########################################################################### # # NULPlug.pm -- Plugin for dummy (.nul) files # # A component of the Greenstone digital library software from the New # Zealand Digital Library Project at the University of Waikato, New # Zealand. # # Copyright (C) 2005 Katherine Don # Copyright (C) 2005 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. # ########################################################################### # NULPlug - a plugin for dummy files # This is a simple Plugin for importing dummy files, along with # their metadata. A fictional document will # be created for every such file, and the metadata added to it. # This is used mainly for the null files resulting from exploding metadata # databases package NULPlug; use BasPlug; use strict; no strict 'refs'; # allow filehandles to be variables and viceversa sub BEGIN { @NULPlug::ISA = ('BasPlug'); } my $arguments = [ { 'name' => "process_exp", 'desc' => "{BasPlug.process_exp}", 'type' => "regexp", 'reqd' => "no", 'deft' => &get_default_process_exp() }, { 'name' => "assoc_field", 'desc' => "{NULPlug.assoc_field}", 'type' => "string", 'deft' => "", 'reqd' => "no" } ]; my $options = { 'name' => "NULPlug", 'desc' => "{NULPlug.desc}", 'abstract' => "no", 'inherits' => "yes", 'args' => $arguments }; sub new { my ($class) = shift (@_); my ($pluginlist,$inputargs,$hashArgOptLists) = @_; push(@$pluginlist, $class); if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});} if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)}; my $self = new BasPlug($pluginlist, $inputargs, $hashArgOptLists); return bless $self, $class; } sub get_default_process_exp { return '(?i)\.nul$'; } # The NULPlug read() function. This function does all the right # things to make general options work for a given plugin. NULPlug # overrides read() because there is no need to read the actual text of # the file in, because the contents of the file is not text... # # # 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 = $self->{'outhandle'}; #check for associate_ext, blocking etc my ($block_status,$filename) = $self->read_block(@_); return $block_status if ((!defined $block_status) || ($block_status==0)); print STDERR "\n" if ($gli); print $outhandle "NULPlug processing \"$filename\"\n" if $self->{'verbosity'} > 1; #if there's a leading directory name, eat it... $file =~ s/^.*[\/\\]//; # create a new document my $doc_obj = new doc ($filename, "indexed_doc"); $doc_obj->set_OIDtype ($processor->{'OIDtype'}, $processor->{'OIDmetadata'}); #$doc_obj->set_OIDtype ("incremental"); $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "Plugin", "$self->{'plugin_type'}"); $doc_obj->add_metadata($doc_obj->get_top_section(), "Source", &ghtml::dmsafe($file)); # set the filename as Source metadata to be consistent with other plugins $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "FileSize", (-s $filename)); my $assoc_field = $self->{'assoc_field'} || "null_file"; $doc_obj->add_metadata ($doc_obj->get_top_section(), $assoc_field, $file); #create an empty text string so we don't break downstream plugins my $text = &gsprintf::lookup_string("{BasPlug.dummy_text}"); # include any metadata passed in from previous plugins my $section = $doc_obj->get_top_section(); $self->extra_metadata ($doc_obj, $section, $metadata); $self->title_fallback($doc_obj,$section,$file); # do plugin specific processing of doc_obj unless (defined ($self->process(\$text, $pluginfo, $base_dir, $file, $metadata, $doc_obj))) { print STDERR "\n" if ($gli); return -1; } # do any automatic metadata extraction $self->auto_extract_metadata ($doc_obj); # add an OID $doc_obj->set_OID(); $doc_obj->add_text($section, $text); # process the document $processor->process($doc_obj); $self->{'num_processed'} ++; return 1; } # NULPlug processing of doc_obj. In practice we don't need to do # anything here because the read function takes care of everything. sub process { my $self = shift (@_); my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj) = @_; my $outhandle = $self->{'outhandle'}; return 1; } 1;