6207bde · typeable/pandoc

git.iko.soy/typeable/pandoc

on master help sign in

CommonMark writer: add plain text fallbacks. (#4531)

6207bdequasicomputational8 years ago

MANUAL.txt+8−2

compare with master

unifiedsplit

@@ -3381,8 +3381,14 @@ Markdown allows it, but it has been made an extension so that it can

3381be disabled if desired.)

3382

3383The raw HTML is passed through unchanged in HTML, S5, Slidy, Slideous,

3384−DZSlides, EPUB, Markdown, Emacs Org mode, and Textile output, and suppressed

3384+DZSlides, EPUB, Markdown, CommonMark, Emacs Org mode, and Textile

3385−in other formats.

3385+output, and suppressed in other formats.

3386+

3387+In the CommonMark format, if `raw_html` is enabled, superscripts,

3388+subscripts, strikeouts and small capitals will be represented as HTML.

3389+Otherwise, plain-text fallbacks will be used. Note that even if

3390+`raw_html` is disabled, tables will be rendered with HTML syntax if

3391+they cannot use pipe syntax.

3386

3392

3387#### Extension: `markdown_in_html_blocks` ####

3393#### Extension: `markdown_in_html_blocks` ####

3388

3394

src/Text/Pandoc/Writers/CommonMark.hs+42−10

@@ -45,7 +45,7 @@ import Network.HTTP (urlEncode)

45import Text.Pandoc.Class (PandocMonad)

46import Text.Pandoc.Definition

47import Text.Pandoc.Options

48−import Text.Pandoc.Shared (isTightList, linesToPara, substitute)

48+import Text.Pandoc.Shared (isTightList, linesToPara, substitute, capitalize)

49import Text.Pandoc.Templates (renderTemplate')

50import Text.Pandoc.Walk (query, walk, walkM)

51import Text.Pandoc.Writers.HTML (writeHtml5String, tagWithAttributes)

@@ -253,18 +253,34 @@ inlineToNodes opts (Strong xs) = (node STRONG (inlinesToNodes opts xs) :)

253inlineToNodes opts (Strikeout xs) =

254 if isEnabled Ext_strikeout opts

255 then (node (CUSTOM_INLINE "~~" "~~") (inlinesToNodes opts xs) :)

256+ else if isEnabled Ext_raw_html opts

256− else ((node (HTML_INLINE (T.pack "<s>")) [] : inlinesToNodes opts xs ++

257+ then ((node (HTML_INLINE (T.pack "<s>")) [] : inlinesToNodes opts xs ++

257− [node (HTML_INLINE (T.pack "</s>")) []]) ++ )

258+ [node (HTML_INLINE (T.pack "</s>")) []]) ++ )

259+ else (inlinesToNodes opts xs ++)

258inlineToNodes opts (Superscript xs) =

260inlineToNodes opts (Superscript xs) =

261+ if isEnabled Ext_raw_html opts

259− ((node (HTML_INLINE (T.pack "")) [] : inlinesToNodes opts xs ++

262+ then ((node (HTML_INLINE (T.pack "")) [] : inlinesToNodes opts xs ++

260− [node (HTML_INLINE (T.pack "")) []]) ++ )

263+ [node (HTML_INLINE (T.pack "")) []]) ++ )

264+ else case traverse toSuperscriptInline xs of

265+ Nothing ->

266+ ((node (TEXT (T.pack "^(")) [] : inlinesToNodes opts xs ++

267+ [node (TEXT (T.pack ")")) []]) ++ )

268+ Just xs' -> (inlinesToNodes opts xs' ++)

261inlineToNodes opts (Subscript xs) =

269inlineToNodes opts (Subscript xs) =

270+ if isEnabled Ext_raw_html opts

262− ((node (HTML_INLINE (T.pack "")) [] : inlinesToNodes opts xs ++

271+ then ((node (HTML_INLINE (T.pack "")) [] : inlinesToNodes opts xs ++

263− [node (HTML_INLINE (T.pack "")) []]) ++ )

272+ [node (HTML_INLINE (T.pack "")) []]) ++ )

273+ else case traverse toSubscriptInline xs of

274+ Nothing ->

275+ ((node (TEXT (T.pack "_(")) [] : inlinesToNodes opts xs ++

276+ [node (TEXT (T.pack ")")) []]) ++ )

277+ Just xs' -> (inlinesToNodes opts xs' ++)

264inlineToNodes opts (SmallCaps xs) =

278inlineToNodes opts (SmallCaps xs) =

279+ if isEnabled Ext_raw_html opts

265− ((node (HTML_INLINE (T.pack "")) []

280+ then ((node (HTML_INLINE (T.pack "")) []

266− : inlinesToNodes opts xs ++

281+ : inlinesToNodes opts xs ++

267− [node (HTML_INLINE (T.pack "")) []]) ++ )

282+ [node (HTML_INLINE (T.pack "")) []]) ++ )

283+ else (inlinesToNodes opts (capitalize xs) ++)

268inlineToNodes opts (Link _ ils (url,tit)) =

284inlineToNodes opts (Link _ ils (url,tit)) =

269 (node (LINK (T.pack url) (T.pack tit)) (inlinesToNodes opts ils) :)

285 (node (LINK (T.pack url) (T.pack tit)) (inlinesToNodes opts ils) :)

270-- title beginning with fig: indicates implicit figure

286-- title beginning with fig: indicates implicit figure

@@ -319,3 +335,19 @@ inlineToNodes opts (Span attr ils) =

319inlineToNodes opts (Cite _ ils) = (inlinesToNodes opts ils ++)

335inlineToNodes opts (Cite _ ils) = (inlinesToNodes opts ils ++)

320inlineToNodes _ (Note _) = id -- should not occur

336inlineToNodes _ (Note _) = id -- should not occur

321-- we remove Note elements in preprocessing

337-- we remove Note elements in preprocessing

338+

339+toSubscriptInline :: Inline -> Maybe Inline

340+toSubscriptInline Space = Just Space

341+toSubscriptInline (Span attr ils) = Span attr <$> traverse toSubscriptInline ils

342+toSubscriptInline (Str s) = Str <$> traverse toSubscript s

343+toSubscriptInline LineBreak = Just LineBreak

344+toSubscriptInline SoftBreak = Just SoftBreak

345+toSubscriptInline _ = Nothing

346+

347+toSuperscriptInline :: Inline -> Maybe Inline

348+toSuperscriptInline Space = Just Space

349+toSuperscriptInline (Span attr ils) = Span attr <$> traverse toSuperscriptInline ils

350+toSuperscriptInline (Str s) = Str <$> traverse toSuperscript s

351+toSuperscriptInline LineBreak = Just LineBreak

352+toSuperscriptInline SoftBreak = Just SoftBreak

353+toSuperscriptInline _ = Nothing

src/Text/Pandoc/Writers/Markdown.hs+1−28

@@ -38,7 +38,7 @@ module Text.Pandoc.Writers.Markdown (writeMarkdown, writePlain) where

38import Prelude

39import Control.Monad.Reader

40import Control.Monad.State.Strict

41−import Data.Char (chr, isPunctuation, isSpace, ord, isAlphaNum)

41+import Data.Char (isPunctuation, isSpace, isAlphaNum)

42import Data.Default

43import qualified Data.HashMap.Strict as H

44import Data.List (find, group, intersperse, sortBy, stripPrefix, transpose)

@@ -1249,33 +1249,6 @@ makeMathPlainer = walk go

1249 go (Emph xs) = Span nullAttr xs

1250 go x = x

1251

1252−toSuperscript :: Char -> Maybe Char

1253−toSuperscript '1' = Just '\x00B9'

1254−toSuperscript '2' = Just '\x00B2'

1255−toSuperscript '3' = Just '\x00B3'

1256−toSuperscript '+' = Just '\x207A'

1257−toSuperscript '-' = Just '\x207B'

1258−toSuperscript '=' = Just '\x207C'

1259−toSuperscript '(' = Just '\x207D'

1260−toSuperscript ')' = Just '\x207E'

1261−toSuperscript c

1262− | c >= '0' && c <= '9' =

1263− Just $ chr (0x2070 + (ord c - 48))

1264− | isSpace c = Just c

1265− | otherwise = Nothing

1266−

1267−toSubscript :: Char -> Maybe Char

1268−toSubscript '+' = Just '\x208A'

1269−toSubscript '-' = Just '\x208B'

1270−toSubscript '=' = Just '\x208C'

1271−toSubscript '(' = Just '\x208D'

1272−toSubscript ')' = Just '\x208E'

1273−toSubscript c

1274− | c >= '0' && c <= '9' =

1275− Just $ chr (0x2080 + (ord c - 48))

1276− | isSpace c = Just c

1277− | otherwise = Nothing

1278−

1279lineBreakToSpace :: Inline -> Inline

1252lineBreakToSpace :: Inline -> Inline

1280lineBreakToSpace LineBreak = Space

1253lineBreakToSpace LineBreak = Space

1281lineBreakToSpace SoftBreak = Space

1254lineBreakToSpace SoftBreak = Space

src/Text/Pandoc/Writers/Shared.hs+30−1

@@ -48,12 +48,15 @@ module Text.Pandoc.Writers.Shared (

48 , lookupMetaString

49 , stripLeadingTrailingSpace

50 , groffEscape

51+ , toSubscript

52+ , toSuperscript

51 )

53 )

52where

54where

53import Prelude

55import Prelude

54import Control.Monad (zipWithM)

56import Control.Monad (zipWithM)

55import Data.Aeson (FromJSON (..), Result (..), ToJSON (..), Value (Object),

57import Data.Aeson (FromJSON (..), Result (..), ToJSON (..), Value (Object),

56 encode, fromJSON)

58 encode, fromJSON)

59+import Data.Char (chr, ord, isAscii, isSpace)

57import qualified Data.HashMap.Strict as H

60import qualified Data.HashMap.Strict as H

58import Data.List (groupBy, intersperse, transpose)

61import Data.List (groupBy, intersperse, transpose)

59import qualified Data.Map as M

62import qualified Data.Map as M

@@ -68,7 +71,6 @@ import Text.Pandoc.Shared (stringify)

68import Text.Pandoc.UTF8 (toStringLazy)

71import Text.Pandoc.UTF8 (toStringLazy)

69import Text.Pandoc.XML (escapeStringForXML)

72import Text.Pandoc.XML (escapeStringForXML)

70import Text.Printf (printf)

73import Text.Printf (printf)

71−import Data.Char (isAscii, ord)

73-- | Create JSON value for template from a 'Meta' and an association list

75-- | Create JSON value for template from a 'Meta' and an association list

74-- of variables, specified at the command line or in the writer.

76-- of variables, specified at the command line or in the writer.

@@ -392,3 +394,30 @@ groffEscape = T.concatMap toUchar

392 | isAscii c = T.singleton c

394 | isAscii c = T.singleton c

393 | otherwise = T.pack $ printf "\\[u%04X]" (ord c)

395 | otherwise = T.pack $ printf "\\[u%04X]" (ord c)

394

396

397+

398+toSuperscript :: Char -> Maybe Char

399+toSuperscript '1' = Just '\x00B9'

400+toSuperscript '2' = Just '\x00B2'

401+toSuperscript '3' = Just '\x00B3'

402+toSuperscript '+' = Just '\x207A'

403+toSuperscript '-' = Just '\x207B'

404+toSuperscript '=' = Just '\x207C'

405+toSuperscript '(' = Just '\x207D'

406+toSuperscript ')' = Just '\x207E'

407+toSuperscript c

408+ | c >= '0' && c <= '9' =

409+ Just $ chr (0x2070 + (ord c - 48))

410+ | isSpace c = Just c

411+ | otherwise = Nothing

412+

413+toSubscript :: Char -> Maybe Char

414+toSubscript '+' = Just '\x208A'

415+toSubscript '-' = Just '\x208B'

416+toSubscript '=' = Just '\x208C'

417+toSubscript '(' = Just '\x208D'

418+toSubscript ')' = Just '\x208E'

419+toSubscript c

420+ | c >= '0' && c <= '9' =

421+ Just $ chr (0x2080 + (ord c - 48))

422+ | isSpace c = Just c

423+ | otherwise = Nothing

test/command/4528.mdnew file+156

@@ -0,0 +1,156 @@

1+# Rendering small caps, superscripts and subscripts with and without `raw_html`

3+## Small caps

5+```

6+% pandoc --wrap=none -f latex -t commonmark-raw_html

7+This has \textsc{small caps} in it.

8+^D

9+This has SMALL CAPS in it.

10+```

11+

12+```

13+% pandoc --wrap=none -f latex -t commonmark+raw_html

14+This has \textsc{small caps} in it.

15+^D

16+This has small caps in it.

17+```

18+```

19+

20+```

21+% pandoc --wrap=none -f latex -t markdown_strict+raw_html

22+This has \textsc{small caps} in it.

23+^D

24+This has small caps in it.

25+```

26+

27+## Strikeout

28+

29+```

30+% pandoc --wrap=none -f html -t commonmark-raw_html-strikeout

31+This has <s>strikeout</s> in it.

32+^D

33+This has strikeout in it.

34+

35+```

36+% pandoc --wrap=none -f html -t commonmark+raw_html-strikeout

37+This has <s>strikeout</s> in it.

38+^D

39+This has <s>strikeout</s> in it.

40+```

41+

42+```

43+% pandoc --wrap=none -f html -t commonmark-raw_html+strikeout

44+This has <s>strikeout</s> in it.

45+^D

46+This has ~~strikeout~~ in it.

47+```

48+

49+```

50+% pandoc --wrap=none -f html -t commonmark+raw_html+strikeout

51+This has <s>strikeout</s> in it.

52+^D

53+This has ~~strikeout~~ in it.

54+```

55+

56+```

57+% pandoc --wrap=none -f html -t markdown_strict-raw_html-strikeout

58+This has <s>strikeout</s> in it.

59+^D

60+This has strikeout in it.

61+```

62+

63+```

64+% pandoc --wrap=none -f html -t markdown_strict+raw_html-strikeout

65+This has <s>strikeout</s> in it.

66+^D

67+This has <s>strikeout</s> in it.

68+```

69+

70+```

71+% pandoc --wrap=none -f html -t markdown_strict-raw_html+strikeout

72+This has <s>strikeout</s> in it.

73+^D

74+This has ~~strikeout~~ in it.

75+```

76+

77+```

78+% pandoc --wrap=none -f html -t markdown_strict+raw_html+strikeout

79+This has <s>strikeout</s> in it.

80+^D

81+This has ~~strikeout~~ in it.

82+```

83+

84+## Superscript

85+

86+```

87+% pandoc --wrap=none -f html -t commonmark-raw_html

88+This has superscript in it and 2 3 again. With emphasis: 2 3. With letters: foo. With a span: 2.

89+^D

90+This has ^(superscript) in it and ² ³ again. With emphasis: ^(*2* 3). With letters: ^(foo). With a span: ².

91+```

92+

93+```

94+% pandoc --wrap=none -f html -t commonmark+raw_html

95+This has superscript in it and 2 again.

96+^D

97+This has superscript in it and 2 again.

98+```

99+

100+```

101+% pandoc --wrap=none -f html -t markdown_strict-raw_html-superscript

102+This has superscript in it and 2 again.

103+^D

104+This has ^(superscript) in it and ² again.

105+```

106+

107+```

108+% pandoc --wrap=none -f html -t markdown_strict+raw_html-superscript

109+This has superscript in it and 2 again.

110+^D

111+This has superscript in it and 2 again.

112+```

113+

114+```

115+% pandoc --wrap=none -f html -t markdown_strict+raw_html+superscript

116+This has superscript in it and 2 again.

117+^D

118+This has ^superscript^ in it and ^2^ again.

119+```

120+

121+## Subscript

122+

123+```

124+% pandoc --wrap=none -f html -t commonmark-raw_html

125+This has subscript in it and 2 3 again. With emphasis: 2 3. With letters: foo. With a span: 2.

126+^D

127+This has \_(subscript) in it and ₂ ₃ again. With emphasis: \_(*2* 3). With letters: \_(foo). With a span: ₂.

128+```

129+

130+```

131+% pandoc --wrap=none -f html -t commonmark+raw_html

132+This has subscript in it and 2 again.

133+^D

134+This has subscript in it and 2 again.

135+```

136+

137+```

138+% pandoc --wrap=none -f html -t markdown_strict-raw_html-subscript

139+This has subscript in it and 2 again.

140+^D

141+This has _(subscript) in it and ₂ again.

142+```

143+

144+```

145+% pandoc --wrap=none -f html -t markdown_strict+raw_html-subscript

146+This has subscript in it and 2 again.

147+^D

148+This has subscript in it and 2 again.

149+```

150+

151+```

152+% pandoc --wrap=none -f html -t markdown_strict+raw_html+subscript

153+This has subscript in it and 2 again.

154+^D

155+This has ~subscript~ in it and ~2~ again.

156+```