1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # NULPlug.pm -- Plugin for dummy (.nul) files
|
---|
4 | #
|
---|
5 | # A component of the Greenstone digital library software from the New
|
---|
6 | # Zealand Digital Library Project at the University of Waikato, New
|
---|
7 | # Zealand.
|
---|
8 | #
|
---|
9 | # Copyright (C) 2005 Katherine Don
|
---|
10 | # Copyright (C) 2005 New Zealand Digital Library Project
|
---|
11 | #
|
---|
12 | # This program is free software; you can redistribute it and/or modify
|
---|
13 | # it under the terms of the GNU General Public License as published by
|
---|
14 | # the Free Software Foundation; either version 2 of the License, or
|
---|
15 | # (at your option) any later version.
|
---|
16 | #
|
---|
17 | # This program is distributed in the hope that it will be useful, but
|
---|
18 | # WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
19 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
---|
20 | # General Public License for more details.
|
---|
21 | #
|
---|
22 | # You should have received a copy of the GNU General Public License
|
---|
23 | # along with this program; if not, write to the Free Software
|
---|
24 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
25 | #
|
---|
26 | ###########################################################################
|
---|
27 |
|
---|
28 | # NULPlug - a plugin for dummy files
|
---|
29 |
|
---|
30 | # This is a simple Plugin for importing dummy files, along with
|
---|
31 | # their metadata. A fictional document will
|
---|
32 | # be created for every such file, and the metadata added to it.
|
---|
33 |
|
---|
34 | # This is used mainly for the null files resulting from exploding metadata
|
---|
35 | # databases
|
---|
36 |
|
---|
37 | package NULPlug;
|
---|
38 |
|
---|
39 | use BasPlug;
|
---|
40 |
|
---|
41 | use strict;
|
---|
42 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
43 |
|
---|
44 | sub BEGIN {
|
---|
45 | @NULPlug::ISA = ('BasPlug');
|
---|
46 | }
|
---|
47 |
|
---|
48 | my $arguments =
|
---|
49 | [
|
---|
50 | { 'name' => "assoc_field",
|
---|
51 | 'desc' => "{NULPlug.assoc_field}",
|
---|
52 | 'type' => "string",
|
---|
53 | 'deft' => "",
|
---|
54 | 'reqd' => "no" }
|
---|
55 | ];
|
---|
56 |
|
---|
57 | my $options = { 'name' => "NULPlug",
|
---|
58 | 'desc' => "{NULPlug.desc}",
|
---|
59 | 'abstract' => "no",
|
---|
60 | 'inherits' => "yes",
|
---|
61 | 'args' => $arguments };
|
---|
62 |
|
---|
63 |
|
---|
64 | sub new {
|
---|
65 | my ($class) = shift (@_);
|
---|
66 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
67 | push(@$pluginlist, $class);
|
---|
68 |
|
---|
69 | if(defined $arguments){ push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});}
|
---|
70 | if(defined $options) { push(@{$hashArgOptLists->{"OptList"}},$options)};
|
---|
71 |
|
---|
72 | my $self = (defined $hashArgOptLists)? new BasPlug($pluginlist,$inputargs,$hashArgOptLists): new BasPlug($pluginlist,$inputargs);
|
---|
73 |
|
---|
74 | return bless $self, $class;
|
---|
75 | }
|
---|
76 |
|
---|
77 | sub get_default_process_exp {
|
---|
78 | return '(?i)\.nul$';
|
---|
79 | }
|
---|
80 |
|
---|
81 | # The NULPlug read() function. This function does all the right
|
---|
82 | # things to make general options work for a given plugin. NULPlug
|
---|
83 | # overrides read() because there is no need to read the actual text of
|
---|
84 | # the file in, because the contents of the file is not text...
|
---|
85 | #
|
---|
86 | #
|
---|
87 | # Return number of files processed, undef if can't process
|
---|
88 | #
|
---|
89 | # Note that $base_dir might be "" and that $file might include directories
|
---|
90 |
|
---|
91 | sub read {
|
---|
92 | my $self = shift (@_);
|
---|
93 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
---|
94 |
|
---|
95 | my $outhandle = $self->{'outhandle'};
|
---|
96 |
|
---|
97 | # Make sure we're processing the correct file
|
---|
98 | my $filename = &util::filename_cat($base_dir, $file);
|
---|
99 | return 0 if $self->{'block_exp'} ne "" && $filename =~ /$self->{'block_exp'}/;
|
---|
100 | if ($filename !~ /$self->{'process_exp'}/ || !-f $filename) {
|
---|
101 | return undef;
|
---|
102 | }
|
---|
103 | print STDERR "<Processing n='$file' p='NULPlug'>\n" if ($gli);
|
---|
104 | print $outhandle "NULPlug processing \"$filename\"\n"
|
---|
105 | if $self->{'verbosity'} > 1;
|
---|
106 |
|
---|
107 | #if there's a leading directory name, eat it...
|
---|
108 | $file =~ s/^.*[\/\\]//;
|
---|
109 |
|
---|
110 | # create a new document
|
---|
111 | my $doc_obj = new doc ($filename, "indexed_doc");
|
---|
112 | $doc_obj->set_OIDtype ($processor->{'OIDtype'});
|
---|
113 | #$doc_obj->set_OIDtype ("incremental");
|
---|
114 | $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "Plugin", "$self->{'plugin_type'}");
|
---|
115 | $doc_obj->add_metadata($doc_obj->get_top_section(), "Source", &ghtml::dmsafe($file)); # set the filename as Source metadata to be consistent with other plugins
|
---|
116 |
|
---|
117 | $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "FileSize", (-s $filename));
|
---|
118 |
|
---|
119 | my $assoc_field = $self->{'assoc_field'} || "null_file";
|
---|
120 | $doc_obj->add_metadata ($doc_obj->get_top_section(), $assoc_field, $file);
|
---|
121 |
|
---|
122 | #create an empty text string so we don't break downstream plugins
|
---|
123 | my $text = &gsprintf::lookup_string("{BasPlug.dummy_text}");
|
---|
124 |
|
---|
125 | # include any metadata passed in from previous plugins
|
---|
126 | my $section = $doc_obj->get_top_section();
|
---|
127 | $self->extra_metadata ($doc_obj, $section, $metadata);
|
---|
128 |
|
---|
129 | $self->title_fallback($doc_obj,$section,$file);
|
---|
130 |
|
---|
131 | # do plugin specific processing of doc_obj
|
---|
132 | unless (defined ($self->process(\$text, $pluginfo, $base_dir, $file, $metadata, $doc_obj))) {
|
---|
133 | print STDERR "<ProcessingError n='$file'>\n" if ($gli);
|
---|
134 | return -1;
|
---|
135 | }
|
---|
136 |
|
---|
137 | # do any automatic metadata extraction
|
---|
138 | $self->auto_extract_metadata ($doc_obj);
|
---|
139 |
|
---|
140 | # add an OID
|
---|
141 | $doc_obj->set_OID();
|
---|
142 | $doc_obj->add_text($section, $text);
|
---|
143 |
|
---|
144 | # process the document
|
---|
145 | $processor->process($doc_obj);
|
---|
146 |
|
---|
147 | $self->{'num_processed'} ++;
|
---|
148 | return 1;
|
---|
149 | }
|
---|
150 |
|
---|
151 |
|
---|
152 | # NULPlug processing of doc_obj. In practice we don't need to do
|
---|
153 | # anything here because the read function takes care of everything.
|
---|
154 |
|
---|
155 | sub process {
|
---|
156 | my $self = shift (@_);
|
---|
157 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj) = @_;
|
---|
158 | my $outhandle = $self->{'outhandle'};
|
---|
159 |
|
---|
160 | return 1;
|
---|
161 | }
|
---|
162 |
|
---|
163 |
|
---|
164 | 1;
|
---|
165 |
|
---|
166 |
|
---|
167 |
|
---|
168 |
|
---|
169 |
|
---|
170 |
|
---|
171 |
|
---|
172 |
|
---|
173 |
|
---|
174 |
|
---|
175 |
|
---|