1433aaa · typeable/pandoc

git.iko.soy/typeable/pandoc

HTML reader: don't parse `data-id` as `id` attribute.

And similarly don't parse any `data-X` as `X` when `X` is a valid HTML attribute. Reported in comment on #5415.

commit1433aaa4c35af84fbe00ecf971acd1414da6dea8 authorJohn MacFarlane <jgm@berkeley.edu> dateWed 12 Feb 2020, 08:46 (7 years ago) parentfae8ea3

1 file changed+9−1

unifiedsplit

src/Text/Pandoc/Readers/HTML.hs+9−1

@@ -52,6 +52,7 @@ import Text.Pandoc.CSS (foldOrElse, pickStyleAttrProps)

5252import Text.Pandoc.Definition

5353import Text.Pandoc.Readers.LaTeX (rawLaTeXInline)

5454import Text.Pandoc.Readers.LaTeX.Types (Macro)

55+import Text.Pandoc.XML (html5Attributes, html4Attributes, rdfaAttributes)

5556import Text.Pandoc.Error

5657import Text.Pandoc.Logging

5758import Text.Pandoc.Options (

@@ -835,7 +836,14 @@ mathMLToTeXMath s = writeTeX <$> readMathML s

835836

836837toStringAttr :: [(Text, Text)] -> [(Text, Text)]

837838toStringAttr = map go

838− where go (x,y) = (fromMaybe x $ T.stripPrefix "data-" x, y)

839+ where

840+ go (x,y) =

841+ case T.stripPrefix "data-" x of

842+ Nothing -> (x,y)

843+ Just x' -> if x' `Set.member` (html5Attributes <>

844+ html4Attributes <> rdfaAttributes)

845+ then (x,y)

846+ else (x',y)

839847

840848pScriptMath :: PandocMonad m => TagParser m Inlines

841849pScriptMath = try $ do