aboutsummaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/UTF8.hs
blob: e27a24e63bf4ad8038e27f85922dff53023d7576 (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
{-
Copyright (C) 2010-2017 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.UTF8
   Copyright   : Copyright (C) 2010-2017 John MacFarlane
   License     : GNU GPL, version 2 or above

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

UTF-8 aware string IO functions that will work with GHC 6.10, 6.12, or 7.
-}
module Text.Pandoc.UTF8 ( readFile
                        , writeFile
                        , getContents
                        , putStr
                        , putStrLn
                        , hPutStr
                        , hPutStrLn
                        , hGetContents
                        , toString
                        , fromString
                        , toStringLazy
                        , fromStringLazy
                        , encodePath
                        , decodeArg
                        )

where

import qualified Data.ByteString.Char8 as B
import qualified Data.ByteString.Lazy as BL
import qualified Data.Text as T
import qualified Data.Text.Encoding as T
import qualified Data.Text.Lazy as TL
import qualified Data.Text.Lazy.Encoding as TL
import Prelude hiding (getContents, putStr, putStrLn, readFile, writeFile)
import System.IO hiding (getContents, hGetContents, hPutStr, hPutStrLn, putStr,
                  putStrLn, readFile, writeFile)
import qualified System.IO as IO

readFile :: FilePath -> IO String
readFile f = do
  h <- openFile (encodePath f) ReadMode
  hGetContents h

writeFile :: FilePath -> String -> IO ()
writeFile f s = withFile (encodePath f) WriteMode $ \h -> hPutStr h s

getContents :: IO String
getContents = hGetContents stdin

putStr :: String -> IO ()
putStr s = hPutStr stdout s

putStrLn :: String -> IO ()
putStrLn s = hPutStrLn stdout s

hPutStr :: Handle -> String -> IO ()
hPutStr h s = hSetEncoding h utf8 >> IO.hPutStr h s

hPutStrLn :: Handle -> String -> IO ()
hPutStrLn h s = hSetEncoding h utf8 >> IO.hPutStrLn h s

hGetContents :: Handle -> IO String
hGetContents = fmap toString . B.hGetContents
-- hGetContents h = hSetEncoding h utf8_bom
--                   >> hSetNewlineMode h universalNewlineMode
--                   >> IO.hGetContents h

-- | Drop BOM (byte order marker) if present at beginning of string.
-- Note that Data.Text converts the BOM to code point FEFF, zero-width
-- no-break space, so if the string begins with this  we strip it off.
dropBOM :: String -> String
dropBOM ('\xFEFF':xs) = xs
dropBOM xs            = xs

filterCRs :: String -> String
filterCRs ('\r':'\n':xs) = '\n': filterCRs xs
filterCRs ('\r':xs)      = '\n' : filterCRs xs
filterCRs (x:xs)         = x : filterCRs xs
filterCRs []             = []

-- | Convert UTF8-encoded ByteString to String, also
-- removing '\r' characters.
toString :: B.ByteString -> String
toString = filterCRs . dropBOM . T.unpack . T.decodeUtf8

fromString :: String -> B.ByteString
fromString = T.encodeUtf8 . T.pack

-- | Convert UTF8-encoded ByteString to String, also
-- removing '\r' characters.
toStringLazy :: BL.ByteString -> String
toStringLazy = filterCRs . dropBOM . TL.unpack . TL.decodeUtf8

fromStringLazy :: String -> BL.ByteString
fromStringLazy = TL.encodeUtf8 . TL.pack

encodePath :: FilePath -> FilePath
encodePath = id

decodeArg :: String -> String
decodeArg = id