aboutsummaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/UTF8.hs
blob: 4621e1765d13502a3fb457d82ded599f857789ee (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
{-# LANGUAGE NoImplicitPrelude #-}
{-# LANGUAGE OverloadedStrings #-}
{- |
   Module      : Text.Pandoc.UTF8
   Copyright   : Copyright (C) 2010-2020 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
                        , getContents
                        , writeFileWith
                        , writeFile
                        , putStrWith
                        , putStr
                        , putStrLnWith
                        , putStrLn
                        , hPutStrWith
                        , hPutStr
                        , hPutStrLnWith
                        , hPutStrLn
                        , hGetContents
                        , toString
                        , toText
                        , fromString
                        , fromText
                        , toStringLazy
                        , fromTextLazy
                        , toTextLazy
                        , fromStringLazy
                        , encodePath
                        , decodeArg
                        )

where

import qualified Data.ByteString.Char8 as B
import qualified Data.ByteString.Lazy.Char8 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

getContents :: IO String
getContents = hGetContents stdin

writeFileWith :: Newline -> FilePath -> String -> IO ()
writeFileWith eol f s =
  withFile (encodePath f) WriteMode $ \h -> hPutStrWith eol h s

writeFile :: FilePath -> String -> IO ()
writeFile = writeFileWith nativeNewline

putStrWith :: Newline -> String -> IO ()
putStrWith eol s = hPutStrWith eol stdout s

putStr :: String -> IO ()
putStr = putStrWith nativeNewline

putStrLnWith :: Newline -> String -> IO ()
putStrLnWith eol s = hPutStrLnWith eol stdout s

putStrLn :: String -> IO ()
putStrLn = putStrLnWith nativeNewline

hPutStrWith :: Newline -> Handle -> String -> IO ()
hPutStrWith eol h s =
  hSetNewlineMode h (NewlineMode eol eol) >>
  hSetEncoding h utf8 >> IO.hPutStr h s

hPutStr :: Handle -> String -> IO ()
hPutStr = hPutStrWith nativeNewline

hPutStrLnWith :: Newline -> Handle -> String -> IO ()
hPutStrLnWith eol h s =
  hSetNewlineMode h (NewlineMode eol eol) >>
  hSetEncoding h utf8 >> IO.hPutStrLn h s

hPutStrLn :: Handle -> String -> IO ()
hPutStrLn = hPutStrLnWith nativeNewline

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

-- | Convert UTF8-encoded ByteString to Text, also
-- removing '\r' characters.
toText :: B.ByteString -> T.Text
toText = T.decodeUtf8 . filterCRs . dropBOM
  where dropBOM bs =
         if "\xEF\xBB\xBF" `B.isPrefixOf` bs
            then B.drop 3 bs
            else bs
        filterCRs = B.filter (/='\r')

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

-- | Convert UTF8-encoded ByteString to Text, also
-- removing '\r' characters.
toTextLazy :: BL.ByteString -> TL.Text
toTextLazy = TL.decodeUtf8 . filterCRs . dropBOM
  where dropBOM bs =
         if "\xEF\xBB\xBF" `BL.isPrefixOf` bs
            then BL.drop 3 bs
            else bs
        filterCRs = BL.filter (/='\r')

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

fromText :: T.Text -> B.ByteString
fromText = T.encodeUtf8

fromTextLazy :: TL.Text -> BL.ByteString
fromTextLazy = TL.encodeUtf8

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

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

encodePath :: FilePath -> FilePath
encodePath = id

decodeArg :: String -> String
decodeArg = id