95f2726 · typeable/pandoc

git.iko.soy/typeable/pandoc

on master help sign in

Added readerAbbreviations to ParserState.

95f2726John MacFarlane10 years ago

src/Text/Pandoc/Options.hs+11

compare with master

unifiedsplit

@@ -47,6 +47,7 @@ module Text.Pandoc.Options ( module Text.Pandoc.Extensions

47 ) where

48import Data.Data (Data)

49import Data.Default

50+import qualified Data.Set as Set

50import Data.Typeable (Typeable)

51import Data.Typeable (Typeable)

51import GHC.Generics (Generic)

52import GHC.Generics (Generic)

52import Text.Pandoc.Extensions

53import Text.Pandoc.Extensions

@@ -60,6 +61,7 @@ data ReaderOptions = ReaderOptions{

60 , readerApplyMacros :: Bool -- ^ Apply macros to TeX math

61 , readerApplyMacros :: Bool -- ^ Apply macros to TeX math

61 , readerIndentedCodeClasses :: [String] -- ^ Default classes for

62 , readerIndentedCodeClasses :: [String] -- ^ Default classes for

62 -- indented code blocks

63 -- indented code blocks

64+ , readerAbbreviations :: Set.Set String -- ^ Strings to treat as abbreviations

63 , readerDefaultImageExtension :: String -- ^ Default extension for images

65 , readerDefaultImageExtension :: String -- ^ Default extension for images

64 , readerTrackChanges :: TrackChanges

66 , readerTrackChanges :: TrackChanges

65} deriving (Show, Read, Data, Typeable, Generic)

67} deriving (Show, Read, Data, Typeable, Generic)

@@ -72,10 +74,19 @@ instance Default ReaderOptions

72 , readerTabStop = 4

74 , readerTabStop = 4

73 , readerApplyMacros = True

75 , readerApplyMacros = True

74 , readerIndentedCodeClasses = []

76 , readerIndentedCodeClasses = []

77+ , readerAbbreviations = defaultAbbrevs

75 , readerDefaultImageExtension = ""

78 , readerDefaultImageExtension = ""

76 , readerTrackChanges = AcceptChanges

79 , readerTrackChanges = AcceptChanges

77 }

80 }

82+defaultAbbrevs :: Set.Set String

83+defaultAbbrevs = Set.fromList

84+ [ "Mr.", "Mrs.", "Ms.", "Capt.", "Dr.", "Prof.",

85+ "Gen.", "Gov.", "e.g.", "i.e.", "Sgt.", "St.",

86+ "vol.", "vs.", "Sen.", "Rep.", "Pres.", "Hon.",

87+ "Rev.", "Ph.D.", "M.D.", "M.A.", "p.", "pp.",

88+ "ch.", "sec.", "cf.", "cp."]

89+

79--

90--

80-- Writer options

91-- Writer options

81--

92--

src/Text/Pandoc/Readers/Markdown.hs+16−25

@@ -42,6 +42,7 @@ import Data.Maybe

42import Data.Monoid ((<>))

43import Data.Ord (comparing)

44import Data.Scientific (base10Exponent, coefficient)

45+import qualified Data.Set as Set

45import Data.Text (Text)

46import Data.Text (Text)

46import qualified Data.Text as T

47import qualified Data.Text as T

47import qualified Data.Vector as V

48import qualified Data.Vector as V

@@ -1688,32 +1689,22 @@ nonEndline = satisfy (/='\n')

1688

1689

1689str :: PandocMonad m => MarkdownParser m (F Inlines)

1690str :: PandocMonad m => MarkdownParser m (F Inlines)

1690str = do

1691str = do

1691− result <- many1 alphaNum

1692+ result <- many1 (alphaNum <|> try (char '.' <* notFollowedBy (char '.')))

1692 updateLastStrPos

1693 updateLastStrPos

1693− let spacesToNbr = map (\c -> if c == ' ' then '\160' else c)

1694+ (do guardEnabled Ext_smart

1694− isSmart <- extensionEnabled Ext_smart <$> getOption readerExtensions

1695+ abbrevs <- getOption readerAbbreviations

1695− if isSmart

1696+ if not (null result) && last result == '.' && result `Set.member` abbrevs

1696− then case likelyAbbrev result of

1697+ then try (do ils <- whitespace <|> endline

1697− [] -> return $ return $ B.str result

1698− xs -> choice (map (\x ->

1699− try (string x >> oneOf " \n" >>

1700− lookAhead alphaNum >>

1698+ lookAhead alphaNum

1701− return (return $ B.str

1699+ return $ do

1702− $ result ++ spacesToNbr x ++ "\160"))) xs)

1700+ ils' <- ils

1701+ if ils' == B.space

1703− <|> (return $ return $ B.str result)

1702+ then return (B.str result <> B.str "\160")

1704− else return $ return $ B.str result

1703+ else -- linebreak or softbreak

1705−

1704+ return (ils' <> B.str result <> B.str "\160"))

1706−-- | if the string matches the beginning of an abbreviation (before

1705+ <|> return (return (B.str result))

1707−-- the first period, return strings that would finish the abbreviation.

1706+ else return (return (B.str result)))

1708−likelyAbbrev :: String -> [String]

1707+ <|> return (return (B.str result))

1709−likelyAbbrev x =

1710− let abbrevs = [ "Mr.", "Mrs.", "Ms.", "Capt.", "Dr.", "Prof.",

1711− "Gen.", "Gov.", "e.g.", "i.e.", "Sgt.", "St.",

1712− "vol.", "vs.", "Sen.", "Rep.", "Pres.", "Hon.",

1713− "Rev.", "Ph.D.", "M.D.", "M.A.", "p.", "pp.",

1714− "ch.", "sec.", "cf.", "cp."]

1715− abbrPairs = map (break (=='.')) abbrevs

1716− in map snd $ filter (\(y,_) -> y == x) abbrPairs

1717

1708

1718-- an endline character that can be treated as a space, not a structural break

1709-- an endline character that can be treated as a space, not a structural break

1719endline :: PandocMonad m => MarkdownParser m (F Inlines)

1710endline :: PandocMonad m => MarkdownParser m (F Inlines)