You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spamassassin.apache.org by jm...@apache.org on 2005/01/13 07:11:08 UTC

svn commit: r125043 - /spamassassin/trunk/lib/Mail/SpamAssassin/HTML.pm

Author: jm
Date: Wed Jan 12 22:11:06 2005
New Revision: 125043

URL: http://svn.apache.org/viewcvs?view=rev&rev=125043
Log:
avoid annoying uninhibitable 'Parsing of undecoded UTF-8' warnings from HTML::Parser
Modified:
   spamassassin/trunk/lib/Mail/SpamAssassin/HTML.pm

Modified: spamassassin/trunk/lib/Mail/SpamAssassin/HTML.pm
Url: http://svn.apache.org/viewcvs/spamassassin/trunk/lib/Mail/SpamAssassin/HTML.pm?view=diff&rev=125043&p1=spamassassin/trunk/lib/Mail/SpamAssassin/HTML.pm&r1=125042&p2=spamassassin/trunk/lib/Mail/SpamAssassin/HTML.pm&r2=125043
==============================================================================
--- spamassassin/trunk/lib/Mail/SpamAssassin/HTML.pm	(original)
+++ spamassassin/trunk/lib/Mail/SpamAssassin/HTML.pm	Wed Jan 12 22:11:06 2005
@@ -258,9 +258,17 @@
   $text =~ s/ / /g;
 
   # ALWAYS pack it into byte-representation, even if we're using 'use bytes',
-  # since the HTML::Parser object may use Unicode internally.
-  # (bug 1417, maybe)
-  $self->SUPER::parse(pack('C0A*', $text));
+  # since the HTML::Parser object may use Unicode internally. (bug 1417,
+  # maybe).  Also, ignore stupid warning that can't be suppressed: 'Parsing of
+  # undecoded UTF-8 will give garbage when decoding entities at ..'
+  {
+    local $SIG{__WARN__} = sub {
+      warn @_ unless ($_[0] =~ /^Parsing of undecoded UTF-8/);
+    };
+
+    $self->SUPER::parse(pack('C0A*', $text));
+  }
+
   $self->SUPER::eof;
 
   return $self->{text};