* Fix aggregator to not warn when a feed contains no body content at all.

* Work around bug #420636 by, if XML::Parser crashes, running the feed
  content though Encode::decode_utf8.

4 files changed, 53 insertions, 10 deletions

diff --git a/IkiWiki/Plugin/aggregate.pm b/IkiWiki/Plugin/aggregate.pm
index 2295691aa..be2c96369 100644
--- a/IkiWiki/Plugin/aggregate.pm
+++ b/IkiWiki/Plugin/aggregate.pm
@@ -229,6 +229,8 @@ sub expire () { #{{{
 sub aggregate () { #{{{
 	eval q{use XML::Feed};
 	error($@) if $@;
+	eval q{use URI::Fetch};
+	error($@) if $@;
 	eval q{use HTML::Entities};
 	error($@) if $@;
 
@@ -237,6 +239,9 @@ sub aggregate () { #{{{
 			time - $feed->{lastupdate} >= $feed->{updateinterval};
 		$feed->{lastupdate}=time;
 		$feed->{newposts}=0;
+		$feed->{message}=sprintf(gettext("processed ok at %s"),
+			displaytime($feed->{lastupdate}));
+		$feed->{error}=0;
 		$IkiWiki::forcerebuild{$feed->{sourcepage}}=1;
 
 		debug(sprintf(gettext("checking feed %s ..."), $feed->{name}));
@@ -251,7 +256,29 @@ sub aggregate () { #{{{
 			}
 			$feed->{feedurl}=pop @urls;
 		}
-		my $f=eval{XML::Feed->parse(URI->new($feed->{feedurl}))};
+		my $res=URI::Fetch->fetch($feed->{feedurl});
+		if (! $res) {
+			$feed->{message}=URI::Fetch->errstr;
+			$feed->{error}=1;
+			debug($feed->{message});
+			next;
+		}
+		if ($res->status == URI::Fetch::URI_GONE()) {
+			$feed->{message}=gettext("feed not found");
+			$feed->{error}=1;
+			debug($feed->{message});
+			next;
+		}
+		my $content=$res->content;
+		my $f=eval{XML::Feed->parse(\$content)};
+		if ($@) {
+			# One common cause of XML::Feed crashing is a feed
+			# that contains invalid UTF-8 sequences. Convert
+			# feed to ascii to try to work around.
+			$feed->{message}=sprintf(gettext("invalid UTF-8 stripped from feed"));
+			$content=Encode::decode_utf8($content);
+			$f=eval{XML::Feed->parse(\$content)};
+		}
 		if ($@) {
 			$feed->{message}=gettext("feed crashed XML::Feed!")." ($@)";
 			$feed->{error}=1;
@@ -270,15 +297,11 @@ sub aggregate () { #{{{
 				feed => $feed,
 				title => defined $entry->title ? decode_entities($entry->title) : "untitled",
 				link => $entry->link,
-				content => $entry->content->body,
+				content => defined $entry->content->body ? $entry->content->body : "",
 				guid => defined $entry->id ? $entry->id : time."_".$feed->name,
 				ctime => $entry->issued ? ($entry->issued->epoch || time) : time,
 			);
 		}
-
-		$feed->{message}=sprintf(gettext("processed ok at %s"),
-			displaytime($feed->{lastupdate}));
-		$feed->{error}=0;
 	}
 } #}}}
 
diff --git a/debian/changelog b/debian/changelog
index e4b0fc75f..7822a4eb0 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -5,8 +5,11 @@ ikiwiki (1.51) UNRELEASED; urgency=low
   * Minor template improvements by Alessandro.
   * In mercurial backend, untaint ipaddr when using it as the user for the
     commit. Thanks, Alexander Wirt. Closes: #420428
+  * Fix aggregator to not warn when a feed contains no body content at all.
+  * Work around bug #420636 by, if XML::Parser crashes, running the feed
+    content though Encode::decode_utf8.
 
- -- Joey Hess <joeyh@debian.org>  Sun, 22 Apr 2007 13:43:49 -0400
+ -- Joey Hess <joeyh@debian.org>  Mon, 23 Apr 2007 14:31:57 -0400
 
 ikiwiki (1.50) unstable; urgency=low
 
diff --git a/doc/bugs/aggregate_plugin_errors.mdwn b/doc/bugs/aggregate_plugin_errors.mdwn
index 5d8b34f53..57a9869f0 100644
--- a/doc/bugs/aggregate_plugin_errors.mdwn
+++ b/doc/bugs/aggregate_plugin_errors.mdwn
@@ -13,7 +13,21 @@ When I run ikiwiki with "--aggregate" I get this error:
     Use of uninitialized value in subroutine entry at /usr/share/perl5/IkiWiki/Plugin/aggregate.pm line 414.
     Use of uninitialized value in subroutine entry at /usr/share/perl5/IkiWiki/Plugin/aggregate.pm line 414.
 
-Also, feeds from DokuWiki seem to crash the aggregate plugin completely, it's not a completely valid feed but presumably crashing is still bad.  The feed I'm seeing this with is http://www.wirelesscommons.org/feed.php
+> Fixed, this occurred when a feed did not include any body content tag.
+> --[[Joey]]
+
+Also, feeds from DokuWiki seem to crash the aggregate plugin completely,
+it's not a completely valid feed but presumably crashing is still bad.  The
+feed I'm seeing this with is http://www.wirelesscommons.org/feed.php
+
+> This is a bug in XML::Parser. Unfortunately, perl does not have a feed
+> parser that handles invalid feeds, and in particular, XML::Parser has
+> issues with feeds that claim to be encoded in utf-8 and contain invalid
+> utf sequences, as well as other encoding issues. See also [[debbug 380426]].
+> Note though that this invalid feed does not really crash the aggregate plugin,
+> it just notes that XML::Parser crashed on it and continues. This is the
+> best I can do in ikiwiki. I have filed a bug on XML::Parser about this,
+> it's [[debbug 420636]].  I've also put in a workaround, so [[done]].
 
     -- System Information:
     Debian Release: 3.1
@@ -43,4 +57,4 @@ Also, feeds from DokuWiki seem to crash the aggregate plugin completely, it's no
 
 
 Cheers,
---[[AdamShand]]
\ No newline at end of file
+--[[AdamShand]]
diff --git a/doc/bugs/aggregate_plugin_errors/discussion.mdwn b/doc/bugs/aggregate_plugin_errors/discussion.mdwn
index 691195595..3425b6d16 100644
--- a/doc/bugs/aggregate_plugin_errors/discussion.mdwn
+++ b/doc/bugs/aggregate_plugin_errors/discussion.mdwn
@@ -1,3 +1,6 @@
 I have the same problem here when I use a feed from googles shared feed. http://www.google.com/reader/public/atom/user/04715560304044435944/state/com.google/broadcast
 
-john
\ No newline at end of file
+john
+
+> I cannot reproduce any problem with this feed. Can you provide details?
+> --[[Joey]]