Diff
Not logged in

Differences From Artifact [719d2c9f48]:

To Artifact [dbf9778521]:


695
696
697
698
699
700
701
702

703
704
705
706
707
708
709
695
696
697
698
699
700
701

702
703
704
705
706
707
708
709







-
+







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

Tcl_UniChar
int
Tcl_UniCharAtIndex(
    register const char *src,	/* The UTF-8 string to dereference. */
    register int index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;

    while (index >= 0) {
815
816
817
818
819
820
821
822


823
824
825
826
827
828
829
830
831
832







833

834
835
836
837
838
839
840
815
816
817
818
819
820
821

822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840

841
842
843
844
845
846
847
848







-
+
+










+
+
+
+
+
+
+
-
+







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

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

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

    src = dst = str;
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	upChar = ch;
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    upChar = (((upChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
	upChar = Tcl_UniCharToUpper(ch);
	upChar = Tcl_UniCharToUpper(upChar);

	/*
	 * 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.
	 */

868
869
870
871
872
873
874
875


876
877
878
879
880
881
882
883
884
885







886

887
888
889
890
891
892
893
876
877
878
879
880
881
882

883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901

902
903
904
905
906
907
908
909







-
+
+










+
+
+
+
+
+
+
-
+







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

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

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

    src = dst = str;
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	lowChar = ch;
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    lowChar = (((lowChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
	lowChar = Tcl_UniCharToLower(ch);
	lowChar = Tcl_UniCharToLower(lowChar);

	/*
	 * 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.
	 */

922
923
924
925
926
927
928
929


930
931
932
933
934
935
936
937
938
939
940
941







942

943
944
945
946
947
948
949
950
951
952
953







954

955
956
957
958
959
960
961
938
939
940
941
942
943
944

945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965

966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984

985
986
987
988
989
990
991
992







-
+
+












+
+
+
+
+
+
+
-
+











+
+
+
+
+
+
+
-
+







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

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

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

    src = dst = str;

    if (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	titleChar = ch;
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    titleChar = (((titleChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
	titleChar = Tcl_UniCharToTitle(ch);
	titleChar = Tcl_UniCharToTitle(titleChar);

	if (bytes < TclUtfCount(titleChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += bytes;
    }
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	lowChar = ch;
	if (!bytes) {
	    /* TclUtfToUniChar only returns 0 for chars > 0xffff ! */
	    bytes = TclUtfToUniChar(src, &ch);
	    /* Combine surrogates */
	    lowChar = (((lowChar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
	lowChar = Tcl_UniCharToLower(ch);
	lowChar = Tcl_UniCharToLower(lowChar);

	if (bytes < TclUtfCount(lowChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
1155
1156
1157
1158
1159
1160
1161
1162

1163
1164
1165

1166

1167
1168
1169
1170
1171





1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190

1191
1192
1193

1194

1195
1196
1197
1198
1199





1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218

1219
1220
1221

1222
1223


1224
1225
1226
1227
1228




1229
1230
1231
1232
1233
1234






1235
1236
1237
1238
1239
1240
1241
1186
1187
1188
1189
1190
1191
1192

1193
1194
1195
1196
1197

1198
1199




1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222

1223
1224
1225
1226
1227

1228
1229




1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252

1253
1254
1255
1256
1257


1258
1259
1260




1261
1262
1263
1264
1265





1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278







-
+



+
-
+

-
-
-
-
+
+
+
+
+


















-
+



+
-
+

-
-
-
-
+
+
+
+
+


















-
+



+
-
-
+
+

-
-
-
-
+
+
+
+

-
-
-
-
-
+
+
+
+
+
+







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

Tcl_UniChar
int
Tcl_UniCharToUpper(
    int ch)			/* Unicode character to convert. */
{
    if (!UNICODE_OUT_OF_RANGE(ch)) {
    int info = GetUniCharInfo(ch);
	int info = GetUniCharInfo(ch);

    if (GetCaseType(info) & 0x04) {
	ch -= GetDelta(info);
    }
    return (Tcl_UniChar) ch;
	if (GetCaseType(info) & 0x04) {
	    ch -= GetDelta(info);
	}
    }
    return ch & 0x1FFFFF;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharToLower --
 *
 *	Compute the lowercase equivalent of the given Unicode character.
 *
 * Results:
 *	Returns the lowercase Unicode character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

Tcl_UniChar
int
Tcl_UniCharToLower(
    int ch)			/* Unicode character to convert. */
{
    if (!UNICODE_OUT_OF_RANGE(ch)) {
    int info = GetUniCharInfo(ch);
	int info = GetUniCharInfo(ch);

    if (GetCaseType(info) & 0x02) {
	ch += GetDelta(info);
    }
    return (Tcl_UniChar) ch;
	if (GetCaseType(info) & 0x02) {
	    ch += GetDelta(info);
	}
    }
    return ch & 0x1FFFFF;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharToTitle --
 *
 *	Compute the titlecase equivalent of the given Unicode character.
 *
 * Results:
 *	Returns the titlecase Unicode character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

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

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

	ch += ((mode & 0x4) ? -1 : 1);
    } else if (mode == 0x4) {
	ch -= GetDelta(info);
    }
    return (Tcl_UniChar) ch;
	    ch += ((mode & 0x4) ? -1 : 1);
	} else if (mode == 0x4) {
	    ch -= GetDelta(info);
	}
    }
    return ch & 0x1FFFFF;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharLen --
 *