use warnings;
use strict;
-use IkiWiki;
+use IkiWiki 2.00;
use HTML::Entities;
use HTML::Parser;
use HTML::Tagset;
} #}}}
sub checkconfig () { #{{{
- IkiWiki::lockwiki();
- loadstate();
- if ($config{aggregate}) {
+ if ($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();
} #}}}
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);
foreach my $required (qw{name url}) {
if (! exists $params{$required}) {
- return "[[".sprintf(gettext("aggregate plugin missing %s parameter"), $required)."]]";
+ return "[[aggregate ".sprintf(gettext("missing %s parameter"), $required)."]]";
}
}
}
} #}}}
+my $state_loaded=0;
sub loadstate () { #{{{
+ return if $state_loaded;
if (-e "$config{wikistatedir}/aggregate") {
- open (IN, "$config{wikistatedir}/aggregate" ||
- die "$config{wikistatedir}/aggregate: $!");
+ open(IN, "$config{wikistatedir}/aggregate") ||
+ die "$config{wikistatedir}/aggregate: $!";
while (<IN>) {
$_=IkiWiki::possibly_foolish_untaint($_);
chomp;
}
close IN;
+
+ $state_loaded=1;
}
} #}}}
sub savestate () { #{{{
eval q{use HTML::Entities};
error($@) if $@;
- open (OUT, ">$config{wikistatedir}/aggregate" ||
- die "$config{wikistatedir}/aggregate: $!");
+ my $newfile="$config{wikistatedir}/aggregate.new";
+ # TODO: This cleanup function could use improvement. Any newly
+ # aggregated files are left behind unrecorded, and should be deleted.
+ my $cleanup = sub { unlink($newfile) };
+ open (OUT, ">$newfile") || error("open $newfile: $!", $cleanup);
foreach my $data (values %feeds, values %guids) {
if ($data->{remove}) {
if ($data->{name}) {
push @line, "$field=".$data->{$field};
}
}
- print OUT join(" ", @line)."\n";
+ print OUT join(" ", @line)."\n" || error("write $newfile: $!", $cleanup);
}
- close OUT;
+ close OUT || error("save $newfile: $!", $cleanup);
+ rename($newfile, "$config{wikistatedir}/aggregate") ||
+ error("rename $newfile: $!", $cleanup);
+} #}}}
+
+sub clearstate () { #{{{
+ %feeds=();
+ %guids=();
+ $state_loaded=0;
} #}}}
sub expire () { #{{{
sub aggregate () { #{{{
eval q{use XML::Feed};
error($@) if $@;
+ eval q{use URI::Fetch};
+ error($@) if $@;
eval q{use HTML::Entities};
error($@) if $@;
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}));
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;
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,
);
}
-
- $feed->{message}=sprintf(gettext("processed ok at "),
- displaytime($feed->{lastupdate}));
- $feed->{error}=0;
}
} #}}}
-e pagefile($page.$c)) {
$c++
}
+
+ # Make sure that the file name isn't too long.
+ # NB: This doesn't check for path length limits.
+ my $max=POSIX::pathconf($config{srcdir}, &POSIX::_PC_NAME_MAX);
+ if (defined $max && length(htmlfn($page)) >= $max) {
+ $c="";
+ $page=$feed->{dir}."/item";
+ while (exists $IkiWiki::pagecase{lc $page.$c} ||
+ -e pagefile($page.$c)) {
+ $c++
+ }
+ }
+
$guid->{page}=$page;
debug(sprintf(gettext("creating new page %s"), $page));
}
if (ref $feed->{tags}) {
$template->param(tags => [map { tag => $_ }, @{$feed->{tags}}]);
}
- writefile(htmlpage($guid->{page}), $config{srcdir},
+ writefile(htmlfn($guid->{page}), $config{srcdir},
$template->output);
# Set the mtime, this lets the build process get the right creation
sub pagefile ($) { #{{{
my $page=shift;
- return "$config{srcdir}/".htmlpage($page);
+ return "$config{srcdir}/".htmlfn($page);
+} #}}}
+
+sub htmlfn ($) { #{{{
+ return shift().".".$config{htmlext};
} #}}}
1