--- trunk/PlusPlus.pm 2004/12/05 15:46:10 15 +++ trunk/PlusPlus.pm 2004/12/05 21:06:48 16 @@ -4,10 +4,11 @@ use strict; use warnings; -our $VERSION = '0.06'; +our $VERSION = '0.10'; use Carp; use File::Temp qw/ tempdir /; +use BerkeleyDB; #use YAML; =head1 NAME @@ -222,21 +223,27 @@ my $query = shift || return; $self->finish_update; + $self->_tie_meta_db(DB_RDONLY); my @results; # escape double quotes in query for shell $query =~ s/"/\\"/g; - my $open_cmd = $self->{'search'}." -i ".$self->{'index_dir'}.'/index "'.$query.'" |'; - print STDERR "## search $open_cmd\n" if ($self->{'debug'}); + my $open_cmd = $self->{'search'} . + ' -i ' . $self->{'index_dir'}.'/index' . + ' "' . $query . '"'. + ' |'; + print STDERR "## search: $open_cmd\n" if ($self->{'debug'}); open(SEARCH, $open_cmd) || confess "can't start $open_cmd: $!"; - while() { - next if (/^#/); - chomp; - print STDERR "## $_\n" if ($self->{'debug'}); - my ($rank,$path,$size,$title) = split(/ /,$_,4); + my $l; + while($l = ) { + next if ($l =~ /^#/); + chomp($l); + print STDERR "## $l\n" if ($self->{'debug'}); + my ($rank,$path,$size,$title) = split(/ /,$l,4); + $path =~ s#^\./##; # strip from path push @results, { rank => $rank, path => $path, @@ -252,6 +259,30 @@ return @results; } +=head2 property + +Return stored meta property from result or result path. + + print $i->property('path', 'title'); + print $i->property($res->{'path'}, 'title'); + +=cut + +sub property { + my $self = shift; + + my ($path,$meta) = @_; + + if ($path =~ m/^HASH/) { + $path = $path->{'path'} || confess "can't find path in input data"; + } + + my $val = $self->{'meta_db'}->{"$path-$meta"}; + + print STDERR "## property $path-$meta: ",($val || 'undef'),"\n" if ($self->{'debug'}); + return $val; +} + =head2 finish_update This method will close index. @@ -267,7 +298,7 @@ print STDERR "## finish_update\n" if ($self->{'debug'}); - $self->_close_index; + $self->_close_index && $self->_untie_meta_db; } sub DESTROY { @@ -313,7 +344,9 @@ $opt .= " -s _stopwords_"; } - my $open_cmd = '| '.$self->{'index'}.' '.$opt.' -e "html:*" -i '.$self->{'index_dir'}.'/index -'; + my $index_dir = $self->{'index_dir'} || confess "no index_dir?"; + + my $open_cmd = '| '.$self->{'index'}.' '.$opt.' -e "html:*" -i '.$index_dir.'/index -'; print STDERR "## init_indexer: $open_cmd\n" if ($self->{'debug'}); @@ -321,9 +354,65 @@ chdir $self->{'cwd'} || confess "can't chdir to ".$self->{'cwd'}.": $!"; + $self->_tie_meta_db(DB_CREATE); + return $self->{'_index_fh'}; } +=head2 _tie_meta_db + +Open BerkeleyDB database with meta properties. + + $i->_tie_meta_db(DB_CREATE); + $i->_tie_meta_db(DB_RDONLY); + +} + +=cut + +sub _tie_meta_db { + my $self = shift; + + my $flags = shift || confess "need DB_CREATE or DB_RDONLY"; + + return if ($self->{'_meta_db_flags'} && $self->{'_meta_db_flags'} == $flags); + + print STDERR "## _tie_meta_db($flags)\n" if ($self->{'debug'}); + + $self->_untie_meta_db; + $self->{'_meta_db_flags'} = $flags; + + my $file = $self->{'index_dir'}.'/meta.db'; + + tie %{$self->{'meta_db'}}, "BerkeleyDB::Hash", + -Filename => $file, + -Flags => $flags + or confess "cannot open $file: $! $BerkeleyDB::Error\n" ; + + return 1; +} + +=head2 _untie_meta_db + +Close BerkeleyDB database with meta properties. + + $i->_untie_meta_db + +=cut + +sub _untie_meta_db { + my $self = shift; + + return unless ($self->{'meta_db'}); + + print STDERR "## _untie_meta_db\n" if ($self->{'debug'}); + untie %{$self->{'meta_db'}} || confess "can't untie!"; + undef $self->{'meta_db'}; + undef $self->{'_meta_db_flags'}; + + return 1; +} + =head2 _create_doc Create temporary file and pass it's name to swish++ @@ -351,7 +440,8 @@ $self->_init_indexer; my $path = $self->{'tmp_dir'} || confess "no tmp_dir?"; - $path .= '/' . $arg->{'path'}; + my $id = $arg->{'path'} || confess "no path?"; + $path .= "/$id"; print STDERR "## _create_doc: $path\n" if ($self->{'debug'}); @@ -366,19 +456,22 @@ my $content = $arg->{'meta'}->{$name}; print TMP qq{}; $arg->{'body'} .= " $content" if ($self->{'meta_in_body'}); + $self->{'meta_db'}->{"$id-$name"} = $content; } } - if (defined($arg->{'title'})) { - print TMP '' . ($arg->{'title'} || '') . ''; - $arg->{'body'} .= " ".$arg->{'title'} if ($self->{'meta_in_body'}); + my $title = $arg->{'title'}; + if (defined($title)) { + print TMP "$title"; + $arg->{'body'} .= " $title" if ($self->{'meta_in_body'}); + $self->{'meta_db'}->{"$id-title"} = $title; } print TMP '' . $arg->{'body'} . ''; close(TMP) || confess "can't close tmp file ".$arg->{'path'}.": $!"; - print { $self->{'_index_fh'} } $arg->{'path'}."\n"; + print { $self->{'_index_fh'} } "$id\n"; } =head2 _close_index @@ -398,8 +491,10 @@ print STDERR "## close index\n" if ($self->{'debug'}); - close($self->{'_index_fh'}); + close($self->{'_index_fh'}) || confess "can't close index: $!"; undef $self->{'_index_fh'}; + + return 1; } 1;