1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # RealMediaPlug.pm -- Extract metadata from Real Media files
|
---|
4 | #
|
---|
5 | # Original code by Xin Gao
|
---|
6 | #
|
---|
7 | # A component of the Greenstone digital library software
|
---|
8 | # from the New Zealand Digital Library Project at the
|
---|
9 | # University of Waikato, New Zealand.
|
---|
10 | #
|
---|
11 | # Copyright (C) 2005 New Zealand Digital Library Project
|
---|
12 | #
|
---|
13 | # This program is free software; you can redistribute it and/or modify
|
---|
14 | # it under the terms of the GNU General Public License as published by
|
---|
15 | # the Free Software Foundation; either version 2 of the License, or
|
---|
16 | # (at your option) any later version.
|
---|
17 | #
|
---|
18 | # This program is distributed in the hope that it will be useful,
|
---|
19 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
20 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
21 | # GNU General Public License for more details.
|
---|
22 | #
|
---|
23 | # You should have received a copy of the GNU General Public License
|
---|
24 | # along with this program; if not, write to the Free Software
|
---|
25 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
26 | #
|
---|
27 | ###########################################################################
|
---|
28 |
|
---|
29 | package RealMediaPlug;
|
---|
30 |
|
---|
31 |
|
---|
32 | use UnknownPlug;
|
---|
33 | use rm::Header::PurePerl;
|
---|
34 |
|
---|
35 | use strict;
|
---|
36 | no strict 'refs'; # make an exception so we can use variables as filehandles
|
---|
37 |
|
---|
38 |
|
---|
39 | sub BEGIN {
|
---|
40 | @RealMediaPlug::ISA = ('UnknownPlug');
|
---|
41 | }
|
---|
42 |
|
---|
43 |
|
---|
44 | my $arguments =
|
---|
45 | [ { 'name' => "process_exp",
|
---|
46 | 'desc' => "{BasPlug.process_exp}",
|
---|
47 | 'type' => "regexp",
|
---|
48 | 'deft' => &get_default_process_exp(),
|
---|
49 | 'reqd' => "no" } ];
|
---|
50 |
|
---|
51 | my $options = { 'name' => "RealMediaPlug",
|
---|
52 | 'desc' => "{RealMediaPlug.desc}",
|
---|
53 | 'abstract' => "no",
|
---|
54 | 'inherits' => "yes",
|
---|
55 | 'args' => $arguments };
|
---|
56 |
|
---|
57 |
|
---|
58 | # This plugin processes Real Media files with the suffixes ".rm" and ".rmvb"
|
---|
59 | sub get_default_process_exp
|
---|
60 | {
|
---|
61 | return q^(?i)(\.rm|rmvb)$^;
|
---|
62 | }
|
---|
63 |
|
---|
64 |
|
---|
65 | sub new
|
---|
66 | {
|
---|
67 | my ($class) = shift(@_);
|
---|
68 | my ($pluginlist, $inputargs, $hashArgOptLists) = @_;
|
---|
69 | push(@$pluginlist, $class);
|
---|
70 |
|
---|
71 | if (defined $arguments) { push(@{$hashArgOptLists->{"ArgList"}}, @{$arguments}); }
|
---|
72 | if (defined $options) { push(@{$hashArgOptLists->{"OptList"}}, $options); }
|
---|
73 |
|
---|
74 | my $self = (defined $hashArgOptLists) ? new UnknownPlug($pluginlist, $inputargs, $hashArgOptLists) : new UnknownPlug($pluginlist, $inputargs);
|
---|
75 |
|
---|
76 | return bless $self, $class;
|
---|
77 | }
|
---|
78 |
|
---|
79 |
|
---|
80 | # do plugin specific processing of doc_obj
|
---|
81 | sub read
|
---|
82 | {
|
---|
83 | my $self = shift (@_);
|
---|
84 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
---|
85 |
|
---|
86 | my $outhandle = $self->{'outhandle'};
|
---|
87 |
|
---|
88 | # filename is the full pathname of the file
|
---|
89 | my $filename = &util::filename_cat($base_dir, $file);
|
---|
90 | return 0 if $self->{block_exp} ne "" && $filename =~ /$self->{'block_exp'}/;
|
---|
91 | if ($filename !~ /$self->{'process_exp'}/ || !-f $filename) {
|
---|
92 | return undef;
|
---|
93 | }
|
---|
94 |
|
---|
95 | # Report that we're processing the file
|
---|
96 | print STDERR "<Processing n='$file' p='RealMediaPlug'>\n" if ($gli);
|
---|
97 | print $outhandle "RealMediaPlug: processing $file\n"
|
---|
98 | if ($self->{'verbosity'}) > 1;
|
---|
99 |
|
---|
100 | # create a new index document
|
---|
101 | my $doc_obj = new doc ($filename, "indexed_doc");
|
---|
102 | $doc_obj->set_OIDtype ("incremental"); # this is done to avoid hashing content of file
|
---|
103 | my $top_section = $doc_obj->get_top_section();
|
---|
104 |
|
---|
105 | # replace spaces in filename with %20 in url for metadata entry
|
---|
106 | my $url = $file;
|
---|
107 | $url =~ s/ /%20/g;
|
---|
108 | # Source (filename) to be consistent with other plugins
|
---|
109 | $doc_obj->add_metadata($top_section, "Source", $url);
|
---|
110 |
|
---|
111 | my $text = "";
|
---|
112 | my $real_media = rm::Header::PurePerl->new($filename);
|
---|
113 | foreach my $key (keys %{$real_media->info})
|
---|
114 | {
|
---|
115 | my $value = $real_media->info->{$key};
|
---|
116 | $doc_obj->add_metadata($top_section, $key, $value);
|
---|
117 | $text .= "$key: $value\n";
|
---|
118 | }
|
---|
119 |
|
---|
120 | $doc_obj->add_utf8_text($top_section, "<pre>\n$text\n</pre>");
|
---|
121 |
|
---|
122 | # srclink
|
---|
123 | $doc_obj->add_metadata($top_section, "FileFormat", "RealMedia");
|
---|
124 | $doc_obj->add_metadata($top_section, "srclink", "<a href=\"_httpcollection_/index/assoc/[assocfilepath]/[Source]\">");
|
---|
125 | $doc_obj->add_metadata($top_section, "/srclink", "</a>");
|
---|
126 | # srcicon (need to include "irmvideo.gif" in the greenstone images directory
|
---|
127 | $doc_obj->add_metadata($top_section, "srcicon", "<img src=\"_httpprefix_/images/irmvideo.gif\" title=\"Download\" border=0>");
|
---|
128 |
|
---|
129 | # Add the actual file as an associated file
|
---|
130 | $doc_obj->associate_file($filename, $file, "RealMedia", $top_section);
|
---|
131 |
|
---|
132 | # include any metadata passed in from previous plugins
|
---|
133 | my $section = $doc_obj->get_top_section();
|
---|
134 | $self->extra_metadata ($doc_obj, $section, $metadata);
|
---|
135 |
|
---|
136 | # do plugin specific processing of doc_obj
|
---|
137 | return undef unless defined ($self->process (\$text, $pluginfo, $base_dir, $file, $metadata, $doc_obj));
|
---|
138 |
|
---|
139 | # do any automatic metadata extraction
|
---|
140 | $self->auto_extract_metadata($doc_obj);
|
---|
141 |
|
---|
142 | # add an OID
|
---|
143 | $doc_obj->set_OID();
|
---|
144 |
|
---|
145 | # process the document
|
---|
146 | $processor->process($doc_obj);
|
---|
147 |
|
---|
148 | $self->{'num_processed'}++;
|
---|
149 | return 1;
|
---|
150 | }
|
---|
151 |
|
---|
152 | 1;
|
---|