The offset for pos is stored as bytes, and converted to (Unicode)

character position when read, if needed. The code for setting pos
inside subst was incorrectly converting to character position before
storing the value. This code appears to have been buggy since it was
added in 2000 in change 7562.

p4raw-id: //depot/perl@33580

diff --git a/pp_ctl.c b/pp_ctl.c
index 0b4da4d..a3be377 100644 (file)
--- a/pp_ctl.c
+++ b/pp_ctl.c
@@ -298,7 +298,6 @@ PP(pp_substcont)
     { /* Update the pos() information. */
        SV * const sv = cx->sb_targ;
        MAGIC *mg;
-       I32 i;
        SvUPGRADE(sv, SVt_PVMG);
        if (!(mg = mg_find(sv, PERL_MAGIC_regex_global))) {
 #ifdef PERL_OLD_COPY_ON_WRITE
@@ -308,10 +307,7 @@ PP(pp_substcont)
            mg = sv_magicext(sv, NULL, PERL_MAGIC_regex_global, &PL_vtbl_mglob,
                             NULL, 0);
        }
-       i = m - orig;
-       if (DO_UTF8(sv))
-           sv_pos_b2u(sv, &i);
-       mg->mg_len = i;
+       mg->mg_len = m - orig;
     }
     if (old != rx)
        (void)ReREFCNT_inc(rx);

diff --git a/t/op/subst.t b/t/op/subst.t
index 6cf84b7..06c04e8 100755 (executable)
--- a/t/op/subst.t
+++ b/t/op/subst.t
@@ -7,7 +7,7 @@ BEGIN {
 }
 
 require './test.pl';
-plan( tests => 136 );
+plan( tests => 139 );
 
 $x = 'foo';
 $_ = "x";
@@ -583,3 +583,11 @@ is($name, "cis", q[#22351 bug with 'e' substitution modifier]);
     is($want,$_,"RT#17542");
 }
 
+{
+    my @tests = ('ABC', "\xA3\xA4\xA5", "\x{410}\x{411}\x{412}");
+    foreach (@tests) {
+       my $id = ord $_;
+       s/./pos/ge;
+       is($_, "012", "RT#52104: $id");
+    }
+}