Diff
Not logged in

Differences From Artifact [840b851393]:

To Artifact [5845f19aa9]:


348
349
350
351
352
353
354
355
356


357
358
359
360
361
362
363
348
349
350
351
352
353
354


355
356
357
358
359
360
361
362
363







-
-
+
+







  0x02C6, 0x2030, 0x0160, 0x2039, 0x0152,   0x8D, 0x017D,   0x8F,
    0x90, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
   0x2DC, 0x2122, 0x0161, 0x203A, 0x0153,   0x9D, 0x017E, 0x0178
};

int
Tcl_UtfToUniChar(
    register const char *src,	/* The UTF-8 string. */
    register Tcl_UniChar *chPtr)/* Filled with the Tcl_UniChar represented by
    const char *src,	/* The UTF-8 string. */
    Tcl_UniChar *chPtr)/* Filled with the Tcl_UniChar represented by
				 * the UTF-8 string. */
{
    Tcl_UniChar byte;

    /*
     * Unroll 1 to 4 byte UTF-8 sequences.
     */
727
728
729
730
731
732
733
734

735
736
737
738
739

740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755

756
757
758
759
760
761
762
727
728
729
730
731
732
733

734
735
736
737
738

739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754

755
756
757
758
759
760
761
762







-
+




-
+















-
+







 *	None.
 *
 *---------------------------------------------------------------------------
 */

int
Tcl_NumUtfChars(
    register const char *src,	/* The UTF-8 string to measure. */
    const char *src,	/* The UTF-8 string to measure. */
    int length)			/* The length of the string in bytes, or -1
				 * for strlen(string). */
{
    Tcl_UniChar ch = 0;
    register int i = 0;
    int i = 0;

    /*
     * The separate implementations are faster.
     *
     * Since this is a time-sensitive function, we also do the check for the
     * single-byte char case specially.
     */

    if (length < 0) {
	while (*src != '\0') {
	    src += TclUtfToUniChar(src, &ch);
	    i++;
	}
	if (i < 0) i = INT_MAX; /* Bug [2738427] */
    } else {
	register const char *endPtr = src + length - 4;
	const char *endPtr = src + length - 4;

	while (src < endPtr) {
	    src += TclUtfToUniChar(src, &ch);
	    i++;
	}
	endPtr += 4;
	while ((src < endPtr) && Tcl_UtfCharComplete(src, endPtr - src)) {
964
965
966
967
968
969
970
971
972


973
974
975
976
977
978
979
964
965
966
967
968
969
970


971
972
973
974
975
976
977
978
979







-
-
+
+







 *	None.
 *
 *---------------------------------------------------------------------------
 */

int
Tcl_UniCharAtIndex(
    register const char *src,	/* The UTF-8 string to dereference. */
    register int index)		/* The position of the desired character. */
    const char *src,	/* The UTF-8 string to dereference. */
    int index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
    int fullchar = 0;
#if TCL_UTF_MAX <= 4
	int len = 0;
#endif

1012
1013
1014
1015
1016
1017
1018
1019
1020


1021
1022
1023
1024
1025
1026
1027
1012
1013
1014
1015
1016
1017
1018


1019
1020
1021
1022
1023
1024
1025
1026
1027







-
-
+
+







 *	None.
 *
 *---------------------------------------------------------------------------
 */

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

    while (index-- > 0) {
	len = TclUtfToUniChar(src, &ch);
	src += len;
1319
1320
1321
1322
1323
1324
1325
1326

1327
1328
1329
1330
1331
1332
1333
1319
1320
1321
1322
1323
1324
1325

1326
1327
1328
1329
1330
1331
1332
1333







-
+







{
    /*
     * We can't simply call 'memcmp(cs, ct, numBytes);' because we need to
     * check for Tcl's \xC0\x80 non-utf-8 null encoding. Otherwise utf-8 lexes
     * fine in the strcmp manner.
     */

    register int result = 0;
    int result = 0;

    for ( ; numBytes != 0; numBytes--, cs++, ct++) {
	if (*cs != *ct) {
	    result = UCHAR(*cs) - UCHAR(*ct);
	    break;
	}
    }