the 100% correct way is to add it to %links on scan

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

diff --git a/IkiWiki/Plugin/aggregate.pm b/IkiWiki/Plugin/aggregate.pm
index bb5edfa65ca5a261ed804f52e55f04abb493eb52..eb5067d9f5977cafea958e6e5849c4fd866a34c1 100644 (file)
--- a/IkiWiki/Plugin/aggregate.pm
+++ b/IkiWiki/Plugin/aggregate.pm
@@ -4,7 +4,7 @@ package IkiWiki::Plugin::aggregate;
 
 use warnings;
 use strict;
-use IkiWiki;
+use IkiWiki 2.00;
 use HTML::Entities;
 use HTML::Parser;
 use HTML::Tagset;
@@ -31,22 +31,29 @@ sub getopt () { #{{{
 } #}}}
 
 sub checkconfig () { #{{{
-       my $nolock=($config{post_commit} && ! IkiWiki::commit_hook_enabled());
-       IkiWiki::lockwiki() unless $nolock;
-       loadstate();
-       if ($config{aggregate} && ! $nolock) {
+       if ($config{aggregate} && ! ($config{post_commit} && 
+                                    IkiWiki::commit_hook_enabled())) {
+               if (! IkiWiki::lockwiki(0)) {
+                       debug("wiki is locked by another process, not aggregating");
+                       exit 1;
+               }
+       
+               loadstate();
                IkiWiki::loadindex();
                aggregate();
                expire();
                savestate();
+               clearstate();
+
+               IkiWiki::unlockwiki();
        }
-       IkiWiki::unlockwiki() unless $nolock;
 } #}}}
 
 sub filter (@) { #{{{
        my %params=@_;
        my $page=$params{page};
 
+       loadstate(); # if not already loaded
        # Mark all feeds originating on this page as removable;
        # preprocess will unmark those that still exist.
        remove_feeds($page);
@@ -117,7 +124,9 @@ sub delete (@) { #{{{
        }
 } #}}}
 
+my $state_loaded=0;
 sub loadstate () { #{{{
+       return if $state_loaded;
        if (-e "$config{wikistatedir}/aggregate") {
                open (IN, "$config{wikistatedir}/aggregate" ||
                        die "$config{wikistatedir}/aggregate: $!");
@@ -148,6 +157,8 @@ sub loadstate () { #{{{
                }
 
                close IN;
+               
+               $state_loaded=1;
        }
 } #}}}
 
@@ -199,6 +210,12 @@ sub savestate () { #{{{
                error("rename $newfile: $!", $cleanup);
 } #}}}
 
+sub clearstate () { #{{{
+       %feeds=();
+       %guids=();
+       $state_loaded=0;
+} #}}}
+
 sub expire () { #{{{
        foreach my $feed (values %feeds) {
                next unless $feed->{expireage} || $feed->{expirecount};
@@ -229,6 +246,8 @@ sub expire () { #{{{
 sub aggregate () { #{{{
        eval q{use XML::Feed};
        error($@) if $@;
+       eval q{use URI::Fetch};
+       error($@) if $@;
        eval q{use HTML::Entities};
        error($@) if $@;
 
@@ -237,6 +256,9 @@ 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 +273,29 @@ 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 +314,11 @@ 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;
        }
 } #}}}
 
@@ -319,7 +359,6 @@ 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 $max && length(htmlfn($page)) >= $max) {
                        $c="";
@@ -432,7 +471,7 @@ sub remove_feeds () { #{{{
 sub pagefile ($) { #{{{
        my $page=shift;
 
-       return "$config{srcdir}/".htmlpage($page);
+       return "$config{srcdir}/".htmlfn($page);
 } #}}}
 
 sub htmlfn ($) { #{{{