edc6510 · typeable/pandoc

git.iko.soy/typeable/pandoc

Fix parsing of citations and quotes after parentheses.

Starting with pandoc 2.4, citations and quoted inlines were no longer recognized after parentheses. This is because of commit 9b0bd4ec6f5c9125efb3e36232e6d1f6ac08a728, which is reverted here. The point of that commit was to allow relocation of soft line breaks to before an abbreviation, so that a nonbreaking space could be added after the abbreviation. Now we simply leave the soft line break in place, even though this means that we won't get a nonbreaking space after "Mr." at the end of a line (and in LaTeX this may result in a longer intersentential space). Those who care about this issue should take care not to end lines with an abbreviation, or to insert nonbreaking spaces manually. Closes #5099.

commitedc651059ee617cf36b511de080a646d2e6513a4 authorJohn MacFarlane <jgm@berkeley.edu> dateSun 25 Nov 2018, 21:57 (8 years ago) parent839bd3c

4 files changed+17−19

compare with master

unifiedsplit

src/Text/Pandoc/Readers/Markdown.hs+2−6 test/command/4635.md+2−2 test/command/5099.md+13 test/command/md-abbrevs.md−11

src/Text/Pandoc/Readers/Markdown.hs+2−6

@@ -1586,7 +1586,6 @@ symbol = do

15861586 <|> try (do lookAhead $ char '\\'

15871587 notFollowedBy' (() <$ rawTeXBlock)

15881588 char '\\')

1589− updateLastStrPos

15901589 return $ return $ B.str [result]

15911590

15921591-- parses inline code, between n `s and n `s

@@ -1633,7 +1632,7 @@ enclosure c = do

16331632 3 -> three c

16341633 2 -> two c mempty

16351634 1 -> one c mempty

1636− _ -> updateLastStrPos >> return (return $ B.str cs)

1635+ _ -> return (return $ B.str cs)

16371636

16381637ender :: PandocMonad m => Char -> Int -> MarkdownParser m ()

16391638ender c n = try $ do

@@ -1717,13 +1716,12 @@ nonEndline = satisfy (/='\n')

17171716

17181717str :: PandocMonad m => MarkdownParser m (F Inlines)

17191718str = do

1720− canRelocateSpace <- notAfterString

17211719 result <- many1 (alphaNum <|> try (char '.' <* notFollowedBy (char '.')))

17221720 updateLastStrPos

17231721 (do guardEnabled Ext_smart

17241722 abbrevs <- getOption readerAbbreviations

17251723 if not (null result) && last result == '.' && result `Set.member` abbrevs

1726− then try (do ils <- whitespace <|> endline

1724+ then try (do ils <- whitespace

17271725 -- ?? lookAhead alphaNum

17281726 -- replace space after with nonbreaking space

17291727 -- if softbreak, move before abbrev if possible (#4635)

@@ -1732,8 +1730,6 @@ str = do

17321730 case B.toList ils' of

17331731 [Space] ->

17341732 return (B.str result <> B.str "\160")

1735− [SoftBreak] | canRelocateSpace ->

1736− return (ils' <> B.str result <> B.str "\160")

17371733 _ -> return (B.str result <> ils'))

17381734 <|> return (return (B.str result))

17391735 else return (return (B.str result)))

test/command/4635.md+2−2

@@ -19,7 +19,7 @@ foo)

1919cf.

2020foo

2121^D

22−[Para [Str "cf.\160foo"]]

22+[Para [Str "cf.",SoftBreak,Str "foo"]]

2323```

2424

2525```

@@ -27,5 +27,5 @@ foo

2727a cf.

2828foo

2929^D

30−[Para [Str "a",SoftBreak,Str "cf.\160foo"]]

30+[Para [Str "a",Space,Str "cf.",SoftBreak,Str "foo"]]

3131```

test/command/5099.mdnew file+13

@@ -0,0 +1,13 @@

1+```

2+% pandoc -t native

3+(@citation

4+^D

5+[Para [Str "(",Cite [Citation {citationId = "citation", citationPrefix = [], citationSuffix = [], citationMode = AuthorInText, citationNoteNum = 0, citationHash = 0}] [Str "@citation"]]]

6+```

8+```

9+% pandoc -t native

10+('asd')

11+^D

12+[Para [Str "(",Quoted SingleQuote [Str "asd"],Str ")"]]

13+```

test/command/md-abbrevs.md−11

@@ -9,17 +9,6 @@ Mr. Bob

99[Para [Str "Mr.\160Bob"]]

1010```

1111

12−Here pandoc readjusts the softbreak so that the nonbreaking

13−space can be inserted:

14−

15−```

16−% pandoc -t native

17−Hi Mr.

18−Bob

19−^D

20−[Para [Str "Hi",SoftBreak,Str "Mr.\160Bob"]]

21−```

22−

2312If you don't want this to happen you can escape the period:

2413

2514```