| ︙ | | | ︙ | |
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
|
};
/*
* Functions used only in this module.
*/
static int Invalid(unsigned char *src);
#define UCS4ToUpper Tcl_UniCharToUpper
#define UCS4ToLower Tcl_UniCharToLower
#define UCS4ToTitle Tcl_UniCharToTitle
|
<
<
<
<
<
|
92
93
94
95
96
97
98
99
100
101
102
103
104
105
|
};
/*
* Functions used only in this module.
*/
static int Invalid(unsigned char *src);
/*
*---------------------------------------------------------------------------
*
* TclUtfCount --
*
* Find the number of bytes in the Utf character "ch".
|
| ︙ | | | ︙ | |
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
|
}
/*
* A three-byte-character lead-byte not followed by two trail-bytes
* represents itself.
*/
}
else if (byte < 0xF8) {
if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80) && ((src[3] & 0xC0) == 0x80)) {
/*
* Four-byte-character lead byte followed by three trail bytes.
*/
*chPtr = (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12)
| ((src[2] & 0x3F) << 6) | (src[3] & 0x3F));
if ((unsigned)(*chPtr - 0x10000) <= 0xFFFFF) {
|
|
|
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
|
}
/*
* A three-byte-character lead-byte not followed by two trail-bytes
* represents itself.
*/
}
else if (byte < 0xF5) {
if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80) && ((src[3] & 0xC0) == 0x80)) {
/*
* Four-byte-character lead byte followed by three trail bytes.
*/
*chPtr = (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12)
| ((src[2] & 0x3F) << 6) | (src[3] & 0x3F));
if ((unsigned)(*chPtr - 0x10000) <= 0xFFFFF) {
|
| ︙ | | | ︙ | |
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
|
}
/*
* A three-byte-character lead-byte not followed by two trail-bytes
* represents itself.
*/
}
else if (byte < 0xF8) {
if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80) && ((src[3] & 0xC0) == 0x80)) {
/*
* Four-byte-character lead byte followed by three trail bytes.
*/
unsigned short high = (((byte & 0x07) << 8) | ((src[1] & 0x3F) << 2)
| ((src[2] & 0x3F) >> 4)) - 0x40;
if (high >= 0x400) {
|
|
|
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
|
}
/*
* A three-byte-character lead-byte not followed by two trail-bytes
* represents itself.
*/
}
else if (byte < 0xF5) {
if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80) && ((src[3] & 0xC0) == 0x80)) {
/*
* Four-byte-character lead byte followed by three trail bytes.
*/
unsigned short high = (((byte & 0x07) << 8) | ((src[1] & 0x3F) << 2)
| ((src[2] & 0x3F) >> 4)) - 0x40;
if (high >= 0x400) {
|
| ︙ | | | ︙ | |
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
|
/*
* Iterate over the string until we hit the terminating null.
*/
src = dst = str;
while (*src) {
len = TclUtfToUCS4(src, &ch);
upChar = UCS4ToUpper(ch);
/*
* To keep badly formed Utf strings from getting inflated by the
* conversion (thereby causing a segfault), only copy the upper case
* char to dst if its size is <= the original char.
*/
|
|
|
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
|
/*
* Iterate over the string until we hit the terminating null.
*/
src = dst = str;
while (*src) {
len = TclUtfToUCS4(src, &ch);
upChar = Tcl_UniCharToUpper(ch);
/*
* To keep badly formed Utf strings from getting inflated by the
* conversion (thereby causing a segfault), only copy the upper case
* char to dst if its size is <= the original char.
*/
|
| ︙ | | | ︙ | |
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
|
/*
* Iterate over the string until we hit the terminating null.
*/
src = dst = str;
while (*src) {
len = TclUtfToUCS4(src, &ch);
lowChar = UCS4ToLower(ch);
/*
* To keep badly formed Utf strings from getting inflated by the
* conversion (thereby causing a segfault), only copy the lower case
* char to dst if its size is <= the original char.
*/
|
|
|
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
|
/*
* Iterate over the string until we hit the terminating null.
*/
src = dst = str;
while (*src) {
len = TclUtfToUCS4(src, &ch);
lowChar = Tcl_UniCharToLower(ch);
/*
* To keep badly formed Utf strings from getting inflated by the
* conversion (thereby causing a segfault), only copy the lower case
* char to dst if its size is <= the original char.
*/
|
| ︙ | | | ︙ | |
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
|
* characters until we get to a null.
*/
src = dst = str;
if (*src) {
len = TclUtfToUCS4(src, &ch);
titleChar = UCS4ToTitle(ch);
if ((len < TclUtfCount(titleChar)) || ((titleChar & 0xF800) == 0xD800)) {
memmove(dst, src, len);
dst += len;
} else {
dst += Tcl_UniCharToUtf(titleChar, dst);
}
src += len;
}
while (*src) {
len = TclUtfToUCS4(src, &ch);
lowChar = ch;
/* Special exception for Georgian Asomtavruli chars, no titlecase. */
if ((unsigned)(lowChar - 0x1C90) >= 0x30) {
lowChar = UCS4ToLower(lowChar);
}
if ((len < TclUtfCount(lowChar)) || ((lowChar & 0xF800) == 0xD800)) {
memmove(dst, src, len);
dst += len;
} else {
dst += Tcl_UniCharToUtf(lowChar, dst);
|
|
|
|
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
|
* characters until we get to a null.
*/
src = dst = str;
if (*src) {
len = TclUtfToUCS4(src, &ch);
titleChar = Tcl_UniCharToTitle(ch);
if ((len < TclUtfCount(titleChar)) || ((titleChar & 0xF800) == 0xD800)) {
memmove(dst, src, len);
dst += len;
} else {
dst += Tcl_UniCharToUtf(titleChar, dst);
}
src += len;
}
while (*src) {
len = TclUtfToUCS4(src, &ch);
lowChar = ch;
/* Special exception for Georgian Asomtavruli chars, no titlecase. */
if ((unsigned)(lowChar - 0x1C90) >= 0x30) {
lowChar = Tcl_UniCharToLower(lowChar);
}
if ((len < TclUtfCount(lowChar)) || ((lowChar & 0xF800) == 0xD800)) {
memmove(dst, src, len);
dst += len;
} else {
dst += Tcl_UniCharToUtf(lowChar, dst);
|
| ︙ | | | ︙ | |