pandoc 2.10 → 2.10.1
raw patch · 87 files changed
+1602/−1213 lines, 87 filesdep +commonmarkdep +commonmark-extensionsdep +commonmark-pandocdep −cmark-gfmPVP ok
version bump matches the API change (PVP)
Dependencies added: commonmark, commonmark-extensions, commonmark-pandoc
Dependencies removed: cmark-gfm
API changes (from Hackage documentation)
+ Text.Pandoc.Extensions: Ext_attributes :: Extension
+ Text.Pandoc.Extensions: Ext_raw_markdown :: Extension
+ Text.Pandoc.Writers.Markdown: instance GHC.Classes.Eq Text.Pandoc.Writers.Markdown.MarkdownVariant
+ Text.Pandoc.Writers.Markdown: instance GHC.Show.Show Text.Pandoc.Writers.Markdown.MarkdownVariant
+ Text.Pandoc.Writers.Markdown: writeCommonMark :: PandocMonad m => WriterOptions -> Pandoc -> m Text
Files
- AUTHORS.md +3/−0
- CONTRIBUTING.md +9/−3
- MANUAL.txt +77/−45
- README.md +102/−92
- benchmark/benchmark-pandoc.hs +35/−25
- cabal.project +5/−0
- changelog.md +172/−1
- data/docx/word/styles.xml +4/−0
- data/templates/default.latex +3/−0
- man/pandoc.1 +79/−43
- pandoc.cabal +7/−3
- src/Text/Pandoc/Extensions.hs +58/−13
- src/Text/Pandoc/Readers.hs +1/−0
- src/Text/Pandoc/Readers/CommonMark.hs +40/−198
- src/Text/Pandoc/Readers/DocBook.hs +2/−1
- src/Text/Pandoc/Readers/Docx.hs +44/−49
- src/Text/Pandoc/Readers/Docx/Combine.hs +38/−61
- src/Text/Pandoc/Readers/Docx/Parse.hs +3/−0
- src/Text/Pandoc/Readers/Docx/Parse/Styles.hs +12/−6
- src/Text/Pandoc/Readers/Ipynb.hs +5/−1
- src/Text/Pandoc/Readers/LaTeX.hs +212/−152
- src/Text/Pandoc/Readers/LaTeX/Parsing.hs +152/−1
- src/Text/Pandoc/Readers/Org/Blocks.hs +4/−1
- src/Text/Pandoc/Readers/Org/ExportSettings.hs +3/−3
- src/Text/Pandoc/Readers/Org/Inlines.hs +17/−6
- src/Text/Pandoc/Readers/Org/ParserState.hs +6/−0
- src/Text/Pandoc/Readers/RST.hs +10/−4
- src/Text/Pandoc/Templates.hs +1/−0
- src/Text/Pandoc/Writers.hs +1/−0
- src/Text/Pandoc/Writers/CommonMark.hs +1/−349
- src/Text/Pandoc/Writers/Docx.hs +17/−4
- src/Text/Pandoc/Writers/HTML.hs +10/−2
- src/Text/Pandoc/Writers/Jira.hs +12/−10
- src/Text/Pandoc/Writers/Markdown.hs +162/−114
- src/Text/Pandoc/Writers/Ms.hs +8/−6
- stack.yaml +4/−0
- test/Tests/Readers/LaTeX.hs +55/−3
- test/Tests/Readers/Org/Directive.hs +30/−0
- test/Tests/Writers/Ms.hs +37/−0
- test/command/01.csv +4/−0
- test/command/1608.md +41/−0
- test/command/3577.md +3/−3
- test/command/3587.md +59/−0
- test/command/3734.md +1/−1
- test/command/4038.md +1/−1
- test/command/4528.md +1/−1
- test/command/4677.md +1/−1
- test/command/5121.md +1/−1
- test/command/5642.md +1/−1
- test/command/6549.md +26/−0
- test/command/gfm.md +4/−4
- test/docx/golden/block_quotes.docx binary
- test/docx/golden/codeblock.docx binary
- test/docx/golden/comments.docx binary
- test/docx/golden/custom_style_no_reference.docx binary
- test/docx/golden/custom_style_preserve.docx binary
- test/docx/golden/definition_list.docx binary
- test/docx/golden/document-properties-short-desc.docx binary
- test/docx/golden/document-properties.docx binary
- test/docx/golden/headers.docx binary
- test/docx/golden/image.docx binary
- test/docx/golden/inline_code.docx binary
- test/docx/golden/inline_formatting.docx binary
- test/docx/golden/inline_images.docx binary
- test/docx/golden/link_in_notes.docx binary
- test/docx/golden/links.docx binary
- test/docx/golden/lists.docx binary
- test/docx/golden/lists_continuing.docx binary
- test/docx/golden/lists_restarting.docx binary
- test/docx/golden/nested_anchors_in_header.docx binary
- test/docx/golden/notes.docx binary
- test/docx/golden/table_one_row.docx binary
- test/docx/golden/table_with_list_cell.docx binary
- test/docx/golden/tables.docx binary
- test/docx/golden/track_changes_deletion.docx binary
- test/docx/golden/track_changes_insertion.docx binary
- test/docx/golden/track_changes_move.docx binary
- test/docx/golden/unicode.docx binary
- test/docx/golden/verbatim_subsuper.docx binary
- test/docx/inline_formatting.native +1/−1
- test/lhs-test.latex +3/−0
- test/lhs-test.latex+lhs +3/−0
- test/test-pandoc.hs +2/−0
- test/writer.html5 +1/−1
- test/writer.jira +2/−2
- test/writer.latex +3/−0
- test/writers-lang-and-dir.latex +3/−0
AUTHORS.md view
@@ -66,6 +66,7 @@ - Douglas Calvert - Eigil Rischel - Emanuel Evans+- Emerson Harkin - Emily Eisenberg - Eric Kow - Eric Seidel@@ -241,6 +242,7 @@ - Urs Liska - Václav Zeman - Václav Haisman+- Vaibhav Sagar - Vanessa McHale - Vasily Alferov - Viktor Kronvall@@ -264,6 +266,7 @@ - dbecher-ito - d-dorazio - ebiim+- favonia - infinity0x - jeongminkim-islab - kaizshang91
CONTRIBUTING.md view
@@ -17,8 +17,14 @@ to make sure the issue hasn't come up before. Also, check the [User's Guide] and [FAQs] for anything relevant. -Make sure you can reproduce the bug with the [latest released version] of pandoc-(or, even better, the [development version]).+Make sure you can reproduce the bug with the [latest released+version] of pandoc---or, even better, the development version,+since the bug may have been fixed since the last release.+[Nightly builds] are available, so you don't need to compile+from source to test againt the development version.+(To fetch a nightly, visit the link, click the topmost "Nightly"+in the table, then choose your platform under "Artifacts." Note+that you must be logged in with a GitHub account.) Your report should give detailed, *reproducible* instructions, including @@ -346,7 +352,7 @@ [open issues]: https://github.com/jgm/pandoc/issues [closed issues]: https://github.com/jgm/pandoc/issues?q=is%3Aissue+is%3Aclosed [latest released version]: https://github.com/jgm/pandoc/releases/latest-[development version]: https://github.com/pandoc-extras/pandoc-nightly/releases/latest+[Nightly builds]: https://github.com/jgm/pandoc/actions?query=workflow%3ANightly [pandoc-discuss]: http://groups.google.com/group/pandoc-discuss [issue tracker]: https://github.com/jgm/pandoc/issues [User's Guide]: http://pandoc.org/MANUAL.html
MANUAL.txt view
@@ -1,7 +1,7 @@ --- title: Pandoc User's Guide author: John MacFarlane-date: June 29, 2020+date: July 23, 2020 --- # Synopsis@@ -226,6 +226,7 @@ ::: {#input-formats} - `commonmark` ([CommonMark] Markdown)+ - `commonmark_x` ([CommonMark] Markdown with extensions) - `creole` ([Creole 1.0]) - `csv` ([CSV] table) - `docbook` ([DocBook])@@ -277,6 +278,7 @@ - `asciidoc` ([AsciiDoc]) or `asciidoctor` ([AsciiDoctor]) - `beamer` ([LaTeX beamer][`beamer`] slide show) - `commonmark` ([CommonMark] Markdown)+ - `commonmark_x` ([CommonMark] Markdown with extensions) - `context` ([ConTeXt]) - `docbook` or `docbook4` ([DocBook] 4) - `docbook5` (DocBook 5)@@ -902,7 +904,7 @@ downloaded). If you're behind a proxy, you also need to set the environment variable `http_proxy` to `http://...`. -`--no-check-certificate+`--no-check-certificate` : Disable the certificate verification to allow access to unsecure HTTP resources (for example when the certificate@@ -980,7 +982,7 @@ `-N`, `--number-sections` -: Number section headings in LaTeX, ConTeXt, HTML, or EPUB output.+: Number section headings in LaTeX, ConTeXt, HTML, Docx, or EPUB output. By default, sections are not numbered. Sections with class `unnumbered` will never be numbered, even if `--number-sections` is specified.@@ -1123,6 +1125,7 @@ - Verbatim Char - Footnote Reference - Hyperlink+ - Section Number Table style: @@ -2767,53 +2770,43 @@ ## Raw HTML/TeX -The following extensions (especially how they affect Markdown-input/output) are also described in more detail in their respective-sections of [Pandoc's Markdown].--#### Extension: `raw_html` {#raw_html}--When converting from HTML, parse elements to raw HTML which are not-representable in pandoc's AST.-By default, this is disabled for HTML input.--#### Extension: `raw_tex` {#raw_tex}--Allows raw LaTeX, TeX, and ConTeXt to be included in a document.--This extension can be enabled/disabled for the following formats-(in addition to `markdown`):--input formats-: `latex`, `org`, `textile`, `html` (environments, `\ref`, and- `\eqref` only), `ipynb`--output formats-: `textile`, `commonmark`--Note: as applied to `ipynb`, `raw_html` and `raw_tex` affect not-only raw TeX in markdown cells, but data with mime type-`text/html` in output cells. Since the `ipynb` reader attempts-to preserve the richest possible outputs when several options-are given, you will get best results if you disable `raw_html`-and `raw_tex` when converting to formats like `docx` which don't-allow raw `html` or `tex`.+The following extensions are described in more detail in+their respective sections of [Pandoc's Markdown]: -#### Extension: `native_divs` {#native_divs}+- [`raw_html`](#extension-raw_html) allows HTML elements which+ are not representable in pandoc's AST to be parsed as raw HTML.+ By default, this is disabled for HTML input. -This extension is enabled by default for HTML input. This means that-`div`s are parsed to pandoc native elements. (Alternatively, you-can parse them to raw HTML using `-f html-native_divs+raw_html`.)+- [`raw_tex`](#extension-raw_tex) allows raw LaTeX, TeX, and ConTeXt+ to be included in a document. This extension can be enabled/disabled+ for the following formats (in addition to `markdown`): -When converting HTML to Markdown, for example, you may want to drop all-`div`s and `span`s:+ input formats+ : `latex`, `org`, `textile`, `html` (environments, `\ref`, and+ `\eqref` only), `ipynb` - pandoc -f html-native_divs-native_spans -t markdown+ output formats+ : `textile`, `commonmark` -#### Extension: `native_spans` {#native_spans}+ Note: as applied to `ipynb`, `raw_html` and `raw_tex` affect not+ only raw TeX in markdown cells, but data with mime type+ `text/html` in output cells. Since the `ipynb` reader attempts+ to preserve the richest possible outputs when several options+ are given, you will get best results if you disable `raw_html`+ and `raw_tex` when converting to formats like `docx` which don't+ allow raw `html` or `tex`. -Analogous to `native_divs` above.+- [`native_divs`](#extension-native_divs) causes HTML `div`+ elements to be parsed as native pandoc Div blocks.+ If you want them to be parsed as raw HTML, use+ `-f html-native_divs+raw_html`. +- [`native_spans`](#extension-native_spans) causes HTML `span`+ elements to be parsed as native pandoc Span inlines.+ If you want them to be parsed as raw HTML, use+ `-f html-native_spans+raw_html`. If you want to drop all+ `div`s and `span`s when converting HTML to Markdown, you+ can use `pandoc -f html-native_divs-native_spans -t markdown`. ## Literate Haskell support @@ -2917,6 +2910,14 @@ In the `muse` input format, this enables Text::Amuse extensions to Emacs Muse markup. +#### Extension: `raw_markdown` ####++In the `ipynb` input format, this causes Markdown cells+to be included as raw Markdown blocks (allowing lossless+round-tripping) rather than being parsed. Use this only+when you are targetting `ipynb` or a markdown-based+output format.+ #### Extension: `citations` {#org-citations} Some aspects of [Pandoc's Markdown citation syntax](#citations) are also accepted@@ -4943,6 +4944,37 @@ name, where `EXTENSION` is the name of the extension. Thus, for example, `markdown+hard_line_breaks` is Markdown with hard line breaks. +#### Extension: `attributes` ####++Allows attributes to be attached to any inline or block-level+element. The syntax for the attributes is the same as that+used in [`header_attributes`][Extension: `header_attributes`].++- Attributes that occur immediately after an inline+ element affect that element. If they follow a space, then they+ belong to the space. (Hence, this option subsumes+ `inline_code_attributes` and `link_attributes`.)+- Attributes that occur immediately before a block+ element, on a line by themselves, affect that+ element.+- Consecutive attribute specifiers may be used,+ either for blocks or for inlines. Their attributes+ will be combined.+- Attributes that occur at the end of the text of+ a Setext or ATX heading (separated by whitespace+ from the text) affect the heading element. (Hence, this+ option subsumes `header_attributes`.)+- Attributes that occur after the opening fence+ in a fenced code block affect the code block element. (Hence,+ this option subsumes `fenced_code_attributes`.)+- Attributes that occur at the end of a reference+ link definition affect links that refer to that+ definition.++Note that pandoc's AST does not currently allow attributes+to be attached to arbitrary elements. Hence a Span or Div+container will be added if needed.+ #### Extension: `old_dashes` #### Selects the pandoc <= 1.8.2.1 behavior for parsing smart dashes:@@ -5141,7 +5173,8 @@ only affects `gfm` output, not input. `gfm` (GitHub-Flavored Markdown)-: `pipe_tables`, `raw_html`, `fenced_code_blocks`, `auto_identifiers`,+: `pipe_tables`, `raw_html`, `native_divs`,+ `fenced_code_blocks`, `auto_identifiers`, `gfm_auto_identifiers`, `backtick_code_blocks`, `autolink_bare_uris`, `space_in_atx_header`, `intraword_underscores`, `strikeout`, `task_lists`, `emoji`,@@ -5633,7 +5666,6 @@ foreword frontmatter preface frontmatter seriespage frontmatter-titlepage frontmatter appendix backmatter colophon backmatter bibliography backmatter
README.md view
@@ -3,7 +3,8 @@ pandoc --lua-filter tools/update-readme.lua README.template -o README.md --> -# Pandoc+Pandoc+====== [](https://github.com/jgm/pandoc/releases)@@ -19,7 +20,8 @@ [](https://groups.google.com/forum/#!forum/pandoc-discuss) -## The universal markup converter+The universal markup converter+------------------------------ Pandoc is a [Haskell](http://haskell.org) library for converting from one markup format to another, and a command-line tool that uses this@@ -27,58 +29,60 @@ <div id="input-formats"> - - `commonmark` ([CommonMark](https://commonmark.org) Markdown)- - `creole` ([Creole 1.0](http://www.wikicreole.org/wiki/Creole1.0))- - `csv` ([CSV](https://tools.ietf.org/html/rfc4180) table)- - `docbook` ([DocBook](https://docbook.org))- - `docx` ([Word docx](https://en.wikipedia.org/wiki/Office_Open_XML))- - `dokuwiki` ([DokuWiki markup](https://www.dokuwiki.org/dokuwiki))- - `epub` ([EPUB](http://idpf.org/epub))- - `fb2`+- `commonmark` ([CommonMark](https://commonmark.org) Markdown)+- `commonmark_x` ([CommonMark](https://commonmark.org) Markdown with+ extensions)+- `creole` ([Creole 1.0](http://www.wikicreole.org/wiki/Creole1.0))+- `csv` ([CSV](https://tools.ietf.org/html/rfc4180) table)+- `docbook` ([DocBook](https://docbook.org))+- `docx` ([Word docx](https://en.wikipedia.org/wiki/Office_Open_XML))+- `dokuwiki` ([DokuWiki markup](https://www.dokuwiki.org/dokuwiki))+- `epub` ([EPUB](http://idpf.org/epub))+- `fb2` ([FictionBook2](http://www.fictionbook.org/index.php/Eng:XML_Schema_Fictionbook_2.1) e-book)- - `gfm` ([GitHub-Flavored+- `gfm` ([GitHub-Flavored Markdown](https://help.github.com/articles/github-flavored-markdown/)), or the deprecated and less accurate `markdown_github`; use [`markdown_github`](https://pandoc.org/MANUAL.html#markdown-variants) only if you need extensions not supported in [`gfm`](https://pandoc.org/MANUAL.html#markdown-variants).- - `haddock` ([Haddock+- `haddock` ([Haddock markup](https://www.haskell.org/haddock/doc/html/ch03s08.html))- - `html` ([HTML](https://www.w3.org/html/))- - `ipynb` ([Jupyter+- `html` ([HTML](https://www.w3.org/html/))+- `ipynb` ([Jupyter notebook](https://nbformat.readthedocs.io/en/latest/))- - `jats` ([JATS](https://jats.nlm.nih.gov) XML)- - `jira`+- `jats` ([JATS](https://jats.nlm.nih.gov) XML)+- `jira` ([Jira](https://jira.atlassian.com/secure/WikiRendererHelpAction.jspa?section=all)/Confluence wiki markup)- - `json` (JSON version of native AST)- - `latex` ([LaTeX](https://www.latex-project.org/))- - `markdown` ([Pandoc’s+- `json` (JSON version of native AST)+- `latex` ([LaTeX](https://www.latex-project.org/))+- `markdown` ([Pandoc’s Markdown](https://pandoc.org/MANUAL.html#pandocs-markdown))- - `markdown_mmd`+- `markdown_mmd` ([MultiMarkdown](https://fletcherpenney.net/multimarkdown/))- - `markdown_phpextra` ([PHP Markdown+- `markdown_phpextra` ([PHP Markdown Extra](https://michelf.ca/projects/php-markdown/extra/))- - `markdown_strict` (original unextended+- `markdown_strict` (original unextended [Markdown](https://daringfireball.net/projects/markdown/))- - `mediawiki` ([MediaWiki+- `mediawiki` ([MediaWiki markup](https://www.mediawiki.org/wiki/Help:Formatting))- - `man` ([roff man](https://man.cx/groff_man\(7\)))- - `muse` ([Muse](https://amusewiki.org/library/manual))- - `native` (native Haskell)- - `odt` ([ODT](https://en.wikipedia.org/wiki/OpenDocument))- - `opml` ([OPML](http://dev.opml.org/spec2.html))- - `org` ([Emacs Org mode](https://orgmode.org))- - `rst`+- `man` ([roff man](https://man.cx/groff_man(7)))+- `muse` ([Muse](https://amusewiki.org/library/manual))+- `native` (native Haskell)+- `odt` ([ODT](https://en.wikipedia.org/wiki/OpenDocument))+- `opml` ([OPML](http://dev.opml.org/spec2.html))+- `org` ([Emacs Org mode](https://orgmode.org))+- `rst` ([reStructuredText](https://docutils.sourceforge.io/docs/ref/rst/introduction.html))- - `t2t` ([txt2tags](https://txt2tags.org))- - `textile` ([Textile](https://www.promptworks.com/textile))- - `tikiwiki` ([TikiWiki+- `t2t` ([txt2tags](https://txt2tags.org))+- `textile` ([Textile](https://www.promptworks.com/textile))+- `tikiwiki` ([TikiWiki markup](https://doc.tiki.org/Wiki-Syntax-Text#The_Markup_Language_Wiki-Syntax))- - `twiki` ([TWiki+- `twiki` ([TWiki markup](https://twiki.org/cgi-bin/view/TWiki/TextFormattingRules))- - `vimwiki` ([Vimwiki](https://vimwiki.github.io))+- `vimwiki` ([Vimwiki](https://vimwiki.github.io)) </div> @@ -86,94 +90,96 @@ <div id="output-formats"> - - `asciidoc` ([AsciiDoc](https://www.methods.co.nz/asciidoc/)) or+- `asciidoc` ([AsciiDoc](https://www.methods.co.nz/asciidoc/)) or `asciidoctor` ([AsciiDoctor](https://asciidoctor.org/))- - `beamer` ([LaTeX beamer](https://ctan.org/pkg/beamer) slide show)- - `commonmark` ([CommonMark](https://commonmark.org) Markdown)- - `context` ([ConTeXt](https://www.contextgarden.net/))- - `docbook` or `docbook4` ([DocBook](https://docbook.org) 4)- - `docbook5` (DocBook 5)- - `docx` ([Word docx](https://en.wikipedia.org/wiki/Office_Open_XML))- - `dokuwiki` ([DokuWiki markup](https://www.dokuwiki.org/dokuwiki))- - `epub` or `epub3` ([EPUB](http://idpf.org/epub) v3 book)- - `epub2` (EPUB v2)- - `fb2`+- `beamer` ([LaTeX beamer](https://ctan.org/pkg/beamer) slide show)+- `commonmark` ([CommonMark](https://commonmark.org) Markdown)+- `commonmark_x` ([CommonMark](https://commonmark.org) Markdown with+ extensions)+- `context` ([ConTeXt](https://www.contextgarden.net/))+- `docbook` or `docbook4` ([DocBook](https://docbook.org) 4)+- `docbook5` (DocBook 5)+- `docx` ([Word docx](https://en.wikipedia.org/wiki/Office_Open_XML))+- `dokuwiki` ([DokuWiki markup](https://www.dokuwiki.org/dokuwiki))+- `epub` or `epub3` ([EPUB](http://idpf.org/epub) v3 book)+- `epub2` (EPUB v2)+- `fb2` ([FictionBook2](http://www.fictionbook.org/index.php/Eng:XML_Schema_Fictionbook_2.1) e-book)- - `gfm` ([GitHub-Flavored+- `gfm` ([GitHub-Flavored Markdown](https://help.github.com/articles/github-flavored-markdown/)), or the deprecated and less accurate `markdown_github`; use [`markdown_github`](https://pandoc.org/MANUAL.html#markdown-variants) only if you need extensions not supported in [`gfm`](https://pandoc.org/MANUAL.html#markdown-variants).- - `haddock` ([Haddock+- `haddock` ([Haddock markup](https://www.haskell.org/haddock/doc/html/ch03s08.html))- - `html` or `html5` ([HTML](https://www.w3.org/html/),+- `html` or `html5` ([HTML](https://www.w3.org/html/), i.e. [HTML5](https://html.spec.whatwg.org/)/XHTML [polyglot markup](https://www.w3.org/TR/html-polyglot/))- - `html4` ([XHTML](https://www.w3.org/TR/xhtml1/) 1.0 Transitional)- - `icml` ([InDesign+- `html4` ([XHTML](https://www.w3.org/TR/xhtml1/) 1.0 Transitional)+- `icml` ([InDesign ICML](https://wwwimages.adobe.com/www.adobe.com/content/dam/acom/en/devnet/indesign/sdk/cs6/idml/idml-cookbook.pdf))- - `ipynb` ([Jupyter+- `ipynb` ([Jupyter notebook](https://nbformat.readthedocs.io/en/latest/))- - `jats_archiving` ([JATS](https://jats.nlm.nih.gov) XML, Archiving+- `jats_archiving` ([JATS](https://jats.nlm.nih.gov) XML, Archiving and Interchange Tag Set)- - `jats_articleauthoring` ([JATS](https://jats.nlm.nih.gov) XML,+- `jats_articleauthoring` ([JATS](https://jats.nlm.nih.gov) XML, Article Authoring Tag Set)- - `jats_publishing` ([JATS](https://jats.nlm.nih.gov) XML, Journal+- `jats_publishing` ([JATS](https://jats.nlm.nih.gov) XML, Journal Publishing Tag Set)- - `jats` (alias for `jats_archiving`)- - `jira`+- `jats` (alias for `jats_archiving`)+- `jira` ([Jira](https://jira.atlassian.com/secure/WikiRendererHelpAction.jspa?section=all)/Confluence wiki markup)- - `json` (JSON version of native AST)- - `latex` ([LaTeX](https://www.latex-project.org/))- - `man` ([roff man](https://man.cx/groff_man\(7\)))- - `markdown` ([Pandoc’s+- `json` (JSON version of native AST)+- `latex` ([LaTeX](https://www.latex-project.org/))+- `man` ([roff man](https://man.cx/groff_man(7)))+- `markdown` ([Pandoc’s Markdown](https://pandoc.org/MANUAL.html#pandocs-markdown))- - `markdown_mmd`+- `markdown_mmd` ([MultiMarkdown](https://fletcherpenney.net/multimarkdown/))- - `markdown_phpextra` ([PHP Markdown+- `markdown_phpextra` ([PHP Markdown Extra](https://michelf.ca/projects/php-markdown/extra/))- - `markdown_strict` (original unextended+- `markdown_strict` (original unextended [Markdown](https://daringfireball.net/projects/markdown/))- - `mediawiki` ([MediaWiki+- `mediawiki` ([MediaWiki markup](https://www.mediawiki.org/wiki/Help:Formatting))- - `ms` ([roff ms](https://man.cx/groff_ms\(7\)))- - `muse` ([Muse](https://amusewiki.org/library/manual)),- - `native` (native Haskell),- - `odt` ([OpenOffice text+- `ms` ([roff ms](https://man.cx/groff_ms(7)))+- `muse` ([Muse](https://amusewiki.org/library/manual)),+- `native` (native Haskell),+- `odt` ([OpenOffice text document](https://en.wikipedia.org/wiki/OpenDocument))- - `opml` ([OPML](http://dev.opml.org/spec2.html))- - `opendocument` ([OpenDocument](http://opendocument.xml.org))- - `org` ([Emacs Org mode](https://orgmode.org))- - `pdf` ([PDF](https://www.adobe.com/pdf/))- - `plain` (plain text),- - `pptx`+- `opml` ([OPML](http://dev.opml.org/spec2.html))+- `opendocument` ([OpenDocument](http://opendocument.xml.org))+- `org` ([Emacs Org mode](https://orgmode.org))+- `pdf` ([PDF](https://www.adobe.com/pdf/))+- `plain` (plain text),+- `pptx` ([PowerPoint](https://en.wikipedia.org/wiki/Microsoft_PowerPoint) slide show)- - `rst`+- `rst` ([reStructuredText](https://docutils.sourceforge.io/docs/ref/rst/introduction.html))- - `rtf` ([Rich Text+- `rtf` ([Rich Text Format](https://en.wikipedia.org/wiki/Rich_Text_Format))- - `texinfo` ([GNU Texinfo](https://www.gnu.org/software/texinfo/))- - `textile` ([Textile](https://www.promptworks.com/textile))- - `slideous` ([Slideous](https://goessner.net/articles/slideous/) HTML+- `texinfo` ([GNU Texinfo](https://www.gnu.org/software/texinfo/))+- `textile` ([Textile](https://www.promptworks.com/textile))+- `slideous` ([Slideous](https://goessner.net/articles/slideous/) HTML and JavaScript slide show)- - `slidy` ([Slidy](https://www.w3.org/Talks/Tools/Slidy2/) HTML and+- `slidy` ([Slidy](https://www.w3.org/Talks/Tools/Slidy2/) HTML and JavaScript slide show)- - `dzslides` ([DZSlides](http://paulrouget.com/dzslides/) HTML5 ++- `dzslides` ([DZSlides](http://paulrouget.com/dzslides/) HTML5 + JavaScript slide show),- - `revealjs` ([reveal.js](https://revealjs.com/) HTML5 + JavaScript+- `revealjs` ([reveal.js](https://revealjs.com/) HTML5 + JavaScript slide show)- - `s5` ([S5](https://meyerweb.com/eric/tools/s5/) HTML and JavaScript+- `s5` ([S5](https://meyerweb.com/eric/tools/s5/) HTML and JavaScript slide show)- - `tei` ([TEI Simple](https://github.com/TEIC/TEI-Simple))- - `xwiki` ([XWiki+- `tei` ([TEI Simple](https://github.com/TEIC/TEI-Simple))+- `xwiki` ([XWiki markup](https://www.xwiki.org/xwiki/bin/view/Documentation/UserGuide/Features/XWikiSyntax/))- - `zimwiki` ([ZimWiki+- `zimwiki` ([ZimWiki markup](https://zim-wiki.org/manual/Help/Wiki_Syntax.html))- - the path of a custom Lua writer, see [Custom+- the path of a custom Lua writer, see [Custom writers](https://pandoc.org/MANUAL.html#custom-writers) below </div>@@ -204,11 +210,13 @@ perfect, conversions from formats more expressive than pandoc’s Markdown can be expected to be lossy. -## Installing+Installing+---------- Here’s [how to install pandoc](INSTALL.md). -## Documentation+Documentation+------------- Pandoc’s website contains a full [User’s Guide](https://pandoc.org/MANUAL.html). It is also available@@ -217,13 +225,15 @@ pandoc](https://pandoc.org/demos.html) and a limited [online demo](https://pandoc.org/try). -## Contributing+Contributing+------------ Pull requests, bug reports, and feature requests are welcome. Please make sure to read [the contributor guidelines](CONTRIBUTING.md) before opening a new issue. -## License+License+------- © 2006-2020 John MacFarlane (jgm@berkeley.edu). Released under the [GPL](http://www.gnu.org/copyleft/gpl.html "GNU General Public License"),
benchmark/benchmark-pandoc.hs view
@@ -1,6 +1,5 @@ {-# LANGUAGE NoImplicitPrelude #-} {-# LANGUAGE OverloadedStrings #-}-{-# LANGUAGE TupleSections #-} {- Copyright (C) 2012-2019 John MacFarlane <jgm@berkeley.edu> @@ -21,39 +20,49 @@ import Prelude import Text.Pandoc import Text.Pandoc.MIME-import Text.Pandoc.Error (PandocError(..))-import Control.Monad.Except (throwError)+import Control.Monad.Except (throwError, liftIO) import qualified Text.Pandoc.UTF8 as UTF8 import qualified Data.ByteString as B import qualified Data.Text as T import Criterion.Main import Criterion.Types (Config(..)) import Data.List (intersect)-import Data.Maybe (mapMaybe)+import Data.Maybe (mapMaybe, catMaybes) import System.Environment (getArgs) import qualified Data.ByteString.Lazy as BL +data Input = InputText {unInputText :: T.Text}+ | InputBS {unInputBS :: BL.ByteString}+ readerBench :: Pandoc -> T.Text- -> Maybe Benchmark-readerBench doc name =- case res of- Right (readerFun, inp) ->- Just $ bench (T.unpack $ name <> " reader")- $ nf (\i -> either (error . show) id $ runPure (readerFun i))- inp- Left _ -> Nothing- where res = runPure $ do- (rdr, rexts) <- getReader name+ -> IO (Maybe Benchmark)+readerBench doc name = do+ let (rdr, rexts) = either (error . show) id . runPure $ getReader name+ res <- runIO $ do (wtr, wexts) <- getWriter name case (rdr, wtr) of (TextReader r, TextWriter w) -> do- setResourcePath ["../test"]+ setResourcePath ["./test"] inp <- w def{ writerWrapText = WrapAuto , writerExtensions = wexts } doc- return $ (r def{ readerExtensions = rexts }, inp)- _ -> throwError $ PandocSomeError $ "not a text format: "+ return (r def{ readerExtensions = rexts } . unInputText, InputText inp)+ (ByteStringReader r, ByteStringWriter w) -> do+ setResourcePath ["./test"]+ tmpl <- Just <$> compileDefaultTemplate name+ inp <- w def{ writerWrapText = WrapAuto+ , writerExtensions = wexts+ , writerTemplate = tmpl } doc+ liftIO $ BL.writeFile "/tmp/test.odt" inp+ return (r def{ readerExtensions = rexts } . unInputBS, InputBS inp)+ _ -> throwError $ PandocSomeError $ "text/bytestring format mismatch: " <> name+ return $ case res of+ Right (readerFun, inp) ->+ Just $ bench (T.unpack $ name <> " reader")+ $ nf (\i -> either (error . show) id $ runPure (readerFun i))+ inp+ Left _ -> Nothing getImages :: IO [(FilePath, MimeType, BL.ByteString)] getImages = do@@ -89,22 +98,23 @@ main = do args <- filter (\x -> T.take 1 x /= "-") . fmap T.pack <$> getArgs print args- let matchReader (n, TextReader _) =+ let matchReader (n, _) = null args || ("reader" `elem` args && n `elem` args)- matchReader _ = False- let matchWriter (n, TextWriter _) =+ matchWriter (n, TextWriter _) = null args || ("writer" `elem` args && n `elem` args) matchWriter _ = False- let matchedReaders = map fst $ (filter matchReader readers+ allWriters = map fst (writers :: [(T.Text, Writer PandocPure)])+ matchedReaders = map fst (filter matchReader readers :: [(T.Text, Reader PandocPure)])- let matchedWriters = map fst $ (filter matchWriter writers+ matchedWriters = map fst (filter matchWriter writers :: [(T.Text, Writer PandocPure)]) inp <- UTF8.toText <$> B.readFile "test/testsuite.txt" let opts = def let doc = either (error . show) id $ runPure $ readMarkdown opts inp- let readerBs = mapMaybe (readerBench doc)- $ filter (/="haddock")- (matchedReaders `intersect` matchedWriters)+ readerBs <- fmap catMaybes+ $ mapM (readerBench doc)+ $ filter (/="haddock")+ (matchedReaders `intersect` allWriters) -- we need the corresponding writer to generate -- input for the reader let writerBs = mapMaybe (writerBench doc) matchedWriters
cabal.project view
@@ -12,3 +12,8 @@ type: git location: https://github.com/jgm/pandoc-citeproc tag: 0.17.0.1++ source-repository-package+ type: git+ location: https://github.com/jgm/commonmark-hs+ tag: 8d4442abc443ce0100cc87af797e7df9a72b9b9a
changelog.md view
@@ -1,7 +1,170 @@ # Revision history for pandoc -## pandoc 2.10 (YYYY-MM-DD)+## pandoc 2.10.1 (2020-07-23) + * Add `commonmark_x` output format. This is `commonmark` with a number+ of useful pandoc extensions enabled.++ * Many more extensions now work with `commonmark` and `gfm`.++ * Add generic `attributes` extension. This allows attributes to+ be added to any block or inline element in a uniform way. Since+ the Pandoc AST doesn't include attributes on each element type,+ the attributes will sometimes be added by creating a surrounding+ Div or Span container. Currently this extension is only+ compatible with the `commonmark` and `gfm` readers.++ To add an attribute to a block-level element, e.g. a paragraph,+ put it before the block:+ ```+ {#mypara}+ This is a paragraph.+ ```+ Multiple attributes may be used and will be combined:+ ```+ {#mypara}+ {.blue .warning key="val"}+ This is a paragraph.+ ```+ To add an attribute to an inline-level element, put it+ immediately after the element:+ ```+ *emphasized text*{.special}+ ```++ * Support `--number-sections` for docx output (#1413).++ * LaTeX reader:++ + Support `\SIRange` reader (#6418, Emerson Harkin).+ + Support table col-span and row-span (#6311, Laurent P. René de Cotret).+ Supports `\multirow` and `\multicolumn`.+ + Support amsthm: `\newtheorem`, `\theoremstyle`, and theorem and+ proof environments, including labels and references. The only thing+ that is unsupported is the second optional argument, which causes+ numbering to be reset after the specified series is incremented.+ + Moved some code to T.P.LaTeX.Parsing. We need to reduce the size+ of the LaTeX reader to ease compilation on resource-limited systems.++ * RST reader:++ + Fix csv tables with multiline cells (#6549).+ + Fix spurious newlines in some attributes from directives.+ + Avoid extra newline in included code blocks.++ * Commonmark reader:++ + Switch from cmark-gfm to commonmark-hs for commonmark and gfm+ parsing. This avoids depending on a C library+ and allows us to support more pandoc extensions for+ `commonmark` and `gfm`.++ * DocBook reader:++ + Parse releaseinfo as metadata (#6542).++ * Docx reader:++ + Only use `bCs/iCs` on runs with `rtl` or `cs` property (#6514, Nikolay+ Yakimov).+ + Code cleanup/refactoring (Nikolay Yakimov).++ * Org reader (Albert Krewinkel):++ + Respect export setting which disables entities+ MathML-like entities, e.g., `\alpha`, can be disabled with the+ `#+OPTION: e:nil` export setting (Albert Krewinkel).+ + Respect export setting disabling footnotes. Footnotes can be removed+ from the final document with the `#+OPTION: f:nil` export setting.+ + Respect tables-excluding export setting. Tables can be removed from+ the final document with the `#+OPTION: |:nil` export setting.++ * Markdown writer:++ + Move `asciify` out of `escapeString`. Otherwise `unsmartify`+ doesn't catch quotes that have already been turned to entities.+ + Add `writeCommonmark` (new exported function, API change).+ + Use unicode super/subscript characters when possible if the+ `superscript` or `subscript` extension or `raw_html` aren't available.+ + Render caption as following paragraph when `table_caption` extension+ is not enabled.+ + Use numerical labels for reference links that are longer+ than 999 characters or contain square brackets, for conformity+ with commonmark (#6560).++ * Commonmark writer:++ + Instead of using cmark-gfm, use `writeCommonmark` from the+ Markdown writer. This function calls the markdown writer+ with appropriate extensions and a few small modifications+ (e.g. not requiring backslashes before spaces inside+ super/subscripts). With this change `comonmark` and+ `gfm` output can be used with a wider selection of+ extensions.++ * Jira writer: keep image caption as alt attribute (#6529, Albert+ Krewinkel).++ * HTML writer:++ + Improve alt-text/caption handling for HTML5 (#6491, Albert Krewinkel).+ Screen readers read an image's `alt` attribute and the figure caption,+ both of which come from the same source in pandoc. The figure caption is+ hidden from screen readers with the `aria-hidden` attribute. This+ improves accessibility. For HTML4, where `aria-hidden` is not allowed,+ pandoc still uses an empty `alt` attribute to avoid duplicate contents.++ * Ms writer:++ + Fix code highlighting with blank lines. Previously blank lines+ were simply omitted from highligted code.+ + Escape starting periods in ms writer code blocks (#6505, Michael+ Hoffmann). If a line of ms code block output starts with a period (.),+ it should be prepended by `\&` so that it is not interpreted as a roff+ command.++ * Text.Pandoc.Extensions:++ + Add `raw_markdown` extension (which only affects `ipynb`+ input).+ + Trim down `githubMarkdownExtensions`.+ Previously it included all of the following, which make+ sense for the legacy `markdown_github` but not for `gfm`,+ since they are part of base commonmark and thus+ can't be turned off in `gfm`:++ - `Ext_all_symbols_escapable`+ - `Ext_backtick_code_blocks`+ - `Ext_fenced_code_blocks`+ - `Ext_space_in_atx_header`+ - `Ext_intraword_underscores`+ - `Ext_lists_without_preceding_blankline`+ - `Ext_shortcut_reference_links`++ These have been removed from `githubMarkdownExtensions`, though+ they're still turned on for legacy `markdown_github`.+ + Add `Ext_attributes` constructor for `Extension` [API change].++ * LaTeX template: use selnolig to selectively suppress ligatures with+ lualatex (#6534).++ * Benchmark bytestring readers (Nikolay Yakimov).++ * Documentation:++ + Update using-the-pandoc-api.md (favonia).+ + Fix Typos in lua-filters.md (tajmone).+ + Rewrite Raw HTML/TeX section in MANUAL.txt to avoid duplicate+ headings for the extensions.+ + Fix typo in MANUAL.txt (Benjamin Wuethrich).+ + Remove duplicate 'titlepage' in MANUAL.txt (Blake Eryx).+ + CONTRIBUTING.md: Advertise the official nightlies in GitHub actions.+ Replaces #6500, thanks to @ickc.++++## pandoc 2.10 (2020-06-29)+ * Use pandoc-types 1.21. This adds two things: + A native Underline constructor for Inline (#6277, Vaibhav Sagar).@@ -154,6 +317,14 @@ * Ipynb reader: + + Implement `raw_markdown` extension (#5408). Specifying+ `-f ipynb+raw_markdown` will cause Markdown cells+ to be represented as raw Markdown blocks, instead of being+ parsed. This is not what you want when going from `ipynb`+ to other formats, but it may be useful when going from `ipynb`+ to Markdown or to `ipynb`, to avoid semantically insignificant+ changes in the contents of the Markdown cells that might+ otherwise be introduced. + Handle application/pdf output as image (#6430). + Properly handle image/svg+xml as an image (#6430).
data/docx/word/styles.xml view
@@ -414,6 +414,10 @@ <w:sz w:val="22" /> </w:rPr> </w:style>+ <w:style w:type="character" w:customStyle="1" w:styleId="SectionNumber">+ <w:name w:val="Section Number" />+ <w:basedOn w:val="BodyTextChar" />+ </w:style> <w:style w:type="character" w:styleId="FootnoteReference"> <w:name w:val="Footnote Reference" /> <w:basedOn w:val="BodyTextChar" />
data/templates/default.latex view
@@ -339,6 +339,9 @@ $endif$ \fi $endif$+\ifluatex+ \usepackage{selnolig} % disable illegal ligatures+\fi $if(dir)$ \ifxetex % Load bidi as late as possible as it modifies e.g. graphicx
man/pandoc.1 view
@@ -1,7 +1,7 @@ .\"t-.\" Automatically generated by Pandoc 2.10+.\" Automatically generated by Pandoc 2.10.1 .\"-.TH "Pandoc User\[aq]s Guide" "" "June 29, 2020" "pandoc 2.10" ""+.TH "Pandoc User\[aq]s Guide" "" "July 23, 2020" "pandoc 2.10.1" "" .hy .SH NAME pandoc - general markup converter@@ -229,6 +229,8 @@ .IP \[bu] 2 \f[C]commonmark\f[R] (CommonMark Markdown) .IP \[bu] 2+\f[C]commonmark_x\f[R] (CommonMark Markdown with extensions)+.IP \[bu] 2 \f[C]creole\f[R] (Creole 1.0) .IP \[bu] 2 \f[C]csv\f[R] (CSV table)@@ -313,6 +315,8 @@ .IP \[bu] 2 \f[C]commonmark\f[R] (CommonMark Markdown) .IP \[bu] 2+\f[C]commonmark_x\f[R] (CommonMark Markdown with extensions)+.IP \[bu] 2 \f[C]context\f[R] (ConTeXt) .IP \[bu] 2 \f[C]docbook\f[R] or \f[C]docbook4\f[R] (DocBook 4)@@ -936,7 +940,7 @@ If you\[aq]re behind a proxy, you also need to set the environment variable \f[C]http_proxy\f[R] to \f[C]http://...\f[R]. .TP-\[ga]--no-check-certificate+\f[B]\f[CB]--no-check-certificate\f[B]\f[R] Disable the certificate verification to allow access to unsecure HTTP resources (for example when the certificate is no longer valid or self signed).@@ -1017,7 +1021,7 @@ their default type. .TP \f[B]\f[CB]-N\f[B]\f[R], \f[B]\f[CB]--number-sections\f[B]\f[R]-Number section headings in LaTeX, ConTeXt, HTML, or EPUB output.+Number section headings in LaTeX, ConTeXt, HTML, Docx, or EPUB output. By default, sections are not numbered. Sections with class \f[C]unnumbered\f[R] will never be numbered, even if \f[C]--number-sections\f[R] is specified.@@ -1196,6 +1200,8 @@ Footnote Reference .IP \[bu] 2 Hyperlink+.IP \[bu] 2+Section Number .PP Table style: .IP \[bu] 2@@ -3131,20 +3137,18 @@ example. .SS Raw HTML/TeX .PP-The following extensions (especially how they affect Markdown-input/output) are also described in more detail in their respective-sections of Pandoc\[aq]s Markdown.-.SS Extension: \f[C]raw_html\f[R]-.PP-When converting from HTML, parse elements to raw HTML which are not-representable in pandoc\[aq]s AST.+The following extensions are described in more detail in their+respective sections of Pandoc\[aq]s Markdown:+.IP \[bu] 2+\f[C]raw_html\f[R] allows HTML elements which are not representable in+pandoc\[aq]s AST to be parsed as raw HTML. By default, this is disabled for HTML input.-.SS Extension: \f[C]raw_tex\f[R]-.PP-Allows raw LaTeX, TeX, and ConTeXt to be included in a document.-.PP+.IP \[bu] 2+\f[C]raw_tex\f[R] allows raw LaTeX, TeX, and ConTeXt to be included in a+document. This extension can be enabled/disabled for the following formats (in addition to \f[C]markdown\f[R]):+.RS 2 .TP input formats \f[C]latex\f[R], \f[C]org\f[R], \f[C]textile\f[R], \f[C]html\f[R]@@ -3162,24 +3166,20 @@ results if you disable \f[C]raw_html\f[R] and \f[C]raw_tex\f[R] when converting to formats like \f[C]docx\f[R] which don\[aq]t allow raw \f[C]html\f[R] or \f[C]tex\f[R].-.SS Extension: \f[C]native_divs\f[R]-.PP-This extension is enabled by default for HTML input.-This means that \f[C]div\f[R]s are parsed to pandoc native elements.-(Alternatively, you can parse them to raw HTML using-\f[C]-f html-native_divs+raw_html\f[R].)-.PP-When converting HTML to Markdown, for example, you may want to drop all-\f[C]div\f[R]s and \f[C]span\f[R]s:-.IP-.nf-\f[C]-pandoc -f html-native_divs-native_spans -t markdown-\f[R]-.fi-.SS Extension: \f[C]native_spans\f[R]-.PP-Analogous to \f[C]native_divs\f[R] above.+.RE+.IP \[bu] 2+\f[C]native_divs\f[R] causes HTML \f[C]div\f[R] elements to be parsed as+native pandoc Div blocks.+If you want them to be parsed as raw HTML, use+\f[C]-f html-native_divs+raw_html\f[R].+.IP \[bu] 2+\f[C]native_spans\f[R] causes HTML \f[C]span\f[R] elements to be parsed+as native pandoc Span inlines.+If you want them to be parsed as raw HTML, use+\f[C]-f html-native_spans+raw_html\f[R].+If you want to drop all \f[C]div\f[R]s and \f[C]span\f[R]s when+converting HTML to Markdown, you can use+\f[C]pandoc -f html-native_divs-native_spans -t markdown\f[R]. .SS Literate Haskell support .SS Extension: \f[C]literate_haskell\f[R] .PP@@ -3289,6 +3289,13 @@ .PP In the \f[C]muse\f[R] input format, this enables Text::Amuse extensions to Emacs Muse markup.+.SS Extension: \f[C]raw_markdown\f[R]+.PP+In the \f[C]ipynb\f[R] input format, this causes Markdown cells to be+included as raw Markdown blocks (allowing lossless round-tripping)+rather than being parsed.+Use this only when you are targetting \f[C]ipynb\f[R] or a+markdown-based output format. .SS Extension: \f[C]citations\f[R] .PP Some aspects of Pandoc\[aq]s Markdown citation syntax are also accepted@@ -5909,6 +5916,39 @@ name, where \f[C]EXTENSION\f[R] is the name of the extension. Thus, for example, \f[C]markdown+hard_line_breaks\f[R] is Markdown with hard line breaks.+.SS Extension: \f[C]attributes\f[R]+.PP+Allows attributes to be attached to any inline or block-level element.+The syntax for the attributes is the same as that used in+\f[C]header_attributes\f[R].+.IP \[bu] 2+Attributes that occur immediately after an inline element affect that+element.+If they follow a space, then they belong to the space.+(Hence, this option subsumes \f[C]inline_code_attributes\f[R] and+\f[C]link_attributes\f[R].)+.IP \[bu] 2+Attributes that occur immediately before a block element, on a line by+themselves, affect that element.+.IP \[bu] 2+Consecutive attribute specifiers may be used, either for blocks or for+inlines.+Their attributes will be combined.+.IP \[bu] 2+Attributes that occur at the end of the text of a Setext or ATX heading+(separated by whitespace from the text) affect the heading element.+(Hence, this option subsumes \f[C]header_attributes\f[R].)+.IP \[bu] 2+Attributes that occur after the opening fence in a fenced code block+affect the code block element.+(Hence, this option subsumes \f[C]fenced_code_attributes\f[R].)+.IP \[bu] 2+Attributes that occur at the end of a reference link definition affect+links that refer to that definition.+.PP+Note that pandoc\[aq]s AST does not currently allow attributes to be+attached to arbitrary elements.+Hence a Span or Div container will be added if needed. .SS Extension: \f[C]old_dashes\f[R] .PP Selects the pandoc <= 1.8.2.1 behavior for parsing smart dashes:@@ -6105,11 +6145,12 @@ Also, \f[C]raw_tex\f[R] only affects \f[C]gfm\f[R] output, not input. .TP \f[B]\f[CB]gfm\f[B]\f[R] (GitHub-Flavored Markdown)-\f[C]pipe_tables\f[R], \f[C]raw_html\f[R], \f[C]fenced_code_blocks\f[R],-\f[C]auto_identifiers\f[R], \f[C]gfm_auto_identifiers\f[R],-\f[C]backtick_code_blocks\f[R], \f[C]autolink_bare_uris\f[R],-\f[C]space_in_atx_header\f[R], \f[C]intraword_underscores\f[R],-\f[C]strikeout\f[R], \f[C]task_lists\f[R], \f[C]emoji\f[R],+\f[C]pipe_tables\f[R], \f[C]raw_html\f[R], \f[C]native_divs\f[R],+\f[C]fenced_code_blocks\f[R], \f[C]auto_identifiers\f[R],+\f[C]gfm_auto_identifiers\f[R], \f[C]backtick_code_blocks\f[R],+\f[C]autolink_bare_uris\f[R], \f[C]space_in_atx_header\f[R],+\f[C]intraword_underscores\f[R], \f[C]strikeout\f[R],+\f[C]task_lists\f[R], \f[C]emoji\f[R], \f[C]shortcut_reference_links\f[R], \f[C]angle_brackets_escapable\f[R], \f[C]lists_without_preceding_blankline\f[R]. .SH PRODUCING SLIDE SHOWS WITH PANDOC@@ -6778,11 +6819,6 @@ T} T{ seriespage-T}@T{-frontmatter-T}-T{-titlepage T}@T{ frontmatter T}
pandoc.cabal view
@@ -1,6 +1,6 @@ cabal-version: 2.2 name: pandoc-version: 2.10+version: 2.10.1 build-type: Simple license: GPL-2.0-or-later license-file: COPYING.md@@ -11,7 +11,7 @@ stability: alpha homepage: https://pandoc.org category: Text-tested-with: GHC == 8.0.2, GHC == 8.2.2, GHC == 8.4.4, GHC == 8.6.5,+tested-with: GHC == 8.2.2, GHC == 8.4.4, GHC == 8.6.5, GHC == 8.8.3, GHC == 8.10.1 synopsis: Conversion between markup formats description: Pandoc is a Haskell library for converting from one markup@@ -205,6 +205,7 @@ test/command/B.txt test/command/C.txt test/command/D.txt+ test/command/01.csv test/command/defaults1.yaml test/command/defaults2.yaml test/command/3533-rst-csv-tables.csv@@ -421,8 +422,10 @@ deepseq >= 1.3 && < 1.5, JuicyPixels >= 3.1.6.1 && < 3.4, Glob >= 0.7 && < 0.11,- cmark-gfm >= 0.2 && < 0.3, doctemplates >= 0.8.2 && < 0.9,+ commonmark-pandoc >= 0.2 && < 0.3,+ commonmark >= 0.1.0.1 && < 0.2,+ commonmark-extensions >= 0.2 && < 0.3, network-uri >= 2.6 && < 2.7, network >= 2.6, connection >= 0.3.1,@@ -816,6 +819,7 @@ Tests.Writers.FB2 Tests.Writers.Powerpoint Tests.Writers.OOXML+ Tests.Writers.Ms if os(windows) cpp-options: -D_WINDOWS default-language: Haskell2010
src/Text/Pandoc/Extensions.hs view
@@ -133,6 +133,7 @@ | Ext_raw_attribute -- ^ Allow explicit raw blocks/inlines | Ext_raw_html -- ^ Allow raw HTML | Ext_raw_tex -- ^ Allow raw TeX (other than math)+ | Ext_raw_markdown -- ^ Parse markdown in ipynb as raw markdown | Ext_shortcut_reference_links -- ^ Shortcut reference links | Ext_simple_tables -- ^ Pandoc-style simple tables | Ext_smart -- ^ "Smart" quotes, apostrophes, ellipses, dashes@@ -150,6 +151,7 @@ | Ext_tex_math_single_backslash -- ^ TeX math btw \(..\) \[..\] | Ext_yaml_metadata_block -- ^ YAML metadata block | Ext_gutenberg -- ^ Use Project Gutenberg conventions for plain+ | Ext_attributes -- ^ Generic attribute syntax deriving (Show, Read, Enum, Eq, Ord, Bounded, Data, Typeable, Generic) -- | Extensions to be used with pandoc-flavored markdown.@@ -242,21 +244,15 @@ -- | Extensions to be used with github-flavored markdown. githubMarkdownExtensions :: Extensions githubMarkdownExtensions = extensionsFromList- [ Ext_all_symbols_escapable- , Ext_pipe_tables+ [ Ext_pipe_tables , Ext_raw_html- , Ext_fenced_code_blocks+ , Ext_native_divs , Ext_auto_identifiers , Ext_gfm_auto_identifiers- , Ext_backtick_code_blocks , Ext_autolink_bare_uris- , Ext_space_in_atx_header- , Ext_intraword_underscores , Ext_strikeout , Ext_task_lists , Ext_emoji- , Ext_lists_without_preceding_blankline- , Ext_shortcut_reference_links ] -- | Extensions to be used with multimarkdown.@@ -308,7 +304,16 @@ getDefaultExtensions "markdown_strict" = strictExtensions getDefaultExtensions "markdown_phpextra" = phpMarkdownExtraExtensions getDefaultExtensions "markdown_mmd" = multimarkdownExtensions-getDefaultExtensions "markdown_github" = githubMarkdownExtensions+getDefaultExtensions "markdown_github" = githubMarkdownExtensions <>+ extensionsFromList+ [ Ext_all_symbols_escapable+ , Ext_backtick_code_blocks+ , Ext_fenced_code_blocks+ , Ext_space_in_atx_header+ , Ext_intraword_underscores+ , Ext_lists_without_preceding_blankline+ , Ext_shortcut_reference_links+ ] getDefaultExtensions "markdown" = pandocExtensions getDefaultExtensions "ipynb" = extensionsFromList@@ -335,6 +340,29 @@ getDefaultExtensions "gfm" = githubMarkdownExtensions getDefaultExtensions "commonmark" = extensionsFromList [Ext_raw_html]+getDefaultExtensions "commonmark_x" = extensionsFromList+ [ Ext_pipe_tables+ , Ext_raw_html+ , Ext_auto_identifiers+ , Ext_strikeout+ , Ext_task_lists+ , Ext_emoji+ , Ext_pipe_tables+ , Ext_raw_html+ , Ext_raw_tex -- only supported in writer (for math)+ , Ext_smart+ , Ext_tex_math_dollars+ , Ext_superscript+ , Ext_subscript+ , Ext_definition_lists+ , Ext_footnotes+ , Ext_fancy_lists+ , Ext_fenced_divs+ , Ext_bracketed_spans+ , Ext_raw_attribute+ , Ext_implicit_header_references+ , Ext_attributes+ ] getDefaultExtensions "org" = extensionsFromList [Ext_citations, Ext_auto_identifiers]@@ -415,7 +443,8 @@ getAll "markdown_mmd" = allMarkdownExtensions getAll "markdown_github" = allMarkdownExtensions getAll "markdown" = allMarkdownExtensions- getAll "ipynb" = allMarkdownExtensions+ getAll "ipynb" = allMarkdownExtensions <> extensionsFromList+ [ Ext_raw_markdown ] getAll "docx" = extensionsFromList [ Ext_empty_paragraphs , Ext_styles@@ -430,16 +459,32 @@ [ Ext_amuse ] getAll "asciidoc" = autoIdExtensions getAll "plain" = allMarkdownExtensions- getAll "gfm" = githubMarkdownExtensions <>+ getAll "gfm" = getAll "commonmark"+ getAll "commonmark" = autoIdExtensions <> extensionsFromList- [ Ext_raw_html+ [ Ext_pipe_tables+ , Ext_autolink_bare_uris+ , Ext_strikeout+ , Ext_task_lists+ , Ext_emoji+ , Ext_raw_html , Ext_raw_tex -- only supported in writer (for math) , Ext_implicit_figures , Ext_hard_line_breaks , Ext_smart+ , Ext_tex_math_dollars+ , Ext_superscript+ , Ext_subscript+ , Ext_definition_lists+ , Ext_footnotes+ , Ext_fancy_lists+ , Ext_fenced_divs+ , Ext_bracketed_spans+ , Ext_raw_attribute+ , Ext_implicit_header_references+ , Ext_attributes ]- getAll "commonmark" = getAll "gfm" getAll "org" = autoIdExtensions <> extensionsFromList [ Ext_citations
src/Text/Pandoc/Readers.hs view
@@ -111,6 +111,7 @@ ,("markdown_github" , TextReader readMarkdown) ,("markdown_mmd", TextReader readMarkdown) ,("commonmark" , TextReader readCommonMark)+ ,("commonmark_x" , TextReader readCommonMark) ,("creole" , TextReader readCreole) ,("dokuwiki" , TextReader readDokuWiki) ,("gfm" , TextReader readCommonMark)
src/Text/Pandoc/Readers/CommonMark.hs view
@@ -1,4 +1,5 @@ {-# LANGUAGE OverloadedStrings #-}+{-# LANGUAGE ScopedTypeVariables #-} {-# LANGUAGE ViewPatterns #-} {- | Module : Text.Pandoc.Readers.CommonMark@@ -16,209 +17,50 @@ module Text.Pandoc.Readers.CommonMark (readCommonMark) where -import CMarkGFM-import Control.Monad.State-import qualified Data.Set as Set+import Commonmark+import Commonmark.Extensions+import Commonmark.Pandoc import Data.Text (Text)-import qualified Data.Text as T import Text.Pandoc.Class.PandocMonad (PandocMonad) import Text.Pandoc.Definition-import Text.Pandoc.Emoji (emojiToInline)+import Text.Pandoc.Builder as B import Text.Pandoc.Options-import Text.Pandoc.Shared (uniqueIdent, taskListItemFromAscii)-import Text.Pandoc.Walk (walkM)+import Text.Pandoc.Error+import Control.Monad.Except+import Data.Functor.Identity (runIdentity) -- | Parse a CommonMark formatted string into a 'Pandoc' structure. readCommonMark :: PandocMonad m => ReaderOptions -> Text -> m Pandoc-readCommonMark opts s = return $- (if isEnabled Ext_auto_identifiers opts- then addHeaderIdentifiers opts- else id) $- nodeToPandoc opts $ commonmarkToNode opts' exts s- where opts' = [ optSmart | isEnabled Ext_smart opts ]- exts = [ extStrikethrough | isEnabled Ext_strikeout opts ] ++- [ extTable | isEnabled Ext_pipe_tables opts ] ++- [ extAutolink | isEnabled Ext_autolink_bare_uris opts ]--convertEmojis :: Text -> [Inline]-convertEmojis s@(T.uncons -> Just (':',xs)) =- case T.break (==':') xs of- (ys, T.uncons -> Just (':',zs)) ->- case emojiToInline ys of- Just em -> em : convertEmojis zs- Nothing -> Str (":" <> ys) : convertEmojis (":" <> zs)- _ -> [Str s]-convertEmojis s =- case T.break (==':') s of- ("","") -> []- (_,"") -> [Str s]- (xs,ys) -> Str xs : convertEmojis ys--addHeaderIdentifiers :: ReaderOptions -> Pandoc -> Pandoc-addHeaderIdentifiers opts doc = evalState (walkM (addHeaderId opts) doc) mempty--addHeaderId :: ReaderOptions -> Block -> State (Set.Set Text) Block-addHeaderId opts (Header lev (_,classes,kvs) ils) = do- ids <- get- let ident = uniqueIdent (readerExtensions opts) ils ids- modify (Set.insert ident)- return $ Header lev (ident,classes,kvs) ils-addHeaderId _ x = return x--nodeToPandoc :: ReaderOptions -> Node -> Pandoc-nodeToPandoc opts (Node _ DOCUMENT nodes) =- Pandoc nullMeta $ foldr (addBlock opts) [] nodes-nodeToPandoc opts n = -- shouldn't happen- Pandoc nullMeta $ foldr (addBlock opts) [] [n]--addBlocks :: ReaderOptions -> [Node] -> [Block]-addBlocks opts = foldr (addBlock opts) []--addBlock :: ReaderOptions -> Node -> [Block] -> [Block]-addBlock opts (Node _ PARAGRAPH nodes) =- case addInlines opts nodes of- [Image attr alt (src,tit)]- | isEnabled Ext_implicit_figures opts- -- the "fig:" prefix indicates an implicit figure- -> (Para [Image attr alt (src, "fig:" <> tit)] :)- ils -> (Para ils :)-addBlock _ (Node _ THEMATIC_BREAK _) =- (HorizontalRule :)-addBlock opts (Node _ BLOCK_QUOTE nodes) =- (BlockQuote (addBlocks opts nodes) :)-addBlock opts (Node _ (HTML_BLOCK t) _)- | isEnabled Ext_raw_html opts = (RawBlock (Format "html") t :)- | otherwise = id--- Note: the cmark parser will never generate CUSTOM_BLOCK,--- so we don't need to handle it:-addBlock _ (Node _ (CUSTOM_BLOCK _onEnter _onExit) _nodes) =- id-addBlock _ (Node _ (CODE_BLOCK info t) _) =- (CodeBlock ("", take 1 (T.words info), []) t :)-addBlock opts (Node _ (HEADING lev) nodes) =- (Header lev ("",[],[]) (addInlines opts nodes) :)-addBlock opts (Node _ (LIST listAttrs) nodes) =- (constructor (map listItem nodes) :)- where constructor = case listType listAttrs of- BULLET_LIST -> BulletList- ORDERED_LIST -> OrderedList- (start, DefaultStyle, delim)- start = listStart listAttrs- listItem = taskListItemFromAscii exts . setTightness- . addBlocks opts . children- setTightness = if listTight listAttrs- then map paraToPlain- else id- paraToPlain (Para xs) = Plain xs- paraToPlain x = x- delim = case listDelim listAttrs of- PERIOD_DELIM -> Period- PAREN_DELIM -> OneParen- exts = readerExtensions opts-addBlock opts (Node _ (TABLE alignments) nodes) =- (Table- nullAttr- (Caption Nothing [])- (zip aligns widths)- (TableHead nullAttr headers)- [TableBody nullAttr 0 [] rows]- (TableFoot nullAttr []) :)- where aligns = map fromTableCellAlignment alignments- fromTableCellAlignment NoAlignment = AlignDefault- fromTableCellAlignment LeftAligned = AlignLeft- fromTableCellAlignment RightAligned = AlignRight- fromTableCellAlignment CenterAligned = AlignCenter- widths = replicate numcols ColWidthDefault- numcols = if null rows'- then 0- else maximum $ map rowLength rows'- rows' = map toRow $ filter isRow nodes- (headers, rows) = case rows' of- (h:rs) -> ([h], rs)- [] -> ([], [])- isRow (Node _ TABLE_ROW _) = True- isRow _ = False- isCell (Node _ TABLE_CELL _) = True- isCell _ = False- toRow (Node _ TABLE_ROW ns) = Row nullAttr $ map toCell $ filter isCell ns- toRow (Node _ t _) = error $ "toRow encountered non-row " ++ show t- toCell (Node _ TABLE_CELL []) = fromSimpleCell []- toCell (Node _ TABLE_CELL (n:ns))- | isBlockNode n = fromSimpleCell $ addBlocks opts (n:ns)- | otherwise = fromSimpleCell [Plain (addInlines opts (n:ns))]- toCell (Node _ t _) = error $ "toCell encountered non-cell " ++ show t- fromSimpleCell = Cell nullAttr AlignDefault 1 1- rowLength (Row _ body) = length body -- all cells are 1×1-addBlock _ (Node _ TABLE_ROW _) = id -- handled in TABLE-addBlock _ (Node _ TABLE_CELL _) = id -- handled in TABLE-addBlock _ _ = id--isBlockNode :: Node -> Bool-isBlockNode (Node _ nodetype _) =- case nodetype of- DOCUMENT -> True- THEMATIC_BREAK -> True- PARAGRAPH -> True- BLOCK_QUOTE -> True- HTML_BLOCK _ -> True- CUSTOM_BLOCK _ _ -> True- CODE_BLOCK _ _ -> True- HEADING _ -> True- LIST _ -> True- ITEM -> True- TEXT _ -> False- SOFTBREAK -> False- LINEBREAK -> False- HTML_INLINE _ -> False- CUSTOM_INLINE _ _ -> False- CODE _ -> False- EMPH -> False- STRONG -> False- LINK _ _ -> False- IMAGE _ _ -> False- STRIKETHROUGH -> False- TABLE _ -> False- TABLE_ROW -> False- TABLE_CELL -> False--children :: Node -> [Node]-children (Node _ _ ns) = ns--addInlines :: ReaderOptions -> [Node] -> [Inline]-addInlines opts = foldr (addInline opts) []+readCommonMark opts s = do+ let res = runIdentity $+ commonmarkWith (foldr (<>) defaultSyntaxSpec exts) "input" s+ case res of+ Left err -> throwError $ PandocParsecError s err+ Right (Cm bls :: Cm () Blocks) -> return $ B.doc bls+ where+ exts = [ hardLineBreaksSpec | isEnabled Ext_hard_line_breaks opts ] +++ [ smartPunctuationSpec | isEnabled Ext_smart opts ] +++ [ strikethroughSpec | isEnabled Ext_strikeout opts ] +++ [ superscriptSpec | isEnabled Ext_superscript opts ] +++ [ subscriptSpec | isEnabled Ext_subscript opts ] +++ [ mathSpec | isEnabled Ext_tex_math_dollars opts ] +++ [ fancyListSpec | isEnabled Ext_fancy_lists opts ] +++ [ fencedDivSpec | isEnabled Ext_fenced_divs opts ] +++ [ bracketedSpanSpec | isEnabled Ext_bracketed_spans opts ] +++ [ rawAttributeSpec | isEnabled Ext_raw_attribute opts ] +++ [ attributesSpec | isEnabled Ext_attributes opts ] +++ [ pipeTableSpec | isEnabled Ext_pipe_tables opts ] +++ [ autolinkSpec | isEnabled Ext_autolink_bare_uris opts ] +++ [ emojiSpec | isEnabled Ext_emoji opts ] +++ [ autoIdentifiersSpec+ | isEnabled Ext_gfm_auto_identifiers opts+ , not (isEnabled Ext_ascii_identifiers opts) ] +++ [ autoIdentifiersAsciiSpec+ | isEnabled Ext_gfm_auto_identifiers opts+ , isEnabled Ext_ascii_identifiers opts ] +++ [ implicitHeadingReferencesSpec+ | isEnabled Ext_implicit_header_references opts ] +++ [ footnoteSpec | isEnabled Ext_footnotes opts ] +++ [ definitionListSpec | isEnabled Ext_definition_lists opts ] +++ [ taskListSpec | isEnabled Ext_task_lists opts ] -addInline :: ReaderOptions -> Node -> [Inline] -> [Inline]-addInline opts (Node _ (TEXT t) _) = (concatMap toinl clumps ++)- where clumps = T.groupBy samekind t- samekind ' ' ' ' = True- samekind ' ' _ = False- samekind _ ' ' = False- samekind _ _ = True- toinl (T.uncons -> Just (' ', _)) = [Space]- toinl xs = if isEnabled Ext_emoji opts- then convertEmojis xs- else [Str xs]-addInline _ (Node _ LINEBREAK _) = (LineBreak :)-addInline opts (Node _ SOFTBREAK _)- | isEnabled Ext_hard_line_breaks opts = (LineBreak :)- | otherwise = (SoftBreak :)-addInline opts (Node _ (HTML_INLINE t) _)- | isEnabled Ext_raw_html opts = (RawInline (Format "html") t :)- | otherwise = id--- Note: the cmark parser will never generate CUSTOM_BLOCK,--- so we don't need to handle it:-addInline _ (Node _ (CUSTOM_INLINE _onEnter _onExit) _nodes) =- id-addInline _ (Node _ (CODE t) _) =- (Code ("",[],[]) t :)-addInline opts (Node _ EMPH nodes) =- (Emph (addInlines opts nodes) :)-addInline opts (Node _ STRONG nodes) =- (Strong (addInlines opts nodes) :)-addInline opts (Node _ STRIKETHROUGH nodes) =- (Strikeout (addInlines opts nodes) :)-addInline opts (Node _ (LINK url title) nodes) =- (Link nullAttr (addInlines opts nodes) (url, title) :)-addInline opts (Node _ (IMAGE url title) nodes) =- (Image nullAttr (addInlines opts nodes) (url, title) :)-addInline _ _ = id
src/Text/Pandoc/Readers/DocBook.hs view
@@ -360,7 +360,7 @@ [x] refsectioninfo - Meta-information for a refsection [ ] refsynopsisdiv - A syntactic synopsis of the subject of the reference page [ ] refsynopsisdivinfo - Meta-information for a RefSynopsisDiv-[x] releaseinfo - Information about a particular release of a document+[ ] releaseinfo - Information about a particular release of a document [ ] remark - A remark (or comment) intended for presentation in a draft manuscript [x] replaceable - Content that may or must be replaced by the user@@ -608,6 +608,7 @@ addMetaField "author" e addMetaField "date" e addMetaField "release" e+ addMetaField "releaseinfo" e return mempty where addMetaField fieldname elt = case filterChildren (named fieldname) elt of
src/Text/Pandoc/Readers/Docx.hs view
@@ -261,47 +261,44 @@ | otherwise = return rPr runStyleToTransform :: PandocMonad m => RunStyle -> DocxContext m (Inlines -> Inlines)-runStyleToTransform rPr- | Just sn <- getStyleName <$> rParentStyle rPr- , sn `elem` spansToKeep = do- transform <- runStyleToTransform rPr{rParentStyle = Nothing}- return $ spanWith ("", [normalizeToClassName sn], []) . transform- | Just s <- rParentStyle rPr = do- ei <- extraInfo spanWith s- transform <- runStyleToTransform rPr{rParentStyle = Nothing}- return $ ei . transform- | Just True <- isItalic rPr = do- transform <- runStyleToTransform rPr{isItalic = Nothing}- return $ emph . transform- | Just True <- isBold rPr = do- transform <- runStyleToTransform rPr{isBold = Nothing}- return $ strong . transform- | Just True <- isSmallCaps rPr = do- transform <- runStyleToTransform rPr{isSmallCaps = Nothing}- return $ smallcaps . transform- | Just True <- isStrike rPr = do- transform <- runStyleToTransform rPr{isStrike = Nothing}- return $ strikeout . transform- | Just True <- isRTL rPr = do- transform <- runStyleToTransform rPr{isRTL = Nothing}- return $ spanWith ("",[],[("dir","rtl")]) . transform- | Just False <- isRTL rPr = do- transform <- runStyleToTransform rPr{isRTL = Nothing}- inBidi <- asks docxInBidi- return $ if inBidi- then spanWith ("",[],[("dir","ltr")]) . transform- else transform- | Just SupScrpt <- rVertAlign rPr = do- transform <- runStyleToTransform rPr{rVertAlign = Nothing}- return $ superscript . transform- | Just SubScrpt <- rVertAlign rPr = do- transform <- runStyleToTransform rPr{rVertAlign = Nothing}- return $ subscript . transform- | Just "single" <- rUnderline rPr = do- transform <- runStyleToTransform rPr{rUnderline = Nothing}- return $ Pandoc.underline . transform- | otherwise = return id+runStyleToTransform rPr' = do+ opts <- asks docxOptions+ inBidi <- asks docxInBidi+ let styles = isEnabled Ext_styles opts+ ctl = (Just True == isRTL rPr') || (Just True == isForceCTL rPr')+ italic rPr | ctl = isItalicCTL rPr+ | otherwise = isItalic rPr+ bold rPr | ctl = isBoldCTL rPr+ | otherwise = isBold rPr+ go rPr+ | Just sn <- getStyleName <$> rParentStyle rPr+ , sn `elem` spansToKeep =+ spanWith ("", [normalizeToClassName sn], [])+ . go rPr{rParentStyle = Nothing}+ | styles, Just s <- rParentStyle rPr =+ spanWith (extraAttr s) . go rPr{rParentStyle = Nothing}+ | Just True <- italic rPr =+ emph . go rPr{isItalic = Nothing, isItalicCTL = Nothing}+ | Just True <- bold rPr =+ strong . go rPr{isBold = Nothing, isBoldCTL = Nothing}+ | Just True <- isSmallCaps rPr =+ smallcaps . go rPr{isSmallCaps = Nothing}+ | Just True <- isStrike rPr =+ strikeout . go rPr{isStrike = Nothing}+ | Just True <- isRTL rPr =+ spanWith ("",[],[("dir","rtl")]) . go rPr{isRTL = Nothing}+ | inBidi, Just False <- isRTL rPr =+ spanWith ("",[],[("dir","ltr")]) . go rPr{isRTL = Nothing}+ | Just SupScrpt <- rVertAlign rPr =+ superscript . go rPr{rVertAlign = Nothing}+ | Just SubScrpt <- rVertAlign rPr = do+ subscript . go rPr{rVertAlign = Nothing}+ | Just "single" <- rUnderline rPr = do+ Pandoc.underline . go rPr{rUnderline = Nothing}+ | otherwise = id+ return $ go rPr' + runToInlines :: PandocMonad m => Run -> DocxContext m Inlines runToInlines (Run rs runElems) | maybe False isCodeCharStyle $ rParentStyle rs = do@@ -512,13 +509,8 @@ isSp LineBreak = True isSp _ = False -extraInfo :: (Eq (StyleName a), PandocMonad m, HasStyleName a)- => (Attr -> i -> i) -> a -> DocxContext m (i -> i)-extraInfo f s = do- opts <- asks docxOptions- return $ if isEnabled Ext_styles opts- then f ("", [], [("custom-style", fromStyleName $ getStyleName s)])- else id+extraAttr :: (Eq (StyleName a), HasStyleName a) => a -> Attr+extraAttr s = ("", [], [("custom-style", fromStyleName $ getStyleName s)]) parStyleToTransform :: PandocMonad m => ParagraphStyle -> DocxContext m (Blocks -> Blocks) parStyleToTransform pPr = case pStyle pPr of@@ -534,8 +526,11 @@ | otherwise -> do let pPr' = pPr { pStyle = cs } transform <- parStyleToTransform pPr'- ei <- extraInfo divWith c- return $ ei . (if isBlockQuote c then blockQuote else id) . transform+ styles <- asks (isEnabled Ext_styles . docxOptions)+ return $+ (if styles then divWith (extraAttr c) else id)+ . (if isBlockQuote c then blockQuote else id)+ . transform [] | Just left <- indentation pPr >>= leftParIndent -> do let pPr' = pPr { indentation = Nothing }
src/Text/Pandoc/Readers/Docx/Combine.hs view
@@ -1,10 +1,9 @@-{-# LANGUAGE FlexibleInstances #-}-{-# LANGUAGE PatternGuards #-} {-# LANGUAGE OverloadedStrings #-} {- | Module : Text.Pandoc.Readers.Docx.Combine Copyright : © 2014-2020 Jesse Rosenthal <jrosenthal@jhu.edu>,- 2014-2020 John MacFarlane <jgm@berkeley.edu>+ 2014-2020 John MacFarlane <jgm@berkeley.edu>,+ 2020 Nikolay Yakimov <root@livid.pp.ru> License : GNU GPL, version 2 or above Maintainer : Jesse Rosenthal <jrosenthal@jhu.edu>@@ -59,79 +58,61 @@ where import Data.List-import Data.Sequence (ViewL (..), ViewR (..), viewl, viewr, (><), (|>))-import qualified Data.Sequence as Seq (null)+import Data.Bifunctor+import Data.Sequence ( ViewL (..), ViewR (..), viewl, viewr, spanr, spanl+ , (><), (|>) ) import Text.Pandoc.Builder data Modifier a = Modifier (a -> a) | AttrModifier (Attr -> a -> a) Attr- | NullModifier spaceOutInlinesL :: Inlines -> (Inlines, Inlines) spaceOutInlinesL ms = (l, stackInlines fs (m' <> r))- where (l, m, r) = spaceOutInlines ms- (fs, m') = unstackInlines m+ where (l, (fs, m'), r) = spaceOutInlines ms spaceOutInlinesR :: Inlines -> (Inlines, Inlines) spaceOutInlinesR ms = (stackInlines fs (l <> m'), r)- where (l, m, r) = spaceOutInlines ms- (fs, m') = unstackInlines m+ where (l, (fs, m'), r) = spaceOutInlines ms -spaceOutInlines :: Inlines -> (Inlines, Inlines, Inlines)+spaceOutInlines :: Inlines -> (Inlines, ([Modifier Inlines], Inlines), Inlines) spaceOutInlines ils = let (fs, ils') = unstackInlines ils- contents = unMany ils'- left = case viewl contents of- (Space :< _) -> space- _ -> mempty- right = case viewr contents of- (_ :> Space) -> space- _ -> mempty in- (left, stackInlines fs $ trimInlines . Many $ contents, right)+ (left, (right, contents')) = second (spanr isSpace) $ spanl isSpace $ unMany ils'+ -- NOTE: spanr counterintuitively returns suffix as the FIRST tuple element+ in (Many left, (fs, Many contents'), Many right) +isSpace :: Inline -> Bool+isSpace Space = True+isSpace SoftBreak = True+isSpace _ = False+ stackInlines :: [Modifier Inlines] -> Inlines -> Inlines stackInlines [] ms = ms-stackInlines (NullModifier : fs) ms = stackInlines fs ms stackInlines (Modifier f : fs) ms =- if isEmpty ms+ if null ms then stackInlines fs ms else f $ stackInlines fs ms stackInlines (AttrModifier f attr : fs) ms = f attr $ stackInlines fs ms unstackInlines :: Inlines -> ([Modifier Inlines], Inlines)-unstackInlines ms = case ilModifier ms of- NullModifier -> ([], ms)- _ -> (f : fs, ms') where- f = ilModifier ms- (fs, ms') = unstackInlines $ ilInnards ms--ilModifier :: Inlines -> Modifier Inlines-ilModifier ils = case viewl (unMany ils) of- (x :< xs) | Seq.null xs -> case x of- (Emph _) -> Modifier emph- (Strong _) -> Modifier strong- (SmallCaps _) -> Modifier smallcaps- (Strikeout _) -> Modifier strikeout- (Superscript _) -> Modifier superscript- (Subscript _) -> Modifier subscript- (Link attr _ tgt) -> Modifier $ linkWith attr (fst tgt) (snd tgt)- (Span attr _) -> AttrModifier spanWith attr- _ -> NullModifier- _ -> NullModifier+unstackInlines ms = case ilModifierAndInnards ms of+ Nothing -> ([], ms)+ Just (f, inner) -> first (f :) $ unstackInlines inner -ilInnards :: Inlines -> Inlines-ilInnards ils = case viewl (unMany ils) of- (x :< xs) | Seq.null xs -> case x of- (Emph lst) -> fromList lst- (Strong lst) -> fromList lst- (SmallCaps lst) -> fromList lst- (Strikeout lst) -> fromList lst- (Superscript lst) -> fromList lst- (Subscript lst) -> fromList lst- (Link _ lst _) -> fromList lst- (Span _ lst) -> fromList lst- _ -> ils- _ -> ils+ilModifierAndInnards :: Inlines -> Maybe (Modifier Inlines, Inlines)+ilModifierAndInnards ils = case viewl $ unMany ils of+ x :< xs | null xs -> second fromList <$> case x of+ Emph lst -> Just (Modifier emph, lst)+ Strong lst -> Just (Modifier strong, lst)+ SmallCaps lst -> Just (Modifier smallcaps, lst)+ Strikeout lst -> Just (Modifier strikeout, lst)+ Underline lst -> Just (Modifier underline, lst)+ Superscript lst -> Just (Modifier superscript, lst)+ Subscript lst -> Just (Modifier subscript, lst)+ Link attr lst tgt -> Just (Modifier $ linkWith attr (fst tgt) (snd tgt), lst)+ Span attr lst -> Just (AttrModifier spanWith attr, lst)+ _ -> Nothing+ _ -> Nothing inlinesL :: Inlines -> (Inlines, Inlines) inlinesL ils = case viewl $ unMany ils of@@ -161,12 +142,12 @@ y_rem_attr = filter isAttrModifier y_remaining in case null shared of- True | isEmpty xs && isEmpty ys ->- stackInlines (x_rem_attr ++ y_rem_attr) mempty- | isEmpty xs ->+ True | null xs && null ys ->+ stackInlines (x_rem_attr <> y_rem_attr) mempty+ | null xs -> let (sp, y') = spaceOutInlinesL y in stackInlines x_rem_attr mempty <> sp <> y'- | isEmpty ys ->+ | null ys -> let (x', sp) = spaceOutInlinesR x in x' <> sp <> stackInlines y_rem_attr mempty | otherwise ->@@ -193,11 +174,7 @@ instance (Monoid a, Eq a) => Eq (Modifier a) where (Modifier f) == (Modifier g) = f mempty == g mempty (AttrModifier f attr) == (AttrModifier g attr') = f attr mempty == g attr' mempty- NullModifier == NullModifier = True _ == _ = False--isEmpty :: (Monoid a, Eq a) => a -> Bool-isEmpty x = x == mempty isAttrModifier :: Modifier a -> Bool isAttrModifier (AttrModifier _ _) = True
src/Text/Pandoc/Readers/Docx/Parse.hs view
@@ -259,10 +259,13 @@ leftBiasedMergeRunStyle :: RunStyle -> RunStyle -> RunStyle leftBiasedMergeRunStyle a b = RunStyle { isBold = isBold a <|> isBold b+ , isBoldCTL = isBoldCTL a <|> isBoldCTL b , isItalic = isItalic a <|> isItalic b+ , isItalicCTL = isItalicCTL a <|> isItalicCTL b , isSmallCaps = isSmallCaps a <|> isSmallCaps b , isStrike = isStrike a <|> isStrike b , isRTL = isRTL a <|> isRTL b+ , isForceCTL = isForceCTL a <|> isForceCTL b , rVertAlign = rVertAlign a <|> rVertAlign b , rUnderline = rUnderline a <|> rUnderline b , rParentStyle = rParentStyle a
src/Text/Pandoc/Readers/Docx/Parse/Styles.hs view
@@ -44,7 +44,6 @@ ) where import Codec.Archive.Zip import Control.Applicative ((<|>))-import Control.Monad.Except import Data.Function (on) import Data.String (IsString(..)) import qualified Data.Map as M@@ -101,10 +100,13 @@ } deriving (Show) data RunStyle = RunStyle { isBold :: Maybe Bool+ , isBoldCTL :: Maybe Bool , isItalic :: Maybe Bool+ , isItalicCTL :: Maybe Bool , isSmallCaps :: Maybe Bool , isStrike :: Maybe Bool , isRTL :: Maybe Bool+ , isForceCTL :: Maybe Bool , rVertAlign :: Maybe VertAlign , rUnderline :: Maybe String , rParentStyle :: Maybe CharStyle@@ -121,10 +123,13 @@ defaultRunStyle :: RunStyle defaultRunStyle = RunStyle { isBold = Nothing+ , isBoldCTL = Nothing , isItalic = Nothing+ , isItalicCTL = Nothing , isSmallCaps = Nothing , isStrike = Nothing , isRTL = Nothing+ , isForceCTL = Nothing , rVertAlign = Nothing , rUnderline = Nothing , rParentStyle = Nothing@@ -240,20 +245,21 @@ elemToCharStyle ns element parentStyle = CharStyle <$> (CharStyleId <$> findAttrTextByName ns "w" "styleId" element) <*> getElementStyleName ns element- <*> (Just $ elemToRunStyle ns element parentStyle)+ <*> Just (elemToRunStyle ns element parentStyle) elemToRunStyle :: NameSpaces -> Element -> Maybe CharStyle -> RunStyle elemToRunStyle ns element parentStyle | Just rPr <- findChildByName ns "w" "rPr" element = RunStyle {- isBold = checkOnOff ns rPr (elemName ns "w" "b") `mplus`- checkOnOff ns rPr (elemName ns "w" "bCs")- , isItalic = checkOnOff ns rPr (elemName ns "w" "i") `mplus`- checkOnOff ns rPr (elemName ns "w" "iCs")+ isBold = checkOnOff ns rPr (elemName ns "w" "b")+ , isBoldCTL = checkOnOff ns rPr (elemName ns "w" "bCs")+ , isItalic = checkOnOff ns rPr (elemName ns "w" "i")+ , isItalicCTL = checkOnOff ns rPr (elemName ns "w" "iCs") , isSmallCaps = checkOnOff ns rPr (elemName ns "w" "smallCaps") , isStrike = checkOnOff ns rPr (elemName ns "w" "strike") , isRTL = checkOnOff ns rPr (elemName ns "w" "rtl")+ , isForceCTL = checkOnOff ns rPr (elemName ns "w" "cs") , rVertAlign = findChildByName ns "w" "vertAlign" rPr >>= findAttrByName ns "w" "val" >>=
src/Text/Pandoc/Readers/Ipynb.hs view
@@ -78,7 +78,11 @@ mapM_ addAttachment attachments case cellType c of Ipynb.Markdown -> do- Pandoc _ bs <- walk fixImage <$> readMarkdown opts source+ bs <- if isEnabled Ext_raw_markdown opts+ then return [RawBlock (Format "markdown") source]+ else do+ Pandoc _ bs <- walk fixImage <$> readMarkdown opts source+ return bs return $ B.divWith ("",["cell","markdown"],kvs) $ B.fromList bs Ipynb.Heading lev -> do
src/Text/Pandoc/Readers/LaTeX.hs view
@@ -35,6 +35,7 @@ import qualified Data.Map as M import Data.Maybe (fromMaybe, maybeToList) import qualified Data.Set as Set+import qualified Data.Sequence as Seq import Data.Text (Text) import qualified Data.Text as T import System.FilePath (addExtension, replaceExtension, takeExtension)@@ -258,6 +259,29 @@ emptyOr160 unit, unit] +-- converts e.g. \SIRange{100}{200}{\ms} to "100 ms--200 ms"+doSIRange :: PandocMonad m => LP m Inlines+doSIRange = do+ skipopts+ startvalue <- tok+ startvalueprefix <- option "" $ bracketed tok+ stopvalue <- tok+ stopvalueprefix <- option "" $ bracketed tok+ unit <- grouped (mconcat <$> many1 siUnit) <|> siUnit <|> tok+ let emptyOr160 "" = ""+ emptyOr160 _ = "\160"+ return . mconcat $ [startvalueprefix,+ emptyOr160 startvalueprefix,+ startvalue,+ emptyOr160 unit,+ unit,+ "\8211", -- An en-dash+ stopvalueprefix,+ emptyOr160 stopvalueprefix,+ stopvalue,+ emptyOr160 unit,+ unit]+ siUnit :: PandocMonad m => LP m Inlines siUnit = do Tok _ (CtrlSeq name) _ <- anyControlSeq@@ -586,44 +610,6 @@ nlToSpace '\n' = ' ' nlToSpace x = x -keyval :: PandocMonad m => LP m (Text, Text)-keyval = try $ do- Tok _ Word key <- satisfyTok isWordTok- sp- val <- option mempty $ do- symbol '='- sp- (untokenize <$> braced) <|>- (mconcat <$> many1 (- (untokenize . snd <$> withRaw braced)- <|>- (untokenize <$> (many1- (satisfyTok- (\t -> case t of- Tok _ Symbol "]" -> False- Tok _ Symbol "," -> False- Tok _ Symbol "{" -> False- Tok _ Symbol "}" -> False- _ -> True))))))- optional (symbol ',')- sp- return (key, T.strip val)--keyvals :: PandocMonad m => LP m [(Text, Text)]-keyvals = try $ symbol '[' >> manyTill keyval (symbol ']') <* sp--accent :: PandocMonad m => Char -> Maybe Char -> LP m Inlines-accent combiningAccent fallBack = try $ do- ils <- tok- case toList ils of- (Str (T.uncons -> Just (x, xs)) : ys) -> return $ fromList $- -- try to normalize to the combined character:- Str (Normalize.normalize Normalize.NFC- (T.pack [x, combiningAccent]) <> xs) : ys- [Space] -> return $ str $ T.singleton $ fromMaybe combiningAccent fallBack- [] -> return $ str $ T.singleton $ fromMaybe combiningAccent fallBack- _ -> return ils- mathDisplay :: Text -> Inlines mathDisplay = displayMath . trimMath @@ -782,6 +768,7 @@ <|> ignore rawcommand lookupListDefault raw names inlineCommands + tok :: PandocMonad m => LP m Inlines tok = try $ spaces >> grouped inline <|> inlineCommand' <|> singleChar' where singleChar' = do@@ -794,36 +781,6 @@ paropt :: PandocMonad m => LP m Inlines paropt = parenWrapped inline -rawopt :: PandocMonad m => LP m Text-rawopt = try $ do- sp- inner <- untokenize <$> bracketedToks- sp- return $ "[" <> inner <> "]"--skipopts :: PandocMonad m => LP m ()-skipopts = skipMany (void overlaySpecification <|> void rawopt)---- opts in angle brackets are used in beamer-overlaySpecification :: PandocMonad m => LP m Text-overlaySpecification = try $ do- symbol '<'- t <- untokenize <$> manyTill overlayTok (symbol '>')- -- see issue #3368- guard $ not (T.all isLetter t) ||- t `elem` ["beamer","presentation", "trans",- "handout","article", "second"]- return $ "<" <> t <> ">"--overlayTok :: PandocMonad m => LP m Tok-overlayTok =- satisfyTok (\t ->- case t of- Tok _ Word _ -> True- Tok _ Spaces _ -> True- Tok _ Symbol c -> c `elem` ["-","+","@","|",":",","]- _ -> False)- inBrackets :: Inlines -> Inlines inBrackets x = str "[" <> x <> str "]" @@ -937,6 +894,7 @@ , ("_", lit "_") , ("{", lit "{") , ("}", lit "}")+ , ("qed", lit "\a0\x25FB") -- old TeX commands , ("em", extractSpaces emph <$> inlines) , ("it", extractSpaces emph <$> inlines)@@ -1140,6 +1098,7 @@ , ("acsp", doAcronymPlural "abbrv") -- siuntix , ("SI", dosiunitx)+ , ("SIRange", doSIRange) -- hyphenat , ("bshyp", lit "\\\173") , ("fshyp", lit "/\173")@@ -1178,6 +1137,19 @@ , ("ifdim", ifdim) ] +accent :: PandocMonad m => Char -> Maybe Char -> LP m Inlines+accent combiningAccent fallBack = try $ do+ ils <- tok+ case toList ils of+ (Str (T.uncons -> Just (x, xs)) : ys) -> return $ fromList $+ -- try to normalize to the combined character:+ Str (Normalize.normalize Normalize.NFC+ (T.pack [x, combiningAccent]) <> xs) : ys+ [Space] -> return $ str $ T.singleton $ fromMaybe combiningAccent fallBack+ [] -> return $ str $ T.singleton $ fromMaybe combiningAccent fallBack+ _ -> return ils++ lettrine :: PandocMonad m => LP m Inlines lettrine = do optional opt@@ -1333,39 +1305,6 @@ convert LineBreak = Str "" convert x = x -getRawCommand :: PandocMonad m => Text -> Text -> LP m Text-getRawCommand name txt = do- (_, rawargs) <- withRaw $- case name of- "write" -> do- void $ satisfyTok isWordTok -- digits- void braced- "titleformat" -> do- void braced- skipopts- void $ count 4 braced- "def" ->- void $ manyTill anyTok braced- _ | isFontSizeCommand name -> return ()- | otherwise -> do- skipopts- option "" (try dimenarg)- void $ many braced- return $ txt <> untokenize rawargs--isFontSizeCommand :: Text -> Bool-isFontSizeCommand "tiny" = True-isFontSizeCommand "scriptsize" = True-isFontSizeCommand "footnotesize" = True-isFontSizeCommand "small" = True-isFontSizeCommand "normalsize" = True-isFontSizeCommand "large" = True-isFontSizeCommand "Large" = True-isFontSizeCommand "LARGE" = True-isFontSizeCommand "huge" = True-isFontSizeCommand "Huge" = True-isFontSizeCommand _ = False- isBlockCommand :: Text -> Bool isBlockCommand s = s `M.member` (blockCommands :: M.Map Text (LP PandocPure Blocks))@@ -1471,20 +1410,6 @@ -- block elements: -begin_ :: PandocMonad m => Text -> LP m ()-begin_ t = try (do- controlSeq "begin"- spaces- txt <- untokenize <$> braced- guard (t == txt)) <?> ("\\begin{" ++ T.unpack t ++ "}")--end_ :: PandocMonad m => Text -> LP m ()-end_ t = try (do- controlSeq "end"- spaces- txt <- untokenize <$> braced- guard $ t == txt) <?> ("\\end{" ++ T.unpack t ++ "}")- preamble :: PandocMonad m => LP m Blocks preamble = mconcat <$> many preambleBlock where preambleBlock = (mempty <$ spaces1)@@ -1824,6 +1749,8 @@ , ("address", mempty <$ (skipopts *> tok >>= addMeta "address")) , ("signature", mempty <$ (skipopts *> authors)) , ("date", mempty <$ (skipopts *> tok >>= addMeta "date"))+ , ("newtheorem", newtheorem)+ , ("theoremstyle", theoremstyle) -- KOMA-Script metadata commands , ("extratitle", mempty <$ (skipopts *> tok >>= addMeta "extratitle")) , ("frontispiece", mempty <$ (skipopts *> tok >>= addMeta "frontispiece"))@@ -1946,6 +1873,8 @@ , ("tikzcd", rawVerbEnv "tikzcd") , ("lilypond", rawVerbEnv "lilypond") , ("ly", rawVerbEnv "ly")+ -- amsthm+ , ("proof", proof) -- etoolbox , ("ifstrequal", ifstrequal) , ("newtoggle", braced >>= newToggle)@@ -1954,16 +1883,127 @@ , ("iftoggle", try $ ifToggle >> block) ] +theoremstyle :: PandocMonad m => LP m Blocks+theoremstyle = do+ stylename <- untokenize <$> braced+ let mbstyle = case stylename of+ "plain" -> Just PlainStyle+ "definition" -> Just DefinitionStyle+ "remark" -> Just RemarkStyle+ _ -> Nothing+ case mbstyle of+ Nothing -> return ()+ Just sty -> updateState $ \s -> s{ sLastTheoremStyle = sty }+ return mempty++newtheorem :: PandocMonad m => LP m Blocks+newtheorem = do+ number <- option True (False <$ symbol '*' <* sp)+ name <- untokenize <$> braced+ sp+ series <- option Nothing $ Just . untokenize <$> bracketedToks+ sp+ showName <- untokenize <$> braced+ sp+ syncTo <- option Nothing $ Just . untokenize <$> bracketedToks+ sty <- sLastTheoremStyle <$> getState+ let spec = TheoremSpec { theoremName = showName+ , theoremStyle = sty+ , theoremSeries = series+ , theoremSyncTo = syncTo+ , theoremNumber = number+ , theoremLastNum = DottedNum [0] }+ tmap <- sTheoremMap <$> getState+ updateState $ \s -> s{ sTheoremMap =+ M.insert name spec tmap }+ return mempty++proof :: PandocMonad m => LP m Blocks+proof = do+ title <- option (B.text "Proof") opt+ bs <- env "proof" blocks+ return $+ B.divWith ("", ["proof"], []) $+ addQed $ addTitle (B.emph (title <> ".")) $ bs++addTitle :: Inlines -> Blocks -> Blocks+addTitle ils bs =+ case B.toList bs of+ (Para xs : rest)+ -> B.fromList (Para (B.toList ils ++ (Space : xs)) : rest)+ _ -> B.para ils <> bs++addQed :: Blocks -> Blocks+addQed bs =+ case Seq.viewr (B.unMany bs) of+ s Seq.:> Para ils+ -> B.Many (s Seq.|> Para (ils ++ B.toList qedSign))+ _ -> bs <> B.para qedSign+ where+ qedSign = B.str "\xa0\x25FB"+ environment :: PandocMonad m => LP m Blocks environment = try $ do controlSeq "begin" name <- untokenize <$> braced M.findWithDefault mzero name environments <|>+ theoremEnvironment name <|> if M.member name (inlineEnvironments :: M.Map Text (LP PandocPure Inlines)) then mzero else try (rawEnv name) <|> rawVerbEnv name +theoremEnvironment :: PandocMonad m => Text -> LP m Blocks+theoremEnvironment name = do+ tmap <- sTheoremMap <$> getState+ case M.lookup name tmap of+ Nothing -> mzero+ Just tspec -> do+ optTitle <- option mempty $ (\x -> space <> "(" <> x <> ")") <$> opt+ mblabel <- option Nothing $ Just . untokenize <$>+ try (spaces >> controlSeq "label" >> spaces >> braced)+ bs <- env name blocks+ number <-+ if theoremNumber tspec+ then do+ let name' = fromMaybe name $ theoremSeries tspec+ num <- getNextNumber+ (fromMaybe (DottedNum [0]) .+ fmap theoremLastNum .+ M.lookup name' . sTheoremMap)+ updateState $ \s ->+ s{ sTheoremMap =+ M.adjust+ (\spec -> spec{ theoremLastNum = num })+ name'+ (sTheoremMap s)+ }++ case mblabel of+ Just ident ->+ updateState $ \s ->+ s{ sLabels = M.insert ident+ [Str (theoremName tspec), Str "\160",+ Str (renderDottedNum num)] (sLabels s) }+ Nothing -> return ()+ return $ space <> B.text (renderDottedNum num)+ else return mempty+ let titleEmph = case theoremStyle tspec of+ PlainStyle -> B.strong+ DefinitionStyle -> B.strong+ RemarkStyle -> B.emph+ let title = titleEmph (B.text (theoremName tspec) <> number)+ <> optTitle <> "." <> space+ return $ divWith (fromMaybe "" mblabel, [name], []) $ addTitle title+ $ case theoremStyle tspec of+ PlainStyle -> walk italicize bs+ _ -> bs++italicize :: Block -> Block+italicize (Para ils) = Para [Emph ils]+italicize (Plain ils) = Plain [Emph ils]+italicize x = x+ env :: PandocMonad m => Text -> LP m a -> LP m a env name p = p <* end_ name @@ -1997,24 +2037,6 @@ report $ SkippedContent raw' pos return mempty -verbEnv :: PandocMonad m => Text -> LP m Text-verbEnv name = withVerbatimMode $ do- optional blankline- res <- manyTill anyTok (end_ name)- return $ stripTrailingNewline- $ untokenize- $ res---- Strip single final newline and any spaces following it.--- Input is unchanged if it doesn't end with newline +--- optional spaces.-stripTrailingNewline :: Text -> Text-stripTrailingNewline t =- let (b, e) = T.breakOnEnd "\n" t- in if T.all (== ' ') e- then T.dropEnd 1 b- else t- fancyverbEnv :: PandocMonad m => Text -> LP m Blocks fancyverbEnv name = do options <- option [] keyvals@@ -2340,10 +2362,9 @@ parseTableRow :: PandocMonad m => Text -- ^ table environment name -> [([Tok], [Tok])] -- ^ pref/suffixes- -> LP m [Blocks]+ -> LP m Row parseTableRow envname prefsufs = do notFollowedBy (spaces *> end_ envname)- let cols = length prefsufs -- add prefixes and suffixes in token stream: let celltoks (pref, suff) = do prefpos <- getPosition@@ -2362,22 +2383,63 @@ cells <- mapM (\ts -> setInput ts >> parseTableCell) rawcells setInput oldInput spaces- let numcells = length cells- guard $ numcells <= cols && numcells >= 1- guard $ cells /= [mempty]- -- note: a & b in a three-column table leaves an empty 3rd cell:- return $ cells ++ replicate (cols - numcells) mempty+ return $ Row nullAttr cells -parseTableCell :: PandocMonad m => LP m Blocks+parseTableCell :: PandocMonad m => LP m Cell parseTableCell = do- let plainify bs = case toList bs of- [Para ils] -> plain (fromList ils)- _ -> bs updateState $ \st -> st{ sInTableCell = True }- cells <- plainify <$> blocks+ cell' <- parseMultiCell <|> parseSimpleCell updateState $ \st -> st{ sInTableCell = False }- return cells+ return cell' +cellAlignment :: PandocMonad m => LP m Alignment+cellAlignment = skipMany (symbol '|') *> alignment <* skipMany (symbol '|')+ where+ alignment = do+ c <- untoken <$> singleChar+ return $ case c of+ "l" -> AlignLeft+ "r" -> AlignRight+ "c" -> AlignCenter+ "*" -> AlignDefault+ _ -> AlignDefault++plainify :: Blocks -> Blocks+plainify bs = case toList bs of+ [Para ils] -> plain (fromList ils)+ _ -> bs++parseMultiCell :: PandocMonad m => LP m Cell+parseMultiCell = (controlSeq "multirow" >> parseMultirowCell) + <|> (controlSeq "multicolumn" >> parseMulticolCell)+ where+ parseMultirowCell = parseMultiXCell RowSpan (const $ ColSpan 1)+ parseMulticolCell = parseMultiXCell (const $ RowSpan 1) ColSpan++ parseMultiXCell rowspanf colspanf = do+ span' <- fmap (fromMaybe 1 . safeRead . untokenize) braced+ alignment <- symbol '{' *> cellAlignment <* symbol '}'++ -- Two possible contents: either a nested \multirow/\multicol, or content.+ -- E.g. \multirow{1}{c}{\multicol{1}{c}{content}}+ let singleCell = do+ content <- plainify <$> blocks+ return $ cell alignment (rowspanf span') (colspanf span') content++ let nestedCell = do+ (Cell _ _ (RowSpan rs) (ColSpan cs) bs) <- parseMultiCell+ return $ cell+ alignment+ (RowSpan $ max span' rs)+ (ColSpan $ max span' cs)+ (fromList bs)++ symbol '{' *> (nestedCell <|> singleCell) <* symbol '}'++-- Parse a simple cell, i.e. not multirow/multicol+parseSimpleCell :: PandocMonad m => LP m Cell+parseSimpleCell = simpleCell <$> (plainify <$> blocks)+ simpTable :: PandocMonad m => Text -> Bool -> LP m Blocks simpTable envname hasWidthParameter = try $ do when hasWidthParameter $ () <$ (spaces >> tok)@@ -2392,8 +2454,8 @@ spaces skipMany hline spaces- header' <- option [] $ try (parseTableRow envname prefsufs <*- lbreak <* many1 hline)+ header' <- option [] . try . fmap (:[]) $+ parseTableRow envname prefsufs <* lbreak <* many1 hline spaces rows <- sepEndBy (parseTableRow envname prefsufs) (lbreak <* optional (skipMany hline))@@ -2405,12 +2467,10 @@ optional lbreak spaces lookAhead $ controlSeq "end" -- make sure we're at end- let toRow = Row nullAttr . map simpleCell- toHeaderRow l = if null l then [] else [toRow l] return $ table emptyCaption (zip aligns widths)- (TableHead nullAttr $ toHeaderRow header')- [TableBody nullAttr 0 [] $ map toRow rows]+ (TableHead nullAttr $ header')+ [TableBody nullAttr 0 [] rows] (TableFoot nullAttr []) addTableCaption :: PandocMonad m => Blocks -> LP m Blocks
src/Text/Pandoc/Readers/LaTeX/Parsing.hs view
@@ -2,6 +2,7 @@ {-# LANGUAGE MultiParamTypeClasses #-} {-# LANGUAGE OverloadedStrings #-} {-# LANGUAGE ScopedTypeVariables #-}+{-# LANGUAGE ViewPatterns #-} {- | Module : Text.Pandoc.Readers.LaTeX.Parsing Copyright : Copyright (C) 2006-2020 John MacFarlane@@ -17,6 +18,8 @@ ( DottedNum(..) , renderDottedNum , incrementDottedNum+ , TheoremSpec(..)+ , TheoremStyle(..) , LaTeXState(..) , defaultLaTeXState , LP@@ -66,6 +69,14 @@ , dimenarg , ignore , withRaw+ , keyvals+ , verbEnv+ , begin_+ , end_+ , getRawCommand+ , skipopts+ , rawopt+ , overlaySpecification ) where import Control.Applicative (many, (<|>))@@ -93,7 +104,7 @@ -- import Debug.Trace newtype DottedNum = DottedNum [Int]- deriving (Show)+ deriving (Show, Eq) renderDottedNum :: DottedNum -> T.Text renderDottedNum (DottedNum xs) = T.pack $@@ -105,6 +116,20 @@ (x:xs) -> reverse (x+1 : xs) [] -> [] -- shouldn't happen +data TheoremStyle =+ PlainStyle | DefinitionStyle | RemarkStyle+ deriving (Show, Eq)++data TheoremSpec =+ TheoremSpec+ { theoremName :: Text+ , theoremStyle :: TheoremStyle+ , theoremSeries :: Maybe Text+ , theoremSyncTo :: Maybe Text+ , theoremNumber :: Bool+ , theoremLastNum :: DottedNum }+ deriving (Show, Eq)+ data LaTeXState = LaTeXState{ sOptions :: ReaderOptions , sMeta :: Meta , sQuoteContext :: QuoteContext@@ -119,6 +144,8 @@ , sLastHeaderNum :: DottedNum , sLastFigureNum :: DottedNum , sLastTableNum :: DottedNum+ , sTheoremMap :: M.Map Text TheoremSpec+ , sLastTheoremStyle :: TheoremStyle , sLastLabel :: Maybe Text , sLabels :: M.Map Text [Inline] , sHasChapters :: Bool@@ -142,6 +169,8 @@ , sLastHeaderNum = DottedNum [] , sLastFigureNum = DottedNum [] , sLastTableNum = DottedNum []+ , sTheoremMap = M.empty+ , sLastTheoremStyle = PlainStyle , sLastLabel = Nothing , sLabels = M.empty , sHasChapters = False@@ -695,3 +724,125 @@ let raw = takeWhile (\(Tok pos _ _) -> maybe True (\p -> sourceName p /= sourceName pos || pos < p) nxtpos) inp return (result, raw)++keyval :: PandocMonad m => LP m (Text, Text)+keyval = try $ do+ Tok _ Word key <- satisfyTok isWordTok+ sp+ val <- option mempty $ do+ symbol '='+ sp+ (untokenize <$> braced) <|>+ (mconcat <$> many1 (+ (untokenize . snd <$> withRaw braced)+ <|>+ (untokenize <$> (many1+ (satisfyTok+ (\t -> case t of+ Tok _ Symbol "]" -> False+ Tok _ Symbol "," -> False+ Tok _ Symbol "{" -> False+ Tok _ Symbol "}" -> False+ _ -> True))))))+ optional (symbol ',')+ sp+ return (key, T.strip val)++keyvals :: PandocMonad m => LP m [(Text, Text)]+keyvals = try $ symbol '[' >> manyTill keyval (symbol ']') <* sp++verbEnv :: PandocMonad m => Text -> LP m Text+verbEnv name = withVerbatimMode $ do+ optional blankline+ res <- manyTill anyTok (end_ name)+ return $ stripTrailingNewline+ $ untokenize+ $ res++-- Strip single final newline and any spaces following it.+-- Input is unchanged if it doesn't end with newline ++-- optional spaces.+stripTrailingNewline :: Text -> Text+stripTrailingNewline t =+ let (b, e) = T.breakOnEnd "\n" t+ in if T.all (== ' ') e+ then T.dropEnd 1 b+ else t++begin_ :: PandocMonad m => Text -> LP m ()+begin_ t = try (do+ controlSeq "begin"+ spaces+ txt <- untokenize <$> braced+ guard (t == txt)) <?> ("\\begin{" ++ T.unpack t ++ "}")++end_ :: PandocMonad m => Text -> LP m ()+end_ t = try (do+ controlSeq "end"+ spaces+ txt <- untokenize <$> braced+ guard $ t == txt) <?> ("\\end{" ++ T.unpack t ++ "}")++getRawCommand :: PandocMonad m => Text -> Text -> LP m Text+getRawCommand name txt = do+ (_, rawargs) <- withRaw $+ case name of+ "write" -> do+ void $ satisfyTok isWordTok -- digits+ void braced+ "titleformat" -> do+ void braced+ skipopts+ void $ count 4 braced+ "def" ->+ void $ manyTill anyTok braced+ _ | isFontSizeCommand name -> return ()+ | otherwise -> do+ skipopts+ option "" (try dimenarg)+ void $ many braced+ return $ txt <> untokenize rawargs++skipopts :: PandocMonad m => LP m ()+skipopts = skipMany (void overlaySpecification <|> void rawopt)++-- opts in angle brackets are used in beamer+overlaySpecification :: PandocMonad m => LP m Text+overlaySpecification = try $ do+ symbol '<'+ t <- untokenize <$> manyTill overlayTok (symbol '>')+ -- see issue #3368+ guard $ not (T.all isLetter t) ||+ t `elem` ["beamer","presentation", "trans",+ "handout","article", "second"]+ return $ "<" <> t <> ">"++overlayTok :: PandocMonad m => LP m Tok+overlayTok =+ satisfyTok (\t ->+ case t of+ Tok _ Word _ -> True+ Tok _ Spaces _ -> True+ Tok _ Symbol c -> c `elem` ["-","+","@","|",":",","]+ _ -> False)++rawopt :: PandocMonad m => LP m Text+rawopt = try $ do+ sp+ inner <- untokenize <$> bracketedToks+ sp+ return $ "[" <> inner <> "]"++isFontSizeCommand :: Text -> Bool+isFontSizeCommand "tiny" = True+isFontSizeCommand "scriptsize" = True+isFontSizeCommand "footnotesize" = True+isFontSizeCommand "small" = True+isFontSizeCommand "normalsize" = True+isFontSizeCommand "large" = True+isFontSizeCommand "Large" = True+isFontSizeCommand "LARGE" = True+isFontSizeCommand "huge" = True+isFontSizeCommand "Huge" = True+isFontSizeCommand _ = False+
src/Text/Pandoc/Readers/Org/Blocks.hs view
@@ -608,7 +608,10 @@ } table :: PandocMonad m => OrgParser m (F Blocks)-table = gridTableWith blocks True <|> orgTable+table = do+ withTables <- getExportSetting exportWithTables+ tbl <- gridTableWith blocks True <|> orgTable+ return $ if withTables then tbl else mempty -- | A normal org table orgTable :: PandocMonad m => OrgParser m (F Blocks)
src/Text/Pandoc/Readers/Org/ExportSettings.hs view
@@ -47,9 +47,9 @@ , booleanSetting "creator" (\val es -> es { exportWithCreator = val }) , complementableListSetting "d" (\val es -> es { exportDrawers = val }) , ignoredSetting "date"- , ignoredSetting "e"+ , booleanSetting "e" (\val es -> es { exportWithEntities = val }) , booleanSetting "email" (\val es -> es { exportWithEmail = val })- , ignoredSetting "f"+ , booleanSetting "f" (\val es -> es { exportWithFootnotes = val }) , integerSetting "H" (\val es -> es { exportHeadlineLevels = val }) , ignoredSetting "inline" , ignoredSetting "num"@@ -64,7 +64,7 @@ , ignoredSetting "title" , ignoredSetting "toc" , booleanSetting "todo" (\val es -> es { exportWithTodoKeywords = val })- , ignoredSetting "|"+ , booleanSetting "|" (\val es -> es { exportWithTables = val }) , ignoreAndWarn ] <?> "export setting"
src/Text/Pandoc/Readers/Org/Inlines.hs view
@@ -378,7 +378,10 @@ else rest footnote :: PandocMonad m => OrgParser m (F Inlines)-footnote = try $ inlineNote <|> referencedNote+footnote = try $ do+ note <- inlineNote <|> referencedNote+ withNote <- getExportSetting exportWithFootnotes+ return $ if withNote then note else mempty inlineNote :: PandocMonad m => OrgParser m (F Inlines) inlineNote = try $ do@@ -790,9 +793,12 @@ inlineLaTeX = try $ do cmd <- inlineLaTeXCommand texOpt <- getExportSetting exportWithLatex+ allowEntities <- getExportSetting exportWithEntities ils <- parseAsInlineLaTeX cmd texOpt maybe mzero returnF $- parseAsMathMLSym cmd `mplus` parseAsMath cmd texOpt `mplus` ils+ parseAsMathMLSym allowEntities cmd `mplus`+ parseAsMath cmd texOpt `mplus`+ ils where parseAsInlineLaTeX :: PandocMonad m => Text -> TeXExport -> OrgParser m (Maybe Inlines)@@ -801,10 +807,15 @@ TeXIgnore -> return (Just mempty) TeXVerbatim -> return (Just $ B.str cs) - parseAsMathMLSym :: Text -> Maybe Inlines- parseAsMathMLSym cs = B.str <$> MathMLEntityMap.getUnicode (clean cs)- -- drop initial backslash and any trailing "{}"- where clean = T.dropWhileEnd (`elem` ("{}" :: String)) . T.drop 1+ parseAsMathMLSym :: Bool -> Text -> Maybe Inlines+ parseAsMathMLSym allowEntities cs = do+ -- drop initial backslash and any trailing "{}"+ let clean = T.dropWhileEnd (`elem` ("{}" :: String)) . T.drop 1+ -- If entities are disabled, then return the string as text, but+ -- only if this *is* a MathML entity.+ case B.str <$> MathMLEntityMap.getUnicode (clean cs) of+ Just _ | not allowEntities -> Just $ B.str cs+ x -> x state :: ParserState state = def{ stateOptions = def{ readerExtensions =
src/Text/Pandoc/Readers/Org/ParserState.hs view
@@ -257,9 +257,12 @@ , exportWithAuthor :: Bool -- ^ Include author in final meta-data , exportWithCreator :: Bool -- ^ Include creator in final meta-data , exportWithEmail :: Bool -- ^ Include email in final meta-data+ , exportWithEntities :: Bool -- ^ Include MathML-like entities+ , exportWithFootnotes :: Bool -- ^ Include footnotes , exportWithLatex :: TeXExport -- ^ Handling of raw TeX commands , exportWithPlanning :: Bool -- ^ Keep planning info after headlines , exportWithTags :: Bool -- ^ Keep tags as part of headlines+ , exportWithTables :: Bool -- ^ Include tables , exportWithTodoKeywords :: Bool -- ^ Keep TODO keywords in headers } @@ -279,8 +282,11 @@ , exportWithAuthor = True , exportWithCreator = True , exportWithEmail = True+ , exportWithEntities = True+ , exportWithFootnotes = True , exportWithLatex = TeXExport , exportWithPlanning = False , exportWithTags = True+ , exportWithTables = True , exportWithTodoKeywords = True }
src/Text/Pandoc/Readers/RST.hs view
@@ -223,7 +223,8 @@ first <- anyLine rest <- option "" $ try $ do lookAhead (count indent (char ' ') >> spaceChar) indentedBlock- let raw = (if T.null first then "" else first <> "\n") <> rest <> "\n"+ let raw = (if T.null first then "" else first <> "\n") <> rest <>+ (if T.null first && T.null rest then "" else "\n") return (name, raw) fieldListItem :: PandocMonad m => Int -> RSTParser m (Inlines, [Blocks])@@ -484,7 +485,7 @@ Just patt -> drop 1 . dropWhile (not . (patt `T.isInfixOf`)) Nothing -> id) $ contentLines'- let contents' = T.unlines contentLines'' <> "\n"+ let contents' = T.unlines contentLines'' case lookup "code" fields of Just lang -> do let classes = maybe [] T.words (lookup "class" fields)@@ -494,7 +495,7 @@ Just _ -> return $ B.rawBlock "rst" contents' Nothing -> do setPosition $ newPos (T.unpack f) 1 1- setInput contents'+ setInput $ contents' <> "\n" bs <- optional blanklines >> (mconcat <$> many block) setInput oldInput@@ -878,7 +879,12 @@ Left e -> throwError $ PandocParsecError "csv table" e Right rawrows -> do- let parseCell = parseFromString' (plain <|> return mempty)+ let singleParaToPlain bs =+ case B.toList bs of+ [Para ils] -> B.fromList [Plain ils]+ _ -> bs+ let parseCell t = singleParaToPlain+ <$> parseFromString' parseBlocks (t <> "\n\n") let parseRow = mapM parseCell rows <- mapM parseRow rawrows let (headerRow,bodyRows,numOfCols) =
src/Text/Pandoc/Templates.hs view
@@ -97,6 +97,7 @@ "markdown_mmd" -> getDefaultTemplate "markdown" "markdown_phpextra" -> getDefaultTemplate "markdown" "gfm" -> getDefaultTemplate "commonmark"+ "commonmark_x" -> getDefaultTemplate "commonmark" _ -> do let fname = "templates" </> "default" <.> T.unpack format UTF8.toText <$> readDataFile fname
src/Text/Pandoc/Writers.hs view
@@ -178,6 +178,7 @@ ,("asciidoctor" , TextWriter writeAsciiDoctor) ,("haddock" , TextWriter writeHaddock) ,("commonmark" , TextWriter writeCommonMark)+ ,("commonmark_x" , TextWriter writeCommonMark) ,("gfm" , TextWriter writeCommonMark) ,("tei" , TextWriter writeTEI) ,("muse" , TextWriter writeMuse)
src/Text/Pandoc/Writers/CommonMark.hs view
@@ -15,353 +15,5 @@ -} module Text.Pandoc.Writers.CommonMark (writeCommonMark) where -import CMarkGFM-import Control.Monad.State.Strict (State, get, modify, runState)-import Data.Char (isAscii)-import Data.Foldable (foldrM)-import Data.List (transpose)-import Data.Text (Text)-import qualified Data.Text as T-import Network.HTTP (urlEncode)-import Text.Pandoc.Class.PandocMonad (PandocMonad)-import Text.Pandoc.Definition-import Text.Pandoc.Options-import Text.Pandoc.Shared (capitalize, isTightList,- linesToPara, onlySimpleTableCells, taskListItemToAscii, tshow)-import Text.Pandoc.Templates (renderTemplate)-import Text.Pandoc.Walk (walk, walkM)-import Text.Pandoc.Writers.HTML (writeHtml5String, tagWithAttributes)-import Text.Pandoc.Writers.Shared-import Text.Pandoc.XML (toHtml5Entities)-import Text.DocLayout (literal, render)---- | Convert Pandoc to CommonMark.-writeCommonMark :: PandocMonad m => WriterOptions -> Pandoc -> m Text-writeCommonMark opts (Pandoc meta blocks) = do- toc <- if writerTableOfContents opts- then blocksToCommonMark opts [ toTableOfContents opts blocks ]- else return mempty-- let (blocks', notes) = runState (walkM processNotes blocks) []- notes' = [OrderedList (1, Decimal, Period) $ reverse notes | not (null notes)]- main <- blocksToCommonMark opts (blocks' ++ notes')- metadata <- metaToContext opts- (fmap (literal . T.stripEnd) . blocksToCommonMark opts)- (fmap (literal . T.stripEnd) . inlinesToCommonMark opts)- meta- let context =- -- for backwards compatibility we populate toc- -- with the contents of the toc, rather than a boolean:- defField "toc" toc- $ defField "table-of-contents" toc- $ defField "body" main metadata- return $- case writerTemplate opts of- Nothing -> main- Just tpl -> render Nothing $ renderTemplate tpl context--softBreakToSpace :: Inline -> Inline-softBreakToSpace SoftBreak = Space-softBreakToSpace x = x--processNotes :: Inline -> State [[Block]] Inline-processNotes (Note bs) = do- modify (bs :)- notes <- get- return $ Str $ "[" <> tshow (length notes) <> "]"-processNotes x = return x--node :: NodeType -> [Node] -> Node-node = Node Nothing--blocksToCommonMark :: PandocMonad m => WriterOptions -> [Block] -> m Text-blocksToCommonMark opts bs = do- let cmarkOpts = [optHardBreaks | isEnabled Ext_hard_line_breaks opts]- colwidth = if writerWrapText opts == WrapAuto- then Just $ writerColumns opts- else Nothing- nodes <- blocksToNodes opts bs- return $ T.stripEnd $- nodeToCommonmark cmarkOpts colwidth $- node DOCUMENT nodes--inlinesToCommonMark :: PandocMonad m => WriterOptions -> [Inline] -> m Text-inlinesToCommonMark opts ils = return $- nodeToCommonmark cmarkOpts colwidth $- node PARAGRAPH (inlinesToNodes opts ils)- where cmarkOpts = [optHardBreaks | isEnabled Ext_hard_line_breaks opts]- colwidth = if writerWrapText opts == WrapAuto- then Just $ writerColumns opts- else Nothing--blocksToNodes :: PandocMonad m => WriterOptions -> [Block] -> m [Node]-blocksToNodes opts = foldrM (blockToNodes opts) []--blockToNodes :: PandocMonad m => WriterOptions -> Block -> [Node] -> m [Node]-blockToNodes opts (Plain xs) ns =- return (node PARAGRAPH (inlinesToNodes opts xs) : ns)-blockToNodes opts (Para xs) ns =- return (node PARAGRAPH (inlinesToNodes opts xs) : ns)-blockToNodes opts (LineBlock lns) ns = blockToNodes opts (linesToPara lns) ns-blockToNodes _ (CodeBlock (_,classes,_) xs) ns = return- (node (CODE_BLOCK (T.unwords classes) xs) [] : ns)-blockToNodes opts (RawBlock (Format f) xs) ns- | f == "html" && isEnabled Ext_raw_html opts- = return (node (HTML_BLOCK xs) [] : ns)- | (f == "latex" || f == "tex") && isEnabled Ext_raw_tex opts- = return (node (CUSTOM_BLOCK xs T.empty) [] : ns)- | f == "markdown"- = return (node (CUSTOM_BLOCK xs T.empty) [] : ns)- | otherwise = return ns-blockToNodes opts (BlockQuote bs) ns = do- nodes <- blocksToNodes opts bs- return (node BLOCK_QUOTE nodes : ns)-blockToNodes opts (BulletList items) ns = do- let exts = writerExtensions opts- nodes <- mapM (blocksToNodes opts . taskListItemToAscii exts) items- return (node (LIST ListAttributes{- listType = BULLET_LIST,- listDelim = PERIOD_DELIM,- listTight = isTightList items,- listStart = 1 }) (map (node ITEM) nodes) : ns)-blockToNodes opts (OrderedList (start, _sty, delim) items) ns = do- let exts = writerExtensions opts- nodes <- mapM (blocksToNodes opts . taskListItemToAscii exts) items- return (node (LIST ListAttributes{- listType = ORDERED_LIST,- listDelim = case delim of- OneParen -> PAREN_DELIM- TwoParens -> PAREN_DELIM- _ -> PERIOD_DELIM,- listTight = isTightList items,- listStart = start }) (map (node ITEM) nodes) : ns)-blockToNodes _ HorizontalRule ns = return (node THEMATIC_BREAK [] : ns)-blockToNodes opts (Header lev _ ils) ns =- return (node (HEADING lev) (inlinesToNodes opts ils) : ns)-blockToNodes opts (Div attr bs) ns = do- nodes <- blocksToNodes opts bs- let op = tagWithAttributes opts True False "div" attr- if isEnabled Ext_raw_html opts- then return (node (HTML_BLOCK op) [] : nodes ++- [node (HTML_BLOCK (T.pack "</div>")) []] ++ ns)- else return (nodes ++ ns)-blockToNodes opts (DefinitionList items) ns =- blockToNodes opts (BulletList items') ns- where items' = map dlToBullet items- dlToBullet (term, (Para xs : ys) : zs) =- Para (term ++ [LineBreak] ++ xs) : ys ++ concat zs- dlToBullet (term, (Plain xs : ys) : zs) =- Plain (term ++ [LineBreak] ++ xs) : ys ++ concat zs- dlToBullet (term, xs) =- Para term : concat xs-blockToNodes opts t@(Table _ blkCapt specs thead tbody tfoot) ns =- let (capt, aligns, _widths, headers, rows) = toLegacyTable blkCapt specs thead tbody tfoot- in if isEnabled Ext_pipe_tables opts && onlySimpleTableCells (headers : rows)- then do- -- We construct a table manually as a CUSTOM_BLOCK, for- -- two reasons: (1) cmark-gfm currently doesn't support- -- rendering TABLE nodes; (2) we can align the column sides;- -- (3) we can render the caption as a regular paragraph.- let capt' = node PARAGRAPH (inlinesToNodes opts capt)- -- backslash | in code and raw:- let fixPipe (Code attr xs) =- Code attr (T.replace "|" "\\|" xs)- fixPipe (RawInline format xs) =- RawInline format (T.replace "|" "\\|" xs)- fixPipe x = x- let toCell [Plain ils] = T.strip- $ nodeToCommonmark [] Nothing- $ node (CUSTOM_INLINE mempty mempty)- $ inlinesToNodes opts- $ walk (fixPipe . softBreakToSpace) ils- toCell [Para ils] = T.strip- $ nodeToCommonmark [] Nothing- $ node (CUSTOM_INLINE mempty mempty)- $ inlinesToNodes opts- $ walk (fixPipe . softBreakToSpace) ils- toCell [] = ""- toCell xs = error $ "toCell encountered " ++ show xs- let separator = " | "- let starter = "| "- let ender = " |"- let rawheaders = map toCell headers- let rawrows = map (map toCell) rows- let maximum' [] = 0- maximum' xs = maximum xs- let colwidths = map (maximum' . map T.length) $- transpose (rawheaders:rawrows)- let toHeaderLine len AlignDefault = T.replicate len "-"- toHeaderLine len AlignLeft = ":" <>- T.replicate (max (len - 1) 1) "-"- toHeaderLine len AlignRight =- T.replicate (max (len - 1) 1) "-" <> ":"- toHeaderLine len AlignCenter = ":" <>- T.replicate (max (len - 2) 1) (T.pack "-") <> ":"- let rawheaderlines = zipWith toHeaderLine colwidths aligns- let headerlines = starter <> T.intercalate separator rawheaderlines <>- ender- let padContent (align, w) t' =- let padding = w - T.length t'- halfpadding = padding `div` 2- in case align of- AlignRight -> T.replicate padding " " <> t'- AlignCenter -> T.replicate halfpadding " " <> t' <>- T.replicate (padding - halfpadding) " "- _ -> t' <> T.replicate padding " "- let toRow xs = starter <> T.intercalate separator- (zipWith padContent (zip aligns colwidths) xs) <>- ender- let table' = toRow rawheaders <> "\n" <> headerlines <> "\n" <>- T.intercalate "\n" (map toRow rawrows)- return (node (CUSTOM_BLOCK table' mempty) [] :- if null capt- then ns- else capt' : ns)- else do -- fall back to raw HTML- s <- writeHtml5String def $! Pandoc nullMeta [t]- return (node (HTML_BLOCK s) [] : ns)-blockToNodes _ Null ns = return ns--inlinesToNodes :: WriterOptions -> [Inline] -> [Node]-inlinesToNodes opts = foldr (inlineToNodes opts) []--inlineToNodes :: WriterOptions -> Inline -> [Node] -> [Node]-inlineToNodes opts (Str s) = stringToNodes opts s'- where s' = if isEnabled Ext_smart opts- then unsmartify opts s- else s-inlineToNodes _ Space = (node (TEXT (T.pack " ")) [] :)-inlineToNodes _ LineBreak = (node LINEBREAK [] :)-inlineToNodes opts SoftBreak- | isEnabled Ext_hard_line_breaks opts = (node (TEXT " ") [] :)- | writerWrapText opts == WrapNone = (node (TEXT " ") [] :)- | otherwise = (node SOFTBREAK [] :)-inlineToNodes opts (Emph xs) = (node EMPH (inlinesToNodes opts xs) :)-inlineToNodes opts (Underline xs)- | isEnabled Ext_raw_html opts =- ((node (HTML_INLINE (T.pack "<u>")) [] : inlinesToNodes opts xs ++- [node (HTML_INLINE (T.pack "</u>")) []]) ++ )- | otherwise = (node EMPH (inlinesToNodes opts xs) :)-inlineToNodes opts (Strong xs) = (node STRONG (inlinesToNodes opts xs) :)-inlineToNodes opts (Strikeout xs)- | isEnabled Ext_strikeout opts = (node (CUSTOM_INLINE "~~" "~~") (inlinesToNodes opts xs) :)- | isEnabled Ext_raw_html opts = ((node (HTML_INLINE (T.pack "<s>")) [] : inlinesToNodes opts xs ++- [node (HTML_INLINE (T.pack "</s>")) []]) ++ )- | otherwise = (inlinesToNodes opts xs ++)-inlineToNodes opts (Superscript xs) =- if isEnabled Ext_raw_html opts- then ((node (HTML_INLINE (T.pack "<sup>")) [] : inlinesToNodes opts xs ++- [node (HTML_INLINE (T.pack "</sup>")) []]) ++ )- else case traverse toSuperscriptInline xs of- Just xs' | not (writerPreferAscii opts)- -> (inlinesToNodes opts xs' ++)- _ ->- ((node (TEXT (T.pack "^(")) [] : inlinesToNodes opts xs ++- [node (TEXT (T.pack ")")) []]) ++ )-inlineToNodes opts (Subscript xs) =- if isEnabled Ext_raw_html opts- then ((node (HTML_INLINE (T.pack "<sub>")) [] : inlinesToNodes opts xs ++- [node (HTML_INLINE (T.pack "</sub>")) []]) ++ )- else case traverse toSubscriptInline xs of- Just xs' | not (writerPreferAscii opts)- -> (inlinesToNodes opts xs' ++)- _ ->- ((node (TEXT (T.pack "_(")) [] : inlinesToNodes opts xs ++- [node (TEXT (T.pack ")")) []]) ++ )-inlineToNodes opts (SmallCaps xs) =- if isEnabled Ext_raw_html opts- then ((node (HTML_INLINE (T.pack "<span class=\"smallcaps\">")) []- : inlinesToNodes opts xs ++- [node (HTML_INLINE (T.pack "</span>")) []]) ++ )- else (inlinesToNodes opts (capitalize xs) ++)-inlineToNodes opts (Link _ ils (url,tit)) =- (node (LINK url tit) (inlinesToNodes opts ils) :)--- title beginning with fig: indicates implicit figure-inlineToNodes opts (Image alt ils (url,T.stripPrefix "fig:" -> Just tit)) =- inlineToNodes opts (Image alt ils (url,tit))-inlineToNodes opts (Image _ ils (url,tit)) =- (node (IMAGE url tit) (inlinesToNodes opts ils) :)-inlineToNodes opts (RawInline (Format f) xs)- | f == "html" && isEnabled Ext_raw_html opts- = (node (HTML_INLINE xs) [] :)- | (f == "latex" || f == "tex") && isEnabled Ext_raw_tex opts- = (node (CUSTOM_INLINE xs T.empty) [] :)- | f == "markdown"- = (node (CUSTOM_INLINE xs T.empty) [] :)- | otherwise = id-inlineToNodes opts (Quoted qt ils) =- ((node (HTML_INLINE start) [] :- inlinesToNodes opts ils ++ [node (HTML_INLINE end) []]) ++)- where (start, end) = case qt of- SingleQuote- | isEnabled Ext_smart opts -> ("'","'")- | writerPreferAscii opts ->- ("‘", "’")- | otherwise -> ("‘", "’")- DoubleQuote- | isEnabled Ext_smart opts -> ("\"", "\"")- | writerPreferAscii opts ->- ("“", "”")- | otherwise -> ("“", "”")-inlineToNodes _ (Code _ str) = (node (CODE str) [] :)-inlineToNodes opts (Math mt str) =- case writerHTMLMathMethod opts of- WebTeX url ->- let core = inlineToNodes opts- (Image nullAttr [Str str] (url <> T.pack (urlEncode $ T.unpack str), str))- sep = if mt == DisplayMath- then (node LINEBREAK [] :)- else id- in (sep . core . sep)- _ ->- case mt of- InlineMath ->- (node (HTML_INLINE ("\\(" <> str <> "\\)")) [] :)- DisplayMath ->- (node (HTML_INLINE ("\\[" <> str <> "\\]")) [] :)-inlineToNodes opts (Span ("",["emoji"],kvs) [Str s]) =- case lookup "data-emoji" kvs of- Just emojiname | isEnabled Ext_emoji opts ->- (node (TEXT (":" <> emojiname <> ":")) [] :)- _ -> (node (TEXT s) [] :)-inlineToNodes opts (Span attr ils) =- let nodes = inlinesToNodes opts ils- op = tagWithAttributes opts True False "span" attr- in if isEnabled Ext_raw_html opts- then ((node (HTML_INLINE op) [] : nodes ++- [node (HTML_INLINE (T.pack "</span>")) []]) ++)- else (nodes ++)-inlineToNodes opts (Cite _ ils) = (inlinesToNodes opts ils ++)-inlineToNodes _ (Note _) = id -- should not occur--- we remove Note elements in preprocessing--stringToNodes :: WriterOptions -> Text -> [Node] -> [Node]-stringToNodes opts s- | not (writerPreferAscii opts) = (node (TEXT s) [] :)- | otherwise = step s- where- step input =- let (ascii, rest) = T.span isAscii input- this = node (TEXT ascii) []- nodes = case T.uncons rest of- Nothing -> id- Just (nonAscii, rest') ->- let escaped = toHtml5Entities (T.singleton nonAscii)- in (node (HTML_INLINE escaped) [] :) . step rest'- in (this :) . nodes--toSubscriptInline :: Inline -> Maybe Inline-toSubscriptInline Space = Just Space-toSubscriptInline (Span attr ils) = Span attr <$> traverse toSubscriptInline ils-toSubscriptInline (Str s) = Str . T.pack <$> traverse toSubscript (T.unpack s)-toSubscriptInline LineBreak = Just LineBreak-toSubscriptInline SoftBreak = Just SoftBreak-toSubscriptInline _ = Nothing+import Text.Pandoc.Writers.Markdown (writeCommonMark) -toSuperscriptInline :: Inline -> Maybe Inline-toSuperscriptInline Space = Just Space-toSuperscriptInline (Span attr ils) = Span attr <$> traverse toSuperscriptInline ils-toSuperscriptInline (Str s) = Str . T.pack <$> traverse toSuperscript (T.unpack s)-toSuperscriptInline LineBreak = Just LineBreak-toSuperscriptInline SoftBreak = Just SoftBreak-toSuperscriptInline _ = Nothing
src/Text/Pandoc/Writers/Docx.hs view
@@ -210,8 +210,11 @@ => WriterOptions -- ^ Writer options -> Pandoc -- ^ Document to convert -> m BL.ByteString-writeDocx opts doc@(Pandoc meta _) = do- let doc' = walk fixDisplayMath doc+writeDocx opts doc = do+ let Pandoc meta blocks = walk fixDisplayMath doc+ let blocks' = makeSections True Nothing blocks+ let doc' = Pandoc meta blocks'+ username <- P.lookupEnv "USERNAME" utctime <- P.getCurrentTime oldUserDataDir <- P.getUserDataDir@@ -898,11 +901,21 @@ header <- dirmod $ stylemod $ blocksToOpenXML opts hs contents <- dirmod $ bibmod $ stylemod $ blocksToOpenXML opts bs' wrapBookmark ident $ header <> contents-blockToOpenXML' opts (Header lev (ident,_,_) lst) = do+blockToOpenXML' opts (Header lev (ident,_,kvs) lst) = do setFirstPara paraProps <- withParaPropM (pStyleM (fromString $ "Heading "++show lev)) $ getParaProps False- contents <- inlinesToOpenXML opts lst+ number <-+ if writerNumberSections opts+ then+ case lookup "number" kvs of+ Just n -> do+ num <- withTextPropM (rStyleM "SectionNumber")+ (inlineToOpenXML opts (Str n))+ return $ num ++ [mknode "w:r" [] [mknode "w:tab" [] ()]]+ Nothing -> return []+ else return []+ contents <- (number ++) <$> inlinesToOpenXML opts lst if T.null ident then return [mknode "w:p" [] (paraProps ++ contents)] else do
src/Text/Pandoc/Writers/HTML.hs view
@@ -1,6 +1,7 @@ {-# LANGUAGE MultiWayIf #-} {-# LANGUAGE OverloadedStrings #-} {-# LANGUAGE ScopedTypeVariables #-}+{-# LANGUAGE TypeApplications #-} {-# LANGUAGE ViewPatterns #-} {- | Module : Text.Pandoc.Writers.HTML@@ -587,11 +588,18 @@ => WriterOptions -> Attr -> [Inline] -> (Text, Text) -> StateT WriterState m Html figure opts attr txt (s,tit) = do- img <- inlineToHtml opts (Image attr [Str ""] (s,tit)) html5 <- gets stHtml5+ -- Screen-readers will normally read the @alt@ text and the figure; we+ -- want to avoid them reading the same text twice. With HTML5 we can+ -- use aria-hidden for the caption; with HTML4, we use an empty+ -- alt-text instead.+ let alt = if html5 then txt else [Str ""] let tocapt = if html5- then H5.figcaption+ then H5.figcaption !+ H5.customAttribute (textTag "aria-hidden")+ (toValue @Text "true") else H.p ! A.class_ "caption"+ img <- inlineToHtml opts (Image attr alt (s,tit)) capt <- if null txt then return mempty else tocapt `fmap` inlineListToHtml opts txt
src/Text/Pandoc/Writers/Jira.hs view
@@ -194,7 +194,7 @@ Jira.Monospaced (escapeSpecialChars cs) Emph xs -> styled Jira.Emphasis xs Underline xs -> styled Jira.Insert xs- Image attr _ tgt -> imageToJira attr (fst tgt) (snd tgt)+ Image attr cap tgt -> imageToJira attr cap (fst tgt) (snd tgt) LineBreak -> pure . singleton $ Jira.Linebreak Link attr xs tgt -> toJiraLink attr tgt xs Math mtype cs -> mathToJira mtype cs@@ -233,16 +233,18 @@ Left _ -> singleton $ Jira.Str t imageToJira :: PandocMonad m- => Attr -> Text -> Text+ => Attr -> [Inline] -> Text -> Text -> JiraConverter m [Jira.Inline]-imageToJira (_, classes, kvs) src title =- let imgParams = if "thumbnail" `elem` classes- then [Jira.Parameter "thumbnail" ""]- else map (uncurry Jira.Parameter) kvs- imgParams' = if T.null title- then imgParams- else Jira.Parameter "title" title : imgParams- in pure . singleton $ Jira.Image imgParams' (Jira.URL src)+imageToJira (_, classes, kvs) caption src title =+ let imageWithParams ps = Jira.Image ps (Jira.URL src)+ alt = stringify caption+ in pure . singleton . imageWithParams $+ if "thumbnail" `elem` classes+ then [Jira.Parameter "thumbnail" ""]+ else map (uncurry Jira.Parameter)+ . (if T.null title then id else (("title", title):))+ . (if T.null alt then id else (("alt", alt):))+ $ kvs -- | Creates a Jira Link element. toJiraLink :: PandocMonad m
src/Text/Pandoc/Writers/Markdown.hs view
@@ -16,7 +16,10 @@ Markdown: <http://daringfireball.net/projects/markdown/> -}-module Text.Pandoc.Writers.Markdown (writeMarkdown, writePlain) where+module Text.Pandoc.Writers.Markdown (+ writeMarkdown,+ writeCommonMark,+ writePlain) where import Control.Monad.Reader import Control.Monad.State.Strict import Data.Char (isAlphaNum)@@ -44,6 +47,7 @@ import Text.Pandoc.Writers.HTML (writeHtml5String) import Text.Pandoc.Writers.Math (texMathToInlines) import Text.Pandoc.XML (toHtml5Entities)+import Data.Coerce (coerce) type Notes = [[Block]] type Ref = (Text, Target, Attr)@@ -55,15 +59,21 @@ evalMD md env st = evalStateT (runReaderT md env) st data WriterEnv = WriterEnv { envInList :: Bool- , envPlain :: Bool+ , envVariant :: MarkdownVariant , envRefShortcutable :: Bool , envBlockLevel :: Int , envEscapeSpaces :: Bool } +data MarkdownVariant =+ PlainText+ | Commonmark+ | Markdown+ deriving (Show, Eq)+ instance Default WriterEnv- where def = WriterEnv { envInList = False- , envPlain = False+ where def = WriterEnv { envInList = False+ , envVariant = Markdown , envRefShortcutable = True , envBlockLevel = 0 , envEscapeSpaces = False@@ -102,8 +112,13 @@ -- pictures, or inline formatting). writePlain :: PandocMonad m => WriterOptions -> Pandoc -> m Text writePlain opts document =- evalMD (pandocToMarkdown opts document) def{ envPlain = True } def+ evalMD (pandocToMarkdown opts document) def{ envVariant = PlainText } def +-- | Convert Pandoc to Commonmark.+writeCommonMark :: PandocMonad m => WriterOptions -> Pandoc -> m Text+writeCommonMark opts document =+ evalMD (pandocToMarkdown opts document) def{ envVariant = Commonmark } def+ pandocTitleBlock :: Doc Text -> [Doc Text] -> Doc Text -> Doc Text pandocTitleBlock tit auths dat = hang 2 (text "% ") tit <> cr <>@@ -187,7 +202,7 @@ let colwidth = if writerWrapText opts == WrapAuto then Just $ writerColumns opts else Nothing- isPlain <- asks envPlain+ variant <- asks envVariant metadata <- metaToContext' (blockListToMarkdown opts) (inlineListToMarkdown opts)@@ -196,7 +211,7 @@ let authors' = fromMaybe [] $ getField "author" metadata let date' = fromMaybe empty $ getField "date" metadata let titleblock = case writerTemplate opts of- Just _ | isPlain ->+ Just _ | variant == PlainText -> plainTitleBlock title' authors' date' | isEnabled Ext_yaml_metadata_block opts -> yamlMetadataBlock metadata@@ -276,10 +291,7 @@ -- | Escape special characters for Markdown. escapeText :: WriterOptions -> Text -> Text-escapeText opts =- (if writerPreferAscii opts- then toHtml5Entities- else id) . T.pack . go . T.unpack+escapeText opts = T.pack . go . T.unpack where go [] = [] go (c:cs) =@@ -422,7 +434,7 @@ attrs' = (id',classes',("markdown","1"):kvs') blockToMarkdown' opts (Plain inlines) = do -- escape if para starts with ordered list marker- isPlain <- asks envPlain+ variant <- asks envVariant let escapeMarker = T.concatMap $ \x -> if x `elemText` ".()" then T.pack ['\\', x] else T.singleton x@@ -430,17 +442,15 @@ startsWithSpace (SoftBreak:_) = True startsWithSpace _ = False let inlines' =- if isPlain+ if variant == PlainText then inlines else case inlines of (Str t:ys)- | not isPlain- , (null ys || startsWithSpace ys)+ | (null ys || startsWithSpace ys) , beginsWithOrderedListMarker t -> RawInline (Format "markdown") (escapeMarker t):ys (Str t:_)- | not isPlain- , t == "+" || t == "-" ||+ | t == "+" || t == "-" || (t == "%" && isEnabled Ext_pandoc_title_block opts && isEnabled Ext_all_symbols_escapable opts) -> RawInline (Format "markdown") "\\" : inlines@@ -465,19 +475,19 @@ return $ (vcat $ map (hang 2 (literal "| ")) mdLines) <> blankline else blockToMarkdown opts $ linesToPara lns blockToMarkdown' opts b@(RawBlock f str) = do- plain <- asks envPlain+ variant <- asks envVariant let Format fmt = f let rawAttribBlock = return $ (literal "```{=" <> literal fmt <> "}") $$ literal str $$ (literal "```" <> literal "\n") let renderEmpty = mempty <$ report (BlockNotRendered b)- case () of- _ | plain -> renderEmpty- | isEnabled Ext_raw_attribute opts -> rawAttribBlock- | f `elem` ["markdown", "markdown_github", "markdown_phpextra",+ case variant of+ PlainText -> renderEmpty+ _ | f `elem` ["markdown", "markdown_github", "markdown_phpextra", "markdown_mmd", "markdown_strict"] -> return $ literal str <> literal "\n"+ | isEnabled Ext_raw_attribute opts -> rawAttribBlock | f `elem` ["html", "html5", "html4"] -> case () of _ | isEnabled Ext_markdown_attribute opts -> return $@@ -503,7 +513,7 @@ then notesAndRefs opts else return empty - plain <- asks envPlain+ variant <- asks envVariant -- we calculate the id that would be used by auto_identifiers -- so we know whether to print an explicit identifier ids <- gets stIds@@ -521,19 +531,20 @@ contents <- inlineListToMarkdown opts $ -- ensure no newlines; see #3736 walk lineBreakToSpace $- if level == 1 && plain && isEnabled Ext_gutenberg opts- then capitalize inlines- else inlines+ if level == 1 && variant == PlainText &&+ isEnabled Ext_gutenberg opts+ then capitalize inlines+ else inlines let setext = writerSetextHeaders opts hdr = nowrap $ case level of- 1 | plain ->+ 1 | variant == PlainText -> if isEnabled Ext_gutenberg opts then blanklines 3 <> contents <> blanklines 2 else contents <> blankline | setext -> contents <> attr' <> cr <> literal (T.replicate (offset contents) "=") <> blankline- 2 | plain ->+ 2 | variant == PlainText -> if isEnabled Ext_gutenberg opts then blanklines 2 <> contents <> blankline else contents <> blankline@@ -541,7 +552,7 @@ contents <> attr' <> cr <> literal (T.replicate (offset contents) "-") <> blankline -- ghc interprets '#' characters in column 1 as linenum specifiers.- _ | plain || isEnabled Ext_literate_haskell opts ->+ _ | variant == PlainText || isEnabled Ext_literate_haskell opts -> contents <> blankline _ -> literal (T.replicate level "#") <> space <> contents <> attr' <> blankline @@ -571,12 +582,12 @@ (_,(cls:_),_) -> " " <> literal cls _ -> empty blockToMarkdown' opts (BlockQuote blocks) = do- plain <- asks envPlain+ variant <- asks envVariant -- if we're writing literate haskell, put a space before the bird tracks -- so they won't be interpreted as lhs... let leader = if isEnabled Ext_literate_haskell opts then " > "- else if plain then " " else "> "+ else if variant == PlainText then " " else "> " contents <- blockListToMarkdown opts blocks return $ (prefixed leader contents) <> blankline blockToMarkdown' opts t@(Table _ blkCapt specs thead tbody tfoot) = do@@ -584,9 +595,12 @@ let numcols = maximum (length aligns : length widths : map length (headers:rows)) caption' <- inlineListToMarkdown opts caption- let caption'' = if null caption || not (isEnabled Ext_table_captions opts)+ let caption'' = if null caption then blankline- else blankline $$ (": " <> caption') $$ blankline+ else+ if isEnabled Ext_table_captions opts+ then blankline $$ (": " <> caption') $$ blankline+ else blankline $$ caption' $$ blankline let hasSimpleCells = onlySimpleTableCells $ headers : rows let isSimple = hasSimpleCells && all (==0) widths let isPlainBlock (Plain _) = True@@ -806,8 +820,8 @@ if isEnabled Ext_definition_lists opts then do let tabStop = writerTabStop opts- isPlain <- asks envPlain- let leader = if isPlain then " " else ": "+ variant <- asks envVariant+ let leader = if variant == PlainText then " " else ": " let sps = case writerTabStop opts - 3 of n | n > 0 -> literal $ T.replicate n " " _ -> literal " "@@ -836,7 +850,7 @@ -> MD m (Doc Text) blockListToMarkdown opts blocks = do inlist <- asks envInList- isPlain <- asks envPlain+ variant <- asks envVariant -- a) insert comment between list and indented code block, or the -- code block will be treated as a list continuation paragraph -- b) change Plain to Para unless it's followed by a RawBlock@@ -870,7 +884,7 @@ isListBlock (OrderedList _ _) = True isListBlock (DefinitionList _) = True isListBlock _ = False- commentSep = if isPlain+ commentSep = if variant == PlainText then Null else if isEnabled Ext_raw_html opts then RawBlock "html" "<!-- -->\n"@@ -890,6 +904,7 @@ prevRefs <- gets stPrevRefs refs <- gets stRefs i <- (+ 1) <$> gets stLastIdx+ modify $ \s -> s{ stLastIdx = i } let refLbls = map (\(r,_,_) -> r) $ prevRefs ++ refs return $ findUsableIndex refLbls i @@ -902,12 +917,15 @@ Just (ref, _, _) -> return ref Nothing -> do keys <- gets stKeys- case M.lookup (getKey label) keys of+ let key = getKey label+ let rawkey = coerce key+ case M.lookup key keys of Nothing -> do -- no other refs with this label- (lab', idx) <- if isEmpty label+ (lab', idx) <- if T.null rawkey ||+ T.length rawkey > 999 ||+ T.any (\c -> c == '[' || c == ']') rawkey then do i <- getNextIndex- modify $ \s -> s{ stLastIdx = i } return (tshow i, i) else return (render Nothing label, 0)@@ -934,11 +952,10 @@ return lab' Nothing -> do -- but this one is to a new target i <- getNextIndex- modify $ \s -> s{ stLastIdx = i } let lab' = tshow i modify (\s -> s{ stRefs = (lab', target, attr) : refs,- stKeys = M.insert (getKey label)+ stKeys = M.insert key (M.insert (target, attr) i km) (stKeys s) }) return lab'@@ -1022,11 +1039,11 @@ return $ ":" <> literal emojiname <> ":" _ -> inlineToMarkdown opts (Str s) inlineToMarkdown opts (Span attrs ils) = do- plain <- asks envPlain+ variant <- asks envVariant contents <- inlineListToMarkdown opts ils- return $ case plain of- True -> contents- False | attrs == nullAttr -> contents+ return $ case variant of+ PlainText -> contents+ _ | attrs == nullAttr -> contents | isEnabled Ext_bracketed_spans opts -> let attrs' = if attrs /= nullAttr then attrsToMarkdown attrs@@ -1038,20 +1055,20 @@ | otherwise -> contents inlineToMarkdown _ (Emph []) = return empty inlineToMarkdown opts (Emph lst) = do- plain <- asks envPlain+ variant <- asks envVariant contents <- inlineListToMarkdown opts lst- return $ if plain- then if isEnabled Ext_gutenberg opts- then "_" <> contents <> "_"- else contents- else "*" <> contents <> "*"+ return $ case variant of+ PlainText+ | isEnabled Ext_gutenberg opts -> "_" <> contents <> "_"+ | otherwise -> contents+ _ -> "*" <> contents <> "*" inlineToMarkdown _ (Underline []) = return empty inlineToMarkdown opts (Underline lst) = do- plain <- asks envPlain+ variant <- asks envVariant contents <- inlineListToMarkdown opts lst- case plain of- True -> return contents- False | isEnabled Ext_bracketed_spans opts ->+ case variant of+ PlainText -> return contents+ _ | isEnabled Ext_bracketed_spans opts -> return $ "[" <> contents <> "]" <> "{.ul}" | isEnabled Ext_native_spans opts -> return $ tagWithAttrs "span" ("", ["underline"], [])@@ -1062,13 +1079,14 @@ | otherwise -> inlineToMarkdown opts (Emph lst) inlineToMarkdown _ (Strong []) = return empty inlineToMarkdown opts (Strong lst) = do- plain <- asks envPlain- if plain- then inlineListToMarkdown opts $- if isEnabled Ext_gutenberg opts- then capitalize lst- else lst- else do+ variant <- asks envVariant+ case variant of+ PlainText ->+ inlineListToMarkdown opts $+ if isEnabled Ext_gutenberg opts+ then capitalize lst+ else lst+ _ -> do contents <- inlineListToMarkdown opts lst return $ "**" <> contents <> "**" inlineToMarkdown _ (Strikeout []) = return empty@@ -1081,33 +1099,43 @@ else contents inlineToMarkdown _ (Superscript []) = return empty inlineToMarkdown opts (Superscript lst) =- local (\env -> env {envEscapeSpaces = True}) $ do+ local (\env -> env {envEscapeSpaces = (envVariant env == Markdown)}) $ do contents <- inlineListToMarkdown opts lst- return $ if isEnabled Ext_superscript opts- then "^" <> contents <> "^"- else if isEnabled Ext_raw_html opts- then "<sup>" <> contents <> "</sup>"- else- let rendered = render Nothing contents- in case mapM toSuperscript (T.unpack rendered) of- Just r -> literal $ T.pack r- Nothing -> literal $ "^(" <> rendered <> ")"+ if isEnabled Ext_superscript opts+ then return $ "^" <> contents <> "^"+ else if isEnabled Ext_raw_html opts+ then return $ "<sup>" <> contents <> "</sup>"+ else+ case traverse toSuperscriptInline lst of+ Just xs' | not (writerPreferAscii opts)+ -> inlineListToMarkdown opts xs'+ _ -> do+ let rendered = render Nothing contents+ return $+ case mapM toSuperscript (T.unpack rendered) of+ Just r -> literal $ T.pack r+ Nothing -> literal $ "^(" <> rendered <> ")" inlineToMarkdown _ (Subscript []) = return empty inlineToMarkdown opts (Subscript lst) =- local (\env -> env {envEscapeSpaces = True}) $ do+ local (\env -> env {envEscapeSpaces = (envVariant env == Markdown)}) $ do contents <- inlineListToMarkdown opts lst- return $ if isEnabled Ext_subscript opts- then "~" <> contents <> "~"- else if isEnabled Ext_raw_html opts- then "<sub>" <> contents <> "</sub>"- else- let rendered = render Nothing contents- in case mapM toSubscript (T.unpack rendered) of- Just r -> literal $ T.pack r- Nothing -> literal $ "_(" <> rendered <> ")"+ if isEnabled Ext_subscript opts+ then return $ "~" <> contents <> "~"+ else if isEnabled Ext_raw_html opts+ then return $ "<sub>" <> contents <> "</sub>"+ else+ case traverse toSubscriptInline lst of+ Just xs' | not (writerPreferAscii opts)+ -> inlineListToMarkdown opts xs'+ _ -> do+ let rendered = render Nothing contents+ return $+ case mapM toSuperscript (T.unpack rendered) of+ Just r -> literal $ T.pack r+ Nothing -> literal $ "_(" <> rendered <> ")" inlineToMarkdown opts (SmallCaps lst) = do- plain <- asks envPlain- if not plain &&+ variant <- asks envVariant+ if variant /= PlainText && (isEnabled Ext_raw_html opts || isEnabled Ext_native_spans opts) then inlineToMarkdown opts (Span ("",["smallcaps"],[]) lst) else inlineListToMarkdown opts $ capitalize lst@@ -1137,18 +1165,22 @@ let attrs = if isEnabled Ext_inline_code_attributes opts && attr /= nullAttr then attrsToMarkdown attr else empty- plain <- asks envPlain- if plain- then return $ literal str- else return $ literal (marker <> spacer <> str <> spacer <> marker) <> attrs+ variant <- asks envVariant+ case variant of+ PlainText -> return $ literal str+ _ -> return $ literal+ (marker <> spacer <> str <> spacer <> marker) <> attrs inlineToMarkdown opts (Str str) = do- isPlain <- asks envPlain- let str' = (if isEnabled Ext_smart opts+ variant <- asks envVariant+ let str' = (if writerPreferAscii opts+ then toHtml5Entities+ else id) .+ (if isEnabled Ext_smart opts then unsmartify opts- else id) $- if isPlain- then str- else escapeText opts str+ else id) .+ (if variant == PlainText+ then id+ else escapeText opts) $ str return $ literal str' inlineToMarkdown opts (Math InlineMath str) = case writerHTMLMathMethod opts of@@ -1161,10 +1193,10 @@ | isEnabled Ext_tex_math_double_backslash opts -> return $ "\\\\(" <> literal str <> "\\\\)" | otherwise -> do- plain <- asks envPlain+ variant <- asks envVariant texMathToInlines InlineMath str >>= inlineListToMarkdown opts .- (if plain then makeMathPlainer else id)+ (if variant == PlainText then makeMathPlainer else id) inlineToMarkdown opts (Math DisplayMath str) = case writerHTMLMathMethod opts of WebTeX url -> (\x -> blankline <> x <> blankline) `fmap`@@ -1183,15 +1215,15 @@ let numticks = if null tickGroups then 1 else 1 + maximum (map T.length tickGroups)- plain <- asks envPlain+ variant <- asks envVariant let Format fmt = f let rawAttribInline = return $ literal (T.replicate numticks "`") <> literal str <> literal (T.replicate numticks "`") <> literal "{=" <> literal fmt <> literal "}" let renderEmpty = mempty <$ report (InlineNotRendered il)- case () of- _ | plain -> renderEmpty- | f `elem` ["markdown", "markdown_github", "markdown_phpextra",+ case variant of+ PlainText -> renderEmpty+ _ | f `elem` ["markdown", "markdown_github", "markdown_phpextra", "markdown_mmd", "markdown_strict"] -> return $ literal str | isEnabled Ext_raw_attribute opts -> rawAttribInline@@ -1207,8 +1239,8 @@ | otherwise -> renderEmpty | otherwise -> renderEmpty inlineToMarkdown opts LineBreak = do- plain <- asks envPlain- if plain || isEnabled Ext_hard_line_breaks opts+ variant <- asks envVariant+ if variant == PlainText || isEnabled Ext_hard_line_breaks opts then return cr else return $ if isEnabled Ext_escaped_line_breaks opts@@ -1261,7 +1293,7 @@ (literal . T.strip) <$> writeHtml5String opts{ writerTemplate = Nothing } (Pandoc nullMeta [Plain [lnk]]) | otherwise = do- plain <- asks envPlain+ variant <- asks envVariant linktext <- inlineListToMarkdown opts txt let linktitle = if T.null tit then empty@@ -1279,9 +1311,9 @@ then literal <$> getReference attr linktext (src, tit) else return mempty return $ if useAuto- then if plain- then literal srcSuffix- else "<" <> literal srcSuffix <> ">"+ then case variant of+ PlainText -> literal srcSuffix+ _ -> "<" <> literal srcSuffix <> ">" else if useRefLinks then let first = "[" <> linktext <> "]" second = if getKey linktext == getKey reftext@@ -1290,9 +1322,9 @@ else "[]" else "[" <> reftext <> "]" in first <> second- else if plain- then linktext- else "[" <> linktext <> "](" <>+ else case variant of+ PlainText -> linktext+ _ -> "[" <> linktext <> "](" <> literal src <> linktitle <> ")" <> linkAttributes opts attr inlineToMarkdown opts img@(Image attr alternate (source, tit))@@ -1302,15 +1334,15 @@ (literal . T.strip) <$> writeHtml5String opts{ writerTemplate = Nothing } (Pandoc nullMeta [Plain [img]]) | otherwise = do- plain <- asks envPlain+ variant <- asks envVariant let txt = if null alternate || alternate == [Str source] -- to prevent autolinks then [Str ""] else alternate linkPart <- inlineToMarkdown opts (Link attr txt (source, tit))- return $ if plain- then "[" <> linkPart <> "]"- else "!" <> linkPart+ return $ case variant of+ PlainText -> "[" <> linkPart <> "]"+ _ -> "!" <> linkPart inlineToMarkdown opts (Note contents) = do modify (\st -> st{ stNotes = contents : stNotes st }) st <- get@@ -1329,3 +1361,19 @@ lineBreakToSpace LineBreak = Space lineBreakToSpace SoftBreak = Space lineBreakToSpace x = x++toSubscriptInline :: Inline -> Maybe Inline+toSubscriptInline Space = Just Space+toSubscriptInline (Span attr ils) = Span attr <$> traverse toSubscriptInline ils+toSubscriptInline (Str s) = Str . T.pack <$> traverse toSubscript (T.unpack s)+toSubscriptInline LineBreak = Just LineBreak+toSubscriptInline SoftBreak = Just SoftBreak+toSubscriptInline _ = Nothing++toSuperscriptInline :: Inline -> Maybe Inline+toSuperscriptInline Space = Just Space+toSuperscriptInline (Span attr ils) = Span attr <$> traverse toSuperscriptInline ils+toSuperscriptInline (Str s) = Str . T.pack <$> traverse toSuperscript (T.unpack s)+toSuperscriptInline LineBreak = Just LineBreak+toSuperscriptInline SoftBreak = Just SoftBreak+toSuperscriptInline _ = Nothing
src/Text/Pandoc/Writers/Ms.hs view
@@ -204,7 +204,9 @@ literal ".IP" $$ literal ".nf" $$ literal "\\f[C]" $$- hlCode $$+ ((case T.uncons str of+ Just ('.',_) -> literal "\\&"+ _ -> mempty) <> hlCode) $$ literal "\\f[]" $$ literal ".fi" blockToMs opts (LineBlock ls) = do@@ -517,11 +519,11 @@ msFormatter :: WriterOptions -> FormatOptions -> [SourceLine] -> Doc Text msFormatter opts _fmtopts =- vcat . map fmtLine- where fmtLine = hcat . map fmtToken- fmtToken (toktype, tok) = literal "\\*" <>- brackets (literal (tshow toktype) <> literal " \""- <> literal (escapeStr opts tok) <> literal "\"")+ literal . T.intercalate "\n" . map fmtLine+ where+ fmtLine = mconcat . map fmtToken+ fmtToken (toktype, tok) =+ "\\*[" <> (tshow toktype) <> " \"" <> (escapeStr opts tok) <> "\"]" highlightCode :: PandocMonad m => WriterOptions -> Attr -> Text -> MS m (Doc Text) highlightCode opts attr str =
stack.yaml view
@@ -27,6 +27,10 @@ - HsYAML-0.2.1.0 - HsYAML-aeson-0.2.0.0 - doctemplates-0.8.2+- commonmark-0.1.0.1+- commonmark-extensions-0.2.0.0+- commonmark-pandoc-0.2.0.0+ ghc-options: "$locals": -fhide-source-paths -Wno-missing-home-modules resolver: lts-14.6
test/Tests/Readers/LaTeX.hs view
@@ -35,13 +35,17 @@ => String -> (Text, c) -> TestTree (=:) = test latex -simpleTable' :: [Alignment] -> [[Blocks]] -> Blocks-simpleTable' aligns rows+table' :: [Alignment] -> [Row] -> Blocks+table' aligns rows = table emptyCaption (zip aligns (repeat ColWidthDefault)) (TableHead nullAttr [])- [TableBody nullAttr 0 [] $ map toRow rows]+ [TableBody nullAttr 0 [] rows] (TableFoot nullAttr [])++simpleTable' :: [Alignment] -> [[Blocks]] -> Blocks+simpleTable' aligns rows+ = table' aligns (map toRow rows) where toRow = Row nullAttr . map simpleCell @@ -137,6 +141,54 @@ , "Table with vertical alignment argument" =: "\\begin{tabular}[t]{r|r}One & Two\\\\ \\end{tabular}" =?> simpleTable' [AlignRight,AlignRight] [[plain "One", plain "Two"]]+ , "Table with multicolumn item" =:+ "\\begin{tabular}{l c r}\\multicolumn{2}{c}{One} & Two\\\\ \\end{tabular}" =?>+ table' [AlignLeft, AlignCenter, AlignRight]+ [ Row nullAttr [ cell AlignCenter (RowSpan 1) (ColSpan 2) (plain "One")+ , simpleCell (plain "Two")+ ]+ ]+ , "Table with multirow item" =:+ T.unlines ["\\begin{tabular}{c}"+ ,"\\multirow{2}{c}{One}\\\\Two\\\\"+ ,"\\end{tabular}"+ ] =?>+ table' [AlignCenter]+ [ Row nullAttr [ cell AlignCenter (RowSpan 2) (ColSpan 1) (plain "One") ]+ , Row nullAttr [ simpleCell (plain "Two") ]+ ]+ , "Table with nested multirow/multicolumn item" =:+ T.unlines [ "\\begin{tabular}{c c c}"+ , "\\multirow{2}{c}{\\multicolumn{2}{c}{One}}&Two\\\\"+ , "Three\\\\"+ , "Four&Five&Six\\\\"+ , "\\end{tabular}"+ ] =?>+ table' [AlignCenter, AlignCenter, AlignCenter]+ [ Row nullAttr [ cell AlignCenter (RowSpan 2) (ColSpan 2) (plain "One")+ , simpleCell (plain "Two")+ ]+ , Row nullAttr [ simpleCell (plain "Three") ]+ , Row nullAttr [ simpleCell (plain "Four") + , simpleCell (plain "Five")+ , simpleCell (plain "Six")+ ]+ ]+ , "Table with multicolumn header" =:+ T.unlines [ "\\begin{tabular}{ |l|l| }"+ , "\\hline\\multicolumn{2}{|c|}{Header}\\\\" + , "\\hline key & val\\\\" + , "\\hline\\end{tabular}"+ ] =?>+ table emptyCaption+ (zip [AlignLeft, AlignLeft] (repeat ColWidthDefault))+ (TableHead nullAttr [ Row nullAttr [cell AlignCenter (RowSpan 1) (ColSpan 2) (plain "Header")]])+ [TableBody nullAttr 0 [] [Row nullAttr [ simpleCell (plain "key")+ , simpleCell (plain "val")+ ]+ ]+ ]+ (TableFoot nullAttr []) ] , testGroup "citations"
test/Tests/Readers/Org/Directive.hs view
@@ -150,6 +150,28 @@ ] =?> Pandoc nullMeta mempty + , "disable MathML-like entities" =:+ T.unlines [ "#+OPTIONS: e:nil"+ , "Icelandic letter: \\thorn"+ ] =?>+ para "Icelandic letter: \\thorn"++ , testGroup "Option f"+ [ "disable inline footnotes" =:+ T.unlines [ "#+OPTIONS: f:nil"+ , "Funny![fn:funny:or not]"+ ] =?>+ para "Funny!"++ , "disable reference footnotes" =:+ T.unlines [ "#+OPTIONS: f:nil"+ , "Burn everything[fn:1] down!"+ , ""+ , "[fn:2] Not quite everything."+ ] =?>+ para "Burn everything down!"+ ]+ , "disable inclusion of todo keywords" =: T.unlines [ "#+OPTIONS: todo:nil" , "** DONE todo export"@@ -256,6 +278,14 @@ , "* Wichtig" ] =?> headerWith ("wichtig", mempty, mempty) 1 "Wichtig"+ ]++ , testGroup "Option |"+ [ "disable export of tables" =:+ T.unlines [ "#+OPTIONS: |:nil"+ , "| chair |"+ ] =?>+ (mempty :: Blocks) ] , testGroup "unknown options"
+ test/Tests/Writers/Ms.hs view
@@ -0,0 +1,37 @@+{-# LANGUAGE NoImplicitPrelude #-}+{-# LANGUAGE OverloadedStrings #-}+module Tests.Writers.Ms (tests) where++import Prelude+import Test.Tasty+import Tests.Helpers+import Text.Pandoc+import Text.Pandoc.Builder++infix 4 =:+(=:) :: (ToString a, ToPandoc a)+ => String -> (a, String) -> TestTree+(=:) = test (purely (writeMs def . toPandoc))++tests :: [TestTree]+tests = [ testGroup "code blocks"+ [ "basic"+ =: codeBlock "hello"+ =?> unlines+ [ ".IP"+ , ".nf"+ , "\\f[C]"+ , "hello"+ , "\\f[]"+ , ".fi"]+ , "escape starting ."+ =: codeBlock ". hello"+ =?> unlines+ [ ".IP"+ , ".nf"+ , "\\f[C]"+ , "\\&. hello"+ , "\\f[]"+ , ".fi"]+ ]+ ]
+ test/command/01.csv view
@@ -0,0 +1,4 @@+"Column1";"Column2"+"Data1";"- data1++- data2"
+ test/command/1608.md view
@@ -0,0 +1,41 @@+```+% pandoc -f latex -t native+\newtheorem{theorem}{Theorem}+\newtheorem{corollary}[theorem]{Corollary}+\newtheorem{lemma}[theorem]{Lemma}+\theoremstyle{definition}+\newtheorem{definition}[theorem]{Definition}+\theoremstyle{remark}+\newtheorem{remark}{Remark}++\begin{definition}[right-angled triangles] \label{def:tri}+A \emph{right-angled triangle} is a triangle whose sides of length~\(a\), \(b\) and~\(c\), in some permutation of order, satisfies \(a^2+b^2=c^2\).+\end{definition}++\begin{lemma}+The triangle with sides of length~\(3\), \(4\) and~\(5\) is right-angled.+\end{lemma}++\begin{proof}+This lemma follows from \cref{def:tri} since \(3^2+4^2=9+16=25=5^2\).+\end{proof}++\begin{theorem}[Pythagorean triplets] \label{thm:py}+Triangles with sides of length \(a=p^2-q^2\), \(b=2pq\) and \(c=p^2+q^2\) are right-angled triangles.+\end{theorem}++\begin{remark}+These are all pretty interesting facts.+\end{remark}+^D+[Div ("def:tri",["definition"],[])+ [Para [Strong [Str "Definition",Space,Str "1"],Space,Str "(right-angled",Space,Str "triangles).",Space,Space,Str "A",Space,Emph [Str "right-angled",Space,Str "triangle"],Space,Str "is",Space,Str "a",Space,Str "triangle",Space,Str "whose",Space,Str "sides",Space,Str "of",Space,Str "length\160",Math InlineMath "a",Str ",",Space,Math InlineMath "b",Space,Str "and\160",Math InlineMath "c",Str ",",Space,Str "in",Space,Str "some",Space,Str "permutation",Space,Str "of",Space,Str "order,",Space,Str "satisfies",Space,Math InlineMath "a^2+b^2=c^2",Str "."]]+,Div ("",["lemma"],[])+ [Para [Strong [Str "Lemma",Space,Str "2"],Str ".",Space,Space,Emph [Str "The",Space,Str "triangle",Space,Str "with",Space,Str "sides",Space,Str "of",Space,Str "length\160",Math InlineMath "3",Str ",",Space,Math InlineMath "4",Space,Str "and\160",Math InlineMath "5",Space,Str "is",Space,Str "right-angled."]]]+,Div ("",["proof"],[])+ [Para [Emph [Str "Proof."],Space,Str "This",Space,Str "lemma",Space,Str "follows",Space,Str "from",Space,Link ("",[],[("reference-type","ref"),("reference","def:tri")]) [Str "Definition",Str "\160",Str "1"] ("#def:tri",""),Space,Str "since",Space,Math InlineMath "3^2+4^2=9+16=25=5^2",Str ".",Str "\160\9723"]]+,Div ("thm:py",["theorem"],[])+ [Para [Strong [Str "Theorem",Space,Str "3"],Space,Str "(Pythagorean",Space,Str "triplets).",Space,Space,Emph [Str "Triangles",Space,Str "with",Space,Str "sides",Space,Str "of",Space,Str "length",Space,Math InlineMath "a=p^2-q^2",Str ",",Space,Math InlineMath "b=2pq",Space,Str "and",Space,Math InlineMath "c=p^2+q^2",Space,Str "are",Space,Str "right-angled",Space,Str "triangles."]]]+,Div ("",["remark"],[])+ [Para [Emph [Str "Remark",Space,Str "1"],Str ".",Space,Space,Str "These",Space,Str "are",Space,Str "all",Space,Str "pretty",Space,Str "interesting",Space,Str "facts."]]]+```
test/command/3577.md view
@@ -16,10 +16,10 @@ \end{figure} ^D <figure>-<img src="img1.jpg" alt="" /><figcaption>Caption 1</figcaption>+<img src="img1.jpg" alt="Caption 1" /><figcaption aria-hidden="true">Caption 1</figcaption> </figure> <figure>-<img src="img2.jpg" alt="" /><figcaption>Caption 2</figcaption>+<img src="img2.jpg" alt="Caption 2" /><figcaption aria-hidden="true">Caption 2</figcaption> </figure> ``` ```@@ -30,6 +30,6 @@ \end{figure} ^D <figure>-<img src="img1.jpg" alt="" /><figcaption>Caption 3</figcaption>+<img src="img1.jpg" alt="Caption 3" /><figcaption aria-hidden="true">Caption 3</figcaption> </figure> ```
test/command/3587.md view
@@ -55,3 +55,62 @@ [Para [Str "18.2\160\176C"]] ``` +# SIRange tests++## Integer range with simple common units++```+% pandoc -f latex -t native+\SIRange{10}{20}{\gram}+^D+[Para [Str "10\160g\8211\&20\160g"]]+```+```+% pandoc -f latex -t native+\SIRange{35}{9}{\milli\meter}+^D+[Para [Str "35\160mm\8211\&9\160mm"]]+```+```+% pandoc -f latex -t native+\SIRange{4}{97367265}{\celsius}+^D+[Para [Str "4\160\176C\8211\&97367265\160\176C"]]+```++## Decimal range with simple units++```+% pandoc -f latex -t native+\SIRange{4.5}{97367265.5}{\celsius}+^D+[Para [Str "4.5\160\176C\8211\&97367265.5\160\176C"]]+```++## Squared units++```+% pandoc -f latex -t native+\SIRange{10}{20}{\square\meter}+^D+[Para [Str "10\160m\178\8211\&20\160m\178"]]+```++## Ignore round precision++`round-precision` option appears to be ignored by `\SI` as of 7c6dbd37e, so+`\SIRange` will ignore it as well.++```+% pandoc -f latex -t native+\SIRange[round-precision=2]{10}{20}{\gram}+^D+[Para [Str "10\160g\8211\&20\160g"]]+```+```+% pandoc -f latex -t native+\SIRange[round-precision=2]{10.0}{20.25}{\gram}+^D+[Para [Str "10.0\160g\8211\&20.25\160g"]]+```+
test/command/3734.md view
@@ -27,6 +27,6 @@ | aaaaaaaaaaaa | | cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc | ^D | aaaaaaaaaaaa | bbbbb | ccccccccccc |-| ------------ | ----- | ------------------------------------------------------------------------ |+|--------------|-------|--------------------------------------------------------------------------| | aaaaaaaaaaaa | | cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc | ```
test/command/4038.md view
@@ -1,5 +1,5 @@ ```-% pandoc -f gfm -t gfm+% pandoc -f gfm -t gfm --atx-headers # ~~Header~~ ^D # ~~Header~~
test/command/4528.md view
@@ -124,7 +124,7 @@ % pandoc --wrap=none -f html -t commonmark-raw_html This has <sub>subscript</sub> in it and <sub>2 3</sub> again. With emphasis: <sub><em>2</em> 3</sub>. With letters: <sub>foo</sub>. With a span: <sub><span class=foo>2</span></sub>. ^D-This has \_(subscript) in it and ₂ ₃ again. With emphasis: \_(*2* 3). With letters: \_(foo). With a span: ₂.+This has _(subscript) in it and ₂ ₃ again. With emphasis: _(*2* 3). With letters: _(foo). With a span: ₂. ``` ```
test/command/4677.md view
@@ -3,6 +3,6 @@ {#img:1} ^D <figure>-<img src="img.png" id="img:1" alt="" /><figcaption>Caption</figcaption>+<img src="img.png" id="img:1" alt="Caption" /><figcaption aria-hidden="true">Caption</figcaption> </figure> ```
test/command/5121.md view
@@ -5,7 +5,7 @@ ## Header 2 ^D <figure>-<img src="./my-figure.jpg" width="500" alt="" /><figcaption>My caption</figcaption>+<img src="./my-figure.jpg" width="500" alt="My caption" /><figcaption aria-hidden="true">My caption</figcaption> </figure> Header 2
test/command/5642.md view
@@ -3,6 +3,6 @@ {aria-describedby="barbaz"} ^D <figure>-<img src="foo" aria-describedby="barbaz" alt="" /><figcaption>test</figcaption>+<img src="foo" aria-describedby="barbaz" alt="test" /><figcaption aria-hidden="true">test</figcaption> </figure> ```
+ test/command/6549.md view
@@ -0,0 +1,26 @@+```+% pandoc -f rst+.. csv-table:: Test table+ :file: command/01.csv+ :delim: ;+ :header-rows: 1+^D+<table>+<caption>Test table</caption>+<thead>+<tr class="header">+<th>Column1</th>+<th>Column2</th>+</tr>+</thead>+<tbody>+<tr class="odd">+<td>Data1</td>+<td><ul>+<li>data1</li>+<li>data2</li>+</ul></td>+</tr>+</tbody>+</table>+```
test/command/gfm.md view
@@ -69,7 +69,7 @@ % pandoc -f gfm+smart -t native "hi" ^D-[Para [Str "\8220hi\8221"]]+[Para [Quoted DoubleQuote [Str "hi"]]] ``` ```@@ -100,7 +100,7 @@ [])] ^D | Fruit | Price |-| ------ | ----: |+|--------|------:| | apple | 0.13 | | orange | 1.12 | @@ -161,6 +161,6 @@ - [ ] foo - [x] bar ^D- - [ ] foo- - [x] bar+- [ ] foo+- [x] bar ```
test/docx/golden/block_quotes.docx view
binary file changed (10036 → 10052 bytes)
test/docx/golden/codeblock.docx view
binary file changed (9882 → 9904 bytes)
test/docx/golden/comments.docx view
binary file changed (10216 → 10239 bytes)
test/docx/golden/custom_style_no_reference.docx view
binary file changed (9980 → 10003 bytes)
test/docx/golden/custom_style_preserve.docx view
binary file changed (10606 → 10624 bytes)
test/docx/golden/definition_list.docx view
binary file changed (9873 → 9895 bytes)
test/docx/golden/document-properties-short-desc.docx view
binary file changed (9884 → 9906 bytes)
test/docx/golden/document-properties.docx view
binary file changed (10361 → 10384 bytes)
test/docx/golden/headers.docx view
binary file changed (10022 → 10040 bytes)
test/docx/golden/image.docx view
binary file changed (26698 → 26718 bytes)
test/docx/golden/inline_code.docx view
binary file changed (9817 → 9840 bytes)
test/docx/golden/inline_formatting.docx view
binary file changed (9989 → 10010 bytes)
test/docx/golden/inline_images.docx view
binary file changed (26753 → 26776 bytes)
test/docx/golden/link_in_notes.docx view
binary file changed (10039 → 10061 bytes)
test/docx/golden/links.docx view
binary file changed (10217 → 10236 bytes)
test/docx/golden/lists.docx view
binary file changed (10307 → 10325 bytes)
test/docx/golden/lists_continuing.docx view
binary file changed (10091 → 10113 bytes)
test/docx/golden/lists_restarting.docx view
binary file changed (10091 → 10113 bytes)
test/docx/golden/nested_anchors_in_header.docx view
binary file changed (10179 → 10199 bytes)
test/docx/golden/notes.docx view
binary file changed (9989 → 10006 bytes)
test/docx/golden/table_one_row.docx view
binary file changed (9863 → 9885 bytes)
test/docx/golden/table_with_list_cell.docx view
binary file changed (10238 → 10260 bytes)
test/docx/golden/tables.docx view
binary file changed (10252 → 10273 bytes)
test/docx/golden/track_changes_deletion.docx view
binary file changed (9861 → 9884 bytes)
test/docx/golden/track_changes_insertion.docx view
binary file changed (9844 → 9867 bytes)
test/docx/golden/track_changes_move.docx view
binary file changed (9878 → 9901 bytes)
test/docx/golden/unicode.docx view
binary file changed (9802 → 9825 bytes)
test/docx/golden/verbatim_subsuper.docx view
binary file changed (9850 → 9873 bytes)
test/docx/inline_formatting.native view
@@ -1,6 +1,6 @@ Pandoc (Meta {unMeta = fromList []}) [Para [Str "Regular",Space,Str "text",Space,Emph [Str "italics"],Space,Strong [Str "bold",Space,Emph [Str "bold",Space,Str "italics"]],Str "."] ,Para [Str "This",Space,Str "is",Space,SmallCaps [Str "Small",Space,Str "Caps"],Str ",",Space,Str "and",Space,Str "this",Space,Str "is",Space,Strikeout [Str "strikethrough"],Str "."]-,Para [Str "Some",Space,Str "people",Space,Str "use",Space,Underline [Str "single",Space,Str "underlines",Space,Str "for",Space],Emph [Underline [Str "emphasis"]],Str "."]+,Para [Str "Some",Space,Str "people",Space,Str "use",Space,Underline [Str "single",Space,Str "underlines",Space,Str "for",Space,Emph [Str "emphasis"]],Str "."] ,Para [Str "Above",Space,Str "the",Space,Str "line",Space,Str "is",Space,Superscript [Str "superscript"],Space,Str "and",Space,Str "below",Space,Str "the",Space,Str "line",Space,Str "is",Space,Subscript [Str "subscript"],Str "."] ,Para [Str "A",Space,Str "line",LineBreak,Str "break."]]
test/lhs-test.latex view
@@ -81,6 +81,9 @@ \providecommand{\tightlist}{% \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}} \setcounter{secnumdepth}{-\maxdimen} % remove section numbering+\ifluatex+ \usepackage{selnolig} % disable illegal ligatures+\fi \author{} \date{}
test/lhs-test.latex+lhs view
@@ -48,6 +48,9 @@ \providecommand{\tightlist}{% \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}} \setcounter{secnumdepth}{-\maxdimen} % remove section numbering+\ifluatex+ \usepackage{selnolig} % disable illegal ligatures+\fi \author{} \date{}
test/test-pandoc.hs view
@@ -37,6 +37,7 @@ import qualified Tests.Writers.Jira import qualified Tests.Writers.LaTeX import qualified Tests.Writers.Markdown+import qualified Tests.Writers.Ms import qualified Tests.Writers.Muse import qualified Tests.Writers.Native import qualified Tests.Writers.Org@@ -70,6 +71,7 @@ , testGroup "Muse" Tests.Writers.Muse.tests , testGroup "FB2" Tests.Writers.FB2.tests , testGroup "PowerPoint" Tests.Writers.Powerpoint.tests+ , testGroup "Ms" Tests.Writers.Ms.tests ] , testGroup "Readers" [ testGroup "LaTeX" Tests.Readers.LaTeX.tests
test/writer.html5 view
@@ -523,7 +523,7 @@ <h1 id="images">Images</h1> <p>From “Voyage dans la Lune” by Georges Melies (1902):</p> <figure>-<img src="lalune.jpg" title="Voyage dans la Lune" alt="" /><figcaption>lalune</figcaption>+<img src="lalune.jpg" title="Voyage dans la Lune" alt="lalune" /><figcaption aria-hidden="true">lalune</figcaption> </figure> <p>Here is a movie <img src="movie.jpg" alt="movie" /> icon.</p> <hr />
test/writer.jira view
@@ -513,9 +513,9 @@ h1. {anchor:images}Images From "Voyage dans la Lune" by Georges Melies \(1902): -!lalune.jpg|title=fig:Voyage dans la Lune!+!lalune.jpg|title=fig:Voyage dans la Lune, alt=lalune! -Here is a movie !movie.jpg! icon.+Here is a movie !movie.jpg|alt=movie! icon. ---- h1. {anchor:footnotes}Footnotes
test/writer.latex view
@@ -63,6 +63,9 @@ \providecommand{\tightlist}{% \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}} \setcounter{secnumdepth}{-\maxdimen} % remove section numbering+\ifluatex+ \usepackage{selnolig} % disable illegal ligatures+\fi \title{Pandoc Test Suite} \author{John MacFarlane \and Anonymous}
test/writers-lang-and-dir.latex view
@@ -66,6 +66,9 @@ \newcommand{\textfrench}[2][]{\foreignlanguage{french}{#2}} \newenvironment{french}[2][]{\begin{otherlanguage}{french}}{\end{otherlanguage}} \fi+\ifluatex+ \usepackage{selnolig} % disable illegal ligatures+\fi \ifxetex % Load bidi as late as possible as it modifies e.g. graphicx \usepackage{bidi}