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
|
{-# LANGUAGE Trustworthy #-}
{-# LANGUAGE NoImplicitPrelude
, BangPatterns
, NondecreasingIndentation
, UnboxedTuples
, MagicHash
#-}
{-# OPTIONS_GHC -funbox-strict-fields #-}
-----------------------------------------------------------------------------
-- |
-- Module : GHC.IO.Encoding.Latin1
-- Copyright : (c) The University of Glasgow, 2009
-- License : see libraries/base/LICENSE
--
-- Maintainer : libraries@haskell.org
-- Stability : internal
-- Portability : non-portable
--
-- Single-byte encodings that map directly to Unicode code points.
--
-- Portions Copyright : (c) Tom Harper 2008-2009,
-- (c) Bryan O'Sullivan 2009,
-- (c) Duncan Coutts 2009
--
-----------------------------------------------------------------------------
module GHC.IO.Encoding.Latin1 (
latin1, mkLatin1,
latin1_checked, mkLatin1_checked,
ascii, mkAscii,
latin1_decode,
ascii_decode,
latin1_encode,
latin1_checked_encode,
ascii_encode,
) where
import GHC.Base
import GHC.Real
import GHC.Num
-- import GHC.IO
import GHC.IO.Buffer
import GHC.IO.Encoding.Failure
import GHC.IO.Encoding.Types
-- -----------------------------------------------------------------------------
-- Latin1
latin1 :: TextEncoding
latin1 = mkLatin1 ErrorOnCodingFailure
-- | @since 4.4.0.0
mkLatin1 :: CodingFailureMode -> TextEncoding
mkLatin1 cfm = TextEncoding { textEncodingName = "ISO-8859-1",
mkTextDecoder = latin1_DF cfm,
mkTextEncoder = latin1_EF cfm }
latin1_DF :: CodingFailureMode -> IO (TextDecoder ())
latin1_DF cfm =
return (BufferCodec# {
encode# = latin1_decode,
recover# = recoverDecode# cfm,
close# = return (),
getState# = return (),
setState# = const $ return ()
})
latin1_EF :: CodingFailureMode -> IO (TextEncoder ())
latin1_EF cfm =
return (BufferCodec# {
encode# = latin1_encode,
recover# = recoverEncode# cfm,
close# = return (),
getState# = return (),
setState# = const $ return ()
})
latin1_checked :: TextEncoding
latin1_checked = mkLatin1_checked ErrorOnCodingFailure
-- | @since 4.4.0.0
mkLatin1_checked :: CodingFailureMode -> TextEncoding
mkLatin1_checked cfm = TextEncoding { textEncodingName = "ISO-8859-1",
mkTextDecoder = latin1_DF cfm,
mkTextEncoder = latin1_checked_EF cfm }
latin1_checked_EF :: CodingFailureMode -> IO (TextEncoder ())
latin1_checked_EF cfm =
return (BufferCodec# {
encode# = latin1_checked_encode,
recover# = recoverEncode# cfm,
close# = return (),
getState# = return (),
setState# = const $ return ()
})
-- -----------------------------------------------------------------------------
-- ASCII
-- | @since 4.9.0.0
ascii :: TextEncoding
ascii = mkAscii ErrorOnCodingFailure
-- | @since 4.9.0.0
mkAscii :: CodingFailureMode -> TextEncoding
mkAscii cfm = TextEncoding { textEncodingName = "ASCII",
mkTextDecoder = ascii_DF cfm,
mkTextEncoder = ascii_EF cfm }
ascii_DF :: CodingFailureMode -> IO (TextDecoder ())
ascii_DF cfm =
return (BufferCodec# {
encode# = ascii_decode,
recover# = recoverDecode# cfm,
close# = return (),
getState# = return (),
setState# = const $ return ()
})
ascii_EF :: CodingFailureMode -> IO (TextEncoder ())
ascii_EF cfm =
return (BufferCodec# {
encode# = ascii_encode,
recover# = recoverEncode# cfm,
close# = return (),
getState# = return (),
setState# = const $ return ()
})
-- -----------------------------------------------------------------------------
-- The actual decoders and encoders
-- TODO: Eliminate code duplication between the checked and unchecked
-- versions of the decoder or encoder (but don't change the Core!)
latin1_decode :: DecodeBuffer#
latin1_decode
input@Buffer{ bufRaw=iraw, bufL=ir0, bufR=iw, bufSize=_ }
output@Buffer{ bufRaw=oraw, bufL=_, bufR=ow0, bufSize=os }
st
= let
loop :: Int -> Int -> DecodingBuffer#
loop !ir !ow st0
| ow >= os = done OutputUnderflow ir ow st0
| ir >= iw = done InputUnderflow ir ow st0
| otherwise = do
let !(# st1, c0 #) = unIO (readWord8Buf iraw ir) st0
!(# st2, ow' #) = unIO (writeCharBuf oraw ow (unsafeChr (fromIntegral c0))) st1
loop (ir+1) ow' st2
-- lambda-lifted, to avoid thunks being built in the inner-loop:
{-# NOINLINE done #-}
done :: CodingProgress -> Int -> Int -> DecodingBuffer#
done why !ir !ow st' =
let !ri = if ir == iw then input{ bufL=0, bufR=0 } else input{ bufL=ir }
!ro = output{ bufR=ow }
in (# st', why, ri, ro #)
in
loop ir0 ow0 st
ascii_decode :: DecodeBuffer#
ascii_decode
input@Buffer{ bufRaw=iraw, bufL=ir0, bufR=iw, bufSize=_ }
output@Buffer{ bufRaw=oraw, bufL=_, bufR=ow0, bufSize=os }
st
= let
loop :: Int -> Int -> DecodingBuffer#
loop !ir !ow st0
| ow >= os = done OutputUnderflow ir ow st0
| ir >= iw = done InputUnderflow ir ow st0
| otherwise = do
let !(# st1, c0 #) = unIO (readWord8Buf iraw ir) st0
if c0 > 0x7f then invalid st1 else do
let !(# st2, ow' #) = unIO (writeCharBuf oraw ow (unsafeChr (fromIntegral c0))) st1
loop (ir+1) ow' st2
where
invalid :: DecodingBuffer#
invalid st' = done InvalidSequence ir ow st'
-- lambda-lifted, to avoid thunks being built in the inner-loop:
{-# NOINLINE done #-}
done :: CodingProgress -> Int -> Int -> DecodingBuffer#
done why !ir !ow st' =
let !ri = if ir == iw then input{ bufL=0, bufR=0 } else input{ bufL=ir }
!ro = output{ bufR=ow }
in (# st', why, ri, ro #)
in
loop ir0 ow0 st
latin1_encode :: EncodeBuffer#
latin1_encode
input@Buffer{ bufRaw=iraw, bufL=ir0, bufR=iw, bufSize=_ }
output@Buffer{ bufRaw=oraw, bufL=_, bufR=ow0, bufSize=os }
st
= let
{-# NOINLINE done #-}
done :: CodingProgress -> Int -> Int -> EncodingBuffer#
done why !ir !ow st' =
let !ri = if ir == iw then input{ bufL=0, bufR=0 } else input{ bufL=ir }
!ro = output{ bufR=ow }
in (# st', why, ri, ro #)
loop :: Int -> Int -> EncodingBuffer#
loop !ir !ow st0
| ow >= os = done OutputUnderflow ir ow st0
| ir >= iw = done InputUnderflow ir ow st0
| otherwise = do
let !(# st1, (c,ir') #) = unIO (readCharBuf iraw ir) st0
!(# st2, () #) = unIO (writeWord8Buf oraw ow (fromIntegral (ord c))) st1
loop ir' (ow+1) st2
in
loop ir0 ow0 st
latin1_checked_encode :: EncodeBuffer#
latin1_checked_encode input output
= single_byte_checked_encode 0xff input output
ascii_encode :: EncodeBuffer#
ascii_encode input output
= single_byte_checked_encode 0x7f input output
single_byte_checked_encode :: Int -> EncodeBuffer#
single_byte_checked_encode max_legal_char
input@Buffer{ bufRaw=iraw, bufL=ir0, bufR=iw, bufSize=_ }
output@Buffer{ bufRaw=oraw, bufL=_, bufR=ow0, bufSize=os }
st
= let
{-# NOINLINE done #-}
done :: CodingProgress -> Int -> Int -> EncodingBuffer#
done why !ir !ow st' =
let !ri = if ir == iw then input{ bufL=0, bufR=0 } else input{ bufL=ir }
!ro = output{ bufR=ow }
in (# st', why, ri, ro #)
loop :: Int -> Int -> EncodingBuffer#
loop !ir !ow st0
| ow >= os = done OutputUnderflow ir ow st0
| ir >= iw = done InputUnderflow ir ow st0
| otherwise = do
let !(# st1, (c,ir') #) = unIO (readCharBuf iraw ir) st0
if ord c > max_legal_char then invalid st1 else do
let !(# st2, () #) = unIO (writeWord8Buf oraw ow (fromIntegral (ord c))) st1
loop ir' (ow+1) st2
where
invalid :: EncodingBuffer#
invalid st' = done InvalidSequence ir ow st'
in
loop ir0 ow0 st
{-# INLINE single_byte_checked_encode #-}
|
