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
|
{-# LANGUAGE RelaxedPolyRec #-} -- needed for inlinesBetween on GHC < 7
{-
Copyright (C) 2012 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.MediaWiki
Copyright : Copyright (C) 2012 John MacFarlane
License : GNU GPL, version 2 or above
Maintainer : John MacFarlane <jgm@berkeley.edu>
Stability : alpha
Portability : portable
Conversion of mediawiki text to 'Pandoc' document.
-}
{-
TODO:
_ make tag parsers more efficient by parsing one HTML tag, checking it,
then...
_ support HTML lists
_ support list style attributes and start values in ol lists, also
value attribute on li
_ support internal links http://www.mediawiki.org/wiki/Help:Links
_ support external links (partially implemented)
_ support images http://www.mediawiki.org/wiki/Help:Images
_ support tables http://www.mediawiki.org/wiki/Help:Tables
_ raw mediawiki:
_ templates or anything in {{}} (can be postprocessed)
_ category links
_ gallery tag?
-}
module Text.Pandoc.Readers.MediaWiki ( readMediaWiki ) where
import Text.Pandoc.Definition
import qualified Text.Pandoc.Builder as B
import Text.Pandoc.Builder (Inlines, Blocks, trimInlines, (<>))
import Text.Pandoc.Options
import Text.Pandoc.Readers.HTML ( htmlTag, isInlineTag,
isBlockTag, isCommentTag )
import Text.Pandoc.XML ( fromEntities )
import Text.Pandoc.Parsing
import Text.Pandoc.Generic ( bottomUp )
import Text.Pandoc.Shared ( stripTrailingNewlines )
import Data.Monoid (mconcat, mempty)
import Control.Applicative ((<$>), (<*), (*>), (<$))
import Control.Monad
import Data.List (intersperse)
import Text.HTML.TagSoup
import Data.Sequence (viewl, ViewL(..), (<|))
-- | Read mediawiki from an input string and return a Pandoc document.
readMediaWiki :: ReaderOptions -- ^ Reader options
-> String -- ^ String to parse (assuming @'\n'@ line endings)
-> Pandoc
readMediaWiki opts s =
(readWith parseMediaWiki) def{ stateOptions = opts } (s ++ "\n\n")
type MWParser = Parser [Char] ParserState
--
-- auxiliary functions
--
specialChars :: [Char]
specialChars = "'[]<=&*"
spaceChars :: [Char]
spaceChars = " \n\t"
sym :: String -> MWParser ()
sym s = () <$ try (string s)
htmlComment :: MWParser ()
htmlComment = () <$ htmlTag isCommentTag
inlinesInTags :: String -> MWParser Inlines
inlinesInTags tag = trimInlines . mconcat <$> try
(htmlTag (~== TagOpen tag []) *>
manyTill inline (htmlTag (~== TagClose tag)))
blocksInTags :: String -> MWParser Blocks
blocksInTags tag = mconcat <$> try
(htmlTag (~== TagOpen tag []) *>
manyTill block (htmlTag (~== TagClose tag)))
charsInTags :: String -> MWParser [Char]
charsInTags tag = innerText . parseTags <$> try
(htmlTag (~== TagOpen tag []) *>
manyTill anyChar (htmlTag (~== TagClose tag)))
--
-- main parser
--
parseMediaWiki :: MWParser Pandoc
parseMediaWiki = do
bs <- mconcat <$> many block
spaces
eof
return $ B.doc bs
--
-- block parsers
--
block :: MWParser Blocks
block = header
<|> hrule
<|> bulletList
<|> orderedList
<|> definitionList
<|> mempty <$ try (spaces *> htmlComment)
<|> preformatted
<|> blockquote
<|> codeblock
<|> syntaxhighlight
<|> haskell
<|> mempty <$ skipMany1 blankline
<|> pTag
<|> blockHtml
<|> para
para :: MWParser Blocks
para = B.para . trimInlines . mconcat <$> many1 inline
-- We can just skip pTags, as contents will be treated as paragraphs
pTag :: MWParser Blocks
pTag = mempty <$ (htmlTag (\t -> t ~== TagOpen "p" [] || t ~== TagClose "p"))
blockHtml :: MWParser Blocks
blockHtml = (B.rawBlock "html" . snd <$> htmlTag isBlockTag)
hrule :: MWParser Blocks
hrule = B.horizontalRule <$ try (string "----" *> many (char '-') *> newline)
preformatted :: MWParser Blocks
preformatted = do
char ' '
let endline' = B.linebreak <$ (try $ newline <* char ' ')
let whitespace' = B.str <$> many1 ('\160' <$ spaceChar)
let spToNbsp ' ' = '\160'
spToNbsp x = x
let nowiki' = mconcat . intersperse B.linebreak . map B.str .
lines . fromEntities . map spToNbsp <$> try
(htmlTag (~== TagOpen "nowiki" []) *>
manyTill anyChar (htmlTag (~== TagClose "nowiki")))
let inline' = whitespace' <|> endline' <|> nowiki' <|> inline
let strToCode (Str s) = Code ("",[],[]) s
strToCode x = x
B.para . bottomUp strToCode . mconcat <$> many1 inline'
blockquote :: MWParser Blocks
blockquote = B.blockQuote <$> blocksInTags "blockquote"
codeblock :: MWParser Blocks
codeblock = B.codeBlock . trimCode <$> charsInTags "pre"
trimCode :: String -> String
trimCode ('\n':xs) = stripTrailingNewlines xs
trimCode xs = stripTrailingNewlines xs
syntaxhighlight :: MWParser Blocks
syntaxhighlight = try $ do
(TagOpen _ attrs, _) <- lookAhead
$ htmlTag (~== TagOpen "syntaxhighlight" [])
let mblang = lookup "lang" attrs
let mbstart = lookup "start" attrs
let mbline = lookup "line" attrs
let classes = maybe [] (:[]) mblang ++ maybe [] (const ["numberLines"]) mbline
let kvs = maybe [] (\x -> [("startFrom",x)]) mbstart
contents <- charsInTags "syntaxhighlight"
return $ B.codeBlockWith ("",classes,kvs) $ trimCode contents
haskell :: MWParser Blocks
haskell = B.codeBlockWith ("",["haskell"],[]) . trimCode <$>
charsInTags "haskell"
header :: MWParser Blocks
header = try $ do
col <- sourceColumn <$> getPosition
guard $ col == 1 -- header must be at beginning of line
eqs <- many1 (char '=')
let lev = length eqs
guard $ lev <= 6
contents <- trimInlines . mconcat <$> manyTill inline (count lev $ char '=')
return $ B.header lev contents
bulletList :: MWParser Blocks
bulletList = B.bulletList <$> many1 (listItem '*')
orderedList :: MWParser Blocks
orderedList = B.orderedList <$> many1 (listItem '#')
definitionList :: MWParser Blocks
definitionList = B.definitionList <$> many1 defListItem
defListItem :: MWParser (Inlines, [Blocks])
defListItem = try $ do
terms <- mconcat . intersperse B.linebreak <$> many defListTerm
defs <- many1 $ listItem ':'
return (terms, defs)
defListTerm :: MWParser Inlines
defListTerm = char ';' >> skipMany spaceChar >> manyTill anyChar newline >>=
parseFromString (trimInlines . mconcat <$> many inline)
listStart :: Char -> MWParser ()
listStart c = char c *> notFollowedBy listStartChar
listStartChar :: MWParser Char
listStartChar = oneOf "*#;:"
anyListStart :: MWParser Char
anyListStart = char '*'
<|> char '#'
<|> char ':'
<|> char ';'
listItem :: Char -> MWParser Blocks
listItem c = try $ do
extras <- many (try $ char c <* lookAhead listStartChar)
if null extras
then listItem' c
else do
skipMany spaceChar
first <- manyTill anyChar newline
rest <- many (try $ string extras *> manyTill anyChar newline)
contents <- parseFromString (many1 $ listItem' c)
(unlines (first : rest))
case c of
'*' -> return $ B.bulletList contents
'#' -> return $ B.orderedList contents
':' -> return $ B.definitionList [(mempty, contents)]
_ -> mzero
listItem' :: Char -> MWParser Blocks
listItem' c = try $ do
listStart c
skipMany spaceChar
first <- manyTill anyChar newline
rest <- many (try $ char c *> lookAhead listStartChar *>
manyTill anyChar newline)
contents <- parseFromString (mconcat <$> many1 block)
$ unlines $ first : rest
case viewl (B.unMany contents) of
(Para xs) :< ys -> return $ B.Many $ (Plain xs) <| ys
_ -> return contents
--
-- inline parsers
--
inline :: MWParser Inlines
inline = whitespace
<|> url
<|> str
<|> strong
<|> emph
<|> nowiki
<|> linebreak
<|> externalLink
<|> strikeout
<|> subscript
<|> superscript
<|> math
<|> code
<|> hask
<|> B.singleton <$> charRef
<|> inlineHtml
<|> special
str :: MWParser Inlines
str = B.str <$> many1 (noneOf $ specialChars ++ spaceChars)
special :: MWParser Inlines
special = B.str <$> count 1 (notFollowedBy' (htmlTag isBlockTag) *>
oneOf specialChars)
inlineHtml :: MWParser Inlines
inlineHtml = B.rawInline "html" . snd <$> htmlTag isInlineTag
whitespace :: MWParser Inlines
whitespace = B.space <$ (skipMany1 spaceChar <|> endline <|> htmlComment)
endline :: MWParser ()
endline = () <$ try (newline <*
notFollowedBy blankline <*
notFollowedBy' hrule <*
notFollowedBy anyListStart)
linebreak :: MWParser Inlines
linebreak = B.linebreak <$
(htmlTag (~== TagOpen "br" []) *>
optional (htmlTag (~== TagClose "br")) *>
optional blankline)
externalLink :: MWParser Inlines
externalLink = try $ do
char '['
(_, src) <- uri
skipMany1 spaceChar
lab <- manyTill inline (char ']')
let lab' = if null lab
then [B.str "1"] -- TODO generate sequentially from state
else lab
return $ B.link src "" $ trimInlines $ mconcat lab'
url :: MWParser Inlines
url = do
(orig, src) <- uri
return $ B.link src "" (B.str orig)
nowiki :: MWParser Inlines
nowiki = B.text . fromEntities <$> try
(htmlTag (~== TagOpen "nowiki" []) *>
manyTill anyChar (htmlTag (~== TagClose "nowiki")))
strikeout :: MWParser Inlines
strikeout = B.strikeout <$> (inlinesInTags "strike" <|> inlinesInTags "del")
superscript :: MWParser Inlines
superscript = B.superscript <$> inlinesInTags "sup"
subscript :: MWParser Inlines
subscript = B.subscript <$> inlinesInTags "sub"
math :: MWParser Inlines
math = B.math <$> charsInTags "math"
code :: MWParser Inlines
code = B.code <$> (charsInTags "code" <|> charsInTags "tt")
hask :: MWParser Inlines
hask = B.codeWith ("",["haskell"],[]) <$> charsInTags "hask"
-- | Parses a list of inlines between start and end delimiters.
inlinesBetween :: (Show b) => MWParser a -> MWParser b -> MWParser Inlines
inlinesBetween start end =
(trimInlines . mconcat) <$> try (start >> many1Till inner end)
where inner = innerSpace <|> (notFollowedBy' (() <$ whitespace) >> inline)
innerSpace = try $ whitespace >>~ notFollowedBy' end
emph :: MWParser Inlines
emph = B.emph <$> nested (inlinesBetween start end)
where start = sym "''" >> lookAhead nonspaceChar
end = try $ notFollowedBy' (() <$ strong) >> sym "''"
strong :: MWParser Inlines
strong = B.strong <$> nested (inlinesBetween start end)
where start = sym "'''" >> lookAhead nonspaceChar
end = try $ sym "'''"
|