X-Git-Url: http://git.vanrenterghem.biz/git.ikiwiki.info.git/blobdiff_plain/d4c61b72813b880d86b316770f2e3819a6428202..e5f1688ac39d9a3e0e63a8683105677af2dc4c1c:/IkiWiki/Plugin/aggregate.pm diff --git a/IkiWiki/Plugin/aggregate.pm b/IkiWiki/Plugin/aggregate.pm index a6f850236..0da527f25 100644 --- 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; @@ -17,7 +17,7 @@ my %guids; sub import { #{{{ hook(type => "getopt", id => "aggregate", call => \&getopt); hook(type => "checkconfig", id => "aggregate", call => \&checkconfig); - hook(type => "filter", id => "aggregate", call => \&filter); + hook(type => "needsbuild", id => "aggregate", call => \&needsbuild); hook(type => "preprocess", id => "aggregate", call => \&preprocess); hook(type => "delete", id => "aggregate", call => \&delete); hook(type => "savestate", id => "aggregate", call => \&savestate); @@ -31,26 +31,36 @@ sub getopt () { #{{{ } #}}} 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}; - - # Mark all feeds originating on this page as removable; - # preprocess will unmark those that still exist. - remove_feeds($page); +sub needsbuild (@) { #{{{ + my $needsbuild=shift; + + loadstate(); # if not already loaded - return $params{content}; + foreach my $feed (values %feeds) { + if (grep { $_ eq $pagesources{$feed->{sourcepage}} } @$needsbuild) { + # Mark all feeds originating on this page as removable; + # preprocess will unmark those that still exist. + remove_feeds($feed->{sourcepage}); + } + } } # }}} sub preprocess (@) { #{{{ @@ -58,7 +68,7 @@ sub preprocess (@) { #{{{ 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)."]]"; } } @@ -116,10 +126,13 @@ sub delete (@) { #{{{ } } #}}} +my $state_loaded=0; sub loadstate () { #{{{ + return if $state_loaded; + $state_loaded=1; if (-e "$config{wikistatedir}/aggregate") { - open (IN, "$config{wikistatedir}/aggregate" || - die "$config{wikistatedir}/aggregate: $!"); + open(IN, "$config{wikistatedir}/aggregate") || + die "$config{wikistatedir}/aggregate: $!"; while () { $_=IkiWiki::possibly_foolish_untaint($_); chomp; @@ -151,11 +164,10 @@ sub loadstate () { #{{{ } #}}} sub savestate () { #{{{ + return unless $state_loaded; eval q{use HTML::Entities}; error($@) if $@; 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 $data (values %feeds, values %guids) { @@ -168,7 +180,8 @@ sub savestate () { #{{{ } } else { - unlink pagefile($data->{page}); + unlink pagefile($data->{page}) + if exists $data->{page}; } next; } @@ -198,10 +211,17 @@ 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}; my $count=0; + my %seen; foreach my $item (sort { $IkiWiki::pagectime{$b->{page}} <=> $IkiWiki::pagectime{$a->{page}} } grep { exists $_->{page} && $_->{feed} eq $feed->{name} && $IkiWiki::pagectime{$_->{page}} } values %guids) { @@ -209,7 +229,7 @@ sub expire () { #{{{ my $days_old = (time - $IkiWiki::pagectime{$item->{page}}) / 60 / 60 / 24; if ($days_old > $feed->{expireage}) { debug(sprintf(gettext("expiring %s (%s days old)"), - $item->{page}, $days_old)); + $item->{page}, int($days_old))); $item->{expired}=1; } } @@ -219,7 +239,10 @@ sub expire () { #{{{ $item->{expired}=1; } else { - $count++; + if (! $seen{$item->{page}}) { + $seen{$item->{page}}=1; + $count++; + } } } } @@ -228,6 +251,8 @@ sub expire () { #{{{ sub aggregate () { #{{{ eval q{use XML::Feed}; error($@) if $@; + eval q{use URI::Fetch}; + error($@) if $@; eval q{use HTML::Entities}; error($@) if $@; @@ -236,6 +261,9 @@ 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 +271,43 @@ 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); + $f=eval{XML::Feed->parse(\$content)}; + } + if ($@) { + # Another possibility is badly escaped entities. + $feed->{message}.=" ".sprintf(gettext("(feed entities escaped)")); + $content=~s/\&(?!amp)(\w+);/&$1;/g; + $content=Encode::decode_utf8($content); + $f=eval{XML::Feed->parse(\$content)}; + } if ($@) { $feed->{message}=gettext("feed crashed XML::Feed!")." ($@)"; $feed->{error}=1; @@ -267,17 +324,14 @@ sub aggregate () { #{{{ foreach my $entry ($f->entries) { add_page( feed => $feed, + copyright => $f->copyright, 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 +372,8 @@ 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} || @@ -351,17 +404,20 @@ sub add_page (@) { #{{{ $template->param(content => htmlescape(htmlabs($params{content}, $feed->{feedurl}))); $template->param(name => $feed->{name}); $template->param(url => $feed->{url}); + $template->param(copyright => $params{copyright}) + if defined $params{copyright} && length $params{copyright}; $template->param(permalink => urlabs($params{link}, $feed->{feedurl})) if defined $params{link}; 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 # time on record for the new page. - utime $mtime, $mtime, pagefile($guid->{page}) if defined $mtime; + utime $mtime, $mtime, pagefile($guid->{page}) + if defined $mtime && $mtime <= time; } #}}} sub htmlescape ($) { #{{{ @@ -431,7 +487,11 @@ sub remove_feeds () { #{{{ sub pagefile ($) { #{{{ my $page=shift; - return "$config{srcdir}/".htmlpage($page); + return "$config{srcdir}/".htmlfn($page); +} #}}} + +sub htmlfn ($) { #{{{ + return shift().".".$config{htmlext}; } #}}} 1