f379edc · typeable/pandoc

git.iko.soy/typeable/pandoc

HTML writer: use character entities references when possible for HTML5.

commitf379edc4ad372f96d4a5cc7cd38292f095dfdf35 authorJohn MacFarlane <jgm@berkeley.edu> dateThu 1 Nov 2018, 16:08 (8 years ago) parent5350ce2

3 files changed+10−4

compare with master

unifiedsplit

MANUAL.txt+1−1 src/Text/Pandoc/Writers/HTML.hs+8−2 test/command/ascii.md+1−1

MANUAL.txt+1−1

@@ -859,7 +859,7 @@ Options affecting specific writers {.options}

859859`--ascii`

860860

861861: Use only ASCII characters in output. Currently supported for

862− XML and HTML formats (which use numerical entities instead of

862+ XML and HTML formats (which use entities instead of

863863 UTF-8 when this option is selected), groff ms

864864 (which use hexadecimal escapes), and to a limited degree

865865 LaTeX (which uses standard commands for accented

src/Text/Pandoc/Writers/HTML.hs+8−2

@@ -75,7 +75,8 @@ import Text.Pandoc.Templates

7575import Text.Pandoc.Walk

7676import Text.Pandoc.Writers.Math

7777import Text.Pandoc.Writers.Shared

78−import Text.Pandoc.XML (escapeStringForXML, fromEntities, toEntities)

78+import Text.Pandoc.XML (escapeStringForXML, fromEntities,

79+ toEntities, toHtml5Entities)

7980#if MIN_VERSION_blaze_markup(0,6,3)

8081#else

8182import Text.Blaze.Internal (preEscapedString, preEscapedText)

@@ -206,7 +207,12 @@ writeHtmlString' :: PandocMonad m

206207 => WriterState -> WriterOptions -> Pandoc -> m Text

207208writeHtmlString' st opts d = do

208209 (body, context) <- evalStateT (pandocToHtml opts d) st

209− (if writerPreferAscii opts then toEntities else id) <$>

210+ (if writerPreferAscii opts

211+ then

212+ if stHtml5 st

213+ then toHtml5Entities

214+ else toEntities

215+ else id) <$>

210216 case writerTemplate opts of

211217 Nothing -> return $ renderHtml' body

212218 Just tpl -> do

test/command/ascii.md+1−1

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

22pandoc -t html --ascii

33äéıå

44^D

5−<p>äéıå</p>

5+<p>äé&inodot;å</p>

66```

88```