From d71b013841f3c9c8c595591e312a31df16a728cb Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Mon, 4 Aug 2014 18:39:39 -0700
Subject: HTML reader:  ignore <?xml..> and <DOCTYPE..> tags.

Previously they were parsed as raw.
---
 src/Text/Pandoc/Readers/HTML.hs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'src/Text')

diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs
index 1ded83ff1..a8df1394c 100644
--- a/src/Text/Pandoc/Readers/HTML.hs
+++ b/src/Text/Pandoc/Readers/HTML.hs
@@ -289,7 +289,7 @@ fixPlains inList bs = if any isParaish bs'
 pRawTag :: TagParser String
 pRawTag = do
   tag <- pAnyTag
-  let ignorable x = x `elem` ["html","head","body"]
+  let ignorable x = x `elem` ["html","head","body","DOCTYPE","?xml"]
   if tagOpen ignorable (const True) tag || tagClose ignorable tag
      then return []
      else return $ renderTags' [tag]
-- 
cgit v1.2.3