diff --git a/INSTALL.md b/INSTALL.md --- a/INSTALL.md +++ b/INSTALL.md @@ -334,5 +334,5 @@ [openSUSE]: https://software.opensuse.org/package/pandoc [source tarball]: http://hackage.haskell.org/package/pandoc [stack]: http://docs.haskellstack.org/en/stable/install_and_upgrade.html -[cabal-install]: http://hackage.haskell.org/trac/hackage/wiki/CabalInstall +[cabal-install]: http://hackage.haskell.org/package/cabal-install [uninstaller]: https://raw.githubusercontent.com/jgm/pandoc/master/macos/uninstall-pandoc.pl diff --git a/MANUAL.txt b/MANUAL.txt --- a/MANUAL.txt +++ b/MANUAL.txt @@ -1,6 +1,6 @@ % Pandoc User's Guide % John MacFarlane -% July 19, 2018 +% August 5, 2018 Synopsis ======== @@ -155,9 +155,10 @@ `xelatex` will use [`mathspec`] instead of [`unicode-math`]. The [`upquote`] and [`microtype`] packages are used if available, and [`csquotes`] will be used for [typography] -if added to the template or included in any header file. The -[`natbib`], [`biblatex`], [`bibtex`], and [`biber`] packages can -optionally be used for [citation rendering]. +if `\usepackage{csquotes}` is present in the template or +included via `/H/--include-in-header`. The [`natbib`], +[`biblatex`], [`bibtex`], and [`biber`] packages can optionally +be used for [citation rendering]. [`amsfonts`]: https://ctan.org/pkg/amsfonts [`amsmath`]: https://ctan.org/pkg/amsmath @@ -1917,7 +1918,7 @@ : `latex`, `org`, `textile` output formats -: `textile` +: `textile`, `commonmark` #### [Extension: `native_divs`] {#native_divs} @@ -4448,26 +4449,30 @@ `allowframebreaks`, `b`, `c`, `t`, `environment`, `label`, `plain`, `shrink`, `standout`, `noframenumbering`. -Background in reveal.js ------------------------ +Background in reveal.js and beamer +---------------------------------- -Background images can be added to self-contained reveal.js slideshows. +Background images can be added to self-contained reveal.js slideshows and +to beamer slideshows. -For the same image on every slide, use the reveal.js configuration -option `parallaxBackgroundImage` either in the YAML metadata block -or as a command-line variable. You can also set -`parallaxBackgroundHorizontal` and `parallaxBackgroundVertical` the same -way and must also set `parallaxBackgroundSize` to have your values -take effect. +For the same image on every slide, use the configuration +option `background-image` either in the YAML metadata block +or as a command-line variable. (There are no other options in +beamer and the rest of this section concerns reveal.js slideshows.) -To set an image for a particular slide, add +For reveal.js, you can instead use the reveal.js-native option +`parallaxBackgroundImage`. You can also set `parallaxBackgroundHorizontal` +and `parallaxBackgroundVertical` the same way and must also set +`parallaxBackgroundSize` to have your values take effect. + +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). In reveal.js's overview mode, the parallaxBackgroundImage will show up only on the first slide. -Other background settings also work on individual slides, including +Other reveal.js background settings also work on individual slides, including `data-background-size`, `data-background-repeat`, `data-background-color`, `data-transition`, and `data-transition-speed`. @@ -4475,7 +4480,7 @@ documentation](https://github.com/hakimel/reveal.js#slide-backgrounds) for more details. -For example: +For example in reveal.js: ``` --- diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -38,9 +38,9 @@ e-book) - `gfm` ([GitHub-Flavored Markdown](https://help.github.com/articles/github-flavored-markdown/)), - or `markdown_github`, which provides deprecated and less accurate - support for Github-Flavored Markdown; please use `gfm` instead, - unless you need to use extensions other than `smart`. + or the deprecated and less accurate `markdown_github`; use + [`markdown_github`](#markdown-variants) only if you need extensions + not supported in [`gfm`](#markdown-variants). - `haddock` ([Haddock markup](https://www.haskell.org/haddock/doc/html/ch03s08.html)) - `html` ([HTML](http://www.w3.org/html/)) @@ -92,9 +92,9 @@ e-book) - `gfm` ([GitHub-Flavored Markdown](https://help.github.com/articles/github-flavored-markdown/)), - or `markdown_github`, which provides deprecated and less accurate - support for Github-Flavored Markdown; please use `gfm` instead, - unless you use extensions that do not work with `gfm`. + or the deprecated and less accurate `markdown_github`; use + [`markdown_github`](#markdown-variants) only if you need extensions + not supported in [`gfm`](#markdown-variants). - `haddock` ([Haddock markup](https://www.haskell.org/haddock/doc/html/ch03s08.html)) - `html` or `html5` ([HTML](http://www.w3.org/html/), i.e. diff --git a/changelog b/changelog --- a/changelog +++ b/changelog @@ -1,3 +1,89 @@ +pandoc (2.2.3) + + * RST reader: improve parsing of inline interpreted text roles (#4811). + + + Use a Span with class "title-reference" for the default + title-reference role. + + Use `B.text` to split up contents into `Space`s, `SoftBreak`s, + and `Str`s for `title-reference`. + + Use Code with class "interpreted-text" instead of Span and Str for + unknown roles. (The RST writer has also been modified to round-trip + this properly.) + + Disallow blank lines in interpreted text. + + Backslash-escape now works in interpreted text. + + Backticks followed by alphanumerics no longer end interpreted text. + + Remove support for nested inlines (Francesco Occhipinti). + RST does not allow nested emphasis, links, or other inline + constructs. This fixes several bugs (#4581, #4561, #4792). + + * Org reader: fix parsers relying on `parseFromString` (#4784, Albert + Krewinkel). Emphasis was not parsed when it followed directly after + some block types (e.g., lists). + + * Markdown reader: Allow unquoted numbers and booleans as YAML mapping + keys. Previously in 2.2.2 you could not do + ``` + --- + 0: bar + ... + ``` + but only + ``` + --- + '0': bar + ... + ``` + With this change, both forms work. + + * DocBook reader: metadata handling improvements. + Now we properly parse title and subtitle elements that are direct + children of book and article (as well as children of bookinfo, + articleinfo, or info). We also now use the `subtitle` metadata + field for subtitles, rather than tacking the subtitle on to the + title. + + * RST writer: + + + Allow images to be directly nested within links (#4810, Francesco + Occhipinti). + + Use `titleblock` instead of `title` variable for title block (#4803, + Francesco Occhipinti). `titleblock` contains a properly formatted + title and subtitle (using top-level headers). `title` and + `subtitle` variables are still available and just contain the + title and subtitle text. Note that this change will require an + update to custom rst templates. + + Render Code with class "interpreted-text" as interpreted text role. + + * MediaWiki writer: Avoid extra blank line in tables with empty cells + (#4794). Note that the old output is semantically identical, but the + new output looks better. + + * Lua Utils module: add function `blocks_to_inlines` (#4799, Albert + Krewinkel). Exposes a function converting which flattenes a list of + blocks into a list of inlines. An example use case would be the + conversion of Note elements into other inlines. + + * RST template: use `titleblock` instead of `title`. Users of + custom RST templates will want to update this. + + * LaTeX template: Moved some beamer code in default.latex template. + This change allows beamer themes to change the template and font (as + Metropolis does) (#4450). + + * Better error message on `-t pdf -o out.pdf` (#1155, Mauro Bieg). + + * Added test case for #4669 to repository. + + * INSTALL.md: Fix broken link for cabal-install (#4806, ChanHoHo). + + * MANUAL.txt: + + + Add beamer info for slide backgrounds (#4802, John Muccigrosso). + + Clarify when `csquotes` is used in LaTeX writer (#4514). + + Add `commonmark` to list of output formats where `raw_tex` has an + effect (see #4527). + + pandoc (2.2.2.1) * Fix regression finding templates in user data directory (#4777). @@ -2609,6 +2695,11 @@ more consistent with other Markdown implementations, and with itself (since the two-space version of a line break doesn't work inside ATX headers, and neither version works inside Setext headers). + + + A space between the opening # and the header is now required for + pandoc and GitHub markdown (but not the other flavors). Disable + the `space_in_atx_header` extension (#3512) to restore the + original behavior. * Org reader (Albert Krewinkel, unless noted): diff --git a/data/templates/default.latex b/data/templates/default.latex --- a/data/templates/default.latex +++ b/data/templates/default.latex @@ -20,7 +20,42 @@ $for(beameroption)$ \setbeameroption{$beameroption$} $endfor$ +% Prevent slide breaks in the middle of a paragraph: +\widowpenalties 1 10000 +\raggedbottom +$if(section-titles)$ +\setbeamertemplate{part page}{ +\centering +\begin{beamercolorbox}[sep=16pt,center]{part title} + \usebeamerfont{part title}\insertpart\par +\end{beamercolorbox} +} +\setbeamertemplate{section page}{ +\centering +\begin{beamercolorbox}[sep=12pt,center]{part title} + \usebeamerfont{section title}\insertsection\par +\end{beamercolorbox} +} +\setbeamertemplate{subsection page}{ +\centering +\begin{beamercolorbox}[sep=8pt,center]{part title} + \usebeamerfont{subsection title}\insertsubsection\par +\end{beamercolorbox} +} +\AtBeginPart{ + \frame{\partpage} +} +\AtBeginSection{ + \ifbibliography + \else + \frame{\sectionpage} + \fi +} +\AtBeginSubsection{ + \frame{\subsectionpage} +} $endif$ +$endif$ $if(beamerarticle)$ \usepackage{beamerarticle} % needs to be loaded first $endif$ @@ -197,43 +232,6 @@ % 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} -$endif$ -$if(beamer)$ -% Prevent slide breaks in the middle of a paragraph: -\widowpenalties 1 10000 -\raggedbottom -$if(section-titles)$ -\setbeamertemplate{part page}{ -\centering -\begin{beamercolorbox}[sep=16pt,center]{part title} - \usebeamerfont{part title}\insertpart\par -\end{beamercolorbox} -} -\setbeamertemplate{section page}{ -\centering -\begin{beamercolorbox}[sep=12pt,center]{part title} - \usebeamerfont{section title}\insertsection\par -\end{beamercolorbox} -} -\setbeamertemplate{subsection page}{ -\centering -\begin{beamercolorbox}[sep=8pt,center]{part title} - \usebeamerfont{subsection title}\insertsubsection\par -\end{beamercolorbox} -} -\AtBeginPart{ - \frame{\partpage} -} -\AtBeginSection{ - \ifbibliography - \else - \frame{\sectionpage} - \fi -} -\AtBeginSubsection{ - \frame{\subsectionpage} -} -$endif$ $endif$ $if(links-as-notes)$ % Make links footnotes instead of hotlinks: diff --git a/data/templates/default.rst b/data/templates/default.rst --- a/data/templates/default.rst +++ b/data/templates/default.rst @@ -1,5 +1,5 @@ -$if(title)$ -$title$ +$if(titleblock)$ +$titleblock$ $endif$ $for(author)$ 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 "July 19, 2018" "pandoc 2.2.2.1" +.TH PANDOC 1 "August 5, 2018" "pandoc 2.2.3" .SH NAME pandoc - general markup converter .SH SYNOPSIS @@ -187,8 +187,9 @@ If the \f[C]mathspec\f[] variable is set, \f[C]xelatex\f[] will use \f[C]mathspec\f[] instead of \f[C]unicode\-math\f[]. The \f[C]upquote\f[] and \f[C]microtype\f[] packages are used if -available, and \f[C]csquotes\f[] will be used for typography if added to -the template or included in any header file. +available, and \f[C]csquotes\f[] will be used for typography if +\f[C]\\usepackage{csquotes}\f[] is present in the template or included +via \f[C]/H/\-\-include\-in\-header\f[]. The \f[C]natbib\f[], \f[C]biblatex\f[], \f[C]bibtex\f[], and \f[C]biber\f[] packages can optionally be used for citation rendering. .SS Reading from the Web @@ -2364,7 +2365,7 @@ .RE .TP .B output formats -\f[C]textile\f[] +\f[C]textile\f[], \f[C]commonmark\f[] .RS .RE .SS Extension: \f[C]native_divs\f[] @@ -5562,32 +5563,38 @@ \f[C]allowframebreaks\f[], \f[C]b\f[], \f[C]c\f[], \f[C]t\f[], \f[C]environment\f[], \f[C]label\f[], \f[C]plain\f[], \f[C]shrink\f[], \f[C]standout\f[], \f[C]noframenumbering\f[]. -.SS Background in reveal.js +.SS Background in reveal.js and beamer .PP -Background images can be added to self\-contained reveal.js slideshows. +Background images can be added to self\-contained reveal.js slideshows +and to beamer slideshows. .PP -For the same image on every slide, use the reveal.js configuration -option \f[C]parallaxBackgroundImage\f[] either in the YAML metadata -block or as a command\-line variable. +For the same image on every slide, use the configuration option +\f[C]background\-image\f[] either in the YAML metadata block or as a +command\-line variable. +(There are no other options in beamer and the rest of this section +concerns reveal.js slideshows.) +.PP +For reveal.js, you can instead use the reveal.js\-native option +\f[C]parallaxBackgroundImage\f[]. You can also set \f[C]parallaxBackgroundHorizontal\f[] and \f[C]parallaxBackgroundVertical\f[] the same way and must also set \f[C]parallaxBackgroundSize\f[] to have your values take effect. .PP -To set an image for a particular slide, add +To set an image for a particular reveal.js slide, add \f[C]{data\-background\-image="/path/to/image"}\f[] to the first slide\-level header 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. .PP -Other background settings also work on individual slides, including -\f[C]data\-background\-size\f[], \f[C]data\-background\-repeat\f[], -\f[C]data\-background\-color\f[], \f[C]data\-transition\f[], and -\f[C]data\-transition\-speed\f[]. +Other reveal.js background settings also work on individual slides, +including \f[C]data\-background\-size\f[], +\f[C]data\-background\-repeat\f[], \f[C]data\-background\-color\f[], +\f[C]data\-transition\f[], and \f[C]data\-transition\-speed\f[]. .PP See the reveal.js documentation for more details. .PP -For example: +For example in reveal.js: .IP .nf \f[C] diff --git a/pandoc.cabal b/pandoc.cabal --- a/pandoc.cabal +++ b/pandoc.cabal @@ -1,5 +1,5 @@ name: pandoc -version: 2.2.2.1 +version: 2.2.3 cabal-version: 2.0 build-type: Custom license: GPL-2 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 @@ -142,6 +142,13 @@ pdfEngines :: [String] pdfEngines = ordNub $ map snd engines +pdfIsNoWriterErrorMsg :: String +pdfIsNoWriterErrorMsg = + "To create a pdf using pandoc, use " ++ + "-t latex|beamer|context|ms|html5" ++ + "\nand specify an output file with " ++ + ".pdf extension (-o filename.pdf)." + pdfWriterAndProg :: Maybe String -- ^ user-specified writer name -> Maybe String -- ^ user-specified pdf-engine -> IO (String, Maybe String) -- ^ IO (writerName, maybePdfEngineProg) @@ -165,6 +172,7 @@ [] -> Left $ "pdf-engine " ++ eng ++ " not known" + engineForWriter "pdf" = Left pdfIsNoWriterErrorMsg engineForWriter w = case [e | (f,e) <- engines, f == baseWriterName w] of eng : _ -> Right eng [] -> Left $ @@ -233,11 +241,7 @@ else case getWriter (map toLower writerName) of Left e -> E.throwIO $ PandocAppError $ if format == "pdf" - then e ++ - "\nTo create a pdf using pandoc, use " ++ - "-t latex|beamer|context|ms|html5" ++ - "\nand specify an output file with " ++ - ".pdf extension (-o filename.pdf)." + then e ++ "\n" ++ pdfIsNoWriterErrorMsg else e Right (w, es) -> return (w :: Writer PandocIO, es) diff --git a/src/Text/Pandoc/Lua/Module/Utils.hs b/src/Text/Pandoc/Lua/Module/Utils.hs --- a/src/Text/Pandoc/Lua/Module/Utils.hs +++ b/src/Text/Pandoc/Lua/Module/Utils.hs @@ -42,6 +42,7 @@ import qualified Data.Digest.Pure.SHA as SHA import qualified Data.ByteString.Lazy as BSL import qualified Foreign.Lua as Lua +import qualified Text.Pandoc.Builder as B import qualified Text.Pandoc.Filter.JSON as JSONFilter import qualified Text.Pandoc.Shared as Shared @@ -49,6 +50,7 @@ pushModule :: Maybe FilePath -> Lua NumResults pushModule mbDatadir = do Lua.newtable + addFunction "blocks_to_inlines" blocksToInlines addFunction "hierarchicalize" hierarchicalize addFunction "normalize_date" normalizeDate addFunction "run_json_filter" (runJSONFilter mbDatadir) @@ -56,6 +58,14 @@ addFunction "stringify" stringify addFunction "to_roman_numeral" toRomanNumeral return 1 + +-- | Squashes a list of blocks into inlines. +blocksToInlines :: [Block] -> Lua.Optional [Inline] -> Lua [Inline] +blocksToInlines blks optSep = do + let sep = case Lua.fromOptional optSep of + Just x -> B.fromList x + Nothing -> Shared.defaultBlocksSeparator + return $ B.toList (Shared.blocksToInlinesWithSep sep blks) -- | Convert list of Pandoc blocks into (hierarchical) list of Elements. hierarchicalize :: [Block] -> Lua [Shared.Element] diff --git a/src/Text/Pandoc/Readers/DocBook.hs b/src/Text/Pandoc/Readers/DocBook.hs --- a/src/Text/Pandoc/Readers/DocBook.hs +++ b/src/Text/Pandoc/Readers/DocBook.hs @@ -537,7 +537,6 @@ data DBState = DBState{ dbSectionLevel :: Int , dbQuoteType :: QuoteType , dbMeta :: Meta - , dbAcceptsMeta :: Bool , dbBook :: Bool , dbFigureTitle :: Inlines , dbContent :: [Content] @@ -547,7 +546,6 @@ def = DBState{ dbSectionLevel = 0 , dbQuoteType = DoubleQuote , dbMeta = mempty - , dbAcceptsMeta = False , dbBook = False , dbFigureTitle = mempty , dbContent = [] } @@ -609,18 +607,26 @@ -- -acceptingMetadata :: PandocMonad m => DB m a -> DB m a -acceptingMetadata p = do - modify (\s -> s { dbAcceptsMeta = True } ) - res <- p - modify (\s -> s { dbAcceptsMeta = False }) - return res - -checkInMeta :: (PandocMonad m, Monoid a) => DB m () -> DB m a -checkInMeta p = do - accepts <- dbAcceptsMeta <$> get - when accepts p - return mempty +addMetadataFromElement :: PandocMonad m => Element -> DB m Blocks +addMetadataFromElement e = do + case filterChild (named "title") e of + Nothing -> return () + Just z -> do + getInlines z >>= addMeta "title" + addMetaField "subtitle" z + case filterChild (named "authorgroup") e of + Nothing -> return () + Just z -> addMetaField "author" z + addMetaField "subtitle" e + addMetaField "author" e + addMetaField "date" e + addMetaField "release" e + return mempty + where addMetaField fieldname elt = + case filterChildren (named fieldname) elt of + [] -> return () + [z] -> getInlines z >>= addMeta fieldname + zs -> mapM getInlines zs >>= addMeta fieldname addMeta :: PandocMonad m => ToMetaValue a => String -> a -> DB m () addMeta field val = modify (setMeta field val) @@ -718,11 +724,6 @@ "attribution" -> return mempty "titleabbrev" -> return mempty "authorinitials" -> return mempty - "title" -> checkInMeta getTitle - "author" -> checkInMeta getAuthor - "authorgroup" -> checkInMeta getAuthorGroup - "releaseinfo" -> checkInMeta (getInlines e >>= addMeta "release") - "date" -> checkInMeta getDate "bibliography" -> sect 0 "bibliodiv" -> sect 1 "biblioentry" -> parseMixed para (elContent e) @@ -788,8 +789,8 @@ "figure" -> getFigure e "mediaobject" -> para <$> getMediaobject e "caption" -> return mempty - "info" -> metaBlock - "articleinfo" -> metaBlock + "info" -> addMetadataFromElement e + "articleinfo" -> addMetadataFromElement e "sectioninfo" -> return mempty -- keywords & other metadata "refsectioninfo" -> return mempty -- keywords & other metadata "refsect1info" -> return mempty -- keywords & other metadata @@ -803,10 +804,11 @@ "chapterinfo" -> return mempty -- keywords & other metadata "glossaryinfo" -> return mempty -- keywords & other metadata "appendixinfo" -> return mempty -- keywords & other metadata - "bookinfo" -> metaBlock + "bookinfo" -> addMetadataFromElement e "article" -> modify (\st -> st{ dbBook = False }) >> - getBlocks e - "book" -> modify (\st -> st{ dbBook = True }) >> getBlocks e + addMetadataFromElement e >> getBlocks e + "book" -> modify (\st -> st{ dbBook = True }) >> + addMetadataFromElement e >> getBlocks e "table" -> parseTable "informaltable" -> parseTable "informalexample" -> divWith ("", ["informalexample"], []) <$> @@ -816,6 +818,8 @@ "screen" -> codeBlockWithLang "programlisting" -> codeBlockWithLang "?xml" -> return mempty + "title" -> return mempty -- handled in parent element + "subtitle" -> return mempty -- handled in parent element _ -> getBlocks e where parseMixed container conts = do let (ils,rest) = break isBlockElement conts @@ -857,19 +861,6 @@ terms' <- mapM getInlines terms items' <- mapM getBlocks items return (mconcat $ intersperse (str "; ") terms', items') - getTitle = do - tit <- getInlines e - subtit <- case filterChild (named "subtitle") e of - Just s -> (text ": " <>) <$> - getInlines s - Nothing -> return mempty - addMeta "title" (tit <> subtit) - - getAuthor = (:[]) <$> getInlines e >>= addMeta "author" - getAuthorGroup = do - let terms = filterChildren (named "author") e - mapM getInlines terms >>= addMeta "author" - getDate = getInlines e >>= addMeta "date" parseTable = do let isCaption x = named "title" x || named "caption" x caption <- case filterChild isCaption e of @@ -935,7 +926,6 @@ modify $ \st -> st{ dbSectionLevel = n - 1 } return $ headerWith (ident,[],[]) n' headerText <> b lineItems = mapM getInlines $ filterChildren (named "line") e - metaBlock = acceptingMetadata (getBlocks e) >> return mempty getInlines :: PandocMonad m => Element -> DB m Inlines getInlines e' = (trimInlines . mconcat) <$> 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 @@ -230,7 +230,6 @@ $ nullMeta updateState $ \st -> st{ stateMeta' = stateMeta' st <> meta' } - yamlMetaBlock :: PandocMonad m => MarkdownParser m (F Blocks) yamlMetaBlock = try $ do guardEnabled Ext_yaml_metadata_block @@ -242,29 +241,31 @@ -- by including --- and ..., we allow yaml blocks with just comments: let rawYaml = unlines ("---" : (rawYamlLines ++ ["..."])) optional blanklines - case YAML.decodeStrict (UTF8.fromString rawYaml) of - Right (YAML.Mapping _ hashmap : _) -> do + case YAML.decodeNode' YAML.failsafeSchemaResolver False False + (UTF8.fromStringLazy rawYaml) of + Right [YAML.Doc (YAML.Mapping _ hashmap)] -> do let alist = M.toList hashmap mapM_ (\(key, v) -> - case YAML.parseEither (YAML.parseYAML key) of - Left e -> fail e - Right k -> do - if ignorable k - then return () - else do - v' <- yamlToMeta v - let k' = T.unpack k - updateState $ \st -> st{ stateMeta' = - do m <- stateMeta' st - -- if there's already a value, leave it unchanged - case lookupMeta k' m of - Just _ -> return m - Nothing -> do - v'' <- v' - return $ B.setMeta (T.unpack k) v'' m} - ) alist + case key of + (YAML.Scalar (YAML.SStr t)) -> handleKey t v + (YAML.Scalar (YAML.SUnknown _ t)) -> handleKey t v + _ -> fail "Non-string key in YAML mapping") alist + where handleKey k v = + if ignorable k + then return () + else do + v' <- yamlToMeta v + let k' = T.unpack k + updateState $ \st -> st{ stateMeta' = + do m <- stateMeta' st + -- if there's already a value, leave it unchanged + case lookupMeta k' m of + Just _ -> return m + Nothing -> do + v'' <- v' + return $ B.setMeta (T.unpack k) v'' m} Right [] -> return () - Right (YAML.Scalar YAML.SNull:_) -> return () + Right [YAML.Doc (YAML.Scalar YAML.SNull)] -> return () Right _ -> do logMessage $ CouldNotParseYamlMetadata "not an object" @@ -303,11 +304,12 @@ => YAML.Node -> MarkdownParser m (F MetaValue) yamlToMeta (YAML.Scalar x) = case x of - YAML.SStr t -> toMetaValue t - YAML.SBool b -> return $ return $ MetaBool b - YAML.SFloat d -> return $ return $ MetaString (show d) - YAML.SInt i -> return $ return $ MetaString (show i) - _ -> return $ return $ MetaString "" + YAML.SStr t -> toMetaValue t + YAML.SBool b -> return $ return $ MetaBool b + YAML.SFloat d -> return $ return $ MetaString (show d) + YAML.SInt i -> return $ return $ MetaString (show i) + YAML.SUnknown _ t -> toMetaValue t + YAML.SNull -> return $ return $ MetaString "" yamlToMeta (YAML.Sequence _ xs) = do xs' <- mapM yamlToMeta xs return $ do diff --git a/src/Text/Pandoc/Readers/Org/Parsing.hs b/src/Text/Pandoc/Readers/Org/Parsing.hs --- a/src/Text/Pandoc/Readers/Org/Parsing.hs +++ b/src/Text/Pandoc/Readers/Org/Parsing.hs @@ -137,14 +137,13 @@ <* updateLastPreCharPos <* updateLastForbiddenCharPos --- The version Text.Pandoc.Parsing cannot be used, as we need additional parts --- of the state saved and restored. +-- | Like @'Text.Pandoc.Parsing'@, but resets the position of the last character +-- allowed before emphasised text. parseFromString :: Monad m => OrgParser m a -> String -> OrgParser m a parseFromString parser str' = do - oldLastPreCharPos <- orgStateLastPreCharPos <$> getState updateState $ \s -> s{ orgStateLastPreCharPos = Nothing } result <- P.parseFromString parser str' - updateState $ \s -> s{ orgStateLastPreCharPos = oldLastPreCharPos } + updateState $ \s -> s { orgStateLastPreCharPos = Nothing } return result -- | Skip one or more tab or space characters. diff --git a/src/Text/Pandoc/Readers/RST.hs b/src/Text/Pandoc/Readers/RST.hs --- a/src/Text/Pandoc/Readers/RST.hs +++ b/src/Text/Pandoc/Readers/RST.hs @@ -37,7 +37,7 @@ import Control.Monad (forM_, guard, liftM, mplus, mzero, when) import Control.Monad.Except (throwError) import Control.Monad.Identity (Identity (..)) -import Data.Char (isHexDigit, isSpace, toLower, toUpper) +import Data.Char (isHexDigit, isSpace, toLower, toUpper, isAlphaNum) import Data.List (deleteFirstsBy, elemIndex, intercalate, isInfixOf, isSuffixOf, nub, sort, transpose, union) import qualified Data.Map as M @@ -1313,20 +1313,25 @@ inline :: PandocMonad m => RSTParser m Inlines inline = choice [ note -- can start with whitespace, so try before ws - , whitespace , link - , str , endline , strong , emph , code , subst , interpretedRole - , smart - , hyphens - , escapedChar - , symbol ] "inline" + , inlineContent ] "inline" +-- strings, spaces and other characters that can appear either by +-- themselves or within inline markup +inlineContent :: PandocMonad m => RSTParser m Inlines +inlineContent = choice [ whitespace + , str + , smart + , hyphens + , escapedChar + , symbol ] "inline content" + parseInlineFromString :: PandocMonad m => String -> RSTParser m Inlines parseInlineFromString = parseFromString' (trimInlines . mconcat <$> many inline) @@ -1368,11 +1373,11 @@ emph :: PandocMonad m => RSTParser m Inlines emph = B.emph . trimInlines . mconcat <$> - enclosed (atStart $ char '*') (char '*') inline + enclosed (atStart $ char '*') (char '*') inlineContent strong :: PandocMonad m => RSTParser m Inlines strong = B.strong . trimInlines . mconcat <$> - enclosed (atStart $ string "**") (try $ string "**") inline + enclosed (atStart $ string "**") (try $ string "**") inlineContent -- Note, this doesn't precisely implement the complex rule in -- http://docutils.sourceforge.net/docs/ref/rst/restructuredtext.html#inline-markup-recognition-rules @@ -1380,7 +1385,6 @@ -- -- TODO: -- - Classes are silently discarded in addNewRole --- - Lacks sensible implementation for title-reference (which is the default) -- - Allows direct use of the :raw: role, rST only allows inherited use. interpretedRole :: PandocMonad m => RSTParser m Inlines interpretedRole = try $ do @@ -1390,12 +1394,12 @@ renderRole :: PandocMonad m => String -> Maybe String -> String -> Attr -> RSTParser m Inlines renderRole contents fmt role attr = case role of - "sup" -> return $ B.superscript $ B.str contents - "superscript" -> return $ B.superscript $ B.str contents - "sub" -> return $ B.subscript $ B.str contents - "subscript" -> return $ B.subscript $ B.str contents - "emphasis" -> return $ B.emph $ B.str contents - "strong" -> return $ B.strong $ B.str contents + "sup" -> return $ B.superscript $ treatAsText contents + "superscript" -> return $ B.superscript $ treatAsText contents + "sub" -> return $ B.subscript $ treatAsText contents + "subscript" -> return $ B.subscript $ treatAsText contents + "emphasis" -> return $ B.emph $ treatAsText contents + "strong" -> return $ B.strong $ treatAsText contents "rfc-reference" -> return $ rfcLink contents "RFC" -> return $ rfcLink contents "pep-reference" -> return $ pepLink contents @@ -1406,7 +1410,7 @@ "title" -> titleRef contents "t" -> titleRef contents "code" -> return $ B.codeWith (addClass "sourceCode" attr) contents - "span" -> return $ B.spanWith attr $ B.str contents + "span" -> return $ B.spanWith attr $ treatAsText contents "raw" -> return $ B.rawInline (fromMaybe "" fmt) contents custom -> do customRoles <- stateRstCustomRoles <$> getState @@ -1414,14 +1418,20 @@ Just (newRole, newFmt, newAttr) -> renderRole contents newFmt newRole newAttr Nothing -> -- undefined role - return $ B.spanWith ("",[],[("role",role)]) (B.str contents) + return $ B.codeWith ("",["interpreted-text"],[("role",role)]) + contents where - titleRef ref = return $ B.str ref -- FIXME: Not a sensible behaviour + titleRef ref = return $ B.spanWith ("",["title-ref"],[]) $ treatAsText ref rfcLink rfcNo = B.link rfcUrl ("RFC " ++ rfcNo) $ B.str ("RFC " ++ rfcNo) where rfcUrl = "http://www.faqs.org/rfcs/rfc" ++ rfcNo ++ ".html" pepLink pepNo = B.link pepUrl ("PEP " ++ pepNo) $ B.str ("PEP " ++ pepNo) where padNo = replicate (4 - length pepNo) '0' ++ pepNo pepUrl = "http://www.python.org/dev/peps/pep-" ++ padNo ++ "/" + treatAsText = B.text . handleEscapes + handleEscapes [] = [] + handleEscapes ('\\':' ':cs) = handleEscapes cs + handleEscapes ('\\':c:cs) = c : handleEscapes cs + handleEscapes (c:cs) = c : handleEscapes cs addClass :: String -> Attr -> Attr addClass c (ident, classes, keyValues) = (ident, classes `union` [c], keyValues) @@ -1445,7 +1455,18 @@ return (role,contents) unmarkedInterpretedText :: PandocMonad m => RSTParser m [Char] -unmarkedInterpretedText = enclosed (atStart $ char '`') (char '`') anyChar +unmarkedInterpretedText = try $ do + atStart (char '`') + contents <- mconcat <$> (many1 + ( many1 (noneOf "`\\\n") + <|> (char '\\' >> ((\c -> ['\\',c]) <$> noneOf "\n")) + <|> (string "\n" <* notFollowedBy blankline) + <|> try (string "`" <* + notFollowedBy (() <$ roleMarker) <* + lookAhead (satisfy isAlphaNum)) + )) + char '`' + return contents whitespace :: PandocMonad m => RSTParser m Inlines whitespace = B.space <$ skipMany1 spaceChar "whitespace" @@ -1480,7 +1501,7 @@ char '`' notFollowedBy (char '`') -- `` marks start of inline code label' <- trimInlines . mconcat <$> - manyTill (notFollowedBy (char '`') >> inline) (char '<') + manyTill (notFollowedBy (char '`') >> inlineContent) (char '<') src <- trim <$> manyTill (noneOf ">\n") (char '>') skipSpaces string "`_" diff --git a/src/Text/Pandoc/Shared.hs b/src/Text/Pandoc/Shared.hs --- a/src/Text/Pandoc/Shared.hs +++ b/src/Text/Pandoc/Shared.hs @@ -94,6 +94,8 @@ -- * for squashing blocks blocksToInlines, blocksToInlines', + blocksToInlinesWithSep, + defaultBlocksSeparator, -- * Safe read safeRead, -- * Temp directory @@ -757,11 +759,18 @@ mconcat . intersperse sep . map blockToInlines blocksToInlines' :: [Block] -> Inlines -blocksToInlines' = blocksToInlinesWithSep parSep - where parSep = B.space <> B.str "¶" <> B.space +blocksToInlines' = blocksToInlinesWithSep defaultBlocksSeparator blocksToInlines :: [Block] -> [Inline] blocksToInlines = B.toList . blocksToInlines' + +-- | Inline elements used to separate blocks when squashing blocks into +-- inlines. +defaultBlocksSeparator :: Inlines +defaultBlocksSeparator = + -- This is used in the pandoc.utils.blocks_to_inlines function. Docs + -- there should be updated if this is changed. + B.space <> B.str "¶" <> B.space -- 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 @@ -313,6 +313,7 @@ let sep = case bs of [Plain _] -> " " [Para _] -> " " + [] -> "" _ -> "\n" return $ marker ++ attr ++ sep ++ trimr contents diff --git a/src/Text/Pandoc/Writers/RST.hs b/src/Text/Pandoc/Writers/RST.hs --- a/src/Text/Pandoc/Writers/RST.hs +++ b/src/Text/Pandoc/Writers/RST.hs @@ -83,13 +83,14 @@ let render' :: Doc -> Text render' = render colwidth let subtit = case lookupMeta "subtitle" meta of - Just (MetaBlocks [Plain xs]) -> xs - _ -> [] + Just (MetaBlocks [Plain xs]) -> xs + Just (MetaInlines xs) -> xs + _ -> [] title <- titleToRST (docTitle meta) subtit metadata <- metaToJSON opts (fmap render' . blockListToRST) (fmap (stripEnd . render') . inlineListToRST) - $ B.deleteMeta "title" $ B.deleteMeta "subtitle" meta + meta body <- blockListToRST' True $ case writerTemplate opts of Just _ -> normalizeHeadings 1 blocks Nothing -> blocks @@ -105,7 +106,7 @@ $ defField "toc-depth" (show $ writerTOCDepth opts) $ defField "number-sections" (writerNumberSections opts) $ defField "math" hasMath - $ defField "title" (render Nothing title :: String) + $ defField "titleblock" (render Nothing title :: String) $ defField "math" hasMath $ defField "rawtex" rawTeX metadata case writerTemplate opts of @@ -472,6 +473,8 @@ -- them and they will be readable and parsable (Quoted _ _, _) -> keep f i (_, Quoted _ _) -> keep f i + -- inlineToRST handles this case properly so it's safe to keep + (Link _ _ _, Image _ _ _) -> keep f i -- parent inlines would prevent links from being correctly -- parsed, in this case we prioritise the content over the -- style @@ -571,15 +574,18 @@ else return $ "“" <> contents <> "”" inlineToRST (Cite _ lst) = writeInlines lst +inlineToRST (Code (_,["interpreted-text"],[("role",role)]) str) = do + return $ ":" <> text role <> ":`" <> text str <> "`" inlineToRST (Code _ str) = do opts <- gets stOptions -- we trim the string because the delimiters must adjoin a -- non-space character; see #3496 -- we use :literal: when the code contains backticks, since -- :literal: allows backslash-escapes; see #3974 - return $ if '`' `elem` str - then ":literal:`" <> text (escapeString opts (trim str)) <> "`" - else "``" <> text (trim str) <> "``" + return $ + if '`' `elem` str + then ":literal:`" <> text (escapeString opts (trim str)) <> "`" + else "``" <> text (trim str) <> "``" inlineToRST (Str str) = do opts <- gets stOptions return $ text $ diff --git a/test/Tests/Lua.hs b/test/Tests/Lua.hs --- a/test/Tests/Lua.hs +++ b/test/Tests/Lua.hs @@ -109,7 +109,8 @@ assertFilterConversion "pandoc.utils doesn't work as expected." "test-pandoc-utils.lua" (doc $ para "doesn't matter") - (doc $ mconcat [ plain (str "hierarchicalize: OK") + (doc $ mconcat [ plain (str "blocks_to_inlines: OK") + , plain (str "hierarchicalize: OK") , plain (str "normalize_date: OK") , plain (str "pipe: OK") , plain (str "failing pipe: OK") diff --git a/test/Tests/Readers/Org/Block/List.hs b/test/Tests/Readers/Org/Block/List.hs --- a/test/Tests/Readers/Org/Block/List.hs +++ b/test/Tests/Readers/Org/Block/List.hs @@ -243,4 +243,15 @@ mconcat [ para "CLOSED: [2015-10-19 Mon 15:03]" , bulletList [ plain "Note taken on [2015-10-19 Mon 13:24]" ] ] + + , "Markup after header and list" =: + T.unlines [ "* headline" + , "- list" + , "" + , "~variable name~" + ] =?> + mconcat [ headerWith ("headline", [], []) 1 "headline" + , bulletList [ plain "list" ] + , para (code "variable name") + ] ] diff --git a/test/Tests/Readers/RST.hs b/test/Tests/Readers/RST.hs --- a/test/Tests/Readers/RST.hs +++ b/test/Tests/Readers/RST.hs @@ -177,7 +177,7 @@ =: ".. role:: haskell(code)\n.. role:: lhs(haskell)\n\n:lhs:`text`" =?> para (codeWith ("", ["lhs", "haskell", "sourceCode"], []) "text") , "unknown role" =: ":unknown:`text`" =?> - para (spanWith ("",[],[("role","unknown")]) (str "text")) + para (codeWith ("",["interpreted-text"],[("role","unknown")]) "text") ] , testGroup "footnotes" [ "remove space before note" =: T.unlines @@ -187,5 +187,16 @@ , " bar" ] =?> para ("foo" <> note (para "bar")) + ] + , testGroup "inlines" + [ "links can contain an URI without being parsed twice (#4581)" =: + "`http://loc `__" =?> + para (link "http://loc" "" "http://loc") + , "inline markup cannot be nested" =: + "**a*b*c**" =?> + para (strong "a*b*c") + , "bare URI parsing disabled inside emphasis (#4561)" =: + "*http://location*" =?> + para (emph (text "http://location")) ] ] diff --git a/test/Tests/Writers/RST.hs b/test/Tests/Writers/RST.hs --- a/test/Tests/Writers/RST.hs +++ b/test/Tests/Writers/RST.hs @@ -16,6 +16,11 @@ => String -> (a, String) -> TestTree (=:) = test (purely (writeRST def . toPandoc)) +testTemplate :: (ToString a, ToString c, ToPandoc a) => + String -> String -> (a, c) -> TestTree +testTemplate t = + test (purely (writeRST def{ writerTemplate = Just t }) . toPandoc) + tests :: [TestTree] tests = [ testGroup "rubrics" [ "in list item" =: @@ -156,4 +161,7 @@ , "Header 2" , "--------"] ] + , testTemplate "$subtitle$\n" "subtitle" $ + (setMeta "subtitle" ("subtitle" :: Inlines) $ doc $ plain "") =?> + ("subtitle" :: String) ] diff --git a/test/command/3407.md b/test/command/3407.md --- a/test/command/3407.md +++ b/test/command/3407.md @@ -1,6 +1,6 @@ ``` % pandoc -f native -t rst -[Para [Span ("",[],[("role","foo")]) [Str "text"]]] +[Para [Code ("",["interpreted-text"],[("role","foo")]) "text"]] ^D :foo:`text` ``` @@ -9,5 +9,5 @@ % pandoc -f rst -t native :foo:`text` ^D -[Para [Span ("",[],[("role","foo")]) [Str "text"]]] +[Para [Code ("",["interpreted-text"],[("role","foo")]) "text"]] ``` diff --git a/test/command/4794.md b/test/command/4794.md new file mode 100644 --- /dev/null +++ b/test/command/4794.md @@ -0,0 +1,18 @@ +``` +% pandoc -f markdown -t mediawiki +| Column1 | Column2 | Column3 | +| ------- | ------- | ------- | +| text | | text | +^D +{| +! Column1 +! Column2 +! Column3 +|- +| text +| +| text +|} + + +``` diff --git a/test/command/4811.md b/test/command/4811.md new file mode 100644 --- /dev/null +++ b/test/command/4811.md @@ -0,0 +1,48 @@ +No blank lines in inline interpreted roles: + +``` +% pandoc -f rst -t native +`no + +blank`:myrole: +^D +[Para [Str "`no"] +,Para [Str "blank`:myrole:"]] +``` + +Backslash escape behaves properly in interpreted roles: + +``` +% pandoc -f rst -t native +`hi\ there`:sup: + +`hi\ there`:code: +^D +[Para [Superscript [Str "hithere"]] +,Para [Code ("",["sourceCode"],[]) "hi\\ there"]] +``` + +Backtick followed by alphanumeric doesn't end the span: +``` +% pandoc -f rst -t native +`hi`there`:myrole: +^D +[Para [Code ("",["interpreted-text"],[("role","myrole")]) "hi`there"]] +``` + +Newline is okay, as long as not blank: +``` +% pandoc -f rst -t native +`hi +there`:myrole: +^D +[Para [Code ("",["interpreted-text"],[("role","myrole")]) "hi\nthere"]] +``` + +Use span for title-reference: +``` +% pandoc -f rst -t native +`default` +^D +[Para [Span ("",["title-ref"],[]) [Str "default"]]] +``` diff --git a/test/docbook-xref.native b/test/docbook-xref.native --- a/test/docbook-xref.native +++ b/test/docbook-xref.native @@ -1,4 +1,4 @@ -Pandoc (Meta {unMeta = fromList []}) +Pandoc (Meta {unMeta = fromList [("title",MetaInlines [Str "An",Space,Str "Example",Space,Str "Book"])]}) [Header 1 ("ch01",[],[]) [Str "XRef",Space,Str "Samples"] ,Para [Str "This",Space,Str "paragraph",Space,Str "demonstrates",Space,Str "several",Space,Str "features",Space,Str "of",SoftBreak,Str "XRef."] ,BulletList diff --git a/test/lua/test-pandoc-utils.lua b/test/lua/test-pandoc-utils.lua --- a/test/lua/test-pandoc-utils.lua +++ b/test/lua/test-pandoc-utils.lua @@ -1,5 +1,19 @@ utils = require 'pandoc.utils' +-- Squash blocks to inlines +------------------------------------------------------------------------ +function test_blocks_to_inlines () + local blocks = { + pandoc.Para{ pandoc.Str 'Paragraph1' }, + pandoc.Para{ pandoc.Emph 'Paragraph2' } + } + local inlines = utils.blocks_to_inlines(blocks, {pandoc.LineBreak()}) + return #inlines == 3 + and inlines[1].text == "Paragraph1" + and inlines[2].t == 'LineBreak' + and inlines[3].content[1].text == "Paragraph2" +end + -- hierarchicalize ------------------------------------------------------------------------ function test_hierarchicalize () @@ -110,6 +124,7 @@ function Para (el) return { + pandoc.Plain{pandoc.Str("blocks_to_inlines: " .. run(test_blocks_to_inlines))}, pandoc.Plain{pandoc.Str("hierarchicalize: " .. run(test_hierarchicalize))}, pandoc.Plain{pandoc.Str("normalize_date: " .. run(test_normalize_date))}, pandoc.Plain{pandoc.Str("pipe: " .. run(test_pipe))}, diff --git a/test/rst-reader.native b/test/rst-reader.native --- a/test/rst-reader.native +++ b/test/rst-reader.native @@ -326,7 +326,7 @@ ,Para [Math DisplayMath "\\alpha = beta",Math DisplayMath "E = mc^2"] ,Para [Str "Some",Space,Superscript [Str "of"],Space,Str "these",Space,Superscript [Str "words"],Space,Str "are",Space,Str "in",Space,Superscript [Str "superscript"],Str "."] ,Para [Str "Reset",Space,Str "default-role",Space,Str "to",Space,Str "the",Space,Str "default",Space,Str "default."] -,Para [Str "And",Space,Str "now",Space,Str "some-invalid-string-3231231",Space,Str "is",Space,Str "nonsense."] +,Para [Str "And",Space,Str "now",Space,Span ("",["title-ref"],[]) [Str "some-invalid-string-3231231"],Space,Str "is",Space,Str "nonsense."] ,Para [Str "And",Space,Str "now",Space,Str "with",Space,RawInline (Format "html") "inline HTML",Str "."] ,Para [Str "And",Space,Str "some",Space,Str "inline",Space,Str "haskell",Space,Code ("",["haskell","sourceCode"],[]) "fmap id [1,2..10]",Str "."] ,Para [Str "Indirect",Space,Str "python",Space,Str "role",Space,Code ("",["py","python","indirect","sourceCode"],[]) "[x*x for x in [1,2,3,4,5]]",Str "."]