summaryrefslogtreecommitdiff
path: root/libraries/base/GHC/IO/Encoding/UTF32.hs
blob: 9319234ca77620a2ddb6e5b8073c7e6690179eeb (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
{-# LANGUAGE Trustworthy #-}
{-# LANGUAGE NoImplicitPrelude
           , BangPatterns
           , NondecreasingIndentation
           , MagicHash
           , UnboxedTuples
  #-}
{-# OPTIONS_GHC  -funbox-strict-fields #-}

-----------------------------------------------------------------------------
-- |
-- Module      :  GHC.IO.Encoding.UTF32
-- Copyright   :  (c) The University of Glasgow, 2009
-- License     :  see libraries/base/LICENSE
--
-- Maintainer  :  libraries@haskell.org
-- Stability   :  internal
-- Portability :  non-portable
--
-- UTF-32 Codecs for the IO library
--
-- Portions Copyright   : (c) Tom Harper 2008-2009,
--                        (c) Bryan O'Sullivan 2009,
--                        (c) Duncan Coutts 2009
--
-----------------------------------------------------------------------------

module GHC.IO.Encoding.UTF32 (
  utf32, mkUTF32,
  utf32_decode,
  utf32_encode,

  utf32be, mkUTF32be,
  utf32be_decode,
  utf32be_encode,

  utf32le, mkUTF32le,
  utf32le_decode,
  utf32le_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
import GHC.Word
import Data.Bits
import GHC.IORef

-- -----------------------------------------------------------------------------
-- The UTF-32 codec: either UTF-32BE or UTF-32LE with a BOM

utf32  :: TextEncoding
utf32 = mkUTF32 ErrorOnCodingFailure

-- | @since 4.4.0.0
mkUTF32 :: CodingFailureMode -> TextEncoding
mkUTF32 cfm = TextEncoding { textEncodingName = "UTF-32",
                             mkTextDecoder = utf32_DF cfm,
                             mkTextEncoder = utf32_EF cfm }

utf32_DF :: CodingFailureMode -> IO (TextDecoder (Maybe DecodeBuffer#))
utf32_DF cfm = do
  seen_bom <- newIORef Nothing
  return (BufferCodec# {
             encode#   = utf32_decode seen_bom,
             recover#  = recoverDecode# cfm,
             close#    = return (),
             getState# = readIORef seen_bom,
             setState# = writeIORef seen_bom
          })

utf32_EF :: CodingFailureMode -> IO (TextEncoder Bool)
utf32_EF cfm = do
  done_bom <- newIORef False
  return (BufferCodec# {
             encode#   = utf32_encode done_bom,
             recover#  = recoverEncode# cfm,
             close#    = return (),
             getState# = readIORef done_bom,
             setState# = writeIORef done_bom
          })

utf32_encode :: IORef Bool -> EncodeBuffer#
utf32_encode done_bom input
  output@Buffer{ bufRaw=oraw, bufL=_, bufR=ow, bufSize=os }
  st0
 = do
  let !(# st1, b #) = unIO (readIORef done_bom) st0
  if b then utf32_native_encode input output st1
       else if os - ow < 4
               then (# st1,OutputUnderflow,input,output #)
               else do
               let !(# st2, () #) = unIO (writeIORef done_bom True) st1
                   !(# st3, () #) = unIO (writeWord8Buf oraw ow     bom0) st2
                   !(# st4, () #) = unIO (writeWord8Buf oraw (ow+1) bom1) st3
                   !(# st5, () #) = unIO (writeWord8Buf oraw (ow+2) bom2) st4
                   !(# st6, () #) = unIO (writeWord8Buf oraw (ow+3) bom3) st5
               utf32_native_encode input output{ bufR = ow+4 } st6

utf32_decode :: IORef (Maybe DecodeBuffer#) -> DecodeBuffer#
utf32_decode seen_bom
  input@Buffer{  bufRaw=iraw, bufL=ir, bufR=iw,  bufSize=_  }
  output
  st0
 = do
   let !(# st1, mb #) = unIO (readIORef seen_bom) st0
   case mb of
     Just decode -> decode input output st1
     Nothing ->
       if iw - ir < 4 then (# st1,InputUnderflow,input,output #) else do
       let !(# st2, c0 #) = unIO (readWord8Buf iraw  ir   ) st1
           !(# st3, c1 #) = unIO (readWord8Buf iraw (ir+1)) st2
           !(# st4, c2 #) = unIO (readWord8Buf iraw (ir+2)) st3
           !(# st5, c3 #) = unIO (readWord8Buf iraw (ir+3)) st4
       case () of
        _ | c0 == bom0 && c1 == bom1 && c2 == bom2 && c3 == bom3 ->
               let !(# st6, () #) = unIO (writeIORef seen_bom (Just utf32be_decode)) st5
               in utf32be_decode input{ bufL= ir+4 } output st6
        _ | c0 == bom3 && c1 == bom2 && c2 == bom1 && c3 == bom0 ->
               let !(# st6, () #) = unIO (writeIORef seen_bom (Just utf32le_decode)) st5
               in utf32le_decode input{ bufL= ir+4 } output st6
          | otherwise ->
               let !(# st6, () #) = unIO (writeIORef seen_bom (Just utf32_native_decode)) st5
               in utf32_native_decode input output st6


bom0, bom1, bom2, bom3 :: Word8
bom0 = 0
bom1 = 0
bom2 = 0xfe
bom3 = 0xff

-- choose UTF-32BE by default for UTF-32 output
utf32_native_decode :: DecodeBuffer#
utf32_native_decode = utf32be_decode

utf32_native_encode :: EncodeBuffer#
utf32_native_encode = utf32be_encode

-- -----------------------------------------------------------------------------
-- UTF32LE and UTF32BE

utf32be :: TextEncoding
utf32be = mkUTF32be ErrorOnCodingFailure

-- | @since 4.4.0.0
mkUTF32be :: CodingFailureMode -> TextEncoding
mkUTF32be cfm = TextEncoding { textEncodingName = "UTF-32BE",
                               mkTextDecoder = utf32be_DF cfm,
                               mkTextEncoder = utf32be_EF cfm }

utf32be_DF :: CodingFailureMode -> IO (TextDecoder ())
utf32be_DF cfm =
  return (BufferCodec# {
             encode#   = utf32be_decode,
             recover#  = recoverDecode# cfm,
             close#    = return (),
             getState# = return (),
             setState# = const $ return ()
          })

utf32be_EF :: CodingFailureMode -> IO (TextEncoder ())
utf32be_EF cfm =
  return (BufferCodec# {
             encode#   = utf32be_encode,
             recover#  = recoverEncode# cfm,
             close#    = return (),
             getState# = return (),
             setState# = const $ return ()
          })


utf32le :: TextEncoding
utf32le = mkUTF32le ErrorOnCodingFailure

-- | @since 4.4.0.0
mkUTF32le :: CodingFailureMode -> TextEncoding
mkUTF32le cfm = TextEncoding { textEncodingName = "UTF-32LE",
                               mkTextDecoder = utf32le_DF cfm,
                               mkTextEncoder = utf32le_EF cfm }

utf32le_DF :: CodingFailureMode -> IO (TextDecoder ())
utf32le_DF cfm =
  return (BufferCodec# {
             encode#   = utf32le_decode,
             recover#  = recoverDecode# cfm,
             close#    = return (),
             getState# = return (),
             setState# = const $ return ()
          })

utf32le_EF :: CodingFailureMode -> IO (TextEncoder ())
utf32le_EF cfm =
  return (BufferCodec# {
             encode#   = utf32le_encode,
             recover#  = recoverEncode# cfm,
             close#    = return (),
             getState# = return (),
             setState# = const $ return ()
          })


utf32be_decode :: DecodeBuffer#
utf32be_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
         | iw - ir < 4 = done InputUnderflow  ir ow st0
         | otherwise = do
              let !(# st1, c0 #) = unIO (readWord8Buf iraw ir    ) st0
                  !(# st2, c1 #) = unIO (readWord8Buf iraw (ir+1)) st1
                  !(# st3, c2 #) = unIO (readWord8Buf iraw (ir+2)) st2
                  !(# st4, c3 #) = unIO (readWord8Buf iraw (ir+3)) st3
              let x1 = chr4 c0 c1 c2 c3
              if not (validate x1) then invalid st4 else do
              let !(# st5, ow' #) = unIO (writeCharBuf oraw ow x1) st4
              loop (ir+4) ow' st5
         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

utf32le_decode :: DecodeBuffer#
utf32le_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
         | iw - ir < 4 = done InputUnderflow  ir ow st0
         | otherwise = do
              let !(# st1, c0 #) = unIO (readWord8Buf iraw ir    ) st0
                  !(# st2, c1 #) = unIO (readWord8Buf iraw (ir+1)) st1
                  !(# st3, c2 #) = unIO (readWord8Buf iraw (ir+2)) st2
                  !(# st4, c3 #) = unIO (readWord8Buf iraw (ir+3)) st3
              let x1 = chr4 c3 c2 c1 c0
              if not (validate x1) then invalid st4 else do
              let !(# st5, ow' #) = unIO (writeCharBuf oraw ow x1) st4
              loop (ir+4) ow' st5
         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

utf32be_encode :: EncodeBuffer#
utf32be_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
        | ir >= iw    = done InputUnderflow  ir ow st0
        | os - ow < 4 = done OutputUnderflow ir ow st0
        | otherwise = do
           let !(# st1, (c,ir') #) = unIO (readCharBuf iraw ir) st0
           if isSurrogate c then done InvalidSequence ir ow st1 else do
             let (c0,c1,c2,c3) = ord4 c
                 !(# st2, () #) = unIO (writeWord8Buf oraw ow     c0) st1
                 !(# st3, () #) = unIO (writeWord8Buf oraw (ow+1) c1) st2
                 !(# st4, () #) = unIO (writeWord8Buf oraw (ow+2) c2) st3
                 !(# st5, () #) = unIO (writeWord8Buf oraw (ow+3) c3) st4
             loop ir' (ow+4) st5
    in
    loop ir0 ow0 st

utf32le_encode :: EncodeBuffer#
utf32le_encode
  input@Buffer{  bufRaw=iraw, bufL=ir0, bufR=iw,  bufSize=_  }
  output@Buffer{ bufRaw=oraw, bufL=_,   bufR=ow0, bufSize=os }
  st
 = let
      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
        | ir >= iw    = done InputUnderflow  ir ow st0
        | os - ow < 4 = done OutputUnderflow ir ow st0
        | otherwise = do
           let !(# st1, (c,ir') #) = unIO (readCharBuf iraw ir) st0
           if isSurrogate c then done InvalidSequence ir ow st1 else do
             let (c0,c1,c2,c3) = ord4 c
                 !(# st2, () #) = unIO (writeWord8Buf oraw ow     c3) st1
                 !(# st3, () #) = unIO (writeWord8Buf oraw (ow+1) c2) st2
                 !(# st4, () #) = unIO (writeWord8Buf oraw (ow+2) c1) st3
                 !(# st5, () #) = unIO (writeWord8Buf oraw (ow+3) c0) st4
             loop ir' (ow+4) st5
    in
    loop ir0 ow0 st

chr4 :: Word8 -> Word8 -> Word8 -> Word8 -> Char
chr4 (W8# x1#) (W8# x2#) (W8# x3#) (W8# x4#) =
    C# (chr# (z1# +# z2# +# z3# +# z4#))
    where
      !y1# = word2Int# (word8ToWord# x1#)
      !y2# = word2Int# (word8ToWord# x2#)
      !y3# = word2Int# (word8ToWord# x3#)
      !y4# = word2Int# (word8ToWord# x4#)
      !z1# = uncheckedIShiftL# y1# 24#
      !z2# = uncheckedIShiftL# y2# 16#
      !z3# = uncheckedIShiftL# y3# 8#
      !z4# = y4#
{-# INLINE chr4 #-}

ord4 :: Char -> (Word8,Word8,Word8,Word8)
ord4 c = (fromIntegral (x `shiftR` 24),
          fromIntegral (x `shiftR` 16),
          fromIntegral (x `shiftR` 8),
          fromIntegral x)
  where
    x = ord c
{-# INLINE ord4 #-}


validate    :: Char -> Bool
validate c = (x1 >= 0x0 && x1 < 0xD800) || (x1 > 0xDFFF && x1 <= 0x10FFFF)
   where x1 = ord c
{-# INLINE validate #-}