c66921f · typeable/pandoc

git.iko.soy/typeable/pandoc

Markdown reader: better handling of intraword _.

The 'str' parser now reads internal _'s as part of the string. This prevents pandoc from getting started looking for an emphasized block, which can cause exponential slowdowns in some cases. Resolves Issue #182.

commitc66921f2acea456af527b93e2daa1d8594798642 authorJohn MacFarlane <jgm@berkeley.edu> dateMon 6 Dec 2010, 22:11 (16 years ago) parent7864f30

1 file changed+5−3

compare with master

unifiedsplit

src/Text/Pandoc/Readers/Markdown.hs+5−3

src/Text/Pandoc/Readers/Markdown.hs+5−3

@@ -47,7 +47,7 @@ import Text.Pandoc.Readers.HTML ( rawHtmlBlock, anyHtmlBlockTag,

4747 htmlBlockElement, htmlComment, unsanitaryURI )

4848import Text.Pandoc.CharacterReferences ( decodeCharacterReferences )

4949import Text.ParserCombinators.Parsec

50−import Control.Monad (when, liftM, unless, guard)

50+import Control.Monad (when, liftM, guard)

5151import Text.TeXMath.Macros (applyMacros, Macro, pMacroDefinition)

5252

5353-- | Read markdown from an input string and return a Pandoc document.

@@ -121,7 +121,7 @@ inlinesInBalancedBrackets :: GenParser Char ParserState Inline

121121inlinesInBalancedBrackets parser = try $ do

122122 char '['

123123 result <- manyTill ( (do lookAhead $ try $ do (Str res) <- parser

124− unless (res == "[") pzero

124+ guard (res == "[")

125125 bal <- inlinesInBalancedBrackets parser

126126 return $ [Str "["] ++ bal ++ [Str "]"])

127127 <|> (count 1 parser))

@@ -1138,7 +1138,9 @@ strChar = noneOf (specialChars ++ " \t\n")

11381138

11391139str :: GenParser Char ParserState Inline

11401140str = do

1141− result <- many1 strChar

1141+ a <- strChar

1142+ as <- many (strChar <|> (try $ char '_' >>~ lookAhead strChar))

1143+ let result = a:as

11421144 state <- getState

11431145 let spacesToNbr = map (\c -> if c == ' ' then '\160' else c)

11441146 if stateSmart state