| ︙ | | |
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
|
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
|
-
+
-
+
|
if (index < 0) {
return -1;
}
while (index-- > 0) {
i = TclUtfToUniChar(src, &ch);
src += i;
}
#if TCL_UTF_MAX <= 3
#if TCL_UTF_MAX < 4
if ((ch >= 0xD800) && (i < 3)) {
/* Index points at character following high Surrogate */
return -1;
}
#endif
TclUtfToUCS4(src, &i);
return i;
}
/*
*---------------------------------------------------------------------------
*
* Tcl_UtfAtIndex --
*
* Returns a pointer to the specified character (not byte) position in
* the UTF-8 string. If TCL_UTF_MAX <= 3, characters > U+FFFF count as
* the UTF-8 string. If TCL_UTF_MAX < 4, characters > U+FFFF count as
* 2 positions, but then the pointer should never be placed between
* the two positions.
*
* Results:
* As above.
*
* Side effects:
|
| ︙ | | |
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
|
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
|
-
+
|
Tcl_UniChar ch = 0;
int len = 0;
while (index-- > 0) {
len = TclUtfToUniChar(src, &ch);
src += len;
}
#if TCL_UTF_MAX <= 3
#if TCL_UTF_MAX < 4
if ((ch >= 0xD800) && (len < 3)) {
/* Index points at character following high Surrogate */
src += TclUtfToUniChar(src, &ch);
}
#endif
return src;
}
|
| ︙ | | |
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
|
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
|
-
+
|
* only when both strings are of at least n chars long (no need for \0
* check)
*/
cs += TclUtfToUniChar(cs, &ch1);
ct += TclUtfToUniChar(ct, &ch2);
if (ch1 != ch2) {
#if TCL_UTF_MAX <= 3
#if TCL_UTF_MAX < 4
/* Surrogates always report higher than non-surrogates */
if (((ch1 & 0xFC00) == 0xD800)) {
if ((ch2 & 0xFC00) != 0xD800) {
return ch1;
}
} else if ((ch2 & 0xFC00) == 0xD800) {
return -ch2;
|
| ︙ | | |
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
|
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
|
-
+
|
* n must be interpreted as chars, not bytes.
* This should be called only when both strings are of
* at least n chars long (no need for \0 check)
*/
cs += TclUtfToUniChar(cs, &ch1);
ct += TclUtfToUniChar(ct, &ch2);
if (ch1 != ch2) {
#if TCL_UTF_MAX <= 3
#if TCL_UTF_MAX < 4
/* Surrogates always report higher than non-surrogates */
if (((ch1 & 0xFC00) == 0xD800)) {
if ((ch2 & 0xFC00) != 0xD800) {
return ch1;
}
} else if ((ch2 & 0xFC00) == 0xD800) {
return -ch2;
|
| ︙ | | |
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
|
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
|
-
+
|
{
Tcl_UniChar ch1 = 0, ch2 = 0;
while (*cs && *ct) {
cs += TclUtfToUniChar(cs, &ch1);
ct += TclUtfToUniChar(ct, &ch2);
if (ch1 != ch2) {
#if TCL_UTF_MAX <= 3
#if TCL_UTF_MAX < 4
/* Surrogates always report higher than non-surrogates */
if (((ch1 & 0xFC00) == 0xD800)) {
if ((ch2 & 0xFC00) != 0xD800) {
return ch1;
}
} else if ((ch2 & 0xFC00) == 0xD800) {
return -ch2;
|
| ︙ | | |
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
|
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
|
-
+
|
{
Tcl_UniChar ch1 = 0, ch2 = 0;
while (*cs && *ct) {
cs += TclUtfToUniChar(cs, &ch1);
ct += TclUtfToUniChar(ct, &ch2);
if (ch1 != ch2) {
#if TCL_UTF_MAX <= 3
#if TCL_UTF_MAX < 4
/* Surrogates always report higher than non-surrogates */
if (((ch1 & 0xFC00) == 0xD800)) {
if ((ch2 & 0xFC00) != 0xD800) {
return ch1;
}
} else if ((ch2 & 0xFC00) == 0xD800) {
return -ch2;
|
| ︙ | | |
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
|
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
|
-
+
|
*
* Side effects:
* None.
*
*---------------------------------------------------------------------------
*/
#if TCL_UTF_MAX <= 3
#if TCL_UTF_MAX < 4
int
TclUtfToUCS4(
const char *src, /* The UTF-8 string. */
int *ucs4Ptr) /* Filled with the UCS4 codepoint represented
* by the UTF-8 string. */
{
/* Make use of the #undef Tcl_UtfToUniChar above, which already handles UCS4. */
|
| ︙ | | |