aboutsummaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/Readers/HTML.hs
blob: 462267d89744775c6d2823595c7611e6597ce3e1 (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
{-
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.Readers.HTML
   Copyright   : Copyright (C) 2006-2010 John MacFarlane
   License     : GNU GPL, version 2 or above 

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

Conversion of HTML to 'Pandoc' document.
-}
module Text.Pandoc.Readers.HTML ( 
                                 readHtml, 
                                 rawHtmlInline, 
                                 rawHtmlBlock, 
                                 anyHtmlBlockTag, 
                                 anyHtmlInlineTag,  
                                 anyHtmlTag,
                                 anyHtmlEndTag,
                                 htmlTag,
                                 htmlEndTag,
                                 extractTagType,
                                 htmlBlockElement,
                                 htmlComment,
                                 unsanitaryURI
                                ) where

import Text.ParserCombinators.Parsec
import Text.Pandoc.Definition
import Text.Pandoc.Shared
import Text.Pandoc.Parsing
import Text.Pandoc.CharacterReferences ( decodeCharacterReferences )
import Data.Maybe ( fromMaybe )
import Data.List ( isPrefixOf, isSuffixOf, intercalate )
import Data.Char ( toLower, isAlphaNum )
import Network.URI ( parseURIReference, URI (..) )
import Control.Monad ( liftM, when )

-- | Convert HTML-formatted string to 'Pandoc' document.
readHtml :: ParserState   -- ^ Parser state
         -> String        -- ^ String to parse (assumes @'\n'@ line endings)
         -> Pandoc
readHtml = readWith parseHtml

--
-- Constants
--

eitherBlockOrInline :: [[Char]]
eitherBlockOrInline = ["applet", "button", "del", "iframe", "ins",
                  "map", "area", "object"]

{-
inlineHtmlTags :: [[Char]]
inlineHtmlTags = ["a", "abbr", "acronym", "b", "basefont", "bdo", "big",
                  "br", "cite", "code", "dfn", "em", "font", "i", "img",
                  "input", "kbd", "label", "q", "s", "samp", "select",
                  "small", "span", "strike", "strong", "sub", "sup",
                  "textarea", "tt", "u", "var"]
-}

blockHtmlTags :: [[Char]]
blockHtmlTags = ["address", "blockquote", "body", "center", "dir", "div",
                 "dl", "fieldset", "form", "h1", "h2", "h3", "h4",
                 "h5", "h6", "head", "hr", "html", "isindex", "menu", "noframes",
                 "noscript", "ol", "p", "pre", "table", "ul", "dd",
                 "dt", "frameset", "li", "tbody", "td", "tfoot",
                 "th", "thead", "tr", "script", "style"]

sanitaryTags :: [[Char]]
sanitaryTags = ["a", "abbr", "acronym", "address", "area", "b", "big",
                "blockquote", "br", "button", "caption", "center",
                "cite", "code", "col", "colgroup", "dd", "del", "dfn",
                "dir", "div", "dl", "dt", "em", "fieldset", "font",
                "form", "h1", "h2", "h3", "h4", "h5", "h6", "hr",
                "i", "img", "input", "ins", "kbd", "label", "legend",
                "li", "map", "menu", "ol", "optgroup", "option", "p",
                "pre", "q", "s", "samp", "select", "small", "span",
                "strike", "strong", "sub", "sup", "table", "tbody",
                "td", "textarea", "tfoot", "th", "thead", "tr", "tt",
                "u", "ul", "var"]

sanitaryAttributes :: [[Char]]
sanitaryAttributes = ["abbr", "accept", "accept-charset",
                      "accesskey", "action", "align", "alt", "axis",
                      "border", "cellpadding", "cellspacing", "char",
                      "charoff", "charset", "checked", "cite", "class",
                      "clear", "cols", "colspan", "color", "compact",
                      "coords", "datetime", "dir", "disabled",
                      "enctype", "for", "frame", "headers", "height",
                      "href", "hreflang", "hspace", "id", "ismap",
                      "label", "lang", "longdesc", "maxlength", "media",
                      "method", "multiple", "name", "nohref", "noshade",
                      "nowrap", "prompt", "readonly", "rel", "rev",
                      "rows", "rowspan", "rules", "scope", "selected",
                      "shape", "size", "span", "src", "start",
                      "summary", "tabindex", "target", "title", "type",
                      "usemap", "valign", "value", "vspace", "width"]

-- taken from HXT and extended

closes :: String -> String -> Bool
"EOF" `closes` _ = True
_ `closes` "body" = False
_ `closes` "html" = False
"a" `closes` "a" = True
"li" `closes` "li" = True
"th" `closes` t | t `elem` ["th","td"] = True
"td" `closes` t | t `elem` ["th","td"] = True
"tr" `closes` t | t `elem` ["th","td","tr"] = True
"dt" `closes` t | t `elem` ["dt","dd"] = True
"dd" `closes` t | t `elem` ["dt","dd"] = True
"hr" `closes` "p" = True
"p" `closes` "p" = True
"meta" `closes` "meta" = True
"colgroup" `closes` "colgroup" = True
"form" `closes` "form" = True
"label" `closes` "label" = True
"map" `closes` "map" = True
"object" `closes` "object" = True
_ `closes` t | t `elem` ["option","style","script","textarea","title"] = True
t `closes` "select" | t /= "option" = True
"thead" `closes` t | t `elem` ["colgroup"] = True
"tfoot" `closes` t | t `elem` ["thead","colgroup"] = True
"tbody" `closes` t | t `elem` ["tbody","tfoot","thead","colgroup"] = True
t `closes` t2 |
   t `elem` ["h1","h2","h3","h4","h5","h6","dl","ol","ul","table","div","p"] &&
   t2 `elem` ["h1","h2","h3","h4","h5","h6","p" ] = True -- not "div"
t1 `closes` t2 |
   t1 `elem` blockHtmlTags &&
   t2 `notElem` (blockHtmlTags ++ eitherBlockOrInline) = True
_ `closes` _ = False

--
-- HTML utility functions
--

-- | Returns @True@ if sanitization is specified and the specified tag is 
--  not on the sanitized tag list.
unsanitaryTag :: [Char]
              -> GenParser tok ParserState Bool
unsanitaryTag tag = do
  st <- getState
  return $ stateSanitizeHTML st && tag `notElem` sanitaryTags

-- | returns @True@ if sanitization is specified and the specified attribute
--  is not on the sanitized attribute list.
unsanitaryAttribute :: ([Char], String, t)
                    -> GenParser tok ParserState Bool
unsanitaryAttribute (attr, val, _) = do
  st <- getState
  return $ stateSanitizeHTML st &&
           (attr `notElem` sanitaryAttributes ||
             (attr `elem` ["href","src"] && unsanitaryURI val))

-- | Returns @True@ if the specified URI is potentially a security risk.
unsanitaryURI :: String -> Bool
unsanitaryURI u =
  let safeURISchemes = [ "", "http:", "https:", "ftp:", "mailto:", "file:",
             "telnet:", "gopher:", "aaa:", "aaas:", "acap:", "cap:", "cid:",
             "crid:", "dav:", "dict:", "dns:", "fax:", "go:", "h323:", "im:",
             "imap:", "ldap:", "mid:", "news:", "nfs:", "nntp:", "pop:",
             "pres:", "sip:", "sips:", "snmp:", "tel:", "urn:", "wais:",
             "xmpp:", "z39.50r:", "z39.50s:", "aim:", "callto:", "cvs:",
             "ed2k:", "feed:", "fish:", "gg:", "irc:", "ircs:", "lastfm:",
             "ldaps:", "magnet:", "mms:", "msnim:", "notes:", "rsync:",
             "secondlife:", "skype:", "ssh:", "sftp:", "smb:", "sms:",
             "snews:", "webcal:", "ymsgr:"]
  in  case parseURIReference (escapeURI u) of
           Just p  -> (map toLower $ uriScheme p) `notElem` safeURISchemes
           Nothing -> True

-- | Read blocks until end tag.
blocksTilEnd :: String -> GenParser Char ParserState [Block]
blocksTilEnd tag = do
  blocks <- manyTill (block >>~ spaces) (htmlEndTag tag)
  return $ filter (/= Null) blocks

-- | Read inlines until end tag.
inlinesTilEnd :: String -> GenParser Char ParserState [Inline]
inlinesTilEnd tag = manyTill inline (htmlEndTag tag)

-- | Parse blocks between open and close tag.
blocksIn :: String -> GenParser Char ParserState [Block]
blocksIn tag = try $ htmlOpenTag tag >> spaces >> blocksTilEnd tag

-- | Parse inlines between open and close tag.
inlinesIn :: String -> GenParser Char ParserState [Inline]
inlinesIn tag = try $ htmlOpenTag tag >> spaces >> inlinesTilEnd tag

-- | Extract type from a tag:  e.g. @br@ from @\<br\>@
extractTagType :: String -> String
extractTagType ('<':rest) = 
  let isSpaceOrSlash c = c `elem` "/ \n\t" in
  map toLower $ takeWhile isAlphaNum $ dropWhile isSpaceOrSlash rest
extractTagType _ = ""

-- Parse any HTML tag (opening or self-closing) and return tag type
anyOpener :: GenParser Char ParserState [Char]
anyOpener = try $ do
  char '<'
  spaces
  tag <- many1 alphaNum
  skipMany htmlAttribute
  spaces
  option "" (string "/")
  spaces
  char '>'
  return $ map toLower tag 

-- | Parse any HTML tag (opening or self-closing) and return text of tag
anyHtmlTag :: GenParser Char ParserState [Char]
anyHtmlTag = try $ do
  char '<'
  spaces
  tag <- many1 alphaNum
  attribs <- many htmlAttribute
  spaces
  ender <- option "" (string "/")
  let ender' = if null ender then "" else " /"
  spaces
  char '>'
  let result = "<" ++ tag ++ 
               concatMap (\(_, _, raw) -> (' ':raw)) attribs ++ ender' ++ ">"
  unsanitary <- unsanitaryTag tag
  if unsanitary
     then return $ "<!-- unsafe HTML removed -->"
     else return result

anyHtmlEndTag :: GenParser Char ParserState [Char]
anyHtmlEndTag = try $ do
  char '<'   
  spaces
  char '/'
  spaces
  tag <- many1 alphaNum
  spaces
  char '>'
  let result = "</" ++ tag ++ ">"
  unsanitary <- unsanitaryTag tag
  if unsanitary
     then return $ "<!-- unsafe HTML removed -->"
     else return result 

htmlTag :: Bool
        -> String
        -> GenParser Char ParserState (String, [(String, String)])
htmlTag selfClosing tag = try $ do
  char '<'
  spaces
  stringAnyCase tag
  attribs <- many htmlAttribute
  spaces
  -- note: we want to handle both HTML and XHTML,
  -- so we don't require the /
  when selfClosing $ optional $ char '/' >> spaces
  char '>'
  return (tag, (map (\(name, content, _) -> (name, content)) attribs))

htmlOpenTag :: String
             -> GenParser Char ParserState (String, [(String, String)])
htmlOpenTag = htmlTag False

htmlCloseTag :: String
             -> GenParser Char ParserState (String, [(String, String)])
htmlCloseTag = htmlTag False . ('/':)

htmlSelfClosingTag :: String
                   -> GenParser Char ParserState (String, [(String, String)])
htmlSelfClosingTag = htmlTag True

-- parses a quoted html attribute value
quoted :: Char -> GenParser Char st (String, String)
quoted quoteChar = do
  result <- between (char quoteChar) (char quoteChar) 
                    (many (noneOf [quoteChar]))
  return (result, [quoteChar])

nullAttribute :: ([Char], [Char], [Char])
nullAttribute = ("", "", "") 

htmlAttribute :: GenParser Char ParserState ([Char], [Char], [Char])
htmlAttribute = do
  attr <- htmlRegularAttribute <|> htmlMinimizedAttribute
  unsanitary <- unsanitaryAttribute attr
  if unsanitary
     then return nullAttribute
     else return attr

-- minimized boolean attribute
htmlMinimizedAttribute :: GenParser Char st ([Char], [Char], [Char])
htmlMinimizedAttribute = try $ do
  many1 space
  name <- many1 (choice [letter, oneOf ".-_:"])
  return (name, name, name)

htmlRegularAttribute :: GenParser Char st ([Char], [Char], [Char])
htmlRegularAttribute = try $ do
  many1 space
  name <- many1 (choice [letter, oneOf ".-_:"])
  spaces
  char '='
  spaces
  (content, quoteStr) <- choice [ (quoted '\''), 
                                  (quoted '"'), 
                                  (do
                                     a <- many (noneOf " \t\n\r\"'<>")
                                     return (a,"")) ]
  return (name, content,
          (name ++ "=" ++ quoteStr ++ content ++ quoteStr))

-- | Parse an end tag of type 'tag'
htmlEndTag :: [Char] -> GenParser Char ParserState [Char]
htmlEndTag tag = try $ do
  closedByNext <- lookAhead $ option False $ liftM (`closes` tag) $
                   anyOpener <|> (eof >> return "EOF")
  if closedByNext
     then return ""
     else do char '<'   
             spaces
             char '/'
             spaces
             stringAnyCase tag
             spaces
             char '>'
             return $ "</" ++ tag ++ ">"

-- | Returns @True@ if the tag is (or can be) a block tag.
isBlock :: String -> Bool
isBlock tag = (extractTagType tag) `elem` (blockHtmlTags ++ eitherBlockOrInline)

anyHtmlBlockTag :: GenParser Char ParserState [Char]
anyHtmlBlockTag = try $ do
  tag <- anyHtmlTag <|> anyHtmlEndTag
  if isBlock tag then return tag else fail "not a block tag"

anyHtmlInlineTag :: GenParser Char ParserState [Char]
anyHtmlInlineTag = try $ do
  tag <- anyHtmlTag <|> anyHtmlEndTag
  if not (isBlock tag) then return tag else fail "not an inline tag"

-- | Parses material between script tags.
-- Scripts must be treated differently, because they can contain '<>' etc.
htmlScript :: GenParser Char ParserState [Char]
htmlScript = try $ do
  lookAhead $ htmlOpenTag "script"
  open <- anyHtmlTag
  rest <- liftM concat $ manyTill scriptChunk (htmlEndTag "script")
  st <- getState
  if stateSanitizeHTML st && not ("script" `elem` sanitaryTags)
     then return "<!-- unsafe HTML removed -->"
     else return $ open ++ rest ++ "</script>"

scriptChunk :: GenParser Char ParserState [Char]
scriptChunk = jsComment <|> jsString <|> jsChars
  where jsComment = jsEndlineComment <|> jsMultilineComment
        jsString  = jsSingleQuoteString <|> jsDoubleQuoteString
        jsChars   = many1 (noneOf "<\"'*/") <|> count 1 anyChar
        jsEndlineComment = try $ do
           string "//"
           res <- manyTill anyChar newline
           return ("//" ++ res)
        jsMultilineComment = try $ do
           string "/*"
           res <- manyTill anyChar (try $ string "*/")
           return ("/*" ++ res ++ "*/")
        jsSingleQuoteString = stringwith '\''
        jsDoubleQuoteString = stringwith '"'
        charWithEsc escapable = try $
           (try $ char '\\' >> oneOf ('\\':escapable) >>= \x -> return ['\\',x])
          <|> count 1 anyChar
        stringwith c = try $ do
           char c
           res <- liftM concat $ manyTill (charWithEsc [c]) (char c)
           return (c : (res ++ [c]))

-- | Parses material between style tags.
-- Style tags must be treated differently, because they can contain CSS
htmlStyle :: GenParser Char ParserState [Char]
htmlStyle = try $ do
  lookAhead $ htmlOpenTag "style"
  open <- anyHtmlTag
  rest <- manyTill anyChar (htmlEndTag "style")
  st <- getState
  if stateSanitizeHTML st && not ("style" `elem` sanitaryTags)
     then return "<!-- unsafe HTML removed -->"
     else return $ open ++ rest ++ "</style>"

htmlBlockElement :: GenParser Char ParserState [Char]
htmlBlockElement = choice [ htmlScript, htmlStyle, htmlComment, xmlDec, definition ]

rawHtmlBlock :: GenParser Char ParserState Block
rawHtmlBlock = try $ do
  body <- htmlBlockElement <|> rawVerbatimBlock <|> anyHtmlBlockTag
  state <- getState
  if stateParseRaw state then return (RawHtml body) else return Null

-- This is a block whose contents should be passed through verbatim, not interpreted.
rawVerbatimBlock :: GenParser Char ParserState [Char]
rawVerbatimBlock = try $ do
  start <- anyHtmlBlockTag
  let tagtype = extractTagType start
  if tagtype `elem` ["pre"]
     then do
       contents <- many (notFollowedBy' (htmlEndTag tagtype) >> anyChar)
       end <- htmlEndTag tagtype
       return $ start ++ contents ++ end
     else fail "Not a verbatim block"

-- We don't want to parse </body> or </html> as raw HTML, since these
-- are handled in parseHtml.
rawHtmlBlock' :: GenParser Char ParserState Block
rawHtmlBlock' = do notFollowedBy' (htmlCloseTag "body" <|>
                                   htmlCloseTag "html")
                   rawHtmlBlock

-- | Parses an HTML comment.
htmlComment :: GenParser Char st [Char]
htmlComment = try $ do
  string "<!--"
  comment <- many $ noneOf "-"
               <|> try (char '-' >>~ notFollowedBy (try (char '-' >> char '>')))
  string "-->"
  return $ "<!--" ++ comment ++ "-->"

--
-- parsing documents
--

xmlDec :: GenParser Char st [Char]
xmlDec = try $ do
  string "<?"
  rest <- manyTill anyChar (char '>')
  return $ "<?" ++ rest ++ ">"

definition :: GenParser Char st [Char]
definition = try $ do
  string "<!"
  rest <- manyTill anyChar (char '>')
  return $ "<!" ++ rest ++ ">"

nonTitleNonHead :: GenParser Char ParserState Char
nonTitleNonHead = try $ do
  notFollowedBy $ (htmlOpenTag "title" >> return ' ') <|> 
                  (htmlEndTag "head" >> return ' ')
  (rawHtmlBlock >> return ' ') <|> anyChar

parseTitle :: GenParser Char ParserState [Inline]
parseTitle = try $ do
  (tag, _) <- htmlOpenTag "title"
  contents <- inlinesTilEnd tag
  spaces
  return contents

-- parse header and return meta-information (for now, just title)
parseHead :: GenParser Char ParserState Meta
parseHead = try $ do
  htmlOpenTag "head"
  spaces
  skipMany nonTitleNonHead
  contents <- option [] parseTitle
  skipMany nonTitleNonHead
  htmlEndTag "head"
  return $ Meta contents [] []

-- h1 class="title" representation of title in body
bodyTitle :: GenParser Char ParserState [Inline]
bodyTitle = try $ do
  (_, attribs) <- htmlOpenTag "h1"  
  case (extractAttribute "class" attribs) of
       Just "title" -> return ""
       _            -> fail "not title"
  inlinesTilEnd "h1"

endOfDoc :: GenParser Char ParserState ()
endOfDoc = try $ do
  spaces
  optional (htmlEndTag "body")
  spaces
  optional (htmlEndTag "html" >> many anyChar) -- ignore stuff after </html>
  eof 

parseHtml :: GenParser Char ParserState Pandoc
parseHtml = do
  sepEndBy (choice [xmlDec, definition, htmlComment]) spaces
  spaces
  optional $ htmlOpenTag "html"
  spaces
  meta <- option (Meta [] [] []) parseHead
  spaces
  optional $ htmlOpenTag "body"
  spaces
  optional bodyTitle  -- skip title in body, because it's represented in meta
  blocks <- parseBlocks
  endOfDoc
  return $ Pandoc meta blocks

--
-- parsing blocks
--

parseBlocks :: GenParser Char ParserState [Block]
parseBlocks = spaces >> sepEndBy block spaces >>= (return . filter (/= Null))

block :: GenParser Char ParserState Block
block = choice [ codeBlock
               , header
               , hrule
               , list
               , blockQuote
               , para
               , plain
               , rawHtmlBlock'
               , notFollowedBy' endOfDoc >> char '<' >> return Null
               ] <?> "block"

--
-- header blocks
--

header :: GenParser Char ParserState Block
header = choice (map headerLevel (enumFromTo 1 5)) <?> "header"

headerLevel :: Int -> GenParser Char ParserState Block
headerLevel n = try $ do
    let level = "h" ++ show n
    htmlOpenTag level
    contents <- inlinesTilEnd level
    return $ Header n (normalizeSpaces contents)

--
-- hrule block
--

hrule :: GenParser Char ParserState Block
hrule = try  $ do
  (_, attribs) <- htmlSelfClosingTag "hr"
  state <- getState
  if not (null attribs) && stateParseRaw state
     then unexpected "attributes in hr" -- parse as raw in this case
     else return HorizontalRule

--
-- code blocks
--

-- Note:  HTML tags in code blocks (e.g. for syntax highlighting) are 
-- skipped, because they are not portable to output formats other than HTML.
codeBlock :: GenParser Char ParserState Block
codeBlock = try $ do
    htmlOpenTag "pre" 
    result <- manyTill 
              (many1 (satisfy (/= '<')) <|> 
               ((anyHtmlTag <|> anyHtmlEndTag) >> return ""))
              (htmlEndTag "pre")
    let result' = concat result
    -- drop leading newline if any
    let result'' = if "\n" `isPrefixOf` result'
                      then drop 1 result'
                      else result'
    -- drop trailing newline if any
    let result''' = if "\n" `isSuffixOf` result''
                       then init result''
                       else result''
    return $ CodeBlock ("",[],[]) $ decodeCharacterReferences result'''

--
-- block quotes
--

blockQuote :: GenParser Char ParserState Block
blockQuote = try $ htmlOpenTag "blockquote" >> spaces >> 
                   blocksTilEnd "blockquote" >>= (return . BlockQuote)

--
-- list blocks
--

list :: GenParser Char ParserState Block
list = choice [ bulletList, orderedList, definitionList ] <?> "list"

orderedList :: GenParser Char ParserState Block
orderedList = try $ do
  (_, attribs) <- htmlOpenTag "ol"
  (start, style) <- option (1, DefaultStyle) $
                           do failIfStrict
                              let sta = fromMaybe "1" $ 
                                        lookup "start" attribs
                              let sty = fromMaybe (fromMaybe "" $
                                        lookup "style" attribs) $
                                        lookup "class" attribs
                              let sty' = case sty of
                                          "lower-roman"  -> LowerRoman
                                          "upper-roman"  -> UpperRoman
                                          "lower-alpha"  -> LowerAlpha
                                          "upper-alpha"  -> UpperAlpha
                                          "decimal"      -> Decimal
                                          _              -> DefaultStyle
                              return (read sta, sty')
  spaces
  -- note: if they have an <ol> or <ul> not in scope of a <li>,
  -- treat it as a list item, though it's not valid xhtml...
  items <- sepEndBy1 (blocksIn "li" <|> liftM (:[]) list) spaces
  htmlEndTag "ol"
  return $ OrderedList (start, style, DefaultDelim) items

bulletList :: GenParser Char ParserState Block
bulletList = try $ do
  htmlOpenTag "ul"
  spaces
  -- note: if they have an <ol> or <ul> not in scope of a <li>,
  -- treat it as a list item, though it's not valid xhtml...
  items <- sepEndBy1 (blocksIn "li" <|> liftM (:[]) list) spaces
  htmlEndTag "ul"
  return $ BulletList items

definitionList :: GenParser Char ParserState Block
definitionList = try $ do
  failIfStrict  -- def lists not part of standard markdown
  htmlOpenTag "dl"
  spaces
  items <- sepEndBy1 definitionListItem spaces
  htmlEndTag "dl"
  return $ DefinitionList items

definitionListItem :: GenParser Char ParserState ([Inline], [[Block]])
definitionListItem = try $ do
  terms <- sepEndBy1 (inlinesIn "dt") spaces
  defs <- sepEndBy1 (blocksIn "dd") spaces
  let term = intercalate [LineBreak] terms
  return (term, defs)

--
-- paragraph block
--

para :: GenParser Char ParserState Block
para = try $ htmlOpenTag "p" >> inlinesTilEnd "p" >>= 
             return . Para . normalizeSpaces

-- 
-- plain block
--

plain :: GenParser Char ParserState Block
plain = many1 inline >>= return . Plain . normalizeSpaces

-- 
-- inline
--

inline :: GenParser Char ParserState Inline
inline = choice [ charRef
                , strong
                , emph
                , superscript
                , subscript
                , strikeout
                , spanStrikeout
                , code
                , str
                , linebreak
                , whitespace
                , link
                , image
                , rawHtmlInline
                , char '&' >> return (Str "&") -- common HTML error
                ] <?> "inline"

code :: GenParser Char ParserState Inline
code = try $ do 
  result <- (htmlOpenTag "code" >> manyTill (noneOf "<>") (htmlEndTag "code"))
        <|> (htmlOpenTag "tt"   >> manyTill (noneOf "<>") (htmlEndTag "tt"))
  -- remove internal line breaks, leading and trailing space,
  -- and decode character references
  return $ Code $ decodeCharacterReferences $ removeLeadingTrailingSpace $ 
                  intercalate " " $ lines result

rawHtmlInline :: GenParser Char ParserState Inline
rawHtmlInline = do
  result <- anyHtmlInlineTag <|> htmlComment
  state <- getState
  if stateParseRaw state then return (HtmlInline result) else return (Str "")

betweenTags :: [Char] -> GenParser Char ParserState [Inline]
betweenTags tag = try $ htmlOpenTag tag >> inlinesTilEnd tag >>= 
                        return . normalizeSpaces

emph :: GenParser Char ParserState Inline
emph = (betweenTags "em" <|> betweenTags "i") >>= return . Emph

strong :: GenParser Char ParserState Inline
strong = (betweenTags "b" <|> betweenTags "strong") >>= return . Strong

superscript :: GenParser Char ParserState Inline
superscript = failIfStrict >> betweenTags "sup" >>= return . Superscript

subscript :: GenParser Char ParserState Inline
subscript = failIfStrict >> betweenTags "sub" >>= return . Subscript

strikeout :: GenParser Char ParserState Inline
strikeout = failIfStrict >> (betweenTags "s" <|> betweenTags "strike") >>=
            return . Strikeout

spanStrikeout :: GenParser Char ParserState Inline
spanStrikeout = try $ do
  failIfStrict -- strict markdown has no strikeout, so treat as raw HTML
  (_, attributes) <- htmlOpenTag "span" 
  result <- case (extractAttribute "class" attributes) of
              Just "strikeout" -> inlinesTilEnd "span"
              _                -> fail "not a strikeout"
  return $ Strikeout result

whitespace :: GenParser Char st Inline
whitespace = many1 space >> return Space

-- hard line break
linebreak :: GenParser Char ParserState Inline
linebreak = htmlSelfClosingTag "br" >> optional newline >> return LineBreak

str :: GenParser Char st Inline
str = many1 (noneOf "< \t\n&") >>= return . Str

--
-- links and images
--

-- extract contents of attribute (attribute names are case-insensitive)
extractAttribute :: [Char] -> [([Char], String)] -> Maybe String
extractAttribute _    [] = Nothing
extractAttribute name ((attrName, contents):rest) = 
  let name'     = map toLower name 
      attrName' = map toLower attrName
  in  if attrName' == name'
         then Just (decodeCharacterReferences contents)
         else extractAttribute name rest

link :: GenParser Char ParserState Inline
link = try $ do
  (_, attributes) <- htmlOpenTag "a"  
  url <- case (extractAttribute "href" attributes) of
           Just url -> return url
           Nothing  -> fail "no href"
  let title = fromMaybe "" $ extractAttribute "title" attributes
  lab <- inlinesTilEnd "a"
  return $ Link (normalizeSpaces lab) (escapeURI url, title)

image :: GenParser Char ParserState Inline
image = try $ do
  (_, attributes) <- htmlSelfClosingTag "img"
  url <- case (extractAttribute "src" attributes) of
           Just url -> return url
           Nothing  -> fail "no src"
  let title = fromMaybe "" $ extractAttribute "title" attributes
  let alt = fromMaybe "" (extractAttribute "alt" attributes)
  return $ Image [Str alt] (escapeURI url, title)