utf8::decode was not respecting copy-on-write, but simply modify-
ing the PV (the scalar’s string buffer) in place, causing problems
with hashes:
my $name = "\x{c3}\x{b3}";
my ($k1) = keys %{ { $name=>undef } };
my $k2 = $name;
utf8::decode($k1);
utf8::decode($k2);
print "k1 eq k2 = '", $k1 eq $k2, "'\n";
my $h = { $k1 => 1, $k2 => 2 };
print "{k1} '", $h->{$k1}, "'\n";
print "{k2} '", $h->{$k2}, "'\n";
This example (from the RT ticket) shows that there were two hash ele-
ments with the same key.
As of this commit, the hash only has one element.
}
{
+ # Make sure utf8::decode respects copy-on-write [perl #91834].
+ # Hash keys are the easiest way to test this.
+ my $name = "\x{c3}\x{b3}";
+ my ($k1) = keys %{ { $name=>undef } };
+ my $k2 = $name;
+ utf8::decode($k1);
+ utf8::decode($k2);
+ my $h = { $k1 => 1, $k2 => 2 };
+ is join('', keys $h), $k2, 'utf8::decode respects copy-on-write';
+}
+
+{
my $a = "456\xb6";
utf8::upgrade($a);
croak_xs_usage(cv, "sv");
else {
SV * const sv = ST(0);
+ if (SvIsCOW(sv)) sv_force_normal(sv);
const bool RETVAL = sv_utf8_decode(sv);
ST(0) = boolSV(RETVAL);
sv_2mortal(ST(0));