? s + (prog->minlen? cl_l : 0)
: (prog->float_substr ? check_at - start_shift + cl_l
: strend) ;
- char *startpos = sv ? strend - SvCUR(sv) : s;
+ char *startpos = sv && SvPOK(sv) ? strend - SvCUR(sv) : s;
t = s;
if (prog->reganch & ROPT_UTF8) {
PL_reg_flags |= RF_tainted;
/* FALL THROUGH */
case SPACE:
- if (!nextchr && locinput >= PL_regeol)
+ if (!nextchr)
sayNO;
if (!(OP(scan) == SPACE
? isSPACE(nextchr) : isSPACE_LC(nextchr)))
PL_reg_flags |= RF_tainted;
/* FALL THROUGH */
case SPACEUTF8:
- if (!nextchr && locinput >= PL_regeol)
+ if (!nextchr)
sayNO;
if (nextchr & 0x80) {
if (!(OP(scan) == SPACEUTF8
- ? swash_fetch(PL_utf8_space,(U8*)locinput)
+ ? swash_fetch(PL_utf8_space, (U8*)locinput)
: isSPACE_LC_utf8((U8*)locinput)))
{
sayNO;
PL_reg_flags |= RF_tainted;
/* FALL THROUGH */
case NSPACE:
- if (!nextchr)
+ if (!nextchr && locinput >= PL_regeol)
sayNO;
- if (OP(scan) == SPACE
+ if (OP(scan) == NSPACE
? isSPACE(nextchr) : isSPACE_LC(nextchr))
sayNO;
nextchr = UCHARAT(++locinput);
PL_reg_flags |= RF_tainted;
/* FALL THROUGH */
case NSPACEUTF8:
- if (!nextchr)
+ if (!nextchr && locinput >= PL_regeol)
sayNO;
if (nextchr & 0x80) {
if (OP(scan) == NSPACEUTF8
- ? swash_fetch(PL_utf8_space,(U8*)locinput)
+ ? swash_fetch(PL_utf8_space, (U8*)locinput)
: isSPACE_LC_utf8((U8*)locinput))
{
sayNO;
PL_reg_flags |= RF_tainted;
/* FALL THROUGH */
case DIGIT:
- if (!nextchr && locinput >= PL_regeol)
+ if (!nextchr)
sayNO;
if (!(OP(scan) == DIGIT
? isDIGIT(nextchr) : isDIGIT_LC(nextchr)))
if (!nextchr)
sayNO;
if (nextchr & 0x80) {
- if (OP(scan) == NDIGITUTF8
- ? swash_fetch(PL_utf8_digit,(U8*)locinput)
- : isDIGIT_LC_utf8((U8*)locinput))
+ if (!(OP(scan) == DIGITUTF8
+ ? swash_fetch(PL_utf8_digit, (U8*)locinput)
+ : isDIGIT_LC_utf8((U8*)locinput)))
{
sayNO;
}
nextchr = UCHARAT(locinput);
break;
}
- if (!isDIGIT(nextchr))
+ if (!(OP(scan) == DIGITUTF8
+ ? isDIGIT(nextchr) : isDIGIT_LC(nextchr)))
sayNO;
nextchr = UCHARAT(++locinput);
break;
PL_reg_flags |= RF_tainted;
/* FALL THROUGH */
case NDIGIT:
- if (!nextchr)
+ if (!nextchr && locinput >= PL_regeol)
sayNO;
- if (OP(scan) == DIGIT
+ if (OP(scan) == NDIGIT
? isDIGIT(nextchr) : isDIGIT_LC(nextchr))
sayNO;
nextchr = UCHARAT(++locinput);
if (!nextchr && locinput >= PL_regeol)
sayNO;
if (nextchr & 0x80) {
- if (swash_fetch(PL_utf8_digit,(U8*)locinput))
+ if (OP(scan) == NDIGITUTF8
+ ? swash_fetch(PL_utf8_digit, (U8*)locinput)
+ : isDIGIT_LC_utf8((U8*)locinput))
+ {
sayNO;
+ }
locinput += PL_utf8skip[nextchr];
nextchr = UCHARAT(locinput);
break;
}
- if (isDIGIT(nextchr))
+ if (OP(scan) == NDIGITUTF8
+ ? isDIGIT(nextchr) : isDIGIT_LC(nextchr))
sayNO;
nextchr = UCHARAT(++locinput);
break;
PL_regcc = cc;
if (n >= cc->max) { /* Maximum greed exceeded? */
- if (ckWARN(WARN_UNSAFE) && n >= REG_INFTY
+ if (ckWARN(WARN_REGEXP) && n >= REG_INFTY
&& !(PL_reg_flags & RF_warned)) {
PL_reg_flags |= RF_warned;
- Perl_warner(aTHX_ WARN_UNSAFE, "%s limit (%d) exceeded",
+ Perl_warner(aTHX_ WARN_REGEXP, "%s limit (%d) exceeded",
"Complex regular subexpression recursion",
REG_INFTY - 1);
}
REPORT_CODE_OFF+PL_regindent*2, "")
);
}
- if (ckWARN(WARN_UNSAFE) && n >= REG_INFTY
+ if (ckWARN(WARN_REGEXP) && n >= REG_INFTY
&& !(PL_reg_flags & RF_warned)) {
PL_reg_flags |= RF_warned;
- Perl_warner(aTHX_ WARN_UNSAFE, "%s limit (%d) exceeded",
+ Perl_warner(aTHX_ WARN_REGEXP, "%s limit (%d) exceeded",
"Complex regular subexpression recursion",
REG_INFTY - 1);
}
n = regrepeat(scan, n);
locinput = PL_reginput;
if (ln < n && PL_regkind[(U8)OP(next)] == EOL &&
- (!PL_multiline || OP(next) == SEOL))
+ (!PL_multiline || OP(next) == SEOL || OP(next) == EOS)) {
ln = n; /* why back off? */
+ /* ...because $ and \Z can match before *and* after
+ newline at the end. Consider "\n\n" =~ /\n+\Z\n/.
+ We should back off by one in this case. */
+ if (UCHARAT(PL_reginput - 1) == '\n' && OP(next) != EOS)
+ ln--;
+ }
REGCP_SET;
if (paren) {
while (n >= ln) {