aboutsummaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/Readers/HTML.hs
blob: caf2b7f5f4e2fe376f115fe45962302ab95c9866 (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
{-
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.HTML
   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 HTML to 'Pandoc' document.
-}
module Text.Pandoc.Readers.HTML ( 
                                 readHtml, 
                                 rawHtmlInline, 
                                 rawHtmlBlock, 
                                 anyHtmlBlockTag, 
                                 anyHtmlInlineTag,  
                                 anyHtmlTag,
                                 anyHtmlEndTag,
                                 htmlEndTag,
                                 extractTagType,
                                 htmlBlockElement 
                                ) where

import Text.ParserCombinators.Parsec
import Text.Pandoc.Definition
import Text.Pandoc.Shared 
import Text.Pandoc.CharacterReferences ( characterReference, 
                                         decodeCharacterReferences )
import Data.Maybe ( fromMaybe )
import Data.List ( takeWhile, dropWhile )
import Data.Char ( toUpper, toLower, isAlphaNum )

-- | Convert HTML-formatted string to 'Pandoc' document.
readHtml :: ParserState   -- ^ Parser state
         -> String        -- ^ String to parse
         -> Pandoc
readHtml = readWith parseHtml

--
-- Constants
--

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

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"] ++ eitherBlockOrInline

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

--
-- HTML utility functions
--

-- | Read blocks until end tag.
blocksTilEnd tag = do
  blocks <- manyTill (block >>~ spaces) (htmlEndTag tag)
  return $ filter (/= Null) blocks

-- | Read inlines until end tag.
inlinesTilEnd tag = manyTill inline (htmlEndTag tag)

-- | Parse blocks between open and close tag.
blocksIn tag = try $ htmlTag tag >> spaces >> blocksTilEnd tag

-- | Parse inlines between open and close tag.
inlinesIn tag = try $ htmlTag 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 (closing or opening) and return text of tag
anyHtmlTag = try $ do
  char '<'
  spaces
  tag <- many1 alphaNum
  attribs <- htmlAttributes
  spaces
  ender <- option "" (string "/")
  let ender' = if null ender then "" else " /"
  spaces
  char '>'
  return $ "<" ++ tag ++ attribs ++ ender' ++ ">"

anyHtmlEndTag = try $ do
  char '<'   
  spaces
  char '/'
  spaces
  tagType <- many1 alphaNum
  spaces
  char '>'
  return $ "</" ++ tagType ++ ">"

htmlTag :: String -> GenParser Char st (String, [(String, String)])
htmlTag tag = try $ do
  char '<'
  spaces
  stringAnyCase tag
  attribs <- many htmlAttribute
  spaces
  optional (string "/")
  spaces
  char '>'
  return (tag, (map (\(name, content, raw) -> (name, content)) attribs))

-- parses a quoted html attribute value
quoted quoteChar = do
  result <- between (char quoteChar) (char quoteChar) 
                    (many (noneOf [quoteChar]))
  return (result, [quoteChar])

htmlAttributes = do
  attrList <- many htmlAttribute
  return $ concatMap (\(name, content, raw) -> raw) attrList

htmlAttribute = htmlRegularAttribute <|> htmlMinimizedAttribute

-- minimized boolean attribute
htmlMinimizedAttribute = try $ do
  many1 space
  name <- many1 (choice [letter, oneOf ".-_:"])
  spaces
  notFollowedBy (char '=')
  let content = name
  return (name, content, (" " ++ name))

htmlRegularAttribute = try $ do
  many1 space
  name <- many1 (choice [letter, oneOf ".-_:"])
  spaces
  char '='
  spaces
  (content, quoteStr) <- choice [ (quoted '\''), 
                                  (quoted '"'), 
                                  (do
                                     a <- many (alphaNum <|> (oneOf "-._:"))
                                     return (a,"")) ]
  return (name, content,
          (" " ++ name ++ "=" ++ quoteStr ++ content ++ quoteStr))

-- | Parse an end tag of type 'tag'
htmlEndTag tag = try $ do
  char '<'   
  spaces
  char '/'
  spaces
  stringAnyCase tag
  spaces
  char '>'
  return $ "</" ++ tag ++ ">"

-- | Returns @True@ if the tag is (or can be) an inline tag.
isInline tag = (extractTagType tag) `elem` inlineHtmlTags

-- | Returns @True@ if the tag is (or can be) a block tag.
isBlock tag = (extractTagType tag) `elem` blockHtmlTags 

anyHtmlBlockTag = try $ do
  tag <- anyHtmlTag <|> anyHtmlEndTag
  if isBlock tag then return tag else fail "inline tag"

anyHtmlInlineTag = try $ do
  tag <- anyHtmlTag <|> anyHtmlEndTag
  if isInline 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 = try $ do
  open <- string "<script"
  rest <- manyTill anyChar (htmlEndTag "script")
  return $ open ++ rest ++ "</script>"

htmlBlockElement = choice [ htmlScript, htmlComment, xmlDec, definition ]

rawHtmlBlock = try $ do
  notFollowedBy' (htmlTag "/body" <|> htmlTag "/html")
  body <- htmlBlockElement <|> anyHtmlTag <|> anyHtmlEndTag
  sp <- many space
  state <- getState
  if stateParseRaw state then return (RawHtml (body ++ sp)) else return Null

-- | Parses an HTML comment.
htmlComment = try $ do
  string "<!--"
  comment <- manyTill anyChar (try (string "-->"))
  return $ "<!--" ++ comment ++ "-->"

--
-- parsing documents
--

xmlDec = try $ do
  string "<?"
  rest <- manyTill anyChar (char '>')
  return $ "<?" ++ rest ++ ">"

definition = try $ do
  string "<!"
  rest <- manyTill anyChar (char '>')
  return $ "<!" ++ rest ++ ">"

nonTitleNonHead = try $ notFollowedBy' (htmlTag "title" <|> htmlTag "/head") >>
  ((rawHtmlBlock >> return ' ') <|> anyChar)

parseTitle = try $ do
  (tag, _) <- htmlTag "title"
  contents <- inlinesTilEnd tag
  spaces
  return contents

-- parse header and return meta-information (for now, just title)
parseHead = try $ do
  htmlTag "head"
  spaces
  skipMany nonTitleNonHead
  contents <- option [] parseTitle
  skipMany nonTitleNonHead
  htmlTag "/head"
  return (contents, [], "")

skipHtmlTag tag = optional (htmlTag tag)

-- h1 class="title" representation of title in body
bodyTitle = try $ do
  (tag, attribs) <- htmlTag "h1"  
  cl <- case (extractAttribute "class" attribs) of
          Just "title" -> return ""
          otherwise    -> fail "not title"
  inlinesTilEnd "h1"

parseHtml = do
  sepEndBy (choice [xmlDec, definition, htmlComment]) spaces
  skipHtmlTag "html"
  spaces
  (title, authors, date) <- option ([], [], "") parseHead 
  spaces
  skipHtmlTag "body"
  spaces
  optional bodyTitle  -- skip title in body, because it's represented in meta
  blocks <- parseBlocks
  spaces
  optional (htmlEndTag "body")
  spaces
  optional (htmlEndTag "html" >> many anyChar) -- ignore anything after </html>
  eof
  return $ Pandoc (Meta title authors date) blocks

--
-- parsing blocks
--

parseBlocks = spaces >> sepEndBy block spaces >>= (return . filter (/= Null))

block = choice [ codeBlock
               , header
               , hrule
               , list
               , blockQuote
               , para
               , plain
               , rawHtmlBlock ] <?> "block"

--
-- header blocks
--

header = choice (map headerLevel (enumFromTo 1 5)) <?> "header"

headerLevel n = try $ do
    let level = "h" ++ show n
    (tag, attribs) <- htmlTag level
    contents <- inlinesTilEnd level
    return $ Header n (normalizeSpaces contents)

--
-- hrule block
--

hrule = try  $ do
  (tag, attribs) <- htmlTag "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
--

codeBlock = preCodeBlock <|> bareCodeBlock <?> "code block"

preCodeBlock = try $ do
    htmlTag "pre" 
    spaces
    result <- bareCodeBlock
    spaces
    htmlEndTag "pre"
    return result

bareCodeBlock = try $ do
    htmlTag "code"
    result <- manyTill anyChar (htmlEndTag "code")
    return $ CodeBlock $ stripTrailingNewlines $ 
             decodeCharacterReferences result

--
-- block quotes
--

blockQuote = try $ htmlTag "blockquote" >> spaces >> 
                   blocksTilEnd "blockquote" >>= (return . BlockQuote)

--
-- list blocks
--

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

orderedList = try $ do
  (_, attribs) <- htmlTag "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
  items <- sepEndBy1 (blocksIn "li") spaces
  htmlEndTag "ol"
  return $ OrderedList (start, style, DefaultDelim) items

bulletList = try $ do
  htmlTag "ul"
  spaces
  items <- sepEndBy1 (blocksIn "li") spaces
  htmlEndTag "ul"
  return $ BulletList items

definitionList = try $ do
  failIfStrict  -- def lists not part of standard markdown
  tag <- htmlTag "dl"
  spaces
  items <- sepEndBy1 definitionListItem spaces
  htmlEndTag "dl"
  return $ DefinitionList items

definitionListItem = try $ do
  terms <- sepEndBy1 (inlinesIn "dt") spaces
  defs <- sepEndBy1 (blocksIn "dd") spaces
  let term = joinWithSep [LineBreak] terms
  return (term, concat defs)

--
-- paragraph block
--

para = try $ htmlTag "p" >> inlinesTilEnd "p" >>= 
             return . Para . normalizeSpaces

-- 
-- plain block
--

plain = many1 inline >>= return . Plain . normalizeSpaces

-- 
-- inline
--

inline = choice [ charRef
                , strong
                , emph
                , superscript
                , subscript
                , strikeout
                , spanStrikeout
                , code
                , str
                , linebreak
                , whitespace
                , link
                , image
                , rawHtmlInline
                ] <?> "inline"

code = try $ do 
  htmlTag "code"
  result <- manyTill anyChar (htmlEndTag "code")
  -- remove internal line breaks, leading and trailing space,
  -- and decode character references
  return $ Code $ decodeCharacterReferences $ removeLeadingTrailingSpace $ 
                  joinWithSep " " $ lines result 

rawHtmlInline = do
  result <- htmlScript <|> htmlComment <|> anyHtmlInlineTag
  state <- getState
  if stateParseRaw state then return (HtmlInline result) else return (Str "")

betweenTags tag = try $ htmlTag tag >> inlinesTilEnd tag >>= 
                        return . normalizeSpaces

emph = (betweenTags "em" <|> betweenTags "it") >>= return . Emph

strong = (betweenTags "b" <|> betweenTags "strong") >>= return . Strong

superscript = failIfStrict >> betweenTags "sup" >>= return . Superscript

subscript = failIfStrict >> betweenTags "sub" >>= return . Subscript

strikeout = failIfStrict >> (betweenTags "s" <|> betweenTags "strike") >>=
            return . Strikeout

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

whitespace = many1 space >> return Space

-- hard line break
linebreak = htmlTag "br" >> optional newline >> return LineBreak

str = many1 (noneOf "<& \t\n") >>= return . Str

--
-- links and images
--

-- extract contents of attribute (attribute names are case-insensitive)
extractAttribute name [] = 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 = try $ do
  (tag, attributes) <- htmlTag "a"  
  url <- case (extractAttribute "href" attributes) of
           Just url -> return url
           Nothing  -> fail "no href"
  let title = fromMaybe "" $ extractAttribute "title" attributes
  label <- inlinesTilEnd "a"
  return $ Link (normalizeSpaces label) (url, title)

image = try $ do
  (tag, attributes) <- htmlTag "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] (url, title)