On Friday 27 April 2007 22:29:03 you wrote:
> Ismail Dönmez <ismail@xxxxxxxxxxxxx> writes:
> >> Which means that there is something else going on. Your change
> >> may fix what you observed (I do not doubt that it fixed what you
> >> observed for you), but without understanding what really is
> >> going on (iow, why it is a fix, when the documentation clearly
> >> indicates they should be equivalent and it should not fix
> >> anything), we cannot tell what *ELSE* we are breaking with this
> >> change.
> >
> > That might be a bug in Encode itself indeed, I will dig a bit more.
> > Thanks.
>
> Thanks.
Ok found out the reason. decode() tries to decode data that is already UTF-8
and borks.
This is from Encode.pm :
sub decode_utf8($;$) {
my ( $str, $check ) = @_;
return $str if is_utf8($str); <--- Checks if the $str is already UTF-8
if ($check) {
return decode( "utf8", $str, $check ); <--- Else do what gitweb does
[...]
So my patch is indeed correct. I attach it again for reference. Can it be
please applied?
Regards,
ismail
--- gitweb/gitweb.perl 2007-04-24 16:53:00.000000000 +0300
+++ gitweb/gitweb.perl 2007-04-24 16:54:22.000000000 +0300
@@ -566,12 +566,6 @@
return $input;
}
-# very thin wrapper for decode("utf8", $str, Encode::FB_DEFAULT);
-sub to_utf8 {
- my $str = shift;
- return decode("utf8", $str, Encode::FB_DEFAULT);
-}
-
# quote unsafe chars, but keep the slash, even when it's not
# correct, but quoted slashes look too horrible in bookmarks
sub esc_param {
@@ -596,7 +590,7 @@
my $str = shift;
my %opts = @_;
- $str = to_utf8($str);
+ $str = decode_utf8($str);
$str = $cgi->escapeHTML($str);
if ($opts{'-nbsp'}) {
$str =~ s/ / /g;
@@ -610,7 +604,7 @@
my $str = shift;
my %opts = @_;
- $str = to_utf8($str);
+ $str = decode_utf8($str);
$str = $cgi->escapeHTML($str);
if ($opts{'-nbsp'}) {
$str =~ s/ / /g;
@@ -893,7 +887,7 @@
if (length($short) < length($long)) {
return $cgi->a({-href => $href, -class => "list subject",
- -title => to_utf8($long)},
+ -title => decode_utf8($long)},
esc_html($short) . $extra);
} else {
return $cgi->a({-href => $href, -class => "list subject"},
@@ -1110,7 +1104,7 @@
if (check_export_ok("$projectroot/$path")) {
my $pr = {
path => $path,
- owner => to_utf8($owner),
+ owner => decode_utf8($owner),
};
push @list, $pr
}
@@ -1139,7 +1133,7 @@
$pr = unescape($pr);
$ow = unescape($ow);
if ($pr eq $project) {
- $owner = to_utf8($ow);
+ $owner = decode_utf8($ow);
last;
}
}
@@ -1613,7 +1607,7 @@
}
my $owner = $gcos;
$owner =~ s/[,;].*$//;
- return to_utf8($owner);
+ return decode_utf8($owner);
}
## ......................................................................
@@ -1696,7 +1690,7 @@
my $title = "$site_name";
if (defined $project) {
- $title .= " - " . to_utf8($project);
+ $title .= " - " . decode_utf8($project);
if (defined $action) {
$title .= "/$action";
if (defined $file_name) {
@@ -1969,7 +1963,7 @@
print "<div class=\"page_path\">";
print $cgi->a({-href => href(action=>"tree", hash_base=>$hb),
- -title => 'tree root'}, to_utf8("[$project]"));
+ -title => 'tree root'}, decode_utf8("[$project]"));
print " / ";
if (defined $name) {
my @dirname = split '/', $name;
@@ -2584,7 +2578,7 @@
($pr->{'age'}, $pr->{'age_string'}) = @aa;
if (!defined $pr->{'descr'}) {
my $descr = git_get_project_description($pr->{'path'}) || "";
- $pr->{'descr_long'} = to_utf8($descr);
+ $pr->{'descr_long'} = decode_utf8($descr);
$pr->{'descr'} = chop_str($descr, 25, 5);
}
if (!defined $pr->{'owner'}) {
@@ -3616,7 +3610,7 @@
$hash = git_get_head_hash($project);
}
- my $filename = to_utf8(basename($project)) . "-$hash.tar.$suffix";
+ my $filename = decode_utf8(basename($project)) . "-$hash.tar.$suffix";
print $cgi->header(
-type => "application/$ctype",