d792427 · typeable/pandoc

git.iko.soy/typeable/pandoc

HTML writer: use numeric character references with `--ascii`.

Previously we used named character references with html5 output. But these aren't valid XML, and we aim to produce html5 that is also valid XHTML (polyglot markup). (This is also needed for epub3.) Closes #5718.

commitd79242796b5bfa24788d30b239de3b15c0ed326c authorJohn MacFarlane <jgm@berkeley.edu> dateMon 2 Sep 2019, 20:36 (7 years ago) parent5e708eb

2 files changed+3−7

compare with master

unifiedsplit

src/Text/Pandoc/Writers/HTML.hs+2−6 test/command/ascii.md+1−1

src/Text/Pandoc/Writers/HTML.hs+2−6

@@ -59,8 +59,7 @@ import Text.DocTemplates (Context(..))

5959import Text.Pandoc.Walk

6060import Text.Pandoc.Writers.Math

6161import Text.Pandoc.Writers.Shared

62−import Text.Pandoc.XML (escapeStringForXML, fromEntities,

63− toEntities, toHtml5Entities)

62+import Text.Pandoc.XML (escapeStringForXML, fromEntities, toEntities)

6463#if MIN_VERSION_blaze_markup(0,6,3)

6564#else

6665import Text.Blaze.Internal (preEscapedString, preEscapedText)

@@ -207,10 +206,7 @@ writeHtmlString' :: PandocMonad m

207206writeHtmlString' st opts d = do

208207 (body, context) <- evalStateT (pandocToHtml opts d) st

209208 (if writerPreferAscii opts

210− then

211− if stHtml5 st

212− then toHtml5Entities

213− else toEntities

209+ then toEntities

214210 else id) <$>

215211 case writerTemplate opts of

216212 Nothing -> return $ renderHtml' body

test/command/ascii.md+1−1

@@ -2,7 +2,7 @@

22pandoc -t html --ascii

33äéıå

44^D

5−<p>äé&imath;å</p>

5+<p>äéıå</p>

66```

88```