aboutsummaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/Shared.hs
blob: ad28b7c23da0ceebae29607075bb4213a028dc31 (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
{-# LANGUAGE DeriveDataTypeable #-}
{-
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.Shared
   Copyright   : Copyright (C) 2006-2010 John MacFarlane
   License     : GNU GPL, version 2 or above

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

Utility functions and definitions used by the various Pandoc modules.
-}
module Text.Pandoc.Shared (
                     -- * List processing
                     splitBy,
                     splitByIndices,
                     splitStringByIndices,
                     substitute,
                     -- * Text processing
                     backslashEscapes,
                     escapeStringUsing,
                     stripTrailingNewlines,
                     removeLeadingTrailingSpace,
                     removeLeadingSpace,
                     removeTrailingSpace,
                     stripFirstAndLast,
                     camelCaseToHyphenated,
                     toRomanNumeral,
                     escapeURI,
                     tabFilter,
                     -- * Date/time
                     normalizeDate,
                     -- * Pandoc block and inline list processing
                     orderedListMarkers,
                     normalizeSpaces,
                     normalize,
                     stringify,
                     compactify,
                     Element (..),
                     hierarchicalize,
                     uniqueIdent,
                     isHeaderBlock,
                     headerShift,
                     -- * File handling
                     inDirectory,
                     findDataFile,
                     readDataFile,
                     -- * Error handling
                     err,
                     warn,
                     -- * Safe read
                     safeRead
                    ) where

import Text.Pandoc.Definition
import Text.Pandoc.Generic
import qualified Text.Pandoc.UTF8 as UTF8
import System.Environment (getProgName)
import System.Exit (exitWith, ExitCode(..))
import Data.Char ( toLower, isLower, isUpper, isAlpha,
                   isLetter, isDigit, isSpace )
import Data.List ( find, isPrefixOf, intercalate )
import Network.URI ( escapeURIString )
import System.Directory
import System.FilePath ( (</>) )
import Data.Generics (Typeable, Data)
import qualified Control.Monad.State as S
import Control.Monad (msum)
import Paths_pandoc (getDataFileName)
import Text.Pandoc.Pretty (charWidth)
import System.Locale (defaultTimeLocale)
import Data.Time
import System.IO (stderr)

--
-- List processing
--

-- | Split list by groups of one or more sep.
splitBy :: (a -> Bool) -> [a] -> [[a]]
splitBy _ [] = []
splitBy isSep lst =
  let (first, rest) = break isSep lst
      rest'         = dropWhile isSep rest
  in  first:(splitBy isSep rest')

splitByIndices :: [Int] -> [a] -> [[a]]
splitByIndices [] lst = [lst]
splitByIndices (x:xs) lst = first:(splitByIndices (map (\y -> y - x)  xs) rest)
  where (first, rest) = splitAt x lst

-- | Split string into chunks divided at specified indices.
splitStringByIndices :: [Int] -> [Char] -> [[Char]]
splitStringByIndices [] lst = [lst]
splitStringByIndices (x:xs) lst =
  let (first, rest) = splitAt' x lst in
  first : (splitStringByIndices (map (\y -> y - x) xs) rest)

splitAt' :: Int -> [Char] -> ([Char],[Char])
splitAt' _ []          = ([],[])
splitAt' n xs | n <= 0 = ([],xs)
splitAt' n (x:xs)      = (x:ys,zs)
  where (ys,zs) = splitAt' (n - charWidth x) xs

-- | Replace each occurrence of one sublist in a list with another.
substitute :: (Eq a) => [a] -> [a] -> [a] -> [a]
substitute _ _ [] = []
substitute [] _ xs = xs
substitute target replacement lst@(x:xs) =
    if target `isPrefixOf` lst
       then replacement ++ substitute target replacement (drop (length target) lst)
       else x : substitute target replacement xs

--
-- Text processing
--

-- | Returns an association list of backslash escapes for the
-- designated characters.
backslashEscapes :: [Char]    -- ^ list of special characters to escape
                 -> [(Char, String)]
backslashEscapes = map (\ch -> (ch, ['\\',ch]))

-- | Escape a string of characters, using an association list of
-- characters and strings.
escapeStringUsing :: [(Char, String)] -> String -> String
escapeStringUsing _ [] = ""
escapeStringUsing escapeTable (x:xs) =
  case (lookup x escapeTable) of
       Just str  -> str ++ rest
       Nothing   -> x:rest
  where rest = escapeStringUsing escapeTable xs

-- | Strip trailing newlines from string.
stripTrailingNewlines :: String -> String
stripTrailingNewlines = reverse . dropWhile (== '\n') . reverse

-- | Remove leading and trailing space (including newlines) from string.
removeLeadingTrailingSpace :: String -> String
removeLeadingTrailingSpace = removeLeadingSpace . removeTrailingSpace

-- | Remove leading space (including newlines) from string.
removeLeadingSpace :: String -> String
removeLeadingSpace = dropWhile (`elem` " \n\t")

-- | Remove trailing space (including newlines) from string.
removeTrailingSpace :: String -> String
removeTrailingSpace = reverse . removeLeadingSpace . reverse

-- | Strip leading and trailing characters from string
stripFirstAndLast :: String -> String
stripFirstAndLast str =
  drop 1 $ take ((length str) - 1) str

-- | Change CamelCase word to hyphenated lowercase (e.g., camel-case).
camelCaseToHyphenated :: String -> String
camelCaseToHyphenated [] = ""
camelCaseToHyphenated (a:b:rest) | isLower a && isUpper b =
  a:'-':(toLower b):(camelCaseToHyphenated rest)
camelCaseToHyphenated (a:rest) = (toLower a):(camelCaseToHyphenated rest)

-- | Convert number < 4000 to uppercase roman numeral.
toRomanNumeral :: Int -> String
toRomanNumeral x =
  if x >= 4000 || x < 0
     then "?"
     else case x of
              _ | x >= 1000 -> "M" ++ toRomanNumeral (x - 1000)
              _ | x >= 900  -> "CM" ++ toRomanNumeral (x - 900)
              _ | x >= 500  -> "D" ++ toRomanNumeral (x - 500)
              _ | x >= 400  -> "CD" ++ toRomanNumeral (x - 400)
              _ | x >= 100  -> "C" ++ toRomanNumeral (x - 100)
              _ | x >= 90   -> "XC" ++ toRomanNumeral (x - 90)
              _ | x >= 50   -> "L"  ++ toRomanNumeral (x - 50)
              _ | x >= 40   -> "XL" ++ toRomanNumeral (x - 40)
              _ | x >= 10   -> "X" ++ toRomanNumeral (x - 10)
              _ | x >= 9    -> "IX" ++ toRomanNumeral (x - 5)
              _ | x >= 5    -> "V" ++ toRomanNumeral (x - 5)
              _ | x >= 4    -> "IV" ++ toRomanNumeral (x - 4)
              _ | x >= 1    -> "I" ++ toRomanNumeral (x - 1)
              _             -> ""

-- | Escape whitespace in URI.
escapeURI :: String -> String
escapeURI = escapeURIString (not . isSpace)

-- | Convert tabs to spaces and filter out DOS line endings.
-- Tabs will be preserved if tab stop is set to 0.
tabFilter :: Int       -- ^ Tab stop
          -> String    -- ^ Input
          -> String
tabFilter tabStop =
  let go _ [] = ""
      go _ ('\n':xs) = '\n' : go tabStop xs
      go _ ('\r':'\n':xs) = '\n' : go tabStop xs
      go _ ('\r':xs) = '\n' : go tabStop xs
      go spsToNextStop ('\t':xs) =
        if tabStop == 0
           then '\t' : go tabStop xs
           else replicate spsToNextStop ' ' ++ go tabStop xs
      go 1 (x:xs) =
        x : go tabStop xs
      go spsToNextStop (x:xs) =
        x : go (spsToNextStop - 1) xs
  in  go tabStop

--
-- Date/time
--

-- | Parse a date and convert (if possible) to "YYYY-MM-DD" format.
normalizeDate :: String -> Maybe String
normalizeDate s = fmap (formatTime defaultTimeLocale "%F")
  (msum $ map (\fs -> parsetimeWith fs s) formats :: Maybe Day)
   where parsetimeWith = parseTime defaultTimeLocale
         formats = ["%x","%m/%d/%Y", "%D","%F", "%d %b %Y",
                    "%d %B %Y", "%b. %d, %Y", "%B %d, %Y"]

--
-- Pandoc block and inline list processing
--

-- | Generate infinite lazy list of markers for an ordered list,
-- depending on list attributes.
orderedListMarkers :: (Int, ListNumberStyle, ListNumberDelim) -> [String]
orderedListMarkers (start, numstyle, numdelim) =
  let singleton c = [c]
      nums = case numstyle of
                     DefaultStyle -> map show [start..]
                     Example      -> map show [start..]
                     Decimal      -> map show [start..]
                     UpperAlpha   -> drop (start - 1) $ cycle $
                                     map singleton ['A'..'Z']
                     LowerAlpha   -> drop (start - 1) $ cycle $
                                     map singleton ['a'..'z']
                     UpperRoman   -> map toRomanNumeral [start..]
                     LowerRoman   -> map (map toLower . toRomanNumeral) [start..]
      inDelim str = case numdelim of
                            DefaultDelim -> str ++ "."
                            Period       -> str ++ "."
                            OneParen     -> str ++ ")"
                            TwoParens    -> "(" ++ str ++ ")"
  in  map inDelim nums

-- | Normalize a list of inline elements: remove leading and trailing
-- @Space@ elements, collapse double @Space@s into singles, and
-- remove empty Str elements.
normalizeSpaces :: [Inline] -> [Inline]
normalizeSpaces = cleanup . dropWhile isSpaceOrEmpty
 where  cleanup []              = []
        cleanup (Space:rest)    = case dropWhile isSpaceOrEmpty rest of
                                        []     -> []
                                        (x:xs) -> Space : x : cleanup xs
        cleanup ((Str ""):rest) = cleanup rest
        cleanup (x:rest)        = x : cleanup rest

isSpaceOrEmpty :: Inline -> Bool
isSpaceOrEmpty Space = True
isSpaceOrEmpty (Str "") = True
isSpaceOrEmpty _ = False

-- | Normalize @Pandoc@ document, consolidating doubled 'Space's,
-- combining adjacent 'Str's and 'Emph's, remove 'Null's and
-- empty elements, etc.
normalize :: (Eq a, Data a) => a -> a
normalize = topDown removeEmptyBlocks .
            topDown consolidateInlines .
            bottomUp (removeEmptyInlines . removeTrailingInlineSpaces)

removeEmptyBlocks :: [Block] -> [Block]
removeEmptyBlocks (Null : xs) = removeEmptyBlocks xs
removeEmptyBlocks (BulletList [] : xs) = removeEmptyBlocks xs
removeEmptyBlocks (OrderedList _ [] : xs) = removeEmptyBlocks xs
removeEmptyBlocks (DefinitionList [] : xs) = removeEmptyBlocks xs
removeEmptyBlocks (RawBlock _ [] : xs) = removeEmptyBlocks xs
removeEmptyBlocks (x:xs) = x : removeEmptyBlocks xs
removeEmptyBlocks [] = []

removeEmptyInlines :: [Inline] -> [Inline]
removeEmptyInlines (Emph [] : zs) = removeEmptyInlines zs
removeEmptyInlines (Strong [] : zs) = removeEmptyInlines zs
removeEmptyInlines (Subscript [] : zs) = removeEmptyInlines zs
removeEmptyInlines (Superscript [] : zs) = removeEmptyInlines zs
removeEmptyInlines (SmallCaps [] : zs) = removeEmptyInlines zs
removeEmptyInlines (Strikeout [] : zs) = removeEmptyInlines zs
removeEmptyInlines (RawInline _ [] : zs) = removeEmptyInlines zs
removeEmptyInlines (Code _ [] : zs) = removeEmptyInlines zs
removeEmptyInlines (Str "" : zs) = removeEmptyInlines zs
removeEmptyInlines (x : xs) = x : removeEmptyInlines xs
removeEmptyInlines [] = []

removeTrailingInlineSpaces :: [Inline] -> [Inline]
removeTrailingInlineSpaces = reverse . removeLeadingInlineSpaces . reverse

removeLeadingInlineSpaces :: [Inline] -> [Inline]
removeLeadingInlineSpaces = dropWhile isSpaceOrEmpty

consolidateInlines :: [Inline] -> [Inline]
consolidateInlines (Str x : ys) =
  case concat (x : map fromStr strs) of
        ""     -> consolidateInlines rest
        n      -> Str n : consolidateInlines rest
   where
     (strs, rest)  = span isStr ys
     isStr (Str _) = True
     isStr _       = False
     fromStr (Str z) = z
     fromStr _       = error "consolidateInlines - fromStr - not a Str"
consolidateInlines (Space : ys) = Space : rest
   where isSp Space = True
         isSp _     = False
         rest       = consolidateInlines $ dropWhile isSp ys
consolidateInlines (Emph xs : Emph ys : zs) = consolidateInlines $
  Emph (xs ++ ys) : zs
consolidateInlines (Strong xs : Strong ys : zs) = consolidateInlines $
  Strong (xs ++ ys) : zs
consolidateInlines (Subscript xs : Subscript ys : zs) = consolidateInlines $
  Subscript (xs ++ ys) : zs
consolidateInlines (Superscript xs : Superscript ys : zs) = consolidateInlines $
  Superscript (xs ++ ys) : zs
consolidateInlines (SmallCaps xs : SmallCaps ys : zs) = consolidateInlines $
  SmallCaps (xs ++ ys) : zs
consolidateInlines (Strikeout xs : Strikeout ys : zs) = consolidateInlines $
  Strikeout (xs ++ ys) : zs
consolidateInlines (RawInline f x : RawInline f' y : zs) | f == f' =
  consolidateInlines $ RawInline f (x ++ y) : zs
consolidateInlines (Code a1 x : Code a2 y : zs) | a1 == a2 =
  consolidateInlines $ Code a1 (x ++ y) : zs
consolidateInlines (x : xs) = x : consolidateInlines xs
consolidateInlines [] = []

-- | Convert list of inlines to a string with formatting removed.
stringify :: [Inline] -> String
stringify = queryWith go
  where go :: Inline -> [Char]
        go Space = " "
        go (Str x) = x
        go (Code _ x) = x
        go (Math _ x) = x
        go LineBreak = " "
        go _ = ""

-- | Change final list item from @Para@ to @Plain@ if the list contains
-- no other @Para@ blocks.
compactify :: [[Block]]  -- ^ List of list items (each a list of blocks)
           -> [[Block]]
compactify [] = []
compactify items =
  case (init items, last items) of
       (_,[])          -> items
       (others, final) ->
            case last final of
                 Para a -> case (filter isPara $ concat items) of
                                -- if this is only Para, change to Plain
                                [_] -> others ++ [init final ++ [Plain a]]
                                _   -> items
                 _      -> items

isPara :: Block -> Bool
isPara (Para _) = True
isPara _        = False

-- | Data structure for defining hierarchical Pandoc documents
data Element = Blk Block
             | Sec Int [Int] String [Inline] [Element]
             --    lvl  num ident  label    contents
             deriving (Eq, Read, Show, Typeable, Data)

-- | Convert Pandoc inline list to plain text identifier.  HTML
-- identifiers must start with a letter, and may contain only
-- letters, digits, and the characters _-.
inlineListToIdentifier :: [Inline] -> String
inlineListToIdentifier =
  dropWhile (not . isAlpha) . intercalate "-" . words .
    map (nbspToSp . toLower) .
    filter (\c -> isLetter c || isDigit c || c `elem` "_-. ") .
    stringify
 where nbspToSp '\160'     =  ' '
       nbspToSp x          =  x

-- | Convert list of Pandoc blocks into (hierarchical) list of Elements
hierarchicalize :: [Block] -> [Element]
hierarchicalize blocks = S.evalState (hierarchicalizeWithIds blocks) ([],[])

hierarchicalizeWithIds :: [Block] -> S.State ([Int],[String]) [Element]
hierarchicalizeWithIds [] = return []
hierarchicalizeWithIds ((Header level title'):xs) = do
  (lastnum, usedIdents) <- S.get
  let ident = uniqueIdent title' usedIdents
  let lastnum' = take level lastnum
  let newnum = if length lastnum' >= level
                  then init lastnum' ++ [last lastnum' + 1]
                  else lastnum ++ replicate (level - length lastnum - 1) 0 ++ [1]
  S.put (newnum, (ident : usedIdents))
  let (sectionContents, rest) = break (headerLtEq level) xs
  sectionContents' <- hierarchicalizeWithIds sectionContents
  rest' <- hierarchicalizeWithIds rest
  return $ Sec level newnum ident title' sectionContents' : rest'
hierarchicalizeWithIds (x:rest) = do
  rest' <- hierarchicalizeWithIds rest
  return $ (Blk x) : rest'

headerLtEq :: Int -> Block -> Bool
headerLtEq level (Header l _) = l <= level
headerLtEq _ _ = False

-- | Generate a unique identifier from a list of inlines.
-- Second argument is a list of already used identifiers.
uniqueIdent :: [Inline] -> [String] -> String
uniqueIdent title' usedIdents =
  let baseIdent = case inlineListToIdentifier title' of
                        ""   -> "section"
                        x    -> x
      numIdent n = baseIdent ++ "-" ++ show n
  in  if baseIdent `elem` usedIdents
        then case find (\x -> numIdent x `notElem` usedIdents) ([1..60000] :: [Int]) of
                  Just x  -> numIdent x
                  Nothing -> baseIdent   -- if we have more than 60,000, allow repeats
        else baseIdent

-- | True if block is a Header block.
isHeaderBlock :: Block -> Bool
isHeaderBlock (Header _ _) = True
isHeaderBlock _ = False

-- | Shift header levels up or down.
headerShift :: Int -> Pandoc -> Pandoc
headerShift n = bottomUp shift
  where shift :: Block -> Block
        shift (Header level inner) = Header (level + n) inner
        shift x                    = x

--
-- File handling
--

-- | Perform an IO action in a directory, returning to starting directory.
inDirectory :: FilePath -> IO a -> IO a
inDirectory path action = do
  oldDir <- getCurrentDirectory
  setCurrentDirectory path
  result <- action
  setCurrentDirectory oldDir
  return result

-- | Get file path for data file, either from specified user data directory,
-- or, if not found there, from Cabal data directory.
findDataFile :: Maybe FilePath -> FilePath -> IO FilePath
findDataFile Nothing f = getDataFileName f
findDataFile (Just u) f = do
  ex <- doesFileExist (u </> f)
  if ex
     then return (u </> f)
     else getDataFileName f

-- | Read file from specified user data directory or, if not found there, from
-- Cabal data directory.
readDataFile :: Maybe FilePath -> FilePath -> IO String
readDataFile userDir fname = findDataFile userDir fname >>= UTF8.readFile

--
-- Error reporting
--

err :: Int -> String -> IO a
err exitCode msg = do
  name <- getProgName
  UTF8.hPutStrLn stderr $ name ++ ": " ++ msg
  exitWith $ ExitFailure exitCode
  return undefined

warn :: String -> IO ()
warn msg = do
  name <- getProgName
  UTF8.hPutStrLn stderr $ name ++ ": " ++ msg

--
-- Safe read
--

safeRead :: (Monad m, Read a) => String -> m a
safeRead s = case reads s of
                  (d,x):_
                    | all isSpace x -> return d
                  _                 -> fail $ "Could not read `" ++ s ++ "'"