lee/pandoc
1
0
Fork 0
mirror of https://github.com/jgm/pandoc.git synced 2026-08-26 18:26:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Recognize data-external when reading HTML img tags (#7429)

Browse Source 
Preserve all attributes in img tags.  If attributes have a `data-`
prefix, it will be stripped.  In particular, this preserves a
`data-external` attribute as an `external` attribute in the pandoc AST.
This commit is contained in:
Michael Hoffmann
2021-07-06 16:06:29 -07:00
committed by GitHub
parent e7f8cc5786
commit e56e2b0e0b
2 changed files with 9 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/Text/Pandoc/Readers/HTML.hs
+3 -8
View File
@@ -722,17 +722,12 @@ pLink = try $ do
pImage :: PandocMonad m => TagParser m Inlines
pImage = do
tag <- pSelfClosing (=="img") (isJust . lookup "src")
tag@(TagOpen _ attr') <- pSelfClosing (=="img") (isJust . lookup "src")
url <- canonicalizeUrl $ fromAttrib "src" tag
let title = fromAttrib "title" tag
let alt = fromAttrib "alt" tag
let uid = fromAttrib "id" tag
let cls = T.words $ fromAttrib "class" tag
let getAtt k = case fromAttrib k tag of
"" -> []
v -> [(k, v)]
let kvs = concatMap getAtt ["width", "height", "sizes", "srcset"]
return $ B.imageWith (uid, cls, kvs) (escapeURI url) title (B.text alt)
let attr = toAttr $ filter (\(k,_) -> k /= "alt" && k /= "title" && k /= "src") attr'
return $ B.imageWith attr (escapeURI url) title (B.text alt)
pSvg :: PandocMonad m => TagParser m Inlines
pSvg = do
test/Tests/Readers/HTML.hs
+6
View File
@@ -74,6 +74,12 @@ tests = [ testGroup "base tag"
[ test html "anchor without href" $ "<a name=\"anchor\"/>" =?>
plain (spanWith ("anchor",[],[]) mempty)
]
, testGroup "img"
[ test html "data-external attribute" $ "<img data-external=\"1\" src=\"http://example.com/stickman.gif\">" =?>
plain (imageWith ("", [], [("external", "1")]) "http://example.com/stickman.gif" "" "")
, test html "title" $ "<img title=\"The title\" src=\"http://example.com/stickman.gif\">" =?>
plain (imageWith ("", [], []) "http://example.com/stickman.gif" "The title" "")
]
, testGroup "lang"
[ test html "lang on <html>" $ "<html lang=\"es\">hola" =?>
setMeta "lang" (text "es") (doc (plain (text "hola")))