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
|
{-
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.ParserCombinators
Copyright : Copyright (C) 2006-7 John MacFarlane
License : GNU GPL, version 2 or above
Maintainer : John MacFarlane <jgm@berkeley.edu>
Stability : alpha
Portability : portable
Parser combinators used in Pandoc readers.
-}
module Text.Pandoc.ParserCombinators (
anyLine,
many1Till,
notFollowedBy',
oneOfStrings,
spaceChar,
skipSpaces,
blankline,
blanklines,
enclosed,
stringAnyCase,
parseFromStr,
lineClump
) where
import Text.ParserCombinators.Parsec
import Data.Char ( toUpper, toLower )
--- | Parse any line of text
anyLine :: GenParser Char st [Char]
anyLine = try (manyTill anyChar newline) <|> many1 anyChar
-- second alternative is for a line ending with eof
-- | Parses a space or tab.
spaceChar :: CharParser st Char
spaceChar = oneOf " \t"
-- | Skips zero or more spaces or tabs.
skipSpaces :: GenParser Char st ()
skipSpaces = skipMany spaceChar
-- | Skips zero or more spaces or tabs, then reads a newline.
blankline :: GenParser Char st Char
blankline = try (do
skipSpaces
newline)
-- | Parses one or more blank lines and returns a string of newlines.
blanklines :: GenParser Char st [Char]
blanklines = try (many1 blankline)
-- | Parses material enclosed between start and end parsers.
enclosed :: GenParser Char st t -- ^ start parser
-> GenParser Char st end -- ^ end parser
-> GenParser Char st a -- ^ content parser (to be used repeatedly)
-> GenParser Char st [a]
enclosed start end parser = try (do
start
notFollowedBy space
result <- many1Till parser end
return result)
-- | Like @manyTill@, but reads at least one item.
many1Till :: GenParser tok st a
-> GenParser tok st end
-> GenParser tok st [a]
many1Till p end = try (do
first <- p
rest <- manyTill p end
return (first:rest))
-- | A more general form of @notFollowedBy@. This one allows any
-- type of parser to be specified, and succeeds only if that parser fails.
-- It does not consume any input.
notFollowedBy' :: Show b => GenParser a st b -> GenParser a st ()
notFollowedBy' parser = try (do { c <- try parser; unexpected (show c) }
<|> return ())
-- | Parses one of a list of strings (tried in order).
oneOfStrings :: [String] -> GenParser Char st String
oneOfStrings listOfStrings = choice $ map (try . string) listOfStrings
-- | Parse string, case insensitive.
stringAnyCase :: [Char] -> CharParser st String
stringAnyCase [] = string ""
stringAnyCase (x:xs) = try (do
firstChar <- choice [ char (toUpper x), char (toLower x) ]
rest <- stringAnyCase xs
return (firstChar:rest))
-- | Parse contents of 'str' using 'parser' and return result.
parseFromStr :: GenParser tok st a -> [tok] -> GenParser tok st a
parseFromStr parser str = try $ do
oldInput <- getInput
setInput str
result <- parser
setInput oldInput
return result
-- | Parse raw line block up to and including blank lines.
lineClump :: GenParser Char st String
lineClump = do
lines <- many1 (do{notFollowedBy blankline; anyLine})
blanks <- blanklines <|> (do{eof; return "\n"})
return ((unlines lines) ++ blanks)
|
