a1a30d6 · typeable/pandoc

git.iko.soy/typeable/pandoc

on master help sign in

+ Removed the convenience symlinks (which don't work on Windows under

a1a30d6fiddlosopher20 years ago

Makefile+3−16

compare with master

unifiedsplit

@@ -26,8 +26,6 @@ EXECSBASE := $(shell sed -ne 's/^[Ee]xecutable:[[:space:]]*//p' $(CABAL).in)

26# Install targets

27#-------------------------------------------------------------------------------

28WRAPPERS := web2markdown markdown2pdf

29−SYMLINKS := markdown2html markdown2latex markdown2s5 markdown2rst \

30− markdown2rtf html2markdown latex2markdown rst2markdown

31# Add .exe extensions if we're running Windows/Cygwin.

29# Add .exe extensions if we're running Windows/Cygwin.

32EXTENSION := $(shell uname | tr '[:upper:]' '[:lower:]' | \

30EXTENSION := $(shell uname | tr '[:upper:]' '[:lower:]' | \

33 sed -ne 's/^cygwin.*$$/\.exe/p')

31 sed -ne 's/^cygwin.*$$/\.exe/p')

@@ -96,12 +94,6 @@ all: build-program

96templates: $(SRCDIR)/templates

94templates: $(SRCDIR)/templates

97 $(MAKE) -C $(SRCDIR)/templates

95 $(MAKE) -C $(SRCDIR)/templates

99−.PHONY: symlinks

100−cleanup_files+=$(SYMLINKS)

101−symlinks: $(SYMLINKS)

102−$(SYMLINKS): $(MAIN)

103− ln -sf ./$(MAIN) $@

104−

105define generate-shell-script

97define generate-shell-script

106echo "Generating $@..."; \

98echo "Generating $@..."; \

107awk ' \

99awk ' \

@@ -141,7 +133,7 @@ build: configure

141 $(BUILDCMD) build

133 $(BUILDCMD) build

142

134

143.PHONY: build-exec

135.PHONY: build-exec

144−build-exec: $(PROGS) $(SYMLINKS)

136+build-exec: $(PROGS)

145cleanup_files+=$(EXECS)

137cleanup_files+=$(EXECS)

146$(EXECS): build

138$(EXECS): build

147 for f in $@; do \

139 for f in $@; do \

@@ -201,9 +193,8 @@ install-exec: build-exec

201 fi; \

193 fi; \

202 $(INSTALL_PROGRAM) $$f $(BINPATH)/; \

194 $(INSTALL_PROGRAM) $$f $(BINPATH)/; \

203 done

195 done

204− cd $(BINPATH); for f in $(SYMLINKS); do ln -sf $(MAIN) $$f; done

205uninstall-exec:

196uninstall-exec:

206− -for f in $(notdir $(PROGS) $(SYMLINKS)); do rm -f $(BINPATH)/$$f; done ;

197+ -for f in $(notdir $(PROGS)); do rm -f $(BINPATH)/$$f; done ;

207

198

208# Program + user documents installation.

199# Program + user documents installation.

209.PHONY: install-program uninstall-program

200.PHONY: install-program uninstall-program

@@ -295,15 +286,11 @@ $(osx_dmg_name): $(osx_pkg_name)

295

286

296.PHONY: win-pkg

287.PHONY: win-pkg

297win_pkg_name:=$(RELNAME).zip

288win_pkg_name:=$(RELNAME).zip

298−win_docs:=COPYING.txt COPYRIGHT.txt BUGS.txt README-WINDOWS.txt README-WINDOWS.html

289+win_docs:=COPYING.txt COPYRIGHT.txt BUGS.txt README.txt README.html

299cleanup_files+=$(win_pkg_name) $(win_docs)

290cleanup_files+=$(win_pkg_name) $(win_docs)

300win-pkg: $(win_pkg_name)

291win-pkg: $(win_pkg_name)

301$(win_pkg_name): $(THIS).exe $(win_docs)

292$(win_pkg_name): $(THIS).exe $(win_docs)

302 zip -r $(win_pkg_name) $(THIS).exe $(win_docs)

293 zip -r $(win_pkg_name) $(THIS).exe $(win_docs)

303−cleanup_files+=README-WINDOWS

304−README-WINDOWS: README

305− sed -e '/^Requirements/,/^\[fancyvrb\]:/ d' \

306− -e '/^Character encodings/,/mysite.com$$/ d' $< > $@

307

294

308.PHONY: test test-markdown

295.PHONY: test test-markdown

309test: $(MAIN)

296test: $(MAIN)

README+64−75

@@ -36,14 +36,11 @@ Requirements

36============

38The `pandoc` program itself does not depend on any external libraries

39−or programs. The convenience programs `markdown2html`, `markdown2latex`,

39+or programs.

40−`markdown2rst`, `markdown2rtf`, `markdown2s5`, `html2markdown`,

41−`latex2markdown`, and `rst2markdown` are implemented as symbolic links to

42−`pandoc`.

44The wrapper script `web2markdown` requires

41The wrapper script `web2markdown` requires

46− - `html2markdown` (included with Pandoc)

43+ - `pandoc` (which must be in the PATH)

47 - a POSIX-compliant shell (installed by default on all linux and unix

44 - a POSIX-compliant shell (installed by default on all linux and unix

48 systems, including Mac OS X, and in [Cygwin] for Windows),

45 systems, including Mac OS X, and in [Cygwin] for Windows),

49 - `HTML Tidy`

46 - `HTML Tidy`

@@ -56,7 +53,7 @@ The wrapper script `web2markdown` requires

57The wrapper script `markdown2pdf` requires

54The wrapper script `markdown2pdf` requires

59− - `markdown2latex` (included with Pandoc)

56+ - `pandoc` (which must be in the PATH)

60 - a POSIX-compliant shell

57 - a POSIX-compliant shell

61 - `pdflatex`, which should be part of any [LaTeX] distribution

58 - `pdflatex`, which should be part of any [LaTeX] distribution

62 - the [unicode] and [fancyvrb] LaTeX packages, which are included

59 - the [unicode] and [fancyvrb] LaTeX packages, which are included

@@ -80,47 +77,11 @@ Using Pandoc

81If you run `pandoc` without arguments, it will accept input from

78If you run `pandoc` without arguments, it will accept input from

82STDIN. If you run it with file names as arguments, it will take input

79STDIN. If you run it with file names as arguments, it will take input

83−from those files. It accepts several command-line options. For a

84−list, type

85−

86− pandoc -h

87−

88−The most important options specify the format of the source file and

89−the output. The default reader is markdown; the default writer is

90−HTML. So if you don't specify a reader or writer, `pandoc` will

91−convert markdown to HTML. For example,

92−

93− pandoc hello.txt

94−

95−will convert `hello.txt` from markdown to HTML. For other conversions,

96−you must specify a reader and/or a writer using the `-r` and `-w`

97−flags. To convert markdown to LaTeX, you would write:

98−

99− pandoc -w latex hello.txt

100−

101−To convert html to markdown:

102−

103− pandoc -r html -w markdown hello.txt

104−

105−Supported writers include `markdown`, `latex`, `html`, `rtf` (rich text

106−format), `rst` (reStructuredText), and `s5` (which produces an HTML

107−file that acts like powerpoint). Supported readers include `markdown`,

108−`html`, `latex`, and `rst`. Note that the `rst` reader only parses

109−a subset of reStructuredText syntax. For example, it doesn't handle

110−tables, definition lists, option lists, or footnotes. It handles only the

111−constructs expressible in unextended markdown. But for simple documents

112−it should be adequate. The `latex` and `html` readers are also limited

113−in what they can do. Because the `html` reader is picky about the HTML

114−it parses, it is recommended that you pipe HTML through [HTML Tidy] before

115−sending it to `pandoc`, or use the `web2markdown` script described below.

116−

117−By default, `pandoc` writes its output to STDOUT. If you want to

80+from those files. By default, `pandoc` writes its output to STDOUT.

118−write to a file, use the `-o` option or shell redirection:

81+If you want to write to a file, use the `-o` option:

119

120 pandoc -o hello.html hello.txt

83 pandoc -o hello.html hello.txt

121

122− pandoc hello.txt > hello.html

123−

124Note that you can specify multiple input files on the command line.

85Note that you can specify multiple input files on the command line.

125`pandoc` will concatenate them all (with blank lines between them)

86`pandoc` will concatenate them all (with blank lines between them)

126before parsing:

87before parsing:

@@ -131,6 +92,44 @@ before parsing:

131with a proper header, rather than a fragment. For more details on this

92with a proper header, rather than a fragment. For more details on this

132and many other command-line options, see below.)

93and many other command-line options, see below.)

133

95+The format of the input and output can be specified explicitly using

96+command-line options. The input format can be specified using the

97+`-r/--read` or `-f/--from` options, the output format using the

98+`-w/--write` or `-t/--to` options. Thus, to convert `hello.txt` from

99+markdown to LaTeX, you could type:

100+

101+ pandoc -f markdown -t latex hello.txt

102+

103+To convert `hello.html` from html to markdown:

104+

105+ pandoc -f html -t markdown hello.html

106+

107+Supported output formats include `markdown`, `latex`, `html`, `rtf`

108+(rich text format), `rst` (reStructuredText), and `s5` (which produces

109+an HTML file that acts like powerpoint). Supported input formats

110+include `markdown`, `html`, `latex`, and `rst`. Note that the `rst`

111+reader only parses a subset of reStructuredText syntax. For example,

112+it doesn't handle tables, definition lists, option lists, or footnotes.

113+It handles only the constructs expressible in unextended markdown.

114+But for simple documents it should be adequate. The `latex` and `html`

115+readers are also limited in what they can do. Because the `html`

116+reader is picky about the HTML it parses, it is recommended that you

117+pipe HTML through [HTML Tidy] before sending it to `pandoc`, or use the

118+`web2markdown` script described below.

119+

120+If you don't specify a reader or writer explicitly, `pandoc` will

121+try to determine the input and output format from the extensions of

122+the input and output filenames. Thus, for example,

123+

124+ pandoc -o hello.tex hello.txt

125+

126+will convert `hello.txt` from markdown to LaTeX. If no output file

127+is specified (so that output goes to STDOUT), or if the output file's

128+extension is unknown, the output format will default to HTML.

129+If no input file is specified (so that input comes from STDIN), or

130+if the input files' extensions are unknown, the input format will

131+be assumed to be markdown unless explicitly specified.

132+

134Character encodings

133Character encodings

135-------------------

134-------------------

136

135

@@ -150,31 +149,16 @@ The shell scripts (described below) automatically convert the input

150from the local encoding to UTF-8 before running them through `pandoc`,

149from the local encoding to UTF-8 before running them through `pandoc`,

151then convert the output back to the local encoding.

150then convert the output back to the local encoding.

152

151

153−Convenience programs and wrapper scripts

152+`markdown2pdf` and `web2markdown`

154−========================================

153+=================================

155−

156−For convenience, eight variant programs are included with Pandoc:

157−`markdown2html` (which is equivalent to `pandoc -w html`),

158−`markdown2latex` (equivalent to `pandoc -w latex`), `markdown2rst`

159−(equivalent to `pandoc -w rst`), `markdown2rtf` (equivalent to

160−`pandoc -w rtf`), `markdown2s5` (equivalent to `pandoc -w s5`),

161−`html2markdown` (equivalent to `pandoc -r html -w markdown`),

162−`latex2markdown` (equivalent to `pandoc -r latex -w markdown`), and

163−`rst2markdown` (equivalent to `pandoc -r rst -w markdown`). These

164−programs take an appropriately restricted subset of `pandoc`'s

165−options. (Run them with the `-h` flag for a full list of allowed

166−options.)

167−

168−Like `pandoc`, all of these programs produce fragments by default.

169−If you want to produce a standalone file, complete with a header

170−and footer appropriate to the format, use the `-s` option:

171

154

172− markdown2latex -s sample.txt > sample.tex

155+Two shell scripts, `markdown2pdf` and `web2markdown`, are included in

173−

156+the standard Pandoc installation. (They are not included in the Windows

174−Two shell scripts have also been included:

157+binary package, as they require a POSIX shell, but they may be used

158+in Windows under Cygwin.)

175

159

1761. `markdown2pdf` produces a PDF file from markdown-formatted

1601. `markdown2pdf` produces a PDF file from markdown-formatted

177− text, using `markdown2latex` and `pdflatex`. The default

161+ text, using `pandoc` and `pdflatex`. The default

178 behavior of `markdown2pdf` is to create a file with the same

162 behavior of `markdown2pdf` is to create a file with the same

179 base name as the first argument and the extension `pdf`; thus,

163 base name as the first argument and the extension `pdf`; thus,

180 for example,

164 for example,

@@ -190,7 +174,7 @@ Two shell scripts have also been included:

190 If no input file is specified, input will be taken from STDIN.

174 If no input file is specified, input will be taken from STDIN.

191

175

1922. `web2markdown` grabs a web page from a file or URL and converts

1762. `web2markdown` grabs a web page from a file or URL and converts

193− it to markdown-formatted text, using `tidy` and `html2markdown`.

177+ it to markdown-formatted text, using `tidy` and `pandoc`.

194 Unless input is from STDIN, an attempt is made to determine the

178 Unless input is from STDIN, an attempt is made to determine the

195 character encoding of the page from the "Content-type" meta tag.

179 character encoding of the page from the "Content-type" meta tag.

196 If this is not present, UTF-8 is assumed. Alternatively, a character

180 If this is not present, UTF-8 is assumed. Alternatively, a character

@@ -207,9 +191,20 @@ Command-line options

207====================

191====================

208

192

209Various command-line options can be used to customize the output.

193Various command-line options can be used to customize the output.

210−For a complete list, type

211

194

212− pandoc --help

195+`-f`, `--from`, `-r`, or `--read` can be used to specify the input

196+format -- the format Pandoc will be converting *from*. Available

197+formats are `native`, `markdown`, `rst`, `html`, and `latex`.

198+

199+`-t`, `--to`, `-w`, or `--write` can be used to specify the output

200+format -- the format Pandoc will be converting *to*. Available formats

201+are `native`, `html`, `s5`, `latex`, `markdown`, `rst`, and `rtf`.

202+

203+`-s` or `--standalone` indicates that a standalone document is to be

204+produced (with appropriate headers and footers), rather than a fragment.

205+

206+`-o` or `--output` specifies the name of the output file. If no output

207+filename is given, output will be sent to STDOUT.

213

208

214`-p` or `--preserve-tabs` causes tabs in the source text to be

209`-p` or `--preserve-tabs` causes tabs in the source text to be

215preserved, rather than converted to spaces (the default).

210preserved, rather than converted to spaces (the default).

@@ -225,12 +220,6 @@ untranslatable HTML codes and LaTeX environments. (The LaTeX reader

225does pass through untranslatable LaTeX commands, even if `-R` is not

220does pass through untranslatable LaTeX commands, even if `-R` is not

226specified.)

221specified.)

227

222

228−`-s` or `--standalone` causes `pandoc` to produce a standalone file,

229−complete with appropriate document headers. By default, `pandoc`

230−produces a fragment.

231−

232−`-o` or `--output-file` can be used to specify an output file.

233−

234`-C` or `--custom-header` can be used to specify a custom document

223`-C` or `--custom-header` can be used to specify a custom document

235header. To see the headers used by default, use the `-D` option:

224header. To see the headers used by default, use the `-D` option:

236for example, `pandoc -D html` prints the default HTML header.

225for example, `pandoc -D html` prints the default HTML header.

man/man1/html2markdown.1deleted−1

@@ -1 +0,0 @@

1−.so man1/pandoc.1

man/man1/latex2markdown.1deleted−1

@@ -1 +0,0 @@

1−.so man1/pandoc.1

man/man1/markdown2html.1deleted−1

@@ -1 +0,0 @@

1−.so man1/pandoc.1

man/man1/markdown2latex.1deleted−1

@@ -1 +0,0 @@

1−.so man1/pandoc.1

man/man1/markdown2pdf.1+11−16

@@ -6,14 +6,13 @@ markdown2pdf \- converts markdown-formatted text to PDF, using pdflatex

6.SH DESCRIPTION

7\fBmarkdown2pdf\fR converts \fIinput\-file\fR (or text from standard

8input) from markdown\-formatted plain text to PDF, using \fBpdflatex\fR.

9−If no output filename is specified, the name of the output file is

9+If no output filename is specified (using the \fB\-o\fR option),

10−derived from the input file; thus, for example, if the input file

10+the name of the output file is derived from the input file; thus, for

11−is \fIhello.txt\fR, the output file will be \fIhello.pdf\fR. If

11+example, if the input file is \fIhello.txt\fR, the output file will be

12−the input is read from STDIN and no output filename is

12+\fIhello.pdf\fR. If the input is read from STDIN and no output filename

13−specified, the output file will be named \fIstdin.pdf\fR. If

13+is specified, the output file will be named \fIstdin.pdf\fR. If multiple

14−multiple input files are specified, they will be concatenated before

14+input files are specified, they will be concatenated before conversion,

15−conversion, and the name of the output file will be derived from

15+and the name of the output file will be derived from the first input file.

16−the first input file.

17.PP

16.PP

18Input is assumed to be in the UTF\-8 character encoding. If your

17Input is assumed to be in the UTF\-8 character encoding. If your

19local character encoding is not UTF\-8, you should pipe input and

18local character encoding is not UTF\-8, you should pipe input and

@@ -21,11 +20,11 @@ output through \fBiconv\fR:

21.IP

20.IP

22.B iconv \-t utf\-8 input.txt | pandoc | iconv \-f utf\-8

21.B iconv \-t utf\-8 input.txt | pandoc | iconv \-f utf\-8

23.PP

22.PP

24−\fBmarkdown2pdf\fR assumes that the 'unicode' package

23+\fBmarkdown2pdf\fR assumes that the 'unicode' and 'fancyvrb' packages

25−is in latex's search path. If this package is not included in your

24+are in latex's search path. If these packages are not included in your

26−latex setup, it can be obtained from <http://ctan.org>.

25+latex setup, they can be obtained from <http://ctan.org>.

27.PP

26.PP

28−\fBmarkdown2pdf\fR is a wrapper around \fBmarkdown2latex\fR.

27+\fBmarkdown2pdf\fR is a wrapper around \fBpandoc\fR.

29.SH OPTIONS

28.SH OPTIONS

30.TP

29.TP

31.B \-o FILE, \-\-output=FILE

30.B \-o FILE, \-\-output=FILE

@@ -37,10 +36,6 @@ Preserve tabs instead of converting them to spaces.

37.B \-\-tab-stop=\fITABSTOP\fB

36.B \-\-tab-stop=\fITABSTOP\fB

38Specify tab stop (default is 4).

37Specify tab stop (default is 4).

39.TP

38.TP

40−.B \-R, \-\-parse-raw

41−Parse untranslatable LaTeX environments as raw LaTeX,

42−instead of ignoring them.

43−.TP

44.B \-N, \-\-number-sections

39.B \-N, \-\-number-sections

45Number section headings in LaTeX output. (Default is not to number them.)

40Number section headings in LaTeX output. (Default is not to number them.)

46.TP

41.TP

man/man1/markdown2rst.1deleted−1

@@ -1 +0,0 @@

1−.so man1/pandoc.1

man/man1/markdown2rtf.1deleted−1

@@ -1 +0,0 @@

1−.so man1/pandoc.1

man/man1/markdown2s5.1deleted−1

@@ -1 +0,0 @@

1−.so man1/pandoc.1

man/man1/pandoc.1+21−29

@@ -1,8 +1,6 @@

1.TH PANDOC 1 "December 15, 2006" Pandoc "User Manuals"

2.SH NAME

3−pandoc, markdown2html, markdown2latex, markdown2rst, markdown2rtf,

4−markdown2s5, html2markdown2, latex2markdown, rst2markdown \- general

5−markup converter

3+pandoc \- general markup converter

6.SH SYNOPSIS

4.SH SYNOPSIS

7\fBpandoc\fR [\fIoptions\fR] [\fIinput\-file\fR]...

5\fBpandoc\fR [\fIoptions\fR] [\fIinput\-file\fR]...

8.SH DESCRIPTION

6.SH DESCRIPTION

@@ -13,41 +11,37 @@ slide shows.

13.PP

11.PP

14If no \fIinput\-file\fR is specified, input is read from STDIN.

12If no \fIinput\-file\fR is specified, input is read from STDIN.

15Otherwise, the \fIinput\-files\fR are concatenated (with a blank

13Otherwise, the \fIinput\-files\fR are concatenated (with a blank

16−line between each) and used as input. Output goes to standard

14+line between each) and used as input. Output goes to STDOUT by

17−output. If you want output to a file, use the \fB\-o\fR option or

15+default. For output to a file, use the \fB\-o\fR option:

18−shell redirection:

19.IP

16.IP

20.B pandoc \-o output.html input.txt

17.B pandoc \-o output.html input.txt

21−.IP

22−.B pandoc input.txt > output.html

23.PP

18.PP

24−The default behavior of \fIPandoc\fR is to convert the input from

25−markdown\-formatted plain text to HTML. Different input and output

26−formats can be specified using command\-line options. For example,

19+The input and output formats may be specified using command-line options

20+(see \fBOPTIONS\fR, below, for details). If these formats are not

21+specified explicitly, \fIPandoc\fR will attempt to determine them

22+from the extensions of the input and output filenames. If input comes

23+from STDIN or from a file with an unknown extension, the input is assumed

24+to be markdown. If no output filename is specified using the \fB\-o\fR

25+option, or if a filename is specified but its extension is unknown,

26+the output will default to HTML. Thus, for example,

27.IP

28−.B pandoc \-f latex \-t markdown chap1.tex > chap1.txt

28+.B pandoc -o chap1.tex chap1.txt

29.PP

30−converts \fIchap1.tex\fR from LaTeX to markdown\-formatted plain text.

30+converts \fIchap1.txt\fR from markdown to LaTeX. And

31−See below for a detailed list of command\-line options.

31+.IP

32+.B pandoc README

32.PP

33.PP

33−For convenience, eight variant programs are available:

34+converts \fIREADME\fR from markdown to HTML.

34−\fBmarkdown2html\fR (same as \fBpandoc \-w html\fR),

35−\fBmarkdown2latex\fR (same as \fBpandoc \-w latex\fR),

36−\fBmarkdown2rst\fR (same as \fBpandoc \-w rst\fR),

37−\fBmarkdown2rtf\fR (same as \fBpandoc \-w rtf\fR),

38−\fBmarkdown2s5\fR (same as \fBpandoc \-w s5\fR),

39−\fBhtml2markdown\fR (same as \fBpandoc \-r html \-w markdown\fR),

40−\fBlatex2markdown\fR (same as \fBpandoc \-r latex \-w markdown\fR),

41−and \fBrst2markdown\fR (same as \fBpandoc \-r rst \-w markdown\fR).

42−These programs take an appropriately restricted subset of \fBpandoc\fR's

43−options. (Run them with the \fB-h\fR flag for a full list of allowed

44−options.)

45.PP

35.PP

46\fIPandoc\fR uses the UTF\-8 character encoding for both input and output.

36\fIPandoc\fR uses the UTF\-8 character encoding for both input and output.

47If your local character encoding is not UTF\-8, you should pipe input

37If your local character encoding is not UTF\-8, you should pipe input

48and output through \fBiconv\fR:

38and output through \fBiconv\fR:

49.IP

39.IP

50.B iconv \-t utf\-8 input.txt | pandoc | iconv \-f utf\-8

40.B iconv \-t utf\-8 input.txt | pandoc | iconv \-f utf\-8

41+.PP

42+\fIPandoc\fR's HTML parser is not very forgiving. If your input is

43+HTML, consider running it through \fBtidy\fR(1) before passing it

44+to Pandoc. Or use \fBweb2markdown\fR(1), a wrapper around \fBpandoc\fR.

52.SH OPTIONS

46.SH OPTIONS

53.TP

47.TP

@@ -158,9 +152,7 @@ Show usage message.

158

152

159.SH "SEE ALSO"

153.SH "SEE ALSO"

160\fBweb2markdown\fR(1),

154\fBweb2markdown\fR(1),

161−\fBmarkdown2pdf\fR(1),

155+\fBmarkdown2pdf\fR(1).

162−\fBiconv\fR(1)

163−

164The

156The

165.I README

157.I README

166file distributed with Pandoc contains full documentation.

158file distributed with Pandoc contains full documentation.

man/man1/rst2markdown.1deleted−1

@@ -1 +0,0 @@

1−.so man1/pandoc.1

man/man1/web2markdown.1+1−2

@@ -16,7 +16,7 @@ option.

16from STDIN, UTF-8 is assumed. A character encoding may be specified

17explicitly using the \fB\-e\fR option.

18.PP

19−\fBweb2markdown\fR is a wrapper for \fBhtml2markdown\fR.

19+\fBweb2markdown\fR is a wrapper for \fBpandoc\fR.

20.SH OPTIONS

21.TP

22.B \-s, \-\-standalone

@@ -76,7 +76,6 @@ web2markdown \-g 'wget \-\-user=foo \-\-password=bar' mysite.com

77.SH "SEE ALSO"

78\fBpandoc\fR(1),

79−\fBhtml2markdown\fR(1),

80\fBiconv\fR(1)

79\fBiconv\fR(1)

81.SH AUTHOR

80.SH AUTHOR

82John MacFarlane and Recai Oktas

81John MacFarlane and Recai Oktas

src/Main.hs+82−75

@@ -45,7 +45,7 @@ import Text.Pandoc.Writers.DefaultHeaders ( defaultHtmlHeader,

45 defaultRTFHeader, defaultS5Header, defaultLaTeXHeader )

46import Text.Pandoc.Definition

47import Text.Pandoc.Shared

48−import Text.Regex ( mkRegex, splitRegex )

48+import Text.Regex ( mkRegex, matchRegex )

49import System ( exitWith, getArgs, getProgName )

50import System.Exit

51import System.Console.GetOpt

@@ -94,8 +94,8 @@ data Opt = Opt

94 { optPreserveTabs :: Bool -- ^ If @False@, convert tabs to spaces

95 , optTabStop :: Int -- ^ Number of spaces per tab

96 , optStandalone :: Bool -- ^ If @True@, include header, footer

97− , optReader :: ParserState -> String -> Pandoc -- ^ Read format

97+ , optReader :: String -- ^ Reader format

98− , optWriter :: WriterOptions -> Pandoc -> String -- ^ Write fmt

98+ , optWriter :: String -- ^ Writer format

99 , optParseRaw :: Bool -- ^ If @True@, parse unconvertable

100 -- HTML and TeX

101 , optCSS :: String -- ^ CSS file to link to

@@ -103,64 +103,55 @@ data Opt = Opt

103 , optIncludeBeforeBody :: String -- ^ File to include at top of body

104 , optIncludeAfterBody :: String -- ^ File to include at end of body

105 , optCustomHeader :: String -- ^ Custom header to use, or "DEFAULT"

106− , optDefaultHeader :: String -- ^ Default header

107 , optTitlePrefix :: String -- ^ Optional prefix for HTML title

106 , optTitlePrefix :: String -- ^ Optional prefix for HTML title

108 , optOutputFile :: String -- ^ Name of output file

107 , optOutputFile :: String -- ^ Name of output file

109 , optNumberSections :: Bool -- ^ If @True@, number sections in LaTeX

108 , optNumberSections :: Bool -- ^ If @True@, number sections in LaTeX

110 , optIncremental :: Bool -- ^ If @True@, incremental lists in S5

109 , optIncremental :: Bool -- ^ If @True@, incremental lists in S5

111 , optSmart :: Bool -- ^ If @True@, use smart typography

110 , optSmart :: Bool -- ^ If @True@, use smart typography

112 , optASCIIMathML :: Bool -- ^ If @True@, use ASCIIMathML in HTML

111 , optASCIIMathML :: Bool -- ^ If @True@, use ASCIIMathML in HTML

113− , optShowUsage :: Bool -- ^ If @True@, show usage message

114 , optDebug :: Bool -- ^ If @True@, output debug messages

112 , optDebug :: Bool -- ^ If @True@, output debug messages

115 }

113 }

116

114

117-- | Defaults for command-line options.

115-- | Defaults for command-line options.

118−startOpt :: Opt

116+defaultOpts :: Opt

119−startOpt = Opt

117+defaultOpts = Opt

120 { optPreserveTabs = False

118 { optPreserveTabs = False

121 , optTabStop = 4

119 , optTabStop = 4

122 , optStandalone = False

120 , optStandalone = False

123− , optReader = readMarkdown

121+ , optReader = "" -- null for default reader

124− , optWriter = writeHtml

122+ , optWriter = "" -- null for default writer

125 , optParseRaw = False

123 , optParseRaw = False

126 , optCSS = ""

124 , optCSS = ""

127 , optIncludeInHeader = ""

125 , optIncludeInHeader = ""

128 , optIncludeBeforeBody = ""

126 , optIncludeBeforeBody = ""

129 , optIncludeAfterBody = ""

127 , optIncludeAfterBody = ""

130 , optCustomHeader = "DEFAULT"

128 , optCustomHeader = "DEFAULT"

131− , optDefaultHeader = defaultHtmlHeader

132 , optTitlePrefix = ""

129 , optTitlePrefix = ""

133 , optOutputFile = "" -- null for stdout

130 , optOutputFile = "" -- null for stdout

134 , optNumberSections = False

131 , optNumberSections = False

135 , optIncremental = False

132 , optIncremental = False

136 , optSmart = False

133 , optSmart = False

137 , optASCIIMathML = False

134 , optASCIIMathML = False

138− , optShowUsage = False

139 , optDebug = False

135 , optDebug = False

140 }

136 }

141

137

142−-- | A list of functions, each transforming the options data structure in response

138+-- | A list of functions, each transforming the options data structure

143−-- to a command-line option.

139+-- in response to a command-line option.

144−allOptions :: [OptDescr (Opt -> IO Opt)]

140+options :: [OptDescr (Opt -> IO Opt)]

145−allOptions =

141+options =

146 [ Option "fr" ["from","read"]

142 [ Option "fr" ["from","read"]

147 (ReqArg

143 (ReqArg

148− (\arg opt -> case (lookup (map toLower arg) readers) of

149− Just reader -> return opt { optReader = reader }

144+ (\arg opt -> return opt { optReader = map toLower arg })

150− Nothing -> error ("Unknown reader: " ++ arg) )

151 "FORMAT")

145 "FORMAT")

152− ("Source format (" ++

146+ ("Input format (" ++ (joinWithSep ", " (map fst readers)) ++

153− (concatMap (\(name, fn) -> " " ++ name) readers) ++ " )")

147+ ")")

154

148

155 , Option "tw" ["to","write"]

149 , Option "tw" ["to","write"]

156 (ReqArg

150 (ReqArg

157− (\arg opt -> case (lookup (map toLower arg) writers) of

158− Just (writer, defaultHeader) ->

159− return opt { optWriter = writer,

151+ (\arg opt -> return opt { optWriter = map toLower arg })

160− optDefaultHeader = defaultHeader }

161− Nothing -> error ("Unknown writer: " ++ arg) )

162 "FORMAT")

152 "FORMAT")

163− ("Output format (" ++ (concatMap (\(name, fn) -> " " ++ name) writers) ++ " )")

153+ ("Output format (" ++ (joinWithSep ", " (map fst writers)) ++

154+ ")")

164

155

165 , Option "s" ["standalone"]

156 , Option "s" ["standalone"]

166 (NoArg

157 (NoArg

@@ -169,8 +160,7 @@ allOptions =

169

160

170 , Option "o" ["output"]

161 , Option "o" ["output"]

171 (ReqArg

162 (ReqArg

172− (\arg opt -> do

173− return opt { optOutputFile = arg })

163+ (\arg opt -> return opt { optOutputFile = arg })

174 "FILENAME")

164 "FILENAME")

175 "Name of output file"

165 "Name of output file"

176

166

@@ -286,57 +276,66 @@ allOptions =

286

276

287 , Option "h" ["help"]

277 , Option "h" ["help"]

288 (NoArg

278 (NoArg

289− (\opt -> return opt { optShowUsage = True }))

279+ (\_ -> do

280+ prg <- getProgName

281+ hPutStr stderr (reformatUsageInfo $

282+ usageInfo (prg ++ " [OPTIONS] [FILES]") options)

283+ exitWith $ ExitFailure 2))

290 "Show help"

284 "Show help"

291 ]

285 ]

292

286

293−-- parse name of calling program and return default reader and writer descriptions

294−parseProgName name =

295− case (splitRegex (mkRegex "2") (map toLower name)) of

296− [from, to] -> (from, to)

297− _ -> ("markdown", "html")

298−

299−-- set default options based on reader and writer descriptions; start is starting options

300−setDefaultOpts from to start =

301− case ((lookup from readers), (lookup to writers)) of

302− (Just reader, Just (writer, header)) -> start {optReader = reader,

303− optWriter = writer,

304− optDefaultHeader = header}

305− _ -> start

306−

307−-- True if single-letter option is in option list

308−inOptList :: [Char] -> OptDescr (Opt -> IO Opt) -> Bool

309−inOptList list desc =

310− let (Option letters _ _ _) = desc in

311− any (\x -> x `elem` list) letters

312−

313-- Reformat usage message so it doesn't wrap illegibly

287-- Reformat usage message so it doesn't wrap illegibly

288+reformatUsageInfo :: String -> String

314reformatUsageInfo = gsub " *--" " --" .

289reformatUsageInfo = gsub " *--" " --" .

315 gsub "(-[A-Za-z0-9]) *--" "\\1, --" .

290 gsub "(-[A-Za-z0-9]) *--" "\\1, --" .

316 gsub " *([^- ])" "\n\t\\1"

291 gsub " *([^- ])" "\n\t\\1"

317

292

318−main = do

293+-- Determine default reader based on source file extensions

319−

294+defaultReaderName :: [String] -> String

320− name <- getProgName

295+defaultReaderName [] = "markdown"

321− let (from, to) = parseProgName name

296+defaultReaderName (x:xs) =

297+ let x' = map toLower x in

298+ case (matchRegex (mkRegex ".*\\.(.*)") x') of

299+ Nothing -> defaultReaderName xs -- no extension

300+ Just ["xhtml"] -> "html"

301+ Just ["html"] -> "html"

302+ Just ["htm"] -> "html"

303+ Just ["tex"] -> "latex"

304+ Just ["latex"] -> "latex"

305+ Just ["ltx"] -> "latex"

306+ Just ["rst"] -> "rst"

307+ Just ["native"] -> "native"

308+ Just _ -> "markdown"

309+

310+-- Determine default writer based on output file extension

311+defaultWriterName :: String -> String

312+defaultWriterName "" = "html" -- no output file

313+defaultWriterName x =

314+ let x' = map toLower x in

315+ case (matchRegex (mkRegex ".*\\.(.*)") x') of

316+ Nothing -> "markdown" -- no extension

317+ Just [""] -> "markdown" -- empty extension

318+ Just ["tex"] -> "latex"

319+ Just ["latex"] -> "latex"

320+ Just ["ltx"] -> "latex"

321+ Just ["rtf"] -> "rtf"

322+ Just ["rst"] -> "rst"

323+ Just ["s5"] -> "s5"

324+ Just ["native"] -> "native"

325+ Just ["txt"] -> "markdown"

326+ Just ["text"] -> "markdown"

327+ Just ["md"] -> "markdown"

328+ Just ["markdown"] -> "markdown"

329+ Just _ -> "html"

322

330

323− let irrelevantOptions = if not ('2' `elem` name)

331+main = do

324− then ""

325− else "frtwD" ++

326− (if (to /= "html" && to /= "s5") then "SmcT" else "") ++

327− (if (to /= "latex") then "N" else "") ++

328− (if (to /= "s5") then "i" else "") ++

329− (if (from /= "html" && from /= "latex") then "R" else "")

330−

331− let options = filter (not . inOptList irrelevantOptions) allOptions

332−

333− let defaultOpts = setDefaultOpts from to startOpt

334

332

335 args <- getArgs

333 args <- getArgs

336 let (actions, sources, errors) = getOpt Permute options args

334 let (actions, sources, errors) = getOpt Permute options args

337

335

338 if (not (null errors))

336 if (not (null errors))

339 then do

337 then do

338+ name <- getProgName

340 mapM (\e -> hPutStrLn stderr e) errors

339 mapM (\e -> hPutStrLn stderr e) errors

341 hPutStrLn stderr (reformatUsageInfo $

340 hPutStrLn stderr (reformatUsageInfo $

342 usageInfo (name ++ " [OPTIONS] [FILES]") options)

341 usageInfo (name ++ " [OPTIONS] [FILES]") options)

@@ -350,30 +349,39 @@ main = do

350 let Opt { optPreserveTabs = preserveTabs

349 let Opt { optPreserveTabs = preserveTabs

351 , optTabStop = tabStop

350 , optTabStop = tabStop

352 , optStandalone = standalone

351 , optStandalone = standalone

353− , optReader = reader

352+ , optReader = readerName

354− , optWriter = writer

353+ , optWriter = writerName

355 , optParseRaw = parseRaw

354 , optParseRaw = parseRaw

356 , optCSS = css

355 , optCSS = css

357 , optIncludeInHeader = includeHeader

356 , optIncludeInHeader = includeHeader

358 , optIncludeBeforeBody = includeBefore

357 , optIncludeBeforeBody = includeBefore

359 , optIncludeAfterBody = includeAfter

358 , optIncludeAfterBody = includeAfter

360 , optCustomHeader = customHeader

359 , optCustomHeader = customHeader

361− , optDefaultHeader = defaultHeader

362 , optTitlePrefix = titlePrefix

360 , optTitlePrefix = titlePrefix

363 , optOutputFile = outputFile

361 , optOutputFile = outputFile

364 , optNumberSections = numberSections

362 , optNumberSections = numberSections

365 , optIncremental = incremental

363 , optIncremental = incremental

366 , optSmart = smart

364 , optSmart = smart

367 , optASCIIMathML = asciiMathML

365 , optASCIIMathML = asciiMathML

368− , optShowUsage = showUsage

369 , optDebug = debug

366 , optDebug = debug

370 } = opts

367 } = opts

371

368

372− if showUsage

369+ -- assign reader and writer based on options and filenames

373− then do

370+ let readerName' = if null readerName

374− hPutStr stderr (reformatUsageInfo $ usageInfo (name ++ " [OPTIONS] [FILES]") options)

371+ then defaultReaderName sources

375− exitWith $ ExitFailure 2

372+ else readerName

373+

374+ let writerName' = if null writerName

375+ then defaultWriterName outputFile

376+ else writerName

377+

378+ reader <- case (lookup readerName' readers) of

376− else return ()

379+ Just r -> return r

380+ Nothing -> error ("Unknown reader: " ++ readerName')

381+

382+ (writer, defaultHeader) <- case (lookup writerName' writers) of

383+ Just (w,h) -> return (w, h)

384+ Nothing -> error ("Unknown writer: " ++ writerName')

377

385

378 output <- if ((null outputFile) || debug)

386 output <- if ((null outputFile) || debug)

379 then return stdout

387 then return stdout

@@ -385,7 +393,6 @@ main = do

385 hPutStr stderr $ concatMap (\s -> "INPUT=" ++ s ++ "\n") sources

393 hPutStr stderr $ concatMap (\s -> "INPUT=" ++ s ++ "\n") sources

386 else return ()

394 else return ()

387

395

388− let writingS5 = (defaultHeader == defaultS5Header)

389 let tabFilter = if preserveTabs then id else (tabsToSpaces tabStop)

396 let tabFilter = if preserveTabs then id else (tabsToSpaces tabStop)

390 let addBlank str = str ++ "\n\n"

397 let addBlank str = str ++ "\n\n"

391 let removeCRs str = filter (/= '\r') str -- remove DOS-style line endings

398 let removeCRs str = filter (/= '\r') str -- remove DOS-style line endings

@@ -407,7 +414,7 @@ main = do

407 writerTitlePrefix = titlePrefix,

414 writerTitlePrefix = titlePrefix,

408 writerSmart = smart,

415 writerSmart = smart,

409 writerTabStop = tabStop,

416 writerTabStop = tabStop,

410− writerS5 = writingS5,

417+ writerS5 = (writerName=="s5"),

411 writerIncremental = incremental,

418 writerIncremental = incremental,

412 writerNumberSections = numberSections,

419 writerNumberSections = numberSections,

413 writerIncludeBefore = includeBefore,

420 writerIncludeBefore = includeBefore,

src/wrappers/markdown2pdf.in+7−4

@@ -1,6 +1,6 @@

1#!/bin/sh -e

3−REQUIRED="markdown2latex pdflatex"

3+REQUIRED="pdflatex"

5### common.sh

@@ -9,9 +9,12 @@ REQUIRED="markdown2latex pdflatex"

9texname=output

10logfile=$THIS_TEMPDIR/log

12−if ! markdown2latex -s -d "$@" >$THIS_TEMPDIR/$texname.tex 2>$logfile; then

12+if ! pandoc -s -d -r markdown -w latex "$@" >$THIS_TEMPDIR/$texname.tex \

13+2>$logfile; then

13− [ -f $logfile ] && sed -e 's/markdown2latex/markdown2pdf/g' \

14+ [ -f $logfile ] && sed -e 's/^pandoc/markdown2pdf/g' \

14− -e '/^INPUT=/d' -e '/^OUTPUT=/d' $logfile >&2

15+ -e '/^INPUT=/d' -e '/^OUTPUT=/d' \

16+ -e '/^[[:space:]]*$-f\|-t\|-s\|-R\|-S\|-m\|-i\|-c\|-T\|-D\|-d$/,/./d'\

17+ -e 's/(implies -s)//g' $logfile >&2

15 exit 1

18 exit 1

16fi

19fi

src/wrappers/web2markdown.in+9−6

@@ -2,7 +2,7 @@

2# converts HTML from a URL, file, or stdin to markdown

3# uses an available program to fetch URL and tidy to normalize it first

5−REQUIRED="tidy html2markdown"

5+REQUIRED="tidy"

7### common.sh

@@ -72,14 +72,16 @@ grabber=

72while [ $# -gt 0 ]; do

73 case "$1" in

74 -h|--help)

75− html2markdown -h 2>&1 | sed -e 's/html2markdown/web2markdown/' 1>&2

75+ pandoc -h 2>&1 | sed -e 's/pandoc/web2markdown/' \

76+ -e '/^[[:space:]]*$-f\|-t\|-S\|-N\|-m\|-i\|-c\|-T\|-D\|-d$/,/./d'\

77+ 1>&2

76 err " -e ENCODING, --encoding=ENCODING"

78 err " -e ENCODING, --encoding=ENCODING"

77 err " Specify character encoding of input"

79 err " Specify character encoding of input"

78 err " -g COMMAND, --grabber=COMMAND"

80 err " -g COMMAND, --grabber=COMMAND"

79 err " Specify command to be used to grab contents of URL"

81 err " Specify command to be used to grab contents of URL"

80 exit 0 ;;

82 exit 0 ;;

81 -v|--version)

83 -v|--version)

82− html2markdown -v

84+ pandoc -v 2>&1 | sed -e 's/pandoc/web2markdown/' 1>&2

83 exit 0 ;;

85 exit 0 ;;

84 -e)

86 -e)

85 shift

87 shift

@@ -112,7 +114,7 @@ while [ $# -gt 0 ]; do

112 shift

114 shift

113done

115done

114

116

115−# Unpack options. Now "$@" will hold the html2markdown options.

117+# Unpack options. Now "$@" will hold the pandoc options.

116oldifs="$IFS"; IFS="$NEWLINE"; set -- $options; IFS="$oldifs"

118oldifs="$IFS"; IFS="$NEWLINE"; set -- $options; IFS="$oldifs"

117

119

118inurl=

120inurl=

@@ -162,10 +164,11 @@ else # assume UTF-8

162fi

164fi

163

165

164if [ -z "$argument" ]; then

166if [ -z "$argument" ]; then

165− tidy -utf8 2>/dev/null | html2markdown "$@"

167+ tidy -utf8 2>/dev/null | pandoc -r html -w markdown "$@"

166else

168else

167 if [ -f "$argument" ]; then

169 if [ -f "$argument" ]; then

168− to_utf8 "$argument" | tidy -utf8 2>/dev/null | html2markdown "$@"

170+ to_utf8 "$argument" |

171+ tidy -utf8 2>/dev/null | pandoc -r html -w markdown "$@"

169 else

172 else

170 err "File '$argument' not found."

173 err "File '$argument' not found."

171 exit 1

174 exit 1