aboutsummaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/Readers/Org.hs
blob: dba61dfe0a748f3d93f7b2616a1c73724f6de86c (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
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
{-# LANGUAGE OverloadedStrings #-}
{-# LANGUAGE GeneralizedNewtypeDeriving #-}
{-
Copyright (C) 2014 Albert Krewinkel <tarleb@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
   Copyright   : Copyright (C) 2014 Albert Krewinkel
   License     : GNU GPL, version 2 or above

   Maintainer  : Albert Krewinkel <tarleb@moltkeplatz.de>

Conversion of org-mode formatted plain text to 'Pandoc' document.
-}
module Text.Pandoc.Readers.Org ( readOrg ) where

import qualified Text.Pandoc.Builder as B
import           Text.Pandoc.Builder ( Inlines, Blocks, HasMeta(..), (<>)
                                     , trimInlines )
import           Text.Pandoc.Definition
import           Text.Pandoc.Options
import qualified Text.Pandoc.Parsing as P
import           Text.Pandoc.Parsing hiding ( F, unF, askF, asksF, runF
                                            , newline, orderedListMarker
                                            , parseFromString
                                            , updateLastStrPos )
import           Text.Pandoc.Shared (compactify', compactify'DL)

import           Control.Applicative ( Applicative, pure
                                     , (<$>), (<$), (<*>), (<*), (*>), (<**>) )
import           Control.Arrow (first)
import           Control.Monad (foldM, guard, liftM, liftM2, mzero, when)
import           Control.Monad.Reader (Reader, runReader, ask, asks)
import           Data.Char (isAlphaNum, toLower)
import           Data.Default
import           Data.List (intersperse, isPrefixOf, isSuffixOf)
import qualified Data.Map as M
import           Data.Maybe (listToMaybe, fromMaybe, isJust)
import           Data.Monoid (Monoid, mconcat, mempty, mappend)
import           Network.HTTP (urlEncode)

-- | Parse org-mode string and return a Pandoc document.
readOrg :: ReaderOptions -- ^ Reader options
        -> String        -- ^ String to parse (assuming @'\n'@ line endings)
        -> Pandoc
readOrg opts s = readWith parseOrg def{ orgStateOptions = opts } (s ++ "\n\n")

type OrgParser = Parser [Char] OrgParserState

parseOrg :: OrgParser Pandoc
parseOrg = do
  blocks' <- parseBlocks
  st <- getState
  let meta = runF (orgStateMeta' st) st
  return $ Pandoc meta $ filter (/= Null) (B.toList $ runF blocks' st)

--
-- Parser State for Org
--

type OrgNoteRecord = (String, F Blocks)
type OrgNoteTable = [OrgNoteRecord]

type OrgBlockAttributes = M.Map String String

type OrgLinkFormatters = M.Map String (String -> String)

-- | Org-mode parser state
data OrgParserState = OrgParserState
                      { orgStateOptions              :: ReaderOptions
                      , orgStateAnchorIds            :: [String]
                      , orgStateBlockAttributes      :: OrgBlockAttributes
                      , orgStateEmphasisCharStack    :: [Char]
                      , orgStateEmphasisNewlines     :: Maybe Int
                      , orgStateLastForbiddenCharPos :: Maybe SourcePos
                      , orgStateLastPreCharPos       :: Maybe SourcePos
                      , orgStateLastStrPos           :: Maybe SourcePos
                      , orgStateLinkFormatters       :: OrgLinkFormatters
                      , orgStateMeta                 :: Meta
                      , orgStateMeta'                :: F Meta
                      , orgStateNotes'               :: OrgNoteTable
                      }

instance HasReaderOptions OrgParserState where
  extractReaderOptions = orgStateOptions

instance HasMeta OrgParserState where
  setMeta field val st =
    st{ orgStateMeta = setMeta field val $ orgStateMeta st }
  deleteMeta field st =
    st{ orgStateMeta = deleteMeta field $ orgStateMeta st }

instance Default OrgParserState where
  def = defaultOrgParserState

defaultOrgParserState :: OrgParserState
defaultOrgParserState = OrgParserState
                        { orgStateOptions = def
                        , orgStateAnchorIds = []
                        , orgStateBlockAttributes = M.empty
                        , orgStateEmphasisCharStack = []
                        , orgStateEmphasisNewlines = Nothing
                        , orgStateLastForbiddenCharPos = Nothing
                        , orgStateLastPreCharPos = Nothing
                        , orgStateLastStrPos = Nothing
                        , orgStateLinkFormatters = M.empty
                        , orgStateMeta = nullMeta
                        , orgStateMeta' = return nullMeta
                        , orgStateNotes' = []
                        }

recordAnchorId :: String -> OrgParser ()
recordAnchorId i = updateState $ \s ->
  s{ orgStateAnchorIds = i : (orgStateAnchorIds s) }

addBlockAttribute :: String -> String -> OrgParser ()
addBlockAttribute key val = updateState $ \s ->
  let attrs = orgStateBlockAttributes s
  in s{ orgStateBlockAttributes = M.insert key val attrs }

lookupBlockAttribute :: String -> OrgParser (Maybe String)
lookupBlockAttribute key =
  M.lookup key . orgStateBlockAttributes <$> getState

resetBlockAttributes :: OrgParser ()
resetBlockAttributes = updateState $ \s ->
  s{ orgStateBlockAttributes = orgStateBlockAttributes def }

updateLastStrPos :: OrgParser ()
updateLastStrPos = getPosition >>= \p ->
  updateState $ \s -> s{ orgStateLastStrPos = Just p }

updateLastForbiddenCharPos :: OrgParser ()
updateLastForbiddenCharPos = getPosition >>= \p ->
  updateState $ \s -> s{ orgStateLastForbiddenCharPos = Just p}

updateLastPreCharPos :: OrgParser ()
updateLastPreCharPos = getPosition >>= \p ->
  updateState $ \s -> s{ orgStateLastPreCharPos = Just p}

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 }

addLinkFormat :: String
              -> (String -> String)
              -> OrgParser ()
addLinkFormat key formatter = updateState $ \s ->
  let fs = orgStateLinkFormatters s
  in s{ orgStateLinkFormatters = M.insert key formatter fs }

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

-- The version Text.Pandoc.Parsing cannot be used, as we need additional parts
-- of the state saved and restored.
parseFromString :: OrgParser a -> String -> OrgParser a
parseFromString parser str' = do
  oldLastPreCharPos <- orgStateLastPreCharPos <$> getState
  updateState $ \s -> s{ orgStateLastPreCharPos = Nothing }
  result <- P.parseFromString parser str'
  updateState $ \s -> s{ orgStateLastPreCharPos = oldLastPreCharPos }
  return result


--
-- Adaptions and specializations of parsing utilities
--

newtype F a = F { unF :: Reader OrgParserState a
                } deriving (Monad, Applicative, Functor)

runF :: F a -> OrgParserState -> a
runF = runReader . unF

askF :: F OrgParserState
askF = F ask

asksF :: (OrgParserState -> a) -> F a
asksF f = F $ asks f

instance Monoid a => Monoid (F a) where
  mempty = return mempty
  mappend = liftM2 mappend
  mconcat = fmap mconcat . sequence

trimInlinesF :: F Inlines -> F Inlines
trimInlinesF = liftM trimInlines

returnF :: a -> OrgParser (F a)
returnF = return . return


-- | Like @Text.Parsec.Char.newline@, but causes additional state changes.
newline :: OrgParser Char
newline =
  P.newline
       <* updateLastPreCharPos
       <* updateLastForbiddenCharPos

--
-- parsing blocks
--

parseBlocks :: OrgParser (F Blocks)
parseBlocks = mconcat <$> manyTill block eof

block :: OrgParser (F Blocks)
block = choice [ mempty <$ blanklines
               , optionalAttributes $ choice
                 [ orgBlock
                 , figure
                 , table
                 ]
               , example
               , drawer
               , specialLine
               , header
               , return <$> hline
               , list
               , latexFragment
               , noteBlock
               , paraOrPlain
               ] <?> "block"

optionalAttributes :: OrgParser (F Blocks) -> OrgParser (F Blocks)
optionalAttributes parser = try $
  resetBlockAttributes *> parseBlockAttributes *> parser

parseBlockAttributes :: OrgParser ()
parseBlockAttributes = do
  attrs <- many attribute
  () <$ mapM (uncurry parseAndAddAttribute) attrs
 where
   attribute :: OrgParser (String, String)
   attribute = try $ do
         key <- metaLineStart *> many1Till (noneOf "\n\r") (char ':')
         val <- skipSpaces *> anyLine
         return (map toLower key, val)

parseAndAddAttribute :: String -> String -> OrgParser ()
parseAndAddAttribute key value = do
  let key' = map toLower key
  () <$ addBlockAttribute key' value

lookupInlinesAttr :: String -> OrgParser (Maybe (F Inlines))
lookupInlinesAttr attr = try $ do
  val <- lookupBlockAttribute attr
  maybe (return Nothing)
        (fmap Just . parseFromString parseInlines)
        val


--
-- Org Blocks (#+BEGIN_... / #+END_...)
--

orgBlock :: OrgParser (F Blocks)
orgBlock = try $ do
  (indent, blockType, args) <- blockHeader
  content <- rawBlockContent indent blockType
  contentBlocks <- parseFromString parseBlocks (content ++ "\n")
  let classArgs = [ translateLang . fromMaybe [] $ listToMaybe args ]
  case blockType of
    "comment" -> return mempty
    "html"    -> returnF $ B.rawBlock "html" content
    "latex"   -> returnF $ B.rawBlock "latex" content
    "ascii"   -> returnF $ B.rawBlock "ascii" content
    "example" -> returnF $ exampleCode content
    "quote"   -> return  $ B.blockQuote <$> contentBlocks
    "verse"   -> parseVerse content
    "src"     -> codeBlockWithAttr classArgs content
    _         -> return  $ B.divWith ("", [blockType], []) <$> contentBlocks
 where
   parseVerse :: String -> OrgParser (F Blocks)
   parseVerse cs =
       fmap B.para . mconcat . intersperse (pure B.linebreak)
       <$> mapM (parseFromString parseInlines) (lines cs)

blockHeader :: OrgParser (Int, String, [String])
blockHeader = (,,) <$> blockIndent
                   <*> blockType
                   <*> (skipSpaces *> blockArgs)
 where blockIndent = length <$> many spaceChar
       blockType = map toLower <$> (stringAnyCase "#+begin_" *> many letter)
       blockArgs = manyTill (many nonspaceChar <* skipSpaces) newline

codeBlockWithAttr :: [String] -> String -> OrgParser (F Blocks)
codeBlockWithAttr classArgs content = do
  identifier <- fromMaybe "" <$> lookupBlockAttribute "name"
  caption <- lookupInlinesAttr "caption"
  let codeBlck = B.codeBlockWith (identifier, classArgs, []) content
  return $ maybe (pure codeBlck) (labelDiv codeBlck) caption
 where
   labelDiv blk value =
       B.divWith nullAttr <$> (mappend <$> labelledBlock value
                                       <*> pure blk)
   labelledBlock = fmap (B.plain . B.spanWith ("", ["label"], []))

rawBlockContent :: Int -> String -> OrgParser String
rawBlockContent indent blockType =
  unlines . map commaEscaped <$> manyTill indentedLine blockEnder
 where
   indentedLine = try $ choice [ blankline         *> pure "\n"
                               , indentWith indent *> anyLine
                               ]
   blockEnder = try $ indentWith indent *> stringAnyCase ("#+end_" <> blockType)

-- indent by specified number of spaces (or equiv. tabs)
indentWith :: Int -> OrgParser String
indentWith num = do
  tabStop <- getOption readerTabStop
  if num < tabStop
     then count num (char ' ')
     else choice [ try (count num (char ' '))
                 , try (char '\t' >> count (num - tabStop) (char ' ')) ]

translateLang :: String -> String
translateLang "C"          = "c"
translateLang "C++"        = "cpp"
translateLang "emacs-lisp" = "commonlisp" -- emacs lisp is not supported
translateLang "js"         = "javascript"
translateLang "lisp"       = "commonlisp"
translateLang "R"          = "r"
translateLang "sh"         = "bash"
translateLang "sqlite"     = "sql"
translateLang cs = cs

commaEscaped :: String -> String
commaEscaped (',':cs@('*':_))     = cs
commaEscaped (',':cs@('#':'+':_)) = cs
commaEscaped cs                   = cs

example :: OrgParser (F Blocks)
example = try $ do
  return . return . exampleCode =<< unlines <$> many1 exampleLine

exampleCode :: String -> Blocks
exampleCode = B.codeBlockWith ("", ["example"], [])

exampleLine :: OrgParser String
exampleLine = try $ string ": " *> anyLine

-- Drawers for properties or a logbook
drawer :: OrgParser (F Blocks)
drawer = try $ do
  drawerStart
  manyTill drawerLine (try drawerEnd)
  return mempty

drawerStart :: OrgParser String
drawerStart = try $
  skipSpaces *> drawerName <* skipSpaces <* newline
 where drawerName = try $  char ':' *> validDrawerName <* char ':'
       validDrawerName =  stringAnyCase "PROPERTIES"
                          <|> stringAnyCase "LOGBOOK"

drawerLine :: OrgParser String
drawerLine = try anyLine

drawerEnd :: OrgParser String
drawerEnd = try $
  skipSpaces *> stringAnyCase ":END:" <* skipSpaces <* newline


--
-- Figures
--

-- Figures (Image on a line by itself, preceded by name and/or caption)
figure :: OrgParser (F Blocks)
figure = try $ do
  (cap, nam) <- nameAndCaption
  src <- skipSpaces *> selfTarget <* skipSpaces <* newline
  guard (isImageFilename src)
  return $ do
    cap' <- cap
    return $ B.para $ B.image src nam cap'
 where
   nameAndCaption =
       do
         maybeCap <- lookupInlinesAttr "caption"
         maybeNam <- lookupBlockAttribute "name"
         guard $ isJust maybeCap || isJust maybeNam
         return ( fromMaybe mempty maybeCap
                , maybe mempty withFigPrefix maybeNam )
   withFigPrefix cs =
       if "fig:" `isPrefixOf` cs
       then cs
       else "fig:" ++ cs

--
-- Comments, Options and Metadata
specialLine :: OrgParser (F Blocks)
specialLine = fmap return . try $ metaLine <|> commentLine

metaLine :: OrgParser Blocks
metaLine = try $ mempty
              <$ (metaLineStart *> (optionLine <|> declarationLine))

commentLine :: OrgParser Blocks
commentLine = try $ commentLineStart *> anyLine *> pure mempty

-- The order, in which blocks are tried, makes sure that we're not looking at
-- the beginning of a block, so we don't need to check for it
metaLineStart :: OrgParser String
metaLineStart = try $ mappend <$> many spaceChar <*> string "#+"

commentLineStart :: OrgParser String
commentLineStart = try $ mappend <$> many spaceChar <*> string "# "

declarationLine :: OrgParser ()
declarationLine = try $ do
  key <- metaKey
  inlinesF <- metaInlines
  updateState $ \st ->
    let meta' = B.setMeta <$> pure key <*> inlinesF <*> pure nullMeta
    in st { orgStateMeta' = orgStateMeta' st <> meta' }
  return ()

metaInlines :: OrgParser (F MetaValue)
metaInlines = fmap (MetaInlines . B.toList) <$> inlinesTillNewline

metaKey :: OrgParser String
metaKey = map toLower <$> many1 (noneOf ": \n\r")
                      <*  char ':'
                      <*  skipSpaces

optionLine :: OrgParser ()
optionLine = try $ do
  key <- metaKey
  case key of
    "link" -> parseLinkFormat >>= uncurry addLinkFormat
    _      -> mzero

parseLinkFormat :: OrgParser ((String, String -> String))
parseLinkFormat = try $ do
  linkType <- (:) <$> letter <*> many (alphaNum <|> oneOf "-_") <* skipSpaces
  linkSubst <- parseFormat
  return (linkType, linkSubst)

-- | An ad-hoc, single-argument-only implementation of a printf-style format
-- parser.
parseFormat :: OrgParser (String -> String)
parseFormat = try $ do
  replacePlain <|> replaceUrl <|> justAppend
 where
   -- inefficient, but who cares
   replacePlain = try $ (\x -> concat . flip intersperse x)
                     <$> sequence [tillSpecifier 's', rest]
   replaceUrl   = try $ (\x -> concat . flip intersperse x . urlEncode)
                     <$> sequence [tillSpecifier 'h', rest]
   justAppend   = try $ (++) <$> rest

   rest            = manyTill anyChar         (eof <|> () <$ oneOf "\n\r")
   tillSpecifier c = manyTill (noneOf "\n\r") (try $ string ('%':c:""))

--
-- Headers
--

-- | Headers
header :: OrgParser (F Blocks)
header = try $ do
  level <- headerStart
  title <- inlinesTillNewline
  return $ B.header level <$> title

headerStart :: OrgParser Int
headerStart = try $
  (length <$> many1 (char '*')) <* many1 (char ' ')


-- Don't use (or need) the reader wrapper here, we want hline to be
-- @show@able.  Otherwise we can't use it with @notFollowedBy'@.

-- | Horizontal Line (five -- dashes or more)
hline :: OrgParser Blocks
hline = try $ do
  skipSpaces
  string "-----"
  many (char '-')
  skipSpaces
  newline
  return B.horizontalRule

--
-- Tables
--

data OrgTableRow = OrgContentRow (F [Blocks])
                 | OrgAlignRow [Alignment]
                 | OrgHlineRow

data OrgTable = OrgTable
  { orgTableColumns    :: Int
  , orgTableAlignments :: [Alignment]
  , orgTableHeader     :: [Blocks]
  , orgTableRows       :: [[Blocks]]
  }

table :: OrgParser (F Blocks)
table = try $ do
  lookAhead tableStart
  do
    rows <- tableRows
    cptn <- fromMaybe (pure "") <$> lookupInlinesAttr "caption"
    return $ (<$> cptn) . orgToPandocTable . normalizeTable =<< rowsToTable rows

orgToPandocTable :: OrgTable
                 -> Inlines
                 -> Blocks
orgToPandocTable (OrgTable _ aligns heads lns) caption =
  B.table caption (zip aligns $ repeat 0) heads lns

tableStart :: OrgParser Char
tableStart = try $ skipSpaces *> char '|'

tableRows :: OrgParser [OrgTableRow]
tableRows = try $ many (tableAlignRow <|> tableHline <|> tableContentRow)

tableContentRow :: OrgParser OrgTableRow
tableContentRow = try $
  OrgContentRow . sequence <$> (tableStart *> manyTill tableContentCell newline)

tableContentCell :: OrgParser (F Blocks)
tableContentCell = try $
  fmap B.plain . trimInlinesF . mconcat <$> many1Till inline endOfCell

endOfCell :: OrgParser Char
endOfCell = try $ char '|' <|> lookAhead newline

tableAlignRow :: OrgParser OrgTableRow
tableAlignRow = try $
  OrgAlignRow <$> (tableStart *> manyTill tableAlignCell newline)

tableAlignCell :: OrgParser Alignment
tableAlignCell =
  choice [ try $ emptyCell *> return AlignDefault
         , try $ skipSpaces
                   *> char '<'
                   *> tableAlignFromChar
                   <* many digit
                   <* char '>'
                   <* emptyCell
         ] <?> "alignment info"
    where emptyCell = try $ skipSpaces *> endOfCell

tableAlignFromChar :: OrgParser Alignment
tableAlignFromChar = try $ choice [ char 'l' *> return AlignLeft
                                  , char 'c' *> return AlignCenter
                                  , char 'r' *> return AlignRight
                                  ]

tableHline :: OrgParser OrgTableRow
tableHline = try $
  OrgHlineRow <$ (tableStart *> char '-' *> anyLine)

rowsToTable :: [OrgTableRow]
            -> F OrgTable
rowsToTable = foldM (flip rowToContent) zeroTable
  where zeroTable = OrgTable 0 mempty mempty mempty

normalizeTable :: OrgTable
               -> OrgTable
normalizeTable (OrgTable cols aligns heads lns) =
  let aligns' = fillColumns aligns AlignDefault
      heads'  = if heads == mempty
                then mempty
                else fillColumns heads (B.plain mempty)
      lns'    = map (`fillColumns` B.plain mempty) lns
      fillColumns base padding = take cols $ base ++ repeat padding
  in OrgTable cols aligns' heads' lns'


-- One or more horizontal rules after the first content line mark the previous
-- line as a header.  All other horizontal lines are discarded.
rowToContent :: OrgTableRow
             -> OrgTable
             -> F OrgTable
rowToContent OrgHlineRow        t = maybeBodyToHeader t
rowToContent (OrgAlignRow as)   t = setLongestRow as =<< setAligns as t
rowToContent (OrgContentRow rf) t = do
  rs <- rf
  setLongestRow rs =<< appendToBody rs t

setLongestRow :: [a]
              -> OrgTable
              -> F OrgTable
setLongestRow rs t =
  return t{ orgTableColumns = max (length rs) (orgTableColumns t) }

maybeBodyToHeader :: OrgTable
                  -> F OrgTable
maybeBodyToHeader t = case t of
  OrgTable{ orgTableHeader = [], orgTableRows = b:[] } ->
         return t{ orgTableHeader = b , orgTableRows = [] }
  _   -> return t

appendToBody :: [Blocks]
             -> OrgTable
             -> F OrgTable
appendToBody r t = return t{ orgTableRows = orgTableRows t ++ [r] }

setAligns :: [Alignment]
          -> OrgTable
          -> F OrgTable
setAligns aligns t = return $ t{ orgTableAlignments = aligns }


--
-- LaTeX fragments
--
latexFragment :: OrgParser (F Blocks)
latexFragment = try $ do
  envName <- latexEnvStart
  content <- mconcat <$> manyTill anyLineNewline (latexEnd envName)
  return . return $ B.rawBlock "latex" (content `inLatexEnv` envName)
 where
   c `inLatexEnv` e = mconcat [ "\\begin{", e, "}\n"
                              , c
                              , "\\end{", e, "}\n"
                              ]

latexEnvStart :: OrgParser String
latexEnvStart = try $ do
  skipSpaces *> string "\\begin{"
             *> latexEnvName
             <* string "}"
             <* blankline

latexEnd :: String -> OrgParser ()
latexEnd envName = try $
  () <$ skipSpaces
     <* string ("\\end{" ++ envName ++ "}")
     <* blankline

-- | Parses a LaTeX environment name.
latexEnvName :: OrgParser String
latexEnvName = try $ do
  mappend <$> many1 alphaNum
          <*> option "" (string "*")


--
-- Footnote defintions
--
noteBlock :: OrgParser (F Blocks)
noteBlock = try $ do
  ref <- noteMarker <* skipSpaces
  content <- mconcat <$> blocksTillHeaderOrNote
  addToNotesTable (ref, content)
  return mempty
 where
   blocksTillHeaderOrNote =
     many1Till block (eof <|> () <$ lookAhead noteMarker
                          <|> () <$ lookAhead headerStart)

-- Paragraphs or Plain text
paraOrPlain :: OrgParser (F Blocks)
paraOrPlain = try $
  parseInlines <**> (fmap <$> option B.plain (try $ newline *> pure B.para))

inlinesTillNewline :: OrgParser (F Inlines)
inlinesTillNewline = trimInlinesF . mconcat <$> manyTill inline newline


--
-- list blocks
--

list :: OrgParser (F Blocks)
list = choice [ definitionList, bulletList, orderedList ] <?> "list"

definitionList :: OrgParser (F Blocks)
definitionList = fmap B.definitionList . fmap compactify'DL . sequence
                 <$> many1 (definitionListItem bulletListStart)

bulletList :: OrgParser (F Blocks)
bulletList = fmap B.bulletList . fmap compactify' . sequence
             <$> many1 (listItem bulletListStart)

orderedList :: OrgParser (F Blocks)
orderedList = fmap B.orderedList . fmap compactify' . sequence
              <$> many1 (listItem orderedListStart)

genericListStart :: OrgParser String
                 -> OrgParser Int
genericListStart listMarker = try $
  (+) <$> (length <$> many spaceChar)
      <*> (length <$> listMarker <* many1 spaceChar)

-- parses bullet list start and returns its length (excl. following whitespace)
bulletListStart :: OrgParser Int
bulletListStart = genericListStart bulletListMarker
  where bulletListMarker = pure <$> oneOf "*-+"

orderedListStart :: OrgParser Int
orderedListStart = genericListStart orderedListMarker
  -- Ordered list markers allowed in org-mode
  where orderedListMarker = mappend <$> many1 digit <*> (pure <$> oneOf ".)")

definitionListItem :: OrgParser Int
                   -> OrgParser (F (Inlines, [Blocks]))
definitionListItem parseMarkerGetLength = try $ do
  markerLength <- parseMarkerGetLength
  term <- manyTill (noneOf "\n\r") (try $ string "::")
  line1 <- anyLineNewline
  blank <- option "" ("\n" <$ blankline)
  cont <- concat <$> many (listContinuation markerLength)
  term' <- parseFromString inline term
  contents' <- parseFromString parseBlocks $ line1 ++ blank ++ cont
  return $ (,) <$> term' <*> fmap (:[]) contents'


-- parse raw text for one list item, excluding start marker and continuations
listItem :: OrgParser Int
         -> OrgParser (F Blocks)
listItem start = try $ do
  markerLength <- try start
  firstLine <- anyLineNewline
  blank <- option "" ("\n" <$ blankline)
  rest <- concat <$> many (listContinuation markerLength)
  parseFromString parseBlocks $ firstLine ++ blank ++ rest

-- continuation of a list item - indented and separated by blankline or endline.
-- Note: nested lists are parsed as continuations.
listContinuation :: Int
                 -> OrgParser String
listContinuation markerLength = try $
  notFollowedBy' blankline
  *> (mappend <$> (concat <$> many1 listLine)
              <*> many blankline)
 where listLine = try $ indentWith markerLength *> anyLineNewline

anyLineNewline :: OrgParser String
anyLineNewline = (++ "\n") <$> anyLine


--
-- inline
--

inline :: OrgParser (F Inlines)
inline =
  choice [ whitespace
         , linebreak
         , footnote
         , linkOrImage
         , anchor
         , inlineCodeBlock
         , str
         , endline
         , emph
         , strong
         , strikeout
         , underline
         , code
         , math
         , displayMath
         , verbatim
         , subscript
         , superscript
         , symbol
         ] <* (guard =<< newlinesCountWithinLimits)
  <?> "inline"

parseInlines :: OrgParser (F Inlines)
parseInlines = 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' exampleLine
  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.space

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'

noteMarker :: OrgParser String
noteMarker = try $ do
  char '['
  choice [ many1Till digit (char ']')
         , (++) <$> string "fn:"
                <*> many1Till (noneOf "\n\r\t ") (char ']')
         ]

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

explicitOrImageLink :: OrgParser (F Inlines)
explicitOrImageLink = try $ do
  char '['
  srcF   <- applyCustomLinkFormat =<< linkTarget
  title  <- enclosedRaw (char '[') (char ']')
  title' <- parseFromString (mconcat <$> many inline) title
  char ']'
  return $ do
    src <- srcF
    if isImageFilename src && 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

selfTarget :: OrgParser String
selfTarget = try $ char '[' *> linkTarget <* char ']'

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

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


linkToInlinesF :: String -> Inlines -> F Inlines
linkToInlinesF s@('#':_) = pure . B.link s ""
linkToInlinesF s
    | isImageFilename s = const . pure $ B.image s "" ""
    | isUri s           = pure . B.link s ""
    | isRelativeUrl s   = pure . B.link s ""
linkToInlinesF s = \title -> do
  anchorB <- (s `elem`) <$> asksF orgStateAnchorIds
  if anchorB
    then pure $ B.link ('#':s) "" title
    else pure $ B.emph title

isRelativeUrl :: String -> Bool
isRelativeUrl s = (':' `notElem` s) && ("./" `isPrefixOf` s)

isUri :: String -> Bool
isUri s = let (scheme, path) = break (== ':') s
          in all (\c -> isAlphaNum c || c `elem` ".-") scheme
             && not (null path)

isImageFilename :: String -> Bool
isImageFilename filename =
  any (\x -> ('.':x)  `isSuffixOf` filename) imageExtensions &&
  (any (\x -> (x++":") `isPrefixOf` filename) protocols ||
   ':' `notElem` filename)
 where
   imageExtensions = [ "jpeg" , "jpg" , "png" , "gif" , "svg" ]
   protocols = [ "file", "http", "https" ]

-- | 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` "_.-:" = 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 '[' ']' blockOption
  inlineCode <- enclosedByPair '{' '}' (noneOf "\n\r")
  let attrClasses = [translateLang lang, rundocBlockClass]
  let attrKeyVal  = map toRundocAttrib (("language", lang) : opts)
  returnF $ B.codeWith ("", attrClasses, attrKeyVal) inlineCode
 where enclosedByPair s e p = char s *> many1Till p (char e)

-- | The class-name used to mark rundoc blocks.
rundocBlockClass :: String
rundocBlockClass = "rundoc-block"

blockOption :: OrgParser (String, String)
blockOption = try $ (,) <$> orgArgKey <*> orgArgValue

orgArgKey :: OrgParser String
orgArgKey = try $
  skipSpaces *> char ':'
             *> many1 orgArgWordChar
             <* many1 spaceChar

orgArgValue :: OrgParser String
orgArgValue = try $
  skipSpaces *> many1 orgArgWordChar
             <* skipSpaces

orgArgWordChar :: OrgParser Char
orgArgWordChar = alphaNum <|> oneOf "-_"

toRundocAttrib :: (String, String) -> (String, String)
toRundocAttrib = first ("rundoc-" ++)

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 '_'

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

verbatim  :: OrgParser (F Inlines)
verbatim  = return . B.rawInline "" <$> 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 "$$"  "$$"
                                                ]
symbol :: OrgParser (F Inlines)
symbol = return . B.str . (: "") <$> (oneOf specialChars >>= updatePositions)
 where updatePositions c
           | c `elem` emphasisPreChars = c <$ updateLastPreCharPos
           | c `elem` emphasisForbiddenBorderChars = c <$ updateLastForbiddenCharPos
           | otherwise = return c

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 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 we are right after the end of a string
notAfterString :: OrgParser Bool
notAfterString = do
  pos <- getPosition
  lastStrPos <- orgStateLastStrPos <$> getState
  return $ lastStrPos /= Just pos

-- | 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 $
  choice [ string "*"
         , mappend <$> option [] ((:[]) <$> oneOf "+-")
                   <*> many1 alphaNum
         ]