From 0646eef97691794eeac5549db18ac82cb6b84576 Mon Sep 17 00:00:00 2001
From: fiddlosopher <fiddlosopher@788f1e2b-df1e-0410-8736-df70ead52e1b>
Date: Wed, 24 Jan 2007 17:43:39 +0000
Subject: Rewrote 'extractTagType' in HTML reader so that it doesn't use
 regexs.

git-svn-id: https://pandoc.googlecode.com/svn/trunk@507 788f1e2b-df1e-0410-8736-df70ead52e1b
---
 src/Text/Pandoc/Readers/HTML.hs | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

(limited to 'src')

diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs
index b3ddc8985..66b55c448 100644
--- a/src/Text/Pandoc/Readers/HTML.hs
+++ b/src/Text/Pandoc/Readers/HTML.hs
@@ -40,7 +40,6 @@ module Text.Pandoc.Readers.HTML (
                                  htmlBlockElement 
                                 ) where
 
-import Text.Regex ( matchRegex, mkRegex )
 import Text.ParserCombinators.Parsec
 import Text.ParserCombinators.Pandoc
 import Text.Pandoc.Definition
@@ -84,10 +83,13 @@ inlinesTilEnd tag = try (do
   return inlines)
 
 -- | Extract type from a tag:  e.g. 'br' from '<br>'
-extractTagType tag = 
-    case (matchRegex (mkRegex  "<[[:space:]]*/?([A-Za-z0-9]+)") tag) of
-          Just [match]   -> (map toLower match)
-          Nothing        -> ""
+extractTagType :: String -> String
+extractTagType "" = ""
+extractTagType ('<':rest) =  
+  if (not (null rest)) && (last rest == '>')
+    then map toLower $ removeLeadingTrailingSpace (init rest) 
+    else ""
+extractTagType _ = ""
 
 -- | Parse any HTML tag (closing or opening) and return text of tag
 anyHtmlTag = try (do
-- 
cgit v1.2.3