File: UTF8CodingSystem.cxx

package info (click to toggle)
opensp 1.5.2-13
  • links: PTS
  • area: main
  • in suites: bookworm, bullseye, buster, stretch
  • size: 8,932 kB
  • ctags: 10,036
  • sloc: cpp: 65,784; ansic: 17,124; sh: 11,503; xml: 2,704; makefile: 926; perl: 561; yacc: 288; sed: 16
file content (282 lines) | stat: -rw-r--r-- 6,069 bytes parent folder | download | duplicates (8)
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
// Copyright (c) 1994 James Clark
// See the file COPYING for copying permission.

#include "splib.h"

#ifdef SP_MULTI_BYTE

#include "UTF8CodingSystem.h"
#include "constant.h"

#ifdef SP_NAMESPACE
namespace SP_NAMESPACE {
#endif

enum {
  // cmaskN is mask for first byte to test for N byte sequence
  cmask1 = 0x80,
  cmask2 = 0xe0,
  cmask3 = 0xf0,
  cmask4 = 0xf8,
  cmask5 = 0xfc,
  cmask6 = 0xfe,
  // cvalN is value of masked first byte of N byte sequence
  cval1 = 0x00,
  cval2 = 0xc0,
  cval3 = 0xe0,
  cval4 = 0xf0,
  cval5 = 0xf8,
  cval6 = 0xfc,
  // vmaskN is mask to get value from first byte in N byte sequence
  vmask2 = 0x1f,
  vmask3 = 0xf,
  vmask4 = 0x7,
  vmask5 = 0x3,
  vmask6 = 0x1,
  // minN is minimum legal resulting value for N byte sequence
  min2 = 0x80,
  min3 = 0x800,
  min4 = 0x10000,
  min5 = 0x200000,
  min6 = 0x4000000,
  max6 = 0x7fffffff
};

class UTF8Decoder : public Decoder {
public:
  UTF8Decoder();
  size_t decode(Char *, const char *, size_t, const char **);
  Boolean convertOffset(unsigned long &offset) const;
private:
  // value for encoding error
  enum { invalid = 0xfffd };
  Boolean recovering_;
  PackedBoolean hadFirstChar_;
  PackedBoolean hadByteOrderMark_;
};

class UTF8Encoder : public Encoder {
public:
  UTF8Encoder();
  void output(const Char *, size_t, OutputByteStream *);
};

Decoder *UTF8CodingSystem::makeDecoder() const
{
  return new UTF8Decoder;
}

Encoder *UTF8CodingSystem::makeEncoder() const
{
  return new UTF8Encoder;
}


UTF8Decoder::UTF8Decoder()
: recovering_(0), hadFirstChar_(0), hadByteOrderMark_(0)
{
}

size_t UTF8Decoder::decode(Char *to, const char *s,
			  size_t slen, const char **result)
{
  // Check for byte-order mark
  if (!hadFirstChar_ && slen >= 3) {
    hadFirstChar_ = 1;

    if ((unsigned char)s[0] == 0xEF &&
        (unsigned char)s[1] == 0xBB &&
        (unsigned char)s[2] == 0xBF) {
      s += 3;
      slen -= 3;
      hadByteOrderMark_ = 1;
    }
  }
  Char *start = to;
  const unsigned char *us = (const unsigned char *)s;
  if (recovering_) {
    recovering_ = 0;
    goto recover;
  }
  while (slen > 0) {
    unsigned c0;
    c0 = us[0];
    if ((c0 & cmask1) == cval1) {
      *to++ = c0;
      us++;
      slen--;
    }
    else if ((c0 & cmask2) == cval2) {
      if (slen < 2)
	goto done;
      unsigned c1 = us[1] ^ 0x80;
      if (c1 & 0xc0)
	goto error;
      unsigned c = ((c0 & vmask2) << 6) | c1;
      if (c < min2)
	c = invalid;
      *to++ = c;
      slen -= 2;
      us += 2;
    }
    else if ((c0 & cmask3) == cval3) {
      if (slen < 3)
	goto done;
      unsigned c1 = us[1] ^ 0x80;
      unsigned c2 = us[2] ^ 0x80;
      if ((c1 | c2) & 0xc0)
	goto error;
      unsigned c = ((((c0 & vmask3) << 6) | c1) << 6) | c2;
      if (c < min3)
	c = invalid;
      *to++ = c;
      slen -= 3;
      us += 3;
    }
    else if ((c0 & cmask4) == cval4) {
      if (slen < 4)
	goto done;
      unsigned c1 = us[1] ^ 0x80;
      unsigned c2 = us[2] ^ 0x80;
      unsigned c3 = us[3] ^ 0x80;
      if ((c1 | c2 | c3) & 0xc0)
	goto error;
      if (charMax < min5 - 1)
	*to++ = invalid;
      else {
	unsigned long c = ((((c0 & vmask4) << 6) | c1) << 6) | c2;
	c = (c << 6) | c3;
	if (c < min4)
	  c = invalid;
	*to++ = c;
      }
      slen -= 4;
      us += 4;
    }
    else if ((c0 & cmask5) == cval5) {
      if (slen < 5)
	goto done;
      unsigned c1 = us[1] ^ 0x80;
      unsigned c2 = us[2] ^ 0x80;
      unsigned c3 = us[3] ^ 0x80;
      unsigned c4 = us[4] ^ 0x80;
      if ((c1 | c2 | c3 | c4) & 0xc0)
	goto error;
      if (charMax < min6 - 1)
	*to++ = invalid;
      else {
	unsigned long c = ((((c0 & vmask5) << 6) | c1) << 6) | c2;
	c = (((c << 6) | c3) << 6) | c4;
	if (c < min5)
	  c = invalid;
	*to++ = c;
      }
      slen -= 5;
      us += 5;
    }
    else if ((c0 & cmask6) == cval6) {
      if (slen < 6)
	goto done;
      unsigned c1 = us[1] ^ 0x80;
      unsigned c2 = us[2] ^ 0x80;
      unsigned c3 = us[3] ^ 0x80;
      unsigned c4 = us[4] ^ 0x80;
      unsigned c5 = us[5] ^ 0x80;
      if ((c1 | c2 | c3 | c4 | c5) & 0xc0)
	goto error;
      if (charMax < max6)
	*to++ = invalid;
      else {
	unsigned long c = ((((c0 & vmask6) << 6) | c1) << 6) | c2;
	c = (((((c << 6) | c3) << 6) | c4) << 6) | c5;
	if (c < min6)
	  c = invalid;
	*to++ = c;
      }
      slen -= 6;
      us += 6;
    }
    else {
    error:
      us++;
      slen--;
      *to++ = invalid;
    recover:
      for (;;) {
	if (slen == 0) {
	  recovering_ = 1;
	  goto done;
	}
	if ((*us & 0xc0) != 0x80)
	  break;
	us++;
	slen--;
      }
    }
  }
 done:
  *result = (char *)us;
  return to - start;
}

Boolean UTF8Decoder::convertOffset(unsigned long &n) const
{
  if (hadByteOrderMark_)
    n += 3;

  return true;
}

UTF8Encoder::UTF8Encoder()
{
}

void UTF8Encoder::output(const Char *s, size_t n, OutputByteStream *sb)
{
  for (; n > 0; s++, n--) {
    Char c = *s;
    if (c < min2)
      sb->sputc((unsigned char)c);
    else if (c < min3) {
      sb->sputc((c >> 6) | cval2);
      sb->sputc((c & 0x3f) | 0x80);
    }
    else if (c < min4) {
      sb->sputc((c >> 12) | cval3);
      sb->sputc(((c >> 6) & 0x3f) | 0x80);
      sb->sputc((c & 0x3f) | 0x80);
    }
    else if (c < min5) {
      sb->sputc((c >> 18) | cval4);
      sb->sputc(((c >> 12) & 0x3f) | 0x80);
      sb->sputc(((c >> 6) & 0x3f) | 0x80);
      sb->sputc((c & 0x3f) | 0x80);
    }
    else if (c < min6) {
      sb->sputc((c >> 24) | cval5);
      sb->sputc(((c >> 18) & 0x3f) | 0x80);
      sb->sputc(((c >> 12) & 0x3f) | 0x80);
      sb->sputc(((c >> 6) & 0x3f) | 0x80);
      sb->sputc((c & 0x3f) | 0x80);
    }
    else if (c <= max6) {
      sb->sputc((c >> 30) | cval6);
      sb->sputc(((c >> 24) & 0x3f) | 0x80);
      sb->sputc(((c >> 18) & 0x3f) | 0x80);
      sb->sputc(((c >> 12) & 0x3f) | 0x80);
      sb->sputc(((c >> 6) & 0x3f) | 0x80);
      sb->sputc((c & 0x3f) | 0x80);
    }
  }
}
#ifdef SP_NAMESPACE
}
#endif

#else /* not SP_MULTI_BYTE */

#ifndef __GNUG__
static char non_empty_translation_unit;	// sigh
#endif

#endif /* not SP_MULTI_BYTE */