aboutsummaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/Readers/Markdown.hs
blob: 3f37c1766feaa4bf86df21c6c20a39840ea611f8 (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
{-
Copyright (C) 2006-7 John MacFarlane <jgm@berkeley.edu>

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.Markdown
   Copyright   : Copyright (C) 2006-7 John MacFarlane
   License     : GNU GPL, version 2 or above 

   Maintainer  : John MacFarlane <jgm@berkeley.edu>
   Stability   : alpha
   Portability : portable

Conversion of markdown-formatted plain text to 'Pandoc' document.
-}
module Text.Pandoc.Readers.Markdown ( 
                                     readMarkdown 
                                    ) where

import Data.List ( findIndex, sortBy, transpose, isSuffixOf, intersect, lookup )
import Data.Char ( isAlphaNum )
import Text.Pandoc.ParserCombinators
import Text.Pandoc.Definition
import Text.Pandoc.Readers.LaTeX ( rawLaTeXInline, rawLaTeXEnvironment )
import Text.Pandoc.Shared 
import Text.Pandoc.Readers.HTML ( rawHtmlBlock, 
                                  anyHtmlBlockTag, anyHtmlInlineTag,
                                  anyHtmlTag, anyHtmlEndTag,
                                  htmlEndTag, extractTagType,
                                  htmlBlockElement )
import Text.Pandoc.Entities ( characterEntity, decodeEntities )
import Text.ParserCombinators.Parsec

-- | Read markdown from an input string and return a Pandoc document.
readMarkdown :: ParserState -> String -> Pandoc
readMarkdown state str = (readWith parseMarkdown) state (str ++ "\n\n")

-- | Parse markdown string with default options and print result (for testing).
testString :: String -> IO ()
testString = testStringWith parseMarkdown 

--
-- Constants and data structure definitions
--

spaceChars = " \t"
bulletListMarkers = "*+-"
hruleChars = "*-_"
titleOpeners = "\"'("
setextHChars = "=-"

-- treat these as potentially non-text when parsing inline:
specialChars = "\\[]*_~`<>$!^-.&'\""

--
-- auxiliary functions
--

-- | Skip a single endline if there is one.
skipEndline = option Space endline

indentSpaces = do
  state <- getState
  let tabStop = stateTabStop state
  try (count tabStop (char ' ')) <|> 
    (do{many (char ' '); string "\t"}) <?> "indentation"

nonindentSpaces = do
  state <- getState
  let tabStop = stateTabStop state
  choice (map (\n -> (try (count n (char ' ')))) (reverse [0..(tabStop - 1)]))

-- | Fail unless we're at beginning of a line.
failUnlessBeginningOfLine = do
  pos <- getPosition
  if sourceColumn pos == 1 then return () else fail "not beginning of line"

-- | Fail unless we're in "smart typography" mode.
failUnlessSmart = do
  state <- getState
  if stateSmart state then return () else fail "Smart typography feature"

-- | Parse a sequence of inline elements between a string
--  @opener@ and a string @closer@, including inlines
--  between balanced pairs of @opener@ and a @closer@.
inlinesInBalanced :: String -> String -> GenParser Char ParserState [Inline]
inlinesInBalanced opener closer = try $ do
  let openerSymbol = try $ do 
         res <- inline 
         if res == Str opener
            then return res 
            else pzero
  try (string opener)
  result <- manyTill (     (do lookAhead openerSymbol
                               bal <- inlinesInBalanced opener closer 
                               return $ [Str opener] ++ bal ++ [Str closer])
                       <|> (count 1 inline)) 
                     (try (string closer))
  return $ concat result

--
-- document structure
--

titleLine = try (do
  char '%'
  skipSpaces
  line <- manyTill inline newline
  return line)

authorsLine = try (do
  char '%'
  skipSpaces
  authors <- sepEndBy (many1 (noneOf ",;\n")) (oneOf ",;")
  newline
  return (map (decodeEntities . removeLeadingTrailingSpace) authors))

dateLine = try (do
  char '%'
  skipSpaces
  date <- many (noneOf "\n")
  newline
  return (decodeEntities $ removeTrailingSpace date))

titleBlock = try (do
  failIfStrict
  title <- option [] titleLine
  author <- option [] authorsLine
  date <- option "" dateLine
  option "" blanklines
  return (title, author, date))

parseMarkdown = do
  updateState (\state -> state { stateParseRaw = True }) -- markdown allows raw HTML
  (title, author, date) <- option ([],[],"") titleBlock
  -- go through once just to get list of reference keys
  refs <- manyTill (referenceKey <|> (do l <- lineClump
                                         return (LineClump l))) eof 
  let keys = map (\(KeyBlock label target) -> (label, target)) $ 
                 filter isKeyBlock refs
  let rawlines = map (\(LineClump ln) -> ln) $ filter isLineClump refs
  setInput $ concat rawlines -- with keys stripped out 
  updateState (\state -> state { stateKeys = keys })
  -- now go through for notes
  refs <- manyTill (noteBlock <|> (do l <- lineClump
                                      return (LineClump l))) eof 
  let notes = map (\(NoteBlock label blocks) -> (label, blocks)) $ 
                   filter isNoteBlock refs
  let rawlines = map (\(LineClump ln) -> ln) $ filter isLineClump refs
  setInput $ concat rawlines -- with note blocks and keys stripped out 
  updateState (\state -> state { stateNotes = notes })
  blocks <- parseBlocks  -- go through again, for real
  let blocks' = filter (/= Null) blocks
  return (Pandoc (Meta title author date) blocks')

-- 
-- initial pass for references
--

referenceKey = try $ do
  nonindentSpaces
  label <- reference
  char ':'
  skipSpaces
  option ' ' (char '<')
  src <- many (noneOf "> \n\t")
  option ' ' (char '>')
  tit <- option "" title 
  blanklines 
  return $ KeyBlock label (removeTrailingSpace src,  tit)

noteMarker = try $ do
  char '['
  char '^'
  manyTill (noneOf " \t\n") (char ']')

rawLine = try $ do
  notFollowedBy' blankline
  notFollowedBy' noteMarker
  contents <- many1 nonEndline
  end <- option "" (do
                      newline
                      option "" (try indentSpaces)
                      return "\n")
  return (contents ++ end)

rawLines = do
    lines <- many1 rawLine
    return (concat lines)

noteBlock = try $ do
  failIfStrict
  ref <- noteMarker
  char ':'
  option ' ' (try blankline)
  option "" (try indentSpaces)
  raw <- sepBy rawLines (try (do {blankline; indentSpaces}))
  option "" blanklines
  -- parse the extracted text, which may contain various block elements:
  rest <- getInput
  setInput $ (joinWithSep "\n" raw) ++ "\n\n"
  contents <- parseBlocks
  setInput rest
  return (NoteBlock ref contents)

--
-- parsing blocks
--

parseBlocks = manyTill block eof

block = choice [ header 
               , table
               , codeBlock
               , hrule
               , list
               , blockQuote
               , htmlBlock
               , rawLaTeXEnvironment'
               , para
               , plain
               , nullBlock ] <?> "block"

--
-- header blocks
--

header = choice [ setextHeader, atxHeader ] <?> "header"

atxHeader = try (do
  lead <- many1 (char '#')
  skipSpaces
  txt <- manyTill inline atxClosing
  return (Header (length lead) (normalizeSpaces txt)))

atxClosing = try (do
  skipMany (char '#')
  skipSpaces
  newline
  option "" blanklines)

setextHeader = choice $ 
               map (\x -> setextH x) (enumFromTo 1 (length setextHChars))

setextH n = try (do
  txt <- many1Till inline newline
  many1 (char (setextHChars !! (n-1)))
  skipSpaces
  newline
  option "" blanklines
  return (Header n (normalizeSpaces txt)))

--
-- hrule block
--

hruleWith chr = try (do
  skipSpaces
  char chr
  skipSpaces
  char chr
  skipSpaces
  char chr
  skipMany (oneOf (chr:spaceChars))
  newline
  option "" blanklines
  return HorizontalRule)

hrule = choice (map hruleWith hruleChars) <?> "hrule"

--
-- code blocks
--

indentedLine = try (do
  indentSpaces
  result <- manyTill anyChar newline
  return (result ++ "\n"))

-- two or more indented lines, possibly separated by blank lines
indentedBlock = try (do 
  res1 <- indentedLine
  blanks <- many blankline 
  res2 <- choice [indentedBlock, indentedLine]
  return (res1 ++ blanks ++ res2))

codeBlock = do
  result <- choice [indentedBlock, indentedLine]
  option "" blanklines
  return (CodeBlock (stripTrailingNewlines result))

--
-- block quotes
--

emacsBoxQuote = try (do
  failIfStrict
  string ",----"
  manyTill anyChar newline
  raw <- manyTill (try (do 
                          char '|'
                          option ' ' (char ' ')
                          result <- manyTill anyChar newline
                          return result))
                   (string "`----")
  manyTill anyChar newline
  option "" blanklines
  return raw)

emailBlockQuoteStart = try (do
  nonindentSpaces
  char '>'
  option ' ' (char ' ')
  return "> ")

emailBlockQuote = try (do
  emailBlockQuoteStart
  raw <- sepBy (many (choice [nonEndline, 
                              (try (do 
                                      endline
                                      notFollowedBy' emailBlockQuoteStart
                                      return '\n'))]))
               (try (do {newline; emailBlockQuoteStart}))
  newline <|> (do{ eof; return '\n' })
  option "" blanklines
  return raw)

blockQuote = do 
  raw <- choice [ emailBlockQuote, emacsBoxQuote ]
  -- parse the extracted block, which may contain various block elements:
  rest <- getInput
  setInput $ (joinWithSep "\n" raw) ++ "\n\n"
  contents <- parseBlocks
  setInput rest
  return (BlockQuote contents)
 
--
-- list blocks
--

list = choice [ bulletList, orderedList, definitionList ] <?> "list"

bulletListStart = try (do
  option ' ' newline -- if preceded by a Plain block in a list context
  nonindentSpaces
  notFollowedBy' hrule  -- because hrules start out just like lists
  oneOf bulletListMarkers
  spaceChar
  skipSpaces)

standardOrderedListStart = try (do
  many1 digit
  char '.')

extendedOrderedListStart = try (do
  failIfStrict
  oneOf ['a'..'n']
  oneOf ".)")

orderedListStart = try $ do
  option ' ' newline -- if preceded by a Plain block in a list context
  nonindentSpaces
  standardOrderedListStart <|> extendedOrderedListStart
  oneOf spaceChars
  skipSpaces

-- parse a line of a list item (start = parser for beginning of list item)
listLine start = try (do
  notFollowedBy' start
  notFollowedBy blankline
  notFollowedBy' (do 
                    indentSpaces
                    many (spaceChar)
                    choice [bulletListStart, orderedListStart])
  line <- manyTill anyChar newline
  return (line ++ "\n"))

-- parse raw text for one list item, excluding start marker and continuations
rawListItem start = try (do
  start
  result <- many1 (listLine start)
  blanks <- many blankline
  return ((concat result) ++ blanks))

-- continuation of a list item - indented and separated by blankline 
-- or (in compact lists) endline.
-- note: nested lists are parsed as continuations
listContinuation start = try (do
  lookAhead indentSpaces
  result <- many1 (listContinuationLine start)
  blanks <- many blankline
  return ((concat result) ++ blanks))

listContinuationLine start = try (do
  notFollowedBy' blankline
  notFollowedBy' start
  option "" (try indentSpaces)
  result <- manyTill anyChar newline
  return (result ++ "\n"))

listItem start = try (do 
  first <- rawListItem start
  continuations <- many (listContinuation start)
  -- parsing with ListItemState forces markers at beginning of lines to
  -- count as list item markers, even if not separated by blank space.
  -- see definition of "endline"
  state <- getState
  let oldContext = stateParserContext state
  setState $ state {stateParserContext = ListItemState}
  -- parse the extracted block, which may contain various block elements:
  rest <- getInput
  let raw = concat (first:continuations)
  setInput raw
  contents <- parseBlocks
  setInput rest
  updateState (\st -> st {stateParserContext = oldContext})
  return contents)

orderedList = try (do
  items <- many1 (listItem orderedListStart)
  let items' = compactify items
  return (OrderedList items'))

bulletList = try (do
  items <- many1 (listItem bulletListStart)
  let items' = compactify items
  return (BulletList items'))

-- definition lists

definitionListItem = try $ do
  notFollowedBy blankline
  notFollowedBy' indentSpaces
  term <- manyTill inline newline
  raw <- many1 defRawBlock
  state <- getState
  let oldContext = stateParserContext state
  -- parse the extracted block, which may contain various block elements:
  rest <- getInput
  setInput (concat raw)
  contents <- parseBlocks
  setInput rest
  updateState (\st -> st {stateParserContext = oldContext})
  return ((normalizeSpaces term), contents)

defRawBlock = try $ do
  char ':'
  state <- getState
  let tabStop = stateTabStop state
  try (count (tabStop - 1) (char ' ')) <|> (do{many (char ' '); string "\t"})
  firstline <- anyLine
  rawlines <- many (do {notFollowedBy' blankline; indentSpaces; anyLine})
  trailing <- option "" blanklines
  return $ firstline ++ "\n" ++ unlines rawlines ++ trailing

definitionList = do
  failIfStrict
  items <- many1 definitionListItem
  let (terms, defs) = unzip items
  let defs' = compactify defs
  let items' = zip terms defs'
  return $ DefinitionList items'

--
-- paragraph block
--

para = try (do 
  result <- many1 inline
  newline
  st <- getState
  if stateStrict st
     then choice [lookAhead blockQuote, lookAhead header, 
                  (do{blanklines; return Null})]
     else choice [(do{lookAhead emacsBoxQuote; return Null}), 
                  (do{blanklines; return Null})]
  let result' = normalizeSpaces result
  return (Para result'))

plain = do
  result <- many1 inline
  let result' = normalizeSpaces result
  return (Plain result')

-- 
-- raw html
--

htmlElement = choice [strictHtmlBlock,
                      htmlBlockElement] <?> "html element"

htmlBlock = do
  st <- getState
  if stateStrict st
    then do
           failUnlessBeginningOfLine
           first <- htmlElement
           finalSpace <- many (oneOf spaceChars)
           finalNewlines <- many newline
           return (RawHtml (first ++ finalSpace ++ finalNewlines))
    else rawHtmlBlocks

-- True if tag is self-closing
isSelfClosing tag = 
  isSuffixOf "/>" $ filter (\c -> (not (c `elem` " \n\t"))) tag

strictHtmlBlock = try (do
  tag <- anyHtmlBlockTag 
  let tag' = extractTagType tag
  if isSelfClosing tag || tag' == "hr" 
     then return tag
     else do
            contents <- many (do{notFollowedBy' (htmlEndTag tag'); 
                                 htmlElement <|> (count 1 anyChar)})
            end <- htmlEndTag tag'
            return $ tag ++ (concat contents) ++ end)

rawHtmlBlocks = try (do
  htmlBlocks <- many1 rawHtmlBlock    
  let combined = concatMap (\(RawHtml str) -> str) htmlBlocks
  let combined' = if (last combined == '\n')
                     then init combined  -- strip extra newline 
                     else combined 
  return (RawHtml combined'))

--
-- LaTeX
--

rawLaTeXEnvironment' = do
  failIfStrict
  rawLaTeXEnvironment

--
-- Tables
-- 

-- Parse a dashed line with optional trailing spaces; return its length
-- and the length including trailing space.
dashedLine ch = do
    dashes <- many1 (char ch)
    sp     <- many spaceChar
    return $ (length dashes, length $ dashes ++ sp)

-- Parse a table header with dashed lines of '-' preceded by 
-- one line of text.
simpleTableHeader = do
    rawContent  <- anyLine
    initSp      <- nonindentSpaces
    dashes      <- many1 (dashedLine '-')
    newline
    let (lengths, lines) = unzip dashes
    let indices  = scanl (+) (length initSp) lines
    let rawHeads = tail $ splitByIndices (init indices) rawContent
    let aligns   = zipWith alignType (map (\a -> [a]) rawHeads) lengths
    return $ (rawHeads, aligns, indices)

-- Parse a table footer - dashed lines followed by blank line.
tableFooter = try $ do
    nonindentSpaces
    many1 (dashedLine '-')
    blanklines

-- Parse a table separator - dashed line.
tableSep = try $ do
    nonindentSpaces
    many1 (dashedLine '-')
    string "\n"

-- Parse a raw line and split it into chunks by indices.
rawTableLine indices = do
    notFollowedBy' (blanklines <|> tableFooter)
    line <- many1Till anyChar newline
    return $ map removeLeadingTrailingSpace $ tail $ 
             splitByIndices (init indices) line

-- Parse a table line and return a list of lists of blocks (columns).
tableLine indices = try $ do
    rawline <- rawTableLine indices
    mapM (parseFromStr (many plain)) rawline

-- Parse a multiline table row and return a list of blocks (columns).
multilineRow indices = try $ do
    colLines <- many1 (rawTableLine indices)
    option "" blanklines
    let cols = map unlines $ transpose colLines
    mapM (parseFromStr (many plain)) cols

-- Calculate relative widths of table columns, based on indices
widthsFromIndices :: Int     -- Number of columns on terminal
                  -> [Int]   -- Indices
                  -> [Float] -- Fractional relative sizes of columns
widthsFromIndices _ [] = []  
widthsFromIndices numColumns indices = 
    let lengths = zipWith (-) indices (0:indices)
        totLength = sum lengths
        quotient = if totLength > numColumns
                     then fromIntegral totLength
                     else fromIntegral numColumns
        fracs = map (\l -> (fromIntegral l) / quotient) lengths in
    tail fracs

-- Parses a table caption:  inlines beginning with 'Table:'
-- and followed by blank lines.
tableCaption = try $ do
    nonindentSpaces
    string "Table:"
    result <- many1 inline
    blanklines
    return $ normalizeSpaces result

-- Parse a table using 'headerParser', 'lineParser', and 'footerParser'.
tableWith headerParser lineParser footerParser = try $ do
    (rawHeads, aligns, indices) <- headerParser
    lines <- many1Till (lineParser indices) footerParser
    caption <- option [] tableCaption
    heads <- mapM (parseFromStr (many plain)) rawHeads
    state <- getState
    let numColumns = stateColumns state
    let widths = widthsFromIndices numColumns indices
    return $ Table caption aligns widths heads lines

-- Parse a simple table with '---' header and one line per row.
simpleTable = tableWith simpleTableHeader tableLine blanklines

-- Parse a multiline table:  starts with row of '-' on top, then header
-- (which may be multiline), then the rows,
-- which may be multiline, separated by blank lines, and
-- ending with a footer (dashed line followed by blank line).
multilineTable = tableWith multilineTableHeader multilineRow tableFooter

multilineTableHeader = try $ do
    tableSep 
    rawContent  <- many1 (do{notFollowedBy' tableSep; 
                             many1Till anyChar newline})
    initSp      <- nonindentSpaces
    dashes      <- many1 (dashedLine '-')
    newline
    let (lengths, lines) = unzip dashes
    let indices  = scanl (+) (length initSp) lines
    let rawHeadsList = transpose $ map 
                       (\ln -> tail $ splitByIndices (init indices) ln)
                       rawContent
    let rawHeads = map (joinWithSep " ") rawHeadsList
    let aligns   = zipWith alignType rawHeadsList lengths
    return $ ((map removeLeadingTrailingSpace rawHeads),
             aligns, indices)

-- Returns the longest of a list of strings.
longest :: [String] -> String
longest [] = ""
longest [x] = x
longest (x:xs) =
    if (length x) >= (maximum $ map length xs)
      then x
      else longest xs

-- Returns an alignment type for a table, based on a list of strings
-- (the rows of the column header) and a number (the length of the
-- dashed line under the rows.
alignType :: [String] -> Int -> Alignment
alignType []  len = AlignDefault
alignType strLst len =
    let str        = longest $ map removeTrailingSpace strLst
        leftSpace  = if null str then False else ((str !! 0) `elem` " \t")
        rightSpace = (length str < len || (str !! (len - 1)) `elem` " \t") in
    case (leftSpace, rightSpace) of
        (True,  False)   -> AlignRight
        (False, True)    -> AlignLeft
        (True, True)     -> AlignCenter
        (False, False)   -> AlignDefault

table = do
    failIfStrict
    result <- simpleTable <|> multilineTable <?> "table"
    return result

-- 
-- inline
--

inline = choice [ rawLaTeXInline'
                , escapedChar
                , entity
                , note
                , inlineNote
                , link
                , referenceLink
                , rawHtmlInline'
                , autoLink
                , image
                , math
                , strong
                , emph
                , strikeout
                , superscript
                , subscript
                , smartPunctuation
                , code
                , ltSign
                , symbol
                , str
                , linebreak
                , tabchar
                , whitespace
                , endline ] <?> "inline"

escapedChar = try $ do
  char '\\'
  state <- getState
  result <- if stateStrict state 
              then oneOf "\\`*_{}[]()>#+-.!~"
              else satisfy (not . isAlphaNum)
  return (Str [result])

ltSign = try (do
  notFollowedBy (noneOf "<")   -- continue only if it's a <
  notFollowedBy' rawHtmlBlocks -- don't return < if it starts html
  char '<'
  return (Str ['<']))

specialCharsMinusLt = filter (/= '<') specialChars

symbol = do 
  result <- oneOf specialCharsMinusLt
  return (Str [result])

-- parses inline code, between n `s and n `s
code = try (do 
  starts <- many1 (char '`')
  let num = length starts
  result <- many1Till anyChar (try (count num (char '`')))
  -- get rid of any internal newlines
  let result' = removeLeadingTrailingSpace $ joinWithSep " " $ lines result
  return (Code result'))

mathWord = many1 (choice [ (noneOf " \t\n\\$"), 
                           (try (do
                                   c <- char '\\'
                                   notFollowedBy (char '$')
                                   return c))])

math = try (do
  failIfStrict
  char '$'
  notFollowedBy space
  words <- sepBy1 mathWord (many1 space)
  char '$'
  return (TeX ("$" ++ (joinWithSep " " words) ++ "$")))

emph = do
  result <- choice [ (enclosed (char '*') (char '*') inline), 
                     (enclosed (char '_') (char '_') inline) ]
  return $ Emph (normalizeSpaces result)

strong = do
  result <- (enclosed (string "**") (string "**") inline) <|> 
            (enclosed (string "__") (string "__") inline)
  return $ Strong (normalizeSpaces result)

strikeout = do
  failIfStrict
  result <- enclosed (string "~~") (string "~~") inline
  return $ Strikeout (normalizeSpaces result)

superscript = do
  failIfStrict
  result <- enclosed (char '^') (char '^') 
            (notFollowedBy' whitespace >> inline)  -- may not contain Space
  return $ Superscript result

subscript = do
  failIfStrict
  result <- enclosed (char '~') (char '~')
           (notFollowedBy' whitespace >> inline)   -- may not contain Space
  return $ Subscript result

smartPunctuation = do
  failUnlessSmart
  choice [ quoted, apostrophe, dash, ellipses ]

apostrophe = do
  char '\'' <|> char '\8217'
  return Apostrophe

quoted = do
  doubleQuoted <|> singleQuoted 

withQuoteContext context parser = do
  oldState <- getState
  let oldQuoteContext = stateQuoteContext oldState
  setState oldState { stateQuoteContext = context }
  result <- parser
  newState <- getState
  setState newState { stateQuoteContext = oldQuoteContext }
  return result

singleQuoted = try $ do
  singleQuoteStart
  withQuoteContext InSingleQuote $ do
    result <- many1Till inline singleQuoteEnd
    return $ Quoted SingleQuote $ normalizeSpaces result

doubleQuoted = try $ do 
  doubleQuoteStart
  withQuoteContext InDoubleQuote $ do
    result <- many1Till inline doubleQuoteEnd
    return $ Quoted DoubleQuote $ normalizeSpaces result

failIfInQuoteContext context = do
  st <- getState
  if (stateQuoteContext st == context)
    then fail "already inside quotes"
    else return ()

singleQuoteStart = try $ do 
  failIfInQuoteContext InSingleQuote
  char '\8216' <|> do 
                     char '\''  
                     notFollowedBy (oneOf ")!],.;:-? \t\n")
                     notFollowedBy (try (do  -- possessive or contraction
                                           oneOfStrings ["s","t","m","ve","ll","re"]
                                           satisfy (not . isAlphaNum)))
                     return '\''

singleQuoteEnd = try $ do
  char '\'' <|> char '\8217'
  notFollowedBy alphaNum

doubleQuoteStart = try $ do
  failIfInQuoteContext InDoubleQuote
  char '"' <|> char '\8220'
  notFollowedBy (oneOf " \t\n")

doubleQuoteEnd = char '"' <|> char '\8221'

ellipses = try (do
  oneOfStrings ["...", " . . . ", ". . .", " . . ."]
  return Ellipses)

dash = enDash <|> emDash

enDash = try (do
  char '-'
  notFollowedBy (noneOf "0123456789")
  return EnDash) 

emDash = try (do
  skipSpaces
  oneOfStrings ["---", "--"]
  skipSpaces
  return EmDash)

whitespace = do
  many1 (oneOf spaceChars) <?> "whitespace"
  return Space

tabchar = do
  tab
  return (Str "\t")

-- hard line break
linebreak = try (do
  oneOf spaceChars
  many1 (oneOf spaceChars) 
  endline
  return LineBreak )

nonEndline = satisfy (/='\n')

entity = do
  ent <- characterEntity
  return $ Str [ent]

strChar = noneOf (specialChars ++ spaceChars ++ "\n")

str = do 
  result <- many1 strChar
  return (Str result)

-- an endline character that can be treated as a space, not a structural break
endline = try (do
  newline
  notFollowedBy blankline
  st <- getState
  if stateStrict st 
    then do
           notFollowedBy' emailBlockQuoteStart
           notFollowedBy (char '#')  -- atx header
           notFollowedBy (try (do{manyTill anyChar newline; 
                                  oneOf setextHChars}))  -- setext header
    else return () 
  -- parse potential list-starts differently if in a list:
  if (stateParserContext st) == ListItemState
     then notFollowedBy' (orderedListStart <|> bulletListStart)
     else return ()
  return Space)

--
-- links
--

-- a reference label for a link
reference = inlinesInBalanced "[" "]" >>= (return . normalizeSpaces)

-- source for a link, with optional title
source = try $ do 
  char '('
  option ' ' (char '<')
  src <- many (noneOf ")> \t\n")
  option ' ' (char '>')
  tit <- option "" title
  skipSpaces
  char ')'
  return (removeTrailingSpace src, tit)

titleWith startChar endChar = try (do
  leadingSpace <- many1 (oneOf " \t\n")
  if length (filter (=='\n') leadingSpace) > 1
    then fail "title must be separated by space and on same or next line"
    else return ()
  char startChar
  tit <- manyTill anyChar (try (do char endChar
                                   skipSpaces
                                   notFollowedBy (noneOf ")\n")))
  return $ decodeEntities tit)

title = choice [ titleWith '(' ')', 
                 titleWith '"' '"', 
                 titleWith '\'' '\''] <?> "title"

link = choice [explicitLink, referenceLink] <?> "link"

explicitLink = try (do
  label <- reference
  src <- source 
  return (Link label src)) 

-- a link like [this][ref] or [this][] or [this]
referenceLink = try $ do
  label <- reference
  ref <- option [] (try (do skipSpaces
                            option ' ' newline
                            skipSpaces
                            reference))
  let ref' = if null ref then label else ref
  state <- getState
  case lookupKeySrc (stateKeys state) ref' of
     Nothing -> fail "no corresponding key" 
     Just target -> return (Link label target)

autoLink = autoLinkEmail <|> autoLinkRegular

-- a link <like@this.com>
autoLinkEmail = try $ do
  char '<'
  name <- many1Till (noneOf "/:<> \t\n") (char '@')
  domain <- sepBy1 (many1 (noneOf "/:.@<> \t\n")) (char '.')
  let src = name ++ "@" ++ (joinWithSep "." domain)
  char '>'
  return $ Link [Str src] (("mailto:" ++ src), "")

-- a link <http://like.this.com>
autoLinkRegular = try $ do
  char '<'
  prot <- oneOfStrings ["http:", "ftp:", "mailto:"]
  rest <- many1Till (noneOf " \t\n<>") (char '>')
  let src = prot ++ rest
  return $ Link [Str src] (src, "")

image = try (do
  char '!'
  (Link label src) <- link
  return (Image label src)) 

note = try $ do
  failIfStrict
  ref <- noteMarker
  state <- getState
  let notes = stateNotes state
  case lookup ref notes of
    Nothing -> fail "note not found"
    Just contents -> return (Note contents)

inlineNote = try $ do
  failIfStrict
  char '^'
  contents <- inlinesInBalanced "[" "]"
  return (Note [Para contents])

rawLaTeXInline' = do
  failIfStrict
  rawLaTeXInline

rawHtmlInline' = do
  st <- getState
  result <- if stateStrict st
              then choice [htmlBlockElement, anyHtmlTag, anyHtmlEndTag] 
              else choice [htmlBlockElement, anyHtmlInlineTag]
  return (HtmlInline result)