Differences From Artifact [d84096c4c4]:

• File generic/tclUtf.c — part of check-in [57aa5dae72] at 2020-04-08 13:26:12 on branch sebres-utf-prev-fix — partially revert [e8bfb4c2ba884b1b], a prevention added previously in string trim functions (compare char lengths) is not needed with new version of Tcl_UtfPrev (leave other optimizations as appropriate, may be important in some obscure case not covered by current or future implementation of Tcl_UtfPrev/Tcl_UtfToUniChar) (user: sebres size: 50138)

To Artifact [63dd626b9c]:

• File generic/tclUtf.c — part of check-in [f10ba6b7ac] at 2020-04-08 15:37:49 on branch sebres-utf-prev-fix — introduces new utf-internal definition UTF_TO_UNI_MAX, as maximal value that Tcl_UtfToUniChar could return depending to UTF_TO_UNI_MAX and tcl version (here 3 or 4), restricting search cycle of Tcl_UtfPrev now. (user: sebres size: 50307)

379
380
381
382
383
384
385






386
387
388
389
390
391
392

	 */
    }
#endif

    *chPtr = (Tcl_UniChar) byte;
    return 1;
}







/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfToUniCharDString --
 *
 *	Convert the UTF-8 string to Unicode.

>
>
>
>
>
>

379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398

	 */
    }
#endif

    *chPtr = (Tcl_UniChar) byte;
    return 1;
}
/* UTF_TO_UNI_MAX -- maximal value Tcl_UtfToUniChar could return */
#if TCL_UTF_MAX <= 3
#  define UTF_TO_UNI_MAX 3
#else
#  define UTF_TO_UNI_MAX 4
#endif

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfToUniCharDString --
 *
 *	Convert the UTF-8 string to Unicode.

684
685
686
687
688
689
690
691
692
693
694
695
696
697
698

	return start;
    }
    /* simplest case - ascii char */
    if (*((unsigned char *) look) < 0x80) {
	return look;
    }
    /* navigate up to max return value of Tcl_UtfToUniChar */
    for (i = 1; i <= 4; i++) {
	if (look < start) {
	    look = start;
	    break;
	}
	if (*((unsigned char *) look) < 0x80) {
	    /* traversing back reaches ascii - either known mark points to char,
	     * or unexpected case with invalid utf-8 or unsupported surrogate 

|

690
691
692
693
694
695
696
697
698
699
700
701
702
703
704

	return start;
    }
    /* simplest case - ascii char */
    if (*((unsigned char *) look) < 0x80) {
	return look;
    }
    /* navigate up to max return value of Tcl_UtfToUniChar */
    for (i = 1; i <= UTF_TO_UNI_MAX; i++) {
	if (look < start) {
	    look = start;
	    break;
	}
	if (*((unsigned char *) look) < 0x80) {
	    /* traversing back reaches ascii - either known mark points to char,
	     * or unexpected case with invalid utf-8 or unsupported surrogate