Diff
Not logged in

Differences From Artifact [a8a9b0c072]:

To Artifact [047d99f7af]:


96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
 *	None.
 *
 *---------------------------------------------------------------------------
 */

static inline int
UtfCount(
    int ch)			/* The Tcl_UniChar whose size is returned. */
{
    if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
	return 1;
    }
    if (ch <= 0x7FF) {
	return 2;
    }







|







96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
 *	None.
 *
 *---------------------------------------------------------------------------
 */

static inline int
UtfCount(
    int ch)			/* The Unicode character whose size is returned. */
{
    if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
	return 1;
    }
    if (ch <= 0x7FF) {
	return 2;
    }
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589

    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(src, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	if (find == fullchar) {
	    return src;
	}
	if (*src == '\0') {
	    return NULL;
	}
	src += len;
    }
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfFindLast --
 *
 *	Returns a pointer to the last occurance of the given Unicode character
 *	in the NULL-terminated UTF-8 string. The NULL terminator is considered
 *	part of the UTF-8 string. Equivalent to Plan 9 utfrrune().
 *
 * Results:
 *	As above. If the Tcl_UniChar does not exist in the given string, the
 *	return value is NULL.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */







|


|



















|







552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589

    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(src, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    return src;
	}
	if (*src == '\0') {
	    return NULL;
	}
	src += len;
    }
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfFindLast --
 *
 *	Returns a pointer to the last occurance of the given Unicode character
 *	in the NULL-terminated UTF-8 string. The NULL terminator is considered
 *	part of the UTF-8 string. Equivalent to Plan 9 utfrrune().
 *
 * Results:
 *	As above. If the Unicode character does not exist in the given string, the
 *	return value is NULL.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(src, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000;
	}
#endif
	if (find == fullchar) {
	    last = src;
	}
	if (*src == '\0') {
	    break;
	}
	src += len;
    }







|


|







600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(src, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    last = src;
	}
	if (*src == '\0') {
	    break;
	}
	src += len;
    }
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UniCharAtIndex --
 *
 *	Returns the Unicode character represented at the specified character
 *	(not byte) position in the UTF-8 string.
 *
 * Results:
 *	As above.
 *
 * Side effects:
 *	None.







|







703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UniCharAtIndex --
 *
 *	Returns the Tcl_UniChar represented at the specified character
 *	(not byte) position in the UTF-8 string.
 *
 * Results:
 *	As above.
 *
 * Side effects:
 *	None.