Diff
Not logged in

Differences From Artifact [f35edc2a16]:

To Artifact [652d56928a]:


83
84
85
86
87
88
89



90
91
92
93
94
95
96
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99







+
+
+








/*
 * Functions used only in this module.
 */

static int		UtfCount(int ch);
static int		Invalid(unsigned char *src);
static int		UCS4ToUpper(int ch);
static int		UCS4ToLower(int ch);
static int		UCS4ToTitle(int ch);

/*
 *---------------------------------------------------------------------------
 *
 * UtfCount --
 *
 *	Find the number of bytes in the Utf character "ch".
1003
1004
1005
1006
1007
1008
1009
1010

1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021


1022
1023
1024
1025
1026
1027
1028
1006
1007
1008
1009
1010
1011
1012

1013
1014
1015
1016
1017
1018
1019
1020
1021
1022


1023
1024
1025
1026
1027
1028
1029
1030
1031







-
+









-
-
+
+







 *----------------------------------------------------------------------
 */

int
Tcl_UtfToUpper(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0, upChar;
    int ch, upChar;
    char *src, *dst;
    int len;

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

    src = dst = str;
    while (*src) {
	len = TclUtfToUniChar(src, &ch);
	upChar = Tcl_UniCharToUpper(ch);
	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.
	 */

1056
1057
1058
1059
1060
1061
1062
1063

1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074


1075
1076
1077
1078
1079
1080
1081
1059
1060
1061
1062
1063
1064
1065

1066
1067
1068
1069
1070
1071
1072
1073
1074
1075


1076
1077
1078
1079
1080
1081
1082
1083
1084







-
+









-
-
+
+







 *----------------------------------------------------------------------
 */

int
Tcl_UtfToLower(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0, lowChar;
    int ch, lowChar;
    char *src, *dst;
    int len;

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

    src = dst = str;
    while (*src) {
	len = TclUtfToUniChar(src, &ch);
	lowChar = Tcl_UniCharToLower(ch);
	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.
	 */

1110
1111
1112
1113
1114
1115
1116
1117

1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130


1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141

1142
1143
1144
1145

1146
1147
1148
1149
1150
1151
1152
1113
1114
1115
1116
1117
1118
1119

1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131


1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143

1144
1145
1146
1147

1148
1149
1150
1151
1152
1153
1154
1155







-
+











-
-
+
+










-
+



-
+







 *----------------------------------------------------------------------
 */

int
Tcl_UtfToTitle(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0, titleChar, lowChar;
    int ch, titleChar, lowChar;
    char *src, *dst;
    int len;

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

    src = dst = str;

    if (*src) {
	len = TclUtfToUniChar(src, &ch);
	titleChar = Tcl_UniCharToTitle(ch);
	len = TclUtfToUCS4(src, &ch);
	titleChar = UCS4ToTitle(ch);

	if (len < UtfCount(titleChar) || ((titleChar & 0xF800) == 0xD800)) {
	    memmove(dst, src, len);
	    dst += len;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += len;
    }
    while (*src) {
	len = TclUtfToUniChar(src, &ch);
	len = TclUtfToUCS4(src, &ch);
	lowChar = ch;
	/* Special exception for Georgian Asomtavruli chars, no titlecase. */
	if ((unsigned)(lowChar - 0x1C90) >= 0x30) {
	    lowChar = Tcl_UniCharToLower(lowChar);
	    lowChar = UCS4ToLower(lowChar);
	}

	if (len < UtfCount(lowChar) || ((lowChar & 0xF800) == 0xD800)) {
	    memmove(dst, src, len);
	    dst += len;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
1378
1379
1380
1381
1382
1383
1384
1385
1386


1387
1388
1389
1390
1391
1392
1393







1394

1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414


1415
1416
1417
1418
1419
1420
1421
1422







1423

1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
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

1461
1462
1463
1464
1465
1466
1467
1381
1382
1383
1384
1385
1386
1387


1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403

1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422


1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
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
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483

1484
1485
1486
1487
1488
1489
1490
1491







-
-
+
+







+
+
+
+
+
+
+
-
+


















-
-
+
+








+
+
+
+
+
+
+
-
+


















-
-
+
+
















+
+
+
+
+
+
+
-
+







 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

Tcl_UniChar
Tcl_UniCharToUpper(
static int
UCS4ToUpper(
    int ch)			/* Unicode character to convert. */
{
    int info = GetUniCharInfo(ch);

    if (GetCaseType(info) & 0x04) {
	ch -= GetDelta(info);
    }
    return ch;
}

Tcl_UniChar
Tcl_UniCharToUpper(
    int ch)			/* Unicode character to convert. */
{
    return (Tcl_UniChar) ch;
    return (Tcl_UniChar) UCS4ToUpper(ch);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharToLower --
 *
 *	Compute the lowercase equivalent of the given Unicode character.
 *
 * Results:
 *	Returns the lowercase Unicode character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

Tcl_UniChar
Tcl_UniCharToLower(
static int
UCS4ToLower(
    int ch)			/* Unicode character to convert. */
{
    int info = GetUniCharInfo(ch);
    int mode = GetCaseType(info);

    if ((mode & 0x02) && (mode != 0x7)) {
	ch += GetDelta(info);
    }
    return ch;
}

Tcl_UniChar
Tcl_UniCharToLower(
    int ch)			/* Unicode character to convert. */
{
    return (Tcl_UniChar) ch;
    return (Tcl_UniChar) UCS4ToLower(ch);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharToTitle --
 *
 *	Compute the titlecase equivalent of the given Unicode character.
 *
 * Results:
 *	Returns the titlecase Unicode character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

Tcl_UniChar
Tcl_UniCharToTitle(
static int
UCS4ToTitle(
    int ch)			/* Unicode character to convert. */
{
    int info = GetUniCharInfo(ch);
    int mode = GetCaseType(info);

    if (mode & 0x1) {
	/*
	 * Subtract or add one depending on the original case.
	 */

	if (mode != 0x7) {
	    ch += ((mode & 0x4) ? -1 : 1);
	}
    } else if (mode == 0x4) {
	ch -= GetDelta(info);
    }
    return ch;
}

Tcl_UniChar
Tcl_UniCharToTitle(
    int ch)			/* Unicode character to convert. */
{
    return (Tcl_UniChar) ch;
    return (Tcl_UniChar) UCS4ToTitle(ch);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharLen --
 *