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
|
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package simplifiedchinese
import (
"errors"
"unicode/utf8"
"golang.org/x/text/encoding"
"golang.org/x/text/encoding/internal"
"golang.org/x/text/encoding/internal/identifier"
"golang.org/x/text/transform"
)
// HZGB2312 is the HZ-GB2312 encoding.
var HZGB2312 encoding.Encoding = &hzGB2312
var hzGB2312 = internal.Encoding{
internal.FuncEncoding{hzGB2312NewDecoder, hzGB2312NewEncoder},
"HZ-GB2312",
identifier.HZGB2312,
}
func hzGB2312NewDecoder() transform.Transformer {
return new(hzGB2312Decoder)
}
func hzGB2312NewEncoder() transform.Transformer {
return new(hzGB2312Encoder)
}
var errInvalidHZGB2312 = errors.New("simplifiedchinese: invalid HZ-GB2312 encoding")
const (
asciiState = iota
gbState
)
type hzGB2312Decoder int
func (d *hzGB2312Decoder) Reset() {
*d = asciiState
}
func (d *hzGB2312Decoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
r, size := rune(0), 0
loop:
for ; nSrc < len(src); nSrc += size {
c0 := src[nSrc]
if c0 >= utf8.RuneSelf {
err = errInvalidHZGB2312
break loop
}
if c0 == '~' {
if nSrc+1 >= len(src) {
err = transform.ErrShortSrc
break loop
}
size = 2
switch src[nSrc+1] {
case '{':
*d = gbState
continue
case '}':
*d = asciiState
continue
case '~':
if nDst >= len(dst) {
err = transform.ErrShortDst
break loop
}
dst[nDst] = '~'
nDst++
continue
case '\n':
continue
default:
err = errInvalidHZGB2312
break loop
}
}
if *d == asciiState {
r, size = rune(c0), 1
} else {
if nSrc+1 >= len(src) {
err = transform.ErrShortSrc
break loop
}
c1 := src[nSrc+1]
if c0 < 0x21 || 0x7e <= c0 || c1 < 0x21 || 0x7f <= c1 {
err = errInvalidHZGB2312
break loop
}
r, size = '\ufffd', 2
if i := int(c0-0x01)*190 + int(c1+0x3f); i < len(decode) {
r = rune(decode[i])
if r == 0 {
r = '\ufffd'
}
}
}
if nDst+utf8.RuneLen(r) > len(dst) {
err = transform.ErrShortDst
break loop
}
nDst += utf8.EncodeRune(dst[nDst:], r)
}
if atEOF && err == transform.ErrShortSrc {
err = errInvalidHZGB2312
}
return nDst, nSrc, err
}
type hzGB2312Encoder int
func (d *hzGB2312Encoder) Reset() {
*d = asciiState
}
func (e *hzGB2312Encoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
r, size := rune(0), 0
for ; nSrc < len(src); nSrc += size {
r = rune(src[nSrc])
// Decode a 1-byte rune.
if r < utf8.RuneSelf {
size = 1
if r == '~' {
if nDst+2 > len(dst) {
err = transform.ErrShortDst
break
}
dst[nDst+0] = '~'
dst[nDst+1] = '~'
nDst += 2
continue
}
} else {
// Decode a multi-byte rune.
r, size = utf8.DecodeRune(src[nSrc:])
if size == 1 {
// All valid runes of size 1 (those below utf8.RuneSelf) were
// handled above. We have invalid UTF-8 or we haven't seen the
// full character yet.
if !atEOF && !utf8.FullRune(src[nSrc:]) {
err = transform.ErrShortSrc
break
}
}
// func init checks that the switch covers all tables.
switch {
case encode0Low <= r && r < encode0High:
if r = rune(encode0[r-encode0Low]); r != 0 {
goto writeGB
}
case encode1Low <= r && r < encode1High:
if r = rune(encode1[r-encode1Low]); r != 0 {
goto writeGB
}
case encode2Low <= r && r < encode2High:
if r = rune(encode2[r-encode2Low]); r != 0 {
goto writeGB
}
case encode3Low <= r && r < encode3High:
if r = rune(encode3[r-encode3Low]); r != 0 {
goto writeGB
}
case encode4Low <= r && r < encode4High:
if r = rune(encode4[r-encode4Low]); r != 0 {
goto writeGB
}
}
r = encoding.ASCIISub
}
writeASCII:
if *e != asciiState {
if nDst+3 > len(dst) {
err = transform.ErrShortDst
break
}
*e = asciiState
dst[nDst+0] = '~'
dst[nDst+1] = '}'
nDst += 2
} else if nDst >= len(dst) {
err = transform.ErrShortDst
break
}
dst[nDst] = uint8(r)
nDst++
continue
writeGB:
c0 := uint8(r>>8) - 0x80
c1 := uint8(r) - 0x80
if c0 < 0x21 || 0x7e <= c0 || c1 < 0x21 || 0x7f <= c1 {
r = encoding.ASCIISub
goto writeASCII
}
if *e == asciiState {
if nDst+4 > len(dst) {
err = transform.ErrShortDst
break
}
*e = gbState
dst[nDst+0] = '~'
dst[nDst+1] = '{'
nDst += 2
} else if nDst+2 > len(dst) {
err = transform.ErrShortDst
break
}
dst[nDst+0] = c0
dst[nDst+1] = c1
nDst += 2
continue
}
return nDst, nSrc, err
}
|
