Diff
Not logged in

Differences From Artifact [f42d134067]:

To Artifact [5e9e721e61]:


674
675
676
677
678
679
680
681

682
683
684
685

686
687
688
689
690
691
692
674
675
676
677
678
679
680

681
682
683
684

685
686
687
688
689
690
691
692







-
+



-
+







    wString = (int *) (Tcl_DStringValue(dsPtr) + oldLength);

    w = wString;
    p = src;
    endPtr = src + length;
    optPtr = endPtr - 4;
    while (p <= optPtr) {
	p += Tcl_UtfToUniChar(p, &ch);
	p += TclUtfToUniChar(p, &ch);
	*w++ = ch;
    }
    while ((p < endPtr) && Tcl_UtfCharComplete(p, endPtr-p)) {
	p += Tcl_UtfToUniChar(p, &ch);
	p += TclUtfToUniChar(p, &ch);
	*w++ = ch;
    }
    while (p < endPtr) {
	*w++ = UCHAR(*p++);
    }
    *w = '\0';
    Tcl_DStringSetLength(dsPtr,
924
925
926
927
928
929
930
931

932
933
934
935
936
937
938
924
925
926
927
928
929
930

931
932
933
934
935
936
937
938







-
+








const char *
Tcl_UtfFindFirst(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The Unicode character to search for. */
{
    while (1) {
	int find, len = Tcl_UtfToUniChar(src, &find);
	int find, len = TclUtfToUniChar(src, &find);

	if (find == ch) {
	    return src;
	}
	if (*src == '\0') {
	    return NULL;
	}
963
964
965
966
967
968
969
970

971
972
973
974
975
976
977
963
964
965
966
967
968
969

970
971
972
973
974
975
976
977







-
+







Tcl_UtfFindLast(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The Unicode character to search for. */
{
    const char *last = NULL;

    while (1) {
	int find, len = Tcl_UtfToUniChar(src, &find);
	int find, len = TclUtfToUniChar(src, &find);

	if (find == ch) {
	    last = src;
	}
	if (*src == '\0') {
	    break;
	}
1186
1187
1188
1189
1190
1191
1192
1193

1194
1195
1196
1197
1198
1199
1200
1186
1187
1188
1189
1190
1191
1192

1193
1194
1195
1196
1197
1198
1199
1200







-
+







    if (index < 0) {
	return -1;
    }
    while (index--) {
	i = TclUtfToUniChar(src, &ch);
	src += i;
    }
    Tcl_UtfToUniChar(src, &i);
    TclUtfToUniChar(src, &i);
    return i;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfAtIndex --
1215
1216
1217
1218
1219
1220
1221
1222

1223
1224
1225
1226
1227
1228
1229
1215
1216
1217
1218
1219
1220
1221

1222
1223
1224
1225
1226
1227
1228
1229







-
+







Tcl_UtfAtIndex(
    const char *src,	/* The UTF-8 string. */
    Tcl_Size index)	/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;

    while (index-- > 0) {
	src += Tcl_UtfToUniChar(src, &ch);
	src += TclUtfToUniChar(src, &ch);
    }
    return src;
}

const char *
TclUtfAtIndex(
    const char *src,	/* The UTF-8 string. */
1325
1326
1327
1328
1329
1330
1331
1332

1333
1334
1335
1336
1337
1338
1339
1325
1326
1327
1328
1329
1330
1331

1332
1333
1334
1335
1336
1337
1338
1339







-
+








    /*
     * Iterate over the string until we hit the terminating null.
     */

    src = dst = str;
    while (*src) {
	len = Tcl_UtfToUniChar(src, &ch);
	len = TclUtfToUniChar(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.
	 */
1378
1379
1380
1381
1382
1383
1384
1385

1386
1387
1388
1389
1390
1391
1392
1378
1379
1380
1381
1382
1383
1384

1385
1386
1387
1388
1389
1390
1391
1392







-
+








    /*
     * Iterate over the string until we hit the terminating null.
     */

    src = dst = str;
    while (*src) {
	len = Tcl_UtfToUniChar(src, &ch);
	len = TclUtfToUniChar(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.
	 */
1434
1435
1436
1437
1438
1439
1440
1441

1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453

1454
1455
1456
1457
1458
1459
1460
1434
1435
1436
1437
1438
1439
1440

1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452

1453
1454
1455
1456
1457
1458
1459
1460







-
+











-
+







     * Capitalize the first character and then lowercase the rest of the
     * characters until we get to a null.
     */

    src = dst = str;

    if (*src) {
	len = Tcl_UtfToUniChar(src, &ch);
	len = TclUtfToUniChar(src, &ch);
	titleChar = Tcl_UniCharToTitle(ch);

	if (len < TclUtfCount(titleChar)) {
	    memmove(dst, src, len);
	    dst += len;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += len;
    }
    while (*src) {
	len = Tcl_UtfToUniChar(src, &ch);
	len = TclUtfToUniChar(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)) {