From 56f56e5e1594ef5d18326d1eb6de3176db307c6a Mon Sep 17 00:00:00 2001 From: Merijn Verstraaten Date: Sat, 7 Sep 2013 18:58:16 +0100 Subject: Added support for LaTeX style literate Haskell code blocks in rST. --- src/Text/Pandoc/Readers/RST.hs | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/RST.hs b/src/Text/Pandoc/Readers/RST.hs index 32893128a..c12a1493a 100644 --- a/src/Text/Pandoc/Readers/RST.hs +++ b/src/Text/Pandoc/Readers/RST.hs @@ -347,14 +347,25 @@ lhsCodeBlock = try $ do getPosition >>= guard . (==1) . sourceColumn guardEnabled Ext_literate_haskell optional codeBlockStart - lns <- many1 birdTrackLine - -- if (as is normal) there is always a space after >, drop it - let lns' = if all (\ln -> null ln || take 1 ln == " ") lns - then map (drop 1) lns - else lns + lns <- latexCodeBlock <|> birdCodeBlock blanklines return $ B.codeBlockWith ("", ["sourceCode", "literate", "haskell"], []) - $ intercalate "\n" lns' + $ intercalate "\n" lns + +latexCodeBlock :: Parser [Char] st [[Char]] +latexCodeBlock = try $ do + try (latexBlockLine "\\begin{code}") + many1Till anyLine (try $ latexBlockLine "\\end{code}") + where + latexBlockLine s = skipMany spaceChar >> string s >> blankline + +birdCodeBlock :: Parser [Char] st [[Char]] +birdCodeBlock = filterSpace <$> many1 birdTrackLine + where filterSpace lns = + -- if (as is normal) there is always a space after >, drop it + if all (\ln -> null ln || take 1 ln == " ") lns + then map (drop 1) lns + else lns birdTrackLine :: Parser [Char] st [Char] birdTrackLine = char '>' >> anyLine -- cgit v1.2.3 From 01fed75b8f755bf4de3d4ec2b720e4dd9e66951a Mon Sep 17 00:00:00 2001 From: MinRK Date: Thu, 7 Nov 2013 22:25:44 -0800 Subject: recognize svg tag in HTML Reader avoids adding lots of `

` tags in embedded SVG content, for instance in markdown to HTML. --- src/Text/Pandoc/Readers/HTML.hs | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs index 80279bf61..d691c9878 100644 --- a/src/Text/Pandoc/Readers/HTML.hs +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -557,7 +557,7 @@ blockHtmlTags = ["address", "article", "aside", "blockquote", "body", "button", "noframes", "noscript", "object", "ol", "output", "p", "pre", "progress", "section", "table", "tbody", "textarea", "thead", "tfoot", "ul", "dd", "dt", "frameset", "li", "tbody", "td", "tfoot", - "th", "thead", "tr", "script", "style", "video"] + "th", "thead", "tr", "script", "style", "svg", "video"] -- We want to allow raw docbook in markdown documents, so we -- include docbook block tags here too. -- cgit v1.2.3 From 0fd2176e29bd1118d314c6179455fb78bed35aea Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Sun, 17 Nov 2013 08:47:14 -0800 Subject: MediaWiki reader: Add automatic header identifiers. --- src/Text/Pandoc/Readers/MediaWiki.hs | 22 ++++++++++++-- tests/mediawiki-reader.native | 58 ++++++++++++++++++------------------ 2 files changed, 49 insertions(+), 31 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/MediaWiki.hs b/src/Text/Pandoc/Readers/MediaWiki.hs index 136701bd0..1c074e3de 100644 --- a/src/Text/Pandoc/Readers/MediaWiki.hs +++ b/src/Text/Pandoc/Readers/MediaWiki.hs @@ -1,4 +1,5 @@ -{-# LANGUAGE RelaxedPolyRec #-} -- needed for inlinesBetween on GHC < 7 +{-# LANGUAGE RelaxedPolyRec, FlexibleInstances, TypeSynonymInstances #-} +-- RelaxedPolyRec needed for inlinesBetween on GHC < 7 {- Copyright (C) 2012 John MacFarlane @@ -51,6 +52,7 @@ import Data.List (intersperse, intercalate, isPrefixOf ) import Text.HTML.TagSoup import Data.Sequence (viewl, ViewL(..), (<|)) import qualified Data.Foldable as F +import qualified Data.Map as M import Data.Char (isDigit, isSpace) -- | Read mediawiki from an input string and return a Pandoc document. @@ -62,6 +64,8 @@ readMediaWiki opts s = , mwMaxNestingLevel = 4 , mwNextLinkNumber = 1 , mwCategoryLinks = [] + , mwHeaderMap = M.empty + , mwIdentifierList = [] } "source" (s ++ "\n") of Left err' -> error $ "\nError:\n" ++ show err' @@ -71,10 +75,23 @@ data MWState = MWState { mwOptions :: ReaderOptions , mwMaxNestingLevel :: Int , mwNextLinkNumber :: Int , mwCategoryLinks :: [Inlines] + , mwHeaderMap :: M.Map Inlines String + , mwIdentifierList :: [String] } type MWParser = Parser [Char] MWState +instance HasReaderOptions MWParser where + askReaderOption f = (f . mwOptions) `fmap` getState + +instance HasHeaderMap MWParser where + getHeaderMap = fmap mwHeaderMap getState + putHeaderMap hm = updateState $ \st -> st{ mwHeaderMap = hm } + +instance HasIdentifierList MWParser where + getIdentifierList = fmap mwIdentifierList getState + putIdentifierList l = updateState $ \st -> st{ mwIdentifierList = l } + -- -- auxiliary functions -- @@ -351,7 +368,8 @@ header = try $ do let lev = length eqs guard $ lev <= 6 contents <- trimInlines . mconcat <$> manyTill inline (count lev $ char '=') - return $ B.header lev contents + attr <- registerHeader nullAttr contents + return $ B.headerWith attr lev contents bulletList :: MWParser Blocks bulletList = B.bulletList <$> diff --git a/tests/mediawiki-reader.native b/tests/mediawiki-reader.native index 0ab51a3aa..238413445 100644 --- a/tests/mediawiki-reader.native +++ b/tests/mediawiki-reader.native @@ -1,39 +1,39 @@ Pandoc (Meta {unMeta = fromList []}) -[Header 1 ("",[],[]) [Str "header"] -,Header 2 ("",[],[]) [Str "header",Space,Str "level",Space,Str "two"] -,Header 3 ("",[],[]) [Str "header",Space,Str "level",Space,Str "3"] -,Header 4 ("",[],[]) [Str "header",Space,Emph [Str "level"],Space,Str "four"] -,Header 5 ("",[],[]) [Str "header",Space,Str "level",Space,Str "5"] -,Header 6 ("",[],[]) [Str "header",Space,Str "level",Space,Str "6"] +[Header 1 ("header",[],[]) [Str "header"] +,Header 2 ("header-level-two",[],[]) [Str "header",Space,Str "level",Space,Str "two"] +,Header 3 ("header-level-3",[],[]) [Str "header",Space,Str "level",Space,Str "3"] +,Header 4 ("header-level-four",[],[]) [Str "header",Space,Emph [Str "level"],Space,Str "four"] +,Header 5 ("header-level-5",[],[]) [Str "header",Space,Str "level",Space,Str "5"] +,Header 6 ("header-level-6",[],[]) [Str "header",Space,Str "level",Space,Str "6"] ,Para [Str "=======",Space,Str "not",Space,Str "a",Space,Str "header",Space,Str "========"] ,Para [Code ("",[],[]) "==\160not\160a\160header\160=="] -,Header 2 ("",[],[]) [Str "emph",Space,Str "and",Space,Str "strong"] +,Header 2 ("emph-and-strong",[],[]) [Str "emph",Space,Str "and",Space,Str "strong"] ,Para [Emph [Str "emph"],Space,Strong [Str "strong"]] ,Para [Strong [Emph [Str "strong",Space,Str "and",Space,Str "emph"]]] ,Para [Strong [Emph [Str "emph",Space,Str "inside"],Space,Str "strong"]] ,Para [Strong [Str "strong",Space,Str "with",Space,Emph [Str "emph"]]] ,Para [Emph [Strong [Str "strong",Space,Str "inside"],Space,Str "emph"]] -,Header 2 ("",[],[]) [Str "horizontal",Space,Str "rule"] +,Header 2 ("horizontal-rule",[],[]) [Str "horizontal",Space,Str "rule"] ,Para [Str "top"] ,HorizontalRule ,Para [Str "bottom"] ,HorizontalRule -,Header 2 ("",[],[]) [Str "nowiki"] +,Header 2 ("nowiki",[],[]) [Str "nowiki"] ,Para [Str "''not",Space,Str "emph''"] -,Header 2 ("",[],[]) [Str "strikeout"] +,Header 2 ("strikeout",[],[]) [Str "strikeout"] ,Para [Strikeout [Str "This",Space,Str "is",Space,Emph [Str "struck",Space,Str "out"]]] -,Header 2 ("",[],[]) [Str "entities"] +,Header 2 ("entities",[],[]) [Str "entities"] ,Para [Str "hi",Space,Str "&",Space,Str "low"] ,Para [Str "hi",Space,Str "&",Space,Str "low"] ,Para [Str "G\246del"] ,Para [Str "\777\2730"] -,Header 2 ("",[],[]) [Str "comments"] +,Header 2 ("comments",[],[]) [Str "comments"] ,Para [Str "inline",Space,Str "comment"] ,Para [Str "between",Space,Str "blocks"] -,Header 2 ("",[],[]) [Str "linebreaks"] +,Header 2 ("linebreaks",[],[]) [Str "linebreaks"] ,Para [Str "hi",LineBreak,Str "there"] ,Para [Str "hi",LineBreak,Str "there"] -,Header 2 ("",[],[]) [Str ":",Space,Str "indents"] +,Header 2 ("indents",[],[]) [Str ":",Space,Str "indents"] ,Para [Str "hi"] ,DefinitionList [([], @@ -46,36 +46,36 @@ Pandoc (Meta {unMeta = fromList []}) [([], [[Plain [Str "there"]]])]]])] ,Para [Str "bud"] -,Header 2 ("",[],[]) [Str "p",Space,Str "tags"] +,Header 2 ("p-tags",[],[]) [Str "p",Space,Str "tags"] ,Para [Str "hi",Space,Str "there"] ,Para [Str "bud"] ,Para [Str "another"] -,Header 2 ("",[],[]) [Str "raw",Space,Str "html"] +,Header 2 ("raw-html",[],[]) [Str "raw",Space,Str "html"] ,Para [Str "hi",Space,RawInline (Format "html") "",Emph [Str "there"],RawInline (Format "html") "",Str "."] ,Para [RawInline (Format "html") "",Str "inserted",RawInline (Format "html") ""] ,RawBlock (Format "html") "

" ,Para [Str "hi",Space,Emph [Str "there"]] ,RawBlock (Format "html") "
" -,Header 2 ("",[],[]) [Str "sup,",Space,Str "sub,",Space,Str "del"] +,Header 2 ("sup-sub-del",[],[]) [Str "sup,",Space,Str "sub,",Space,Str "del"] ,Para [Str "H",Subscript [Str "2"],Str "O",Space,Str "base",Superscript [Emph [Str "exponent"]],Space,Strikeout [Str "hello"]] -,Header 2 ("",[],[]) [Str "inline",Space,Str "code"] +,Header 2 ("inline-code",[],[]) [Str "inline",Space,Str "code"] ,Para [Code ("",[],[]) "*\8594*",Space,Code ("",[],[]) "typed",Space,Code ("",["haskell"],[]) ">>="] -,Header 2 ("",[],[]) [Str "code",Space,Str "blocks"] +,Header 2 ("code-blocks",[],[]) [Str "code",Space,Str "blocks"] ,CodeBlock ("",[],[]) "case xs of\n (_:_) -> reverse xs\n [] -> ['*']" ,CodeBlock ("",["haskell"],[]) "case xs of\n (_:_) -> reverse xs\n [] -> ['*']" ,CodeBlock ("",["ruby","numberLines"],[("startFrom","100")]) "widgets.each do |w|\n print w.price\nend" -,Header 2 ("",[],[]) [Str "block",Space,Str "quotes"] +,Header 2 ("block-quotes",[],[]) [Str "block",Space,Str "quotes"] ,Para [Str "Regular",Space,Str "paragraph"] ,BlockQuote [Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "block",Space,Str "quote."] ,Para [Str "With",Space,Str "two",Space,Str "paragraphs."]] ,Para [Str "Nother",Space,Str "paragraph."] -,Header 2 ("",[],[]) [Str "external",Space,Str "links"] +,Header 2 ("external-links",[],[]) [Str "external",Space,Str "links"] ,Para [Link [Emph [Str "Google"],Space,Str "search",Space,Str "engine"] ("http://google.com","")] ,Para [Link [Str "http://johnmacfarlane.net/pandoc/"] ("http://johnmacfarlane.net/pandoc/","")] ,Para [Link [Str "1"] ("http://google.com",""),Space,Link [Str "2"] ("http://yahoo.com","")] ,Para [Link [Str "email",Space,Str "me"] ("mailto:info@example.org","")] -,Header 2 ("",[],[]) [Str "internal",Space,Str "links"] +,Header 2 ("internal-links",[],[]) [Str "internal",Space,Str "links"] ,Para [Link [Str "Help"] ("Help","wikilink")] ,Para [Link [Str "the",Space,Str "help",Space,Str "page"] ("Help","wikilink")] ,Para [Link [Str "Helpers"] ("Help","wikilink")] @@ -83,12 +83,12 @@ Pandoc (Meta {unMeta = fromList []}) ,Para [Link [Str "Contents"] ("Help:Contents","wikilink")] ,Para [Link [Str "#My",Space,Str "anchor"] ("#My_anchor","wikilink")] ,Para [Link [Str "and",Space,Str "text"] ("Page#with_anchor","wikilink")] -,Header 2 ("",[],[]) [Str "images"] +,Header 2 ("images",[],[]) [Str "images"] ,Para [Image [Str "caption"] ("example.jpg","fig:caption")] ,Para [Image [Str "the",Space,Emph [Str "caption"],Space,Str "with",Space,Link [Str "external",Space,Str "link"] ("http://google.com","")] ("example.jpg","fig:the caption with external link")] ,Para [Image [Str "caption"] ("example.jpg","fig:caption")] ,Para [Image [Str "example.jpg"] ("example.jpg","fig:example.jpg")] -,Header 2 ("",[],[]) [Str "lists"] +,Header 2 ("lists",[],[]) [Str "lists"] ,BulletList [[Plain [Str "Start",Space,Str "each",Space,Str "line"]] ,[Plain [Str "with",Space,Str "an",Space,Str "asterisk",Space,Str "(*)."] @@ -161,10 +161,10 @@ Pandoc (Meta {unMeta = fromList []}) [[Plain [Str "Amsterdam"]] ,[Plain [Str "Rotterdam"]] ,[Plain [Str "The",Space,Str "Hague"]]] -,Header 2 ("",[],[]) [Str "math"] +,Header 2 ("math",[],[]) [Str "math"] ,Para [Str "Here",Space,Str "is",Space,Str "some",Space,Math InlineMath "x=\\frac{y^\\pi}{z}",Str "."] ,Para [Str "With",Space,Str "spaces:",Space,Math InlineMath "x=\\frac{y^\\pi}{z}",Str "."] -,Header 2 ("",[],[]) [Str "preformatted",Space,Str "blocks"] +,Header 2 ("preformatted-blocks",[],[]) [Str "preformatted",Space,Str "blocks"] ,Para [Code ("",[],[]) "Start\160each\160line\160with\160a\160space.",LineBreak,Code ("",[],[]) "Text\160is\160",Strong [Code ("",[],[]) "preformatted"],Code ("",[],[]) "\160and",LineBreak,Emph [Code ("",[],[]) "markups"],Code ("",[],[]) "\160",Strong [Emph [Code ("",[],[]) "can"]],Code ("",[],[]) "\160be\160done."] ,Para [Code ("",[],[]) "\160hell\160\160\160\160\160\160yeah"] ,Para [Code ("",[],[]) "Start\160with\160a\160space\160in\160the\160first\160column,",LineBreak,Code ("",[],[]) "(before\160the\160).",LineBreak,Code ("",[],[]) "",LineBreak,Code ("",[],[]) "Then\160your\160block\160format\160will\160be",LineBreak,Code ("",[],[]) "\160\160\160\160maintained.",LineBreak,Code ("",[],[]) "",LineBreak,Code ("",[],[]) "This\160is\160good\160for\160copying\160in\160code\160blocks:",LineBreak,Code ("",[],[]) "",LineBreak,Code ("",[],[]) "def\160function():",LineBreak,Code ("",[],[]) "\160\160\160\160\"\"\"documentation\160string\"\"\"",LineBreak,Code ("",[],[]) "",LineBreak,Code ("",[],[]) "\160\160\160\160if\160True:",LineBreak,Code ("",[],[]) "\160\160\160\160\160\160\160\160print\160True",LineBreak,Code ("",[],[]) "\160\160\160\160else:",LineBreak,Code ("",[],[]) "\160\160\160\160\160\160\160\160print\160False"] @@ -174,12 +174,12 @@ Pandoc (Meta {unMeta = fromList []}) ,Para [Str "Don't",Space,Str "need"] ,Para [Code ("",[],[]) "a\160blank\160line"] ,Para [Str "around",Space,Str "a",Space,Str "preformatted",Space,Str "block."] -,Header 2 ("",[],[]) [Str "templates"] +,Header 2 ("templates",[],[]) [Str "templates"] ,RawBlock (Format "mediawiki") "{{Welcome}}" ,RawBlock (Format "mediawiki") "{{Foo:Bar}}" ,RawBlock (Format "mediawiki") "{{Thankyou|all your effort|Me}}" ,Para [Str "Written",Space,RawInline (Format "mediawiki") "{{{date}}}",Space,Str "by",Space,RawInline (Format "mediawiki") "{{{name}}}",Str "."] -,Header 2 ("",[],[]) [Str "tables"] +,Header 2 ("tables",[],[]) [Str "tables"] ,Table [] [AlignDefault,AlignDefault] [0.0,0.0] [[] ,[]] @@ -245,6 +245,6 @@ Pandoc (Meta {unMeta = fromList []}) [[]] [[[Para [Str "Orange"]]]] ,Para [Str "Paragraph",Space,Str "after",Space,Str "the",Space,Str "table."] -,Header 2 ("",[],[]) [Str "notes"] +,Header 2 ("notes",[],[]) [Str "notes"] ,Para [Str "My",Space,Str "note!",Note [Plain [Str "This."]]] ,Para [Str "URL",Space,Str "note.",Note [Plain [Link [Str "http://docs.python.org/library/functions.html#range"] ("http://docs.python.org/library/functions.html#range","")]]]] -- cgit v1.2.3 From e690c87dc4c3ff79689d9a887a9b5e3bffbb5d37 Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Sun, 17 Nov 2013 09:07:25 -0800 Subject: LaTeX reader: Support `\textnormal` as span with class "nodecor". This is needed for pandoc-citeproc. --- src/Text/Pandoc/Readers/LaTeX.hs | 1 + 1 file changed, 1 insertion(+) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs index 681dcb077..689b12c8e 100644 --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -373,6 +373,7 @@ inlineCommands = M.fromList $ , ("backslash", lit "\\") , ("slash", lit "/") , ("textbf", strong <$> tok) + , ("textnormal", spanWith ("",["nodecor"],[]) <$> tok) , ("ldots", lit "…") , ("dots", lit "…") , ("mdots", lit "…") -- cgit v1.2.3 From a3eba6ee848497f98f72aef5dad112c49bdd4fec Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Mon, 18 Nov 2013 20:28:27 -0800 Subject: LaTeX reader: Parse contents of curly quotes or matched `"` as quotes. --- src/Text/Pandoc/Readers/LaTeX.hs | 24 +++++++++++++++++------- tests/latex-reader.native | 2 +- 2 files changed, 18 insertions(+), 8 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs index 689b12c8e..75e29ebb9 100644 --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -163,13 +163,23 @@ mathChars = concat <$> <|> (\c -> ['\\',c]) <$> (try $ char '\\' *> anyChar) ) +quoted' :: (Inlines -> Inlines) -> LP String -> LP () -> LP Inlines +quoted' f starter ender = do + startchs <- starter + try ((f . mconcat) <$> manyTill inline ender) <|> lit startchs + double_quote :: LP Inlines -double_quote = (doubleQuoted . mconcat) <$> - (try $ string "``" *> manyTill inline (try $ string "''")) +double_quote = + ( quoted' doubleQuoted (try $ string "``") (void $ try $ string "''") + <|> quoted' doubleQuoted (string "“") (void $ char '”') + <|> quoted' doubleQuoted (string "\"") (void $ char '"') + ) single_quote :: LP Inlines -single_quote = (singleQuoted . mconcat) <$> - (try $ char '`' *> manyTill inline (try $ char '\'' >> notFollowedBy letter)) +single_quote = + ( quoted' singleQuoted (string "`") (try $ char '\'' >> notFollowedBy letter) + <|> quoted' singleQuoted (string "‘") (try $ char '’' >> notFollowedBy letter) + ) inline :: LP Inlines inline = (mempty <$ comment) @@ -181,10 +191,10 @@ inline = (mempty <$ comment) ((char '-') *> option (str "–") (str "—" <$ char '-'))) <|> double_quote <|> single_quote - <|> (str "“" <$ try (string "``")) -- nb. {``} won't be caught by double_quote <|> (str "”" <$ try (string "''")) - <|> (str "‘" <$ char '`') -- nb. {`} won't be caught by single_quote + <|> (str "”" <$ char '”') <|> (str "’" <$ char '\'') + <|> (str "’" <$ char '’') <|> (str "\160" <$ char '~') <|> (mathDisplay $ string "$$" *> mathChars <* string "$$") <|> (mathInline $ char '$' *> mathChars <* char '$') @@ -755,7 +765,7 @@ inlineText :: LP Inlines inlineText = str <$> many1 inlineChar inlineChar :: LP Char -inlineChar = noneOf "\\$%^_&~#{}^'`-[] \t\n" +inlineChar = noneOf "\\$%^_&~#{}^'`\"‘’“”-[] \t\n" environment :: LP Blocks environment = do diff --git a/tests/latex-reader.native b/tests/latex-reader.native index 15b667b2f..fcc3153cf 100644 --- a/tests/latex-reader.native +++ b/tests/latex-reader.native @@ -302,7 +302,7 @@ Pandoc (Meta {unMeta = fromList [("authors",MetaList [MetaInlines [Str "John",Sp ,Para [Str "4",Space,Str "<",Space,Str "5."] ,Para [Str "6",Space,Str ">",Space,Str "5."] ,Para [Str "Backslash:",Space,Str "\\"] -,Para [Str "Backtick:",Space,Str "\8216"] +,Para [Str "Backtick:",Space,Str "`"] ,Para [Str "Asterisk:",Space,Str "*"] ,Para [Str "Underscore:",Space,Str "_"] ,Para [Str "Left",Space,Str "brace:",Space,Str "{"] -- cgit v1.2.3 From cf149fcf38d98b1bee79ecd9056fa0f46264e7ce Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Fri, 22 Nov 2013 19:41:08 -0800 Subject: Fixed bug with intraword emphasis. Closes #1066. --- src/Text/Pandoc/Readers/Markdown.hs | 3 ++- tests/Tests/Readers/Markdown.hs | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index ea49d8c1d..33d1a9620 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -1455,6 +1455,7 @@ enclosure c = do -- Parse inlines til you hit one c or a sequence of two cs. -- If one c, emit emph and then parse two. -- If two cs, emit strong and then parse one. +-- Otherwise, emit ccc then the results. three :: Char -> MarkdownParser (F Inlines) three c = do contents <- mconcat <$> many (notFollowedBy (char c) >> inline) @@ -1479,7 +1480,7 @@ one c prefix' = do contents <- mconcat <$> many ( (notFollowedBy (char c) >> inline) <|> try (string [c,c] >> notFollowedBy (char c) >> - two c prefix') ) + two c mempty) ) (char c >> return (B.emph <$> (prefix' <> contents))) <|> return (return (B.str [c]) <> (prefix' <> contents)) diff --git a/tests/Tests/Readers/Markdown.hs b/tests/Tests/Readers/Markdown.hs index ccca147ab..b04ff9a0d 100644 --- a/tests/Tests/Readers/Markdown.hs +++ b/tests/Tests/Readers/Markdown.hs @@ -136,6 +136,11 @@ tests = [ testGroup "inline code" "`*` {.haskell .special x=\"7\"}" =?> para (codeWith ("",["haskell","special"],[("x","7")]) "*") ] + , testGroup "emph and strong" + [ "two strongs in emph" =: + "***a**b **c**d*" =?> para (emph (strong (str "a") <> str "b" <> space + <> strong (str "c") <> str "d")) + ] , testGroup "raw LaTeX" [ "in URL" =: "\\begin\n" =?> para (text "\\begin") -- cgit v1.2.3 From 5314df51f368853f7ee4bf8f75eedf43afc0400e Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Wed, 4 Dec 2013 10:00:40 -0800 Subject: Stop parsing "list lines" when we hit a block tag. This fixes exponential slowdown in certain input, e.g. a series of lists followed by ``. --- src/Text/Pandoc/Readers/Markdown.hs | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index 33d1a9620..4cb75d86c 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -732,7 +732,8 @@ listLine = try $ do notFollowedBy' (do indentSpaces many (spaceChar) listStart) - chunks <- manyTill (liftM snd (htmlTag isCommentTag) <|> count 1 anyChar) newline + chunks <- manyTill (liftM snd (htmlTag isCommentTag) <|> count 1 (satisfy (/='<')) + <|> (notFollowedBy' (htmlTag isBlockTag) >> count 1 anyChar)) newline return $ concat chunks -- parse raw text for one list item, excluding start marker and continuations @@ -759,6 +760,7 @@ listContinuationLine :: MarkdownParser String listContinuationLine = try $ do notFollowedBy blankline notFollowedBy' listStart + notFollowedBy' $ try $ skipMany spaceChar >> htmlTag (~== TagClose "div") optional indentSpaces result <- anyLine return $ result ++ "\n" -- cgit v1.2.3 From def05d3504bfc90c31c1621438f7a51c95079ad2 Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Fri, 6 Dec 2013 16:43:59 -0800 Subject: HTML reader: Parse LaTeX math if appropriate options are set. * Moved inlineMath, displayMath from Markdown reader to Parsing. * Export them from Parsing. (API change.) * Generalize their types. --- src/Text/Pandoc/Parsing.hs | 35 +++++++++++++++++++++++++++++++++++ src/Text/Pandoc/Readers/HTML.hs | 9 ++++++++- src/Text/Pandoc/Readers/LaTeX.hs | 3 ++- src/Text/Pandoc/Readers/Markdown.hs | 33 --------------------------------- 4 files changed, 45 insertions(+), 35 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Parsing.hs b/src/Text/Pandoc/Parsing.hs index 9687d7712..e15854333 100644 --- a/src/Text/Pandoc/Parsing.hs +++ b/src/Text/Pandoc/Parsing.hs @@ -48,6 +48,8 @@ module Text.Pandoc.Parsing ( (>>~), romanNumeral, emailAddress, uri, + mathInline, + mathDisplay, withHorizDisplacement, withRaw, escaped, @@ -455,6 +457,39 @@ uri = try $ do let uri' = scheme ++ ":" ++ fromEntities str' return (uri', escapeURI uri') +mathInlineWith :: String -> String -> Parser [Char] st String +mathInlineWith op cl = try $ do + string op + notFollowedBy space + words' <- many1Till (count 1 (noneOf "\n\\") + <|> (char '\\' >> anyChar >>= \c -> return ['\\',c]) + <|> count 1 newline <* notFollowedBy' blankline + *> return " ") + (try $ string cl) + notFollowedBy digit -- to prevent capture of $5 + return $ concat words' + +mathDisplayWith :: String -> String -> Parser [Char] st String +mathDisplayWith op cl = try $ do + string op + many1Till (noneOf "\n" <|> (newline >>~ notFollowedBy' blankline)) (try $ string cl) + +mathDisplay :: Parser [Char] ParserState String +mathDisplay = + (guardEnabled Ext_tex_math_dollars >> mathDisplayWith "$$" "$$") + <|> (guardEnabled Ext_tex_math_single_backslash >> + mathDisplayWith "\\[" "\\]") + <|> (guardEnabled Ext_tex_math_double_backslash >> + mathDisplayWith "\\\\[" "\\\\]") + +mathInline :: Parser [Char] ParserState String +mathInline = + (guardEnabled Ext_tex_math_dollars >> mathInlineWith "$" "$") + <|> (guardEnabled Ext_tex_math_single_backslash >> + mathInlineWith "\\(" "\\)") + <|> (guardEnabled Ext_tex_math_double_backslash >> + mathInlineWith "\\\\(" "\\\\)") + -- | Applies a parser, returns tuple of its results and its horizontal -- displacement (the difference between the source column at the end -- and the source column at the beginning). Vertical displacement diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs index d691c9878..e758f712f 100644 --- a/src/Text/Pandoc/Readers/HTML.hs +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -467,7 +467,13 @@ pBlank = try $ do pTagContents :: Parser [Char] ParserState Inline pTagContents = - pStr <|> pSpace <|> smartPunctuation pTagContents <|> pSymbol <|> pBad + Math InlineMath `fmap` mathInline + <|> Math DisplayMath `fmap` mathDisplay + <|> pStr + <|> pSpace + <|> smartPunctuation pTagContents + <|> pSymbol + <|> pBad pStr :: Parser [Char] ParserState Inline pStr = do @@ -482,6 +488,7 @@ isSpecial '"' = True isSpecial '\'' = True isSpecial '.' = True isSpecial '-' = True +isSpecial '$' = True isSpecial '\8216' = True isSpecial '\8217' = True isSpecial '\8220' = True diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs index 75e29ebb9..509cb5d74 100644 --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -38,7 +38,8 @@ import Text.Pandoc.Definition import Text.Pandoc.Walk import Text.Pandoc.Shared import Text.Pandoc.Options -import Text.Pandoc.Parsing hiding ((<|>), many, optional, space) +import Text.Pandoc.Parsing hiding ((<|>), many, optional, space, + mathDisplay, mathInline) import qualified Text.Pandoc.UTF8 as UTF8 import Data.Char ( chr, ord ) import Control.Monad diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index 4cb75d86c..11168bc09 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -1408,39 +1408,6 @@ math :: MarkdownParser (F Inlines) math = (return . B.displayMath <$> (mathDisplay >>= applyMacros')) <|> (return . B.math <$> (mathInline >>= applyMacros')) -mathDisplay :: MarkdownParser String -mathDisplay = - (guardEnabled Ext_tex_math_dollars >> mathDisplayWith "$$" "$$") - <|> (guardEnabled Ext_tex_math_single_backslash >> - mathDisplayWith "\\[" "\\]") - <|> (guardEnabled Ext_tex_math_double_backslash >> - mathDisplayWith "\\\\[" "\\\\]") - -mathDisplayWith :: String -> String -> MarkdownParser String -mathDisplayWith op cl = try $ do - string op - many1Till (noneOf "\n" <|> (newline >>~ notFollowedBy' blankline)) (try $ string cl) - -mathInline :: MarkdownParser String -mathInline = - (guardEnabled Ext_tex_math_dollars >> mathInlineWith "$" "$") - <|> (guardEnabled Ext_tex_math_single_backslash >> - mathInlineWith "\\(" "\\)") - <|> (guardEnabled Ext_tex_math_double_backslash >> - mathInlineWith "\\\\(" "\\\\)") - -mathInlineWith :: String -> String -> MarkdownParser String -mathInlineWith op cl = try $ do - string op - notFollowedBy space - words' <- many1Till (count 1 (noneOf "\n\\") - <|> (char '\\' >> anyChar >>= \c -> return ['\\',c]) - <|> count 1 newline <* notFollowedBy' blankline - *> return " ") - (try $ string cl) - notFollowedBy digit -- to prevent capture of $5 - return $ concat words' - -- Parses material enclosed in *s, **s, _s, or __s. -- Designed to avoid backtracking. enclosure :: Char -- cgit v1.2.3 From e5a7c31a32b2b53ef5073355b70dc17ecf1d16af Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Sat, 7 Dec 2013 17:12:52 -0800 Subject: Markdown reader: Fixed bug with literal `` in lists. Closes #1078. --- src/Text/Pandoc/Readers/Markdown.hs | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index 11168bc09..c32c5ed86 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -732,8 +732,9 @@ listLine = try $ do notFollowedBy' (do indentSpaces many (spaceChar) listStart) - chunks <- manyTill (liftM snd (htmlTag isCommentTag) <|> count 1 (satisfy (/='<')) - <|> (notFollowedBy' (htmlTag isBlockTag) >> count 1 anyChar)) newline + notFollowedBy' $ htmlTag (~== TagClose "div") + chunks <- manyTill (liftM snd (htmlTag isCommentTag) <|> count 1 anyChar) + newline return $ concat chunks -- parse raw text for one list item, excluding start marker and continuations @@ -760,7 +761,7 @@ listContinuationLine :: MarkdownParser String listContinuationLine = try $ do notFollowedBy blankline notFollowedBy' listStart - notFollowedBy' $ try $ skipMany spaceChar >> htmlTag (~== TagClose "div") + notFollowedBy' $ htmlTag (~== TagClose "div") optional indentSpaces result <- anyLine return $ result ++ "\n" -- cgit v1.2.3 From e2c4156c20f113b6f965ccd9313c5aa062cc198f Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Sat, 7 Dec 2013 19:41:42 -0800 Subject: Small performance improvement in list parsing. --- src/Text/Pandoc/Readers/Markdown.hs | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index c32c5ed86..a948d5ad3 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -733,8 +733,9 @@ listLine = try $ do many (spaceChar) listStart) notFollowedBy' $ htmlTag (~== TagClose "div") - chunks <- manyTill (liftM snd (htmlTag isCommentTag) <|> count 1 anyChar) - newline + chunks <- manyTill (liftM snd (htmlTag isCommentTag) + <|> many1 (satisfy (/='\n')) + <|> count 1 anyChar) newline return $ concat chunks -- parse raw text for one list item, excluding start marker and continuations -- cgit v1.2.3 From 8e255fad98baf2448d8c1866d7c03c5d110a505f Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Sat, 7 Dec 2013 19:56:54 -0800 Subject: Another small performance improvement. --- src/Text/Pandoc/Readers/Markdown.hs | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index a948d5ad3..e77dda8d7 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -733,9 +733,11 @@ listLine = try $ do many (spaceChar) listStart) notFollowedBy' $ htmlTag (~== TagClose "div") - chunks <- manyTill (liftM snd (htmlTag isCommentTag) - <|> many1 (satisfy (/='\n')) - <|> count 1 anyChar) newline + chunks <- manyTill + ( many1 (satisfy $ \c -> c /= '\n' && c /= '<') + <|> liftM snd (htmlTag isCommentTag) + <|> count 1 anyChar + ) newline return $ concat chunks -- parse raw text for one list item, excluding start marker and continuations -- cgit v1.2.3 From 6d0cd9203ce968b96ffa8fc2fbae5a50c99b125b Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Thu, 12 Dec 2013 22:34:13 -0800 Subject: Markdown reader: Fixed regression in title blocks. If author field was empty, date was being ignored. Closes #1089. --- src/Text/Pandoc/Readers/Markdown.hs | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index e77dda8d7..8014d480c 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -215,10 +215,10 @@ pandocTitleBlock = try $ do author' <- author date' <- date return $ - ( if B.isNull title' then id else B.setMeta "title" title' - . if null author' then id else B.setMeta "author" author' - . if B.isNull date' then id else B.setMeta "date" date' ) - nullMeta + (if B.isNull title' then id else B.setMeta "title" title') + . (if null author' then id else B.setMeta "author" author') + . (if B.isNull date' then id else B.setMeta "date" date') + $ nullMeta updateState $ \st -> st{ stateMeta' = stateMeta' st <> meta' } yamlMetaBlock :: MarkdownParser (F Blocks) -- cgit v1.2.3 From 5adbe7b36592ba8779563bba791ad4724fde927c Mon Sep 17 00:00:00 2001 From: Jeff Arnold Date: Fri, 13 Dec 2013 19:16:04 -0500 Subject: LaTeX reader: add support for Verb macro --- src/Text/Pandoc/Readers/LaTeX.hs | 1 + 1 file changed, 1 insertion(+) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs index 509cb5d74..736f2ff1c 100644 --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -455,6 +455,7 @@ inlineCommands = M.fromList $ , ("footnote", (note . mconcat) <$> (char '{' *> manyTill block (char '}'))) , ("verb", doverb) , ("lstinline", doverb) + , ("Verb", doverb) , ("texttt", (code . stringify . toList) <$> tok) , ("url", (unescapeURL <$> braced) >>= \url -> pure (link url "" (str url))) -- cgit v1.2.3 From 2f00f5c7c22ef879df3a21f1c3da967d106628e9 Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Sun, 15 Dec 2013 12:27:29 -0800 Subject: Properly handle script blocks in strict mode. (That is, markdown-markdown_in_html_blocks.) Previously a spurious `

` tag was being added. Closes #1093. --- src/Text/Pandoc/Readers/Markdown.hs | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index 8014d480c..b2e88d47e 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -902,7 +902,9 @@ plain = fmap B.plain . trimInlinesF . mconcat <$> many1 inline -- htmlElement :: MarkdownParser String -htmlElement = strictHtmlBlock <|> liftM snd (htmlTag isBlockTag) +htmlElement = rawVerbatimBlock + <|> strictHtmlBlock + <|> liftM snd (htmlTag isBlockTag) htmlBlock :: MarkdownParser (F Blocks) htmlBlock = do -- cgit v1.2.3 From 826443926f85b72840b49cd7973e91ed80a09b5d Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Mon, 16 Dec 2013 13:58:54 -0800 Subject: Docbook reader: Avoid failure if tbody contains no tr or row elements. --- src/Text/Pandoc/Readers/DocBook.hs | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/DocBook.hs b/src/Text/Pandoc/Readers/DocBook.hs index fc29988d5..03c6140ac 100644 --- a/src/Text/Pandoc/Readers/DocBook.hs +++ b/src/Text/Pandoc/Readers/DocBook.hs @@ -806,7 +806,9 @@ parseBlock (Elem e) = (x >= '0' && x <= '9') || x == '.') w Nothing -> 0 :: Double - let numrows = maximum $ map length bodyrows + let numrows = case bodyrows of + [] -> 0 + xs -> maximum $ map length xs let aligns = case colspecs of [] -> replicate numrows AlignDefault cs -> map toAlignment cs -- cgit v1.2.3 From 0132f6fcb75e58774846e92bac6df2afd7a50e6f Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Tue, 17 Dec 2013 16:03:43 -0800 Subject: LaTeX reader: Support babel-style quoting: `` "`..."' ``. --- src/Text/Pandoc/Readers/LaTeX.hs | 2 ++ 1 file changed, 2 insertions(+) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs index 736f2ff1c..0020a8f26 100644 --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -173,6 +173,8 @@ double_quote :: LP Inlines double_quote = ( quoted' doubleQuoted (try $ string "``") (void $ try $ string "''") <|> quoted' doubleQuoted (string "“") (void $ char '”') + -- the following is used by babel for localized quotes: + <|> quoted' doubleQuoted (try $ string "\"`") (void $ try $ string "\"'") <|> quoted' doubleQuoted (string "\"") (void $ char '"') ) -- cgit v1.2.3 From 0c5e7cf8cb4fe6959d7e89880e8925afe6625414 Mon Sep 17 00:00:00 2001 From: Henry de Valence Date: Thu, 19 Dec 2013 20:19:24 -0500 Subject: HLint: use `elem` and `notElem` Replaces long conditional chains with calls to `elem` and `notElem`. --- pandoc.hs | 2 +- src/Text/Pandoc/Parsing.hs | 4 ++-- src/Text/Pandoc/Readers/LaTeX.hs | 5 ++--- src/Text/Pandoc/Readers/Markdown.hs | 8 ++++---- src/Text/Pandoc/Shared.hs | 12 ++++-------- src/Text/Pandoc/Writers/Markdown.hs | 11 ++++++----- src/Text/Pandoc/Writers/Org.hs | 2 +- 7 files changed, 20 insertions(+), 24 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/pandoc.hs b/pandoc.hs index cada3347d..ccd3e57fb 100644 --- a/pandoc.hs +++ b/pandoc.hs @@ -656,7 +656,7 @@ options = (ReqArg (\arg opt -> do let b = takeBaseName arg - if (b == "pdflatex" || b == "lualatex" || b == "xelatex") + if b `elem` ["pdflatex", "lualatex", "xelatex"] then return opt { optLaTeXEngine = arg } else err 45 "latex-engine must be pdflatex, lualatex, or xelatex.") "PROGRAM") diff --git a/src/Text/Pandoc/Parsing.hs b/src/Text/Pandoc/Parsing.hs index e15854333..2f21e1253 100644 --- a/src/Text/Pandoc/Parsing.hs +++ b/src/Text/Pandoc/Parsing.hs @@ -271,7 +271,7 @@ spaceChar = satisfy $ \c -> c == ' ' || c == '\t' -- | Parses a nonspace, nonnewline character. nonspaceChar :: Parser [Char] st Char -nonspaceChar = satisfy $ \x -> x /= '\t' && x /= '\n' && x /= ' ' && x /= '\r' +nonspaceChar = satisfy $ flip notElem ['\t', '\n', ' ', '\r'] -- | Skips zero or more spaces or tabs. skipSpaces :: Parser [Char] st () @@ -1062,7 +1062,7 @@ doubleQuoteStart :: Parser [Char] ParserState () doubleQuoteStart = do failIfInQuoteContext InDoubleQuote try $ do charOrRef "\"\8220\147" - notFollowedBy (satisfy (\c -> c == ' ' || c == '\t' || c == '\n')) + notFollowedBy . satisfy $ flip elem [' ', '\t', '\n'] doubleQuoteEnd :: Parser [Char] st () doubleQuoteEnd = do diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs index 0020a8f26..51271edc5 100644 --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -874,9 +874,8 @@ verbatimEnv = do (_,r) <- withRaw $ do controlSeq "begin" name <- braced - guard $ name == "verbatim" || name == "Verbatim" || - name == "lstlisting" || name == "minted" || - name == "alltt" + guard $ name `elem` ["verbatim", "Verbatim", "lstlisting", + "minted", "alltt"] verbEnv name rest <- getInput return (r,rest) diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index b2e88d47e..f483ab059 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -789,8 +789,8 @@ listItem start = try $ do orderedList :: MarkdownParser (F Blocks) orderedList = try $ do (start, style, delim) <- lookAhead anyOrderedListStart - unless ((style == DefaultStyle || style == Decimal || style == Example) && - (delim == DefaultDelim || delim == Period)) $ + unless (style `elem` [DefaultStyle, Decimal, Example] && + delim `elem` [DefaultDelim, Period]) $ guardEnabled Ext_fancy_lists when (style == Example) $ guardEnabled Ext_example_lists items <- fmap sequence $ many1 $ listItem @@ -925,8 +925,8 @@ strictHtmlBlock = htmlInBalanced (not . isInlineTag) rawVerbatimBlock :: MarkdownParser String rawVerbatimBlock = try $ do - (TagOpen tag _, open) <- htmlTag (tagOpen (\t -> - t == "pre" || t == "style" || t == "script") + (TagOpen tag _, open) <- htmlTag (tagOpen (flip elem + ["pre", "style", "script"]) (const True)) contents <- manyTill anyChar (htmlTag (~== TagClose tag)) return $ open ++ contents ++ renderTags [TagClose tag] diff --git a/src/Text/Pandoc/Shared.hs b/src/Text/Pandoc/Shared.hs index cd2f7e24d..3446f4343 100644 --- a/src/Text/Pandoc/Shared.hs +++ b/src/Text/Pandoc/Shared.hs @@ -564,14 +564,10 @@ makeMeta title authors date = -- | Render HTML tags. renderTags' :: [Tag String] -> String renderTags' = renderTagsOptions - renderOptions{ optMinimize = \x -> - let y = map toLower x - in y == "hr" || y == "br" || - y == "img" || y == "meta" || - y == "link" - , optRawTag = \x -> - let y = map toLower x - in y == "script" || y == "style" } + renderOptions{ optMinimize = matchTags ["hr", "br", "img", + "meta", "link"] + , optRawTag = matchTags ["script", "style"] } + where matchTags = \tags -> flip elem tags . map toLower -- -- File handling diff --git a/src/Text/Pandoc/Writers/Markdown.hs b/src/Text/Pandoc/Writers/Markdown.hs index c0b189b75..278e5cc9d 100644 --- a/src/Text/Pandoc/Writers/Markdown.hs +++ b/src/Text/Pandoc/Writers/Markdown.hs @@ -338,7 +338,7 @@ blockToMarkdown opts (RawBlock f str) else return $ if isEnabled Ext_markdown_attribute opts then text (addMarkdownAttribute str) <> text "\n" else text str <> text "\n" - | f == "latex" || f == "tex" || f == "markdown" = do + | f `elem` ["latex", "tex", "markdown"] = do st <- get if stPlain st then return empty @@ -628,10 +628,11 @@ getReference label (src, tit) = do Nothing -> do let label' = case find ((== label) . fst) (stRefs st) of Just _ -> -- label is used; generate numerical label - case find (\n -> not (any (== [Str (show n)]) - (map fst (stRefs st)))) [1..(10000 :: Integer)] of - Just x -> [Str (show x)] - Nothing -> error "no unique label" + case find (\n -> notElem [Str (show n)] + (map fst (stRefs st))) + [1..(10000 :: Integer)] of + Just x -> [Str (show x)] + Nothing -> error "no unique label" Nothing -> label modify (\s -> s{ stRefs = (label', (src,tit)) : stRefs st }) return label' diff --git a/src/Text/Pandoc/Writers/Org.hs b/src/Text/Pandoc/Writers/Org.hs index 51083f52b..d318c5f6a 100644 --- a/src/Text/Pandoc/Writers/Org.hs +++ b/src/Text/Pandoc/Writers/Org.hs @@ -129,7 +129,7 @@ blockToOrg (Para inlines) = do blockToOrg (RawBlock "html" str) = return $ blankline $$ "#+BEGIN_HTML" $$ nest 2 (text str) $$ "#+END_HTML" $$ blankline -blockToOrg (RawBlock f str) | f == "org" || f == "latex" || f == "tex" = +blockToOrg (RawBlock f str) | f `elem` ["org", "latex", "tex"] = return $ text str blockToOrg (RawBlock _ _) = return empty blockToOrg HorizontalRule = return $ blankline $$ "--------------" $$ blankline -- cgit v1.2.3 From f6d151889c8fff303be8ee8a4f9be67a04de9210 Mon Sep 17 00:00:00 2001 From: Henry de Valence Date: Thu, 19 Dec 2013 20:43:25 -0500 Subject: HLint: redundant parens Remove parens enclosing a single element. --- pandoc.hs | 6 ++---- src/Text/Pandoc/Readers/Markdown.hs | 2 +- src/Text/Pandoc/Readers/Textile.hs | 2 +- src/Text/Pandoc/Writers/HTML.hs | 2 +- src/Text/Pandoc/Writers/MediaWiki.hs | 2 +- src/Text/Pandoc/Writers/Textile.hs | 2 +- tests/Tests/Readers/LaTeX.hs | 2 +- tests/Tests/Readers/Markdown.hs | 4 ++-- 8 files changed, 10 insertions(+), 12 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/pandoc.hs b/pandoc.hs index ccd3e57fb..574c89771 100644 --- a/pandoc.hs +++ b/pandoc.hs @@ -1034,12 +1034,10 @@ main = do variables' <- case mathMethod of LaTeXMathML Nothing -> do - s <- readDataFileUTF8 datadir - ("LaTeXMathML.js") + s <- readDataFileUTF8 datadir "LaTeXMathML.js" return $ ("mathml-script", s) : variables MathML Nothing -> do - s <- readDataFileUTF8 datadir - ("MathMLinHTML.js") + s <- readDataFileUTF8 datadir "MathMLinHTML.js" return $ ("mathml-script", s) : variables _ -> return variables diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index f483ab059..166c524ef 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -730,7 +730,7 @@ listStart = bulletListStart <|> (anyOrderedListStart >> return ()) listLine :: MarkdownParser String listLine = try $ do notFollowedBy' (do indentSpaces - many (spaceChar) + many spaceChar listStart) notFollowedBy' $ htmlTag (~== TagClose "div") chunks <- manyTill diff --git a/src/Text/Pandoc/Readers/Textile.hs b/src/Text/Pandoc/Readers/Textile.hs index 23e07f621..93658cdea 100644 --- a/src/Text/Pandoc/Readers/Textile.hs +++ b/src/Text/Pandoc/Readers/Textile.hs @@ -594,7 +594,7 @@ surrounded border = enclosed (border *> notFollowedBy (oneOf " \t\n\r")) (try bo simpleInline :: Parser [Char] ParserState t -- ^ surrounding parser -> ([Inline] -> Inline) -- ^ Inline constructor -> Parser [Char] ParserState Inline -- ^ content parser (to be used repeatedly) -simpleInline border construct = surrounded border (inlineWithAttribute) >>= +simpleInline border construct = surrounded border inlineWithAttribute >>= return . construct . normalizeSpaces where inlineWithAttribute = (try $ optional attributes) >> inline diff --git a/src/Text/Pandoc/Writers/HTML.hs b/src/Text/Pandoc/Writers/HTML.hs index 641652276..2c6435457 100644 --- a/src/Text/Pandoc/Writers/HTML.hs +++ b/src/Text/Pandoc/Writers/HTML.hs @@ -524,7 +524,7 @@ blockToHtml opts (DefinitionList lst) = do contents <- mapM (\(term, defs) -> do term' <- if null term then return mempty - else liftM (H.dt) $ inlineListToHtml opts term + else liftM H.dt $ inlineListToHtml opts term defs' <- mapM ((liftM (\x -> H.dd $ (x >> nl opts))) . blockListToHtml opts) defs return $ mconcat $ nl opts : term' : nl opts : diff --git a/src/Text/Pandoc/Writers/MediaWiki.hs b/src/Text/Pandoc/Writers/MediaWiki.hs index 61741a61e..83fefaa29 100644 --- a/src/Text/Pandoc/Writers/MediaWiki.hs +++ b/src/Text/Pandoc/Writers/MediaWiki.hs @@ -51,7 +51,7 @@ data WriterState = WriterState { writeMediaWiki :: WriterOptions -> Pandoc -> String writeMediaWiki opts document = evalState (pandocToMediaWiki opts document) - (WriterState { stNotes = False, stListLevel = [], stUseTags = False }) + WriterState { stNotes = False, stListLevel = [], stUseTags = False } -- | Return MediaWiki representation of document. pandocToMediaWiki :: WriterOptions -> Pandoc -> State WriterState String diff --git a/src/Text/Pandoc/Writers/Textile.hs b/src/Text/Pandoc/Writers/Textile.hs index 7c102cc86..95aedf780 100644 --- a/src/Text/Pandoc/Writers/Textile.hs +++ b/src/Text/Pandoc/Writers/Textile.hs @@ -51,7 +51,7 @@ data WriterState = WriterState { writeTextile :: WriterOptions -> Pandoc -> String writeTextile opts document = evalState (pandocToTextile opts document) - (WriterState { stNotes = [], stListLevel = [], stUseTags = False }) + WriterState { stNotes = [], stListLevel = [], stUseTags = False } -- | Return Textile representation of document. pandocToTextile :: WriterOptions -> Pandoc -> State WriterState String diff --git a/tests/Tests/Readers/LaTeX.hs b/tests/Tests/Readers/LaTeX.hs index c1efd1b68..8ff23ebc1 100644 --- a/tests/Tests/Readers/LaTeX.hs +++ b/tests/Tests/Readers/LaTeX.hs @@ -21,7 +21,7 @@ tests = [ testGroup "basic" [ "simple" =: "word" =?> para "word" , "space" =: - "some text" =?> para ("some text") + "some text" =?> para "some text" , "emphasized" =: "\\emph{emphasized}" =?> para (emph "emphasized") ] diff --git a/tests/Tests/Readers/Markdown.hs b/tests/Tests/Readers/Markdown.hs index b04ff9a0d..492680a35 100644 --- a/tests/Tests/Readers/Markdown.hs +++ b/tests/Tests/Readers/Markdown.hs @@ -171,13 +171,13 @@ tests = [ testGroup "inline code" , testGroup "smart punctuation" [ test markdownSmart "quote before ellipses" ("'...hi'" - =?> para (singleQuoted ("…hi"))) + =?> para (singleQuoted "…hi")) , test markdownSmart "apostrophe before emph" ("D'oh! A l'*aide*!" =?> para ("D’oh! A l’" <> emph "aide" <> "!")) , test markdownSmart "apostrophe in French" ("À l'arrivée de la guerre, le thème de l'«impossibilité du socialisme»" - =?> para ("À l’arrivée de la guerre, le thème de l’«impossibilité du socialisme»")) + =?> para "À l’arrivée de la guerre, le thème de l’«impossibilité du socialisme»") ] , testGroup "mixed emphasis and strong" [ "emph and strong emph alternating" =: -- cgit v1.2.3 From 3d70059a4896c66cab59832a3ed9eb8334b84a2f Mon Sep 17 00:00:00 2001 From: Henry de Valence Date: Thu, 19 Dec 2013 21:07:09 -0500 Subject: HLint: use fromMaybe Replace uses of `maybe x id` with `fromMaybe x`. --- src/Text/Pandoc/PDF.hs | 3 ++- src/Text/Pandoc/Readers/DocBook.hs | 7 ++++--- src/Text/Pandoc/Readers/HTML.hs | 4 ++-- src/Text/Pandoc/Readers/Markdown.hs | 4 ++-- src/Text/Pandoc/Readers/MediaWiki.hs | 7 ++++--- src/Text/Pandoc/Writers/Docx.hs | 6 ++++-- src/Text/Pandoc/Writers/EPUB.hs | 12 ++++++------ src/Text/Pandoc/Writers/HTML.hs | 4 ++-- src/Text/Pandoc/Writers/LaTeX.hs | 3 ++- src/Text/Pandoc/Writers/ODT.hs | 3 ++- 10 files changed, 30 insertions(+), 23 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/PDF.hs b/src/Text/Pandoc/PDF.hs index e8683b98f..360338f8f 100644 --- a/src/Text/Pandoc/PDF.hs +++ b/src/Text/Pandoc/PDF.hs @@ -41,6 +41,7 @@ import System.Directory import System.Environment import Control.Monad (unless) import Data.List (isInfixOf) +import Data.Maybe (fromMaybe) import qualified Data.ByteString.Base64 as B64 import qualified Text.Pandoc.UTF8 as UTF8 import Text.Pandoc.Definition @@ -87,7 +88,7 @@ handleImage' baseURL tmpdir (Image ils (src,tit)) = do res <- fetchItem baseURL src case res of Right (contents, Just mime) -> do - let ext = maybe (takeExtension src) id $ + let ext = fromMaybe (takeExtension src) $ extensionFromMimeType mime let basename = UTF8.toString $ B64.encode $ UTF8.fromString src let fname = tmpdir basename <.> ext diff --git a/src/Text/Pandoc/Readers/DocBook.hs b/src/Text/Pandoc/Readers/DocBook.hs index 03c6140ac..56cb16b20 100644 --- a/src/Text/Pandoc/Readers/DocBook.hs +++ b/src/Text/Pandoc/Readers/DocBook.hs @@ -12,6 +12,7 @@ import Data.Char (isSpace) import Control.Monad.State import Control.Applicative ((<$>)) import Data.List (intersperse) +import Data.Maybe (fromMaybe) {- @@ -683,7 +684,7 @@ parseBlock (Elem e) = "lowerroman" -> LowerRoman "upperroman" -> UpperRoman _ -> Decimal - let start = maybe 1 id $ + let start = fromMaybe 1 $ (attrValue "override" <$> filterElement (named "listitem") e) >>= safeRead orderedListWith (start,listStyle,DefaultDelim) @@ -779,7 +780,7 @@ parseBlock (Elem e) = caption <- case filterChild isCaption e of Just t -> getInlines t Nothing -> return mempty - let e' = maybe e id $ filterChild (named "tgroup") e + let e' = fromMaybe e $ filterChild (named "tgroup") e let isColspec x = named "colspec" x || named "col" x let colspecs = case filterChild (named "colgroup") e' of Just c -> filterChildren isColspec c @@ -801,7 +802,7 @@ parseBlock (Elem e) = Just "center" -> AlignCenter _ -> AlignDefault let toWidth c = case findAttr (unqual "colwidth") c of - Just w -> maybe 0 id + Just w -> fromMaybe 0 $ safeRead $ '0': filter (\x -> (x >= '0' && x <= '9') || x == '.') w diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs index e758f712f..4b44a3a21 100644 --- a/src/Text/Pandoc/Readers/HTML.hs +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -207,7 +207,7 @@ pHeader = try $ do let bodyTitle = TagOpen tagtype attr ~== TagOpen "h1" [("class","title")] let level = read (drop 1 tagtype) contents <- liftM concat $ manyTill inline (pCloses tagtype <|> eof) - let ident = maybe "" id $ lookup "id" attr + let ident = fromMaybe "" $ lookup "id" attr let classes = maybe [] words $ lookup "class" attr let keyvals = [(k,v) | (k,v) <- attr, k /= "class", k /= "id"] return $ if bodyTitle @@ -257,7 +257,7 @@ pCol = try $ do skipMany pBlank return $ case lookup "width" attribs of Just x | not (null x) && last x == '%' -> - maybe 0.0 id $ safeRead ('0':'.':init x) + fromMaybe 0.0 $ safeRead ('0':'.':init x) _ -> 0.0 pColgroup :: TagParser [Double] diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index 166c524ef..3a5d29b4e 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -1722,7 +1722,7 @@ spanHtml = try $ do guardEnabled Ext_markdown_in_html_blocks (TagOpen _ attrs, _) <- htmlTag (~== TagOpen "span" []) contents <- mconcat <$> manyTill inline (htmlTag (~== TagClose "span")) - let ident = maybe "" id $ lookup "id" attrs + let ident = fromMaybe "" $ lookup "id" attrs let classes = maybe [] words $ lookup "class" attrs let keyvals = [(k,v) | (k,v) <- attrs, k /= "id" && k /= "class"] return $ B.spanWith (ident, classes, keyvals) <$> contents @@ -1732,7 +1732,7 @@ divHtml = try $ do guardEnabled Ext_markdown_in_html_blocks (TagOpen _ attrs, _) <- htmlTag (~== TagOpen "div" []) contents <- mconcat <$> manyTill block (htmlTag (~== TagClose "div")) - let ident = maybe "" id $ lookup "id" attrs + let ident = fromMaybe "" $ lookup "id" attrs let classes = maybe [] words $ lookup "class" attrs let keyvals = [(k,v) | (k,v) <- attrs, k /= "id" && k /= "class"] return $ B.divWith (ident, classes, keyvals) <$> contents diff --git a/src/Text/Pandoc/Readers/MediaWiki.hs b/src/Text/Pandoc/Readers/MediaWiki.hs index 1c074e3de..8d8ea0199 100644 --- a/src/Text/Pandoc/Readers/MediaWiki.hs +++ b/src/Text/Pandoc/Readers/MediaWiki.hs @@ -54,6 +54,7 @@ import Data.Sequence (viewl, ViewL(..), (<|)) import qualified Data.Foldable as F import qualified Data.Map as M import Data.Char (isDigit, isSpace) +import Data.Maybe (fromMaybe) -- | Read mediawiki from an input string and return a Pandoc document. readMediaWiki :: ReaderOptions -- ^ Reader options @@ -204,7 +205,7 @@ table = do tableStart styles <- option [] parseAttrs <* blankline let tableWidth = case lookup "width" styles of - Just w -> maybe 1.0 id $ parseWidth w + Just w -> fromMaybe 1.0 $ parseWidth w Nothing -> 1.0 caption <- option mempty tableCaption optional rowsep @@ -285,7 +286,7 @@ tableCell = try $ do Just "center" -> AlignCenter _ -> AlignDefault let width = case lookup "width" attrs of - Just xs -> maybe 0.0 id $ parseWidth xs + Just xs -> fromMaybe 0.0 $ parseWidth xs Nothing -> 0.0 return ((align, width), bs) @@ -387,7 +388,7 @@ orderedList = spaces items <- many (listItem '#' <|> li) optional (htmlTag (~== TagClose "ol")) - let start = maybe 1 id $ safeRead $ fromAttrib "start" tag + let start = fromMaybe 1 $ safeRead $ fromAttrib "start" tag return $ B.orderedListWith (start, DefaultStyle, DefaultDelim) items definitionList :: MWParser Blocks diff --git a/src/Text/Pandoc/Writers/Docx.hs b/src/Text/Pandoc/Writers/Docx.hs index 5c7341b69..32ba7715a 100644 --- a/src/Text/Pandoc/Writers/Docx.hs +++ b/src/Text/Pandoc/Writers/Docx.hs @@ -29,6 +29,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA Conversion of 'Pandoc' documents to docx. -} module Text.Pandoc.Writers.Docx ( writeDocx ) where +import Data.Maybe (fromMaybe) import Data.List ( intercalate, groupBy ) import qualified Data.ByteString as B import qualified Data.ByteString.Lazy as BL @@ -130,7 +131,8 @@ writeDocx opts doc@(Pandoc meta _) = do let mkOverrideNode (part', contentType') = mknode "Override" [("PartName",part'),("ContentType",contentType')] () let mkImageOverride (_, imgpath, mbMimeType, _, _) = - mkOverrideNode ("/word/" ++ imgpath, maybe "application/octet-stream" id mbMimeType) + mkOverrideNode ("/word/" ++ imgpath, + fromMaybe "application/octet-stream" mbMimeType) let overrides = map mkOverrideNode [("/word/webSettings.xml", "application/vnd.openxmlformats-officedocument.wordprocessingml.webSettings+xml") @@ -322,7 +324,7 @@ mkNum markers marker numid = NumberMarker _ _ start -> map (\lvl -> mknode "w:lvlOverride" [("w:ilvl",show (lvl :: Int))] $ mknode "w:startOverride" [("w:val",show start)] ()) [0..6] - where absnumid = maybe 0 id $ M.lookup marker markers + where absnumid = fromMaybe 0 $ M.lookup marker markers mkAbstractNum :: (ListMarker,Int) -> IO Element mkAbstractNum (marker,numid) = do diff --git a/src/Text/Pandoc/Writers/EPUB.hs b/src/Text/Pandoc/Writers/EPUB.hs index 36ead0b8f..4daa9609e 100644 --- a/src/Text/Pandoc/Writers/EPUB.hs +++ b/src/Text/Pandoc/Writers/EPUB.hs @@ -176,8 +176,8 @@ addMetadataFromXML e@(Element (QName name _ (Just "dc")) attrs _ _) md , titleFileAs = getAttr "file-as" , titleType = getAttr "type" } : epubTitle md } - | name == "date" = md{ epubDate = maybe "" id $ normalizeDate' - $ strContent e } + | name == "date" = md{ epubDate = fromMaybe "" $ normalizeDate' + $ strContent e } | name == "language" = md{ epubLanguage = strContent e } | name == "creator" = md{ epubCreator = Creator{ creatorText = strContent e @@ -271,7 +271,7 @@ metadataFromMeta opts meta = EPUBMetadata{ } where identifiers = getIdentifier meta titles = getTitle meta - date = maybe "" id $ + date = fromMaybe "" $ (metaValueToString <$> lookupMeta "date" meta) >>= normalizeDate' language = maybe "" metaValueToString $ lookupMeta "language" meta `mplus` lookupMeta "lang" meta @@ -297,7 +297,7 @@ writeEPUB :: WriterOptions -- ^ Writer options -> Pandoc -- ^ Document to convert -> IO B.ByteString writeEPUB opts doc@(Pandoc meta _) = do - let version = maybe EPUB2 id (writerEpubVersion opts) + let version = fromMaybe EPUB2 (writerEpubVersion opts) let epub3 = version == EPUB3 epochtime <- floor `fmap` getPOSIXTime let mkEntry path content = toEntry path epochtime content @@ -401,7 +401,7 @@ writeEPUB opts doc@(Pandoc meta _) = do chapToEntry num (Chapter mbnum bs) = mkEntry (showChapter num) $ renderHtml $ writeHtml opts'{ writerNumberOffset = - maybe [] id mbnum } + fromMaybe [] mbnum } $ case bs of (Header _ _ xs : _) -> Pandoc (setMeta "title" (fromList xs) nullMeta) bs @@ -436,7 +436,7 @@ writeEPUB opts doc@(Pandoc meta _) = do let fontNode ent = unode "item" ! [("id", takeBaseName $ eRelativePath ent), ("href", eRelativePath ent), - ("media-type", maybe "" id $ getMimeType $ eRelativePath ent)] $ () + ("media-type", fromMaybe "" $ getMimeType $ eRelativePath ent)] $ () let plainTitle = case docTitle meta of [] -> case epubTitle metadata of [] -> "UNTITLED" diff --git a/src/Text/Pandoc/Writers/HTML.hs b/src/Text/Pandoc/Writers/HTML.hs index 2c6435457..129776363 100644 --- a/src/Text/Pandoc/Writers/HTML.hs +++ b/src/Text/Pandoc/Writers/HTML.hs @@ -45,7 +45,7 @@ import Numeric ( showHex ) import Data.Char ( ord, toLower ) import Data.List ( isPrefixOf, intersperse ) import Data.String ( fromString ) -import Data.Maybe ( catMaybes ) +import Data.Maybe ( catMaybes, fromMaybe ) import Control.Monad.State import Text.Blaze.Html hiding(contents) import Text.Blaze.Internal(preEscapedString) @@ -118,7 +118,7 @@ pandocToHtml opts (Pandoc meta blocks) = do let stringifyHTML = escapeStringForXML . stringify let authsMeta = map stringifyHTML $ docAuthors meta let dateMeta = stringifyHTML $ docDate meta - let slideLevel = maybe (getSlideLevel blocks) id $ writerSlideLevel opts + let slideLevel = fromMaybe (getSlideLevel blocks) $ writerSlideLevel opts let sects = hierarchicalize $ if writerSlideVariant opts == NoSlides then blocks diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs index 1deacecb4..a76d6d82b 100644 --- a/src/Text/Pandoc/Writers/LaTeX.hs +++ b/src/Text/Pandoc/Writers/LaTeX.hs @@ -40,6 +40,7 @@ import Network.URI ( isURI, unEscapeString ) import Data.List ( (\\), isSuffixOf, isInfixOf, isPrefixOf, intercalate, intersperse ) import Data.Char ( toLower, isPunctuation, isAscii, isLetter, isDigit, ord ) +import Data.Maybe ( fromMaybe ) import Control.Applicative ((<|>)) import Control.Monad.State import Text.Pandoc.Pretty @@ -240,7 +241,7 @@ inCmd cmd contents = char '\\' <> text cmd <> braces contents toSlides :: [Block] -> State WriterState [Block] toSlides bs = do opts <- gets stOptions - let slideLevel = maybe (getSlideLevel bs) id $ writerSlideLevel opts + let slideLevel = fromMaybe (getSlideLevel bs) $ writerSlideLevel opts let bs' = prepSlides slideLevel bs concat `fmap` (mapM (elementToBeamer slideLevel) $ hierarchicalize bs') diff --git a/src/Text/Pandoc/Writers/ODT.hs b/src/Text/Pandoc/Writers/ODT.hs index cc0a06243..25cd5ae13 100644 --- a/src/Text/Pandoc/Writers/ODT.hs +++ b/src/Text/Pandoc/Writers/ODT.hs @@ -31,6 +31,7 @@ Conversion of 'Pandoc' documents to ODT. module Text.Pandoc.Writers.ODT ( writeODT ) where import Data.IORef import Data.List ( isPrefixOf ) +import Data.Maybe ( fromMaybe ) import qualified Data.ByteString.Lazy as B import Text.Pandoc.UTF8 ( fromStringLazy ) import Codec.Archive.Zip @@ -127,7 +128,7 @@ transformPic opts entriesRef (Image lab (src,_)) = do return $ Emph lab Right (img, _) -> do let size = imageSize img - let (w,h) = maybe (0,0) id $ sizeInPoints `fmap` size + let (w,h) = fromMaybe (0,0) $ sizeInPoints `fmap` size let tit' = show w ++ "x" ++ show h entries <- readIORef entriesRef let newsrc = "Pictures/" ++ show (length entries) ++ takeExtension src -- cgit v1.2.3 From f3ee82373b4ad8e955db12d3c2c2159a2bea53a0 Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Wed, 1 Jan 2014 09:22:37 -0800 Subject: HTML reader: Parse name/content pairs from meta tags as metadata. Closes #1106. --- src/Text/Pandoc/Readers/HTML.hs | 11 ++++++++++- tests/html-reader.native | 2 +- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs index 4b44a3a21..506fe7770 100644 --- a/src/Text/Pandoc/Readers/HTML.hs +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -76,9 +76,18 @@ pBody :: TagParser [Block] pBody = pInTags "body" block pHead :: TagParser [Block] -pHead = pInTags "head" $ pTitle <|> ([] <$ pAnyTag) +pHead = pInTags "head" $ pTitle <|> pMetaTag <|> ([] <$ pAnyTag) where pTitle = pInTags "title" inline >>= setTitle . normalizeSpaces setTitle t = [] <$ (updateState $ B.setMeta "title" (B.fromList t)) + pMetaTag = do + mt <- pSatisfy (~== TagOpen "meta" []) + let name = fromAttrib "name" mt + if null name + then return [] + else do + let content = fromAttrib "content" mt + updateState $ B.setMeta name (B.text content) + return [] block :: TagParser [Block] block = choice diff --git a/tests/html-reader.native b/tests/html-reader.native index 794512426..e80905729 100644 --- a/tests/html-reader.native +++ b/tests/html-reader.native @@ -1,4 +1,4 @@ -Pandoc (Meta {unMeta = fromList [("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]}) +Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]}) [Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc",Str ".",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber",Str "'",Str "s",Space,Str "markdown",Space,Str "test",Space,Str "suite",Str "."] ,HorizontalRule ,Header 1 ("",[],[]) [Str "Headers"] -- cgit v1.2.3 From d9eff99f27bb6426534651c9ff85b2b4354e6d16 Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Tue, 7 Jan 2014 23:39:49 -0800 Subject: Markdown reader: Allow hard line breaks in table cells. The \-newline form must be used; the two-space+newline form won't work, since in a table cell nearly every line ends with two spaces. --- src/Text/Pandoc/Readers/Markdown.hs | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index 3a5d29b4e..88d0bf439 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -1126,12 +1126,12 @@ multilineTableHeader headless = try $ do then liftM (map (:[]) . tail . splitStringByIndices (init indices)) $ lookAhead anyLine else return $ transpose $ map - (\ln -> tail $ splitStringByIndices (init indices) ln) + (tail . splitStringByIndices (init indices)) rawContent let aligns = zipWith alignType rawHeadsList lengths let rawHeads = if headless then replicate (length dashes) "" - else map unwords rawHeadsList + else map (unlines . map trim) rawHeadsList heads <- fmap sequence $ mapM (parseFromString (mconcat <$> many plain)) $ map trim rawHeads @@ -1188,7 +1188,7 @@ gridTableHeader headless = try $ do -- RST does not have a notion of alignments let rawHeads = if headless then replicate (length dashes) "" - else map unwords $ transpose + else map (unlines . map trim) $ transpose $ map (gridTableSplitLine indices) rawContent heads <- fmap sequence $ mapM (parseFromString parseBlocks . trim) rawHeads return (heads, aligns, indices) -- cgit v1.2.3 From b9b1546ed238ca8fd4d65a6e02fa7ecbf9a4be65 Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Thu, 9 Jan 2014 11:25:24 -0800 Subject: Markdown parser: be more permissive about citation keys. Keys may now start with an underscore as well as a letter. Underscores do not count as internal punctuation, but are treated like alphanumerics, so "key:_2008" will work, as it did not before. (This change was necessary to use keys generated by zotero.) Closes #1111, closes #1011. --- src/Text/Pandoc/Readers/Markdown.hs | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index 88d0bf439..3feafd362 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -1811,9 +1811,10 @@ citeKey = try $ do guard $ lastStrPos /= Just pos suppress_author <- option False (char '-' >> return True) char '@' - first <- letter - let internal p = try $ p >>~ lookAhead (letter <|> digit) - rest <- many $ letter <|> digit <|> internal (oneOf ":.#$%&-_+?<>~/") + first <- letter <|> char '_' + let regchar = satisfy (\c -> isAlphaNum c || c == '_') + let internal p = try $ p >>~ lookAhead regchar + rest <- many $ regchar <|> internal (oneOf ":.#$%&-+?<>~/") let key = first:rest return (suppress_author, key) -- cgit v1.2.3 From 6c59f060a769c7f312137d5c1a49cf878ea5b2a2 Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Mon, 20 Jan 2014 11:09:44 -0800 Subject: HTML reader: Fixed bug reading inline math with `$$`. See #225. --- src/Text/Pandoc/Readers/HTML.hs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs index 506fe7770..d1e4d0024 100644 --- a/src/Text/Pandoc/Readers/HTML.hs +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -476,8 +476,8 @@ pBlank = try $ do pTagContents :: Parser [Char] ParserState Inline pTagContents = - Math InlineMath `fmap` mathInline - <|> Math DisplayMath `fmap` mathDisplay + Math DisplayMath `fmap` mathDisplay + <|> Math InlineMath `fmap` mathInline <|> pStr <|> pSpace <|> smartPunctuation pTagContents -- cgit v1.2.3 From 9f3b2f6f5d06a4cf3142ffc74c8de4c1cc2bd928 Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Wed, 22 Jan 2014 22:07:13 -0800 Subject: Fixed mediawiki ordered list parsing. Closes #1122. --- src/Text/Pandoc/Readers/MediaWiki.hs | 25 +++++++++++++++---------- tests/mediawiki-reader.wiki | 4 ++-- 2 files changed, 17 insertions(+), 12 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/MediaWiki.hs b/src/Text/Pandoc/Readers/MediaWiki.hs index 8d8ea0199..794890eb6 100644 --- a/src/Text/Pandoc/Readers/MediaWiki.hs +++ b/src/Text/Pandoc/Readers/MediaWiki.hs @@ -149,9 +149,16 @@ inlinesInTags tag = try $ do blocksInTags :: String -> MWParser Blocks blocksInTags tag = try $ do (_,raw) <- htmlTag (~== TagOpen tag []) + let closer = if tag == "li" + then htmlTag (~== TagClose "li") + <|> lookAhead ( + htmlTag (~== TagOpen "li" []) + <|> htmlTag (~== TagClose "ol") + <|> htmlTag (~== TagClose "ul")) + else htmlTag (~== TagClose tag) if '/' `elem` raw -- self-closing tag then return mempty - else mconcat <$> manyTill block (htmlTag (~== TagClose tag)) + else mconcat <$> manyTill block closer charsInTags :: String -> MWParser [Char] charsInTags tag = try $ do @@ -381,15 +388,13 @@ bulletList = B.bulletList <$> orderedList :: MWParser Blocks orderedList = (B.orderedList <$> many1 (listItem '#')) - <|> (B.orderedList <$> (htmlTag (~== TagOpen "ul" []) *> spaces *> - many (listItem '#' <|> li) <* - optional (htmlTag (~== TagClose "ul")))) - <|> do (tag,_) <- htmlTag (~== TagOpen "ol" []) - spaces - items <- many (listItem '#' <|> li) - optional (htmlTag (~== TagClose "ol")) - let start = fromMaybe 1 $ safeRead $ fromAttrib "start" tag - return $ B.orderedListWith (start, DefaultStyle, DefaultDelim) items + <|> try + (do (tag,_) <- htmlTag (~== TagOpen "ol" []) + spaces + items <- many (listItem '#' <|> li) + optional (htmlTag (~== TagClose "ol")) + let start = fromMaybe 1 $ safeRead $ fromAttrib "start" tag + return $ B.orderedListWith (start, DefaultStyle, DefaultDelim) items) definitionList :: MWParser Blocks definitionList = B.definitionList <$> many1 defListItem diff --git a/tests/mediawiki-reader.wiki b/tests/mediawiki-reader.wiki index 26f4ef164..c0c22bec6 100644 --- a/tests/mediawiki-reader.wiki +++ b/tests/mediawiki-reader.wiki @@ -232,11 +232,11 @@ ends the list.

  • list item A2
    • -
      +
        #abc #def #ghi -
    +
    1. Amsterdam
      2. -- cgit v1.2.3 From 3127ab2b5ede10224f9f86722125573d34d7d3dd Mon Sep 17 00:00:00 2001 From: John MacFarlane Date: Tue, 4 Feb 2014 10:05:52 -0800 Subject: Slight code reorganization in endline. --- src/Text/Pandoc/Readers/Markdown.hs | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'src/Text/Pandoc/Readers') diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index 3feafd362..8a41cef49 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -1540,16 +1540,14 @@ endline :: MarkdownParser (F Inlines) endline = try $ do newline notFollowedBy blankline + -- parse potential list-starts differently if in a list: + st <- getState + when (stateParserContext st == ListItemState) $ notFollowedBy listStart guardDisabled Ext_lists_without_preceding_blankline <|> notFollowedBy listStart guardEnabled Ext_blank_before_blockquote <|> notFollowedBy emailBlockQuoteStart guardEnabled Ext_blank_before_header <|> notFollowedBy (char '#') -- atx header guardEnabled Ext_backtick_code_blocks >> notFollowedBy (() <$ (lookAhead (char '`') >> codeBlockFenced)) - -- parse potential list-starts differently if in a list: - st <- getState - when (stateParserContext st == ListItemState) $ do - notFollowedBy' bulletListStart - notFollowedBy' anyOrderedListStart (guardEnabled Ext_hard_line_breaks >> return (return B.linebreak)) <|> (guardEnabled Ext_ignore_line_breaks >> return mempty) <|> (return $ return B.space) -- cgit v1.2.3