ln = STR_LEN(c);
if (UTF) {
STRLEN ulen1, ulen2;
- U8 tmpbuf1[UTF8_MAXLEN*2+1];
- U8 tmpbuf2[UTF8_MAXLEN*2+1];
+ U8 tmpbuf1[UTF8_MAXLEN_UCLC+1];
+ U8 tmpbuf2[UTF8_MAXLEN_UCLC+1];
to_utf8_lower((U8*)m, tmpbuf1, &ulen1);
to_utf8_upper((U8*)m, tmpbuf2, &ulen2);
if (do_utf8) {
STRLEN len;
+ /* The ibcmp_utf8() uses to_uni_fold() which is more
+ * correct folding for Unicode than using lowercase.
+ * However, it doesn't work quite fully since the folding
+ * is a one-to-many mapping and the regex optimizer is
+ * unaware of this, so it may throw out good matches.
+ * Fortunately, not getting this right is allowed
+ * for Unicode Regular Expression Support level 1,
+ * only one-to-one matching is required. --jhi */
if (c1 == c2)
while (s <= e) {
if ( utf8_to_uvchr((U8*)s, &len) == c1
- && regtry(prog, s) )
+ && (ln == 1 ||
+ ibcmp_utf8(s, do_utf8, strend - s,
+ m, UTF, ln)) )
goto got_it;
s += len;
}
else
while (s <= e) {
UV c = utf8_to_uvchr((U8*)s, &len);
- if ( (c == c1 || c == c2) && regtry(prog, s) )
+ if ( (c == c1 || c == c2)
+ && (ln == 1 ||
+ ibcmp_utf8(s, do_utf8, strend - s,
+ m, UTF, ln)) )
goto got_it;
s += len;
}
New(22,PL_reg_start_tmp, PL_reg_start_tmpl, char*);
}
+#ifdef DEBUGGING
+ sv_setpvn(PERL_DEBUG_PAD(0), "", 0);
+ sv_setpvn(PERL_DEBUG_PAD(1), "", 0);
+ sv_setpvn(PERL_DEBUG_PAD(2), "", 0);
+#endif
+
/* XXXX What this code is doing here?!!! There should be no need
to do this again and again, PL_reglastparen should take care of
this! --ilya*/
char *l = locinput;
char *e;
STRLEN ulen;
- U8 tmpbuf[UTF8_MAXLEN*2+1];
+ U8 tmpbuf[UTF8_MAXLEN_UCLC+1];
e = s + ln;
while (s < e) {
if (l >= PL_regeol)
*/
if (OP(scan) == REFF) {
STRLEN ulen1, ulen2;
- U8 tmpbuf1[UTF8_MAXLEN*2+1];
- U8 tmpbuf2[UTF8_MAXLEN*2+1];
+ U8 tmpbuf1[UTF8_MAXLEN_UCLC+1];
+ U8 tmpbuf2[UTF8_MAXLEN_UCLC+1];
while (s < e) {
if (l >= PL_regeol)
sayNO;
c1 = *(PL_bostr + ln);
}
else { c1 = (U8)*STRING(text_node); }
- if (OP(next) == EXACTF)
+ if (OP(text_node) == EXACTF || OP(text_node) == REFF)
c2 = PL_fold[c1];
- else if (OP(text_node) == EXACTFL)
+ else if (OP(text_node) == EXACTFL || OP(text_node) == REFFL)
c2 = PL_fold_locale[c1];
else
c2 = c1;
}
else { c1 = (U8)*STRING(text_node); }
- if (OP(text_node) == EXACTF)
+ if (OP(text_node) == EXACTF || OP(text_node) == REFF)
c2 = PL_fold[c1];
- else if (OP(text_node) == EXACTFL)
+ else if (OP(text_node) == EXACTFL || OP(text_node) == REFFL)
c2 = PL_fold_locale[c1];
else
c2 = c1;
if (!UTF) {
c2 = c1 = *s;
- if (OP(text_node) == EXACTF)
+ if (OP(text_node) == EXACTF || OP(text_node) == REFF)
c2 = PL_fold[c1];
- else if (OP(text_node) == EXACTFL)
+ else if (OP(text_node) == EXACTFL || OP(text_node) == REFFL)
c2 = PL_fold_locale[c1];
}
else { /* UTF */
- if (OP(text_node) == EXACTF) {
+ if (OP(text_node) == EXACTF || OP(text_node) == REFF) {
STRLEN ulen1, ulen2;
- U8 tmpbuf1[UTF8_MAXLEN*2+1];
- U8 tmpbuf2[UTF8_MAXLEN*2+1];
+ U8 tmpbuf1[UTF8_MAXLEN_UCLC+1];
+ U8 tmpbuf2[UTF8_MAXLEN_UCLC+1];
to_utf8_lower((U8*)s, tmpbuf1, &ulen1);
to_utf8_upper((U8*)s, tmpbuf2, &ulen2);
match = TRUE;
else if (flags & ANYOF_FOLD) {
STRLEN ulen;
- U8 tmpbuf[UTF8_MAXLEN*2+1];
+ U8 tmpbuf[UTF8_MAXLEN_FOLD+1];
- toLOWER_utf8(p, tmpbuf, &ulen);
+ to_utf8_fold(p, tmpbuf, &ulen);
+ if (swash_fetch(sw, tmpbuf, do_utf8))
+ match = TRUE;
+ to_utf8_upper(p, tmpbuf, &ulen);
if (swash_fetch(sw, tmpbuf, do_utf8))
match = TRUE;
}