summaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/Readers/Org/Inlines.hs
blob: fdefd2a3fd088ecadaa1a2a4b3c2e997d806ccd7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
{-# LANGUAGE OverloadedStrings #-}
{-
Copyright (C) 2014-2016 Albert Krewinkel <tarleb+pandoc@moltkeplatz.de>

This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-}

{- |
   Module      : Text.Pandoc.Readers.Org.Options
   Copyright   : Copyright (C) 2014-2016 Albert Krewinkel
   License     : GNU GPL, version 2 or above

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

Parsers for Org-mode inline elements.
-}
module Text.Pandoc.Readers.Org.Inlines
  ( inline
  , inlines
  , addToNotesTable
  , linkTarget
  ) where

import           Text.Pandoc.Readers.Org.BlockStarts
import           Text.Pandoc.Readers.Org.ParserState
import           Text.Pandoc.Readers.Org.Parsing
import           Text.Pandoc.Readers.Org.Shared
                   ( isImageFilename, rundocBlockClass, toRundocAttrib
                   , translateLang )

import qualified Text.Pandoc.Builder as B
import           Text.Pandoc.Builder ( Inlines )
import           Text.Pandoc.Definition
import           Text.Pandoc.Compat.Monoid ( (<>) )
import           Text.Pandoc.Options
import           Text.Pandoc.Readers.LaTeX ( inlineCommand, rawLaTeXInline )
import           Text.TeXMath ( readTeX, writePandoc, DisplayType(..) )
import qualified Text.TeXMath.Readers.MathML.EntityMap as MathMLEntityMap

import           Control.Monad ( guard, mplus, mzero, when )
import           Data.Char ( isAlphaNum, isSpace )
import           Data.List ( isPrefixOf )
import           Data.Maybe ( fromMaybe )
import qualified Data.Map as M

--
-- Functions acting on the parser state
--
recordAnchorId :: String -> OrgParser ()
recordAnchorId i = updateState $ \s ->
  s{ orgStateAnchorIds = i : (orgStateAnchorIds s) }

pushToInlineCharStack :: Char -> OrgParser ()
pushToInlineCharStack c = updateState $ \s ->
  s{ orgStateEmphasisCharStack = c:orgStateEmphasisCharStack s }

popInlineCharStack :: OrgParser ()
popInlineCharStack = updateState $ \s ->
  s{ orgStateEmphasisCharStack = drop 1 . orgStateEmphasisCharStack $ s }

surroundingEmphasisChar :: OrgParser [Char]
surroundingEmphasisChar =
  take 1 . drop 1 . orgStateEmphasisCharStack <$> getState

startEmphasisNewlinesCounting :: Int -> OrgParser ()
startEmphasisNewlinesCounting maxNewlines = updateState $ \s ->
  s{ orgStateEmphasisNewlines = Just maxNewlines }

decEmphasisNewlinesCount :: OrgParser ()
decEmphasisNewlinesCount = updateState $ \s ->
  s{ orgStateEmphasisNewlines = (\n -> n - 1) <$> orgStateEmphasisNewlines s }

newlinesCountWithinLimits :: OrgParser Bool
newlinesCountWithinLimits = do
  st <- getState
  return $ ((< 0) <$> orgStateEmphasisNewlines st) /= Just True

resetEmphasisNewlines :: OrgParser ()
resetEmphasisNewlines = updateState $ \s ->
  s{ orgStateEmphasisNewlines = Nothing }

addToNotesTable :: OrgNoteRecord -> OrgParser ()
addToNotesTable note = do
  oldnotes <- orgStateNotes' <$> getState
  updateState $ \s -> s{ orgStateNotes' = note:oldnotes }

-- | Parse a single Org-mode inline element
inline :: OrgParser (F Inlines)
inline =
  choice [ whitespace
         , linebreak
         , cite
         , footnote
         , linkOrImage
         , anchor
         , inlineCodeBlock
         , str
         , endline
         , emphasizedText
         , code
         , math
         , displayMath
         , verbatim
         , subscript
         , superscript
         , inlineLaTeX
         , smart
         , symbol
         ] <* (guard =<< newlinesCountWithinLimits)
  <?> "inline"

-- | Read the rest of the input as inlines.
inlines :: OrgParser (F Inlines)
inlines = trimInlinesF . mconcat <$> many1 inline

-- treat these as potentially non-text when parsing inline:
specialChars :: [Char]
specialChars = "\"$'()*+-,./:<=>[\\]^_{|}~"


whitespace :: OrgParser (F Inlines)
whitespace = pure B.space <$ skipMany1 spaceChar
                          <* updateLastPreCharPos
                          <* updateLastForbiddenCharPos
             <?> "whitespace"

linebreak :: OrgParser (F Inlines)
linebreak = try $ pure B.linebreak <$ string "\\\\" <* skipSpaces <* newline

str :: OrgParser (F Inlines)
str = return . B.str <$> many1 (noneOf $ specialChars ++ "\n\r ")
      <* updateLastStrPos

-- | An endline character that can be treated as a space, not a structural
-- break.  This should reflect the values of the Emacs variable
-- @org-element-pagaraph-separate@.
endline :: OrgParser (F Inlines)
endline = try $ do
  newline
  notFollowedBy blankline
  notFollowedBy' exampleLineStart
  notFollowedBy' hline
  notFollowedBy' noteMarker
  notFollowedBy' tableStart
  notFollowedBy' drawerStart
  notFollowedBy' headerStart
  notFollowedBy' metaLineStart
  notFollowedBy' latexEnvStart
  notFollowedBy' commentLineStart
  notFollowedBy' bulletListStart
  notFollowedBy' orderedListStart
  decEmphasisNewlinesCount
  guard =<< newlinesCountWithinLimits
  updateLastPreCharPos
  return . return $ B.softbreak

cite :: OrgParser (F Inlines)
cite = try $ do
  guardEnabled Ext_citations
  (cs, raw) <- withRaw (pandocOrgCite <|> orgRefCite)
  return $ (flip B.cite (B.text raw)) <$> cs

-- | A citation in Pandoc Org-mode style (@[\@citekey]@).
pandocOrgCite :: OrgParser (F [Citation])
pandocOrgCite = try $
  char '[' *> skipSpaces *> citeList <* skipSpaces <* char ']'

orgRefCite :: OrgParser (F [Citation])
orgRefCite = try $ normalOrgRefCite <|> (fmap (:[]) <$> linkLikeOrgRefCite)

normalOrgRefCite :: OrgParser (F [Citation])
normalOrgRefCite = try $ do
  mode <- orgRefCiteMode
  sequence <$> sepBy1 (orgRefCiteList mode) (char ',')
 where
   -- | A list of org-ref style citation keys, parsed as citation of the given
   -- citation mode.
   orgRefCiteList :: CitationMode -> OrgParser (F Citation)
   orgRefCiteList citeMode = try $ do
     key <- orgRefCiteKey
     returnF $ Citation
      { citationId      = key
      , citationPrefix  = mempty
      , citationSuffix  = mempty
      , citationMode    = citeMode
      , citationNoteNum = 0
      , citationHash    = 0
      }

-- | Read a link-like org-ref style citation.  The citation includes pre and
-- post text.  However, multiple citations are not possible due to limitations
-- in the syntax.
linkLikeOrgRefCite :: OrgParser (F Citation)
linkLikeOrgRefCite = try $ do
  _    <- string "[["
  mode <- orgRefCiteMode
  key  <- orgRefCiteKey
  _    <- string "]["
  pre  <- trimInlinesF . mconcat <$> manyTill inline (try $ string "::")
  spc  <- option False (True <$ spaceChar)
  suf  <- trimInlinesF . mconcat <$> manyTill inline (try $ string "]]")
  return $ do
    pre' <- pre
    suf' <- suf
    return Citation
      { citationId      = key
      , citationPrefix  = B.toList pre'
      , citationSuffix  = B.toList (if spc then B.space <> suf' else suf')
      , citationMode    = mode
      , citationNoteNum = 0
      , citationHash    = 0
      }

-- | Read a citation key.  The characters allowed in citation keys are taken
-- from the `org-ref-cite-re` variable in `org-ref.el`.
orgRefCiteKey :: OrgParser String
orgRefCiteKey = try . many1 . satisfy $ \c ->
                  isAlphaNum c || c `elem` ("-_:\\./"::String)

-- | Supported citation types.  Only a small subset of org-ref types is
-- supported for now.  TODO: rewrite this, use LaTeX reader as template.
orgRefCiteMode :: OrgParser CitationMode
orgRefCiteMode =
  choice $ map (\(s, mode) -> mode <$ try (string s <* char ':'))
    [ ("cite", AuthorInText)
    , ("citep", NormalCitation)
    , ("citep*", NormalCitation)
    , ("citet", AuthorInText)
    , ("citet*", AuthorInText)
    , ("citeyear", SuppressAuthor)
    ]

citeList :: OrgParser (F [Citation])
citeList = sequence <$> sepBy1 citation (try $ char ';' *> skipSpaces)

citation :: OrgParser (F Citation)
citation = try $ do
  pref <- prefix
  (suppress_author, key) <- citeKey
  suff <- suffix
  return $ do
    x <- pref
    y <- suff
    return $ Citation{ citationId      = key
                     , citationPrefix  = B.toList x
                     , citationSuffix  = B.toList y
                     , citationMode    = if suppress_author
                                            then SuppressAuthor
                                            else NormalCitation
                     , citationNoteNum = 0
                     , citationHash    = 0
                     }
 where
   prefix = trimInlinesF . mconcat <$>
            manyTill inline (char ']' <|> (']' <$ lookAhead citeKey))
   suffix = try $ do
     hasSpace <- option False (notFollowedBy nonspaceChar >> return True)
     skipSpaces
     rest <- trimInlinesF . mconcat <$>
             many (notFollowedBy (oneOf ";]") *> inline)
     return $ if hasSpace
              then (B.space <>) <$> rest
              else rest

footnote :: OrgParser (F Inlines)
footnote = try $ inlineNote <|> referencedNote

inlineNote :: OrgParser (F Inlines)
inlineNote = try $ do
  string "[fn:"
  ref <- many alphaNum
  char ':'
  note <- fmap B.para . trimInlinesF . mconcat <$> many1Till inline (char ']')
  when (not $ null ref) $
       addToNotesTable ("fn:" ++ ref, note)
  return $ B.note <$> note

referencedNote :: OrgParser (F Inlines)
referencedNote = try $ do
  ref <- noteMarker
  return $ do
    notes <- asksF orgStateNotes'
    case lookup ref notes of
      Nothing   -> return $ B.str $ "[" ++ ref ++ "]"
      Just contents  -> do
        st <- askF
        let contents' = runF contents st{ orgStateNotes' = [] }
        return $ B.note contents'

linkOrImage :: OrgParser (F Inlines)
linkOrImage = explicitOrImageLink
              <|> selflinkOrImage
              <|> angleLink
              <|> plainLink
              <?> "link or image"

explicitOrImageLink :: OrgParser (F Inlines)
explicitOrImageLink = try $ do
  char '['
  srcF   <- applyCustomLinkFormat =<< possiblyEmptyLinkTarget
  title  <- enclosedRaw (char '[') (char ']')
  title' <- parseFromString (mconcat <$> many inline) title
  char ']'
  return $ do
    src <- srcF
    if isImageFilename title
      then pure $ B.link src "" $ B.image title mempty mempty
      else linkToInlinesF src =<< title'

selflinkOrImage :: OrgParser (F Inlines)
selflinkOrImage = try $ do
  src <- char '[' *> linkTarget <* char ']'
  return $ linkToInlinesF src (B.str src)

plainLink :: OrgParser (F Inlines)
plainLink = try $ do
  (orig, src) <- uri
  returnF $ B.link src "" (B.str orig)

angleLink :: OrgParser (F Inlines)
angleLink = try $ do
  char '<'
  link <- plainLink
  char '>'
  return link

linkTarget :: OrgParser String
linkTarget = enclosedByPair '[' ']' (noneOf "\n\r[]")

possiblyEmptyLinkTarget :: OrgParser String
possiblyEmptyLinkTarget = try linkTarget <|> ("" <$ string "[]")

applyCustomLinkFormat :: String -> OrgParser (F String)
applyCustomLinkFormat link = do
  let (linkType, rest) = break (== ':') link
  return $ do
    formatter <- M.lookup linkType <$> asksF orgStateLinkFormatters
    return $ maybe link ($ drop 1 rest) formatter

-- | Take a link and return a function which produces new inlines when given
-- description inlines.
linkToInlinesF :: String -> Inlines -> F Inlines
linkToInlinesF linkStr =
  case linkStr of
    ""      -> pure . B.link mempty ""       -- wiki link (empty by convention)
    ('#':_) -> pure . B.link linkStr ""      -- document-local fraction
    _       -> case cleanLinkString linkStr of
                 (Just cleanedLink) -> if isImageFilename cleanedLink
                                       then const . pure $ B.image cleanedLink "" ""
                                       else pure . B.link cleanedLink ""
                 Nothing -> internalLink linkStr  -- other internal link

-- | Cleanup and canonicalize a string describing a link.  Return @Nothing@ if
-- the string does not appear to be a link.
cleanLinkString :: String -> Maybe String
cleanLinkString s =
  case s of
    '/':_                  -> Just $ "file://" ++ s  -- absolute path
    '.':'/':_              -> Just s                 -- relative path
    '.':'.':'/':_          -> Just s                 -- relative path
    -- Relative path or URL (file schema)
    'f':'i':'l':'e':':':s' -> Just $ if ("//" `isPrefixOf` s') then s else s'
    _ | isUrl s            -> Just s                 -- URL
    _                      -> Nothing
 where
   isUrl :: String -> Bool
   isUrl cs =
     let (scheme, path) = break (== ':') cs
     in all (\c -> isAlphaNum c || c `elem` (".-"::String)) scheme
          && not (null path)

internalLink :: String -> Inlines -> F Inlines
internalLink link title = do
  anchorB <- (link `elem`) <$> asksF orgStateAnchorIds
  if anchorB
    then return $ B.link ('#':link) "" title
    else return $ B.emph title

-- | Parse an anchor like @<<anchor-id>>@ and return an empty span with
-- @anchor-id@ set as id.  Legal anchors in org-mode are defined through
-- @org-target-regexp@, which is fairly liberal.  Since no link is created if
-- @anchor-id@ contains spaces, we are more restrictive in what is accepted as
-- an anchor.

anchor :: OrgParser (F Inlines)
anchor =  try $ do
  anchorId <- parseAnchor
  recordAnchorId anchorId
  returnF $ B.spanWith (solidify anchorId, [], []) mempty
 where
       parseAnchor = string "<<"
                     *> many1 (noneOf "\t\n\r<>\"' ")
                     <* string ">>"
                     <* skipSpaces

-- | Replace every char but [a-zA-Z0-9_.-:] with a hypen '-'.  This mirrors
-- the org function @org-export-solidify-link-text@.

solidify :: String -> String
solidify = map replaceSpecialChar
 where replaceSpecialChar c
           | isAlphaNum c    = c
           | c `elem` ("_.-:" :: String) = c
           | otherwise       = '-'

-- | Parses an inline code block and marks it as an babel block.
inlineCodeBlock :: OrgParser (F Inlines)
inlineCodeBlock = try $ do
  string "src_"
  lang <- many1 orgArgWordChar
  opts <- option [] $ enclosedByPair '[' ']' inlineBlockOption
  inlineCode <- enclosedByPair '{' '}' (noneOf "\n\r")
  let attrClasses = [translateLang lang, rundocBlockClass]
  let attrKeyVal  = map toRundocAttrib (("language", lang) : opts)
  returnF $ B.codeWith ("", attrClasses, attrKeyVal) inlineCode
 where
   inlineBlockOption :: OrgParser (String, String)
   inlineBlockOption = try $ do
     argKey <- orgArgKey
     paramValue <- option "yes" orgInlineParamValue
     return (argKey, paramValue)

   orgInlineParamValue :: OrgParser String
   orgInlineParamValue = try $
     skipSpaces
       *> notFollowedBy (char ':')
       *> many1 (noneOf "\t\n\r ]")
       <* skipSpaces


emphasizedText :: OrgParser (F Inlines)
emphasizedText = do
  state <- getState
  guard . exportEmphasizedText . orgStateExportSettings $ state
  try $ choice
    [ emph
    , strong
    , strikeout
    , underline
    ]

enclosedByPair :: Char          -- ^ opening char
               -> Char          -- ^ closing char
               -> OrgParser a   -- ^ parser
               -> OrgParser [a]
enclosedByPair s e p = char s *> many1Till p (char e)

emph      :: OrgParser (F Inlines)
emph      = fmap B.emph         <$> emphasisBetween '/'

strong    :: OrgParser (F Inlines)
strong    = fmap B.strong       <$> emphasisBetween '*'

strikeout :: OrgParser (F Inlines)
strikeout = fmap B.strikeout    <$> emphasisBetween '+'

-- There is no underline, so we use strong instead.
underline :: OrgParser (F Inlines)
underline = fmap B.strong       <$> emphasisBetween '_'

verbatim  :: OrgParser (F Inlines)
verbatim  = return . B.code     <$> verbatimBetween '='

code      :: OrgParser (F Inlines)
code      = return . B.code     <$> verbatimBetween '~'

subscript   :: OrgParser (F Inlines)
subscript   = fmap B.subscript   <$> try (char '_' *> subOrSuperExpr)

superscript :: OrgParser (F Inlines)
superscript = fmap B.superscript <$> try (char '^' *> subOrSuperExpr)

math      :: OrgParser (F Inlines)
math      = return . B.math      <$> choice [ math1CharBetween '$'
                                            , mathStringBetween '$'
                                            , rawMathBetween "\\(" "\\)"
                                            ]

displayMath :: OrgParser (F Inlines)
displayMath = return . B.displayMath <$> choice [ rawMathBetween "\\[" "\\]"
                                                , rawMathBetween "$$"  "$$"
                                                ]

updatePositions :: Char
                -> OrgParser (Char)
updatePositions c = do
  when (c `elem` emphasisPreChars) updateLastPreCharPos
  when (c `elem` emphasisForbiddenBorderChars) updateLastForbiddenCharPos
  return c

symbol :: OrgParser (F Inlines)
symbol = return . B.str . (: "") <$> (oneOf specialChars >>= updatePositions)

emphasisBetween :: Char
                -> OrgParser (F Inlines)
emphasisBetween c = try $ do
  startEmphasisNewlinesCounting emphasisAllowedNewlines
  res <- enclosedInlines (emphasisStart c) (emphasisEnd c)
  isTopLevelEmphasis <- null . orgStateEmphasisCharStack <$> getState
  when isTopLevelEmphasis
       resetEmphasisNewlines
  return res

verbatimBetween :: Char
                -> OrgParser String
verbatimBetween c = try $
  emphasisStart c *>
  many1TillNOrLessNewlines 1 (noneOf "\n\r") (emphasisEnd c)

-- | Parses a raw string delimited by @c@ using Org's math rules
mathStringBetween :: Char
                  -> OrgParser String
mathStringBetween c = try $ do
  mathStart c
  body <- many1TillNOrLessNewlines mathAllowedNewlines
                                   (noneOf (c:"\n\r"))
                                   (lookAhead $ mathEnd c)
  final <- mathEnd c
  return $ body ++ [final]

-- | Parse a single character between @c@ using math rules
math1CharBetween :: Char
                -> OrgParser String
math1CharBetween c = try $ do
  char c
  res <- noneOf $ c:mathForbiddenBorderChars
  char c
  eof <|> () <$ lookAhead (oneOf mathPostChars)
  return [res]

rawMathBetween :: String
               -> String
               -> OrgParser String
rawMathBetween s e = try $ string s *> manyTill anyChar (try $ string e)

-- | Parses the start (opening character) of emphasis
emphasisStart :: Char -> OrgParser Char
emphasisStart c = try $ do
  guard =<< afterEmphasisPreChar
  guard =<< notAfterString
  char c
  lookAhead (noneOf emphasisForbiddenBorderChars)
  pushToInlineCharStack c
  return c

-- | Parses the closing character of emphasis
emphasisEnd :: Char -> OrgParser Char
emphasisEnd c = try $ do
  guard =<< notAfterForbiddenBorderChar
  char c
  eof <|> () <$ lookAhead acceptablePostChars
  updateLastStrPos
  popInlineCharStack
  return c
 where acceptablePostChars =
           surroundingEmphasisChar >>= \x -> oneOf (x ++ emphasisPostChars)

mathStart :: Char -> OrgParser Char
mathStart c = try $
  char c <* notFollowedBy' (oneOf (c:mathForbiddenBorderChars))

mathEnd :: Char -> OrgParser Char
mathEnd c = try $ do
  res <- noneOf (c:mathForbiddenBorderChars)
  char c
  eof <|> () <$ lookAhead (oneOf mathPostChars)
  return res


enclosedInlines :: OrgParser a
                -> OrgParser b
                -> OrgParser (F Inlines)
enclosedInlines start end = try $
  trimInlinesF . mconcat <$> enclosed start end inline

enclosedRaw :: OrgParser a
            -> OrgParser b
            -> OrgParser String
enclosedRaw start end = try $
  start *> (onSingleLine <|> spanningTwoLines)
 where onSingleLine = try $ many1Till (noneOf "\n\r") end
       spanningTwoLines = try $
         anyLine >>= \f -> mappend (f <> " ") <$> onSingleLine

-- | Like many1Till, but parses at most @n+1@ lines.  @p@ must not consume
--   newlines.
many1TillNOrLessNewlines :: Int
                         -> OrgParser Char
                         -> OrgParser a
                         -> OrgParser String
many1TillNOrLessNewlines n p end = try $
  nMoreLines (Just n) mempty >>= oneOrMore
 where
   nMoreLines Nothing  cs = return cs
   nMoreLines (Just 0) cs = try $ (cs ++) <$> finalLine
   nMoreLines k        cs = try $ (final k cs <|> rest k cs)
                                  >>= uncurry nMoreLines
   final _ cs = (\x -> (Nothing,      cs ++ x)) <$> try finalLine
   rest  m cs = (\x -> (minus1 <$> m, cs ++ x ++ "\n")) <$> try (manyTill p newline)
   finalLine = try $ manyTill p end
   minus1 k = k - 1
   oneOrMore cs = guard (not $ null cs) *> return cs

-- Org allows customization of the way it reads emphasis.  We use the defaults
-- here (see, e.g., the Emacs Lisp variable `org-emphasis-regexp-components`
-- for details).

-- | Chars allowed to occur before emphasis (spaces and newlines are ok, too)
emphasisPreChars :: [Char]
emphasisPreChars = "\t \"'({"

-- | Chars allowed at after emphasis
emphasisPostChars :: [Char]
emphasisPostChars = "\t\n !\"'),-.:;?\\}"

-- | Chars not allowed at the (inner) border of emphasis
emphasisForbiddenBorderChars :: [Char]
emphasisForbiddenBorderChars = "\t\n\r \"',"

-- | The maximum number of newlines within
emphasisAllowedNewlines :: Int
emphasisAllowedNewlines = 1

-- LaTeX-style math: see `org-latex-regexps` for details

-- | Chars allowed after an inline ($...$) math statement
mathPostChars :: [Char]
mathPostChars = "\t\n \"'),-.:;?"

-- | Chars not allowed at the (inner) border of math
mathForbiddenBorderChars :: [Char]
mathForbiddenBorderChars = "\t\n\r ,;.$"

-- | Maximum number of newlines in an inline math statement
mathAllowedNewlines :: Int
mathAllowedNewlines = 2

-- | Whether we are right behind a char allowed before emphasis
afterEmphasisPreChar :: OrgParser Bool
afterEmphasisPreChar = do
  pos <- getPosition
  lastPrePos <- orgStateLastPreCharPos <$> getState
  return . fromMaybe True $ (== pos) <$> lastPrePos

-- | Whether the parser is right after a forbidden border char
notAfterForbiddenBorderChar :: OrgParser Bool
notAfterForbiddenBorderChar = do
  pos <- getPosition
  lastFBCPos <- orgStateLastForbiddenCharPos <$> getState
  return $ lastFBCPos /= Just pos

-- | Read a sub- or superscript expression
subOrSuperExpr :: OrgParser (F Inlines)
subOrSuperExpr = try $
  choice [ id                   <$> charsInBalanced '{' '}' (noneOf "\n\r")
         , enclosing ('(', ')') <$> charsInBalanced '(' ')' (noneOf "\n\r")
         , simpleSubOrSuperString
         ] >>= parseFromString (mconcat <$> many inline)
 where enclosing (left, right) s = left : s ++ [right]

simpleSubOrSuperString :: OrgParser String
simpleSubOrSuperString = try $ do
  state <- getState
  guard . exportSubSuperscripts . orgStateExportSettings $ state
  choice [ string "*"
         , mappend <$> option [] ((:[]) <$> oneOf "+-")
                   <*> many1 alphaNum
         ]

inlineLaTeX :: OrgParser (F Inlines)
inlineLaTeX = try $ do
  cmd <- inlineLaTeXCommand
  maybe mzero returnF $
     parseAsMath cmd `mplus` parseAsMathMLSym cmd `mplus` parseAsInlineLaTeX cmd
 where
   parseAsMath :: String -> Maybe Inlines
   parseAsMath cs = B.fromList <$> texMathToPandoc cs

   parseAsInlineLaTeX :: String -> Maybe Inlines
   parseAsInlineLaTeX cs = maybeRight $ runParser inlineCommand state "" cs

   parseAsMathMLSym :: String -> Maybe Inlines
   parseAsMathMLSym cs = B.str <$> MathMLEntityMap.getUnicode (clean cs)
    -- drop initial backslash and any trailing "{}"
    where clean = dropWhileEnd (`elem` ("{}" :: String)) . drop 1

   state :: ParserState
   state = def{ stateOptions = def{ readerParseRaw = True }}

   texMathToPandoc :: String -> Maybe [Inline]
   texMathToPandoc cs = (maybeRight $ readTeX cs) >>= writePandoc DisplayInline

maybeRight :: Either a b -> Maybe b
maybeRight = either (const Nothing) Just

inlineLaTeXCommand :: OrgParser String
inlineLaTeXCommand = try $ do
  rest <- getInput
  case runParser rawLaTeXInline def "source" rest of
    Right (RawInline _ cs) -> do
      -- drop any trailing whitespace, those are not be part of the command as
      -- far as org mode is concerned.
      let cmdNoSpc = dropWhileEnd isSpace cs
      let len = length cmdNoSpc
      count len anyChar
      return cmdNoSpc
    _ -> mzero

-- Taken from Data.OldList.
dropWhileEnd :: (a -> Bool) -> [a] -> [a]
dropWhileEnd p = foldr (\x xs -> if p x && null xs then [] else x : xs) []

smart :: OrgParser (F Inlines)
smart = do
  getOption readerSmart >>= guard
  doubleQuoted <|> singleQuoted <|>
    choice (map (return <$>) [orgApostrophe, orgDash, orgEllipses])
  where
    orgDash = dash <* updatePositions '-'
    orgEllipses = ellipses <* updatePositions '.'
    orgApostrophe =
          (char '\'' <|> char '\8217') <* updateLastPreCharPos
                                       <* updateLastForbiddenCharPos
                                       *> return (B.str "\x2019")

singleQuoted :: OrgParser (F Inlines)
singleQuoted = try $ do
  guard . exportSmartQuotes . orgStateExportSettings =<< getState
  singleQuoteStart
  updatePositions '\''
  withQuoteContext InSingleQuote $
    fmap B.singleQuoted . trimInlinesF . mconcat <$>
      many1Till inline (singleQuoteEnd <* updatePositions '\'')

-- doubleQuoted will handle regular double-quoted sections, as well
-- as dialogues with an open double-quote without a close double-quote
-- in the same paragraph.
doubleQuoted :: OrgParser (F Inlines)
doubleQuoted = try $ do
  guard . exportSmartQuotes . orgStateExportSettings =<< getState
  doubleQuoteStart
  updatePositions '"'
  contents <- mconcat <$> many (try $ notFollowedBy doubleQuoteEnd >> inline)
  (withQuoteContext InDoubleQuote $ (doubleQuoteEnd <* updateLastForbiddenCharPos) >> return
       (fmap B.doubleQuoted . trimInlinesF $ contents))
   <|> (return $ return (B.str "\8220") <> contents)