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
|
/* ================================================================ */
/*
File: ConvertUTF.C
Author: Mark E. Davis
Copyright (C) 1994 Taligent, Inc. All rights reserved.
This code is copyrighted. Under the copyright laws, this code may not
be copied, in whole or part, without prior written consent of Taligent.
Taligent grants the right to use or reprint this code as long as this
ENTIRE copyright notice is reproduced in the code or reproduction.
The code is provided AS-IS, AND TALIGENT DISCLAIMS ALL WARRANTIES,
EITHER EXPRESS OR IMPLIED, INCLUDING, BUT NOT LIMITED TO IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. IN
NO EVENT WILL TALIGENT BE LIABLE FOR ANY DAMAGES WHATSOEVER (INCLUDING,
WITHOUT LIMITATION, DAMAGES FOR LOSS OF BUSINESS PROFITS, BUSINESS
INTERRUPTION, LOSS OF BUSINESS INFORMATION, OR OTHER PECUNIARY
LOSS) ARISING OUT OF THE USE OR INABILITY TO USE THIS CODE, EVEN
IF TALIGENT HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
BECAUSE SOME STATES DO NOT ALLOW THE EXCLUSION OR LIMITATION OF
LIABILITY FOR CONSEQUENTIAL OR INCIDENTAL DAMAGES, THE ABOVE
LIMITATION MAY NOT APPLY TO YOU.
RESTRICTED RIGHTS LEGEND: Use, duplication, or disclosure by the
government is subject to restrictions as set forth in subparagraph
(c)(l)(ii) of the Rights in Technical Data and Computer Software
clause at DFARS 252.227-7013 and FAR 52.227-19.
This code may be protected by one or more U.S. and International
Patents.
TRADEMARKS: Taligent and the Taligent Design Mark are registered
trademarks of Taligent, Inc.
*/
/* ================================================================ */
#include "CVTUTF.H"
/* ================================================================ */
const int halfShift = 10;
const UCS4 halfBase = 0x0010000UL;
const UCS4 halfMask = 0x3FFUL;
const UCS4 kSurrogateHighStart = 0xD800UL;
const UCS4 kSurrogateHighEnd = 0xDBFFUL;
const UCS4 kSurrogateLowStart = 0xDC00UL;
const UCS4 kSurrogateLowEnd = 0xDFFFUL;
/* ================================================================ */
ConversionResult ConvertUCS4toUTF16 (
UCS4** sourceStart, const UCS4* sourceEnd,
UTF16** targetStart, const UTF16* targetEnd) {
ConversionResult result = ok;
register UCS4* source = *sourceStart;
register UTF16* target = *targetStart;
while (source < sourceEnd) {
register UCS4 ch;
if (target >= targetEnd) {
result = targetExhausted; break;
};
ch = *source++;
if (ch <= kMaximumUCS2) {
*target++ = ch;
} else if (ch > kMaximumUTF16) {
*target++ = kReplacementCharacter;
} else {
if (target + 1 >= targetEnd) {
result = targetExhausted; break;
};
ch -= halfBase;
*target++ = (ch >> halfShift) + kSurrogateHighStart;
*target++ = (ch & halfMask) + kSurrogateLowStart;
};
};
*sourceStart = source;
*targetStart = target;
return result;
};
/* ================================================================ */
ConversionResult ConvertUTF16toUCS4 (
UTF16** sourceStart, UTF16* sourceEnd,
UCS4** targetStart, const UCS4* targetEnd) {
ConversionResult result = ok;
register UTF16* source = *sourceStart;
register UCS4* target = *targetStart;
while (source < sourceEnd) {
register UCS4 ch;
ch = *source++;
if (ch >= kSurrogateHighStart && ch <= kSurrogateHighEnd && source < sourceEnd) {
register UCS4 ch2 = *source;
if (ch2 >= kSurrogateLowStart && ch2 <= kSurrogateLowEnd) {
ch = ((ch - kSurrogateHighStart) << halfShift)
+ (ch2 - kSurrogateLowStart) + halfBase;
++source;
};
};
if (target >= targetEnd) {
result = targetExhausted; break;
};
*target++ = ch;
};
*sourceStart = source;
*targetStart = target;
return result;
};
/* ================================================================ */
UCS4 offsetsFromUTF8[6] = {0x00000000UL, 0x00003080UL, 0x000E2080UL,
0x03C82080UL, 0xFA082080UL, 0x82082080UL};
char bytesFromUTF8[256] = {
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5};
UTF8 firstByteMark[7] = {0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC};
/* ================================================================ */
/* This code is similar in effect to making successive calls on the
mbtowc and wctomb routines in FSS-UTF. However, it is considerably
different in code:
* it is adapted to be consistent with UTF16,
* the interface converts a whole buffer to avoid function-call overhead
* constants have been gathered.
* loops & conditionals have been removed as much as possible for
efficiency, in favor of drop-through switch statements.
*/
/* ================================================================ */
ConversionResult ConvertUTF16toUTF8 (
UTF16** sourceStart, const UTF16* sourceEnd,
UTF8** targetStart, const UTF8* targetEnd)
{
ConversionResult result = ok;
register UTF16* source = *sourceStart;
register UTF8* target = *targetStart;
while (source < sourceEnd) {
register UCS4 ch;
register unsigned short bytesToWrite = 0;
register const UCS4 byteMask = 0xBF;
register const UCS4 byteMark = 0x80;
ch = *source++;
if (ch >= kSurrogateHighStart && ch <= kSurrogateHighEnd
&& source < sourceEnd) {
register UCS4 ch2 = *source;
if (ch2 >= kSurrogateLowStart && ch2 <= kSurrogateLowEnd) {
ch = ((ch - kSurrogateHighStart) << halfShift)
+ (ch2 - kSurrogateLowStart) + halfBase;
++source;
};
};
if (ch < 0x80) { bytesToWrite = 1;
} else if (ch < 0x800) { bytesToWrite = 2;
} else if (ch < 0x10000) { bytesToWrite = 3;
} else if (ch < 0x200000) { bytesToWrite = 4;
} else if (ch < 0x4000000) { bytesToWrite = 5;
} else if (ch <= kMaximumUCS4){ bytesToWrite = 6;
} else { bytesToWrite = 2;
ch = kReplacementCharacter;
}; /* I wish there were a smart way to avoid this conditional */
target += bytesToWrite;
if (target > targetEnd) {
target -= bytesToWrite; result = targetExhausted; break;
};
switch (bytesToWrite) { /* note: code falls through cases! */
case 6: *--target = (ch | byteMark) & byteMask; ch >>= 6;
case 5: *--target = (ch | byteMark) & byteMask; ch >>= 6;
case 4: *--target = (ch | byteMark) & byteMask; ch >>= 6;
case 3: *--target = (ch | byteMark) & byteMask; ch >>= 6;
case 2: *--target = (ch | byteMark) & byteMask; ch >>= 6;
case 1: *--target = ch | firstByteMark[bytesToWrite];
};
target += bytesToWrite;
};
*sourceStart = source;
*targetStart = target;
return result;
};
/* ================================================================ */
ConversionResult ConvertUTF8toUTF16 (
UTF8** sourceStart, UTF8* sourceEnd,
UTF16** targetStart, const UTF16* targetEnd)
{
ConversionResult result = ok;
register UTF8* source = *sourceStart;
register UTF16* target = *targetStart;
while (source < sourceEnd) {
register UCS4 ch = 0;
register unsigned short extraBytesToWrite = bytesFromUTF8[*source];
if (source + extraBytesToWrite > sourceEnd) {
result = sourceExhausted; break;
};
switch(extraBytesToWrite) { /* note: code falls through cases! */
case 5: ch += *source++; ch <<= 6;
case 4: ch += *source++; ch <<= 6;
case 3: ch += *source++; ch <<= 6;
case 2: ch += *source++; ch <<= 6;
case 1: ch += *source++; ch <<= 6;
case 0: ch += *source++;
};
ch -= offsetsFromUTF8[extraBytesToWrite];
if (target >= targetEnd) {
result = targetExhausted; break;
};
if (ch <= kMaximumUCS2) {
*target++ = ch;
} else if (ch > kMaximumUTF16) {
*target++ = kReplacementCharacter;
} else {
if (target + 1 >= targetEnd) {
result = targetExhausted; break;
};
ch -= halfBase;
*target++ = (ch >> halfShift) + kSurrogateHighStart;
*target++ = (ch & halfMask) + kSurrogateLowStart;
};
};
*sourceStart = source;
*targetStart = target;
return result;
};
/* ================================================================ */
ConversionResult ConvertUCS4toUTF8 (
UCS4** sourceStart, const UCS4* sourceEnd,
UTF8** targetStart, const UTF8* targetEnd)
{
ConversionResult result = ok;
register UCS4* source = *sourceStart;
register UTF8* target = *targetStart;
while (source < sourceEnd) {
register UCS4 ch;
register unsigned short bytesToWrite = 0;
register const UCS4 byteMask = 0xBF;
register const UCS4 byteMark = 0x80;
ch = *source++;
if (ch >= kSurrogateHighStart && ch <= kSurrogateHighEnd
&& source < sourceEnd) {
register UCS4 ch2 = *source;
if (ch2 >= kSurrogateLowStart && ch2 <= kSurrogateLowEnd) {
ch = ((ch - kSurrogateHighStart) << halfShift)
+ (ch2 - kSurrogateLowStart) + halfBase;
++source;
};
};
if (ch < 0x80) { bytesToWrite = 1;
} else if (ch < 0x800) { bytesToWrite = 2;
} else if (ch < 0x10000) { bytesToWrite = 3;
} else if (ch < 0x200000) { bytesToWrite = 4;
} else if (ch < 0x4000000) { bytesToWrite = 5;
} else if (ch <= kMaximumUCS4){ bytesToWrite = 6;
} else { bytesToWrite = 2;
ch = kReplacementCharacter;
}; /* I wish there were a smart way to avoid this conditional */
target += bytesToWrite;
if (target > targetEnd) {
target -= bytesToWrite; result = targetExhausted; break;
};
switch (bytesToWrite) { /* note: code falls through cases! */
case 6: *--target = (ch | byteMark) & byteMask; ch >>= 6;
case 5: *--target = (ch | byteMark) & byteMask; ch >>= 6;
case 4: *--target = (ch | byteMark) & byteMask; ch >>= 6;
case 3: *--target = (ch | byteMark) & byteMask; ch >>= 6;
case 2: *--target = (ch | byteMark) & byteMask; ch >>= 6;
case 1: *--target = ch | firstByteMark[bytesToWrite];
};
target += bytesToWrite;
};
*sourceStart = source;
*targetStart = target;
return result;
};
/* ================================================================ */
ConversionResult ConvertUTF8toUCS4 (
UTF8** sourceStart, UTF8* sourceEnd,
UCS4** targetStart, const UCS4* targetEnd)
{
ConversionResult result = ok;
register UTF8* source = *sourceStart;
register UCS4* target = *targetStart;
while (source < sourceEnd) {
register UCS4 ch = 0;
register unsigned short extraBytesToWrite = bytesFromUTF8[*source];
if (source + extraBytesToWrite > sourceEnd) {
result = sourceExhausted; break;
};
switch(extraBytesToWrite) { /* note: code falls through cases! */
case 5: ch += *source++; ch <<= 6;
case 4: ch += *source++; ch <<= 6;
case 3: ch += *source++; ch <<= 6;
case 2: ch += *source++; ch <<= 6;
case 1: ch += *source++; ch <<= 6;
case 0: ch += *source++;
};
ch -= offsetsFromUTF8[extraBytesToWrite];
if (target >= targetEnd) {
result = targetExhausted; break;
};
if (ch <= kMaximumUCS2) {
*target++ = ch;
} else if (ch > kMaximumUCS4) {
*target++ = kReplacementCharacter;
} else {
if (target + 1 >= targetEnd) {
result = targetExhausted; break;
};
ch -= halfBase;
*target++ = (ch >> halfShift) + kSurrogateHighStart;
*target++ = (ch & halfMask) + kSurrogateLowStart;
};
};
*sourceStart = source;
*targetStart = target;
return result;
};
|
