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

[ikiwiki.git] / IkiWiki / Plugin / aggregate.pm

diff --git a/IkiWiki/Plugin/aggregate.pm b/IkiWiki/Plugin/aggregate.pm
index b1b069b006005f179216dfcf76e0cf0dfdbd5159..be2c963694c033d86853278ad7ebdb86b2593093 100644 (file)
--- a/IkiWiki/Plugin/aggregate.pm
+++ b/IkiWiki/Plugin/aggregate.pm
@@ -31,15 +31,16 @@ sub getopt () { #{{{
 } #}}}
 
 sub checkconfig () { #{{{
-       IkiWiki::lockwiki();
+       my $nolock=($config{post_commit} && ! IkiWiki::commit_hook_enabled());
+       IkiWiki::lockwiki() unless $nolock;
        loadstate();
-       if ($config{aggregate}) {
+       if ($config{aggregate} && ! $nolock) {
                IkiWiki::loadindex();
                aggregate();
                expire();
                savestate();
        }
-       IkiWiki::unlockwiki();
+       IkiWiki::unlockwiki() unless $nolock;
 } #}}}
 
 sub filter (@) { #{{{
@@ -228,6 +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 $@;
 
@@ -236,6 +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}));
@@ -243,14 +249,36 @@ sub aggregate () { #{{{
                if (! length $feed->{feedurl}) {
                        my @urls=XML::Feed->find_feeds($feed->{url});
                        if (! @urls) {
-                               $feed->{message}=sprintf(gettext("could not find feed at %s"), $feed->{feedurl});
+                               $feed->{message}=sprintf(gettext("could not find feed at %s"), $feed->{url});
                                $feed->{error}=1;
                                debug($feed->{message});
                                next;
                        }
                        $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;
@@ -269,15 +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;
        }
 } #}}}
 
@@ -318,9 +342,8 @@ sub add_page (@) { #{{{
 
                # Make sure that the file name isn't too long. 
                # NB: This doesn't check for path length limits.
-               eval q{use POSIX};
                my $max=POSIX::pathconf($config{srcdir}, &POSIX::_PC_NAME_MAX);
-               if (defined $max && length(htmlpage($page)) >= $max) {
+               if (defined $max && length(htmlfn($page)) >= $max) {
                        $c="";
                        $page=$feed->{dir}."/item";
                        while (exists $IkiWiki::pagecase{lc $page.$c} ||
@@ -356,7 +379,7 @@ sub add_page (@) { #{{{
        if (ref $feed->{tags}) {
                $template->param(tags => [map { tag => $_ }, @{$feed->{tags}}]);
        }
-       writefile(htmlpage($guid->{page}), $config{srcdir},
+       writefile(htmlfn($guid->{page}), $config{srcdir},
                $template->output);
 
        # Set the mtime, this lets the build process get the right creation
@@ -431,7 +454,11 @@ sub remove_feeds () { #{{{
 sub pagefile ($) { #{{{
        my $page=shift;
 
-       return "$config{srcdir}/".htmlpage($page);
+       return "$config{srcdir}/".htmlfn($page);
+} #}}}
+
+sub htmlfn ($) { #{{{
+       return shift().".html";
 } #}}}
 
 1