a340c72 · typeable/pandoc

git.iko.soy/typeable/pandoc

on master help sign in

Org reader: extract parsing function to module

a340c72Albert Krewinkel10 years ago

pandoc.cabal+1

compare with master

unifiedsplit

@@ -394,6 +394,7 @@ Library

394 Text.Pandoc.Readers.Odt.Arrows.State,

395 Text.Pandoc.Readers.Odt.Arrows.Utils,

396 Text.Pandoc.Readers.Org.ParserState,

397+ Text.Pandoc.Readers.Org.Parsing,

397 Text.Pandoc.Writers.Shared,

398 Text.Pandoc.Writers.Shared,

398 Text.Pandoc.Asciify,

399 Text.Pandoc.Asciify,

399 Text.Pandoc.MIME,

400 Text.Pandoc.MIME,

src/Text/Pandoc/Readers/Org.hs+10−76

@@ -29,27 +29,23 @@ Conversion of org-mode formatted plain text to 'Pandoc' document.

29-}

30module Text.Pandoc.Readers.Org ( readOrg ) where

32+import Text.Pandoc.Readers.Org.ParserState

33+import Text.Pandoc.Readers.Org.Parsing

34+

32import qualified Text.Pandoc.Builder as B

35import qualified Text.Pandoc.Builder as B

33import Text.Pandoc.Builder ( Inlines, Blocks )

36import Text.Pandoc.Builder ( Inlines, Blocks )

34import Text.Pandoc.Definition

37import Text.Pandoc.Definition

35import Text.Pandoc.Compat.Monoid ((<>))

38import Text.Pandoc.Compat.Monoid ((<>))

36import Text.Pandoc.Error

39import Text.Pandoc.Error

37import Text.Pandoc.Options

40import Text.Pandoc.Options

38−import qualified Text.Pandoc.Parsing as P

39−import Text.Pandoc.Parsing hiding ( F, unF, askF, asksF, runF

40− , anyLine, blanklines, newline

41− , orderedListMarker

42− , parseFromString

43− )

44import Text.Pandoc.Readers.LaTeX (inlineCommand, rawLaTeXInline)

41import Text.Pandoc.Readers.LaTeX (inlineCommand, rawLaTeXInline)

45−import Text.Pandoc.Readers.Org.ParserState

46import Text.Pandoc.Shared (compactify', compactify'DL)

42import Text.Pandoc.Shared (compactify', compactify'DL)

47import Text.TeXMath (readTeX, writePandoc, DisplayType(..))

43import Text.TeXMath (readTeX, writePandoc, DisplayType(..))

48import qualified Text.TeXMath.Readers.MathML.EntityMap as MathMLEntityMap

44import qualified Text.TeXMath.Readers.MathML.EntityMap as MathMLEntityMap

50import Control.Arrow (first)

46import Control.Arrow (first)

51import Control.Monad (foldM, guard, mplus, mzero, when)

47import Control.Monad (foldM, guard, mplus, mzero, when)

52−import Control.Monad.Reader ( Reader, runReader )

48+import Control.Monad.Reader ( runReader )

53import Data.Char (isAlphaNum, isSpace, toLower, toUpper)

49import Data.Char (isAlphaNum, isSpace, toLower, toUpper)

54import Data.List ( foldl', intersperse, isPrefixOf, isSuffixOf )

50import Data.List ( foldl', intersperse, isPrefixOf, isSuffixOf )

55import qualified Data.Map as M

51import qualified Data.Map as M

@@ -63,9 +59,6 @@ readOrg :: ReaderOptions -- ^ Reader options

63 -> Either PandocError Pandoc

59 -> Either PandocError Pandoc

64readOrg opts s = flip runReader def $ readWithM parseOrg def{ orgStateOptions = opts } (s ++ "\n\n")

60readOrg opts s = flip runReader def $ readWithM parseOrg def{ orgStateOptions = opts } (s ++ "\n\n")

66−-- | The parser used to read org files.

67−type OrgParser = ParserT [Char] OrgParserState (Reader OrgParserLocal)

68−

69--

62--

70-- Functions acting on the parser state

63-- Functions acting on the parser state

71--

64--

@@ -73,14 +66,6 @@ recordAnchorId :: String -> OrgParser ()

73recordAnchorId i = updateState $ \s ->

66recordAnchorId i = updateState $ \s ->

74 s{ orgStateAnchorIds = i : (orgStateAnchorIds s) }

67 s{ orgStateAnchorIds = i : (orgStateAnchorIds s) }

76−updateLastForbiddenCharPos :: OrgParser ()

77−updateLastForbiddenCharPos = getPosition >>= \p ->

78− updateState $ \s -> s{ orgStateLastForbiddenCharPos = Just p}

79−

80−updateLastPreCharPos :: OrgParser ()

81−updateLastPreCharPos = getPosition >>= \p ->

82− updateState $ \s -> s{ orgStateLastPreCharPos = Just p}

83−

84pushToInlineCharStack :: Char -> OrgParser ()

69pushToInlineCharStack :: Char -> OrgParser ()

85pushToInlineCharStack c = updateState $ \s ->

70pushToInlineCharStack c = updateState $ \s ->

86 s{ orgStateEmphasisCharStack = c:orgStateEmphasisCharStack s }

71 s{ orgStateEmphasisCharStack = c:orgStateEmphasisCharStack s }

@@ -258,57 +243,6 @@ isHeaderLevelLowerEq n blk =

258 _ -> False

243 _ -> False

259

244

260

245

261−--

262−-- Adaptions and specializations of parsing utilities

263−--

264−

265−-- The version Text.Pandoc.Parsing cannot be used, as we need additional parts

266−-- of the state saved and restored.

267−parseFromString :: OrgParser a -> String -> OrgParser a

268−parseFromString parser str' = do

269− oldLastPreCharPos <- orgStateLastPreCharPos <$> getState

270− updateState $ \s -> s{ orgStateLastPreCharPos = Nothing }

271− result <- P.parseFromString parser str'

272− updateState $ \s -> s{ orgStateLastPreCharPos = oldLastPreCharPos }

273− return result

274−

275−-- | Like @Text.Parsec.Char.newline@, but causes additional state changes.

276−newline :: OrgParser Char

277−newline =

278− P.newline

279− <* updateLastPreCharPos

280− <* updateLastForbiddenCharPos

281−

282−-- | Like @Text.Parsec.Char.blanklines@, but causes additional state changes.

283−blanklines :: OrgParser [Char]

284−blanklines =

285− P.blanklines

286− <* updateLastPreCharPos

287− <* updateLastForbiddenCharPos

288−

289−anyLine :: OrgParser String

290−anyLine =

291− P.anyLine

292− <* updateLastPreCharPos

293− <* updateLastForbiddenCharPos

294−

295−-- | Succeeds when we're in list context.

296−inList :: OrgParser ()

297−inList = do

298− ctx <- orgStateParserContext <$> getState

299− guard (ctx == ListItemState)

300−

301−-- | Parse in different context

302−withContext :: ParserContext -- ^ New parser context

303− -> OrgParser a -- ^ Parser to run in that context

304− -> OrgParser a

305−withContext context parser = do

306− oldContext <- orgStateParserContext <$> getState

307− updateState $ \s -> s{ orgStateParserContext = context }

308− result <- parser

309− updateState $ \s -> s{ orgStateParserContext = oldContext }

310− return result

311−

312--

246--

313-- parsing blocks

247-- parsing blocks

314--

248--

@@ -398,7 +332,7 @@ keyValues = try $

398 endOfValue :: OrgParser ()

332 endOfValue :: OrgParser ()

399 endOfValue =

333 endOfValue =

400 lookAhead $ (() <$ try (many1 spaceChar <* key))

334 lookAhead $ (() <$ try (many1 spaceChar <* key))

401− <|> () <$ P.newline

335+ <|> () <$ newline

402

336

403

337

404--

338--

@@ -675,7 +609,7 @@ propertiesDrawer = try $ do

675 key = try $ skipSpaces *> char ':' *> many1Till nonspaceChar (char ':')

609 key = try $ skipSpaces *> char ':' *> many1Till nonspaceChar (char ':')

676

610

677 value :: OrgParser String

611 value :: OrgParser String

678− value = try $ skipSpaces *> manyTill anyChar (try $ skipSpaces *> P.newline)

612+ value = try $ skipSpaces *> manyTill anyChar (try $ skipSpaces *> newline)

679

613

680keyValuesToAttr :: [(String, String)] -> Attr

614keyValuesToAttr :: [(String, String)] -> Attr

681keyValuesToAttr kvs =

615keyValuesToAttr kvs =

@@ -696,7 +630,7 @@ keyValuesToAttr kvs =

696figure :: OrgParser (F Blocks)

630figure :: OrgParser (F Blocks)

697figure = try $ do

631figure = try $ do

698 figAttrs <- blockAttributes

632 figAttrs <- blockAttributes

699− src <- skipSpaces *> selfTarget <* skipSpaces <* P.newline

633+ src <- skipSpaces *> selfTarget <* skipSpaces <* newline

700 guard . not . isNothing . blockAttrCaption $ figAttrs

634 guard . not . isNothing . blockAttrCaption $ figAttrs

701 guard (isImageFilename src)

635 guard (isImageFilename src)

702 let figName = fromMaybe mempty $ blockAttrName figAttrs

636 let figName = fromMaybe mempty $ blockAttrName figAttrs

@@ -785,7 +719,7 @@ parseFormat = try $ do

785header :: OrgParser (F Blocks)

719header :: OrgParser (F Blocks)

786header = try $ do

720header = try $ do

787 level <- headerStart

721 level <- headerStart

788− title <- manyTill inline (lookAhead $ optional headerTags <* P.newline)

722+ title <- manyTill inline (lookAhead $ optional headerTags <* newline)

789 tags <- option [] headerTags

723 tags <- option [] headerTags

790 newline

724 newline

791 propAttr <- option nullAttr (keyValuesToAttr <$> propertiesDrawer)

725 propAttr <- option nullAttr (keyValuesToAttr <$> propertiesDrawer)

@@ -1083,7 +1017,7 @@ definitionListItem parseMarkerGetLength = try $ do

1083 return $ (,) <$> term' <*> fmap (:[]) contents'

1017 return $ (,) <$> term' <*> fmap (:[]) contents'

1084 where

1018 where

1085 definitionMarker =

1019 definitionMarker =

1086− spaceChar *> string "::" <* (spaceChar <|> lookAhead P.newline)

1020+ spaceChar *> string "::" <* (spaceChar <|> lookAhead newline)

1087

1021

1088

1022

1089-- parse raw text for one list item, excluding start marker and continuations

1023-- parse raw text for one list item, excluding start marker and continuations

@@ -1559,7 +1493,7 @@ many1TillNOrLessNewlines n p end = try $

1559 nMoreLines k cs = try $ (final k cs <|> rest k cs)

1493 nMoreLines k cs = try $ (final k cs <|> rest k cs)

1560 >>= uncurry nMoreLines

1494 >>= uncurry nMoreLines

1561 final _ cs = (\x -> (Nothing, cs ++ x)) <$> try finalLine

1495 final _ cs = (\x -> (Nothing, cs ++ x)) <$> try finalLine

1562− rest m cs = (\x -> (minus1 <$> m, cs ++ x ++ "\n")) <$> try (manyTill p P.newline)

1496+ rest m cs = (\x -> (minus1 <$> m, cs ++ x ++ "\n")) <$> try (manyTill p newline)

1563 finalLine = try $ manyTill p end

1497 finalLine = try $ manyTill p end

1564 minus1 k = k - 1

1498 minus1 k = k - 1

1565 oneOrMore cs = guard (not $ null cs) *> return cs

1499 oneOrMore cs = guard (not $ null cs) *> return cs

src/Text/Pandoc/Readers/Org/ParserState.hs+5−2

@@ -29,9 +29,11 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA

29Define the Org-mode parser state.

30-}

31module Text.Pandoc.Readers.Org.ParserState

32− ( OrgParserState(..)

32+ ( OrgParserState (..)

33− , OrgParserLocal(..)

33+ , OrgParserLocal (..)

34 , OrgNoteRecord

35+ , HasReaderOptions (..)

36+ , HasQuoteContext (..)

35 , F(..)

37 , F(..)

36 , askF

38 , askF

37 , asksF

39 , asksF

@@ -184,6 +186,7 @@ modifyExportSettings :: ExportSettingSetter a -> a -> OrgParserState -> OrgParse

184modifyExportSettings setter val state =

186modifyExportSettings setter val state =

185 state { orgStateExportSettings = setter val . orgStateExportSettings $ state }

187 state { orgStateExportSettings = setter val . orgStateExportSettings $ state }

186

188

189+

187--

190--

188-- Parser state reader

191-- Parser state reader

189--

192--

src/Text/Pandoc/Readers/Org/Parsing.hsnew file+182

@@ -0,0 +1,182 @@

1+{-

4+This program is free software; you can redistribute it and/or modify

5+it under the terms of the GNU General Public License as published by

6+the Free Software Foundation; either version 2 of the License, or

7+(at your option) any later version.

9+This program is distributed in the hope that it will be useful,

10+but WITHOUT ANY WARRANTY; without even the implied warranty of

11+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the

12+GNU General Public License for more details.

13+

14+You should have received a copy of the GNU General Public License

15+along with this program; if not, write to the Free Software

16+Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA

17+-}

18+

19+{- |

20+ Module : Text.Pandoc.Readers.Org.Options

22+ License : GNU GPL, version 2 or above

23+

24+ Maintainer : Albert Krewinkel <tarleb+pandoc@moltkeplatz.de>

25+

26+Org-mode parsing utilities.

27+

28+Most functions are simply re-exports from @Text.Pandoc.Parsing@, some

29+functions are adapted to Org-mode specific functionality.

30+-}

31+module Text.Pandoc.Readers.Org.Parsing

32+ ( OrgParser

33+ , anyLine

34+ , blanklines

35+ , newline

36+ , parseFromString

37+ , inList

38+ , withContext

39+ , updateLastForbiddenCharPos

40+ , updateLastPreCharPos

41+ -- * Re-exports from Text.Pandoc.Parser

42+ , ParserContext (..)

43+ , many1Till

44+ , notFollowedBy'

45+ , spaceChar

46+ , nonspaceChar

47+ , skipSpaces

48+ , blankline

49+ , enclosed

50+ , stringAnyCase

51+ , charsInBalanced

52+ , uri

53+ , withRaw

54+ , readWithM

55+ , guardEnabled

56+ , updateLastStrPos

57+ , notAfterString

58+ , ParserState (..)

59+ , registerHeader

60+ , QuoteContext (..)

61+ , singleQuoteStart

62+ , singleQuoteEnd

63+ , doubleQuoteStart

64+ , doubleQuoteEnd

65+ , dash

66+ , ellipses

67+ , citeKey

68+ -- * Re-exports from Text.Pandoc.Parsec

69+ , runParser

70+ , getInput

71+ , char

72+ , letter

73+ , digit

74+ , alphaNum

75+ , skipMany1

76+ , spaces

77+ , anyChar

78+ , string

79+ , count

80+ , eof

81+ , noneOf

82+ , oneOf

83+ , lookAhead

84+ , notFollowedBy

85+ , many

86+ , many1

87+ , manyTill

88+ , (<|>)

89+ , (<?>)

90+ , choice

91+ , try

92+ , sepBy

93+ , sepBy1

94+ , option

95+ , optional

96+ , optionMaybe

97+ , getState

98+ , updateState

99+ , SourcePos

100+ , getPosition

101+ ) where

102+

103+import Text.Pandoc.Readers.Org.ParserState

104+

105+import qualified Text.Pandoc.Parsing as P

106+import Text.Pandoc.Parsing hiding ( anyLine, blanklines, newline

107+ , parseFromString )

108+

109+import Control.Monad ( guard )

110+import Control.Monad.Reader ( Reader )

111+

112+-- | The parser used to read org files.

113+type OrgParser = ParserT [Char] OrgParserState (Reader OrgParserLocal)

114+

115+--

116+-- Adaptions and specializations of parsing utilities

117+--

118+

119+-- | Parse any line of text

120+anyLine :: OrgParser String

121+anyLine =

122+ P.anyLine

123+ <* updateLastPreCharPos

124+ <* updateLastForbiddenCharPos

125+

126+-- The version Text.Pandoc.Parsing cannot be used, as we need additional parts

127+-- of the state saved and restored.

128+parseFromString :: OrgParser a -> String -> OrgParser a

129+parseFromString parser str' = do

130+ oldLastPreCharPos <- orgStateLastPreCharPos <$> getState

131+ updateState $ \s -> s{ orgStateLastPreCharPos = Nothing }

132+ result <- P.parseFromString parser str'

133+ updateState $ \s -> s{ orgStateLastPreCharPos = oldLastPreCharPos }

134+ return result

135+

136+-- | Like @Text.Parsec.Char.newline@, but causes additional state changes.

137+newline :: OrgParser Char

138+newline =

139+ P.newline

140+ <* updateLastPreCharPos

141+ <* updateLastForbiddenCharPos

142+

143+-- | Like @Text.Parsec.Char.blanklines@, but causes additional state changes.

144+blanklines :: OrgParser [Char]

145+blanklines =

146+ P.blanklines

147+ <* updateLastPreCharPos

148+ <* updateLastForbiddenCharPos

149+

150+-- | Succeeds when we're in list context.

151+inList :: OrgParser ()

152+inList = do

153+ ctx <- orgStateParserContext <$> getState

154+ guard (ctx == ListItemState)

155+

156+-- | Parse in different context

157+withContext :: ParserContext -- ^ New parser context

158+ -> OrgParser a -- ^ Parser to run in that context

159+ -> OrgParser a

160+withContext context parser = do

161+ oldContext <- orgStateParserContext <$> getState

162+ updateState $ \s -> s{ orgStateParserContext = context }

163+ result <- parser

164+ updateState $ \s -> s{ orgStateParserContext = oldContext }

165+ return result

166+

167+--

168+-- Parser state update functions

169+--

170+

171+-- | Set the current position as the last position at which a forbidden char

172+-- was found (i.e. a character which is not allowed at the inner border of

173+-- markup).

174+updateLastForbiddenCharPos :: OrgParser ()

175+updateLastForbiddenCharPos = getPosition >>= \p ->

176+ updateState $ \s -> s{ orgStateLastForbiddenCharPos = Just p}

177+

178+-- | Set the current parser position as the position at which a character was

179+-- seen which allows inline markup to follow.

180+updateLastPreCharPos :: OrgParser ()

181+updateLastPreCharPos = getPosition >>= \p ->

182+ updateState $ \s -> s{ orgStateLastPreCharPos = Just p}