Stop pos() from being confused by changing utf8ness

The value of pos() is stored as a byte offset.  If it is stored on a
tied variable or a reference (or glob), then the stringification could
change, resulting in pos() now pointing to a different character off-
set or pointing to the middle of a character:

$ ./perl -Ilib -le '$x = bless [], chr 256; pos $x=1; bless $x, a; print pos $x'
2
$ ./perl -Ilib -le '$x = bless [], chr 256; pos $x=1; bless $x, "\x{1000}"; print pos $x'
Malformed UTF-8 character (unexpected end of string) in match position at -e line 1.
0

So pos() should be stored as a character offset.

The regular expression engine expects byte offsets always, so allow it
to store bytes when possible (a pure non-magical string) but use char-
acters otherwise.

This does result in more complexity than I should like, but the alter-
native (always storing a character offset) would slow down regular
expressions, which is a big no-no.

1 files changed, 11 insertions, 3 deletions

diff --git a/regexec.c b/regexec.c
index d207d0d951..44690b3280 100644
--- a/regexec.c
+++ b/regexec.c
@@ -2256,7 +2256,8 @@ Perl_regexec_flags(pTHX_ REGEXP * const rx, char *stringarg, char *strend,
             (flags & REXEC_IGNOREPOS)
             ? stringarg /* use start pos rather than pos() */
             : (sv && (mg = mg_find_mglob(sv)) && mg->mg_len >= 0)
-            ? strbeg + mg->mg_len /* Defined pos() */
+              /* Defined pos(): */
+            ? strbeg + MgBYTEPOS(mg, sv, strbeg, strend-strbeg)
             : strbeg; /* pos() not defined; use start of string */
 
         DEBUG_GPOS_r(PerlIO_printf(Perl_debug_log,
@@ -5027,8 +5028,9 @@ S_regmatch(pTHX_ regmatch_info *reginfo, char *startpos, regnode *prog)
 
 		rex->offs[0].end = locinput - reginfo->strbeg;
                 if (reginfo->info_aux_eval->pos_magic)
-                        reginfo->info_aux_eval->pos_magic->mg_len
-                                        = locinput - reginfo->strbeg;
+                    MgBYTEPOS_set(reginfo->info_aux_eval->pos_magic,
+                                  reginfo->sv, reginfo->strbeg,
+                                  locinput - reginfo->strbeg);
 
                 if (sv_yes_mark) {
                     SV *sv_mrk = get_sv("REGMARK", 1);
@@ -7648,6 +7650,7 @@ S_setup_eval_state(pTHX_ regmatch_info *const reginfo)
         }
         eval_state->pos_magic = mg;
         eval_state->pos       = mg->mg_len;
+        eval_state->pos_flags = mg->mg_flags;
     }
     else
         eval_state->pos_magic = NULL;
@@ -7722,7 +7725,12 @@ S_cleanup_regmatch_info_aux(pTHX_ void *arg)
             RXp_MATCH_COPIED_on(rex);
         }
         if (eval_state->pos_magic)
+        {
             eval_state->pos_magic->mg_len = eval_state->pos;
+            eval_state->pos_magic->mg_flags =
+                 (eval_state->pos_magic->mg_flags & ~MGf_BYTES)
+               | (eval_state->pos_flags & MGf_BYTES);
+        }
 
         PL_curpm = eval_state->curpm;
     }