########################################################################### # # ArchivesInfPlugin.pm -- # A component of the Greenstone digital library software # from the New Zealand Digital Library Project at the # University of Waikato, New Zealand. # # Copyright (C) 1999 New Zealand Digital Library Project # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. # ########################################################################### # plugin which recurses through an archives.inf file # (i.e. the file generated in the archives directory # when an import is done), processing each file it finds # 12-05-02 Added usage datastructure - John Thompson package ArchivesInfPlugin; use util; use AbstractPlugin; use plugin; use arcinfo; use gsprintf; use strict; no strict 'refs'; # allow filehandles to be variables and viceversa BEGIN { @ArchivesInfPlugin::ISA = ('AbstractPlugin'); } my $arguments = [ ]; my $options = { 'name' => "ArchivesInfPlugin", 'desc' => "{ArchivesInfPlugin.desc}", 'abstract' => "no", 'inherits' => "yes" }; sub gsprintf { return &gsprintf::gsprintf(@_); } sub new { my ($class) = shift (@_); my ($pluginlist,$inputargs,$hashArgOptLists) = @_; push(@$pluginlist, $class); push(@{$hashArgOptLists->{"ArgList"}},@{$arguments}); push(@{$hashArgOptLists->{"OptList"}},$options); my $self = new AbstractPlugin($pluginlist, $inputargs, $hashArgOptLists); return bless $self, $class; } sub deinit { my ($self) = @_; my $archive_info = $self->{'archive_info'}; if (defined $archive_info) { my $archive_info_filename = $self->{'archive_info_filename'}; my $file_list = $archive_info->get_file_list(); # change each file to "Been Indexed" foreach my $subfile (@$file_list) { my $doc_oid = $subfile->[1]; # why do we get this when it is not used??? my $index_status = $archive_info->get_status_info($doc_oid); $archive_info->set_status_info($doc_oid,"B"); } $archive_info->save_info($archive_info_filename); } } # return 1 if this class might recurse using $pluginfo sub is_recursive { my $self = shift (@_); return 1; } # return number of files processed, undef if can't process # Note that $base_dir might be "" and that $file might # include directories sub read { my $self = shift (@_); my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs,$total_count, $gli) = @_; my $outhandle = $self->{'outhandle'}; my $count = 0; # see if this has a archives information file within it my $archive_info_filename = &util::filename_cat($base_dir,$file,"archives.inf"); if (-e $archive_info_filename) { # found an archives.inf file &gsprintf($outhandle, "ArchivesInfPlugin: {common.processing} $archive_info_filename\n") if $self->{'verbosity'} > 1; # read in the archives information file my $archive_info = new arcinfo (); $self->{'archive_info'} = $archive_info; $self->{'archive_info_filename'} = $archive_info_filename; $archive_info->load_info ($archive_info_filename); my $file_list = $archive_info->get_file_list(); # process each file foreach my $subfile (@$file_list) { last if ($maxdocs != -1 && ($total_count + $count) >= $maxdocs); my $tmp = &util::filename_cat ($file, $subfile->[0]); next if $tmp eq $file; # We always process the file... my $process_file = 1; # ...unless the build processor is incremental capable and -incremental was specified if ($processor->is_incremental_capable() && $self->{'incremental'}) { # We don't need to process the file if it has already been built my $doc_oid = $subfile->[1]; my $index_status = $archive_info->get_status_info($doc_oid); if ($index_status eq "B") { # Don't process this file $process_file = 0; } } if ($process_file) { # note: metadata is not carried on to the next level $count += &plugin::read ($pluginfo, $base_dir, $tmp, {}, $processor, $maxdocs, ($total_count+$count), $gli); } } return $count; } # wasn't an archives directory, someone else will have to process it return undef; } 1;