From 3e61333af0f5ac1cdb045bdab0293f03e2e1e39e Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Sat, 1 Jan 2011 22:46:30 -0800
Subject: Fixed regression in markdown reader.

'(_hi_)' was being parsed with literal underscores (no emphasis).
The fix:  the 'str' parser now only parses alphanumerics and
embedded underscores.  All other symbols are handled by the
'symbol' parser.  This has a slight effect on the AST, since
you'll get [Str "hi",Str ":"] insntead of [Str "hi:"].  But there
should not be a visible effect in any of the writers.

Thanks to gwern for pointing out the regression.
---
 src/Text/Pandoc/Readers/Markdown.hs | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'src')

diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs
index 6ba19d7a1..feeb1a69c 100644
--- a/src/Text/Pandoc/Readers/Markdown.hs
+++ b/src/Text/Pandoc/Readers/Markdown.hs
@@ -970,7 +970,7 @@ exampleRef = try $ do
 
 symbol :: GenParser Char ParserState Inline
 symbol = do 
-  result <- oneOf specialCharsMinusLt
+  result <- noneOf "<\n\t "
   return $ Str [result]
 
 -- parses inline code, between n `s and n `s
@@ -1057,8 +1057,8 @@ strChar = noneOf (specialChars ++ " \t\n")
 
 str :: GenParser Char ParserState Inline
 str = do
-  a <- strChar
-  as <- many (strChar <|> (try $ char '_' >>~ lookAhead alphaNum))
+  a <- alphaNum
+  as <- many $ alphaNum <|> (try $ char '_' >>~ lookAhead alphaNum)
   let result = a:as
   state <- getState
   let spacesToNbr = map (\c -> if c == ' ' then '\160' else c)
-- 
cgit v1.2.3