Bug 476305: Clean up and merge HTML filtering code - Patch by Vitaly Fedrushkov ...

diff --git a/Bugzilla/Template.pm b/Bugzilla/Template.pm
index 48cd905084a294b4e17d1e3127211b8fb8d6b4b0..d7ebfc055dcb8ae0814033aaa8382f626b236e02 100644 (file)
--- a/Bugzilla/Template.pm
+++ b/Bugzilla/Template.pm
@@ -641,39 +641,7 @@ sub create {
                       1
                     ],
 
-            # Bug 120030: Override html filter to obscure the '@' in user
-            #             visible strings.
-            # Bug 319331: Handle BiDi disruptions.
-            html => sub {
-                my ($var) = Template::Filters::html_filter(@_);
-                # Obscure '@'.
-                $var =~ s/\@/\@/g;
-                if (Bugzilla->params->{'utf8'}) {
-                    # Remove the following characters because they're
-                    # influencing BiDi:
-                    # --------------------------------------------------------
-                    # |Code  |Name                      |UTF-8 representation|
-                    # |------|--------------------------|--------------------|
-                    # |U+202a|Left-To-Right Embedding   |0xe2 0x80 0xaa      |
-                    # |U+202b|Right-To-Left Embedding   |0xe2 0x80 0xab      |
-                    # |U+202c|Pop Directional Formatting|0xe2 0x80 0xac      |
-                    # |U+202d|Left-To-Right Override    |0xe2 0x80 0xad      |
-                    # |U+202e|Right-To-Left Override    |0xe2 0x80 0xae      |
-                    # --------------------------------------------------------
-                    #
-                    # The following are characters influencing BiDi, too, but
-                    # they can be spared from filtering because they don't
-                    # influence more than one character right or left:
-                    # --------------------------------------------------------
-                    # |Code  |Name                      |UTF-8 representation|
-                    # |------|--------------------------|--------------------|
-                    # |U+200e|Left-To-Right Mark        |0xe2 0x80 0x8e      |
-                    # |U+200f|Right-To-Left Mark        |0xe2 0x80 0x8f      |
-                    # --------------------------------------------------------
-                    $var =~ s/[\x{202a}-\x{202e}]//g;
-                }
-                return $var;
-            },
+            html => \&Bugzilla::Util::html_quote,
 
             html_light => \&Bugzilla::Util::html_light_quote,
 

diff --git a/Bugzilla/Util.pm b/Bugzilla/Util.pm
index b3d5b0eaadba3d3b55d59ec15caa773f698f3ddc..55ec6dcf8ce796d6648b9ac672cdef8006d3b495 100644 (file)
--- a/Bugzilla/Util.pm
+++ b/Bugzilla/Util.pm
@@ -55,6 +55,7 @@ use DateTime::TimeZone;
 use Digest;
 use Email::Address;
 use Scalar::Util qw(tainted);
+use Template::Filters;
 use Text::Wrap;
 
 sub trick_taint {
@@ -81,12 +82,37 @@ sub detaint_signed {
     return (defined($_[0]));
 }
 
+# Bug 120030: Override html filter to obscure the '@' in user
+#             visible strings.
+# Bug 319331: Handle BiDi disruptions.
 sub html_quote {
-    my ($var) = (@_);
-    $var =~ s/\&/\&/g;
-    $var =~ s/</\&lt;/g;
-    $var =~ s/>/\&gt;/g;
-    $var =~ s/\"/\&quot;/g;
+    my ($var) = Template::Filters::html_filter(@_);
+    # Obscure '@'.
+    $var =~ s/\@/\&#64;/g;
+    if (Bugzilla->params->{'utf8'}) {
+        # Remove the following characters because they're
+        # influencing BiDi:
+        # --------------------------------------------------------
+        # |Code  |Name                      |UTF-8 representation|
+        # |------|--------------------------|--------------------|
+        # |U+202a|Left-To-Right Embedding   |0xe2 0x80 0xaa      |
+        # |U+202b|Right-To-Left Embedding   |0xe2 0x80 0xab      |
+        # |U+202c|Pop Directional Formatting|0xe2 0x80 0xac      |
+        # |U+202d|Left-To-Right Override    |0xe2 0x80 0xad      |
+        # |U+202e|Right-To-Left Override    |0xe2 0x80 0xae      |
+        # --------------------------------------------------------
+        #
+        # The following are characters influencing BiDi, too, but
+        # they can be spared from filtering because they don't
+        # influence more than one character right or left:
+        # --------------------------------------------------------
+        # |Code  |Name                      |UTF-8 representation|
+        # |------|--------------------------|--------------------|
+        # |U+200e|Left-To-Right Mark        |0xe2 0x80 0x8e      |
+        # |U+200f|Right-To-Left Mark        |0xe2 0x80 0x8f      |
+        # --------------------------------------------------------
+        $var =~ s/[\x{202a}-\x{202e}]//g;
+    }
     return $var;
 }
 
@@ -745,8 +771,9 @@ be done in the template where possible.
 
 =item C<html_quote($val)>
 
-Returns a value quoted for use in HTML, with &, E<lt>, E<gt>, and E<34> being
-replaced with their appropriate HTML entities.
+Returns a value quoted for use in HTML, with &, E<lt>, E<gt>, E<34> and @ being
+replaced with their appropriate HTML entities.  Also, Unicode BiDi controls are
+deleted.
 
 =item C<html_light_quote($val)>
 

diff --git a/t/007util.t b/t/007util.t
index c0433639bf0c8932dc833891fc9cd64f006faa7f..af36e94acde669319fc8f6507ea3cfb11bff6926 100644 (file)
--- a/t/007util.t
+++ b/t/007util.t
@@ -45,7 +45,7 @@ my $tz = Bugzilla->local_timezone->short_name_for_datetime(DateTime->new(year =>
 # XXX: test taint functions
 
 #html_quote():
-is(html_quote("<lala&>"),"&lt;lala&amp;&gt;",'html_quote');
+is(html_quote("<lala&@>"),"&lt;lala&amp;&#64;&gt;",'html_quote');
 
 #url_quote():
 is(url_quote("<lala&>gaa\"'[]{\\"),"%3Clala%26%3Egaa%22%27%5B%5D%7B%5C",'url_quote');