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
|
{-# LANGUAGE OverloadedStrings #-}
{-
Copyright (C) 2014 Albert Krewinkel <tarleb@moltkeplatz.de>
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.Org
Copyright : Copyright (C) 2014 Albert Krewinkel
License : GNU GPL, version 2 or above
Maintainer : Albert Krewinkel <tarleb@moltkeplatz.de>
Conversion of Org-Mode to 'Pandoc' document.
-}
module Text.Pandoc.Readers.Org ( readOrg ) where
import qualified Text.Pandoc.Builder as B
import Text.Pandoc.Builder (Inlines, Blocks, trimInlines, (<>), HasMeta(..))
import Text.Pandoc.Definition
import Text.Pandoc.Options
import Text.Pandoc.Parsing hiding (orderedListMarker, updateLastStrPos)
import Text.Pandoc.Shared (compactify')
import Control.Applicative (pure, (<$>), (<$), (<*>), (<*), (*>), (<**>))
import Control.Monad (guard, mzero)
import Data.Char (toLower)
import Data.Default
import Data.List (foldl', isPrefixOf, isSuffixOf)
import Data.Maybe (listToMaybe, fromMaybe)
import Data.Monoid (mconcat, mempty, mappend)
-- | Parse org-mode string and return a Pandoc document.
readOrg :: ReaderOptions -- ^ Reader options
-> String -- ^ String to parse (assuming @'\n'@ line endings)
-> Pandoc
readOrg opts s = (readWith parseOrg) def{ orgOptions = opts } (s ++ "\n\n")
type OrgParser = Parser [Char] OrgParserState
-- | Org-mode parser state
data OrgParserState = OrgParserState
{ orgOptions :: ReaderOptions
, orgInlineCharStack :: [Char]
, orgLastStrPos :: Maybe SourcePos
, orgMeta :: Meta
} deriving (Show)
instance HasReaderOptions OrgParserState where
extractReaderOptions = orgOptions
instance HasMeta OrgParserState where
setMeta field val st =
st{ orgMeta = setMeta field val $ orgMeta st }
deleteMeta field st =
st{ orgMeta = deleteMeta field $ orgMeta st }
instance Default OrgParserState where
def = defaultOrgParserState
defaultOrgParserState :: OrgParserState
defaultOrgParserState = OrgParserState
{ orgOptions = def
, orgInlineCharStack = []
, orgLastStrPos = Nothing
, orgMeta = nullMeta
}
updateLastStrPos :: OrgParser ()
updateLastStrPos = getPosition >>= \p ->
updateState $ \s -> s{ orgLastStrPos = Just p }
parseOrg:: OrgParser Pandoc
parseOrg = do
blocks' <- B.toList <$> parseBlocks
st <- getState
let meta = orgMeta st
return $ Pandoc meta $ filter (/= Null) blocks'
--
-- parsing blocks
--
parseBlocks :: OrgParser Blocks
parseBlocks = mconcat <$> manyTill block eof
block :: OrgParser Blocks
block = choice [ mempty <$ blanklines
, orgBlock
, example
, drawer
, specialLine
, header
, hline
, list
, table
, paraOrPlain
] <?> "block"
--
-- Org Blocks (#+BEGIN_... / #+END_...)
--
orgBlock :: OrgParser Blocks
orgBlock = try $ do
(indent, blockType, args) <- blockHeader
blockStr <- rawBlockContent indent blockType
let classArgs = [ translateLang . fromMaybe [] $ listToMaybe args ]
case blockType of
"comment" -> return mempty
"src" -> return $ B.codeBlockWith ("", classArgs, []) blockStr
_ -> B.divWith ("", [blockType], [])
<$> (parseFromString parseBlocks blockStr)
blockHeader :: OrgParser (Int, String, [String])
blockHeader = (,,) <$> blockIndent
<*> blockType
<*> (skipSpaces *> blockArgs)
where blockIndent = length <$> many spaceChar
blockType = map toLower <$> (stringAnyCase "#+begin_" *> many letter)
blockArgs = manyTill (many nonspaceChar <* skipSpaces) newline
rawBlockContent :: Int -> String -> OrgParser String
rawBlockContent indent blockType =
unlines . map commaEscaped <$> manyTill indentedLine blockEnder
where
indentedLine = try $ choice [ blankline *> pure "\n"
, indentWith indent *> anyLine
]
blockEnder = try $ indentWith indent *> stringAnyCase ("#+end_" <> blockType)
-- indent by specified number of spaces (or equiv. tabs)
indentWith :: Int -> OrgParser String
indentWith num = do
tabStop <- getOption readerTabStop
if (num < tabStop)
then count num (char ' ')
else choice [ try (count num (char ' '))
, try (char '\t' >> count (num - tabStop) (char ' ')) ]
translateLang :: String -> String
translateLang "C" = "c"
translateLang "C++" = "cpp"
translateLang "emacs-lisp" = "commonlisp" -- emacs lisp is not supported
translateLang "js" = "javascript"
translateLang "lisp" = "commonlisp"
translateLang "R" = "r"
translateLang "sh" = "bash"
translateLang "sqlite" = "sql"
translateLang cs = cs
commaEscaped :: String -> String
commaEscaped (',':cs@('*':_)) = cs
commaEscaped (',':cs@('#':'+':_)) = cs
commaEscaped cs = cs
example :: OrgParser Blocks
example = try $
B.codeBlockWith ("", ["example"], []) . unlines <$> many1 exampleLine
exampleLine :: OrgParser String
exampleLine = try $ string ": " *> anyLine
-- Drawers for properties or a logbook
drawer :: OrgParser Blocks
drawer = try $ do
drawerStart
manyTill drawerLine (try drawerEnd)
return mempty
drawerStart :: OrgParser String
drawerStart = try $
skipSpaces *> drawerName <* skipSpaces <* newline
where drawerName = try $ char ':' *> validDrawerName <* char ':'
validDrawerName = stringAnyCase "PROPERTIES"
<|> stringAnyCase "LOGBOOK"
drawerLine :: OrgParser String
drawerLine = try $ anyLine
drawerEnd :: OrgParser String
drawerEnd = try $
skipSpaces *> stringAnyCase ":END:" <* skipSpaces <* newline
-- Comments, Options and Metadata
specialLine :: OrgParser Blocks
specialLine = try $ metaLine <|> commentLine
metaLine :: OrgParser Blocks
metaLine = try $ metaLineStart *> declarationLine
commentLine :: OrgParser Blocks
commentLine = try $ commentLineStart *> anyLine *> pure mempty
-- The order, in which blocks are tried, makes sure that we're not looking at
-- the beginning of a block, so we don't need to check for it
metaLineStart :: OrgParser String
metaLineStart = try $ mappend <$> many spaceChar <*> string "#+"
commentLineStart :: OrgParser String
commentLineStart = try $ mappend <$> many spaceChar <*> string "# "
declarationLine :: OrgParser Blocks
declarationLine = try $ do
meta' <- B.setMeta <$> metaKey <*> metaValue <*> pure nullMeta
updateState $ \st -> st { orgMeta = orgMeta st <> meta' }
return mempty
metaValue :: OrgParser MetaValue
metaValue = MetaInlines . B.toList . trimInlines <$> restOfLine
metaKey :: OrgParser [Char]
metaKey = map toLower <$> many1 (noneOf ": \n\r")
<* char ':'
<* skipSpaces
-- | Headers
header :: OrgParser Blocks
header = try $
B.header <$> headerStart
<*> (trimInlines <$> restOfLine)
headerStart :: OrgParser Int
headerStart = try $
(length <$> many1 (char '*')) <* many1 (char ' ')
-- Horizontal Line (five dashes or more)
hline :: OrgParser Blocks
hline = try $ do
skipSpaces
string "-----"
many (char '-')
skipSpaces
newline
return B.horizontalRule
--
-- Tables
--
data OrgTableRow = OrgContentRow [Blocks]
| OrgAlignRow [Alignment]
| OrgHlineRow
deriving (Eq, Show)
data OrgTable = OrgTable
{ orgTableColumns :: Int
, orgTableAlignments :: [Alignment]
, orgTableHeader :: [Blocks]
, orgTableRows :: [[Blocks]]
} deriving (Eq, Show)
table :: OrgParser Blocks
table = try $ do
lookAhead tableStart
orgToPandocTable . normalizeTable . rowsToTable <$> tableRows
orgToPandocTable :: OrgTable
-> Blocks
orgToPandocTable (OrgTable _ aligns heads lns) =
B.table "" (zip aligns $ repeat 0) heads lns
tableStart :: OrgParser Char
tableStart = try $ skipSpaces *> char '|'
tableRows :: OrgParser [OrgTableRow]
tableRows = try $ many (tableAlignRow <|> tableHline <|> tableContentRow)
tableContentRow :: OrgParser OrgTableRow
tableContentRow = try $
OrgContentRow <$> (tableStart *> manyTill tableContentCell newline)
tableContentCell :: OrgParser Blocks
tableContentCell = try $
B.plain . trimInlines . mconcat <$> many1Till inline endOfCell
endOfCell :: OrgParser Char
endOfCell = try $ char '|' <|> lookAhead newline
tableAlignRow :: OrgParser OrgTableRow
tableAlignRow = try $
OrgAlignRow <$> (tableStart *> manyTill tableAlignCell newline)
tableAlignCell :: OrgParser Alignment
tableAlignCell =
choice [ try $ emptyCell *> return (AlignDefault)
, try $ skipSpaces
*> char '<'
*> tableAlignFromChar
<* many digit
<* char '>'
<* emptyCell
] <?> "alignment info"
where emptyCell = try $ skipSpaces *> endOfCell
tableAlignFromChar :: OrgParser Alignment
tableAlignFromChar = try $ choice [ char 'l' *> return AlignLeft
, char 'c' *> return AlignCenter
, char 'r' *> return AlignRight
]
tableHline :: OrgParser OrgTableRow
tableHline = try $
OrgHlineRow <$ (tableStart *> char '-' *> anyLine)
rowsToTable :: [OrgTableRow]
-> OrgTable
rowsToTable = foldl' (flip rowToContent) zeroTable
where zeroTable = OrgTable 0 mempty mempty mempty
normalizeTable :: OrgTable
-> OrgTable
normalizeTable (OrgTable cols aligns heads lns) =
let aligns' = fillColumns aligns AlignDefault
heads' = if heads == mempty
then mempty
else fillColumns heads (B.plain mempty)
lns' = map (flip fillColumns (B.plain mempty)) lns
fillColumns base padding = take cols $ base ++ repeat padding
in OrgTable cols aligns' heads' lns'
-- One or more horizontal rules after the first content line mark the previous
-- line as a header. All other horizontal lines are discarded.
rowToContent :: OrgTableRow
-> OrgTable
-> OrgTable
rowToContent OrgHlineRow = maybeBodyToHeader
rowToContent (OrgContentRow rs) = setLongestRow rs . appendToBody rs
rowToContent (OrgAlignRow as) = setLongestRow as . setAligns as
setLongestRow :: [a]
-> OrgTable
-> OrgTable
setLongestRow rs t = t{ orgTableColumns = max (length rs) (orgTableColumns t) }
maybeBodyToHeader :: OrgTable
-> OrgTable
maybeBodyToHeader t = case t of
OrgTable{ orgTableHeader = [], orgTableRows = b:[] } ->
t{ orgTableHeader = b , orgTableRows = [] }
_ -> t
appendToBody :: [Blocks]
-> OrgTable
-> OrgTable
appendToBody r t = t{ orgTableRows = orgTableRows t ++ [r] }
setAligns :: [Alignment]
-> OrgTable
-> OrgTable
setAligns aligns t = t{ orgTableAlignments = aligns }
-- Paragraphs or Plain text
paraOrPlain :: OrgParser Blocks
paraOrPlain = try $
trimInlines . mconcat
<$> many1 inline
<**> option B.plain
(try $ newline *> pure B.para)
restOfLine :: OrgParser Inlines
restOfLine = mconcat <$> manyTill inline newline
--
-- list blocks
--
list :: OrgParser Blocks
list = choice [ definitionList, bulletList, orderedList ] <?> "list"
definitionList :: OrgParser Blocks
definitionList = B.definitionList <$> many1 (definitionListItem bulletListStart)
bulletList :: OrgParser Blocks
bulletList = B.bulletList . compactify' <$> many1 (listItem bulletListStart)
orderedList :: OrgParser Blocks
orderedList = B.orderedList . compactify' <$> many1 (listItem orderedListStart)
genericListStart :: OrgParser String
-> OrgParser Int
genericListStart listMarker = try $
(+) <$> (length <$> many spaceChar)
<*> (length <$> listMarker <* many1 spaceChar)
-- parses bullet list start and returns its length (excl. following whitespace)
bulletListStart :: OrgParser Int
bulletListStart = genericListStart bulletListMarker
where bulletListMarker = pure <$> oneOf "*-+"
orderedListStart :: OrgParser Int
orderedListStart = genericListStart orderedListMarker
-- Ordered list markers allowed in org-mode
where orderedListMarker = mappend <$> many1 digit <*> (pure <$> oneOf ".)")
definitionListItem :: OrgParser Int
-> OrgParser (Inlines, [Blocks])
definitionListItem parseMarkerGetLength = try $ do
markerLength <- parseMarkerGetLength
term <- manyTill (noneOf "\n\r") (try $ string "::")
first <- anyLineNewline
cont <- concat <$> many (listContinuation markerLength)
term' <- parseFromString inline term
contents' <- parseFromString parseBlocks $ first ++ cont
return (term', [contents'])
-- parse raw text for one list item, excluding start marker and continuations
listItem :: OrgParser Int
-> OrgParser Blocks
listItem start = try $ do
markerLength <- try start
firstLine <- anyLineNewline
rest <- concat <$> many (listContinuation markerLength)
parseFromString parseBlocks $ firstLine ++ rest
-- continuation of a list item - indented and separated by blankline or endline.
-- Note: nested lists are parsed as continuations.
listContinuation :: Int
-> OrgParser String
listContinuation markerLength = try $
mappend <$> many blankline
<*> (concat <$> many1 listLine)
where listLine = try $ indentWith markerLength *> anyLineNewline
anyLineNewline :: OrgParser String
anyLineNewline = (++ "\n") <$> anyLine
--
-- inline
--
inline :: OrgParser Inlines
inline = choice inlineParsers <?> "inline"
where inlineParsers = [ whitespace
, link
, str
, endline
, emph
, strong
, strikeout
, underline
, code
, verbatim
, subscript
, superscript
, symbol
]
-- treat these as potentially non-text when parsing inline:
specialChars :: [Char]
specialChars = "\"$'()*+-./:<=>[\\]^_{|}~"
whitespace :: OrgParser Inlines
whitespace = B.space <$ skipMany1 spaceChar <?> "whitespace"
str :: OrgParser Inlines
str = B.str <$> many1 (noneOf $ specialChars ++ "\n\r ")
<* updateLastStrPos
-- an endline character that can be treated as a space, not a structural break
endline :: OrgParser Inlines
endline = try $ do
newline
notFollowedBy blankline
notFollowedBy' exampleLine
notFollowedBy' hline
notFollowedBy' tableStart
notFollowedBy' drawerStart
notFollowedBy' headerStart
notFollowedBy' metaLineStart
notFollowedBy' commentLineStart
notFollowedBy' bulletListStart
notFollowedBy' orderedListStart
return B.space
link :: OrgParser Inlines
link = explicitOrImageLink <|> selflinkOrImage <?> "link"
explicitOrImageLink :: OrgParser Inlines
explicitOrImageLink = try $ do
char '['
src <- enclosedRaw (char '[') (char ']')
title <- enclosedRaw (char '[') (char ']')
title' <- parseFromString (mconcat <$> many inline) title
char ']'
return $ if (isImage src) && (isImage title)
then B.link src "" (B.image title "" "")
else B.link src "" title'
selflinkOrImage :: OrgParser Inlines
selflinkOrImage = try $ do
src <- enclosedRaw (string "[[") (string "]]")
return $ if isImage src
then B.image src "" ""
else B.link src "" (B.str src)
emph :: OrgParser Inlines
emph = B.emph <$> inlinesEnclosedBy '/'
strong :: OrgParser Inlines
strong = B.strong <$> inlinesEnclosedBy '*'
strikeout :: OrgParser Inlines
strikeout = B.strikeout <$> inlinesEnclosedBy '+'
-- There is no underline, so we use strong instead.
underline :: OrgParser Inlines
underline = B.strong <$> inlinesEnclosedBy '_'
code :: OrgParser Inlines
code = B.code <$> rawEnclosedBy '='
verbatim :: OrgParser Inlines
verbatim = B.rawInline "" <$> rawEnclosedBy '~'
subscript :: OrgParser Inlines
subscript = B.subscript <$> (try $ char '_' *> maybeGroupedByBraces)
superscript :: OrgParser Inlines
superscript = B.superscript <$> (try $ char '^' *> maybeGroupedByBraces)
maybeGroupedByBraces :: OrgParser Inlines
maybeGroupedByBraces = try $
choice [ try $ enclosedInlines (char '{') (char '}')
, B.str . (:"") <$> anyChar
]
symbol :: OrgParser Inlines
symbol = B.str . (: "") <$> oneOf specialChars
enclosedInlines :: OrgParser a
-> OrgParser b
-> OrgParser Inlines
enclosedInlines start end = try $
trimInlines . mconcat <$> enclosed start end inline
-- FIXME: This is a hack
inlinesEnclosedBy :: Char
-> OrgParser Inlines
inlinesEnclosedBy c = try $ do
updateState $ \st -> st { orgInlineCharStack = c:(orgInlineCharStack st) }
res <- enclosedInlines (atStart (char c) <* endsOnThisOrNextLine c)
(atEnd $ char c)
updateState $ \st -> st { orgInlineCharStack = drop 1 . orgInlineCharStack $ st }
return res
enclosedRaw :: OrgParser a
-> OrgParser b
-> OrgParser String
enclosedRaw start end = try $
start *> (onSingleLine <|> spanningTwoLines)
where onSingleLine = try $ many1Till (noneOf "\n\r") end
spanningTwoLines = try $
anyLine >>= \f -> mappend (f <> " ") <$> onSingleLine
rawEnclosedBy :: Char
-> OrgParser String
rawEnclosedBy c = enclosedRaw (atStart $ char c) (atEnd $ char c)
-- succeeds only if we're not right after a str (ie. in middle of word)
atStart :: OrgParser a -> OrgParser a
atStart p = do
pos <- getPosition
st <- getState
guard $ orgLastStrPos st /= Just pos
p
-- | succeeds only if we're at the end of a word
atEnd :: OrgParser a -> OrgParser a
atEnd p = try $ do
p <* lookingAtEndOfWord
where lookingAtEndOfWord =
eof <|> const (return ()) =<< lookAhead . oneOf =<< postWordChars
postWordChars :: OrgParser [Char]
postWordChars = do
st <- getState
return $ "\t\n\r !\"'),-.:?}" ++ (take 1 . drop 1 . orgInlineCharStack $ st)
-- FIXME: These functions are hacks and should be replaced
endsOnThisOrNextLine :: Char
-> OrgParser ()
endsOnThisOrNextLine c = do
inp <- getInput
let doOtherwise = \rest -> endsOnThisLine rest c (const mzero)
endsOnThisLine inp c doOtherwise
endsOnThisLine :: [Char]
-> Char
-> ([Char] -> OrgParser ())
-> OrgParser ()
endsOnThisLine input c doOnOtherLines = do
postWordChars' <- postWordChars
case break (`elem` c:"\n") input of
(_,'\n':rest) -> doOnOtherLines rest
(_,_:[]) -> return ()
(_,_:rest@(n:_)) -> if n `elem` postWordChars'
then return ()
else endsOnThisLine rest c doOnOtherLines
_ -> mzero
isImage :: String -> Bool
isImage filename =
any (\x -> ('.':x) `isSuffixOf` filename) imageExtensions &&
any (\x -> (x++":") `isPrefixOf` filename) protocols ||
':' `notElem` filename
where
imageExtensions = [ "jpeg" , "jpg" , "png" , "gif" , "svg" ]
protocols = [ "file", "http", "https" ]
|