)?header|footer|example[0-9]+)\.(html|tex|xml|css)$$'); \ - do highlight -u utf-8 --style emacs $$file > $$file.html; \ + do highlight -k monospace -u utf-8 --style emacs $$file > $$file.html; \ done index.html : index.txt diff --git a/web/demos b/web/demos --- a/web/demos +++ b/web/demos @@ -70,5 +70,5 @@ [xmlto]: http://cyberelk.net/tim/xmlto/ 15. A simple wiki program using [HAppS](http://happs.org) and pandoc: - [pandocwiki](pandocwiki-0.1.tar.gz). + [pandocwiki](http://pandocwiki.googlecode.com/svn/trunk/) diff --git a/web/highlight.css b/web/highlight.css deleted file mode 100644 --- a/web/highlight.css +++ /dev/null @@ -1,20 +0,0 @@ -/* Style definition file generated by highlight 2.4.8, http://www.andre-simon.de/ */ - -/* Highlighting theme definition: */ - -body.hl { background-color:#ffffff; } -pre.hl { color:#000000; background-color:#ffffff; font-size:10pt; font-family: monospace;} -.num { color:#000000; } -.esc { color:#bd8d8b; } -.str { color:#bd8d8b; } -.dstr { color:#bd8d8b; } -.slc { color:#ac2020; font-style:italic; } -.com { color:#ac2020; font-style:italic; } -.dir { color:#000000; } -.sym { color:#000000; } -.line { color:#555555; } -.kwa { color:#9c20ee; font-weight:bold; } -.kwb { color:#208920; } -.kwc { color:#0000ff; } -.kwd { color:#000000; } - diff --git a/web/index.txt.in b/web/index.txt.in --- a/web/index.txt.in +++ b/web/index.txt.in @@ -13,7 +13,7 @@ - Modular design, using separate writers and readers for each supported format. - A real markdown parser, not based on regex substitutions. - [More accurate] and [faster], in many cases, than `Markdown.pl`. + [More accurate] and [much faster] than `Markdown.pl`. - Also parses (subsets of) reStructuredText, LaTeX, and HTML. - Multiple output formats: HTML, Docbook XML, LaTeX, ConTeXt, reStructuredText, Markdown, RTF, groff man pages, S5 slide shows. @@ -51,19 +51,17 @@ - [`html2markdown(1)`](html2markdown1.html) - [`hsmarkdown(1)`](hsmarkdown1.html) - [Library documentation](doc/index.html) (for Haskell programmers) -- [Instructions for installing from source](INSTALL.html) +- [Installation instructions](INSTALL.html) - [Changelog](changelog) # Downloads For installation instructions for all architectures, see -[INSTALL](INSTALL.html). +[INSTALL](INSTALL.html). Note that pandoc is in the [MacPorts], +[Debian unstable], and [FreeBSD ports] repositories. - [Source tarball] - [Windows binary package] -- [MacPorts Portfile] -- [FreeBSD port] -- [Debian linux package] (thanks to Recai Oktaş) # Code repository @@ -85,17 +83,35 @@ # News -- Version 0.42 released (August 26, 2006). +- Version 0.43 released (September 2, 2007). + + HUGE increase in performance: markdown is parsed five times + faster than with 0.42 on large benchmark files. + + Prettyprinting library used in LaTeX writer, so that LaTeX output + is wrapped and intelligently indented. + + Fixed bugs in LaTeX ordered lists and LaTeX command and environment + parsers. + + Blank lines are no longer required after code blocks. + + Fixed inline code parsing so that it uses the method of Markdown.pl: + the delimiters are blocks of N `` ` `` characters not followed by another + `` ` `` character. For example: + ```` ` h ``` i ` ```` -> `h ``` i`. + + Markdown writer escapes paragraphs that begin like list items. + + MacPorts Portfile now installs library as well as executable. + + Added pandocwiki demonstration to the website. + +- Version 0.42 released (August 26, 2007). + + Fixes bugs in ordered list handling, LaTeX footnotes, UTF8 in include files, and HTML tables. See [changelog] for details. + Added new rule for enhanced ordered lists: capital letters followed by periods must be separated from the list item by two spaces, to avoid misinterpretation of initials. See - [README](README#lists) for details. + [README](README.html#lists) for details. + Improved strict markdown compatibility. + OSX packages are no longer supported. There were too many issues with dynamic libraries. Instead, a MacPorts Portfile is now provided. + + Exposed Text.Pandoc.ASCIIMathML. - Version 0.41 released (August 19, 2007). @@ -137,7 +153,7 @@ kind. [More accurate]: http://code.google.com/p/pandoc/wiki/PandocVsMarkdownPl -[faster]: http://code.google.com/p/pandoc/wiki/Benchmarks +[much faster]: http://code.google.com/p/pandoc/wiki/Benchmarks [ASCIIMathML]: http://www1.chapman.edu/~jipsen/mathml/asciimath.html [John MacFarlane]: http://sophos.berkeley.edu/macfarlane/ @@ -156,9 +172,9 @@ [Source tarball]: http://code.google.com/p/pandoc/downloads/detail?name=pandoc-@VERSION@.tar.gz "Download source tarball from Pandoc's Google Code site" [MacOS X binary package]: http://code.google.com/p/pandoc/downloads/detail?name=pandoc-@VERSION@.dmg "Download Mac OS X disk image from Pandoc's Google Code site" [Windows binary package]: http://code.google.com/p/pandoc/downloads/detail?name=pandoc-@VERSION@.zip "Download Windows zip file from Pandoc's Google Code site" -[MacPorts Portfile]: Portfile -[Debian linux package]: pandoc_@VERSION@_i386.deb -[FreeBSD port]: http://www.freshports.org/textproc/pandoc/ +[Debian unstable]: http://packages.debian.org/unstable/text/pandoc +[FreeBSD ports]: http://www.freshports.org/textproc/pandoc/ +[MacPorts]: http://www.macports.org/ [pandoc-announce]: http://groups.google.com/group/pandoc-announce [pandoc-discuss]: http://groups.google.com/group/pandoc-discuss [changelog]: changelog diff --git a/web/pandocwiki-0.1.tar.gz b/web/pandocwiki-0.1.tar.gz deleted file mode 100644 Binary files a/web/pandocwiki-0.1.tar.gz and /dev/null differ