From: Joey Hess <joey@kitenet.net>
Date: Tue, 14 Sep 2010 19:23:16 +0000 (-0400)
Subject: blogspam: Fix crash when content contained utf-8.
X-Git-Url: https://sipb.mit.edu/gitweb.cgi/ikiwiki.git/commitdiff_plain/e0898ae1a8e64a12c4e47b3f922d6cf1fad4f31c?hp=ad5f4f14f52233148a9ecae2b3e7e0964c6c02ba;ds=sidebyside

blogspam: Fix crash when content contained utf-8.

I also tried setting RPC::XML::ENCODING but that did not prevent the crash,
and it seems that blogspam.net doesn't like getting xml encoded in unicode,
since it mis-flagged comments as spammy that way that are normally allowed
through.
---

diff --git a/IkiWiki/Plugin/blogspam.pm b/IkiWiki/Plugin/blogspam.pm
index 8db3780e8..f0b6cb2a2 100644
--- a/IkiWiki/Plugin/blogspam.pm
+++ b/IkiWiki/Plugin/blogspam.pm
@@ -4,6 +4,7 @@ package IkiWiki::Plugin::blogspam;
 use warnings;
 use strict;
 use IkiWiki 3.00;
+use Encode;
 
 my $defaulturl='http://test.blogspam.net:8888/';
 
@@ -68,6 +69,7 @@ sub checkcontent (@) {
 
 	my $url=$defaulturl;
 	$url = $config{blogspam_server} if exists $config{blogspam_server};
+
 	my $client = RPC::XML::Client->new($url);
 
 	my @options = split(",", $config{blogspam_options})
@@ -90,12 +92,12 @@ sub checkcontent (@) {
 
 	my %req=(
 		ip => $session->remote_addr(),
-		comment => defined $params{diff} ? $params{diff} : $params{content},
-		subject => defined $params{subject} ? $params{subject} : "",
-		name => defined $params{author} ? $params{author} : "",
-		link => exists $params{url} ? $params{url} : "",
+		comment => encode_utf8(defined $params{diff} ? $params{diff} : $params{content}),
+		subject => encode_utf8(defined $params{subject} ? $params{subject} : ""),
+		name => encode_utf8(defined $params{author} ? $params{author} : ""),
+		link => encode_utf8(exists $params{url} ? $params{url} : ""),
 		options => join(",", @options),
-		site => $config{url},
+		site => encode_utf8($config{url}),
 		version => "ikiwiki ".$IkiWiki::version,
 	);
 	my $res = $client->send_request('testComment', \%req);
diff --git a/debian/changelog b/debian/changelog
index 8b127b574..0eb5810d0 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -18,6 +18,7 @@ ikiwiki (3.20100832) UNRELEASED; urgency=low
   * actiontabs: Improve tab padding.
   * blueview: Fix display of links to translated pages in the page header.
   * Set isPermaLink="no" for guids in rss feeds. 
+  * blogspam: Fix crash when content contained utf-8.
 
  -- Joey Hess <joeyh@debian.org>  Tue, 07 Sep 2010 12:08:05 -0400
 
diff --git a/doc/bugs/blog_spam_plugin_not_allowing_non-ASCII_chars__63__.mdwn b/doc/bugs/blog_spam_plugin_not_allowing_non-ASCII_chars__63__.mdwn
index 22242a97f..265040d67 100644
--- a/doc/bugs/blog_spam_plugin_not_allowing_non-ASCII_chars__63__.mdwn
+++ b/doc/bugs/blog_spam_plugin_not_allowing_non-ASCII_chars__63__.mdwn
@@ -8,3 +8,8 @@ This seems to happen because I had a non-ASCII character in the comment (an elli
 The interesting part is that the comment preview works fine, just the save fails. Probably
 this means that the blogspam plugin is the culprit (hence the error in RPC::XML::Client library).
 I'm using version 3.20100815~bpo50+. Thanks!
+
+> I've filed an upstream bug about this on RPC::XML:
+> <https://rt.cpan.org/Ticket/Display.html?id=61333>
+> 
+> Worked around it in blogspam by decoding. --[[Joey]]