diff --git a/AUTHORS.md b/AUTHORS.md --- a/AUTHORS.md +++ b/AUTHORS.md @@ -51,6 +51,7 @@ - David Lazar - David Röthlisberger - Denis Laxalde +- Derek Chen-Becker - Douglas Calvert - Emanuel Evans - Emily Eisenberg diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -144,10 +144,9 @@ 9. It is better not to introduce new dependencies. Dependencies on external C libraries should especially be avoided. -10. We aim for compatibility with ghc versions from 7.10.3 to the +10. We aim for compatibility with ghc versions from 8.0 to the latest release. All pull requests and commits are tested - automatically on , using GHC versions in the - `Tested-With` stanza of `pandoc.cabal`. + automatically on CircleCI. Tests ----- diff --git a/MANUAL.txt b/MANUAL.txt --- a/MANUAL.txt +++ b/MANUAL.txt @@ -1,6 +1,6 @@ % Pandoc User's Guide % John MacFarlane -% March 12, 2019 +% April 5, 2019 Synopsis ======== @@ -327,6 +327,7 @@ - `revealjs` ([reveal.js] HTML5 + JavaScript slide show) - `s5` ([S5] HTML and JavaScript slide show) - `tei` ([TEI Simple]) + - `xwiki` ([XWiki markup]) - `zimwiki` ([ZimWiki markup]) - the path of a custom lua writer, see [Custom writers] below ::: @@ -436,7 +437,7 @@ [XHTML]: http://www.w3.org/TR/xhtml1/ [LaTeX]: http://latex-project.org [`beamer`]: https://ctan.org/pkg/beamer -[Beamer User's Guide]: http://ctan.math.utah.edu/ctan/tex-archive/macros/latex/contrib/beamer/doc/beameruserguide.pdf +[Beamer User's Guide]: http://mirrors.ctan.org/macros/latex/contrib/beamer/doc/beameruserguide.pdf [ConTeXt]: http://www.contextgarden.net/ [Rich Text Format]: http://en.wikipedia.org/wiki/Rich_Text_Format [DocBook]: http://docbook.org @@ -450,6 +451,7 @@ [MediaWiki markup]: https://www.mediawiki.org/wiki/Help:Formatting [DokuWiki markup]: https://www.dokuwiki.org/dokuwiki [ZimWiki markup]: http://zim-wiki.org/manual/Help/Wiki_Syntax.html +[XWiki markup]: https://www.xwiki.org/xwiki/bin/view/Documentation/UserGuide/Features/XWikiSyntax/ [TWiki markup]: http://twiki.org/cgi-bin/view/TWiki/TextFormattingRules [TikiWiki markup]: https://doc.tiki.org/Wiki-Syntax-Text#The_Markup_Language_Wiki-Syntax [Haddock markup]: https://www.haskell.org/haddock/doc/html/ch03s08.html @@ -478,7 +480,7 @@ `--base-header-level=`*NUMBER* -: Specify the base level for headers (defaults to 1). +: Specify the base level for headings (defaults to 1). `--strip-empty-paragraphs` @@ -752,8 +754,8 @@ `--toc-depth=`*NUMBER* : Specify the number of section levels to include in the table - of contents. The default is 3 (which means that level 1, 2, and 3 - headers will be listed in the contents). + of contents. The default is 3 (which means that level-1, 2, and 3 + headings will be listed in the contents). `--strip-comments` @@ -905,23 +907,23 @@ `--atx-headers` -: Use ATX-style headers in Markdown output. The default is - to use setext-style headers for levels 1-2, and then ATX headers. - (Note: for `gfm` output, ATX headers are always used.) +: Use ATX-style headings in Markdown output. The default is + to use setext-style headings for levels 1 to 2, and then ATX headings. + (Note: for `gfm` output, ATX headings are always used.) This option also affects markdown cells in `ipynb` output. `--top-level-division=[default|section|chapter|part]` -: Treat top-level headers as the given division type in LaTeX, ConTeXt, +: Treat top-level headings as the given division type in LaTeX, ConTeXt, DocBook, and TEI output. The hierarchy order is part, chapter, then section; - all headers are shifted such that the top-level header becomes the specified + all headings are shifted such that the top-level heading becomes the specified type. The default behavior is to determine the best division type via heuristics: unless other conditions apply, `section` is chosen. When the LaTeX document class is set to `report`, `book`, or `memoir` (unless the `article` option is specified), `chapter` is implied as the setting for this option. If `beamer` is the output format, specifying either `chapter` or - `part` will cause top-level headers to become `\part{..}`, while - second-level headers remain as their default type. + `part` will cause top-level headings to become `\part{..}`, while + second-level headings remain as their default type. `-N`, `--number-sections` @@ -934,10 +936,10 @@ : Offset for section headings in HTML output (ignored in other output formats). The first number is added to the section number for - top-level headers, the second for second-level headers, and so on. - So, for example, if you want the first top-level header in your + top-level headings, the second for second-level headings, and so on. + So, for example, if you want the first top-level heading in your document to be numbered "6", specify `--number-offset=5`. - If your document starts with a level-2 header which you want to + If your document starts with a level-2 heading which you want to be numbered "1.5", specify `--number-offset=1,4`. Offsets are 0 by default. Implies `--number-sections`. @@ -955,12 +957,12 @@ `--slide-level=`*NUMBER* -: Specifies that headers with the specified level create - slides (for `beamer`, `s5`, `slidy`, `slideous`, `dzslides`). Headers +: Specifies that headings with the specified level create + slides (for `beamer`, `s5`, `slidy`, `slideous`, `dzslides`). Headings above this level in the hierarchy are used to divide the - slide show into sections; headers below this level create + slide show into sections; headings below this level create subheads within a slide. Note that content that is - not contained under slide-level headers will not appear in + not contained under slide-level headings will not appear in the slide show. The default is to set the slide level based on the contents of the document; see [Structuring the slide show]. @@ -969,8 +971,8 @@ : Wrap sections in `
` tags (or `
` tags for `html4`), and attach identifiers to the enclosing `
` (or `
`) - rather than the header itself. See - [Header identifiers], below. + rather than the heading itself. See + [Heading identifiers], below. `--email-obfuscation=none`|`javascript`|`references` @@ -1092,12 +1094,12 @@ PowerPoint - : Any template included with a recent install of Microsoft - PowerPoint (either with `.pptx` or `.potx` extension) should - work, as will most templates derived from these. + : Templates included with Microsoft PowerPoint 2013 (either with + `.pptx` or `.potx` extension) are known to work, as are most + templates derived from these. - The specific requirement is that the template should contain - the following four layouts as its first four layouts: + The specific requirement is that the template should begin with + the following first four layouts: 1. Title Slide 2. Title and Content @@ -1180,12 +1182,12 @@ `--epub-chapter-level=`*NUMBER* -: Specify the header level at which to split the EPUB into separate - "chapter" files. The default is to split into chapters at level 1 - headers. This option only affects the internal composition of the +: Specify the heading level at which to split the EPUB into separate + "chapter" files. The default is to split into chapters at level-1 + headings. This option only affects the internal composition of the EPUB, not the way chapters and sections are displayed to users. Some readers may be slow if the chapter files are too large, so for large - documents with few level 1 headers, one might want to use a chapter + documents with few level-1 headings, one might want to use a chapter level of 2 or 3. `--epub-subdirectory=`*DIRNAME* @@ -1548,18 +1550,52 @@ ### Layout +`block-headings` +: make `\paragraph` and `\subparagraph` (fourth- and fifth-level headings, or + fifth- and sixth-level with book classes) free-standing rather than run-in; + requires further formatting to distinguish from `\subsubsection` (third- or + fourth-level headings). Instead of using this option, [KOMA-Script] can adjust + headings more extensively: + + --- + documentclass: scrartcl + header-includes: | + \RedeclareSectionCommand[ + beforeskip=-10pt plus -2pt minus -1pt, + afterskip=1sp plus -1sp minus 1sp, + font=\normalfont\itshape]{paragraph} + \RedeclareSectionCommand[ + beforeskip=-10pt plus -2pt minus -1pt, + afterskip=1sp plus -1sp minus 1sp, + font=\normalfont\scshape, + indent=0pt]{subparagraph} + ... + `classoption` -: option for document class, e.g. `oneside`; repeat for multiple options +: option for document class, e.g. `oneside`; repeat for multiple options: + --- + classoption: + - twocolumn + - landscape + ... + `documentclass` -: document class: usually one of the standard classes, [`article`], [`report`], - and [`book`]; the [KOMA-Script] equivalents, `scrartcl`, `scrreprt`, - and `scrbook`, which default to smaller margins; or [`memoir`] +: document class: usually one of the standard classes, [`article`], [`book`], + and [`report`]; the [KOMA-Script] equivalents, `scrartcl`, `scrbook`, + and `scrreprt`, which default to smaller margins; or [`memoir`] `geometry` : option for [`geometry`] package, e.g. `margin=1in`; - repeat for multiple options + repeat for multiple options: + --- + geometry: + - top=30mm + - left=20mm + - heightrounded + ... + `indent` : uses document class settings for indentation (the default LaTeX template otherwise removes indentation and adds space between paragraphs) @@ -1584,10 +1620,6 @@ : numbering depth for sections (with `--number-sections` option or `numbersections` variable) -`subparagraph` -: disables default behavior of LaTeX template that redefines (sub)paragraphs - as sections, changing the appearance of nested headings in some classes - ### Fonts `fontenc` @@ -2007,13 +2039,13 @@ to use the ligatures when possible; if `smart` is disabled pandoc will use unicode quotation mark and dash characters. -Headers and sections --------------------- +Headings and sections +--------------------- #### Extension: `auto_identifiers` #### -A header without an explicitly specified identifier will be -automatically assigned a unique identifier based on the header text. +A heading without an explicitly specified identifier will be +automatically assigned a unique identifier based on the heading text. This extension can be enabled/disabled for the following formats: @@ -2027,7 +2059,7 @@ : `markdown`, `muse` The default algorithm used to derive the identifier from the -header text is: +heading text is: - Remove all formatting, links, etc. - Remove all footnotes. @@ -2041,9 +2073,9 @@ Thus, for example, - Header Identifier + Heading Identifier ------------------------------- ---------------------------- - `Header identifiers in HTML` `header-identifiers-in-html` + `Heading identifiers in HTML` `heading-identifiers-in-html` `Maître d'hôtel` `maître-dhôtel` `*Dogs*?--in *my* house?` `dogs--in-my-house` `[HTML], [S5], or [RTF]?` `html-s5-or-rtf` @@ -2051,7 +2083,7 @@ `33` `section` These rules should, in most cases, allow one to determine the identifier -from the header text. The exception is when several headers have the +from the heading text. The exception is when several headings have the same text; in this case, the first will get an identifier as described above; the second will get the same identifier with `-1` appended; the third with `-2`; and so on. @@ -2065,7 +2097,7 @@ another. A link to this section, for example, might look like this: See the section on - [header identifiers](#header-identifiers-in-html-latex-and-context). + [heading identifiers](#heading-identifiers-in-html-latex-and-context). Note, however, that this method of providing links to sections works only in HTML, LaTeX, and ConTeXt formats. @@ -2073,7 +2105,7 @@ If the `--section-divs` option is specified, then each section will be wrapped in a `section` (or a `div`, if `html4` was specified), and the identifier will be attached to the enclosing `
` -(or `
`) tag rather than the header itself. This allows entire +(or `
`) tag rather than the heading itself. This allows entire sections to be manipulated using JavaScript or treated differently in CSS. @@ -2174,12 +2206,12 @@ - In Markdown input, "bird track" sections will be parsed as Haskell code rather than block quotations. Text between `\begin{code}` and `\end{code}` will also be treated as Haskell code. For - ATX-style headers the character '=' will be used instead of '#'. + ATX-style headings the character '=' will be used instead of '#'. - In Markdown output, code blocks with classes `haskell` and `literate` will be rendered using bird tracks, and block quotations will be indented one space, so they will not be treated as Haskell code. - In addition, headers will be rendered setext-style (with underlines) + In addition, headings will be rendered setext-style (with underlines) rather than ATX-style (with '#' characters). (This is because ghc treats '#' characters in column 1 as introducing line numbers.) @@ -2307,43 +2339,43 @@ to create a hard line break, since trailing spaces in the cells are ignored. -Headers -------- +Headings +-------- -There are two kinds of headers: Setext and ATX. +There are two kinds of headings: Setext and ATX. -### Setext-style headers ### +### Setext-style headings ### -A setext-style header is a line of text "underlined" with a row of `=` signs -(for a level one header) or `-` signs (for a level two header): +A setext-style heading is a line of text "underlined" with a row of `=` signs +(for a level-one heading) or `-` signs (for a level-two heading): - A level-one header - ================== + A level-one heading + =================== - A level-two header - ------------------ + A level-two heading + ------------------- -The header text can contain inline formatting, such as emphasis (see +The heading text can contain inline formatting, such as emphasis (see [Inline formatting], below). -### ATX-style headers ### +### ATX-style headings ### -An ATX-style header consists of one to six `#` signs and a line of +An ATX-style heading consists of one to six `#` signs and a line of text, optionally followed by any number of `#` signs. The number of -`#` signs at the beginning of the line is the header level: +`#` signs at the beginning of the line is the heading level: - ## A level-two header + ## A level-two heading - ### A level-three header ### + ### A level-three heading ### -As with setext-style headers, the header text can contain formatting: +As with setext-style headings, the heading text can contain formatting: - # A level-one header with a [link](/url) and *emphasis* + # A level-one heading with a [link](/url) and *emphasis* #### Extension: `blank_before_header` #### -Standard Markdown syntax does not require a blank line before a header. +Standard Markdown syntax does not require a blank line before a heading. Pandoc does require this (except, of course, at the beginning of the document). The reason for the requirement is that it is all too easy for a `#` to end up at the beginning of a line by accident (perhaps through line @@ -2355,29 +2387,29 @@ #### Extension: `space_in_atx_header` #### Many Markdown implementations do not require a space between the -opening `#`s of an ATX header and the header text, so that -`#5 bolt` and `#hashtag` count as headers. With this extension, +opening `#`s of an ATX heading and the heading text, so that +`#5 bolt` and `#hashtag` count as headings. With this extension, pandoc does require the space. -### Header identifiers ### +### Heading identifiers ### See also the [`auto_identifiers` extension](#extension-auto_identifiers) above. #### Extension: `header_attributes` #### -Headers can be assigned attributes using this syntax at the end -of the line containing the header text: +Headings can be assigned attributes using this syntax at the end +of the line containing the heading text: {#identifier .class .class key=value key=value} -Thus, for example, the following headers will all be assigned the identifier +Thus, for example, the following headings will all be assigned the identifier `foo`: - # My header {#foo} + # My heading {#foo} - ## My header ## {#foo} + ## My heading ## {#foo} - My other header {#foo} + My other heading {#foo} --------------- (This syntax is compatible with [PHP Markdown Extra].) @@ -2388,49 +2420,49 @@ as EPUB and slidy. Identifiers are used for labels and link anchors in the LaTeX, ConTeXt, Textile, and AsciiDoc writers. -Headers with the class `unnumbered` will not be numbered, even if +Headings with the class `unnumbered` will not be numbered, even if `--number-sections` is specified. A single hyphen (`-`) in an attribute context is equivalent to `.unnumbered`, and preferable in non-English documents. So, - # My header {-} + # My heading {-} is just the same as - # My header {.unnumbered} + # My heading {.unnumbered} #### Extension: `implicit_header_references` #### -Pandoc behaves as if reference links have been defined for each header. -So, to link to a header +Pandoc behaves as if reference links have been defined for each heading. +So, to link to a heading - # Header identifiers in HTML + # Heading identifiers in HTML you can simply write - [Header identifiers in HTML] + [Heading identifiers in HTML] or - [Header identifiers in HTML][] + [Heading identifiers in HTML][] or - [the section on header identifiers][header identifiers in + [the section on heading identifiers][heading identifiers in HTML] instead of giving the identifier explicitly: - [Header identifiers in HTML](#header-identifiers-in-html) + [Heading identifiers in HTML](#heading-identifiers-in-html) -If there are multiple headers with identical text, the corresponding +If there are multiple headings with identical text, the corresponding reference will link to the first one only, and you will need to use explicit links to link to the others, as described above. Like regular reference links, these references are case-insensitive. Explicit link reference definitions always take priority over -implicit header references. So, in the following example, the +implicit heading references. So, in the following example, the link will point to `bar`, not to `#foo`: # Foo @@ -2444,7 +2476,7 @@ Markdown uses email conventions for quoting blocks of text. A block quotation is one or more paragraphs or other block elements -(such as lists or headers), with each line preceded by a `>` character +(such as lists or headings), with each line preceded by a `>` character and an optional space. (The `>` need not start at the left margin, but it should not be indented more than three spaces.) @@ -2995,7 +3027,7 @@ Table: Demonstration of simple table syntax. -The headers and table rows must each fit on one line. Column +The header and table rows must each fit on one line. Column alignments are determined by the position of the header text relative to the dashed line below it:[^4] @@ -3014,7 +3046,7 @@ The table must end with a blank line, or a line of dashes followed by a blank line. -The column headers may be omitted, provided a dashed line is used +The column header row may be omitted, provided a dashed line is used to end the table. For example: ------- ------ ---------- ------- @@ -3023,13 +3055,13 @@ 1 1 1 1 ------- ------ ---------- ------- -When headers are omitted, column alignments are determined on the basis +When the header row is omitted, column alignments are determined on the basis of the first line of the table body. So, in the tables above, the columns would be right, left, center, and right aligned, respectively. #### Extension: `multiline_tables` #### -Multiline tables allow headers and table rows to span multiple lines +Multiline tables allow header and table rows to span multiple lines of text (but cells that span multiple columns or rows of the table are not supported). Here is an example: @@ -3051,7 +3083,7 @@ These work like simple tables, but with the following differences: - They must begin with a row of dashes, before the header text - (unless the headers are omitted). + (unless the header row is omitted). - They must end with a row of dashes, then a blank line. - The rows must be separated by blank lines. @@ -3060,7 +3092,7 @@ the output. So, if you find that one of the columns is too narrow in the output, try widening it in the Markdown source. -Headers may be omitted in multiline tables as well as simple tables: +The header may be omitted in multiline tables as well as simple tables: ----------- ------- --------------- ------------------------- First row 12.0 Example of a row that @@ -3071,7 +3103,7 @@ rows. ----------- ------- --------------- ------------------------- - : Here's a multiline table without headers. + : Here's a multiline table without a header. It is possible for a multiline table to have just one row, but the row should be followed by a blank line (and then the row of dashes that ends @@ -3527,6 +3559,9 @@ ~ It will appear verbatim surrounded by `$...$` (for inline math) or `$$...$$` (for display math). +XWiki + ~ It will appear verbatim surrounded by `{{formula}}..{{/formula}}`. + reStructuredText ~ It will be rendered using an [interpreted text role `:math:`]. @@ -3844,7 +3879,7 @@ ### Internal links ### To link to another section of the same document, use the automatically -generated identifier (see [Header identifiers]). For example: +generated identifier (see [Heading identifiers]). For example: See the [Introduction](#introduction). @@ -4201,8 +4236,8 @@ Generation of the bibliography can be suppressed by setting `suppress-bibliography: true` in the YAML metadata. -If you wish the bibliography to have a section header, you can -set `reference-section-title` in the metadata, or put the header +If you wish the bibliography to have a section heading, you can +set `reference-section-title` in the metadata, or put the heading at the beginning of the div with id `refs` (if you are using it) or at the end of your document: @@ -4210,8 +4245,8 @@ # References -The bibliography will be inserted after this header. Note that -the `unnumbered` class will be added to this header, so that the +The bibliography will be inserted after this heading. Note that +the `unnumbered` class will be added to this heading, so that the section will not be numbered. If you want to include items in the bibliography without actually @@ -4379,8 +4414,8 @@ #### Extension: `mmd_header_identifiers` #### -Parses multimarkdown style header identifiers (in square brackets, -after the header but before any trailing `#`s in an ATX header). +Parses multimarkdown style heading identifiers (in square brackets, +after the heading but before any trailing `#`s in an ATX heading). #### Extension: `compact_definition_lists` #### @@ -4537,11 +4572,11 @@ Structuring the slide show -------------------------- -By default, the *slide level* is the highest header level in +By default, the *slide level* is the highest heading level in the hierarchy that is followed immediately by content, and not another -header, somewhere in the document. In the example above, level 1 headers -are always followed by level 2 headers, which are followed by content, -so 2 is the slide level. This default can be overridden using +heading, somewhere in the document. In the example above, level-1 headings +are always followed by level-2 headings, which are followed by content, +so the slide level is 2. This default can be overridden using the `--slide-level` option. The document is carved up into slides according to the following @@ -4549,15 +4584,15 @@ * A horizontal rule always starts a new slide. - * A header at the slide level always starts a new slide. + * A heading at the slide level always starts a new slide. - * Headers *below* the slide level in the hierarchy create - headers *within* a slide. + * Headings *below* the slide level in the hierarchy create + headings *within* a slide. - * Headers *above* the slide level in the hierarchy create + * Headings *above* the slide level in the hierarchy create "title slides," which just contain the section title and help to break the slide show into sections. - Non-slide content under these headers will be included + Non-slide content under these headings will be included on the title slide (for HTML slide shows) or in a subsequent slide with the same title (for beamer). @@ -4567,13 +4602,13 @@ These rules are designed to support many different styles of slide show. If you don't care about structuring your slides into sections and subsections, -you can just use level 1 headers for all each slide. (In that case, level 1 +you can just use level-1 headings for all each slide. (In that case, level-1 will be the slide level.) But you can also structure the slide show into sections, as in the example above. Note: in reveal.js slide shows, if slide level is 2, a two-dimensional -layout will be produced, with level 1 headers building horizontally -and level 2 headers building vertically. It is not recommended that +layout will be produced, with level-1 headings building horizontally +and level-2 headings building vertically. It is not recommended that you use deeper nesting of section levels with reveal.js. Incremental lists @@ -4655,9 +4690,9 @@ pandoc -t beamer habits.txt -V theme:Warsaw -o habits.pdf -Note that header attributes will turn into slide attributes +Note that heading attributes will turn into slide attributes (on a `
` or `
`) in HTML slide formats, allowing you -to style individual slides. In beamer, the only header attribute +to style individual slides. In beamer, the only heading attribute that affects slides is the `allowframebreaks` class, which sets the `allowframebreaks` option, causing multiple slides to be created if the content overfills the frame. This is recommended especially for @@ -4708,7 +4743,7 @@ Sometimes it is necessary to add the LaTeX `[fragile]` option to a frame in beamer (for example, when using the `minted` environment). -This can be forced by adding the `fragile` class to the header +This can be forced by adding the `fragile` class to the heading introducing the slide: # Fragile slide {.fragile} @@ -4736,7 +4771,7 @@ To set an image for a particular reveal.js slide, add `{data-background-image="/path/to/image"}` -to the first slide-level header on the slide (which may even be empty). +to the first slide-level heading on the slide (which may even be empty). In reveal.js's overview mode, the parallaxBackgroundImage will show up only on the first slide. @@ -4763,7 +4798,7 @@ ## {data-background-image="/path/to/special_image.jpg"} -Slide 2 has a special image for its background, even though the header has no content. +Slide 2 has a special image for its background, even though the heading has no content. ``` Creating EPUBs with pandoc @@ -4875,7 +4910,7 @@ The `epub:type` attribute ------------------------- -For `epub3` output, you can mark up the header that corresponds to an EPUB +For `epub3` output, you can mark up the heading that corresponds to an EPUB chapter using the [`epub:type` attribute][epub-type]. For example, to set the attribute to the value `prologue`, use this markdown: @@ -5047,6 +5082,12 @@ specifying the extensions `-raw_html-raw_tex+raw_attribute` when translating between Markdown and ipynb notebooks. +Note that options and extensions that affect reading and +writing of Markdown will also affect Markdown cells in ipynb +notebooks. For example, `--wrap=preserve` will preserve +soft line breaks in Markdown cells; `--atx-headers` will +cause ATX-style headings to be used; and `--preserve-tabs` will +prevent tabs from being turned to spaces. Syntax highlighting =================== @@ -5233,7 +5274,7 @@ If `raw_html` is enabled for the Markdown input, users can inject arbitrary HTML. Even if `raw_html` is disabled, users can include dangerous content in attributes for - headers, spans, and code blocks. To be safe, you should + headings, spans, and code blocks. To be safe, you should run all the generated HTML through an HTML sanitizer. Authors diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -154,6 +154,8 @@ - `s5` ([S5](http://meyerweb.com/eric/tools/s5/) HTML and JavaScript slide show) - `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 markup](http://zim-wiki.org/manual/Help/Wiki_Syntax.html)) - the path of a custom lua writer, see [Custom diff --git a/changelog b/changelog --- a/changelog +++ b/changelog @@ -1,3 +1,168 @@ +pandoc (2.7.2) + + * Add XWiki writer (#1800, Derek Chen-Becker). + Add `Text.Pandoc.Writers.XWiki`, exporting `writeXWiki` [API change]. + + * Dokuwiki Reader: parse single curly brace (#5416, Mauro Bieg). + + * Vimwiki reader: improve handling of internal links (#5414). + We no longer append `.html` to link targets, and we add a title + `wikilink`. This mirrors behavior of other wiki readers. Generally + the `.html` extension is not wanted. It may be important for output + to HTML in certain circumstances, but it can always be added using a + filter that matches on links with title `wikilink`. + + If your workflow requires the current behavior, here is a lua filter + that will add the `.html` extension: + + ```lua + function Link(el) + if el.title == 'wikilink' then + el.target = el.target .. ".html" + end + return el + end + ``` + * ipynb reader: + + + Use format `ipynb` for raw cell where no format given. + + Avoid introducing spurious `.0` on integers in metadata. + + * Markdown reader: fenced div takes priority over setext header. + + * HTML reader: read `data-foo` attribute into `foo` (#5392). + The HTML writer adds the `data-` prefix for HTML5 for nonstandard + attributes. But the attributes are represented in the AST without + the `data-` prefix, so we should strip this when reading HTML. + + * LaTeX reader: Improve autolink detection (#5340). + + * PowerPoint writer (Jesse Rosenthal): + + + Expand builtin reference doc to model all layouts. + The previous built-in reference doc had only title and content + layouts. Add in a section-header slide and a two-content slide, so + users can more easily modify it to build their own templates. + + Always open up in slide view. When editing a + template/reference-doc, the user might be in Master view, but when + producing a slide show, it is assumed that slide view will be + desired. + + Remove `handoutsMasterList` from template presentation.xml + + Fix numerous errors in templating (#5402). Previously, some templates + produced by Office 365 (MacOS) would not render with `--reference-doc` + correctly. We now apply correct shapes for content, and build + shape trees correctly. + + Make default placeholder type for template lookup. + + Apply speaker notes to metadata slide if applicable. + + Test for speaker notes after breaking header. + + Correctly handle notes after section-title header. + Previously, if notes came after a section-title header (ie, a level-1 + header in a slide-level=2 presentation), they would go on the next + slide. This keeps them on the slide with the header. + + Internal improvements. + + * ipynb writer: + + + Use format `ipynb` for raw cell where no format given. + According to nbformat docs, this is supposed to render in every + format. We don't do that, but we at least preserve it as a raw + block in markdown, so you can round-trip. + + Consolidate adjacent raw blocks. Sometimes pandoc creates two + HTML blocks, e.g. one for the open tag and one for a close tag. + If these aren't consolidated, only one will show up in output cell. + + Fixed carry-over of nbformat from metadata. + + Preserve `nbformat_minor` if it's given. This helps with round-tripping. + + * LaTeX writer: + + + Avoid inadvertently creating ?` or !` ligatures (#5407). + These are upside down ? and !, resp. + + Fix footnotes in table caption and cells (#5367). This fixes a + bug wherein footnotes appeared in the wrong order, and with + duplicate numbers, when in table captions and cells. + We now use regular `\footnote` commands, even in the table + caption and the minipages containing cells. Apparently + longtable knows how to handle this. + + * HTML writer: Don't add data- prefix to RDFa attributes (#5403). + + * JATS writer: Ensure that plain strings go inside `` tag (#5397). + + * Markdown writer: + + + Better rendering of numbers (#5398). If the number is integral, + we render it as an integral not a float. + + Proper rendering of empty map in YAML metadata (#5398). Should + be `{}`, not empty string. + + Properly escape attributes in Markdown writer (#5369). + + Be sure implicit figures work in list contexts (#5368). + Previously they would sometimes not work: e.g., when they + occured in final paragraphs in lists that were originally + parsed as Plain and converted later using PlainToPara. + + * Docx writer: Use `w:br` without attributes for line breaks (#5377). + We previously added the attribute `type="textWrapping"`, but + this causes problems on Word Online. + + * LaTeX template (Andrew Dunning): + + + Ensure correct heading/table order (#5365). Improve workaround + (#1658) for tables following headings. The new solution works whether + or not the `indent` variable is enabled. + + Remove `subparagraph` variable. The default is now to use run-in + style for level 4 and 5 headings (`\paragraph` and `\subparagraph`). + To get the previous default behavior (where these were formatted as + blocks, like `\subsubsection`), set the `block-headings` variable. + + Add pandoc to PDF metadata (#5388). + + Group graphics-related code (#5389). + + Move `\setstretch` after front matter (#5179). Ensures that + `\maketitle`, `\tableofcontents`, and so forth are not affected by + changes to line spacing. + + * Update data/jats.csl to avoid commas between name-part elements + (#5397). + + * Add support for golang (`go`) with `--listings` (#5427). + + * Text.Pandoc.Shared - improve `metaToJSON` behavior with numbers. + We now do a better job marshalling numbers from MetaString + or MetaInlines into JSON Number. + + * Text.Pandoc.Writers.Shared: `metaValueToJSON`: use Number Values for + integers. Pandoc's MetaValue doesn't have a distinguished number type, + so numbers are put in MetaStrings. If the MetaString consists + entirely of digits, we convert it to a Number. We should probably + consider adding a MetaNumber constructor to MetaValue, for better + round-tripping with JSON etc. This change aids round-tripping in + ipynb metadata fields, like `toc_depth`. + + * Text.Pandoc.Class: `fetchItem`: don't treat UNC paths as + protocol-relative URLs (#5127). These are paths beginning `//?/UNC/...`. + + * Text.Pandoc.ImageSize: Improve `pdfSize` so it handles + a wider range of PDFs (#4322, with help from Richard Davis). + + * Text.Pandoc.Pretty: avoid stack overflow by using strict sum (#5401). + + * Fix harmless error in file-scope code (#5422). + + * MANUAL.txt: + + + Improve 'header' and 'heading' usage (#5423, Andrew + Dunning). The term 'header' was being used where 'heading' + is more appropriate. + + Add paragraph on options affecting markdown in ipynb. + + * stack.yaml - remove -Wmissing-home-modules + This seems to cause problems with stack ghci. Remove RTS options. + + * Add ghc-options to cabal.project. + + * appveyor.yml - use ghc 8.6.4. Fixes segfault issues on Windows (#5037). + + * linux build process: Remove clone of pandoc-citeproc (#5366). + It wasn't being used; cabal.project specifies the version to use. + pandoc (2.7.1) * Add tectonic as an option for --pdf-engine (#5345, Cormac Relf). diff --git a/data/jats.csl b/data/jats.csl --- a/data/jats.csl +++ b/data/jats.csl @@ -26,8 +26,8 @@ - - + + diff --git a/data/pptx/[Content_Types].xml b/data/pptx/[Content_Types].xml --- a/data/pptx/[Content_Types].xml +++ b/data/pptx/[Content_Types].xml @@ -1,2 +1,2 @@ - + diff --git a/data/pptx/docProps/app.xml b/data/pptx/docProps/app.xml --- a/data/pptx/docProps/app.xml +++ b/data/pptx/docProps/app.xml @@ -1,2 +1,2 @@ -126Microsoft Office PowerPointOn-screen Show (4:3)102200falseFonts Used2Theme1Slide Titles2ArialCalibriOffice ThemeTitleSlide Titlefalsefalsefalse15.0000 +249Microsoft Office PowerPointOn-screen Show (4:3)154200falseFonts Used2Theme1Slide Titles4ArialCalibriOffice ThemePresentation TitleSlide TitleSection headerSlide Title for Two-Contentfalsefalsefalse15.0000 diff --git a/data/pptx/docProps/core.xml b/data/pptx/docProps/core.xml --- a/data/pptx/docProps/core.xml +++ b/data/pptx/docProps/core.xml @@ -1,2 +1,2 @@ -TitleJesse RosenthalKSAS-IT32017-06-05T14:10:58Z2018-02-17T16:21:08Z +TitleJesse RosenthalJesse Rosenthal42017-06-05T14:10:58Z2019-04-05T11:11:56Z diff --git a/data/pptx/ppt/_rels/presentation.xml.rels b/data/pptx/ppt/_rels/presentation.xml.rels --- a/data/pptx/ppt/_rels/presentation.xml.rels +++ b/data/pptx/ppt/_rels/presentation.xml.rels @@ -1,2 +1,2 @@ - + diff --git a/data/pptx/ppt/notesMasters/notesMaster1.xml b/data/pptx/ppt/notesMasters/notesMaster1.xml --- a/data/pptx/ppt/notesMasters/notesMaster1.xml +++ b/data/pptx/ppt/notesMasters/notesMaster1.xml @@ -1,2 +1,2 @@ -2/17/2018Click to edit Master text stylesSecond levelThird levelFourth levelFifth level‹#› +4/5/2019Click to edit Master text stylesSecond levelThird levelFourth levelFifth level‹#› diff --git a/data/pptx/ppt/presentation.xml b/data/pptx/ppt/presentation.xml --- a/data/pptx/ppt/presentation.xml +++ b/data/pptx/ppt/presentation.xml @@ -1,2 +1,2 @@ - + diff --git a/data/pptx/ppt/slideLayouts/slideLayout1.xml b/data/pptx/ppt/slideLayouts/slideLayout1.xml --- a/data/pptx/ppt/slideLayouts/slideLayout1.xml +++ b/data/pptx/ppt/slideLayouts/slideLayout1.xml @@ -1,2 +1,2 @@ -Click to edit Master title styleClick to edit Master subtitle style2/17/2018‹#› +Click to edit Master title styleClick to edit Master subtitle style4/5/2019‹#› diff --git a/data/pptx/ppt/slideLayouts/slideLayout10.xml b/data/pptx/ppt/slideLayouts/slideLayout10.xml --- a/data/pptx/ppt/slideLayouts/slideLayout10.xml +++ b/data/pptx/ppt/slideLayouts/slideLayout10.xml @@ -1,2 +1,2 @@ -Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth level2/17/2018‹#› +Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth level4/5/2019‹#› diff --git a/data/pptx/ppt/slideLayouts/slideLayout11.xml b/data/pptx/ppt/slideLayouts/slideLayout11.xml --- a/data/pptx/ppt/slideLayouts/slideLayout11.xml +++ b/data/pptx/ppt/slideLayouts/slideLayout11.xml @@ -1,2 +1,2 @@ -Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth level2/17/2018‹#› +Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth level4/5/2019‹#› diff --git a/data/pptx/ppt/slideLayouts/slideLayout2.xml b/data/pptx/ppt/slideLayouts/slideLayout2.xml --- a/data/pptx/ppt/slideLayouts/slideLayout2.xml +++ b/data/pptx/ppt/slideLayouts/slideLayout2.xml @@ -1,2 +1,2 @@ -Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth level2/17/2018‹#› +Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth level4/5/2019‹#› diff --git a/data/pptx/ppt/slideLayouts/slideLayout3.xml b/data/pptx/ppt/slideLayouts/slideLayout3.xml --- a/data/pptx/ppt/slideLayouts/slideLayout3.xml +++ b/data/pptx/ppt/slideLayouts/slideLayout3.xml @@ -1,2 +1,2 @@ -Click to edit Master title styleClick to edit Master text styles2/17/2018‹#› +Click to edit Master title styleClick to edit Master text styles4/5/2019‹#› diff --git a/data/pptx/ppt/slideLayouts/slideLayout4.xml b/data/pptx/ppt/slideLayouts/slideLayout4.xml --- a/data/pptx/ppt/slideLayouts/slideLayout4.xml +++ b/data/pptx/ppt/slideLayouts/slideLayout4.xml @@ -1,2 +1,2 @@ -Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth levelClick to edit Master text stylesSecond levelThird levelFourth levelFifth level2/17/2018‹#› +Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth levelClick to edit Master text stylesSecond levelThird levelFourth levelFifth level4/5/2019‹#› diff --git a/data/pptx/ppt/slideLayouts/slideLayout5.xml b/data/pptx/ppt/slideLayouts/slideLayout5.xml --- a/data/pptx/ppt/slideLayouts/slideLayout5.xml +++ b/data/pptx/ppt/slideLayouts/slideLayout5.xml @@ -1,2 +1,2 @@ -Click to edit Master title styleClick to edit Master text stylesClick to edit Master text stylesSecond levelThird levelFourth levelFifth levelClick to edit Master text stylesClick to edit Master text stylesSecond levelThird levelFourth levelFifth level2/17/2018‹#› +Click to edit Master title styleClick to edit Master text stylesClick to edit Master text stylesSecond levelThird levelFourth levelFifth levelClick to edit Master text stylesClick to edit Master text stylesSecond levelThird levelFourth levelFifth level4/5/2019‹#› diff --git a/data/pptx/ppt/slideLayouts/slideLayout6.xml b/data/pptx/ppt/slideLayouts/slideLayout6.xml --- a/data/pptx/ppt/slideLayouts/slideLayout6.xml +++ b/data/pptx/ppt/slideLayouts/slideLayout6.xml @@ -1,2 +1,2 @@ -Click to edit Master title style2/17/2018‹#› +Click to edit Master title style4/5/2019‹#› diff --git a/data/pptx/ppt/slideLayouts/slideLayout7.xml b/data/pptx/ppt/slideLayouts/slideLayout7.xml --- a/data/pptx/ppt/slideLayouts/slideLayout7.xml +++ b/data/pptx/ppt/slideLayouts/slideLayout7.xml @@ -1,2 +1,2 @@ -2/17/2018‹#› +4/5/2019‹#› diff --git a/data/pptx/ppt/slideLayouts/slideLayout8.xml b/data/pptx/ppt/slideLayouts/slideLayout8.xml --- a/data/pptx/ppt/slideLayouts/slideLayout8.xml +++ b/data/pptx/ppt/slideLayouts/slideLayout8.xml @@ -1,2 +1,2 @@ -Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth levelClick to edit Master text styles2/17/2018‹#› +Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth levelClick to edit Master text styles4/5/2019‹#› diff --git a/data/pptx/ppt/slideLayouts/slideLayout9.xml b/data/pptx/ppt/slideLayouts/slideLayout9.xml --- a/data/pptx/ppt/slideLayouts/slideLayout9.xml +++ b/data/pptx/ppt/slideLayouts/slideLayout9.xml @@ -1,2 +1,2 @@ -Click to edit Master title styleClick to edit Master text styles2/17/2018‹#› +Click to edit Master title styleClick to edit Master text styles4/5/2019‹#› diff --git a/data/pptx/ppt/slideMasters/slideMaster1.xml b/data/pptx/ppt/slideMasters/slideMaster1.xml --- a/data/pptx/ppt/slideMasters/slideMaster1.xml +++ b/data/pptx/ppt/slideMasters/slideMaster1.xml @@ -1,2 +1,2 @@ -Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth level2/17/2018‹#› +Click to edit Master title styleClick to edit Master text stylesSecond levelThird levelFourth levelFifth level4/5/2019‹#› diff --git a/data/pptx/ppt/slides/_rels/slide3.xml.rels b/data/pptx/ppt/slides/_rels/slide3.xml.rels new file mode 100644 --- /dev/null +++ b/data/pptx/ppt/slides/_rels/slide3.xml.rels @@ -0,0 +1,2 @@ + + diff --git a/data/pptx/ppt/slides/_rels/slide4.xml.rels b/data/pptx/ppt/slides/_rels/slide4.xml.rels new file mode 100644 --- /dev/null +++ b/data/pptx/ppt/slides/_rels/slide4.xml.rels @@ -0,0 +1,2 @@ + + diff --git a/data/pptx/ppt/slides/slide1.xml b/data/pptx/ppt/slides/slide1.xml --- a/data/pptx/ppt/slides/slide1.xml +++ b/data/pptx/ppt/slides/slide1.xml @@ -1,2 +1,2 @@ -TitleSubtitle +Presentation TitlePresentation Subtitle diff --git a/data/pptx/ppt/slides/slide3.xml b/data/pptx/ppt/slides/slide3.xml new file mode 100644 --- /dev/null +++ b/data/pptx/ppt/slides/slide3.xml @@ -0,0 +1,2 @@ + +Section headerSome explanatory text diff --git a/data/pptx/ppt/slides/slide4.xml b/data/pptx/ppt/slides/slide4.xml new file mode 100644 --- /dev/null +++ b/data/pptx/ppt/slides/slide4.xml @@ -0,0 +1,2 @@ + +Slide Title for Two-ContentSome content on the left.Some content on the right. diff --git a/data/pptx/ppt/viewProps.xml b/data/pptx/ppt/viewProps.xml --- a/data/pptx/ppt/viewProps.xml +++ b/data/pptx/ppt/viewProps.xml @@ -1,2 +1,2 @@ - + diff --git a/data/templates/default.latex b/data/templates/default.latex --- a/data/templates/default.latex +++ b/data/templates/default.latex @@ -1,5 +1,5 @@ % Options for packages loaded elsewhere -\PassOptionsToPackage{unicode=true$for(hyperrefoptions)$,$hyperrefoptions$$endfor$}{hyperref} +\PassOptionsToPackage{unicode$for(hyperrefoptions)$,$hyperrefoptions$$endfor$}{hyperref} \PassOptionsToPackage{hyphens}{url} $if(colorlinks)$ \PassOptionsToPackage{dvipsnames,svgnames*,x11names*}{xcolor} @@ -93,15 +93,14 @@ $endif$ $if(linestretch)$ \usepackage{setspace} -\setstretch{$linestretch$} $endif$ \usepackage{amssymb,amsmath} \usepackage{ifxetex,ifluatex} \ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex \usepackage[$if(fontenc)$$fontenc$$else$T1$endif$]{fontenc} \usepackage[utf8]{inputenc} - \usepackage{textcomp} % provides euro and other symbols -\else % if luatex or xelatex + \usepackage{textcomp} % provide euro and other symbols +\else % if luatex or xetex $if(mathspec)$ \ifxetex \usepackage{mathspec} @@ -221,10 +220,10 @@ $else$ hidelinks, $endif$ -} + pdfcreator={LaTeX via pandoc}} \urlstyle{same} % disable monospaced font for URLs $if(verbatim-in-note)$ -\VerbatimFootnotes % allows verbatim text in footnotes +\VerbatimFootnotes % allow verbatim text in footnotes $endif$ $if(geometry)$ \usepackage[$for(geometry)$$geometry$$sep$,$endfor$]{geometry} @@ -253,6 +252,11 @@ \def\fnum@table{\tablename~\thetable} \makeatother $else$ +% Correct order of tables after \paragraph or \subparagraph +\usepackage{etoolbox} +\makeatletter +\patchcmd\longtable{\par}{\if@noskipsec\mbox{}\fi\par}{}{} +\makeatother % Allow footnotes in longtable head/foot \IfFileExists{footnotehyper.sty}{\usepackage{footnotehyper}}{\usepackage{footnote}} \makesavenoteenv{longtable} @@ -268,6 +272,10 @@ % margins by default, and it is still possible to overwrite the defaults % using explicit options in \includegraphics[width, height, ...]{} \setkeys{Gin}{width=\maxwidth,height=\maxheight,keepaspectratio} +% Set default figure placement to htbp +\makeatletter +\def\fps@figure{htbp} +\makeatother $endif$ $if(links-as-notes)$ % Make links footnotes instead of hotlinks: @@ -288,9 +296,8 @@ $endif$ $if(beamer)$ $else$ -$if(subparagraph)$ -$else$ -% Redefines (sub)paragraphs to behave more like sections +$if(block-headings)$ +% Make \paragraph and \subparagraph free-standing \ifx\paragraph\undefined\else \let\oldparagraph\paragraph \renewcommand{\paragraph}[1]{\oldparagraph{#1}\mbox{}} @@ -304,12 +311,6 @@ $if(pagestyle)$ \pagestyle{$pagestyle$} $endif$ - -% Set default figure placement to htbp -\makeatletter -\def\fps@figure{htbp} -\makeatother - $for(header-includes)$ $header-includes$ $endfor$ @@ -430,6 +431,9 @@ $endif$ $if(lof)$ \listoffigures +$endif$ +$if(linestretch)$ +\setstretch{$linestretch$} $endif$ $if(has-frontmatter)$ \mainmatter diff --git a/data/templates/default.xwiki b/data/templates/default.xwiki new file mode 100644 --- /dev/null +++ b/data/templates/default.xwiki @@ -0,0 +1,13 @@ +$for(include-before)$ +$include-before$ + +$endfor$ +$if(toc)$ +{{toc /}} + +$endif$ +$body$ +$for(include-after)$ + +$include-after$ +$endfor$ diff --git a/man/pandoc.1 b/man/pandoc.1 --- a/man/pandoc.1 +++ b/man/pandoc.1 @@ -1,5 +1,5 @@ .\"t -.TH PANDOC 1 "March 12, 2019" "pandoc 2.7.1" +.TH PANDOC 1 "April 5, 2019" "pandoc 2.7.2" .SH NAME pandoc - general markup converter .SH SYNOPSIS @@ -393,6 +393,8 @@ .IP \[bu] 2 \f[C]tei\f[R] (TEI Simple) .IP \[bu] 2 +\f[C]xwiki\f[R] (XWiki markup) +.IP \[bu] 2 \f[C]zimwiki\f[R] (ZimWiki markup) .IP \[bu] 2 the path of a custom lua writer, see Custom writers below @@ -488,7 +490,7 @@ .SS Reader options .TP .B \f[C]--base-header-level=\f[R]\f[I]NUMBER\f[R] -Specify the base level for headers (defaults to 1). +Specify the base level for headings (defaults to 1). .TP .B \f[C]--strip-empty-paragraphs\f[R] \f[I]Deprecated. Use the \f[CI]+empty_paragraphs\f[I] extension @@ -767,7 +769,7 @@ .B \f[C]--toc-depth=\f[R]\f[I]NUMBER\f[R] Specify the number of section levels to include in the table of contents. -The default is 3 (which means that level 1, 2, and 3 headers will be +The default is 3 (which means that level-1, 2, and 3 headings will be listed in the contents). .TP .B \f[C]--strip-comments\f[R] @@ -919,17 +921,17 @@ Currently only affects the markdown writer. .TP .B \f[C]--atx-headers\f[R] -Use ATX-style headers in Markdown output. -The default is to use setext-style headers for levels 1-2, and then ATX -headers. -(Note: for \f[C]gfm\f[R] output, ATX headers are always used.) This +Use ATX-style headings in Markdown output. +The default is to use setext-style headings for levels 1 to 2, and then +ATX headings. +(Note: for \f[C]gfm\f[R] output, ATX headings are always used.) This option also affects markdown cells in \f[C]ipynb\f[R] output. .TP .B \f[C]--top-level-division=[default|section|chapter|part]\f[R] -Treat top-level headers as the given division type in LaTeX, ConTeXt, +Treat top-level headings as the given division type in LaTeX, ConTeXt, DocBook, and TEI output. -The hierarchy order is part, chapter, then section; all headers are -shifted such that the top-level header becomes the specified type. +The hierarchy order is part, chapter, then section; all headings are +shifted such that the top-level heading becomes the specified type. The default behavior is to determine the best division type via heuristics: unless other conditions apply, \f[C]section\f[R] is chosen. When the LaTeX document class is set to \f[C]report\f[R], @@ -937,8 +939,8 @@ is specified), \f[C]chapter\f[R] is implied as the setting for this option. If \f[C]beamer\f[R] is the output format, specifying either -\f[C]chapter\f[R] or \f[C]part\f[R] will cause top-level headers to -become \f[C]\[rs]part{..}\f[R], while second-level headers remain as +\f[C]chapter\f[R] or \f[C]part\f[R] will cause top-level headings to +become \f[C]\[rs]part{..}\f[R], while second-level headings remain as their default type. .TP .B \f[C]-N\f[R], \f[C]--number-sections\f[R] @@ -950,11 +952,12 @@ .B \f[C]--number-offset=\f[R]\f[I]NUMBER\f[R][\f[C],\f[R]\f[I]NUMBER\f[R]\f[C],\f[R]\f[I]...\f[R]] Offset for section headings in HTML output (ignored in other output formats). -The first number is added to the section number for top-level headers, -the second for second-level headers, and so on. -So, for example, if you want the first top-level header in your document -to be numbered \[dq]6\[dq], specify \f[C]--number-offset=5\f[R]. -If your document starts with a level-2 header which you want to be +The first number is added to the section number for top-level headings, +the second for second-level headings, and so on. +So, for example, if you want the first top-level heading in your +document to be numbered \[dq]6\[dq], specify +\f[C]--number-offset=5\f[R]. +If your document starts with a level-2 heading which you want to be numbered \[dq]1.5\[dq], specify \f[C]--number-offset=1,4\f[R]. Offsets are 0 by default. Implies \f[C]--number-sections\f[R]. @@ -971,13 +974,13 @@ The default is for lists to be displayed all at once. .TP .B \f[C]--slide-level=\f[R]\f[I]NUMBER\f[R] -Specifies that headers with the specified level create slides (for +Specifies that headings with the specified level create slides (for \f[C]beamer\f[R], \f[C]s5\f[R], \f[C]slidy\f[R], \f[C]slideous\f[R], \f[C]dzslides\f[R]). -Headers above this level in the hierarchy are used to divide the slide -show into sections; headers below this level create subheads within a +Headings above this level in the hierarchy are used to divide the slide +show into sections; headings below this level create subheads within a slide. -Note that content that is not contained under slide-level headers will +Note that content that is not contained under slide-level headings will not appear in the slide show. The default is to set the slide level based on the contents of the document; see Structuring the slide show. @@ -985,8 +988,8 @@ .B \f[C]--section-divs\f[R] Wrap sections in \f[C]
\f[R] tags (or \f[C]
\f[R] tags for \f[C]html4\f[R]), and attach identifiers to the enclosing -\f[C]
\f[R] (or \f[C]
\f[R]) rather than the header itself. -See Header identifiers, below. +\f[C]
\f[R] (or \f[C]
\f[R]) rather than the heading itself. +See Heading identifiers, below. .TP .B \f[C]--email-obfuscation=none\f[R]|\f[C]javascript\f[R]|\f[C]references\f[R] Specify a method for obfuscating \f[C]mailto:\f[R] links in HTML @@ -1145,13 +1148,13 @@ .RE .TP .B PowerPoint -Any template included with a recent install of Microsoft PowerPoint -(either with \f[C].pptx\f[R] or \f[C].potx\f[R] extension) should work, -as will most templates derived from these. +Templates included with Microsoft PowerPoint 2013 (either with +\f[C].pptx\f[R] or \f[C].potx\f[R] extension) are known to work, as are +most templates derived from these. .RS .PP -The specific requirement is that the template should contain the -following four layouts as its first four layouts: +The specific requirement is that the template should begin with the +following first four layouts: .IP "1." 3 Title Slide .IP "2." 3 @@ -1251,13 +1254,13 @@ .RE .TP .B \f[C]--epub-chapter-level=\f[R]\f[I]NUMBER\f[R] -Specify the header level at which to split the EPUB into separate +Specify the heading level at which to split the EPUB into separate \[dq]chapter\[dq] files. -The default is to split into chapters at level 1 headers. +The default is to split into chapters at level-1 headings. This option only affects the internal composition of the EPUB, not the way chapters and sections are displayed to users. Some readers may be slow if the chapter files are too large, so for -large documents with few level 1 headers, one might want to use a +large documents with few level-1 headings, one might want to use a chapter level of 2 or 3. .TP .B \f[C]--epub-subdirectory=\f[R]\f[I]DIRNAME\f[R] @@ -1646,19 +1649,73 @@ Pandoc uses these variables when creating a PDF with a LaTeX engine. .SS Layout .TP +.B \f[C]block-headings\f[R] +make \f[C]\[rs]paragraph\f[R] and \f[C]\[rs]subparagraph\f[R] (fourth- +and fifth-level headings, or fifth- and sixth-level with book classes) +free-standing rather than run-in; requires further formatting to +distinguish from \f[C]\[rs]subsubsection\f[R] (third- or fourth-level +headings). +Instead of using this option, KOMA-Script can adjust headings more +extensively: +.RS +.IP +.nf +\f[C] +--- +documentclass: scrartcl +header-includes: | + \[rs]RedeclareSectionCommand[ + beforeskip=-10pt plus -2pt minus -1pt, + afterskip=1sp plus -1sp minus 1sp, + font=\[rs]normalfont\[rs]itshape]{paragraph} + \[rs]RedeclareSectionCommand[ + beforeskip=-10pt plus -2pt minus -1pt, + afterskip=1sp plus -1sp minus 1sp, + font=\[rs]normalfont\[rs]scshape, + indent=0pt]{subparagraph} +\&... +\f[R] +.fi +.RE +.TP .B \f[C]classoption\f[R] option for document class, e.g. -\f[C]oneside\f[R]; repeat for multiple options +\f[C]oneside\f[R]; repeat for multiple options: +.RS +.IP +.nf +\f[C] +--- +classoption: +- twocolumn +- landscape +\&... +\f[R] +.fi +.RE .TP .B \f[C]documentclass\f[R] document class: usually one of the standard classes, \f[C]article\f[R], -\f[C]report\f[R], and \f[C]book\f[R]; the KOMA-Script equivalents, -\f[C]scrartcl\f[R], \f[C]scrreprt\f[R], and \f[C]scrbook\f[R], which +\f[C]book\f[R], and \f[C]report\f[R]; the KOMA-Script equivalents, +\f[C]scrartcl\f[R], \f[C]scrbook\f[R], and \f[C]scrreprt\f[R], which default to smaller margins; or \f[C]memoir\f[R] .TP .B \f[C]geometry\f[R] option for \f[C]geometry\f[R] package, e.g. -\f[C]margin=1in\f[R]; repeat for multiple options +\f[C]margin=1in\f[R]; repeat for multiple options: +.RS +.IP +.nf +\f[C] +--- +geometry: +- top=30mm +- left=20mm +- heightrounded +\&... +\f[R] +.fi +.RE .TP .B \f[C]indent\f[R] uses document class settings for indentation (the default LaTeX template @@ -1684,11 +1741,6 @@ .B \f[C]secnumdepth\f[R] numbering depth for sections (with \f[C]--number-sections\f[R] option or \f[C]numbersections\f[R] variable) -.TP -.B \f[C]subparagraph\f[R] -disables default behavior of LaTeX template that redefines -(sub)paragraphs as sections, changing the appearance of nested headings -in some classes .SS Fonts .TP .B \f[C]fontenc\f[R] @@ -2145,11 +2197,11 @@ In writing LaTeX, enabling \f[C]smart\f[R] tells pandoc to use the ligatures when possible; if \f[C]smart\f[R] is disabled pandoc will use unicode quotation mark and dash characters. -.SS Headers and sections +.SS Headings and sections .SS Extension: \f[C]auto_identifiers\f[R] .PP -A header without an explicitly specified identifier will be -automatically assigned a unique identifier based on the header text. +A heading without an explicitly specified identifier will be +automatically assigned a unique identifier based on the heading text. .PP This extension can be enabled/disabled for the following formats: .TP @@ -2163,8 +2215,8 @@ .B enabled by default in \f[C]markdown\f[R], \f[C]muse\f[R] .PP -The default algorithm used to derive the identifier from the header text -is: +The default algorithm used to derive the identifier from the heading +text is: .IP \[bu] 2 Remove all formatting, links, etc. .IP \[bu] 2 @@ -2188,15 +2240,15 @@ tab(@); l l. T{ -Header +Heading T}@T{ Identifier T} _ T{ -\f[C]Header identifiers in HTML\f[R] +\f[C]Heading identifiers in HTML\f[R] T}@T{ -\f[C]header-identifiers-in-html\f[R] +\f[C]heading-identifiers-in-html\f[R] T} T{ \f[C]Ma\[^i]tre d\[aq]h\[^o]tel\f[R] @@ -2226,8 +2278,8 @@ .TE .PP These rules should, in most cases, allow one to determine the identifier -from the header text. -The exception is when several headers have the same text; in this case, +from the heading text. +The exception is when several headings have the same text; in this case, the first will get an identifier as described above; the second will get the same identifier with \f[C]-1\f[R] appended; the third with \f[C]-2\f[R]; and so on. @@ -2244,7 +2296,7 @@ .nf \f[C] See the section on -[header identifiers](#header-identifiers-in-html-latex-and-context). +[heading identifiers](#heading-identifiers-in-html-latex-and-context). \f[R] .fi .PP @@ -2255,7 +2307,7 @@ will be wrapped in a \f[C]section\f[R] (or a \f[C]div\f[R], if \f[C]html4\f[R] was specified), and the identifier will be attached to the enclosing \f[C]
\f[R] (or \f[C]
\f[R]) tag rather than -the header itself. +the heading itself. This allows entire sections to be manipulated using JavaScript or treated differently in CSS. .SS Extension: \f[C]ascii_identifiers\f[R] @@ -2354,14 +2406,14 @@ Haskell code rather than block quotations. Text between \f[C]\[rs]begin{code}\f[R] and \f[C]\[rs]end{code}\f[R] will also be treated as Haskell code. -For ATX-style headers the character \[aq]=\[aq] will be used instead of +For ATX-style headings the character \[aq]=\[aq] will be used instead of \[aq]#\[aq]. .IP \[bu] 2 In Markdown output, code blocks with classes \f[C]haskell\f[R] and \f[C]literate\f[R] will be rendered using bird tracks, and block quotations will be indented one space, so they will not be treated as Haskell code. -In addition, headers will be rendered setext-style (with underlines) +In addition, headings will be rendered setext-style (with underlines) rather than ATX-style (with \[aq]#\[aq] characters). (This is because ghc treats \[aq]#\[aq] characters in column 1 as introducing line numbers.) @@ -2490,52 +2542,52 @@ A backslash followed by a newline is also a hard line break. Note: in multiline and grid table cells, this is the only way to create a hard line break, since trailing spaces in the cells are ignored. -.SS Headers +.SS Headings .PP -There are two kinds of headers: Setext and ATX. -.SS Setext-style headers +There are two kinds of headings: Setext and ATX. +.SS Setext-style headings .PP -A setext-style header is a line of text \[dq]underlined\[dq] with a row -of \f[C]=\f[R] signs (for a level one header) or \f[C]-\f[R] signs (for -a level two header): +A setext-style heading is a line of text \[dq]underlined\[dq] with a row +of \f[C]=\f[R] signs (for a level-one heading) or \f[C]-\f[R] signs (for +a level-two heading): .IP .nf \f[C] -A level-one header -================== +A level-one heading +=================== -A level-two header ------------------- +A level-two heading +------------------- \f[R] .fi .PP -The header text can contain inline formatting, such as emphasis (see +The heading text can contain inline formatting, such as emphasis (see Inline formatting, below). -.SS ATX-style headers +.SS ATX-style headings .PP -An ATX-style header consists of one to six \f[C]#\f[R] signs and a line +An ATX-style heading consists of one to six \f[C]#\f[R] signs and a line of text, optionally followed by any number of \f[C]#\f[R] signs. The number of \f[C]#\f[R] signs at the beginning of the line is the -header level: +heading level: .IP .nf \f[C] -## A level-two header +## A level-two heading -### A level-three header ### +### A level-three heading ### \f[R] .fi .PP -As with setext-style headers, the header text can contain formatting: +As with setext-style headings, the heading text can contain formatting: .IP .nf \f[C] -# A level-one header with a [link](/url) and *emphasis* +# A level-one heading with a [link](/url) and *emphasis* \f[R] .fi .SS Extension: \f[C]blank_before_header\f[R] .PP -Standard Markdown syntax does not require a blank line before a header. +Standard Markdown syntax does not require a blank line before a heading. Pandoc does require this (except, of course, at the beginning of the document). The reason for the requirement is that it is all too easy for a @@ -2552,16 +2604,16 @@ .SS Extension: \f[C]space_in_atx_header\f[R] .PP Many Markdown implementations do not require a space between the opening -\f[C]#\f[R]s of an ATX header and the header text, so that -\f[C]#5 bolt\f[R] and \f[C]#hashtag\f[R] count as headers. +\f[C]#\f[R]s of an ATX heading and the heading text, so that +\f[C]#5 bolt\f[R] and \f[C]#hashtag\f[R] count as headings. With this extension, pandoc does require the space. -.SS Header identifiers +.SS Heading identifiers .PP See also the \f[C]auto_identifiers\f[R] extension above. .SS Extension: \f[C]header_attributes\f[R] .PP -Headers can be assigned attributes using this syntax at the end of the -line containing the header text: +Headings can be assigned attributes using this syntax at the end of the +line containing the heading text: .IP .nf \f[C] @@ -2569,16 +2621,16 @@ \f[R] .fi .PP -Thus, for example, the following headers will all be assigned the +Thus, for example, the following headings will all be assigned the identifier \f[C]foo\f[R]: .IP .nf \f[C] -# My header {#foo} +# My heading {#foo} -## My header ## {#foo} +## My heading ## {#foo} -My other header {#foo} +My other heading {#foo} --------------- \f[R] .fi @@ -2593,7 +2645,7 @@ Identifiers are used for labels and link anchors in the LaTeX, ConTeXt, Textile, and AsciiDoc writers. .PP -Headers with the class \f[C]unnumbered\f[R] will not be numbered, even +Headings with the class \f[C]unnumbered\f[R] will not be numbered, even if \f[C]--number-sections\f[R] is specified. A single hyphen (\f[C]-\f[R]) in an attribute context is equivalent to \f[C].unnumbered\f[R], and preferable in non-English documents. @@ -2601,7 +2653,7 @@ .IP .nf \f[C] -# My header {-} +# My heading {-} \f[R] .fi .PP @@ -2609,17 +2661,17 @@ .IP .nf \f[C] -# My header {.unnumbered} +# My heading {.unnumbered} \f[R] .fi .SS Extension: \f[C]implicit_header_references\f[R] .PP -Pandoc behaves as if reference links have been defined for each header. -So, to link to a header +Pandoc behaves as if reference links have been defined for each heading. +So, to link to a heading .IP .nf \f[C] -# Header identifiers in HTML +# Heading identifiers in HTML \f[R] .fi .PP @@ -2627,7 +2679,7 @@ .IP .nf \f[C] -[Header identifiers in HTML] +[Heading identifiers in HTML] \f[R] .fi .PP @@ -2635,7 +2687,7 @@ .IP .nf \f[C] -[Header identifiers in HTML][] +[Heading identifiers in HTML][] \f[R] .fi .PP @@ -2643,7 +2695,7 @@ .IP .nf \f[C] -[the section on header identifiers][header identifiers in +[the section on heading identifiers][heading identifiers in HTML] \f[R] .fi @@ -2652,18 +2704,18 @@ .IP .nf \f[C] -[Header identifiers in HTML](#header-identifiers-in-html) +[Heading identifiers in HTML](#heading-identifiers-in-html) \f[R] .fi .PP -If there are multiple headers with identical text, the corresponding +If there are multiple headings with identical text, the corresponding reference will link to the first one only, and you will need to use explicit links to link to the others, as described above. .PP Like regular reference links, these references are case-insensitive. .PP Explicit link reference definitions always take priority over implicit -header references. +heading references. So, in the following example, the link will point to \f[C]bar\f[R], not to \f[C]#foo\f[R]: .IP @@ -2680,7 +2732,7 @@ .PP Markdown uses email conventions for quoting blocks of text. A block quotation is one or more paragraphs or other block elements -(such as lists or headers), with each line preceded by a \f[C]>\f[R] +(such as lists or headings), with each line preceded by a \f[C]>\f[R] character and an optional space. (The \f[C]>\f[R] need not start at the left margin, but it should not be indented more than three spaces.) @@ -3373,7 +3425,7 @@ \f[R] .fi .PP -The headers and table rows must each fit on one line. +The header and table rows must each fit on one line. Column alignments are determined by the position of the header text relative to the dashed line below it: .IP \[bu] 2 @@ -3392,8 +3444,8 @@ The table must end with a blank line, or a line of dashes followed by a blank line. .PP -The column headers may be omitted, provided a dashed line is used to end -the table. +The column header row may be omitted, provided a dashed line is used to +end the table. For example: .IP .nf @@ -3406,13 +3458,13 @@ \f[R] .fi .PP -When headers are omitted, column alignments are determined on the basis -of the first line of the table body. +When the header row is omitted, column alignments are determined on the +basis of the first line of the table body. So, in the tables above, the columns would be right, left, center, and right aligned, respectively. .SS Extension: \f[C]multiline_tables\f[R] .PP -Multiline tables allow headers and table rows to span multiple lines of +Multiline tables allow header and table rows to span multiple lines of text (but cells that span multiple columns or rows of the table are not supported). Here is an example: @@ -3439,7 +3491,7 @@ These work like simple tables, but with the following differences: .IP \[bu] 2 They must begin with a row of dashes, before the header text (unless the -headers are omitted). +header row is omitted). .IP \[bu] 2 They must end with a row of dashes, then a blank line. .IP \[bu] 2 @@ -3451,7 +3503,7 @@ So, if you find that one of the columns is too narrow in the output, try widening it in the Markdown source. .PP -Headers may be omitted in multiline tables as well as simple tables: +The header may be omitted in multiline tables as well as simple tables: .IP .nf \f[C] @@ -3464,7 +3516,7 @@ rows. ----------- ------- --------------- ------------------------- -: Here\[aq]s a multiline table without headers. +: Here\[aq]s a multiline table without a header. \f[R] .fi .PP @@ -4057,6 +4109,10 @@ It will appear verbatim surrounded by \f[C]$...$\f[R] (for inline math) or \f[C]$$...$$\f[R] (for display math). .TP +.B XWiki +It will appear verbatim surrounded by +\f[C]{{formula}}..{{/formula}}\f[R]. +.TP .B reStructuredText It will be rendered using an interpreted text role \f[C]:math:\f[R]. .TP @@ -4439,7 +4495,7 @@ .SS Internal links .PP To link to another section of the same document, use the automatically -generated identifier (see Header identifiers). +generated identifier (see Heading identifiers). For example: .IP .nf @@ -4949,8 +5005,8 @@ Generation of the bibliography can be suppressed by setting \f[C]suppress-bibliography: true\f[R] in the YAML metadata. .PP -If you wish the bibliography to have a section header, you can set -\f[C]reference-section-title\f[R] in the metadata, or put the header at +If you wish the bibliography to have a section heading, you can set +\f[C]reference-section-title\f[R] in the metadata, or put the heading at the beginning of the div with id \f[C]refs\f[R] (if you are using it) or at the end of your document: .IP @@ -4962,8 +5018,8 @@ \f[R] .fi .PP -The bibliography will be inserted after this header. -Note that the \f[C]unnumbered\f[R] class will be added to this header, +The bibliography will be inserted after this heading. +Note that the \f[C]unnumbered\f[R] class will be added to this heading, so that the section will not be numbered. .PP If you want to include items in the bibliography without actually citing @@ -5136,8 +5192,9 @@ .fi .SS Extension: \f[C]mmd_header_identifiers\f[R] .PP -Parses multimarkdown style header identifiers (in square brackets, after -the header but before any trailing \f[C]#\f[R]s in an ATX header). +Parses multimarkdown style heading identifiers (in square brackets, +after the heading but before any trailing \f[C]#\f[R]s in an ATX +heading). .SS Extension: \f[C]compact_definition_lists\f[R] .PP Activates the definition list syntax of pandoc 1.12.x and earlier. @@ -5306,26 +5363,26 @@ .fi .SS Structuring the slide show .PP -By default, the \f[I]slide level\f[R] is the highest header level in the -hierarchy that is followed immediately by content, and not another -header, somewhere in the document. -In the example above, level 1 headers are always followed by level 2 -headers, which are followed by content, so 2 is the slide level. +By default, the \f[I]slide level\f[R] is the highest heading level in +the hierarchy that is followed immediately by content, and not another +heading, somewhere in the document. +In the example above, level-1 headings are always followed by level-2 +headings, which are followed by content, so the slide level is 2. This default can be overridden using the \f[C]--slide-level\f[R] option. .PP The document is carved up into slides according to the following rules: .IP \[bu] 2 A horizontal rule always starts a new slide. .IP \[bu] 2 -A header at the slide level always starts a new slide. +A heading at the slide level always starts a new slide. .IP \[bu] 2 -Headers \f[I]below\f[R] the slide level in the hierarchy create headers -\f[I]within\f[R] a slide. +Headings \f[I]below\f[R] the slide level in the hierarchy create +headings \f[I]within\f[R] a slide. .IP \[bu] 2 -Headers \f[I]above\f[R] the slide level in the hierarchy create +Headings \f[I]above\f[R] the slide level in the hierarchy create \[dq]title slides,\[dq] which just contain the section title and help to break the slide show into sections. -Non-slide content under these headers will be included on the title +Non-slide content under these headings will be included on the title slide (for HTML slide shows) or in a subsequent slide with the same title (for beamer). .IP \[bu] 2 @@ -5336,13 +5393,13 @@ .PP These rules are designed to support many different styles of slide show. If you don\[aq]t care about structuring your slides into sections and -subsections, you can just use level 1 headers for all each slide. -(In that case, level 1 will be the slide level.) But you can also +subsections, you can just use level-1 headings for all each slide. +(In that case, level-1 will be the slide level.) But you can also structure the slide show into sections, as in the example above. .PP Note: in reveal.js slide shows, if slide level is 2, a two-dimensional -layout will be produced, with level 1 headers building horizontally and -level 2 headers building vertically. +layout will be produced, with level-1 headings building horizontally and +level-2 headings building vertically. It is not recommended that you use deeper nesting of section levels with reveal.js. .SS Incremental lists @@ -5448,10 +5505,10 @@ \f[R] .fi .PP -Note that header attributes will turn into slide attributes (on a +Note that heading attributes will turn into slide attributes (on a \f[C]
\f[R] or \f[C]
\f[R]) in HTML slide formats, allowing you to style individual slides. -In beamer, the only header attribute that affects slides is the +In beamer, the only heading attribute that affects slides is the \f[C]allowframebreaks\f[R] class, which sets the \f[C]allowframebreaks\f[R] option, causing multiple slides to be created if the content overfills the frame. @@ -5510,7 +5567,7 @@ Sometimes it is necessary to add the LaTeX \f[C][fragile]\f[R] option to a frame in beamer (for example, when using the \f[C]minted\f[R] environment). -This can be forced by adding the \f[C]fragile\f[R] class to the header +This can be forced by adding the \f[C]fragile\f[R] class to the heading introducing the slide: .IP .nf @@ -5543,7 +5600,7 @@ .PP To set an image for a particular reveal.js slide, add \f[C]{data-background-image=\[dq]/path/to/image\[dq]}\f[R] to the first -slide-level header on the slide (which may even be empty). +slide-level heading on the slide (which may even be empty). .PP In reveal.js\[aq]s overview mode, the parallaxBackgroundImage will show up only on the first slide. @@ -5570,7 +5627,7 @@ ## {data-background-image=\[dq]/path/to/special_image.jpg\[dq]} -Slide 2 has a special image for its background, even though the header has no content. +Slide 2 has a special image for its background, even though the heading has no content. \f[R] .fi .SH CREATING EPUBS WITH PANDOC @@ -5697,7 +5754,7 @@ .RE .SS The \f[C]epub:type\f[R] attribute .PP -For \f[C]epub3\f[R] output, you can mark up the header that corresponds +For \f[C]epub3\f[R] output, you can mark up the heading that corresponds to an EPUB chapter using the \f[C]epub:type\f[R] attribute. For example, to set the attribute to the value \f[C]prologue\f[R], use this markdown: @@ -5954,6 +6011,13 @@ attributes, we recommend specifying the extensions \f[C]-raw_html-raw_tex+raw_attribute\f[R] when translating between Markdown and ipynb notebooks. +.PP +Note that options and extensions that affect reading and writing of +Markdown will also affect Markdown cells in ipynb notebooks. +For example, \f[C]--wrap=preserve\f[R] will preserve soft line breaks in +Markdown cells; \f[C]--atx-headers\f[R] will cause ATX-style headings to +be used; and \f[C]--preserve-tabs\f[R] will prevent tabs from being +turned to spaces. .SH SYNTAX HIGHLIGHTING .PP Pandoc will automatically highlight syntax in fenced code blocks that @@ -6168,7 +6232,7 @@ If \f[C]raw_html\f[R] is enabled for the Markdown input, users can inject arbitrary HTML. Even if \f[C]raw_html\f[R] is disabled, users can include dangerous -content in attributes for headers, spans, and code blocks. +content in attributes for headings, spans, and code blocks. To be safe, you should run all the generated HTML through an HTML sanitizer. .SH AUTHORS diff --git a/pandoc.cabal b/pandoc.cabal --- a/pandoc.cabal +++ b/pandoc.cabal @@ -1,5 +1,5 @@ name: pandoc -version: 2.7.1 +version: 2.7.2 cabal-version: 2.0 build-type: Simple license: GPL-2 @@ -11,8 +11,7 @@ stability: alpha homepage: https://pandoc.org category: Text -tested-with: GHC == 7.10.3, GHC == 8.0.2, GHC == 8.2.2, GHC == 8.4.4, - GHC == 8.6.3 +tested-with: GHC == 8.0.2, GHC == 8.2.2, GHC == 8.4.4, GHC == 8.6.3 synopsis: Conversion between markup formats description: Pandoc is a Haskell library for converting from one markup format to another, and a command-line tool that uses @@ -25,10 +24,11 @@ roff man, and Textile, and it can write Markdown, reStructuredText, XHTML, HTML 5, LaTeX, ConTeXt, DocBook, JATS, OPML, TEI, OpenDocument, ODT, Word docx, - PowerPoint pptx, RTF, MediaWiki, DokuWiki, ZimWiki, Textile, - roff man, roff ms, plain text, Emacs Org-Mode, - AsciiDoc, Haddock markup, EPUB (v2 and v3), ipynb, - FictionBook2, InDesign ICML, Muse, LaTeX beamer slides, + PowerPoint pptx, RTF, MediaWiki, DokuWiki, XWiki, + ZimWiki, Textile, roff man, roff ms, plain text, + Emacs Org-Mode, AsciiDoc, Haddock markup, + EPUB (v2 and v3), ipynb, FictionBook2, + InDesign ICML, Muse, LaTeX beamer slides, and several kinds of HTML/JavaScript slide shows (S5, Slidy, Slideous, DZSlides, reveal.js). . @@ -62,6 +62,7 @@ data/templates/default.plain data/templates/default.mediawiki data/templates/default.dokuwiki + data/templates/default.xwiki data/templates/default.zimwiki data/templates/default.rtf data/templates/default.s5 @@ -138,6 +139,10 @@ data/pptx/ppt/slides/_rels/slide2.xml.rels data/pptx/ppt/slides/slide2.xml data/pptx/ppt/slides/slide1.xml + data/pptx/ppt/slides/_rels/slide3.xml.rels + data/pptx/ppt/slides/_rels/slide4.xml.rels + data/pptx/ppt/slides/slide3.xml + data/pptx/ppt/slides/slide4.xml data/pptx/ppt/viewProps.xml data/pptx/ppt/tableStyles.xml data/pptx/ppt/slideMasters/_rels/slideMaster1.xml.rels @@ -288,6 +293,7 @@ test/writer.opml test/writer.dokuwiki test/writer.zimwiki + test/writer.xwiki test/writer.muse test/writer.custom test/writers-lang-and-dir.latex @@ -376,6 +382,7 @@ random >= 1 && < 1.2, pandoc-types >= 1.17.5 && < 1.18, aeson >= 0.7 && < 1.5, + scientific >= 0.3 && < 0.4, aeson-pretty >= 0.8.5 && < 0.9, tagsoup >= 0.14.6 && < 0.15, base64-bytestring >= 0.1 && < 1.1, @@ -404,7 +411,8 @@ case-insensitive >= 1.2 && < 1.3, unicode-transforms >= 0.3 && < 0.4, HsYAML >= 0.1.1.1 && < 0.2, - ipynb >= 0.1 && < 0.2 + ipynb >= 0.1 && < 0.2, + attoparsec >= 0.12 && < 0.14 if impl(ghc < 8.0) build-depends: semigroups == 0.18.*, -- basement 0.0.8 and foundation 0.0.21, transitive @@ -505,6 +513,7 @@ Text.Pandoc.Writers.Textile, Text.Pandoc.Writers.MediaWiki, Text.Pandoc.Writers.DokuWiki, + Text.Pandoc.Writers.XWiki, Text.Pandoc.Writers.ZimWiki, Text.Pandoc.Writers.RTF, Text.Pandoc.Writers.ODT, diff --git a/src/Text/Pandoc/App.hs b/src/Text/Pandoc/App.hs --- a/src/Text/Pandoc/App.hs +++ b/src/Text/Pandoc/App.hs @@ -256,11 +256,11 @@ case reader of TextReader r | optFileScope opts || readerName == "json" -> - mconcat <$> mapM (readSource >=> r readerOpts) sources + mconcat <$> mapM (readSource >=> r readerOpts) sources' | otherwise -> readSources sources' >>= r readerOpts ByteStringReader r -> - mconcat <$> mapM (readFile' >=> r readerOpts) sources + mconcat <$> mapM (readFile' >=> r readerOpts) sources' when (readerName == "markdown_github" || diff --git a/src/Text/Pandoc/Class.hs b/src/Text/Pandoc/Class.hs --- a/src/Text/Pandoc/Class.hs +++ b/src/Text/Pandoc/Class.hs @@ -9,10 +9,6 @@ {-# LANGUAGE FlexibleContexts #-} {-# LANGUAGE UndecidableInstances #-} {-# LANGUAGE ScopedTypeVariables #-} -#if MIN_VERSION_base(4,8,0) -#else -{-# LANGUAGE OverlappingInstances #-} -#endif {- | Module : Text.Pandoc.Class Copyright : Copyright (C) 2016-17 Jesse Rosenthal, John MacFarlane @@ -569,7 +565,8 @@ case parseURIReference' s' of Just u' -> openURL $ show $ u' `nonStrictRelativeTo` u Nothing -> openURL s' -- will throw error - (Nothing, s'@('/':'/':_)) -> -- protocol-relative URI + (Nothing, s'@('/':'/':c:_)) | c /= '?' -> -- protocol-relative URI + -- we exclude //? because of //?UNC/ on Windows case parseURIReference' s' of Just u' -> openURL $ show $ u' `nonStrictRelativeTo` httpcolon Nothing -> openURL s' -- will throw error @@ -706,6 +703,10 @@ , "ppt/slides/slide1.xml" , "ppt/slides/_rels/slide2.xml.rels" , "ppt/slides/slide2.xml" + , "ppt/slides/_rels/slide3.xml.rels" + , "ppt/slides/slide3.xml" + , "ppt/slides/_rels/slide4.xml.rels" + , "ppt/slides/slide4.xml" , "ppt/tableStyles.xml" , "ppt/theme/theme1.xml" , "ppt/viewProps.xml" @@ -1040,11 +1041,7 @@ putCommonState = lift . putCommonState logOutput = lift . logOutput -#if MIN_VERSION_base(4,8,0) instance {-# OVERLAPS #-} PandocMonad m => PandocMonad (ParsecT s st m) where -#else -instance PandocMonad m => PandocMonad (ParsecT s st m) where -#endif lookupEnv = lift . lookupEnv getCurrentTime = lift getCurrentTime getCurrentTimeZone = lift getCurrentTimeZone diff --git a/src/Text/Pandoc/Highlighting.hs b/src/Text/Pandoc/Highlighting.hs --- a/src/Text/Pandoc/Highlighting.hs +++ b/src/Text/Pandoc/Highlighting.hs @@ -139,6 +139,7 @@ ("gap","GAP"), ("gcl","GCL"), ("gnuplot","Gnuplot"), + ("go","Go"), ("hansl","hansl"), ("haskell","Haskell"), ("html","HTML"), diff --git a/src/Text/Pandoc/ImageSize.hs b/src/Text/Pandoc/ImageSize.hs --- a/src/Text/Pandoc/ImageSize.hs +++ b/src/Text/Pandoc/ImageSize.hs @@ -50,7 +50,9 @@ import qualified Text.XML.Light as Xml import qualified Data.Map as M import Control.Monad.Except +import Control.Applicative import Data.Maybe (fromMaybe) +import qualified Data.Attoparsec.ByteString.Char8 as A -- quick and dirty functions to get image sizes -- algorithms borrowed from wwwis.pl @@ -267,26 +269,32 @@ pdfSize :: ByteString -> Maybe ImageSize pdfSize img = - case dropWhile (\l -> not (l == "stream" || - "/MediaBox" `B.isPrefixOf` l)) (B.lines img) of - (x:_) - | "/MediaBox" `B.isPrefixOf` x - -> case B.words . B.takeWhile (/=']') - . B.drop 1 - . B.dropWhile (/='[') - $ x of - [x1, y1, x2, y2] -> do - x1' <- safeRead $ B.unpack x1 - x2' <- safeRead $ B.unpack x2 - y1' <- safeRead $ B.unpack y1 - y2' <- safeRead $ B.unpack y2 - return ImageSize{ - pxX = x2' - x1' - , pxY = y2' - y1' - , dpiX = 72 - , dpiY = 72 } - _ -> mzero - _ -> mzero + case A.parseOnly pPdfSize img of + Left _ -> Nothing + Right sz -> Just sz + +pPdfSize :: A.Parser ImageSize +pPdfSize = do + A.skipWhile (/='/') + A.char8 '/' + (do A.string "MediaBox" + A.skipSpace + A.char8 '[' + A.skipSpace + [x1,y1,x2,y2] <- A.count 4 $ do + A.skipSpace + raw <- A.many1 $ A.satisfy (\c -> isDigit c || c == '.') + case safeRead raw of + Just (r :: Double) -> return $ floor r + Nothing -> mzero + A.skipSpace + A.char8 ']' + return $ ImageSize{ + pxX = x2 - x1 + , pxY = y2 - y1 + , dpiX = 72 + , dpiY = 72 } + ) <|> pPdfSize pngSize :: ByteString -> Maybe ImageSize pngSize img = do diff --git a/src/Text/Pandoc/PDF.hs b/src/Text/Pandoc/PDF.hs --- a/src/Text/Pandoc/PDF.hs +++ b/src/Text/Pandoc/PDF.hs @@ -34,11 +34,7 @@ import System.IO (stdout) import System.IO.Temp (withSystemTempDirectory, withTempDirectory, withTempFile) -#if MIN_VERSION_base(4,8,3) import System.IO.Error (IOError, isDoesNotExistError) -#else -import System.IO.Error (isDoesNotExistError) -#endif import Text.Pandoc.Definition import Text.Pandoc.Error (PandocError (PandocPDFProgramNotFoundError)) import Text.Pandoc.MIME (getMimeType) diff --git a/src/Text/Pandoc/Pretty.hs b/src/Text/Pandoc/Pretty.hs --- a/src/Text/Pandoc/Pretty.hs +++ b/src/Text/Pandoc/Pretty.hs @@ -65,7 +65,7 @@ import Control.Monad.State.Strict import Data.Char (isSpace) import Data.Foldable (toList) -import Data.List (intersperse) +import Data.List (intersperse, foldl') import Data.Sequence (Seq, ViewL (..), fromList, mapWithIndex, singleton, viewl, (<|)) import qualified Data.Sequence as Seq @@ -305,7 +305,7 @@ let xs' = dropWhile isBreakingSpace xs let next = takeWhile isText xs' st <- get - let off = sum $ map offsetOf next + let off = foldl' (+) 0 $ map offsetOf next case lineLength st of Just l | column st + 1 + off > l -> do outp (-1) "\n" @@ -540,4 +540,4 @@ -- | Get real length of string, taking into account combining and double-wide -- characters. realLength :: String -> Int -realLength = sum . map charWidth +realLength = foldl' (+) 0 . map charWidth diff --git a/src/Text/Pandoc/Readers/Docx.hs b/src/Text/Pandoc/Readers/Docx.hs --- a/src/Text/Pandoc/Readers/Docx.hs +++ b/src/Text/Pandoc/Readers/Docx.hs @@ -79,9 +79,6 @@ import Text.Pandoc.Shared import Text.Pandoc.Walk import Text.TeXMath (writeTeX) -#if !(MIN_VERSION_base(4,8,0)) -import Data.Traversable (traverse) -#endif import Control.Monad.Except (throwError) import Text.Pandoc.Class (PandocMonad) import qualified Text.Pandoc.Class as P diff --git a/src/Text/Pandoc/Readers/DokuWiki.hs b/src/Text/Pandoc/Readers/DokuWiki.hs --- a/src/Text/Pandoc/Readers/DokuWiki.hs +++ b/src/Text/Pandoc/Readers/DokuWiki.hs @@ -358,7 +358,7 @@ _ -> Nothing image :: PandocMonad m => DWParser m B.Inlines -image = parseLink fromRaw "{{" "}}" +image = try $ parseLink fromRaw "{{" "}}" where fromRaw path description = if linkOnly diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs --- a/src/Text/Pandoc/Readers/HTML.hs +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -807,7 +807,8 @@ toStringAttr :: [(Text, Text)] -> [(String, String)] toStringAttr = map go - where go (x,y) = (T.unpack x, T.unpack y) + where go (x,y) = (T.unpack (fromMaybe x $ T.stripPrefix "data-" x), + T.unpack y) pScriptMath :: PandocMonad m => TagParser m Inlines pScriptMath = try $ do diff --git a/src/Text/Pandoc/Readers/Ipynb.hs b/src/Text/Pandoc/Readers/Ipynb.hs --- a/src/Text/Pandoc/Readers/Ipynb.hs +++ b/src/Text/Pandoc/Readers/Ipynb.hs @@ -23,6 +23,7 @@ import Data.Maybe (fromMaybe) import Data.Digest.Pure.SHA (sha1, showDigest) import Text.Pandoc.Options +import qualified Data.Scientific as Scientific import qualified Text.Pandoc.Builder as B import Text.Pandoc.Logging import Text.Pandoc.Definition @@ -89,10 +90,11 @@ return $ B.divWith ("",["cell","markdown"],kvs) $ B.fromList bs Ipynb.Raw -> do - let format = fromMaybe "" $ lookup "format" kvs + -- we use ipynb to indicate no format given (a wildcard in nbformat) + let format = fromMaybe "ipynb" $ lookup "format" kvs let format' = case format of - "text/html" -> "html" + "text/html" -> "html" "text/latex" -> "latex" "application/pdf" -> "latex" "text/markdown" -> "markdown" @@ -209,7 +211,9 @@ Success xs -> MetaList $ map valueToMetaValue xs valueToMetaValue (Bool b) = MetaBool b valueToMetaValue (String t) = MetaString (T.unpack t) - valueToMetaValue (Number n) = MetaString (show n) + valueToMetaValue (Number n) + | Scientific.isInteger n = MetaString (show (floor n :: Integer)) + | otherwise = MetaString (show n) valueToMetaValue Aeson.Null = MetaString "" jsonMetaToPairs :: JSONMeta -> [(String, String)] diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -489,10 +489,10 @@ -- note: bulletList needs to be before header because of -- the possibility of empty list items: - , bulletList - , header - , lhsCodeBlock , divHtml , divFenced + , header + , lhsCodeBlock , htmlBlock , table , codeBlockIndented @@ -1039,7 +1039,18 @@ para :: PandocMonad m => MarkdownParser m (F Blocks) para = try $ do exts <- getOption readerExtensions - result <- trimInlinesF <$> inlines1 + let implicitFigures x + | extensionEnabled Ext_implicit_figures exts = do + x' <- x + case B.toList x' of + [Image attr alt (src,tit)] + | not (null alt) -> + -- the fig: at beginning of title indicates a figure + return $ B.singleton + $ Image attr alt (src,'f':'i':'g':':':tit) + _ -> return x' + | otherwise = x + result <- implicitFigures . trimInlinesF <$> inlines1 option (B.plain <$> result) $ try $ do newline @@ -1062,16 +1073,7 @@ if divLevel > 0 then lookAhead divFenceEnd else mzero - return $ do - result' <- result - case B.toList result' of - [Image attr alt (src,tit)] - | not (null alt) && - Ext_implicit_figures `extensionEnabled` exts -> - -- the fig: at beginning of title indicates a figure - return $ B.para $ B.singleton - $ Image attr alt (src,'f':'i':'g':':':tit) - _ -> return $ B.para result' + return $ B.para <$> result plain :: PandocMonad m => MarkdownParser m (F Blocks) plain = fmap B.plain . trimInlinesF <$> inlines1 diff --git a/src/Text/Pandoc/Readers/Vimwiki.hs b/src/Text/Pandoc/Readers/Vimwiki.hs --- a/src/Text/Pandoc/Readers/Vimwiki.hs +++ b/src/Text/Pandoc/Readers/Vimwiki.hs @@ -74,7 +74,8 @@ many1Till, orderedListMarker, readWithM, registerHeader, spaceChar, stateMeta, stateOptions, uri) -import Text.Pandoc.Shared (crFilter, splitBy, stringify, stripFirstAndLast) +import Text.Pandoc.Shared (crFilter, splitBy, stringify, stripFirstAndLast, + isURI) import Text.Parsec.Char (alphaNum, anyChar, char, newline, noneOf, oneOf, space, spaces, string) import Text.Parsec.Combinator (between, choice, count, eof, lookAhead, many1, @@ -544,11 +545,17 @@ False -> do manyTill anyChar (string "]]") -- not using try here because [[hell]o]] is not rendered as a link in vimwiki - return $ B.link (procLink contents) "" (B.str contents) + let tit = if isURI contents + then "" + else "wikilink" + return $ B.link (procLink contents) tit (B.str contents) True -> do url <- manyTill anyChar $ char '|' lab <- mconcat <$> manyTill inline (string "]]") - return $ B.link (procLink url) "" lab + let tit = if isURI url + then "" + else "wikilink" + return $ B.link (procLink url) tit lab image :: PandocMonad m => VwParser m Inlines image = try $ do @@ -580,13 +587,13 @@ procLink' :: String -> String procLink' s | take 6 s == "local:" = "file" ++ drop 5 s - | take 6 s == "diary:" = "diary/" ++ drop 6 s ++ ".html" + | take 6 s == "diary:" = "diary/" ++ drop 6 s | or ((`isPrefixOf` s) <$> [ "http:", "https:", "ftp:", "file:", "mailto:", "news:", "telnet:" ]) = s | s == "" = "" | last s == '/' = s - | otherwise = s ++ ".html" + | otherwise = s procLink :: String -> String procLink s = procLink' x ++ y diff --git a/src/Text/Pandoc/Writers.hs b/src/Text/Pandoc/Writers.hs --- a/src/Text/Pandoc/Writers.hs +++ b/src/Text/Pandoc/Writers.hs @@ -63,6 +63,7 @@ , writeTEI , writeTexinfo , writeTextile + , writeXWiki , writeZimWiki , getWriter ) where @@ -107,6 +108,7 @@ import Text.Pandoc.Writers.TEI import Text.Pandoc.Writers.Texinfo import Text.Pandoc.Writers.Textile +import Text.Pandoc.Writers.XWiki import Text.Pandoc.Writers.ZimWiki import Text.Parsec.Error @@ -156,6 +158,7 @@ ,("rst" , TextWriter writeRST) ,("mediawiki" , TextWriter writeMediaWiki) ,("dokuwiki" , TextWriter writeDokuWiki) + ,("xwiki" , TextWriter writeXWiki) ,("zimwiki" , TextWriter writeZimWiki) ,("textile" , TextWriter writeTextile) ,("rtf" , TextWriter writeRTF) diff --git a/src/Text/Pandoc/Writers/Docx.hs b/src/Text/Pandoc/Writers/Docx.hs --- a/src/Text/Pandoc/Writers/Docx.hs +++ b/src/Text/Pandoc/Writers/Docx.hs @@ -1389,10 +1389,7 @@ ) br :: Element -br = breakElement "textWrapping" - -breakElement :: String -> Element -breakElement kind = mknode "w:r" [] [mknode "w:br" [("w:type",kind)] () ] +br = mknode "w:r" [] [mknode "w:br" [] ()] -- Word will insert these footnotes into the settings.xml file -- (whether or not they're visible in the document). If they're in the diff --git a/src/Text/Pandoc/Writers/HTML.hs b/src/Text/Pandoc/Writers/HTML.hs --- a/src/Text/Pandoc/Writers/HTML.hs +++ b/src/Text/Pandoc/Writers/HTML.hs @@ -603,7 +603,7 @@ return $ mapMaybe (\(x,y) -> if html5 then - if x `Set.member` html5Attributes + if x `Set.member` (html5Attributes <> rdfaAttributes) || ':' `elem` x -- e.g. epub: namespace || "data-" `isPrefixOf` x then Just $ customAttribute (fromString x) (toValue y) @@ -611,7 +611,7 @@ (toValue y) else if mbEpubVersion == Just EPUB2 && - not (x `Set.member` html4Attributes || + not (x `Set.member` (html4Attributes <> rdfaAttributes) || "xml:" `isPrefixOf` x) then Nothing else Just $ customAttribute (fromString x) (toValue y)) @@ -1469,6 +1469,23 @@ , "width" , "workertype" , "wrap" + ] + +-- See https://en.wikipedia.org/wiki/RDFa, https://www.w3.org/TR/rdfa-primer/ +rdfaAttributes :: Set.Set String +rdfaAttributes = Set.fromList + [ "about" + , "rel" + , "rev" + , "src" + , "href" + , "resource" + , "property" + , "content" + , "datatype" + , "typeof" + , "vocab" + , "prefix" ] html4Attributes :: Set.Set String diff --git a/src/Text/Pandoc/Writers/Ipynb.hs b/src/Text/Pandoc/Writers/Ipynb.hs --- a/src/Text/Pandoc/Writers/Ipynb.hs +++ b/src/Text/Pandoc/Writers/Ipynb.hs @@ -19,6 +19,7 @@ import Prelude import Control.Monad.State import qualified Data.Map as M +import Data.Char (toLower) import Data.Maybe (catMaybes, fromMaybe) import Text.Pandoc.Options import Text.Pandoc.Definition @@ -62,8 +63,16 @@ opts{ writerTemplate = Nothing } (Pandoc nullMeta [Plain ils]) let jupyterMeta = case lookupMeta "jupyter" meta of - Just (MetaMap m) -> (Meta m <> B.deleteMeta "jupyter" meta) + Just (MetaMap m) -> Meta m _ -> mempty + let nbformat = + case (lookupMeta "nbformat" jupyterMeta, + lookupMeta "nbformat_minor" jupyterMeta) of + (Just (MetaInlines [Str "4"]), Just (MetaInlines [Str y])) -> + case safeRead y of + Just z -> (4, z) + Nothing -> (4, 5) + _ -> (4, 5) -- write as v4.5 metadata' <- metaToJSON' blockWriter inlineWriter $ B.deleteMeta "nbformat" $ B.deleteMeta "nbformat_minor" $ jupyterMeta @@ -74,7 +83,7 @@ cells <- extractCells opts blocks return $ Notebook{ notebookMetadata = metadata - , notebookFormat = (4, 5) + , notebookFormat = nbformat , notebookCells = cells } addAttachment :: PandocMonad m @@ -125,10 +134,10 @@ , cellAttachments = Nothing } :) <$> extractCells opts bs | "cell" `elem` classes , "raw" `elem` classes = - case xs of + case consolidateAdjacentRawBlocks xs of [RawBlock (Format f) raw] -> do let format' = - case f of + case map toLower f of "html" -> "text/html" "revealjs" -> "text/html" "latex" -> "text/latex" @@ -138,8 +147,10 @@ (Cell{ cellType = Raw , cellSource = Source $ breakLines $ T.pack raw - , cellMetadata = M.insert "format" - (Aeson.String $ T.pack format') mempty + , cellMetadata = if format' == "ipynb" -- means no format given + then mempty + else M.insert "format" + (Aeson.String $ T.pack format') mempty , cellAttachments = Nothing } :) <$> extractCells opts bs _ -> extractCells opts bs extractCells opts (CodeBlock (_id,classes,kvs) raw : bs) @@ -187,7 +198,7 @@ extractData :: PandocMonad m => [Block] -> m (MimeBundle, JSONMeta) extractData bs = do - (mmap, meta) <- foldM go mempty bs + (mmap, meta) <- foldM go mempty $ consolidateAdjacentRawBlocks bs return (MimeBundle mmap, meta) where go (mmap, meta) b@(Para [Image (_,_,kvs) _ (src,_)]) = do @@ -219,3 +230,11 @@ | (k,v) <- kvs , k /= "execution_count" ] + +consolidateAdjacentRawBlocks :: [Block] -> [Block] +consolidateAdjacentRawBlocks [] = [] +consolidateAdjacentRawBlocks (RawBlock f1 x : RawBlock f2 y : xs) + | f1 == f2 + = consolidateAdjacentRawBlocks (RawBlock f1 (x <> "\n" <> y) : xs) +consolidateAdjacentRawBlocks (x : xs) = + x : consolidateAdjacentRawBlocks xs diff --git a/src/Text/Pandoc/Writers/JATS.hs b/src/Text/Pandoc/Writers/JATS.hs --- a/src/Text/Pandoc/Writers/JATS.hs +++ b/src/Text/Pandoc/Writers/JATS.hs @@ -319,7 +319,15 @@ -- | Convert a list of inline elements to JATS. inlinesToJATS :: PandocMonad m => WriterOptions -> [Inline] -> JATS m Doc -inlinesToJATS opts lst = hcat <$> mapM (inlineToJATS opts) lst +inlinesToJATS opts lst = hcat <$> mapM (inlineToJATS opts) (fixCitations lst) + where + fixCitations [] = [] + fixCitations (x@(RawInline (Format "jats") "") : xs) = + let isRawInline (RawInline{}) = True + isRawInline _ = False + (ys,zs) = break isRawInline xs + in x : Str (stringify ys) : fixCitations zs + fixCitations (x:xs) = x : fixCitations xs -- | Convert an inline element to JATS. inlineToJATS :: PandocMonad m => WriterOptions -> Inline -> JATS m Doc diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs --- a/src/Text/Pandoc/Writers/LaTeX.hs +++ b/src/Text/Pandoc/Writers/LaTeX.hs @@ -20,6 +20,7 @@ import Prelude import Control.Applicative ((<|>)) import Control.Monad.State.Strict +import Data.Monoid (Any(..)) import Data.Aeson (FromJSON, object, (.=)) import Data.Char (isAlphaNum, isAscii, isDigit, isLetter, isSpace, isPunctuation, ord, toLower) @@ -51,7 +52,8 @@ data WriterState = WriterState { stInNote :: Bool -- true if we're in a note , stInQuote :: Bool -- true if in a blockquote - , stInMinipage :: Bool -- true if in minipage + , stExternalNotes :: Bool -- true if in context where + -- we need to store footnotes , stInHeading :: Bool -- true if in a section heading , stInItem :: Bool -- true if in \item[..] , stNotes :: [Doc] -- notes in a minipage @@ -76,7 +78,7 @@ startingState options = WriterState { stInNote = False , stInQuote = False - , stInMinipage = False + , stExternalNotes = False , stInHeading = False , stInItem = False , stNotes = [] @@ -340,6 +342,14 @@ -> cs <> xs _ -> cs <> "{}" <> xs in case x of + '?' | ligatures -> -- avoid ?` ligature + case xs of + '`':_ -> emits "?{}" + _ -> emitc x + '!' | ligatures -> -- avoid !` ligature + case xs of + '`':_ -> emits "!{}" + _ -> emitc x '{' -> emits "\\{" '}' -> emits "\\}" '`' | ctx == CodeString -> emitcseq "\\textasciigrave" @@ -590,7 +600,7 @@ inlineListToLaTeX $ dropWhile isLineBreakOrSpace lst -- title beginning with fig: indicates that the image is a figure blockToLaTeX (Para [Image attr@(ident, _, _) txt (src,'f':'i':'g':':':tit)]) = do - (capt, captForLof, footnotes) <- getCaption txt + (capt, captForLof, footnotes) <- getCaption True txt lab <- labelFor ident let caption = "\\caption" <> captForLof <> braces capt <> lab img <- inlineToLaTeX (Image attr txt (src,tit)) @@ -598,7 +608,7 @@ "\\centering" $$ img $$ caption <> cr let figure = cr <> "\\begin{figure}" $$ innards $$ "\\end{figure}" st <- get - return $ if stInNote st || stInMinipage st + return $ if stExternalNotes st -- can't have figures in notes or minipage (here, table cell) -- http://www.tex.ac.uk/FAQ-ouparmd.html then "\\begin{center}" $$ img $+$ capt $$ "\\end{center}" @@ -783,7 +793,7 @@ modify $ \s -> s{stInHeading = False} return hdr blockToLaTeX (Table caption aligns widths heads rows) = do - (captionText, captForLof, footnotes) <- getCaption caption + (captionText, captForLof, captNotes) <- getCaption False caption let toHeaders hs = do contents <- tableRowToLaTeX True aligns widths hs return ("\\toprule" $$ contents $$ "\\midrule") let removeNote (Note _) = Span ("", [], []) [] @@ -804,6 +814,7 @@ rows' <- mapM (tableRowToLaTeX False aligns widths) rows let colDescriptors = text $ concatMap toColDescriptor aligns modify $ \s -> s{ stTable = True } + notes <- notesToLaTeX <$> gets stNotes return $ "\\begin{longtable}[]" <> braces ("@{}" <> colDescriptors <> "@{}") -- the @{} removes extra space at beginning and end @@ -814,20 +825,25 @@ $$ vcat rows' $$ "\\bottomrule" $$ "\\end{longtable}" - $$ footnotes + $$ captNotes + $$ notes -getCaption :: PandocMonad m => [Inline] -> LW m (Doc, Doc, Doc) -getCaption txt = do - inMinipage <- gets stInMinipage - modify $ \st -> st{ stInMinipage = True, stNotes = [] } +getCaption :: PandocMonad m => Bool -> [Inline] -> LW m (Doc, Doc, Doc) +getCaption externalNotes txt = do + oldExternalNotes <- gets stExternalNotes + modify $ \st -> st{ stExternalNotes = externalNotes, stNotes = [] } capt <- inlineListToLaTeX txt - notes <- gets stNotes - modify $ \st -> st{ stInMinipage = inMinipage, stNotes = [] } + modify $ \st -> st{ stExternalNotes = oldExternalNotes, stNotes = [] } -- We can't have footnotes in the list of figures/tables, so remove them: - captForLof <- if null notes - then return empty - else brackets <$> inlineListToLaTeX (walk deNote txt) - let footnotes = notesToLaTeX notes + let getNote (Note _) = Any True + getNote _ = Any False + let hasNotes = getAny . query getNote + captForLof <- if hasNotes txt + then brackets <$> inlineListToLaTeX (walk deNote txt) + else return empty + footnotes <- if externalNotes + then notesToLaTeX <$> gets stNotes + else return empty return (capt, captForLof, footnotes) toColDescriptor :: Alignment -> String @@ -893,10 +909,13 @@ tableCellToLaTeX _ (0, _, blocks) = blockListToLaTeX $ walk fixLineBreaks $ walk displayMathToInline blocks tableCellToLaTeX header (width, align, blocks) = do - modify $ \st -> st{ stInMinipage = True, stNotes = [] } + beamer <- gets stBeamer + externalNotes <- gets stExternalNotes + -- See #5367 -- footnotehyper/footnote don't work in beamer, + -- so we need to produce the notes outside the table... + modify $ \st -> st{ stExternalNotes = beamer } cellContents <- blockListToLaTeX blocks - notes <- gets stNotes - modify $ \st -> st{ stInMinipage = False, stNotes = [] } + modify $ \st -> st{ stExternalNotes = externalNotes } let valign = text $ if header then "[b]" else "[t]" let halign = case align of AlignLeft -> "\\raggedright" @@ -906,8 +925,7 @@ return $ ("\\begin{minipage}" <> valign <> braces (text (printf "%.2f\\columnwidth" width)) <> (halign <> cr <> cellContents <> "\\strut" <> cr) <> - "\\end{minipage}") $$ - notesToLaTeX notes + "\\end{minipage}") notesToLaTeX :: [Doc] -> Doc notesToLaTeX [] = empty @@ -1219,12 +1237,12 @@ return $ text "\\protect\\hyperlink" <> braces (text lab) <> braces contents inlineToLaTeX (Link _ txt (src, _)) = case txt of - [Str x] | escapeURI x == src -> -- autolink + [Str x] | unEscapeString x == unEscapeString src -> -- autolink do modify $ \s -> s{ stUrl = True } src' <- stringToLaTeX URLString (escapeURI src) return $ text $ "\\url{" ++ src' ++ "}" [Str x] | Just rest <- stripPrefix "mailto:" src, - escapeURI x == rest -> -- email autolink + unEscapeString x == unEscapeString rest -> -- email autolink do modify $ \s -> s{ stUrl = True } src' <- stringToLaTeX URLString (escapeURI src) contents <- inlineListToLaTeX txt @@ -1274,10 +1292,10 @@ dims <> braces (text source'') inlineToLaTeX (Note contents) = do setEmptyLine False - inMinipage <- gets stInMinipage - modify (\s -> s{stInNote = True}) + externalNotes <- gets stExternalNotes + modify (\s -> s{stInNote = True, stExternalNotes = True}) contents' <- blockListToLaTeX contents - modify (\s -> s {stInNote = False}) + modify (\s -> s {stInNote = False, stExternalNotes = externalNotes}) let optnl = case reverse contents of (CodeBlock _ _ : _) -> cr _ -> empty @@ -1287,12 +1305,12 @@ let beamerMark = if beamer then text "<.->" else empty - modify $ \st -> st{ stNotes = noteContents : stNotes st } - return $ - if inMinipage - then "\\footnotemark{}" + if externalNotes + then do + modify $ \st -> st{ stNotes = noteContents : stNotes st } + return "\\footnotemark{}" -- note: a \n before } needed when note ends with a Verbatim environment - else "\\footnote" <> beamerMark <> braces noteContents + else return $ "\\footnote" <> beamerMark <> braces noteContents -- A comment at the end of math needs to be followed by a newline, -- or the closing delimiter gets swallowed. diff --git a/src/Text/Pandoc/Writers/Markdown.hs b/src/Text/Pandoc/Writers/Markdown.hs --- a/src/Text/Pandoc/Writers/Markdown.hs +++ b/src/Text/Pandoc/Writers/Markdown.hs @@ -29,6 +29,7 @@ import Data.Monoid (Any (..)) import Data.Ord (comparing) import qualified Data.Set as Set +import qualified Data.Scientific as Scientific import Data.Text (Text) import qualified Data.Text as T import qualified Data.Vector as V @@ -149,7 +150,9 @@ (k', Array vec, x) | V.null vec -> empty | otherwise -> (k' <> ":") $$ x - (k', Object _, x) -> (k' <> ":") $$ nest 2 x + (k', Object hm, x) + | H.null hm -> k' <> ": {}" + | otherwise -> (k' <> ":") $$ nest 2 x (_, String "", _) -> empty (k', _, x) -> k' <> ":" <> space <> hang 2 "" x) $ sortBy (comparing fst) $ H.toList hashmap @@ -162,7 +165,9 @@ | not (any isPunctuation x) -> text x | otherwise -> text $ "'" ++ substitute "'" "''" x ++ "'" jsonToYaml (Bool b) = text $ show b -jsonToYaml (Number n) = text $ show n +jsonToYaml (Number n) + | Scientific.isInteger n = text $ show (floor n :: Integer) + | otherwise = text $ show n jsonToYaml _ = empty -- | Return markdown representation of document. @@ -306,17 +311,22 @@ attrsToMarkdown attribs = braces $ hsep [attribId, attribClasses, attribKeys] where attribId = case attribs of ([],_,_) -> empty - (i,_,_) -> "#" <> text i + (i,_,_) -> "#" <> escAttr i attribClasses = case attribs of (_,[],_) -> empty (_,cs,_) -> hsep $ - map (text . ('.':)) + map (escAttr . ('.':)) cs attribKeys = case attribs of (_,_,[]) -> empty (_,_,ks) -> hsep $ - map (\(k,v) -> text k - <> "=\"" <> text v <> "\"") ks + map (\(k,v) -> escAttr k + <> "=\"" <> + escAttr v <> "\"") ks + escAttr = mconcat . map escAttrChar + escAttrChar '"' = text "\\\"" + escAttrChar '\\' = text "\\\\" + escAttrChar c = text [c] linkAttributes :: WriterOptions -> Attr -> Doc linkAttributes opts attr = diff --git a/src/Text/Pandoc/Writers/MediaWiki.hs b/src/Text/Pandoc/Writers/MediaWiki.hs --- a/src/Text/Pandoc/Writers/MediaWiki.hs +++ b/src/Text/Pandoc/Writers/MediaWiki.hs @@ -12,7 +12,7 @@ MediaWiki: -} -module Text.Pandoc.Writers.MediaWiki ( writeMediaWiki ) where +module Text.Pandoc.Writers.MediaWiki ( writeMediaWiki, highlightingLangs ) where import Prelude import Control.Monad.Reader import Control.Monad.State.Strict diff --git a/src/Text/Pandoc/Writers/Powerpoint/Output.hs b/src/Text/Pandoc/Writers/Powerpoint/Output.hs --- a/src/Text/Pandoc/Writers/Powerpoint/Output.hs +++ b/src/Text/Pandoc/Writers/Powerpoint/Output.hs @@ -166,7 +166,6 @@ , "ppt/theme/theme1.xml" , "ppt/theme/_rels/theme1.xml.rels" , "ppt/presProps.xml" - , "ppt/viewProps.xml" , "ppt/tableStyles.xml" , "ppt/media/image*" ] @@ -213,7 +212,6 @@ , "ppt/slideMasters/slideMaster1.xml" , "ppt/slideMasters/_rels/slideMaster1.xml.rels" , "ppt/theme/theme1.xml" - , "ppt/viewProps.xml" , "ppt/tableStyles.xml" ] @@ -231,6 +229,8 @@ ) newArch' <- foldM copyFileToArchive emptyArchive filePaths + -- we make a modified ppt/viewProps.xml out of the presentation viewProps + viewPropsEntry <- makeViewPropsEntry -- we make a docProps/core.xml entry out of the presentation docprops docPropsEntry <- docPropsToEntry docProps -- we make a docProps/custom.xml entry out of the custom properties @@ -258,7 +258,7 @@ spkNotesRelEntries ++ mediaEntries ++ [contentTypesEntry, docPropsEntry, docCustomPropsEntry, relsEntry, - presEntry, presRelsEntry] + presEntry, presRelsEntry, viewPropsEntry] makeSlideIdMap :: Presentation -> M.Map SlideId Int makeSlideIdMap (Presentation _ slides) = @@ -336,22 +336,18 @@ nm == ident | otherwise = False --- The content shape in slideLayout2 (Title/Content) has id=3 In --- slideLayout4 (two column) the left column is id=3, and the right --- column is id=4. getContentShape :: PandocMonad m => NameSpaces -> Element -> P m Element getContentShape ns spTreeElem | isElem ns "p" "spTree" spTreeElem = do contentType <- asks envContentType - let idx = case contentType of - NormalContent -> "1" - TwoColumnLeftContent -> "1" - TwoColumnRightContent -> "2" - case getShapeByPlaceHolderIndex ns spTreeElem idx of - Just e -> return e - Nothing -> throwError $ - PandocSomeError $ - "Could not find shape for Powerpoint content" + let contentShapes = getShapesByPlaceHolderType ns spTreeElem ObjType + case contentType of + NormalContent | (sp : _) <- contentShapes -> return sp + TwoColumnLeftContent | (sp : _) <- contentShapes -> return sp + TwoColumnRightContent | (_ : sp : _) <- contentShapes -> return sp + _ -> throwError $ + PandocSomeError $ + "Could not find shape for Powerpoint content" getContentShape _ _ = throwError $ PandocSomeError $ "Attempted to find content on non shapeTree" @@ -413,12 +409,22 @@ PandocSomeError $ "Attempted to find content shape size in non-layout" +buildSpTree :: NameSpaces -> Element -> [Element] -> Element +buildSpTree ns spTreeElem newShapes = + emptySpTreeElem { elContent = newContent } + where newContent = elContent emptySpTreeElem ++ map Elem newShapes + emptySpTreeElem = spTreeElem { elContent = filter fn (elContent spTreeElem) } + fn :: Content -> Bool + fn (Elem e) = isElem ns "p" "nvGrpSpPr" e || + isElem ns "p" "grpSpPr" e + fn _ = True + replaceNamedChildren :: NameSpaces - -> String - -> String - -> [Element] - -> Element - -> Element + -> String + -> String + -> [Element] + -> Element + -> Element replaceNamedChildren ns prefix name newKids element = element { elContent = concat $ fun True $ elContent element } where @@ -975,42 +981,56 @@ ] ] -getShapeByPlaceHolderType :: NameSpaces -> Element -> String -> Maybe Element -getShapeByPlaceHolderType ns spTreeElem phType - | isElem ns "p" "spTree" spTreeElem = - let findPhType element = isElem ns "p" "sp" element && - Just phType == (Just element >>= - findChild (elemName ns "p" "nvSpPr") >>= - findChild (elemName ns "p" "nvPr") >>= - findChild (elemName ns "p" "ph") >>= - findAttr (QName "type" Nothing Nothing)) + +-- We get the shape by placeholder type. If there is NO type, it +-- defaults to a content placeholder. + +data PHType = PHType String | ObjType + deriving (Show, Eq) + +findPHType :: NameSpaces -> Element -> PHType -> Bool +findPHType ns spElem phType + | isElem ns "p" "sp" spElem = + let mbPHElem = (Just spElem >>= + findChild (elemName ns "p" "nvSpPr") >>= + findChild (elemName ns "p" "nvPr") >>= + findChild (elemName ns "p" "ph")) in - filterChild findPhType spTreeElem - | otherwise = Nothing + case mbPHElem of + -- if it's a named PHType, we want to check that the attribute + -- value matches. + Just phElem | (PHType tp) <- phType -> + case findAttr (QName "type" Nothing Nothing) phElem of + Just tp' -> tp == tp' + Nothing -> False + -- if it's an ObjType, we want to check that there is NO + -- "type" attribute. In other words, a lookup should return nothing. + Just phElem | ObjType <- phType -> + case findAttr (QName "type" Nothing Nothing) phElem of + Just _ -> False + Nothing -> True + Nothing -> False +findPHType _ _ _ = False +getShapesByPlaceHolderType :: NameSpaces -> Element -> PHType -> [Element] +getShapesByPlaceHolderType ns spTreeElem phType + | isElem ns "p" "spTree" spTreeElem = + filterChildren (\e -> findPHType ns e phType) spTreeElem + | otherwise = [] + +getShapeByPlaceHolderType :: NameSpaces -> Element -> PHType -> Maybe Element +getShapeByPlaceHolderType ns spTreeElem phType = + listToMaybe $ getShapesByPlaceHolderType ns spTreeElem phType + -- Like the above, but it tries a number of different placeholder types -getShapeByPlaceHolderTypes :: NameSpaces -> Element -> [String] -> Maybe Element +getShapeByPlaceHolderTypes :: NameSpaces -> Element -> [PHType] -> Maybe Element getShapeByPlaceHolderTypes _ _ [] = Nothing getShapeByPlaceHolderTypes ns spTreeElem (s:ss) = case getShapeByPlaceHolderType ns spTreeElem s of Just element -> Just element Nothing -> getShapeByPlaceHolderTypes ns spTreeElem ss -getShapeByPlaceHolderIndex :: NameSpaces -> Element -> String -> Maybe Element -getShapeByPlaceHolderIndex ns spTreeElem phIdx - | isElem ns "p" "spTree" spTreeElem = - let findPhType element = isElem ns "p" "sp" element && - Just phIdx == (Just element >>= - findChild (elemName ns "p" "nvSpPr") >>= - findChild (elemName ns "p" "nvPr") >>= - findChild (elemName ns "p" "ph") >>= - findAttr (QName "idx" Nothing Nothing)) - in - filterChild findPhType spTreeElem - | otherwise = Nothing - - -nonBodyTextToElement :: PandocMonad m => Element -> [String] -> [ParaElem] -> P m Element +nonBodyTextToElement :: PandocMonad m => Element -> [PHType] -> [ParaElem] -> P m Element nonBodyTextToElement layout phTypes paraElements | ns <- elemToNameSpaces layout , Just cSld <- findChild (elemName ns "p" "cSld") layout @@ -1030,17 +1050,14 @@ | ns <- elemToNameSpaces layout , Just cSld <- findChild (elemName ns "p" "cSld") layout , Just spTree <- findChild (elemName ns "p" "spTree") cSld = do - element <- nonBodyTextToElement layout ["title"] hdrShape + element <- nonBodyTextToElement layout [PHType "title"] hdrShape let hdrShapeElements = if null hdrShape then [] else [element] contentElements <- local (\env -> env {envContentType = NormalContent}) (shapesToElements layout shapes) - return $ - replaceNamedChildren ns "p" "sp" - (hdrShapeElements ++ contentElements) - spTree + return $ buildSpTree ns spTree (hdrShapeElements ++ contentElements) contentToElement _ _ _ = return $ mknode "p:sp" [] () twoColumnToElement :: PandocMonad m => Element -> [ParaElem] -> [Shape] -> [Shape] -> P m Element @@ -1048,7 +1065,7 @@ | ns <- elemToNameSpaces layout , Just cSld <- findChild (elemName ns "p" "cSld") layout , Just spTree <- findChild (elemName ns "p" "spTree") cSld = do - element <- nonBodyTextToElement layout ["title"] hdrShape + element <- nonBodyTextToElement layout [PHType "title"] hdrShape let hdrShapeElements = if null hdrShape then [] else [element] @@ -1060,10 +1077,7 @@ (shapesToElements layout shapesR) -- let contentElementsL' = map (setIdx ns "1") contentElementsL -- contentElementsR' = map (setIdx ns "2") contentElementsR - return $ - replaceNamedChildren ns "p" "sp" - (hdrShapeElements ++ contentElementsL ++ contentElementsR) - spTree + return $ buildSpTree ns spTree (hdrShapeElements ++ contentElementsL ++ contentElementsR) twoColumnToElement _ _ _ _= return $ mknode "p:sp" [] () @@ -1072,11 +1086,11 @@ | ns <- elemToNameSpaces layout , Just cSld <- findChild (elemName ns "p" "cSld") layout , Just spTree <- findChild (elemName ns "p" "spTree") cSld = do - element <- nonBodyTextToElement layout ["title", "ctrTitle"] titleElems + element <- nonBodyTextToElement layout [PHType "title", PHType "ctrTitle"] titleElems let titleShapeElements = if null titleElems then [] else [element] - return $ replaceNamedChildren ns "p" "sp" titleShapeElements spTree + return $ buildSpTree ns spTree titleShapeElements titleToElement _ _ = return $ mknode "p:sp" [] () metadataToElement :: PandocMonad m => Element -> [ParaElem] -> [ParaElem] -> [[ParaElem]] -> [ParaElem] -> P m Element @@ -1086,18 +1100,16 @@ , Just spTree <- findChild (elemName ns "p" "spTree") cSld = do titleShapeElements <- if null titleElems then return [] - else sequence [nonBodyTextToElement layout ["ctrTitle"] titleElems] + else sequence [nonBodyTextToElement layout [PHType "ctrTitle"] titleElems] let combinedAuthorElems = intercalate [Break] authorsElems subtitleAndAuthorElems = intercalate [Break, Break] [subtitleElems, combinedAuthorElems] subtitleShapeElements <- if null subtitleAndAuthorElems then return [] - else sequence [nonBodyTextToElement layout ["subTitle"] subtitleAndAuthorElems] + else sequence [nonBodyTextToElement layout [PHType "subTitle"] subtitleAndAuthorElems] dateShapeElements <- if null dateElems then return [] - else sequence [nonBodyTextToElement layout ["dt"] dateElems] - return $ replaceNamedChildren ns "p" "sp" - (titleShapeElements ++ subtitleShapeElements ++ dateShapeElements) - spTree + else sequence [nonBodyTextToElement layout [PHType "dt"] dateElems] + return $ buildSpTree ns spTree (titleShapeElements ++ subtitleShapeElements ++ dateShapeElements) metadataToElement _ _ _ _ _ = return $ mknode "p:sp" [] () slideToElement :: PandocMonad m => Slide -> P m Element @@ -1155,7 +1167,7 @@ | ns <- elemToNameSpaces notesMaster , Just cSld <- findChild (elemName ns "p" "cSld") notesMaster , Just spTree <- findChild (elemName ns "p" "spTree") cSld - , Just sp <- getShapeByPlaceHolderType ns spTree "sldNum" + , Just sp <- getShapeByPlaceHolderType ns spTree (PHType "sldNum") , Just txBody <- findChild (elemName ns "p" "txBody") sp , Just p <- findChild (elemName ns "a" "p") txBody , Just fld <- findChild (elemName ns "a" "fld") p @@ -1607,16 +1619,18 @@ -- if there's a notesMasterIdLst in the presentation.xml file, -- we want to remove it. We then want to put our own, if - -- necessary, after the slideMasterIdLst element. + -- necessary, after the slideMasterIdLst element. We also remove + -- handouts master, since we don't want it. - removeNotesMaster' :: Content -> [Content] - removeNotesMaster' (Elem e) = case elName e of + removeUnwantedMaster' :: Content -> [Content] + removeUnwantedMaster' (Elem e) = case elName e of (QName "notesMasterIdLst" _ _) -> [] + (QName "handoutMasterIdLst" _ _) -> [] _ -> [Elem e] - removeNotesMaster' ct = [ct] + removeUnwantedMaster' ct = [ct] - removeNotesMaster :: [Content] -> [Content] - removeNotesMaster = concatMap removeNotesMaster' + removeUnwantedMaster :: [Content] -> [Content] + removeUnwantedMaster = concatMap removeUnwantedMaster' insertNotesMaster' :: Content -> [Content] insertNotesMaster' (Elem e) = case elName e of @@ -1630,7 +1644,7 @@ else id newContent = insertNotesMaster $ - removeNotesMaster $ + removeUnwantedMaster $ map modifySldIdLst $ elContent element @@ -1687,6 +1701,23 @@ docCustomPropsToEntry docProps = docCustomPropsElement docProps >>= elemToEntry "docProps/custom.xml" +-- We read from the template, but we remove the lastView, so it always +-- opens on slide view. Templates will sometimes be open in master +-- view for editing. +viewPropsElement :: PandocMonad m => P m Element +viewPropsElement = do + refArchive <- asks envRefArchive + distArchive <- asks envDistArchive + viewPrElement <- parseXml refArchive distArchive "ppt/viewProps.xml" + -- remove "lastView" if it exists: + let notLastView :: Text.XML.Light.Attr -> Bool + notLastView attr = (qName $ attrKey attr) /= "lastView" + return $ + viewPrElement {elAttribs = filter notLastView (elAttribs viewPrElement)} + +makeViewPropsEntry :: PandocMonad m => P m Entry +makeViewPropsEntry = viewPropsElement >>= elemToEntry "ppt/viewProps.xml" + defaultContentTypeToElem :: DefaultContentType -> Element defaultContentTypeToElem dct = mknode "Default" @@ -1773,9 +1804,11 @@ (mapMaybe mediaFileContentType $ mediaFps) inheritedOverrides = mapMaybe pathToOverride filePaths - docPropsOverride = mapMaybe pathToOverride ["docProps/core.xml"] - docCustomPropsOverride = mapMaybe pathToOverride ["docProps/custom.xml"] - presOverride = mapMaybe pathToOverride ["ppt/presentation.xml"] + createdOverrides = mapMaybe pathToOverride [ "docProps/core.xml" + , "docProps/custom.xml" + , "ppt/presentation.xml" + , "ppt/viewProps.xml" + ] relativePaths <- mapM slideToFilePath slides let slideOverrides = mapMaybe (\fp -> pathToOverride $ "ppt/slides/" ++ fp) @@ -1783,8 +1816,7 @@ speakerNotesOverrides <- (mapMaybe pathToOverride) <$> getSpeakerNotesFilePaths return $ ContentTypes (defaults ++ mediaDefaults) - (inheritedOverrides ++ docPropsOverride ++ docCustomPropsOverride ++ - presOverride ++ slideOverrides ++ speakerNotesOverrides) + (inheritedOverrides ++ createdOverrides ++ slideOverrides ++ speakerNotesOverrides) presML :: String presML = "application/vnd.openxmlformats-officedocument.presentationml" diff --git a/src/Text/Pandoc/Writers/Powerpoint/Presentation.hs b/src/Text/Pandoc/Writers/Powerpoint/Presentation.hs --- a/src/Text/Pandoc/Writers/Powerpoint/Presentation.hs +++ b/src/Text/Pandoc/Writers/Powerpoint/Presentation.hs @@ -183,20 +183,15 @@ newtype SpeakerNotes = SpeakerNotes {fromSpeakerNotes :: [Paragraph]} deriving (Show, Eq, Monoid, Semigroup) -data Layout = MetadataSlide { metadataSlideTitle :: [ParaElem] - , metadataSlideSubtitle :: [ParaElem] - , metadataSlideAuthors :: [[ParaElem]] - , metadataSlideDate :: [ParaElem] - } - | TitleSlide { titleSlideHeader :: [ParaElem]} - | ContentSlide { contentSlideHeader :: [ParaElem] - , contentSlideContent :: [Shape] - } - | TwoColumnSlide { twoColumnSlideHeader :: [ParaElem] - , twoColumnSlideLeft :: [Shape] - , twoColumnSlideRight :: [Shape] - } - deriving (Show, Eq) +data Layout = MetadataSlide [ParaElem] [ParaElem] [[ParaElem]] [ParaElem] + -- title subtitle authors date + | TitleSlide [ParaElem] + -- heading + | ContentSlide [ParaElem] [Shape] + -- heading content + | TwoColumnSlide [ParaElem] [Shape] [Shape] + -- heading left right + deriving (Show, Eq) data Shape = Pic PicProps FilePath [ParaElem] | GraphicFrame [Graphic] [ParaElem] @@ -575,10 +570,11 @@ splitBlocks' [] (acc ++ (if null cur then [] else [cur])) blks splitBlocks' cur acc (h@(Header n _ _) : blks) = do slideLevel <- asks envSlideLevel + let (nts, blks') = span isNotesDiv blks case compare n slideLevel of - LT -> splitBlocks' [] (acc ++ (if null cur then [] else [cur]) ++ [[h]]) blks - EQ -> splitBlocks' [h] (acc ++ (if null cur then [] else [cur])) blks - GT -> splitBlocks' (cur ++ [h]) acc blks + LT -> splitBlocks' [] (acc ++ (if null cur then [] else [cur]) ++ [h : nts]) blks' + EQ -> splitBlocks' (h:nts) (acc ++ (if null cur then [] else [cur])) blks' + GT -> splitBlocks' (cur ++ (h:nts)) acc blks' -- `blockToParagraphs` treats Plain and Para the same, so we can save -- some code duplication by treating them the same here. splitBlocks' cur acc (Plain ils : blks) = splitBlocks' cur acc (Para ils : blks) @@ -620,7 +616,7 @@ registerAnchorId ident sldId <- asks envCurSlideId hdr <- inlinesToParElems ils - return $ Slide sldId TitleSlide {titleSlideHeader = hdr} spkNotes + return $ Slide sldId (TitleSlide hdr) spkNotes | n == lvl = do registerAnchorId ident hdr <- inlinesToParElems ils @@ -651,10 +647,7 @@ sldId <- asks envCurSlideId return $ Slide sldId - TwoColumnSlide { twoColumnSlideHeader = [] - , twoColumnSlideLeft = shapesL - , twoColumnSlideRight = shapesR - } + (TwoColumnSlide [] shapesL shapesR) spkNotes blocksToSlide' _ (blk : blks) spkNotes = do inNoteSlide <- asks envInNoteSlide @@ -665,42 +658,42 @@ return $ Slide sldId - ContentSlide { contentSlideHeader = [] - , contentSlideContent = shapes - } + (ContentSlide [] shapes) spkNotes blocksToSlide' _ [] spkNotes = do sldId <- asks envCurSlideId return $ Slide sldId - ContentSlide { contentSlideHeader = [] - , contentSlideContent = [] - } + (ContentSlide [] []) spkNotes -handleNotes :: Block -> Pres () -handleNotes (Div (_, ["notes"], _) blks) = - local (\env -> env{envInSpeakerNotes=True}) $ do - spNotes <- SpeakerNotes <$> concatMapM blockToParagraphs blks +blockToSpeakerNotes :: Block -> Pres SpeakerNotes +blockToSpeakerNotes (Div (_, ["notes"], _) blks) = + local (\env -> env{envInSpeakerNotes=True}) $ + SpeakerNotes <$> concatMapM blockToParagraphs blks +blockToSpeakerNotes _ = return mempty + +handleSpeakerNotes :: Block -> Pres () +handleSpeakerNotes blk = do + spNotes <- blockToSpeakerNotes blk modify $ \st -> st{stSpeakerNotes = (stSpeakerNotes st) <> spNotes} -handleNotes _ = return () -handleAndFilterNotes' :: [Block] -> Pres [Block] -handleAndFilterNotes' blks = do - mapM_ handleNotes blks +handleAndFilterSpeakerNotes' :: [Block] -> Pres [Block] +handleAndFilterSpeakerNotes' blks = do + mapM_ handleSpeakerNotes blks return $ filter (not . isNotesDiv) blks -handleAndFilterNotes :: [Block] -> Pres ([Block], SpeakerNotes) -handleAndFilterNotes blks = do +handleAndFilterSpeakerNotes :: [Block] -> Pres ([Block], SpeakerNotes) +handleAndFilterSpeakerNotes blks = do modify $ \st -> st{stSpeakerNotes = mempty} - blks' <- walkM handleAndFilterNotes' blks + blks' <- walkM handleAndFilterSpeakerNotes' blks spkNotes <- gets stSpeakerNotes return (blks', spkNotes) blocksToSlide :: [Block] -> Pres Slide blocksToSlide blks = do - (blks', spkNotes) <- handleAndFilterNotes blks + (blks', spkNotes) <- handleAndFilterSpeakerNotes blks slideLevel <- asks envSlideLevel blocksToSlide' slideLevel blks' spkNotes @@ -751,13 +744,16 @@ Just $ Slide metadataSlideId - MetadataSlide { metadataSlideTitle = title - , metadataSlideSubtitle = subtitle - , metadataSlideAuthors = authors - , metadataSlideDate = date - } + (MetadataSlide title subtitle authors date) mempty +addSpeakerNotesToMetaSlide :: Slide -> [Block] -> Pres (Slide, [Block]) +addSpeakerNotesToMetaSlide (Slide sldId layout@(MetadataSlide _ _ _ _) spkNotes) blks = + do let (ntsBlks, blks') = span isNotesDiv blks + spkNotes' <- mconcat <$> mapM blockToSpeakerNotes ntsBlks + return (Slide sldId layout (spkNotes <> spkNotes'), blks') +addSpeakerNotesToMetaSlide sld blks = return (sld, blks) + makeTOCSlide :: [Block] -> Pres Slide makeTOCSlide blks = local (\env -> env{envCurSlideId = tocSlideId}) $ do opts <- asks envOpts @@ -870,7 +866,16 @@ blocksToPresentationSlides :: [Block] -> Pres [Slide] blocksToPresentationSlides blks = do opts <- asks envOpts - metadataslides <- maybeToList <$> getMetaSlide + mbMetadataSlide <- getMetaSlide + -- if the metadata slide exists, we try to add any speakerNotes + -- which immediately follow it. We also convert from maybe to a + -- list, so that it will be able to add together more easily with + -- the other lists of slides. + (metadataslides, blks') <- case mbMetadataSlide of + Just sld -> + do (s, bs) <- addSpeakerNotesToMetaSlide sld blks + return ([s], bs) + Nothing -> return ([], blks) -- As far as I can tell, if we want to have a variable-length toc in -- the future, we'll have to make it twice. Once to get the length, -- and a second time to include the notes slide. We can't make the @@ -881,7 +886,7 @@ -- For now, though, since the TOC slide is only length 1, if it -- exists, we'll just get the length, and then come back to make the -- slide later - blksLst <- splitBlocks blks + blksLst <- splitBlocks blks' bodySlideIds <- mapM (\n -> runUniqueSlideId $ "BodySlide" ++ show n) (take (length blksLst) [1..] :: [Integer]) @@ -892,7 +897,7 @@ endNotesSlideBlocks <- makeEndNotesSlideBlocks -- now we come back and make the real toc... tocSlides <- if writerTableOfContents opts - then do toc <- makeTOCSlide $ blks ++ endNotesSlideBlocks + then do toc <- makeTOCSlide $ blks' ++ endNotesSlideBlocks return [toc] else return [] -- ... and the notes slide. We test to see if the blocks are empty, diff --git a/src/Text/Pandoc/Writers/Shared.hs b/src/Text/Pandoc/Writers/Shared.hs --- a/src/Text/Pandoc/Writers/Shared.hs +++ b/src/Text/Pandoc/Writers/Shared.hs @@ -1,4 +1,5 @@ {-# LANGUAGE NoImplicitPrelude #-} +{-# LANGUAGE ScopedTypeVariables #-} {-# LANGUAGE OverloadedStrings #-} {- | Module : Text.Pandoc.Writers.Shared @@ -36,11 +37,13 @@ where import Prelude import Control.Monad (zipWithM) +import qualified Data.Aeson as Aeson import Data.Aeson (FromJSON (..), Result (..), ToJSON (..), Value (Object), encode, fromJSON) import Data.Char (chr, ord, isSpace) import qualified Data.HashMap.Strict as H -import Data.List (groupBy, intersperse, transpose) +import Data.List (groupBy, intersperse, transpose, foldl') +import Data.Scientific (Scientific) import qualified Data.Map as M import Data.Maybe (isJust) import qualified Data.Text as T @@ -49,7 +52,8 @@ import Text.Pandoc.Definition import Text.Pandoc.Options import Text.Pandoc.Pretty -import Text.Pandoc.Shared (stringify, hierarchicalize, Element(..), deNote) +import Text.Pandoc.Shared (stringify, hierarchicalize, Element(..), deNote, + safeRead) import Text.Pandoc.Walk (walk) import Text.Pandoc.UTF8 (toStringLazy) import Text.Pandoc.XML (escapeStringForXML) @@ -105,9 +109,13 @@ metaValueToJSON blockWriter inlineWriter (MetaList xs) = toJSON <$> Traversable.mapM (metaValueToJSON blockWriter inlineWriter) xs metaValueToJSON _ _ (MetaBool b) = return $ toJSON b -metaValueToJSON _ inlineWriter (MetaString s) = toJSON <$> - inlineWriter (Builder.toList (Builder.text s)) +metaValueToJSON _ inlineWriter (MetaString s) = + case safeRead s of + Just (n :: Scientific) -> return $ Aeson.Number n + Nothing -> toJSON <$> inlineWriter (Builder.toList (Builder.text s)) metaValueToJSON blockWriter _ (MetaBlocks bs) = toJSON <$> blockWriter bs +metaValueToJSON blockWriter inlineWriter (MetaInlines [Str s]) = + metaValueToJSON blockWriter inlineWriter (MetaString s) metaValueToJSON _ inlineWriter (MetaInlines is) = toJSON <$> inlineWriter is -- | Retrieve a field value from a JSON object. @@ -274,7 +282,7 @@ -- handleGivenWidths let handleZeroWidths = do (widthsInChars', rawHeaders', rawRows') <- handleFullWidths - if sum widthsInChars' > writerColumns opts + if foldl' (+) 0 widthsInChars' > writerColumns opts then -- use even widths handleGivenWidths (replicate numcols (1.0 / fromIntegral numcols) :: [Double]) diff --git a/src/Text/Pandoc/Writers/XWiki.hs b/src/Text/Pandoc/Writers/XWiki.hs new file mode 100644 --- /dev/null +++ b/src/Text/Pandoc/Writers/XWiki.hs @@ -0,0 +1,266 @@ +{-# LANGUAGE NoImplicitPrelude #-} +{-# LANGUAGE OverloadedStrings #-} +{- +Copyright (C) 2008-2017 John MacFarlane + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.Writers.XWiki + Copyright : Copyright (C) 2008-2017 John MacFarlane + License : GNU GPL, version 2 or above + + Maintainer : Derek Chen-Becker + Stability : alpha + Portability : portable + +Conversion of 'Pandoc' documents to XWiki markup. + +XWiki: +XWiki Syntax: +-} + +module Text.Pandoc.Writers.XWiki ( writeXWiki ) where +import Prelude +import Control.Monad.Reader (ReaderT, asks, local, runReaderT) +import qualified Data.Set as Set +import qualified Data.Text as Text +import Data.Text (Text, intercalate, pack, replace, split) +import Text.Pandoc.Class (PandocMonad, report) +import Text.Pandoc.Definition +import Text.Pandoc.Logging +import Text.Pandoc.Options +import Text.Pandoc.Shared (escapeURI, isURI, linesToPara) +import Text.Pandoc.Writers.MediaWiki (highlightingLangs) + +data WriterState = WriterState { + listLevel :: Text -- String at the beginning of items +} + +type XWikiReader m = ReaderT WriterState m + +-- | Convert Pandoc to XWiki. +writeXWiki :: PandocMonad m => WriterOptions -> Pandoc -> m Text +writeXWiki _ (Pandoc _ blocks) = do + let env = WriterState { listLevel = "" } + body <- runReaderT (blockListToXWiki blocks) env + return $ body + +-- | Concatenates strings with line breaks between them. +vcat :: [Text] -> Text +vcat = intercalate "\n" + +-- If an id is provided, we can generate an anchor using the id macro +-- https://extensions.xwiki.org/xwiki/bin/view/Extension/Id%20Macro +genAnchor :: String -> Text +genAnchor id' = if null id' + then "" + else pack $ "{{id name=\"" ++ id' ++ "\" /}}" + +blockListToXWiki :: PandocMonad m => [Block] -> XWikiReader m Text +blockListToXWiki blocks = + fmap vcat $ mapM blockToXWiki blocks + +blockToXWiki :: PandocMonad m => Block -> XWikiReader m Text + +blockToXWiki Null = return "" + +blockToXWiki (Div (id', _, _) blocks) = do + content <- blockListToXWiki blocks + return $ (genAnchor id') <> content + +blockToXWiki (Plain inlines) = + inlineListToXWiki inlines + +blockToXWiki (Para inlines) = do + contents <- inlineListToXWiki inlines + return $ contents <> "\n" + +blockToXWiki (LineBlock lns) = + blockToXWiki $ linesToPara lns + +blockToXWiki b@(RawBlock f str) + | f == Format "xwiki" = return $ pack str + | otherwise = "" <$ report (BlockNotRendered b) + +blockToXWiki HorizontalRule = return "\n----\n" + +blockToXWiki (Header level (id', _, _) inlines) = do + contents <- inlineListToXWiki inlines + let eqs = Text.replicate level "=" + return $ eqs <> " " <> contents <> " " <> (genAnchor id') <> eqs <> "\n" + +-- XWiki doesn't appear to differentiate between inline and block-form code, so we delegate +-- We do amend the text to ensure that the code markers are on their own lines, since this is a block +blockToXWiki (CodeBlock attrs str) = do + contents <- inlineToXWiki (Code attrs ("\n" <> str <> "\n")) + return $ "\n" <> contents <> "\n" + +blockToXWiki (BlockQuote blocks) = do + blockText <- blockListToXWiki blocks + let quoteLines = split (== '\n') blockText + let prefixed = map (">" <>) quoteLines + return $ vcat prefixed + +blockToXWiki (BulletList contents) = blockToXWikiList "*" $ contents + +blockToXWiki (OrderedList _ contents) = blockToXWikiList "1" $ contents + +blockToXWiki (DefinitionList items) = do + lev <- asks listLevel + contents <- local (\s -> s { listLevel = listLevel s <> ";" }) $ mapM definitionListItemToMediaWiki items + return $ vcat contents <> if Text.null lev then "\n" else "" + +-- TODO: support more features +blockToXWiki (Table _ _ _ headers rows') = do + headers' <- mapM (tableCellXWiki True) headers + otherRows <- mapM formRow rows' + return $ Text.unlines (Text.unwords headers':otherRows) + +formRow :: PandocMonad m => [[Block]] -> XWikiReader m Text +formRow row = do + cellStrings <- mapM (tableCellXWiki False) row + return $ Text.unwords cellStrings + + +tableCellXWiki :: PandocMonad m => Bool -> [Block] -> XWikiReader m Text +tableCellXWiki isHeader cell = do + contents <- blockListToXWiki cell + let cellBorder = if isHeader then "|=" else "|" + return $ cellBorder <> contents + + +inlineListToXWiki :: PandocMonad m => [Inline] -> XWikiReader m Text +inlineListToXWiki lst = + mconcat <$> mapM inlineToXWiki lst + +inlineToXWiki :: PandocMonad m => Inline -> XWikiReader m Text + +inlineToXWiki (Str str) = return $ escapeXWikiString $ pack str + +inlineToXWiki Space = return " " + +-- Special syntax for XWiki 2.0. This won't break table cells +inlineToXWiki LineBreak = return "\\\\" + +inlineToXWiki SoftBreak = return " " + +inlineToXWiki (Emph lst) = do + contents <- inlineListToXWiki lst + return $ "//" <> contents <> "//" + +inlineToXWiki (Strong lst) = do + contents <- inlineListToXWiki lst + return $ "**" <> contents <> "**" + +inlineToXWiki (Strikeout lst) = do + contents <- inlineListToXWiki lst + return $ "--" <> contents <> "--" + +inlineToXWiki (Superscript lst) = do + contents <- inlineListToXWiki lst + return $ "^^" <> contents <> "^^" + +inlineToXWiki (Subscript lst) = do + contents <- inlineListToXWiki lst + return $ ",," <> contents <> ",," + +-- TODO: Not supported. Maybe escape to HTML? +inlineToXWiki (SmallCaps lst) = do + contents <- inlineListToXWiki lst + return contents + +inlineToXWiki (Quoted SingleQuote lst) = do + contents <- inlineListToXWiki lst + return $ "‘" <> contents <> "’" + +inlineToXWiki (Quoted DoubleQuote lst) = do + contents <- inlineListToXWiki lst + return $ "“" <> contents <> "”" + +inlineToXWiki (Code (_,classes,_) contents') = do + let at = Set.fromList classes `Set.intersection` highlightingLangs + let contents = pack contents' + return $ + case Set.toList at of + [] -> "{{code}}" <> contents <> "{{/code}}" + (l:_) -> "{{code language=\"" <> (pack l) <> "\"}}" <> contents <> "{{/code}}" + +inlineToXWiki (Cite _ lst) = inlineListToXWiki lst + +-- FIXME: optionally support this (plugin?) +inlineToXWiki (Math _ str) = return $ "{{formula}}" <> (pack str) <> "{{/formula}}" + +inlineToXWiki il@(RawInline frmt str) + | frmt == Format "xwiki" = return $ pack str + | otherwise = "" <$ report (InlineNotRendered il) + +-- TODO: Handle anchors +inlineToXWiki (Link (id', _, _) txt (src, _)) = do + label <- inlineListToXWiki txt + case txt of + [Str s] | isURI src && escapeURI s == src -> return $ (pack src) <> (genAnchor id') + _ -> return $ "[[" <> label <> ">>" <> (pack src) <> "]]" <> (genAnchor id') + +inlineToXWiki (Image _ alt (source, tit)) = do + alt' <- inlineListToXWiki alt + let + titText = pack tit + params = intercalate " " $ filter (not . Text.null) [ + if Text.null alt' then "" else "alt=\"" <> alt' <> "\"", + if Text.null titText then "" else "title=\"" <> titText <> "\"" + ] + return $ "[[image:" <> (pack source) <> (if Text.null params then "" else "||" <> params) <> "]]" + +inlineToXWiki (Note contents) = do + contents' <- blockListToXWiki contents + return $ "{{footnote}}" <> (Text.strip contents') <> "{{/footnote}}" + +-- TODO: support attrs other than id (anchor) +inlineToXWiki (Span (id', _, _) contents) = do + contents' <- inlineListToXWiki contents + return $ (genAnchor id') <> contents' + +-- Utility method since (for now) all lists are handled the same way +blockToXWikiList :: PandocMonad m => Text -> [[Block]] -> XWikiReader m Text +blockToXWikiList marker contents = do + lev <- asks listLevel + contents' <- local (\s -> s { listLevel = listLevel s <> marker } ) $ mapM listItemToXWiki contents + return $ vcat contents' <> if Text.null lev then "\n" else "" + + +listItemToXWiki :: PandocMonad m => [Block] -> XWikiReader m Text +listItemToXWiki contents = do + marker <- asks listLevel + contents' <- blockListToXWiki contents + return $ marker <> ". " <> (Text.strip contents') + + +-- | Convert definition list item (label, list of blocks) to MediaWiki. +definitionListItemToMediaWiki :: PandocMonad m + => ([Inline],[[Block]]) + -> XWikiReader m Text +definitionListItemToMediaWiki (label, items) = do + labelText <- inlineListToXWiki label + contents <- mapM blockListToXWiki items + marker <- asks listLevel + return $ marker <> " " <> labelText <> "\n" <> + intercalate "\n" (map (\d -> (Text.init marker) <> ": " <> d) contents) + +-- Escape the escape character, as well as formatting pairs +escapeXWikiString :: Text -> Text +escapeXWikiString s = foldr (uncurry replace) s $ zip ["--", "**", "//", "^^", ",,", "~"] ["~-~-", "~*~*", "~/~/", "~^~^", "~,~,", "~~"] + diff --git a/stack.yaml b/stack.yaml --- a/stack.yaml +++ b/stack.yaml @@ -18,5 +18,5 @@ - texmath-0.11.2.2 - cmark-gfm-0.1.8 ghc-options: - "$locals": -fhide-source-paths -XNoImplicitPrelude + "$locals": -Wall -fno-warn-unused-do-bind -Wincomplete-record-updates -Wnoncanonical-monad-instances -Wnoncanonical-monadfail-instances -Wincomplete-uni-patterns -Widentities -Wcpp-undef -fhide-source-paths resolver: lts-13.9 diff --git a/test/Tests/Old.hs b/test/Tests/Old.hs --- a/test/Tests/Old.hs +++ b/test/Tests/Old.hs @@ -159,7 +159,8 @@ "tikiwiki-reader.tikiwiki" "tikiwiki-reader.native" ] , testGroup "other writers" $ map (\f -> testGroup f $ writerTests' f) [ "opendocument" , "context" , "texinfo", "icml", "tei" - , "man" , "plain" , "rtf", "org", "asciidoc", "asciidoctor", "zimwiki" + , "man" , "plain" , "rtf", "org", "asciidoc", "asciidoctor" + , "xwiki", "zimwiki" ] , testGroup "writers-lang-and-dir" [ test' "latex" ["-f", "native", "-t", "latex", "-s"] diff --git a/test/Tests/Readers/HTML.hs b/test/Tests/Readers/HTML.hs --- a/test/Tests/Readers/HTML.hs +++ b/test/Tests/Readers/HTML.hs @@ -83,7 +83,7 @@ , test htmlNativeDivs "
becomes
" $ "
hello
" =?> doc (divWith ("", [], [("role", "foobar")]) (plain (text "hello"))) , test htmlNativeDivs "
has attributes preserved" $ "
hello
" =?> - doc (divWith ("foo", ["bar"], [("role", "main"), ("data-baz", "qux")]) (plain (text "hello"))) + doc (divWith ("foo", ["bar"], [("role", "main"), ("baz", "qux")]) (plain (text "hello"))) , test htmlNativeDivs "
closes

" $ "

hello

main content
" =?> doc (para (text "hello") <> divWith ("", [], [("role", "main")]) (plain (text "main content"))) , test htmlNativeDivs "
followed by text" $ "
main content
non-main content" =?> diff --git a/test/Tests/Writers/Powerpoint.hs b/test/Tests/Writers/Powerpoint.hs --- a/test/Tests/Writers/Powerpoint.hs +++ b/test/Tests/Writers/Powerpoint.hs @@ -91,6 +91,14 @@ def "pptx/speaker_notes_afterseps.native" "pptx/speaker_notes_afterseps.pptx" + , pptxTests "speaker notes after a separating header" + def + "pptx/speaker_notes_afterheader.native" + "pptx/speaker_notes_afterheader.pptx" + , pptxTests "speaker notes after metadata" + def + "pptx/speaker_notes_after_metadata.native" + "pptx/speaker_notes_after_metadata.pptx" , pptxTests "remove empty slides" def "pptx/remove_empty_slides.native" diff --git a/test/command/5340.md b/test/command/5340.md new file mode 100644 --- /dev/null +++ b/test/command/5340.md @@ -0,0 +1,14 @@ +``` +% pandoc -f html -t latex --wrap=preserve +https://example.com/foo-bar +https://example.com/foo--bar +https://example.com/foo-bar +https://example.com/foo--bar +https://example.com/foo%2D%2Dbar +^D +\url{https://example.com/foo-bar} +\url{https://example.com/foo--bar} +\url{https://example.com/foo\%2Dbar} +\url{https://example.com/foo\%2D\%2Dbar} +\url{https://example.com/foo\%2D\%2Dbar} +``` diff --git a/test/command/5367.md b/test/command/5367.md new file mode 100644 --- /dev/null +++ b/test/command/5367.md @@ -0,0 +1,44 @@ +``` +% pandoc -t latex +hello[^1] + +: Sample table.[^2] + +----------- + Fruit[^3] +----------- + Bans[^4] +----------- + +dolly[^5] + +[^1]: doc footnote +[^2]: caption footnote +[^3]: header footnote +[^4]: table cell footnote +[^5]: doc footnote +^D +hello\footnote{doc footnote} + +\begin{longtable}[]{@{}c@{}} +\caption[Sample table.]{Sample table.\footnote{caption footnote}}\tabularnewline +\toprule +\begin{minipage}[b]{0.16\columnwidth}\centering +Fruit\footnote{header footnote}\strut +\end{minipage}\tabularnewline +\midrule +\endfirsthead +\toprule +\begin{minipage}[b]{0.16\columnwidth}\centering +Fruit{}\strut +\end{minipage}\tabularnewline +\midrule +\endhead +\begin{minipage}[t]{0.16\columnwidth}\centering +Bans\footnote{table cell footnote}\strut +\end{minipage}\tabularnewline +\bottomrule +\end{longtable} + +dolly\footnote{doc footnote} +``` diff --git a/test/command/5368.md b/test/command/5368.md new file mode 100644 --- /dev/null +++ b/test/command/5368.md @@ -0,0 +1,23 @@ +``` +% pandoc -t native +1. foo + + ![bar](bar.png) +2. foo2 + + ![bar2](bar2.png) +3. foo3 + + ![foo3](foo3.png) + +Quux. +^D +[OrderedList (1,Decimal,Period) + [[Para [Str "foo"] + ,Para [Image ("",[],[]) [Str "bar"] ("bar.png","fig:")]] + ,[Para [Str "foo2"] + ,Para [Image ("",[],[]) [Str "bar2"] ("bar2.png","fig:")]] + ,[Para [Str "foo3"] + ,Para [Image ("",[],[]) [Str "foo3"] ("foo3.png","fig:")]]] +,Para [Str "Quux."]] +``` diff --git a/test/command/5369.md b/test/command/5369.md new file mode 100644 --- /dev/null +++ b/test/command/5369.md @@ -0,0 +1,7 @@ +``` +% pandoc -f native -t markdown +[Div ("",[],[("tags","[\"o\\ne\",\"two\"]")]) [] ] +^D +::: {tags="[\"o\\ne\",\"two\"]"} +::: +``` diff --git a/test/command/5407.md b/test/command/5407.md new file mode 100644 --- /dev/null +++ b/test/command/5407.md @@ -0,0 +1,14 @@ +``` +% pandoc -t latex --wrap=preserve +hi there?“ +hi there!“ +hi there?‘ +hi there!‘ +hi there! +^D +hi there?{}`` +hi there!{}`` +hi there?{}` +hi there!{}` +hi there! +``` diff --git a/test/command/5416.md b/test/command/5416.md new file mode 100644 --- /dev/null +++ b/test/command/5416.md @@ -0,0 +1,13 @@ +``` +% pandoc -f dokuwiki -t native +{ +^D +[Para [Str "{"]] +``` + +``` +% pandoc -f dokuwiki -t native +{{ +^D +[Para [Str "{{"]] +``` diff --git a/test/command/setext-fenced-div.md b/test/command/setext-fenced-div.md new file mode 100644 --- /dev/null +++ b/test/command/setext-fenced-div.md @@ -0,0 +1,9 @@ +``` +% pandoc -t native +::: {.cell} +--- +::: +^D +[Div ("",["cell"],[]) + [HorizontalRule]] +``` diff --git a/test/docx/golden/codeblock.docx b/test/docx/golden/codeblock.docx Binary files a/test/docx/golden/codeblock.docx and b/test/docx/golden/codeblock.docx differ diff --git a/test/docx/golden/inline_formatting.docx b/test/docx/golden/inline_formatting.docx Binary files a/test/docx/golden/inline_formatting.docx and b/test/docx/golden/inline_formatting.docx differ diff --git a/test/lhs-test.latex b/test/lhs-test.latex --- a/test/lhs-test.latex +++ b/test/lhs-test.latex @@ -1,5 +1,5 @@ % Options for packages loaded elsewhere -\PassOptionsToPackage{unicode=true}{hyperref} +\PassOptionsToPackage{unicode}{hyperref} \PassOptionsToPackage{hyphens}{url} % \documentclass[ @@ -10,8 +10,8 @@ \ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex \usepackage[T1]{fontenc} \usepackage[utf8]{inputenc} - \usepackage{textcomp} % provides euro and other symbols -\else % if luatex or xelatex + \usepackage{textcomp} % provide euro and other symbols +\else % if luatex or xetex \usepackage{unicode-math} \defaultfontfeatures{Scale=MatchLowercase} \defaultfontfeatures[\rmfamily]{Ligatures=TeX,Scale=1} @@ -37,7 +37,7 @@ \IfFileExists{bookmark.sty}{\usepackage{bookmark}}{\usepackage{hyperref}} \hypersetup{ hidelinks, -} + pdfcreator={LaTeX via pandoc}} \urlstyle{same} % disable monospaced font for URLs \usepackage{color} \usepackage{fancyvrb} @@ -81,21 +81,6 @@ \providecommand{\tightlist}{% \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}} \setcounter{secnumdepth}{-\maxdimen} % remove section numbering -% Redefines (sub)paragraphs to behave more like sections -\ifx\paragraph\undefined\else - \let\oldparagraph\paragraph - \renewcommand{\paragraph}[1]{\oldparagraph{#1}\mbox{}} -\fi -\ifx\subparagraph\undefined\else - \let\oldsubparagraph\subparagraph - \renewcommand{\subparagraph}[1]{\oldsubparagraph{#1}\mbox{}} -\fi - -% Set default figure placement to htbp -\makeatletter -\def\fps@figure{htbp} -\makeatother - \date{} diff --git a/test/lhs-test.latex+lhs b/test/lhs-test.latex+lhs --- a/test/lhs-test.latex+lhs +++ b/test/lhs-test.latex+lhs @@ -1,5 +1,5 @@ % Options for packages loaded elsewhere -\PassOptionsToPackage{unicode=true}{hyperref} +\PassOptionsToPackage{unicode}{hyperref} \PassOptionsToPackage{hyphens}{url} % \documentclass[ @@ -10,8 +10,8 @@ \ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex \usepackage[T1]{fontenc} \usepackage[utf8]{inputenc} - \usepackage{textcomp} % provides euro and other symbols -\else % if luatex or xelatex + \usepackage{textcomp} % provide euro and other symbols +\else % if luatex or xetex \usepackage{unicode-math} \defaultfontfeatures{Scale=MatchLowercase} \defaultfontfeatures[\rmfamily]{Ligatures=TeX,Scale=1} @@ -37,7 +37,7 @@ \IfFileExists{bookmark.sty}{\usepackage{bookmark}}{\usepackage{hyperref}} \hypersetup{ hidelinks, -} + pdfcreator={LaTeX via pandoc}} \urlstyle{same} % disable monospaced font for URLs \usepackage{listings} \newcommand{\passthrough}[1]{#1} @@ -48,21 +48,6 @@ \providecommand{\tightlist}{% \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}} \setcounter{secnumdepth}{-\maxdimen} % remove section numbering -% Redefines (sub)paragraphs to behave more like sections -\ifx\paragraph\undefined\else - \let\oldparagraph\paragraph - \renewcommand{\paragraph}[1]{\oldparagraph{#1}\mbox{}} -\fi -\ifx\subparagraph\undefined\else - \let\oldsubparagraph\subparagraph - \renewcommand{\subparagraph}[1]{\oldsubparagraph{#1}\mbox{}} -\fi - -% Set default figure placement to htbp -\makeatletter -\def\fps@figure{htbp} -\makeatother - \date{} diff --git a/test/pptx/document-properties-short-desc.pptx b/test/pptx/document-properties-short-desc.pptx Binary files a/test/pptx/document-properties-short-desc.pptx and b/test/pptx/document-properties-short-desc.pptx differ diff --git a/test/pptx/document-properties-short-desc_templated.pptx b/test/pptx/document-properties-short-desc_templated.pptx Binary files a/test/pptx/document-properties-short-desc_templated.pptx and b/test/pptx/document-properties-short-desc_templated.pptx differ diff --git a/test/pptx/document-properties.pptx b/test/pptx/document-properties.pptx Binary files a/test/pptx/document-properties.pptx and b/test/pptx/document-properties.pptx differ diff --git a/test/pptx/document-properties_templated.pptx b/test/pptx/document-properties_templated.pptx Binary files a/test/pptx/document-properties_templated.pptx and b/test/pptx/document-properties_templated.pptx differ diff --git a/test/pptx/endnotes.pptx b/test/pptx/endnotes.pptx Binary files a/test/pptx/endnotes.pptx and b/test/pptx/endnotes.pptx differ diff --git a/test/pptx/endnotes_templated.pptx b/test/pptx/endnotes_templated.pptx Binary files a/test/pptx/endnotes_templated.pptx and b/test/pptx/endnotes_templated.pptx differ diff --git a/test/pptx/endnotes_toc.pptx b/test/pptx/endnotes_toc.pptx Binary files a/test/pptx/endnotes_toc.pptx and b/test/pptx/endnotes_toc.pptx differ diff --git a/test/pptx/endnotes_toc_templated.pptx b/test/pptx/endnotes_toc_templated.pptx Binary files a/test/pptx/endnotes_toc_templated.pptx and b/test/pptx/endnotes_toc_templated.pptx differ diff --git a/test/pptx/images.pptx b/test/pptx/images.pptx Binary files a/test/pptx/images.pptx and b/test/pptx/images.pptx differ diff --git a/test/pptx/images_templated.pptx b/test/pptx/images_templated.pptx Binary files a/test/pptx/images_templated.pptx and b/test/pptx/images_templated.pptx differ diff --git a/test/pptx/inline_formatting.pptx b/test/pptx/inline_formatting.pptx Binary files a/test/pptx/inline_formatting.pptx and b/test/pptx/inline_formatting.pptx differ diff --git a/test/pptx/inline_formatting_templated.pptx b/test/pptx/inline_formatting_templated.pptx Binary files a/test/pptx/inline_formatting_templated.pptx and b/test/pptx/inline_formatting_templated.pptx differ diff --git a/test/pptx/lists.pptx b/test/pptx/lists.pptx Binary files a/test/pptx/lists.pptx and b/test/pptx/lists.pptx differ diff --git a/test/pptx/lists_templated.pptx b/test/pptx/lists_templated.pptx Binary files a/test/pptx/lists_templated.pptx and b/test/pptx/lists_templated.pptx differ diff --git a/test/pptx/raw_ooxml.pptx b/test/pptx/raw_ooxml.pptx Binary files a/test/pptx/raw_ooxml.pptx and b/test/pptx/raw_ooxml.pptx differ diff --git a/test/pptx/raw_ooxml_templated.pptx b/test/pptx/raw_ooxml_templated.pptx Binary files a/test/pptx/raw_ooxml_templated.pptx and b/test/pptx/raw_ooxml_templated.pptx differ diff --git a/test/pptx/remove_empty_slides.pptx b/test/pptx/remove_empty_slides.pptx Binary files a/test/pptx/remove_empty_slides.pptx and b/test/pptx/remove_empty_slides.pptx differ diff --git a/test/pptx/remove_empty_slides_templated.pptx b/test/pptx/remove_empty_slides_templated.pptx Binary files a/test/pptx/remove_empty_slides_templated.pptx and b/test/pptx/remove_empty_slides_templated.pptx differ diff --git a/test/pptx/slide_breaks.pptx b/test/pptx/slide_breaks.pptx Binary files a/test/pptx/slide_breaks.pptx and b/test/pptx/slide_breaks.pptx differ diff --git a/test/pptx/slide_breaks_slide_level_1.pptx b/test/pptx/slide_breaks_slide_level_1.pptx Binary files a/test/pptx/slide_breaks_slide_level_1.pptx and b/test/pptx/slide_breaks_slide_level_1.pptx differ diff --git a/test/pptx/slide_breaks_slide_level_1_templated.pptx b/test/pptx/slide_breaks_slide_level_1_templated.pptx Binary files a/test/pptx/slide_breaks_slide_level_1_templated.pptx and b/test/pptx/slide_breaks_slide_level_1_templated.pptx differ diff --git a/test/pptx/slide_breaks_templated.pptx b/test/pptx/slide_breaks_templated.pptx Binary files a/test/pptx/slide_breaks_templated.pptx and b/test/pptx/slide_breaks_templated.pptx differ diff --git a/test/pptx/slide_breaks_toc.pptx b/test/pptx/slide_breaks_toc.pptx Binary files a/test/pptx/slide_breaks_toc.pptx and b/test/pptx/slide_breaks_toc.pptx differ diff --git a/test/pptx/slide_breaks_toc_templated.pptx b/test/pptx/slide_breaks_toc_templated.pptx Binary files a/test/pptx/slide_breaks_toc_templated.pptx and b/test/pptx/slide_breaks_toc_templated.pptx differ diff --git a/test/pptx/speaker_notes.pptx b/test/pptx/speaker_notes.pptx Binary files a/test/pptx/speaker_notes.pptx and b/test/pptx/speaker_notes.pptx differ diff --git a/test/pptx/speaker_notes_after_metadata.native b/test/pptx/speaker_notes_after_metadata.native new file mode 100644 --- /dev/null +++ b/test/pptx/speaker_notes_after_metadata.native @@ -0,0 +1,5 @@ +Pandoc (Meta {unMeta = fromList [("author",MetaInlines [Str "Jesse",Space,Str "Rosenthal"]),("title",MetaInlines [Str "Testing"])]}) +[Div ("",["notes"],[]) + [Para [Str "Some",Space,Str "speaker",Space,Str "notes"]] +,Header 1 ("a-header",[],[]) [Str "A",Space,Str "header"] +,Para [Str "And",Space,Str "a",Space,Str "new",Space,Str "slide."]] diff --git a/test/pptx/speaker_notes_after_metadata.pptx b/test/pptx/speaker_notes_after_metadata.pptx new file mode 100644 Binary files /dev/null and b/test/pptx/speaker_notes_after_metadata.pptx differ diff --git a/test/pptx/speaker_notes_after_metadata_templated.pptx b/test/pptx/speaker_notes_after_metadata_templated.pptx new file mode 100644 Binary files /dev/null and b/test/pptx/speaker_notes_after_metadata_templated.pptx differ diff --git a/test/pptx/speaker_notes_afterheader.native b/test/pptx/speaker_notes_afterheader.native new file mode 100644 --- /dev/null +++ b/test/pptx/speaker_notes_afterheader.native @@ -0,0 +1,3 @@ +[Header 1 ("here-is-a-single-header",[],[]) [Str "Here",Space,Str "is",Space,Str "a",Space,Str "single",Space,Str "header"] +,Div ("",["notes"],[]) + [Para [Str "and",Space,Str "here",Space,Str "are",Space,Str "some",Space,Str "notes"]]] diff --git a/test/pptx/speaker_notes_afterheader.pptx b/test/pptx/speaker_notes_afterheader.pptx new file mode 100644 Binary files /dev/null and b/test/pptx/speaker_notes_afterheader.pptx differ diff --git a/test/pptx/speaker_notes_afterheader_templated.pptx b/test/pptx/speaker_notes_afterheader_templated.pptx new file mode 100644 Binary files /dev/null and b/test/pptx/speaker_notes_afterheader_templated.pptx differ diff --git a/test/pptx/speaker_notes_afterseps.pptx b/test/pptx/speaker_notes_afterseps.pptx Binary files a/test/pptx/speaker_notes_afterseps.pptx and b/test/pptx/speaker_notes_afterseps.pptx differ diff --git a/test/pptx/speaker_notes_afterseps_templated.pptx b/test/pptx/speaker_notes_afterseps_templated.pptx Binary files a/test/pptx/speaker_notes_afterseps_templated.pptx and b/test/pptx/speaker_notes_afterseps_templated.pptx differ diff --git a/test/pptx/speaker_notes_templated.pptx b/test/pptx/speaker_notes_templated.pptx Binary files a/test/pptx/speaker_notes_templated.pptx and b/test/pptx/speaker_notes_templated.pptx differ diff --git a/test/pptx/tables.pptx b/test/pptx/tables.pptx Binary files a/test/pptx/tables.pptx and b/test/pptx/tables.pptx differ diff --git a/test/pptx/tables_templated.pptx b/test/pptx/tables_templated.pptx Binary files a/test/pptx/tables_templated.pptx and b/test/pptx/tables_templated.pptx differ diff --git a/test/pptx/two_column.pptx b/test/pptx/two_column.pptx Binary files a/test/pptx/two_column.pptx and b/test/pptx/two_column.pptx differ diff --git a/test/pptx/two_column_templated.pptx b/test/pptx/two_column_templated.pptx Binary files a/test/pptx/two_column_templated.pptx and b/test/pptx/two_column_templated.pptx differ diff --git a/test/vimwiki-reader.native b/test/vimwiki-reader.native --- a/test/vimwiki-reader.native +++ b/test/vimwiki-reader.native @@ -62,14 +62,14 @@ ,Para [Link ("",[],[]) [Str "email",Space,Str "me"] ("mailto:info@example.org","")] ,Para [Link ("",[],[]) [Str "mailto:hello@bye.com"] ("mailto:hello@bye.com","")] ,Header 2 ("internal links",[],[]) [Str "internal",Space,Str "links"] -,Para [Link ("",[],[]) [Str "This is a link"] ("This is a link.html","")] -,Para [Link ("",[],[]) [Str "Description",Space,Str "of",Space,Str "the",Space,Str "link"] ("This is a link source.html","")] -,Para [Link ("",[],[]) [Str "projects/Important Project 1"] ("projects/Important Project 1.html",""),SoftBreak,Link ("",[],[]) [Str "../index"] ("../index.html",""),SoftBreak,Link ("",[],[]) [Str "Other",Space,Str "files"] ("a subdirectory/","")] -,Para [Link ("",[],[]) [Str "try",Space,Str "me",Space,Str "to",Space,Str "test",Space,Str "tag",Space,Str "anchors"] ("#tag-one","")] -,Para [Link ("",[],[]) [Str "try",Space,Str "me",Space,Str "to",Space,Str "test",Space,Str "header",Space,Str "anchors"] ("#block quotes","")] -,Para [Link ("",[],[]) [Str "try",Space,Str "me",Space,Str "to",Space,Str "test",Space,Str "strong",Space,Str "anchors"] ("#strong","")] -,Para [Link ("",[],[]) [Str "Tasks",Space,Str "for",Space,Str "tomorrow"] ("Todo List.html#Tomorrow","")] -,Para [Link ("",[],[]) [Str "diary:2017-05-01"] ("diary/2017-05-01.html","")] +,Para [Link ("",[],[]) [Str "This is a link"] ("This is a link","wikilink")] +,Para [Link ("",[],[]) [Str "Description",Space,Str "of",Space,Str "the",Space,Str "link"] ("This is a link source","wikilink")] +,Para [Link ("",[],[]) [Str "projects/Important Project 1"] ("projects/Important Project 1","wikilink"),SoftBreak,Link ("",[],[]) [Str "../index"] ("../index","wikilink"),SoftBreak,Link ("",[],[]) [Str "Other",Space,Str "files"] ("a subdirectory/","wikilink")] +,Para [Link ("",[],[]) [Str "try",Space,Str "me",Space,Str "to",Space,Str "test",Space,Str "tag",Space,Str "anchors"] ("#tag-one","wikilink")] +,Para [Link ("",[],[]) [Str "try",Space,Str "me",Space,Str "to",Space,Str "test",Space,Str "header",Space,Str "anchors"] ("#block quotes","wikilink")] +,Para [Link ("",[],[]) [Str "try",Space,Str "me",Space,Str "to",Space,Str "test",Space,Str "strong",Space,Str "anchors"] ("#strong","wikilink")] +,Para [Link ("",[],[]) [Str "Tasks",Space,Str "for",Space,Str "tomorrow"] ("Todo List#Tomorrow","wikilink")] +,Para [Link ("",[],[]) [Str "diary:2017-05-01"] ("diary/2017-05-01","wikilink")] ,Para [Link ("",[],[]) [Str "Important",Space,Str "Data"] ("file:../assets/data.csv","")] ,Header 3 ("links with thumbnails",[],[]) [Str "links",Space,Str "with",Space,Str "thumbnails"] ,Para [Link ("",[],[]) [Image ("",[],[]) [Str ""] ("./movie.jpg","")] ("http://www.google.com","")] diff --git a/test/writer.latex b/test/writer.latex --- a/test/writer.latex +++ b/test/writer.latex @@ -1,5 +1,5 @@ % Options for packages loaded elsewhere -\PassOptionsToPackage{unicode=true}{hyperref} +\PassOptionsToPackage{unicode}{hyperref} \PassOptionsToPackage{hyphens}{url} % \documentclass[ @@ -10,8 +10,8 @@ \ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex \usepackage[T1]{fontenc} \usepackage[utf8]{inputenc} - \usepackage{textcomp} % provides euro and other symbols -\else % if luatex or xelatex + \usepackage{textcomp} % provide euro and other symbols +\else % if luatex or xetex \usepackage{unicode-math} \defaultfontfeatures{Scale=MatchLowercase} \defaultfontfeatures[\rmfamily]{Ligatures=TeX,Scale=1} @@ -40,9 +40,9 @@ pdftitle={Pandoc Test Suite}, pdfauthor={John MacFarlane; Anonymous}, hidelinks, -} + pdfcreator={LaTeX via pandoc}} \urlstyle{same} % disable monospaced font for URLs -\VerbatimFootnotes % allows verbatim text in footnotes +\VerbatimFootnotes % allow verbatim text in footnotes \usepackage{graphicx,grffile} \makeatletter \def\maxwidth{\ifdim\Gin@nat@width>\linewidth\linewidth\else\Gin@nat@width\fi} @@ -52,6 +52,10 @@ % margins by default, and it is still possible to overwrite the defaults % using explicit options in \includegraphics[width, height, ...]{} \setkeys{Gin}{width=\maxwidth,height=\maxheight,keepaspectratio} +% Set default figure placement to htbp +\makeatletter +\def\fps@figure{htbp} +\makeatother \usepackage[normalem]{ulem} % Avoid problems with \sout in headers with hyperref \pdfstringdefDisableCommands{\renewcommand{\sout}{}} @@ -59,21 +63,6 @@ \providecommand{\tightlist}{% \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}} \setcounter{secnumdepth}{-\maxdimen} % remove section numbering -% Redefines (sub)paragraphs to behave more like sections -\ifx\paragraph\undefined\else - \let\oldparagraph\paragraph - \renewcommand{\paragraph}[1]{\oldparagraph{#1}\mbox{}} -\fi -\ifx\subparagraph\undefined\else - \let\oldsubparagraph\subparagraph - \renewcommand{\subparagraph}[1]{\oldsubparagraph{#1}\mbox{}} -\fi - -% Set default figure placement to htbp -\makeatletter -\def\fps@figure{htbp} -\makeatother - \title{Pandoc Test Suite} \author{John MacFarlane \and Anonymous} diff --git a/test/writer.xwiki b/test/writer.xwiki new file mode 100644 --- /dev/null +++ b/test/writer.xwiki @@ -0,0 +1,650 @@ +This is a set of tests for pandoc. Most of them are adapted from John Gruber’s markdown test suite. + + +---- + += Headers {{id name="headers" /}}= + +== Level 2 with an [[embedded link>>/url]] {{id name="level-2-with-an-embedded-link" /}}== + +=== Level 3 with //emphasis// {{id name="level-3-with-emphasis" /}}=== + +==== Level 4 {{id name="level-4" /}}==== + +===== Level 5 {{id name="level-5" /}}===== + += Level 1 {{id name="level-1" /}}= + +== Level 2 with //emphasis// {{id name="level-2-with-emphasis" /}}== + +=== Level 3 {{id name="level-3" /}}=== + +with no blank line + +== Level 2 {{id name="level-2" /}}== + +with no blank line + + +---- + += Paragraphs {{id name="paragraphs" /}}= + +Here’s a regular paragraph. + +In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item. + +Here’s one with a bullet. * criminey. + +There should be a hard line break\\here. + + +---- + += Block Quotes {{id name="block-quotes" /}}= + +E-mail style: + +>This is a block quote. It is pretty short. +> +>Code in a block quote: +> +> +>{{code}} +>sub status { +> print "working"; +>} +>{{/code}} +> +>A list: +> +>1. item one +>1. item two +> +>Nested block quotes: +> +>>nested +>> +>>nested +>> +This should not be a block quote: 2 > 1. + +And a following paragraph. + + +---- + += Code Blocks {{id name="code-blocks" /}}= + +Code: + + +{{code}} +---- (should be four hyphens) + +sub status { + print "working"; +} + +this code block is indented by one tab +{{/code}} + +And: + + +{{code}} + this code block is indented by two tabs + +These should not be escaped: \$ \\ \> \[ \{ +{{/code}} + + +---- + += Lists {{id name="lists" /}}= + +== Unordered {{id name="unordered" /}}== + +Asterisks tight: + +*. asterisk 1 +*. asterisk 2 +*. asterisk 3 + +Asterisks loose: + +*. asterisk 1 +*. asterisk 2 +*. asterisk 3 + +Pluses tight: + +*. Plus 1 +*. Plus 2 +*. Plus 3 + +Pluses loose: + +*. Plus 1 +*. Plus 2 +*. Plus 3 + +Minuses tight: + +*. Minus 1 +*. Minus 2 +*. Minus 3 + +Minuses loose: + +*. Minus 1 +*. Minus 2 +*. Minus 3 + +== Ordered {{id name="ordered" /}}== + +Tight: + +1. First +1. Second +1. Third + +and: + +1. One +1. Two +1. Three + +Loose using tabs: + +1. First +1. Second +1. Third + +and using spaces: + +1. One +1. Two +1. Three + +Multiple paragraphs: + +1. Item 1, graf one. + +Item 1. graf two. The quick brown fox jumped over the lazy dog’s back. +1. Item 2. +1. Item 3. + +== Nested {{id name="nested" /}}== + +*. Tab +**. Tab +***. Tab + +Here’s another: + +1. First +1. Second: +1*. Fee +1*. Fie +1*. Foe +1. Third + +Same thing but with paragraphs: + +1. First +1. Second: + +1*. Fee +1*. Fie +1*. Foe +1. Third + +== Tabs and spaces {{id name="tabs-and-spaces" /}}== + +*. this is a list item indented with tabs +*. this is a list item indented with spaces + +**. this is an example list item indented with tabs +**. this is an example list item indented with spaces + +== Fancy list markers {{id name="fancy-list-markers" /}}== + +1. begins with 2 +1. and now 3 + +with a continuation + +11. sublist with roman numerals, starting with 4 +11. more items +111. a subsublist +111. a subsublist + +Nesting: + +1. Upper Alpha +11. Upper Roman. +111. Decimal start with 6 +1111. Lower alpha with paren + +Autonumbering: + +1. Autonumber. +1. More. +11. Nested. + +Should not be a list item: + +M.A. 2007 + +B. Williams + + +---- + += Definition Lists {{id name="definition-lists" /}}= + +Tight using spaces: + +; apple +: red fruit +; orange +: orange fruit +; banana +: yellow fruit + +Tight using tabs: + +; apple +: red fruit +; orange +: orange fruit +; banana +: yellow fruit + +Loose: + +; apple +: red fruit + +; orange +: orange fruit + +; banana +: yellow fruit + + +Multiple blocks with italics: + +; //apple// +: red fruit + +contains seeds, crisp, pleasant to taste + +; //orange// +: orange fruit + + +{{code}} +{ orange code block } +{{/code}} + +>orange block quote +> + +Multiple definitions, tight: + +; apple +: red fruit +: computer +; orange +: orange fruit +: bank + +Multiple definitions, loose: + +; apple +: red fruit + +: computer + +; orange +: orange fruit + +: bank + + +Blank line after term, indented marker, alternate markers: + +; apple +: red fruit + +: computer + +; orange +: orange fruit + +;1. sublist +;1. sublist + += HTML Blocks {{id name="html-blocks" /}}= + +Simple block on one line: + +foo +And nested without indentation: + +foo + +bar +Interpreted markdown in a table: + + + + +This is //emphasized// + + +And this is **strong** + + + + +Here’s a simple block: + +foo + +This should be a code block, though: + + +{{code}} +
+ foo +
+{{/code}} + +As should this: + + +{{code}} +
foo
+{{/code}} + +Now, nested: + +foo +This should just be an HTML comment: + + +Multiline: + + + +Code block: + + +{{code}} + +{{/code}} + +Just plain comment, with trailing spaces on the line: + + +Code: + + +{{code}} +
+{{/code}} + +Hr’s: + + + + + + + + + + + +---- + += Inline Markup {{id name="inline-markup" /}}= + +This is //emphasized//, and so //is this//. + +This is **strong**, and so **is this**. + +An //[[emphasized link>>/url]]//. + +**//This is strong and em.//** + +So is **//this//** word. + +**//This is strong and em.//** + +So is **//this//** word. + +This is code: {{code}}>{{/code}}, {{code}}${{/code}}, {{code}}\{{/code}}, {{code}}\${{/code}}, {{code}}{{/code}}. + +--This is //strikeout//.-- + +Superscripts: a^^bc^^d a^^//hello//^^ a^^hello there^^. + +Subscripts: H,,2,,O, H,,23,,O, H,,many of them,,O. + +These should not be superscripts or subscripts, because of the unescaped spaces: a^b c^d, a~~b c~~d. + + +---- + += Smart quotes, ellipses, dashes {{id name="smart-quotes-ellipses-dashes" /}}= + +“Hello,” said the spider. “‘Shelob’ is my name.” + +‘A’, ‘B’, and ‘C’ are letters. + +‘Oak,’ ‘elm,’ and ‘beech’ are names of trees. So is ‘pine.’ + +‘He said, “I want to go.”’ Were you alive in the 70’s? + +Here is some quoted ‘{{code}}code{{/code}}’ and a “[[quoted link>>http://example.com/?foo=1&bar=2]]”. + +Some dashes: one—two — three—four — five. + +Dashes between numbers: 5–7, 255–66, 1987–1999. + +Ellipses…and…and…. + + +---- + += LaTeX {{id name="latex" /}}= + +*. +*. {{formula}}2+2=4{{/formula}} +*. {{formula}}x \in y{{/formula}} +*. {{formula}}\alpha \wedge \omega{{/formula}} +*. {{formula}}223{{/formula}} +*. {{formula}}p{{/formula}}-Tree +*. Here’s some display math: {{formula}}\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}{{/formula}} +*. Here’s one that has a line break in it: {{formula}}\alpha + \omega \times x^2{{/formula}}. + +These shouldn’t be math: + +*. To get the famous equation, write {{code}}$e = mc^2${{/code}}. +*. $22,000 is a //lot// of money. So is $34,000. (It worked if “lot” is emphasized.) +*. Shoes ($20) and socks ($5). +*. Escaped {{code}}${{/code}}: $73 //this should be emphasized// 23$. + +Here’s a LaTeX table: + + + +---- + += Special Characters {{id name="special-characters" /}}= + +Here is some unicode: + +*. I hat: Î +*. o umlaut: ö +*. section: § +*. set membership: ∈ +*. copyright: © + +AT&T has an ampersand in their name. + +AT&T is another way to write it. + +This & that. + +4 < 5. + +6 > 5. + +Backslash: \ + +Backtick: ` + +Asterisk: * + +Underscore: _ + +Left brace: { + +Right brace: } + +Left bracket: [ + +Right bracket: ] + +Left paren: ( + +Right paren: ) + +Greater-than: > + +Hash: # + +Period: . + +Bang: ! + +Plus: + + +Minus: - + + +---- + += Links {{id name="links" /}}= + +== Explicit {{id name="explicit" /}}== + +Just a [[URL>>/url/]]. + +[[URL and title>>/url/]]. + +[[URL and title>>/url/]]. + +[[URL and title>>/url/]]. + +[[URL and title>>/url/]] + +[[URL and title>>/url/]] + +[[with_underscore>>/url/with_underscore]] + +[[Email link>>mailto:nobody@nowhere.net]] + +[[Empty>>]]. + +== Reference {{id name="reference" /}}== + +Foo [[bar>>/url/]]. + +With [[embedded [brackets]>>/url/]]. + +[[b>>/url/]] by itself should be a link. + +Indented [[once>>/url]]. + +Indented [[twice>>/url]]. + +Indented [[thrice>>/url]]. + +This should [not][] be a link. + + +{{code}} +[not]: /url +{{/code}} + +Foo [[bar>>/url/]]. + +Foo [[biz>>/url/]]. + +== With ampersands {{id name="with-ampersands" /}}== + +Here’s a [[link with an ampersand in the URL>>http://example.com/?foo=1&bar=2]]. + +Here’s a link with an amersand in the link text: [[AT&T>>http://att.com/]]. + +Here’s an [[inline link>>/script?foo=1&bar=2]]. + +Here’s an [[inline link in pointy braces>>/script?foo=1&bar=2]]. + +== Autolinks {{id name="autolinks" /}}== + +With an ampersand: http://example.com/?foo=1&bar=2 + +*. In a list? +*. http://example.com/ +*. It should. + +An e-mail address: [[nobody@nowhere.net>>mailto:nobody@nowhere.net]] + +>Blockquoted: http://example.com/ +> +Auto-links should not occur here: {{code}}{{/code}} + + +{{code}} +or here: +{{/code}} + + +---- + += Images {{id name="images" /}}= + +From “Voyage dans la Lune” by Georges Melies (1902): + +[[image:lalune.jpg||alt="lalune" title="fig:Voyage dans la Lune"]] + +Here is a movie [[image:movie.jpg||alt="movie"]] icon. + + +---- + += Footnotes {{id name="footnotes" /}}= + +Here is a footnote reference,{{footnote}}Here is the footnote. It can go anywhere after the footnote reference. It need not be placed at the end of the document.{{/footnote}} and another.{{footnote}}Here’s the long note. This one contains multiple blocks. + +Subsequent blocks are indented to show that they belong to the footnote (as with list items). + + +{{code}} + { } +{{/code}} + +If you want, you can indent every line, but you can also be lazy and just indent the first line of each block.{{/footnote}} This should //not// be a footnote reference, because it contains a space.[^my note] Here is an inline note.{{footnote}}This is //easier// to type. Inline notes may contain [[links>>http://google.com]] and {{code}}]{{/code}} verbatim characters, as well as [bracketed text].{{/footnote}} + +>Notes can go in quotes.{{footnote}}In quote.{{/footnote}} +> +1. And in list items.{{footnote}}In list.{{/footnote}} + +This paragraph should not be part of the note, as it is not indented. diff --git a/test/writers-lang-and-dir.latex b/test/writers-lang-and-dir.latex --- a/test/writers-lang-and-dir.latex +++ b/test/writers-lang-and-dir.latex @@ -1,5 +1,5 @@ % Options for packages loaded elsewhere -\PassOptionsToPackage{unicode=true}{hyperref} +\PassOptionsToPackage{unicode}{hyperref} \PassOptionsToPackage{hyphens}{url} % \documentclass[ @@ -11,8 +11,8 @@ \ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex \usepackage[T1]{fontenc} \usepackage[utf8]{inputenc} - \usepackage{textcomp} % provides euro and other symbols -\else % if luatex or xelatex + \usepackage{textcomp} % provide euro and other symbols +\else % if luatex or xetex \usepackage{unicode-math} \defaultfontfeatures{Scale=MatchLowercase} \defaultfontfeatures[\rmfamily]{Ligatures=TeX,Scale=1} @@ -38,27 +38,12 @@ \IfFileExists{bookmark.sty}{\usepackage{bookmark}}{\usepackage{hyperref}} \hypersetup{ hidelinks, -} + pdfcreator={LaTeX via pandoc}} \urlstyle{same} % disable monospaced font for URLs \setlength{\emergencystretch}{3em} % prevent overfull lines \providecommand{\tightlist}{% \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}} \setcounter{secnumdepth}{-\maxdimen} % remove section numbering -% Redefines (sub)paragraphs to behave more like sections -\ifx\paragraph\undefined\else - \let\oldparagraph\paragraph - \renewcommand{\paragraph}[1]{\oldparagraph{#1}\mbox{}} -\fi -\ifx\subparagraph\undefined\else - \let\oldsubparagraph\subparagraph - \renewcommand{\subparagraph}[1]{\oldsubparagraph{#1}\mbox{}} -\fi - -% Set default figure placement to htbp -\makeatletter -\def\fps@figure{htbp} -\makeatother - \ifxetex % Load polyglossia as late as possible: uses bidi with RTL langages (e.g. Hebrew, Arabic) \usepackage{polyglossia}