[PATCH 5.005_63] utf8 REx botches

[Ilya Zakharevich <ilya@math.ohio-state.edu>]

Gurusamy Sarathy writes:
> I'm hotly pursuing the utf8 trail right now, and expect to have v5.5.640
> out some time this weekend.

This fixes all UTEST failures but complex.t one (I think this one is not
related to RExen).

Enjoy,
Ilya

--- ./regexec.c~	Fri Dec 17 03:08:26 1999
+++ ./regexec.c	Thu Jan  6 17:21:00 2000
@@ -688,6 +690,8 @@ Perl_re_intuit_start(pTHX_ regexp *prog,
 	char *startpos = sv ? strend - SvCUR(sv) : s;
 
 	t = s;
+	if (prog->reganch & ROPT_UTF8)
+	    PL_regdata = prog->data;	/* Used by REGINCLASS UTF logic */
         s = find_byclass(prog, prog->regstclass, s, endpos, startpos, 1);
 	if (!s) {
 #ifdef DEBUGGING
@@ -869,9 +873,9 @@ S_find_byclass(pTHX_ regexp * prog, regn
 	    /* FALL THROUGH */
 	case BOUNDUTF8:
 	    tmp = (I32)(s != startpos) ? utf8_to_uv(reghop((U8*)s, -1), 0) : '\n';
-	    tmp = ((OP(c) == BOUND ? isALNUM_uni(tmp) : isALNUM_LC_uni(tmp)) != 0);
+	    tmp = ((OP(c) == BOUNDUTF8 ? isALNUM_uni(tmp) : isALNUM_LC_uni(tmp)) != 0);
 	    while (s < strend) {
-		if (tmp == !(OP(c) == BOUND ?
+		if (tmp == !(OP(c) == BOUNDUTF8 ?
 			     swash_fetch(PL_utf8_alnum, (U8*)s) :
 			     isALNUM_LC_utf8((U8*)s)))
 		{
@@ -904,12 +908,10 @@ S_find_byclass(pTHX_ regexp * prog, regn
 	    PL_reg_flags |= RF_tainted;
 	    /* FALL THROUGH */
 	case NBOUNDUTF8:
-	    if (prog->minlen)
-		strend = reghop_c(strend, -1);
 	    tmp = (I32)(s != startpos) ? utf8_to_uv(reghop((U8*)s, -1), 0) : '\n';
-	    tmp = ((OP(c) == NBOUND ? isALNUM_uni(tmp) : isALNUM_LC_uni(tmp)) != 0);
+	    tmp = ((OP(c) == NBOUNDUTF8 ? isALNUM_uni(tmp) : isALNUM_LC_uni(tmp)) != 0);
 	    while (s < strend) {
-		if (tmp == !(OP(c) == NBOUND ?
+		if (tmp == !(OP(c) == NBOUNDUTF8 ?
 			     swash_fetch(PL_utf8_alnum, (U8*)s) :
 			     isALNUM_LC_utf8((U8*)s)))
 		    tmp = !tmp;

---

Follow-Ups from:

Gurusamy Sarathy <gsar@activestate.com>

References to:

Gurusamy Sarathy <gsar@activestate.com>

---

[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index][Thread Index][Top&Search][Original]

---