Re: unpack A strip patch

[Ton Hospel]

In article <[EMAIL PROTECTED]>,
        Rafael Garcia-Suarez <[EMAIL PROTECTED]> writes:
> I'd prefer 3, because it's the more conservative. However, having to
> choose between 1 and 2, I think 1 is more right, since it continues
> what the current implementation does more consistently.
> 

Ok, here is 1) then:

diff -ru perl-rsync/pod/perlfunc.pod perl-dev/pod/perlfunc.pod
--- perl-rsync/pod/perlfunc.pod Mon Mar 21 11:57:09 2005
+++ perl-dev/pod/perlfunc.pod   Mon Mar 21 21:42:41 2005
@@ -3425,7 +3425,7 @@
 
 The C<a>, C<A>, and C<Z> types gobble just one value, but pack it as a
 string of length count, padding with nulls or spaces as necessary.  When
-unpacking, C<A> strips trailing spaces and nulls, C<Z> strips everything
+unpacking, C<A> strips trailing whitespace and nulls, C<Z> strips everything
 after the first null, and C<a> returns data verbatim.
 
 If the value-to-pack is too long, it is truncated.  If too long and an
diff -ru perl-rsync/pp_pack.c perl-dev/pp_pack.c
--- perl-rsync/pp_pack.c        Mon Mar 21 11:57:09 2005
+++ perl-dev/pp_pack.c  Mon Mar 21 22:17:08 2005
@@ -1373,9 +1373,19 @@
            } else if (datumtype == 'A') {
                /* 'A' strips both nulls and spaces */
                char *ptr;
-               for (ptr = s+len-1; ptr >= s; ptr--)
-                   if (*ptr != 0 && !isSPACE(*ptr)) break;
-               ptr++;
+               if (utf8 && (symptr->flags & FLAG_WAS_UTF8)) {
+                   for (ptr = s+len-1; ptr >= s; ptr--)
+                       if (*ptr != 0 && !UTF8_IS_CONTINUATION(*ptr) &&
+                           !is_utf8_space(ptr)) break;
+                   if (ptr >= s) ptr += UTF8SKIP(ptr);
+                   else ptr++;
+                   if (ptr > s+len) 
+                       Perl_croak(aTHX_ "Malformed UTF-8 string in unpack");
+               } else {
+                   for (ptr = s+len-1; ptr >= s; ptr--)
+                       if (*ptr != 0 && !isSPACE(*ptr)) break;
+                   ptr++;
+               }
                sv = newSVpvn(s, ptr-s);
            } else sv = newSVpvn(s, len);
 
diff -ru perl-rsync/t/op/pack.t perl-dev/t/op/pack.t
--- perl-rsync/t/op/pack.t      Mon Mar 21 11:57:09 2005
+++ perl-dev/t/op/pack.t        Mon Mar 21 22:18:49 2005
@@ -12,7 +12,7 @@
 my $no_signedness = $] > 5.009 ? '' :
   "Signed/unsigned pack modifiers not available on this perl";
 
-plan tests => 14621;
+plan tests => 14627;
 
 use strict;
 use warnings;
@@ -1806,4 +1806,19 @@
     is(pack("Z*/Z"), "1\0\0", "pack Z*/Z makes an extended string");
     is(pack("Z*/Z", ""), "1\0\0", "pack Z*/Z makes an extended string");
     is(pack("Z*/a", ""), "0\0", "pack Z*/a makes an extended string");
+}
+{
+    # unpack("A*", $unicode) strips general unicode spaces
+    is(unpack("A*", "ab \n\xa0 \0"), "ab \n\xa0", 
+       'normal A* strip leaves \xa0');
+    is(unpack("U0C0A*", "ab \n\xa0 \0"), "ab \n\xa0", 
+       'normal A* strip leaves \xa0 even if it got upgraded for technical 
reasons');
+    is(unpack("A*", pack("a*(U0U)a*", "ab \n", 0xa0, " \0")), "ab",
+       'upgraded strings A* removes \xa0');
+    is(unpack("A*", pack("a*(U0UU)a*", "ab \n", 0xa0, 0x1680, " \0")), "ab",
+       'upgraded strings A* removes all unicode whitespace');
+    is(unpack("A5", pack("a*(U0U)a*", "ab \n", 0x1680, "def", "ab")), "ab",
+       'upgraded strings A5 removes all unicode whitespace');
+    is(unpack("A*", pack("U", 0x1680)), "",
+       'upgraded strings A* with nothing left');
 }