d71b013 · typeable/pandoc

git.iko.soy/typeable/pandoc

HTML reader: ignore <?xml..> and <DOCTYPE..> tags.

Previously they were parsed as raw.

commitd71b013841f3c9c8c595591e312a31df16a728cb authorJohn MacFarlane <jgm@berkeley.edu> dateMon 4 Aug 2014, 18:39 (12 years ago) parent2fabdf9

1 file changed+1−1

unifiedsplit

src/Text/Pandoc/Readers/HTML.hs+1−1

@@ -289,7 +289,7 @@ fixPlains inList bs = if any isParaish bs'

289289pRawTag :: TagParser String

290290pRawTag = do

291291 tag <- pAnyTag

292− let ignorable x = x `elem` ["html","head","body"]

292+ let ignorable x = x `elem` ["html","head","body","DOCTYPE","?xml"]

293293 if tagOpen ignorable (const True) tag || tagClose ignorable tag

294294 then return []

295295 else return $ renderTags' [tag]