/* doop.c
*
- * Copyright (c) 1991-2002, Larry Wall
+ * Copyright (C) 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999,
+ * 2000, 2001, 2002, by Larry Wall and others
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
#include "perl.h"
#ifndef PERL_MICRO
-#if !defined(NSIG) || defined(M_UNIX) || defined(M_XENIX)
#include <signal.h>
#endif
-#endif
STATIC I32
S_do_trans_simple(pTHX_ SV *sv)
s = (U8*)SvPV(sv, len);
send = s + len;
- /* First, take care of non-UTF8 input strings, because they're easy */
+ /* First, take care of non-UTF-8 input strings, because they're easy */
if (!SvUTF8(sv)) {
while (s < send) {
if ((ch = tbl[*s]) >= 0) {
s += ulen;
}
else { /* No match -> copy */
- Copy(s, d, ulen, U8);
+ Move(s, d, ulen, U8);
d += ulen;
s += ulen;
}
UV comp = utf8_to_uvchr(s, &len);
if (comp > 0xff) {
if (!complement) {
- Copy(s, d, len, U8);
+ Move(s, d, len, U8);
d += len;
}
else {
}
else if (uv == none) {
int i = UTF8SKIP(s);
- Copy(s, d, i, U8);
+ Move(s, d, i, U8);
d += i;
s += i;
}
}
else if (uv == none) { /* "none" is unmapped character */
int i = UTF8SKIP(s);
- Copy(s, d, i, U8);
+ Move(s, d, i, U8);
d += i;
s += i;
puv = 0xfeedface;
STRLEN len;
uv = utf8_to_uvuni(s, &len);
if (uv != puv) {
- Copy(s, d, len, U8);
+ Move(s, d, len, U8);
d += len;
puv = uv;
}
}
else if (uv == none) { /* "none" is unmapped character */
int i = UTF8SKIP(s);
- Copy(s, d, i, U8);
+ Move(s, d, i, U8);
d += i;
s += i;
continue;
DEBUG_t( Perl_deb(aTHX_ "2.TBL\n"));
- switch (PL_op->op_private & ~hasutf & 63) {
+ switch (PL_op->op_private & ~hasutf & (
+ OPpTRANS_FROM_UTF|OPpTRANS_TO_UTF|OPpTRANS_IDENTICAL|
+ OPpTRANS_SQUASH|OPpTRANS_DELETE|OPpTRANS_COMPLEMENT)) {
case 0:
if (hasutf)
return do_trans_simple_utf8(sv);
++mark;
}
- sv_setpv(sv, "");
+ sv_setpvn(sv, "", 0);
+ /* sv_setpv retains old UTF8ness [perl #24846] */
+ if (SvUTF8(sv))
+ SvUTF8_off(sv);
+
if (PL_tainting && SvMAGICAL(sv))
SvTAINTED_off(sv);
STRLEN len;
STRLEN n_a;
char *s;
+ char *temp_buffer = NULL;
+ SV* svrecode = Nullsv;
if (RsSNARF(PL_rs))
return 0;
if (SvREADONLY(sv))
Perl_croak(aTHX_ PL_no_modify);
}
+
+ if (PL_encoding) {
+ if (!SvUTF8(sv)) {
+ /* XXX, here sv is utf8-ized as a side-effect!
+ If encoding.pm is used properly, almost string-generating
+ operations, including literal strings, chr(), input data, etc.
+ should have been utf8-ized already, right?
+ */
+ sv_recode_to_utf8(sv, PL_encoding);
+ }
+ }
+
s = SvPV(sv, len);
if (s && len) {
s += --len;
}
}
else {
- STRLEN rslen;
+ STRLEN rslen, rs_charlen;
char *rsptr = SvPV(PL_rs, rslen);
+
+ rs_charlen = SvUTF8(PL_rs)
+ ? sv_len_utf8(PL_rs)
+ : rslen;
+
+ if (SvUTF8(PL_rs) != SvUTF8(sv)) {
+ /* Assumption is that rs is shorter than the scalar. */
+ if (SvUTF8(PL_rs)) {
+ /* RS is utf8, scalar is 8 bit. */
+ bool is_utf8 = TRUE;
+ temp_buffer = (char*)bytes_from_utf8((U8*)rsptr,
+ &rslen, &is_utf8);
+ if (is_utf8) {
+ /* Cannot downgrade, therefore cannot possibly match
+ */
+ assert (temp_buffer == rsptr);
+ temp_buffer = NULL;
+ goto nope;
+ }
+ rsptr = temp_buffer;
+ }
+ else if (PL_encoding) {
+ /* RS is 8 bit, encoding.pm is used.
+ * Do not recode PL_rs as a side-effect. */
+ svrecode = newSVpvn(rsptr, rslen);
+ sv_recode_to_utf8(svrecode, PL_encoding);
+ rsptr = SvPV(svrecode, rslen);
+ rs_charlen = sv_len_utf8(svrecode);
+ }
+ else {
+ /* RS is 8 bit, scalar is utf8. */
+ temp_buffer = (char*)bytes_to_utf8((U8*)rsptr, &rslen);
+ rsptr = temp_buffer;
+ }
+ }
if (rslen == 1) {
if (*s != *rsptr)
goto nope;
s -= rslen - 1;
if (memNE(s, rsptr, rslen))
goto nope;
- count += rslen;
+ count += rs_charlen;
}
}
s = SvPV_force(sv, n_a);
SvSETMAGIC(sv);
}
nope:
+
+ if (svrecode)
+ SvREFCNT_dec(svrecode);
+
+ Safefree(temp_buffer);
return count;
}
if (sv != left || (optype != OP_BIT_AND && !SvOK(sv) && !SvGMAGICAL(sv)))
sv_setpvn(sv, "", 0); /* avoid undef warning on |= and ^= */
- lsave = lc = SvPV(left, leftlen);
- rsave = rc = SvPV(right, rightlen);
+ lsave = lc = SvPV_nomg(left, leftlen);
+ rsave = rc = SvPV_nomg(right, rightlen);
len = leftlen < rightlen ? leftlen : rightlen;
lensave = len;
if ((left_utf || right_utf) && (sv == left || sv == right)) {
}
else if (SvOK(sv) || SvTYPE(sv) > SVt_PVMG) {
STRLEN n_a;
- dc = SvPV_force(sv, n_a);
+ dc = SvPV_force_nomg(sv, n_a);
if (SvCUR(sv) < (STRLEN)len) {
dc = SvGROW(sv, (STRLEN)(len + 1));
(void)memzero(dc + SvCUR(sv), len - SvCUR(sv) + 1);