Diff
Not logged in

Differences From Artifact [dbf9778521]:

To Artifact [e1dd3d468b]:


394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
    const char *src,		/* UTF-8 string to convert to Unicode. */
    int length,			/* Length of UTF-8 string in bytes, or -1 for
				 * strlen(). */
    Tcl_DString *dsPtr)		/* Unicode representation of string is
				 * appended to this previously initialized
				 * DString. */
{
    Tcl_UniChar ch, *w, *wString;
    const char *p, *end;
    int oldLength;

    if (length < 0) {
	length = strlen(src);
    }








|







394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
    const char *src,		/* UTF-8 string to convert to Unicode. */
    int length,			/* Length of UTF-8 string in bytes, or -1 for
				 * strlen(). */
    Tcl_DString *dsPtr)		/* Unicode representation of string is
				 * appended to this previously initialized
				 * DString. */
{
    Tcl_UniChar ch = 0, *w, *wString;
    const char *p, *end;
    int oldLength;

    if (length < 0) {
	length = strlen(src);
    }

518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548







549
550
551
552
553
554
555
556
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfFindFirst --
 *
 *	Returns a pointer to the first occurance of the given Tcl_UniChar in
 *	the NULL-terminated UTF-8 string. The NULL terminator is considered
 *	part of the UTF-8 string. Equivalent to Plan 9 utfrune().
 *
 * Results:
 *	As above. If the Tcl_UniChar does not exist in the given string, the
 *	return value is NULL.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

const char *
Tcl_UtfFindFirst(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The Tcl_UniChar to search for. */
{
    int len;
    Tcl_UniChar find = 0;

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







	if (find == ch) {
	    return src;
	}
	if (*src == '\0') {
	    return NULL;
	}
	src += len;
    }







|




|











|

|




>
>
>
>
>
>
>
|







518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfFindFirst --
 *
 *	Returns a pointer to the first occurance of the given character in
 *	the NULL-terminated UTF-8 string. The NULL terminator is considered
 *	part of the UTF-8 string. Equivalent to Plan 9 utfrune().
 *
 * Results:
 *	As above. If the character does not exist in the given string, the
 *	return value is NULL.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

const char *
Tcl_UtfFindFirst(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The character to search for. */
{
    int len, fullchar;
    Tcl_UniChar find = 0;

    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(stringPtr, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	if (find == fullchar) {
	    return src;
	}
	if (*src == '\0') {
	    return NULL;
	}
	src += len;
    }
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589







590
591
592
593
594
595
596
597
 *
 *---------------------------------------------------------------------------
 */

const char *
Tcl_UtfFindLast(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The Tcl_UniChar to search for. */
{
    int len;
    Tcl_UniChar find = 0;
    const char *last;

    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);







	if (find == ch) {
	    last = src;
	}
	if (*src == '\0') {
	    break;
	}
	src += len;
    }







|

|






>
>
>
>
>
>
>
|







581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
 *
 *---------------------------------------------------------------------------
 */

const char *
Tcl_UtfFindLast(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The character to search for. */
{
    int len, fullchar;
    Tcl_UniChar find = 0;
    const char *last;

    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(stringPtr, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	if (find == fullchar) {
	    last = src;
	}
	if (*src == '\0') {
	    break;
	}
	src += len;
    }
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168

int
TclUtfCasecmp(
    const char *cs,		/* UTF string to compare to ct. */
    const char *ct)		/* UTF string cs is compared to. */
{
    while (*cs && *ct) {
	Tcl_UniChar ch1, ch2;

	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
	    ch1 = Tcl_UniCharToLower(ch1);
	    ch2 = Tcl_UniCharToLower(ch2);
	    if (ch1 != ch2) {







|







1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182

int
TclUtfCasecmp(
    const char *cs,		/* UTF string to compare to ct. */
    const char *ct)		/* UTF string cs is compared to. */
{
    while (*cs && *ct) {
	Tcl_UniChar ch1 = 0, ch2 = 0;

	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
	    ch1 = Tcl_UniCharToLower(ch1);
	    ch2 = Tcl_UniCharToLower(ch2);
	    if (ch1 != ch2) {