aboutsummaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/Parsing.hs
blob: 48c6aa70d9313500de449a35bf7441b8c72588c4 (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
{-
Copyright (C) 2006-2010 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.Parsing
   Copyright   : Copyright (C) 2006-2010 John MacFarlane
   License     : GNU GPL, version 2 or above 

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

A utility library with parsers used in pandoc readers.
-}
module Text.Pandoc.Parsing ( (>>~),
                             anyLine,
                             many1Till,
                             notFollowedBy',
                             oneOfStrings,
                             spaceChar,
                             skipSpaces,
                             blankline,
                             blanklines,
                             enclosed,
                             stringAnyCase,
                             parseFromString,
                             lineClump,
                             charsInBalanced,
                             charsInBalanced',
                             romanNumeral,
                             emailAddress,
                             uri,
                             withHorizDisplacement,
                             nullBlock,
                             failIfStrict,
                             failUnlessLHS,
                             escaped,
                             anyOrderedListMarker,
                             orderedListMarker,
                             charRef,
                             tableWith,
                             gridTableWith,
                             readWith,
                             testStringWith,
                             ParserState (..),
                             defaultParserState,
                             HeaderType (..),
                             ParserContext (..),
                             QuoteContext (..),
                             NoteTable,
                             KeyTable,
                             Key,
                             toKey,
                             fromKey,
                             lookupKeySrc,
                             smartPunctuation )
where

import Text.Pandoc.Definition
import qualified Text.Pandoc.UTF8 as UTF8 (putStrLn)
import Text.ParserCombinators.Parsec
import Text.Pandoc.CharacterReferences ( characterReference )
import Data.Char ( toLower, toUpper, ord, isAscii, isAlphaNum )
import Data.List ( intercalate, transpose )
import Network.URI ( parseURI, URI (..), isAllowedInURI )
import Control.Monad ( join, liftM, guard )
import Text.Pandoc.Shared
import qualified Data.Map as M
import Text.TeXMath.Macros (Macro)

-- | Like >>, but returns the operation on the left.
-- (Suggested by Tillmann Rendel on Haskell-cafe list.)
(>>~) :: (Monad m) => m a -> m b -> m a
a >>~ b = a >>= \x -> b >> return x

-- | Parse any line of text
anyLine :: GenParser Char st [Char]
anyLine = manyTill anyChar newline

-- | Like @manyTill@, but reads at least one item.
many1Till :: GenParser tok st a
          -> GenParser tok st end
          -> GenParser tok st [a]
many1Till p end = do
         first <- p
         rest <- manyTill p end
         return (first:rest)

-- | A more general form of @notFollowedBy@.  This one allows any 
-- type of parser to be specified, and succeeds only if that parser fails.
-- It does not consume any input.
notFollowedBy' :: Show b => GenParser a st b -> GenParser a st ()
notFollowedBy' p  = try $ join $  do  a <- try p
                                      return (unexpected (show a))
                                  <|>
                                  return (return ())
-- (This version due to Andrew Pimlott on the Haskell mailing list.)

-- | Parses one of a list of strings (tried in order).  
oneOfStrings :: [String] -> GenParser Char st String
oneOfStrings listOfStrings = choice $ map (try . string) listOfStrings

-- | Parses a space or tab.
spaceChar :: CharParser st Char
spaceChar = char ' ' <|> char '\t'

-- | Skips zero or more spaces or tabs.
skipSpaces :: GenParser Char st ()
skipSpaces = skipMany spaceChar

-- | Skips zero or more spaces or tabs, then reads a newline.
blankline :: GenParser Char st Char
blankline = try $ skipSpaces >> newline

-- | Parses one or more blank lines and returns a string of newlines.
blanklines :: GenParser Char st [Char]
blanklines = many1 blankline

-- | Parses material enclosed between start and end parsers.
enclosed :: GenParser Char st t   -- ^ start parser
         -> GenParser Char st end  -- ^ end parser
         -> GenParser Char st a    -- ^ content parser (to be used repeatedly)
         -> GenParser Char st [a]
enclosed start end parser = try $ 
  start >> notFollowedBy space >> many1Till parser end

-- | Parse string, case insensitive.
stringAnyCase :: [Char] -> CharParser st String
stringAnyCase [] = string ""
stringAnyCase (x:xs) = do
  firstChar <- char (toUpper x) <|> char (toLower x)
  rest <- stringAnyCase xs
  return (firstChar:rest)

-- | Parse contents of 'str' using 'parser' and return result.
parseFromString :: GenParser tok st a -> [tok] -> GenParser tok st a
parseFromString parser str = do
  oldPos <- getPosition
  oldInput <- getInput
  setInput str
  result <- parser
  setInput oldInput
  setPosition oldPos
  return result

-- | Parse raw line block up to and including blank lines.
lineClump :: GenParser Char st String
lineClump = blanklines 
          <|> (many1 (notFollowedBy blankline >> anyLine) >>= return . unlines)

-- | Parse a string of characters between an open character
-- and a close character, including text between balanced
-- pairs of open and close, which must be different. For example,
-- @charsInBalanced '(' ')'@ will parse "(hello (there))"
-- and return "hello (there)".  Stop if a blank line is
-- encountered.
charsInBalanced :: Char -> Char -> GenParser Char st String
charsInBalanced open close = try $ do
  char open
  raw <- many $     (many1 (noneOf [open, close, '\n']))
                <|> (do res <- charsInBalanced open close
                        return $ [open] ++ res ++ [close])
                <|> try (string "\n" >>~ notFollowedBy' blanklines)
  char close
  return $ concat raw

-- | Like @charsInBalanced@, but allow blank lines in the content.
charsInBalanced' :: Char -> Char -> GenParser Char st String
charsInBalanced' open close = try $ do
  char open
  raw <- many $       (many1 (noneOf [open, close]))
                  <|> (do res <- charsInBalanced' open close
                          return $ [open] ++ res ++ [close])
  char close
  return $ concat raw

-- Auxiliary functions for romanNumeral:

lowercaseRomanDigits :: [Char]
lowercaseRomanDigits = ['i','v','x','l','c','d','m']

uppercaseRomanDigits :: [Char]
uppercaseRomanDigits = map toUpper lowercaseRomanDigits

-- | Parses a roman numeral (uppercase or lowercase), returns number.
romanNumeral :: Bool                  -- ^ Uppercase if true
             -> GenParser Char st Int
romanNumeral upperCase = do
    let romanDigits = if upperCase 
                         then uppercaseRomanDigits 
                         else lowercaseRomanDigits
    lookAhead $ oneOf romanDigits 
    let [one, five, ten, fifty, hundred, fivehundred, thousand] = 
          map char romanDigits
    thousands <- many thousand >>= (return . (1000 *) . length)
    ninehundreds <- option 0 $ try $ hundred >> thousand >> return 900
    fivehundreds <- many fivehundred >>= (return . (500 *) . length)
    fourhundreds <- option 0 $ try $ hundred >> fivehundred >> return 400
    hundreds <- many hundred >>= (return . (100 *) . length)
    nineties <- option 0 $ try $ ten >> hundred >> return 90
    fifties <- many fifty >>= (return . (50 *) . length)
    forties <- option 0 $ try $ ten >> fifty >> return 40
    tens <- many ten >>= (return . (10 *) . length)
    nines <- option 0 $ try $ one >> ten >> return 9
    fives <- many five >>= (return . (5 *) . length)
    fours <- option 0 $ try $ one >> five >> return 4
    ones <- many one >>= (return . length)
    let total = thousands + ninehundreds + fivehundreds + fourhundreds +
                hundreds + nineties + fifties + forties + tens + nines +
                fives + fours + ones
    if total == 0
       then fail "not a roman numeral"
       else return total

-- Parsers for email addresses and URIs

emailChar :: GenParser Char st Char
emailChar = alphaNum <|> oneOf "-+_."

domainChar :: GenParser Char st Char
domainChar = alphaNum <|> char '-'

domain :: GenParser Char st [Char]
domain = do
  first <- many1 domainChar
  dom <- many1 $ try (char '.' >> many1 domainChar )
  return $ intercalate "." (first:dom)

-- | Parses an email address; returns original and corresponding
-- escaped mailto: URI.
emailAddress :: GenParser Char st (String, String)
emailAddress = try $ do
  firstLetter <- alphaNum
  restAddr <- many emailChar
  let addr = firstLetter:restAddr
  char '@'
  dom <- domain
  let full = addr ++ '@':dom
  return (full, escapeURI $ "mailto:" ++ full)

-- | Parses a URI. Returns pair of original and URI-escaped version.
uri :: GenParser Char st (String, String)
uri = try $ do
  let protocols = [ "http:", "https:", "ftp:", "file:", "mailto:",
                    "news:", "telnet:" ]
  lookAhead $ oneOfStrings protocols
  -- scan non-ascii characters and ascii characters allowed in a URI
  str <- many1 $ satisfy (\c -> not (isAscii c) || isAllowedInURI c)
  -- now see if they amount to an absolute URI
  case parseURI (escapeURI str) of
       Just uri' -> if uriScheme uri' `elem` protocols
                       then return (str, show uri')
                       else fail "not a URI"
       Nothing   -> fail "not a URI"

-- | Applies a parser, returns tuple of its results and its horizontal
-- displacement (the difference between the source column at the end
-- and the source column at the beginning). Vertical displacement
-- (source row) is ignored.
withHorizDisplacement :: GenParser Char st a  -- ^ Parser to apply
                      -> GenParser Char st (a, Int) -- ^ (result, displacement)
withHorizDisplacement parser = do
  pos1 <- getPosition
  result <- parser
  pos2 <- getPosition
  return (result, sourceColumn pos2 - sourceColumn pos1)

-- | Parses a character and returns 'Null' (so that the parser can move on
-- if it gets stuck).
nullBlock :: GenParser Char st Block
nullBlock = anyChar >> return Null

-- | Fail if reader is in strict markdown syntax mode.
failIfStrict :: GenParser Char ParserState ()
failIfStrict = do
  state <- getState
  if stateStrict state then fail "strict mode" else return ()

-- | Fail unless we're in literate haskell mode.
failUnlessLHS :: GenParser tok ParserState ()
failUnlessLHS = do
  state <- getState
  if stateLiterateHaskell state then return () else fail "Literate haskell feature"

-- | Parses backslash, then applies character parser.
escaped :: GenParser Char st Char  -- ^ Parser for character to escape
        -> GenParser Char st Inline
escaped parser = try $ do
  char '\\'
  result <- parser
  return (Str [result])

-- | Parses an uppercase roman numeral and returns (UpperRoman, number).
upperRoman :: GenParser Char st (ListNumberStyle, Int)
upperRoman = do
  num <- romanNumeral True
  return (UpperRoman, num)

-- | Parses a lowercase roman numeral and returns (LowerRoman, number).
lowerRoman :: GenParser Char st (ListNumberStyle, Int)
lowerRoman = do
  num <- romanNumeral False
  return (LowerRoman, num)

-- | Parses a decimal numeral and returns (Decimal, number).
decimal :: GenParser Char st (ListNumberStyle, Int)
decimal = do
  num <- many1 digit
  return (Decimal, read num)

-- | Parses a '@' and optional label and
-- returns (DefaultStyle, [next example number]).  The next
-- example number is incremented in parser state, and the label
-- (if present) is added to the label table.
exampleNum :: GenParser Char ParserState (ListNumberStyle, Int)
exampleNum = do
  char '@'
  lab <- many (alphaNum <|> oneOf "_-")
  st <- getState
  let num = stateNextExample st
  let newlabels = if null lab
                     then stateExamples st
                     else M.insert lab num $ stateExamples st
  updateState $ \s -> s{ stateNextExample = num + 1
                       , stateExamples    = newlabels }
  return (Example, num)

-- | Parses a '#' returns (DefaultStyle, 1).
defaultNum :: GenParser Char st (ListNumberStyle, Int)
defaultNum = do
  char '#'
  return (DefaultStyle, 1)

-- | Parses a lowercase letter and returns (LowerAlpha, number).
lowerAlpha :: GenParser Char st (ListNumberStyle, Int)
lowerAlpha = do
  ch <- oneOf ['a'..'z']
  return (LowerAlpha, ord ch - ord 'a' + 1)

-- | Parses an uppercase letter and returns (UpperAlpha, number).
upperAlpha :: GenParser Char st (ListNumberStyle, Int)
upperAlpha = do
  ch <- oneOf ['A'..'Z']
  return (UpperAlpha, ord ch - ord 'A' + 1)

-- | Parses a roman numeral i or I
romanOne :: GenParser Char st (ListNumberStyle, Int)
romanOne = (char 'i' >> return (LowerRoman, 1)) <|>
           (char 'I' >> return (UpperRoman, 1))

-- | Parses an ordered list marker and returns list attributes.
anyOrderedListMarker :: GenParser Char ParserState ListAttributes 
anyOrderedListMarker = choice $ 
  [delimParser numParser | delimParser <- [inPeriod, inOneParen, inTwoParens],
                           numParser <- [decimal, exampleNum, defaultNum, romanOne,
                           lowerAlpha, lowerRoman, upperAlpha, upperRoman]]

-- | Parses a list number (num) followed by a period, returns list attributes.
inPeriod :: GenParser Char st (ListNumberStyle, Int)
         -> GenParser Char st ListAttributes 
inPeriod num = try $ do
  (style, start) <- num
  char '.'
  let delim = if style == DefaultStyle
                 then DefaultDelim
                 else Period
  return (start, style, delim)
 
-- | Parses a list number (num) followed by a paren, returns list attributes.
inOneParen :: GenParser Char st (ListNumberStyle, Int)
           -> GenParser Char st ListAttributes 
inOneParen num = try $ do
  (style, start) <- num
  char ')'
  return (start, style, OneParen)

-- | Parses a list number (num) enclosed in parens, returns list attributes.
inTwoParens :: GenParser Char st (ListNumberStyle, Int)
            -> GenParser Char st ListAttributes 
inTwoParens num = try $ do
  char '('
  (style, start) <- num
  char ')'
  return (start, style, TwoParens)

-- | Parses an ordered list marker with a given style and delimiter,
-- returns number.
orderedListMarker :: ListNumberStyle 
                  -> ListNumberDelim 
                  -> GenParser Char ParserState Int
orderedListMarker style delim = do
  let num = defaultNum <|>  -- # can continue any kind of list
            case style of
               DefaultStyle -> decimal
               Example      -> exampleNum
               Decimal      -> decimal
               UpperRoman   -> upperRoman
               LowerRoman   -> lowerRoman
               UpperAlpha   -> upperAlpha
               LowerAlpha   -> lowerAlpha
  let context = case delim of
               DefaultDelim -> inPeriod
               Period       -> inPeriod
               OneParen     -> inOneParen
               TwoParens    -> inTwoParens
  (start, _, _) <- context num
  return start

-- | Parses a character reference and returns a Str element.
charRef :: GenParser Char st Inline
charRef = do
  c <- characterReference
  return $ Str [c]

-- | Parse a table using 'headerParser', 'rowParser',
-- 'lineParser', and 'footerParser'.
tableWith :: GenParser Char ParserState ([[Block]], [Alignment], [Int])
          -> ([Int] -> GenParser Char ParserState [[Block]])
          -> GenParser Char ParserState sep
          -> GenParser Char ParserState end
          -> GenParser Char ParserState [Inline]
          -> GenParser Char ParserState Block
tableWith headerParser rowParser lineParser footerParser captionParser = try $ do
    caption' <- option [] captionParser
    (heads, aligns, indices) <- headerParser
    lines' <- rowParser indices `sepEndBy` lineParser
    footerParser
    caption <- if null caption'
                  then option [] captionParser
                  else return caption'
    state <- getState
    let numColumns = stateColumns state
    let widths = widthsFromIndices numColumns indices
    return $ Table caption aligns widths heads lines'

-- Calculate relative widths of table columns, based on indices
widthsFromIndices :: Int      -- Number of columns on terminal
                  -> [Int]    -- Indices
                  -> [Double] -- Fractional relative sizes of columns
widthsFromIndices _ [] = []  
widthsFromIndices numColumns indices = 
  let lengths' = zipWith (-) indices (0:indices)
      lengths  = reverse $
                 case reverse lengths' of
                      []       -> []
                      [x]      -> [x]
                      -- compensate for the fact that intercolumn
                      -- spaces are counted in widths of all columns
                      -- but the last...
                      (x:y:zs) -> if x < y && y - x <= 2
                                     then y:y:zs
                                     else x:y:zs
      totLength = sum lengths
      quotient = if totLength > numColumns
                   then fromIntegral totLength
                   else fromIntegral numColumns
      fracs = map (\l -> (fromIntegral l) / quotient) lengths in
  tail fracs

-- Parse a grid table:  starts with row of '-' on top, then header
-- (which may be grid), then the rows,
-- which may be grid, separated by blank lines, and
-- ending with a footer (dashed line followed by blank line).
gridTableWith :: GenParser Char ParserState Block    -- ^ Block parser
              -> GenParser Char ParserState [Inline] -- ^ Caption parser
              -> Bool                                -- ^ Headerless table
              -> GenParser Char ParserState Block
gridTableWith block tableCaption headless =
  tableWith (gridTableHeader headless block) (gridTableRow block) (gridTableSep '-') gridTableFooter tableCaption

gridTableSplitLine :: [Int] -> String -> [String]
gridTableSplitLine indices line =
  map removeFinalBar $ tail $ splitByIndices (init indices) line

gridPart :: Char -> GenParser Char st (Int, Int)
gridPart ch = do
  dashes <- many1 (char ch)
  char '+'
  return (length dashes, length dashes + 1)

gridDashedLines :: Char -> GenParser Char st [(Int,Int)]
gridDashedLines ch = try $ char '+' >> many1 (gridPart ch) >>~ blankline

removeFinalBar :: String -> String
removeFinalBar = reverse . dropWhile (=='|') .  dropWhile (`elem` " \t") .
                 reverse

-- | Separator between rows of grid table.
gridTableSep :: Char -> GenParser Char ParserState Char
gridTableSep ch = try $ gridDashedLines ch >> return '\n'

-- | Parse header for a grid table.
gridTableHeader :: Bool -- ^ Headerless table
                -> GenParser Char ParserState Block
                -> GenParser Char ParserState ([[Block]], [Alignment], [Int])
gridTableHeader headless block = try $ do
  optional blanklines
  dashes <- gridDashedLines '-'
  rawContent  <- if headless
                    then return $ repeat "" 
                    else many1
                         (notFollowedBy (gridTableSep '=') >> char '|' >>
                           many1Till anyChar newline)
  if headless
     then return ()
     else gridTableSep '=' >> return ()
  let lines'   = map snd dashes
  let indices  = scanl (+) 0 lines'
  let aligns   = replicate (length lines') AlignDefault
  -- RST does not have a notion of alignments
  let rawHeads = if headless
                    then replicate (length dashes) ""
                    else map (intercalate " ") $ transpose
                       $ map (gridTableSplitLine indices) rawContent
  heads <- mapM (parseFromString $ many block) $
               map removeLeadingTrailingSpace rawHeads
  return (heads, aligns, indices)

gridTableRawLine :: [Int] -> GenParser Char ParserState [String]
gridTableRawLine indices = do
  char '|'
  line <- many1Till anyChar newline
  return (gridTableSplitLine indices $ removeTrailingSpace line)

-- | Parse row of grid table.
gridTableRow :: GenParser Char ParserState Block
             -> [Int]
             -> GenParser Char ParserState [[Block]]
gridTableRow block indices = do
  colLines <- many1 (gridTableRawLine indices)
  let cols = map ((++ "\n") . unlines . removeOneLeadingSpace) $
               transpose colLines
  mapM (liftM compactifyCell . parseFromString (many block)) cols

removeOneLeadingSpace :: [String] -> [String]
removeOneLeadingSpace xs =
  if all startsWithSpace xs
     then map (drop 1) xs
     else xs
   where startsWithSpace ""     = True
         startsWithSpace (y:_) = y == ' '

compactifyCell :: [Block] -> [Block]
compactifyCell bs = head $ compactify [bs]

-- | Parse footer for a grid table.
gridTableFooter :: GenParser Char ParserState [Char]
gridTableFooter = blanklines

---

-- | Parse a string with a given parser and state.
readWith :: GenParser Char ParserState a      -- ^ parser
         -> ParserState                    -- ^ initial state
         -> String                         -- ^ input string
         -> a
readWith parser state input = 
    case runParser parser state "source" input of
      Left err     -> error $ "\nError:\n" ++ show err
      Right result -> result

-- | Parse a string with @parser@ (for testing).
testStringWith :: (Show a) => GenParser Char ParserState a
               -> String
               -> IO ()
testStringWith parser str = UTF8.putStrLn $ show $
                            readWith parser defaultParserState str

-- | Parsing options.
data ParserState = ParserState
    { stateParseRaw        :: Bool,          -- ^ Parse raw HTML and LaTeX?
      stateParserContext   :: ParserContext, -- ^ Inside list?
      stateQuoteContext    :: QuoteContext,  -- ^ Inside quoted environment?
      stateKeys            :: KeyTable,      -- ^ List of reference keys
      stateCitations       :: [String],      -- ^ List of available citations
      stateNotes           :: NoteTable,     -- ^ List of notes
      stateTabStop         :: Int,           -- ^ Tab stop
      stateStandalone      :: Bool,          -- ^ Parse bibliographic info?
      stateTitle           :: [Inline],      -- ^ Title of document
      stateAuthors         :: [[Inline]],    -- ^ Authors of document
      stateDate            :: [Inline],      -- ^ Date of document
      stateStrict          :: Bool,          -- ^ Use strict markdown syntax?
      stateSmart           :: Bool,          -- ^ Use smart typography?
      stateLiterateHaskell :: Bool,          -- ^ Treat input as literate haskell
      stateColumns         :: Int,           -- ^ Number of columns in terminal
      stateHeaderTable     :: [HeaderType],  -- ^ Ordered list of header types used
      stateIndentedCodeClasses :: [String],  -- ^ Classes to use for indented code blocks
      stateNextExample     :: Int,           -- ^ Number of next example
      stateExamples        :: M.Map String Int, -- ^ Map from example labels to numbers 
      stateHasChapters     :: Bool,          -- ^ True if \chapter encountered
      stateApplyMacros     :: Bool,          -- ^ Apply LaTeX macros?
      stateMacros          :: [Macro]        -- ^ List of macros defined so far
    }
    deriving Show

defaultParserState :: ParserState
defaultParserState = 
    ParserState { stateParseRaw        = False,
                  stateParserContext   = NullState,
                  stateQuoteContext    = NoQuote,
                  stateKeys            = M.empty,
                  stateCitations       = [],
                  stateNotes           = [],
                  stateTabStop         = 4,
                  stateStandalone      = False,
                  stateTitle           = [],
                  stateAuthors         = [],
                  stateDate            = [],
                  stateStrict          = False,
                  stateSmart           = False,
                  stateLiterateHaskell = False,
                  stateColumns         = 80,
                  stateHeaderTable     = [],
                  stateIndentedCodeClasses = [],
                  stateNextExample     = 1,
                  stateExamples        = M.empty,
                  stateHasChapters     = False,
                  stateApplyMacros     = True,
                  stateMacros          = []}

data HeaderType 
    = SingleHeader Char  -- ^ Single line of characters underneath
    | DoubleHeader Char  -- ^ Lines of characters above and below
    deriving (Eq, Show)

data ParserContext 
    = ListItemState   -- ^ Used when running parser on list item contents
    | NullState       -- ^ Default state
    deriving (Eq, Show)

data QuoteContext
    = InSingleQuote   -- ^ Used when parsing inside single quotes
    | InDoubleQuote   -- ^ Used when parsing inside double quotes
    | NoQuote         -- ^ Used when not parsing inside quotes
    deriving (Eq, Show)

type NoteTable = [(String, String)]

newtype Key = Key [Inline] deriving (Show, Read, Eq, Ord)

toKey :: [Inline] -> Key
toKey = Key . processWith lowercase
  where lowercase :: Inline -> Inline
        lowercase (Str xs)        = Str (map toLower xs)
        lowercase (Math t xs)     = Math t (map toLower xs)
        lowercase (Code xs)       = Code (map toLower xs)
        lowercase (TeX xs)        = TeX (map toLower xs)
        lowercase (HtmlInline xs) = HtmlInline (map toLower xs)
        lowercase LineBreak       = Space
        lowercase x               = x

fromKey :: Key -> [Inline]
fromKey (Key xs) = xs

type KeyTable = M.Map Key Target

-- | Look up key in key table and return target object.
lookupKeySrc :: KeyTable  -- ^ Key table
             -> Key       -- ^ Key
             -> Maybe Target
lookupKeySrc table key = case M.lookup key table of
                           Nothing  -> Nothing
                           Just src -> Just src

-- | Fail unless we're in "smart typography" mode.
failUnlessSmart :: GenParser tok ParserState ()
failUnlessSmart = getState >>= guard . stateSmart

smartPunctuation :: GenParser Char ParserState Inline
                 -> GenParser Char ParserState Inline
smartPunctuation inlineParser = do
  failUnlessSmart
  choice [ quoted inlineParser, apostrophe, dash, ellipses ]

apostrophe :: GenParser Char ParserState Inline
apostrophe = (char '\'' <|> char '\8217') >> return Apostrophe

quoted :: GenParser Char ParserState Inline
       -> GenParser Char ParserState Inline
quoted inlineParser = doubleQuoted inlineParser <|> singleQuoted inlineParser

withQuoteContext :: QuoteContext
                 -> (GenParser Char ParserState Inline)
                 -> GenParser Char ParserState Inline
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 :: GenParser Char ParserState Inline
             -> GenParser Char ParserState Inline
singleQuoted inlineParser = try $ do
  singleQuoteStart
  withQuoteContext InSingleQuote $ many1Till inlineParser singleQuoteEnd >>=
    return . Quoted SingleQuote . normalizeSpaces

doubleQuoted :: GenParser Char ParserState Inline
             -> GenParser Char ParserState Inline
doubleQuoted inlineParser = try $ do
  doubleQuoteStart
  withQuoteContext InDoubleQuote $ do
    contents <- manyTill inlineParser doubleQuoteEnd
    return . Quoted DoubleQuote . normalizeSpaces $ contents

failIfInQuoteContext :: QuoteContext -> GenParser tok ParserState ()
failIfInQuoteContext context = do
  st <- getState
  if stateQuoteContext st == context
     then fail "already inside quotes"
     else return ()

charOrRef :: [Char] -> GenParser Char st Char
charOrRef cs =
  oneOf cs <|> try (do c <- characterReference
                       guard (c `elem` cs)
                       return c)

singleQuoteStart :: GenParser Char ParserState ()
singleQuoteStart = do 
  failIfInQuoteContext InSingleQuote
  try $ do charOrRef "'\8216"
           notFollowedBy (oneOf ")!],.;:-? \t\n")
           notFollowedBy (try (oneOfStrings ["s","t","m","ve","ll","re"] >>
                               satisfy (not . isAlphaNum))) 
                               -- possess/contraction
           return ()

singleQuoteEnd :: GenParser Char st ()
singleQuoteEnd = try $ do
  charOrRef "'\8217"
  notFollowedBy alphaNum

doubleQuoteStart :: GenParser Char ParserState ()
doubleQuoteStart = do
  failIfInQuoteContext InDoubleQuote
  try $ do charOrRef "\"\8220"
           notFollowedBy (oneOf " \t\n")

doubleQuoteEnd :: GenParser Char st ()
doubleQuoteEnd = do
  charOrRef "\"\8221"
  return ()

ellipses :: GenParser Char st Inline
ellipses = do
  try (charOrRef "…") <|> try (string "..." >> return '…')
  return Ellipses

dash :: GenParser Char st Inline
dash = enDash <|> emDash

enDash :: GenParser Char st Inline
enDash = do
  try (charOrRef "–") <|>
    try (char '-' >> notFollowedBy (noneOf "0123456789") >> return '–')
  return EnDash

emDash :: GenParser Char st Inline
emDash = do
  try (charOrRef "—") <|> (oneOfStrings ["---", "--"] >> return '—')
  return EmDash