Nicholas Clark writes:
> On Sun, Sep 07, 2003 at 02:50:35PM +0000, Peter Gibbs wrote:
> > # New Ticket Created by Peter Gibbs
> > # Please include the string: [perl #23752]
> > # in the subject line of all future correspondence about this issue.
> > # <URL: http://rt.perl.org/rt2/Ticket/Display.html?id=23752 >
> >
> >
> > The 'index' opcode searches for a substring in another string. It seems
> > reasonable to expect that equal strings would match at offset zero. But the
> > program:
> > ----------------------------------------
> > set S0, "\xAB"
> > find_chartype I0, "8859-1"
> > set_chartype S0, I0
> > find_encoding I0, "singlebyte"
> > set_encoding S0, I0
> >
> > find_encoding I0, "utf8"
> > find_chartype I1, "unicode"
> > transcode S1, S0, I0, I1
> >
> > eq S0, S1, equal
> > print "not "
> > equal:
> > print "equal\n"
> >
> > index I0, S0, S1
> > print I0
> > print "\n"
> >
> > end
> > ----------------------------------------
> > yields the output:
> > ----------------------------------------
> > equal
> > -1
> > ----------------------------------------
> > which doesn't seem quite right.
>
> Looks like a bug to me, but I'm no expert on where to start searching for
> it.
Here's a fix.
Luke
Index: string.c
===================================================================
RCS file: /cvs/public/parrot/string.c,v
retrieving revision 1.145
diff -u -r1.145 string.c
--- string.c 7 Sep 2003 12:45:48 -0000 1.145
+++ string.c 21 Sep 2003 22:23:30 -0000
@@ -327,17 +327,17 @@
string_str_index_multibyte(struct Parrot_Interp *interpreter,
const STRING *str, const STRING *find, UINTVAL start)
{
- const void* const lastmatch =
- str->encoding->skip_backward((char*)str->strstart + str->strlen,
- find->encoding->characters(find, find->strlen));
- const void* const lastfind = (char*)find->strstart + find->strlen;
+ const void* const lastmatch = str->encoding->skip_backward(
+ (char*)str->strstart + str->buflen, find->strlen);
+ const void* const lastfind = find->encoding->skip_forward(
+ find->strstart, find->strlen);
const void* sp;
const void* fp;
const void* ip;
INTVAL pos = start;
sp = str->encoding->skip_forward(str->strstart, start);
- while (sp < lastmatch) {
+ while (sp <= lastmatch) {
fp = find->strstart;
ip = sp;
Index: t/op/string.t
===================================================================
RCS file: /cvs/public/parrot/t/op/string.t,v
retrieving revision 1.54
diff -u -r1.54 string.t
--- t/op/string.t 20 Aug 2003 09:43:16 -0000 1.54
+++ t/op/string.t 21 Sep 2003 22:23:30 -0000
@@ -1,6 +1,6 @@
#! perl -w
-use Parrot::Test tests => 117;
+use Parrot::Test tests => 119;
use Test::More;
output_is( <<'CODE', <<OUTPUT, "set_s_s|sc" );
@@ -1294,6 +1294,57 @@
CODE
46368
-1
+OUTPUT
+
+output_is(<<'CODE',<<OUTPUT,"index, multibyte matching");
+ set S0, "\xAB"
+ find_chartype I0, "usascii"
+ set_chartype S0, I0
+ find_encoding I0, "singlebyte"
+ set_encoding S0, I0
+
+ find_encoding I0, "utf8"
+ find_chartype I1, "unicode"
+ transcode S1, S0, I0, I1
+
+ eq S0, S1, equal
+ print "not "
+equal:
+ print "equal\n"
+
+ index I0, S0, S1
+ print I0
+ print "\n"
+ index I0, S1, S0
+ print I0
+ print "\n"
+CODE
+equal
+0
+0
+OUTPUT
+
+output_is(<<'CODE',<<OUTPUT,"index, multibyte matching 2");
+ set S0, "\xAB\xBA"
+ set S1, "foo\xAB\xAB\xBAbar"
+ find_chartype I0, "usascii"
+ set_chartype S0, I0
+ find_encoding I0, "singlebyte"
+ set_encoding S0, I0
+
+ find_chartype I0, "unicode"
+ find_encoding I1, "utf8"
+ transcode S1, S1, I1, I0
+
+ index I0, S0, S1
+ print I0
+ print "\n"
+ index I0, S1, S0
+ print I0
+ print "\n"
+CODE
+-1
+4
OUTPUT
output_is(<<'CODE',<<OUTPUT,"num to string");
