aboutsummaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/Shared.hs
blob: b79af235d5fb6e1fafb0c0f7772fdb3ddd871295 (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
{-
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.Shared
   Copyright   : Copyright (C) 2006-7 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,
                     substitute,
                     -- * Text processing
                     joinWithSep,
                     tabsToSpaces,
                     backslashEscapes,
                     escapeStringUsing,
                     endsWith,
                     stripTrailingNewlines,
                     removeLeadingTrailingSpace,
                     removeLeadingSpace,
                     removeTrailingSpace,
                     stripFirstAndLast,
                     -- * Parsing
                     readWith,
                     testStringWith,
                     Reference (..),
                     isNoteBlock,
                     isKeyBlock,
                     isLineClump,
                     HeaderType (..),
                     ParserContext (..),
                     QuoteContext (..),
                     ParserState (..),
                     NoteTable,
                     defaultParserState,
                     nullBlock,
                     failIfStrict,
                     escaped,
                     -- * Native format prettyprinting
                     prettyPandoc,
                     -- * Pandoc block and inline list processing
                     normalizeSpaces,
                     compactify,
                     Element (..),
                     hierarchicalize,
                     isHeaderBlock,
                     -- * Writer options
                     WriterOptions (..),
                     defaultWriterOptions,
                     -- * Reference key lookup functions
                     KeyTable,
                     lookupKeySrc,
                     refsMatch,
                    ) where
import Text.Pandoc.Definition
import Text.ParserCombinators.Parsec
import Text.Pandoc.Entities ( decodeEntities, escapeStringForXML )
import Data.Char ( toLower, ord )
import Data.List ( find, groupBy, isPrefixOf )

-- | Parse a string with a given parser and state.
readWith :: GenParser Char ParserState a      -- ^ parser
            -> ParserState                    -- ^ initial state
            -> String                         -- ^ input string
            -> a
readWith parser state input = 
    case runParser parser state "source" input of
      Left err     -> error $ "\nError:\n" ++ show err
      Right result -> result

-- | Parse a string with @parser@ (for testing).
testStringWith :: (Show a) =>
                  GenParser Char ParserState a
                  -> String
                  -> IO ()
testStringWith parser str = putStrLn $ show $ 
                            readWith parser defaultParserState str

data HeaderType 
    = SingleHeader Char  -- ^ Single line of characters underneath
    | DoubleHeader Char  -- ^ Lines of characters above and below
    deriving (Eq, Show)

data ParserContext 
    = ListItemState   -- ^ Used when running parser on list item contents
    | NullState       -- ^ Default state
    deriving (Eq, Show)

data QuoteContext
    = InSingleQuote   -- ^ Used when we're parsing inside single quotes
    | InDoubleQuote   -- ^ Used when we're parsing inside double quotes
    | NoQuote         -- ^ Used when we're not parsing inside quotes
    deriving (Eq, Show)

type KeyTable = [([Inline], Target)]

type NoteTable = [(String, [Block])]

-- | References from preliminary parsing
data Reference
  = KeyBlock [Inline] Target  -- ^ Key for reference-style link (label URL title)
  | NoteBlock String [Block]  -- ^ Footnote reference and contents
  | LineClump String          -- ^ Raw clump of lines with blanks at end
  deriving (Eq, Read, Show)

-- | Auxiliary functions used in preliminary parsing
isNoteBlock :: Reference -> Bool
isNoteBlock (NoteBlock _ _) = True
isNoteBlock _ = False

isKeyBlock :: Reference -> Bool
isKeyBlock (KeyBlock _ _) = True
isKeyBlock _ = False

isLineClump :: Reference -> Bool
isLineClump (LineClump _) = True
isLineClump _ = False

data ParserState = ParserState
    { stateParseRaw        :: Bool,          -- ^ Parse untranslatable HTML 
                                             -- and LaTeX?
      stateParserContext   :: ParserContext, -- ^ What are we parsing?  
      stateQuoteContext    :: QuoteContext,  -- ^ Inside quoted environment?
      stateKeys            :: KeyTable,      -- ^ List of reference keys
      stateNotes           :: NoteTable,     -- ^ List of notes
      stateTabStop         :: Int,           -- ^ Tab stop
      stateStandalone      :: Bool,          -- ^ If @True@, parse 
                                             -- bibliographic info
      stateTitle           :: [Inline],      -- ^ Title of document
      stateAuthors         :: [String],      -- ^ Authors of document
      stateDate            :: String,        -- ^ Date of document
      stateStrict          :: Bool,          -- ^ Use strict markdown syntax
      stateSmart           :: Bool,          -- ^ Use smart typography
      stateColumns         :: Int,           -- ^ Number of columns in
                                             -- terminal (used for tables)
      stateHeaderTable     :: [HeaderType]   -- ^ List of header types used,
                                             -- in what order (rst only)
    }
    deriving Show

defaultParserState :: ParserState
defaultParserState = 
    ParserState { stateParseRaw        = False,
                  stateParserContext   = NullState,
                  stateQuoteContext    = NoQuote,
                  stateKeys            = [],
                  stateNotes           = [],
                  stateTabStop         = 4,
                  stateStandalone      = False,
                  stateTitle           = [],
                  stateAuthors         = [],
                  stateDate            = [],
                  stateStrict          = False,
                  stateSmart           = False,
                  stateColumns         = 80,
                  stateHeaderTable     = [] }

-- | Parses a character and returns 'Null' (so that the parser can move on
-- if it gets stuck).
nullBlock :: GenParser Char st Block
nullBlock = do
  anyChar 
  return Null

-- | Fail if reader is in strict markdown syntax mode.
failIfStrict :: GenParser Char ParserState ()
failIfStrict = do
    state <- getState
    if stateStrict state then fail "Strict mode" else return ()

-- | Parses backslash, then applies character parser.
escaped :: GenParser Char st Char  -- ^ Parser for character to escape
        -> GenParser Char st Inline
escaped parser = try (do
                        char '\\'
                        result <- parser
                        return (Str [result]))

-- | Indent string as a block.
indentBy :: Int    -- ^ Number of spaces to indent the block 
         -> Int    -- ^ Number of spaces (rel to block) to indent first line
         -> String -- ^ Contents of block to indent
         -> String
indentBy num first [] = ""
indentBy num first str = 
    let (firstLine:restLines) = lines str 
        firstLineIndent = num + first in
    (replicate firstLineIndent ' ') ++ firstLine ++ "\n" ++ (joinWithSep "\n" $ map (\line -> (replicate num ' ') ++ line) restLines)

-- | Prettyprint list of Pandoc blocks elements.
prettyBlockList :: Int       -- ^ Number of spaces to indent list of blocks
                -> [Block]   -- ^ List of blocks
                -> String
prettyBlockList indent [] = indentBy indent 0 "[]"
prettyBlockList indent blocks = indentBy indent (-2) $ "[ " ++ 
                        (joinWithSep "\n, " (map prettyBlock blocks)) ++ " ]"

-- | Prettyprint Pandoc block element.
prettyBlock :: Block -> String
prettyBlock (BlockQuote blocks) = "BlockQuote\n  " ++ 
                                  (prettyBlockList 2 blocks) 
prettyBlock (OrderedList blockLists) = 
   "OrderedList\n" ++ indentBy 2 0 ("[ " ++ (joinWithSep ", " 
   (map (\blocks -> prettyBlockList 2 blocks) blockLists))) ++ " ]"
prettyBlock (BulletList blockLists) = "BulletList\n" ++ 
   indentBy 2 0 ("[ " ++ (joinWithSep ", " 
   (map (\blocks -> prettyBlockList 2 blocks) blockLists))) ++ " ]" 
prettyBlock (DefinitionList blockLists) = "DefinitionList\n" ++ 
   indentBy 2 0 ("[" ++ (joinWithSep ",\n" 
   (map (\(term, blocks) -> "  (" ++ show term ++ ",\n" ++ 
   indentBy 1 2 (prettyBlockList 2 blocks) ++ "  )") blockLists))) ++ " ]" 
prettyBlock (Table caption aligns widths header rows) = 
   "Table " ++ show caption ++ " " ++ show aligns ++ " " ++ 
   show widths ++ "\n" ++ prettyRow header ++ " [\n" ++  
   (joinWithSep ",\n" (map prettyRow rows)) ++ " ]"
   where prettyRow cols = indentBy 2 0 ("[ " ++ (joinWithSep ", "
                          (map (\blocks -> prettyBlockList 2 blocks) 
                          cols))) ++ " ]"
prettyBlock block = show block

-- | Prettyprint Pandoc document.
prettyPandoc :: Pandoc -> String
prettyPandoc (Pandoc meta blocks) = "Pandoc " ++ "(" ++ (show meta) ++ 
    ")\n" ++ (prettyBlockList 0 blocks) ++ "\n"

-- | Convert tabs to spaces (with adjustable tab stop).
tabsToSpaces :: Int     -- ^ Tabstop
             -> String  -- ^ String to convert
             -> String
tabsToSpaces tabstop str =
    unlines (map (tabsInLine tabstop tabstop) (lines str))

-- | Convert tabs to spaces in one line.
tabsInLine :: Int      -- ^ Number of spaces to next tab stop
           -> Int      -- ^ Tabstop
           -> String   -- ^ Line to convert
           -> String
tabsInLine num tabstop "" = ""
tabsInLine num tabstop (c:cs) = 
    let replacement = (if (c == '\t') then (replicate num ' ') else [c]) in
    let nextnumraw = (num - (length replacement)) in
    let nextnum = if (nextnumraw < 1)
                     then (nextnumraw + tabstop)
                     else nextnumraw in
    replacement ++ (tabsInLine nextnum tabstop cs)

-- | 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 escapeTable "" = ""
escapeStringUsing escapeTable (x:xs) = 
  case (lookup x escapeTable) of
       Just str  -> str ++ rest
       Nothing   -> x:rest
  where rest = escapeStringUsing escapeTable xs

-- | Returns @True@ if string ends with given character.
endsWith :: Char -> [Char] -> Bool
endsWith char [] = False
endsWith char str = (char == last str)

-- | Joins a list of lists, separated by another list.
joinWithSep :: [a]    -- ^ List to use as separator
            -> [[a]]  -- ^ Lists to join
            -> [a]
joinWithSep sep [] = []
joinWithSep sep lst = foldr1 (\a b -> a ++ sep ++ b) lst

-- | Strip trailing newlines from string.
stripTrailingNewlines :: String -> String
stripTrailingNewlines "" = ""
stripTrailingNewlines str = 
    if (last str) == '\n'
       then stripTrailingNewlines (init str)
       else str

-- | 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 (\x -> (x == ' ') || (x == '\n') || 
                                (x == '\t')) 

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

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

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

-- | Split list into groups separated by sep.
splitBy :: (Eq a) => a -> [a] -> [[a]]
splitBy _ [] = []
splitBy sep lst = 
  let (first, rest) = break (== sep) lst
      rest'         = dropWhile (== sep) rest in
  first:(splitBy sep rest')

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

-- | 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 [] = []
normalizeSpaces list = 
    let removeDoubles [] = []
        removeDoubles (Space:Space:rest) = removeDoubles (Space:rest)
        removeDoubles ((Str ""):rest) = removeDoubles rest 
        removeDoubles (x:rest) = x:(removeDoubles rest) in
    let removeLeading [] = []
        removeLeading lst = if ((head lst) == Space)
                               then tail lst
                               else lst in
    let removeTrailing [] = []
        removeTrailing lst = if ((last lst) == Space)
                               then init lst
                               else lst in
    removeLeading $ removeTrailing $ removeDoubles list

-- | Change final list item from @Para@ to @Plain@ if the list should 
-- be compact.
compactify :: [[Block]]  -- ^ List of list items (each a list of blocks)
           -> [[Block]]
compactify [] = []
compactify items =
    let final = last items
        others = init items in
    case final of
      [Para a]  -> if any containsPara others
                      then items
                      else others ++ [[Plain a]]
      otherwise -> items

containsPara :: [Block] -> Bool
containsPara [] = False
containsPara ((Para a):rest) = True
containsPara ((BulletList items):rest) =  (any containsPara items) ||
                                          (containsPara rest)
containsPara ((OrderedList items):rest) = (any containsPara items) ||
                                          (containsPara rest)
containsPara (x:rest) = containsPara rest

-- | Data structure for defining hierarchical Pandoc documents
data Element = Blk Block 
             | Sec [Inline] [Element] deriving (Eq, Read, Show)

-- | Returns true on Header block with level at least 'level'
headerAtLeast :: Int -> Block -> Bool
headerAtLeast level (Header x _) = x <= level
headerAtLeast level _ = False

-- | Convert list of Pandoc blocks into list of Elements (hierarchical) 
hierarchicalize :: [Block] -> [Element]
hierarchicalize [] = []
hierarchicalize (block:rest) = 
  case block of
    (Header level title) -> let (thisSection, rest') = break (headerAtLeast 
                                                       level) rest in
                            (Sec title (hierarchicalize thisSection)):
                            (hierarchicalize rest') 
    x                    -> (Blk x):(hierarchicalize rest)

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

-- | Options for writers
data WriterOptions = WriterOptions
    { writerStandalone      :: Bool   -- ^ Include header and footer
    , writerTitlePrefix     :: String -- ^ Prefix for HTML titles
    , writerHeader          :: String -- ^ Header for the document
    , writerIncludeBefore   :: String -- ^ String to include before the  body
    , writerIncludeAfter    :: String -- ^ String to include after the body
    , writerTableOfContents :: Bool   -- ^ Include table of contents
    , writerS5              :: Bool   -- ^ We're writing S5 
    , writerUseASCIIMathML  :: Bool   -- ^ Use ASCIIMathML
    , writerASCIIMathMLURL  :: Maybe String -- ^ URL to asciiMathML.js 
    , writerIgnoreNotes     :: Bool   -- ^ Ignore footnotes (used in making toc)
    , writerIncremental     :: Bool   -- ^ Incremental S5 lists
    , writerNumberSections  :: Bool   -- ^ Number sections in LaTeX
    , writerStrictMarkdown  :: Bool   -- ^ Use strict markdown syntax
    , writerReferenceLinks  :: Bool   -- ^ Use reference links in writing markdown, rst
    , writerTabStop         :: Int    -- ^ Tabstop for conversion between 
                                      -- spaces and tabs
    } deriving Show

-- | Default writer options.
defaultWriterOptions = 
    WriterOptions { writerStandalone      = False,
                    writerHeader          = "",
                    writerTitlePrefix     = "",
                    writerTabStop         = 4,
                    writerTableOfContents = False,
                    writerS5              = False,
                    writerUseASCIIMathML  = False,
                    writerASCIIMathMLURL  = Nothing,
                    writerIgnoreNotes     = False,
                    writerIncremental     = False,
                    writerNumberSections  = False,
                    writerIncludeBefore   = "",
                    writerIncludeAfter    = "",
                    writerStrictMarkdown  = False,
                    writerReferenceLinks  = False }

--
-- code to lookup reference keys in key table
--

-- | Look up key in key table and return target object.
lookupKeySrc :: KeyTable  -- ^ Key table
             -> [Inline]  -- ^ Key
             -> Maybe Target
lookupKeySrc table key = case table of
                           []            -> Nothing
                           (k, src):rest -> if (refsMatch k key) 
                                               then Just src
                                               else lookupKeySrc rest key

-- | Returns @True@ if keys match (case insensitive).
refsMatch :: [Inline] -> [Inline] -> Bool
refsMatch ((Str x):restx) ((Str y):resty) = 
    ((map toLower x) == (map toLower y)) && refsMatch restx resty
refsMatch ((Emph x):restx) ((Emph y):resty) = 
    refsMatch x y && refsMatch restx resty
refsMatch ((Strong x):restx) ((Strong y):resty) = 
    refsMatch x y && refsMatch restx resty
refsMatch ((Strikeout x):restx) ((Strikeout y):resty) = 
    refsMatch x y && refsMatch restx resty
refsMatch ((Superscript x):restx) ((Superscript y):resty) = 
    refsMatch x y && refsMatch restx resty
refsMatch ((Subscript x):restx) ((Subscript y):resty) = 
    refsMatch x y && refsMatch restx resty
refsMatch ((Quoted t x):restx) ((Quoted u y):resty) = 
    t == u && refsMatch x y && refsMatch restx resty
refsMatch ((Code x):restx) ((Code y):resty) = 
    ((map toLower x) == (map toLower y)) && refsMatch restx resty
refsMatch ((TeX x):restx) ((TeX y):resty) = 
    ((map toLower x) == (map toLower y)) && refsMatch restx resty
refsMatch ((HtmlInline x):restx) ((HtmlInline y):resty) = 
    ((map toLower x) == (map toLower y)) && refsMatch restx resty
refsMatch (x:restx) (y:resty) = (x == y) && refsMatch restx resty
refsMatch [] x = null x
refsMatch x [] = null x