1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # OpenDocumentPlugin.pm -- The Open Document plugin
|
---|
4 | # A component of the Greenstone digital library software
|
---|
5 | # from the New Zealand Digital Library Project at the
|
---|
6 | # University of Waikato, New Zealand.
|
---|
7 | #
|
---|
8 | # Copyright (C) 2001 New Zealand Digital Library Project
|
---|
9 | #
|
---|
10 | # This program is free software; you can redistribute it and/or modify
|
---|
11 | # it under the terms of the GNU General Public License as published by
|
---|
12 | # the Free Software Foundation; either version 2 of the License, or
|
---|
13 | # (at your option) any later version.
|
---|
14 | #
|
---|
15 | # This program is distributed in the hope that it will be useful,
|
---|
16 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
17 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
18 | # GNU General Public License for more details.
|
---|
19 | #
|
---|
20 | # You should have received a copy of the GNU General Public License
|
---|
21 | # along with this program; if not, write to the Free Software
|
---|
22 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
23 | #
|
---|
24 | ###########################################################################
|
---|
25 |
|
---|
26 | # Processes OASIS Open Document format.
|
---|
27 | # Word processing document: .odt, template: .ott
|
---|
28 | # Spreadsheet document: .ods, template: .ots
|
---|
29 | # Presentation document: .odp, template: .otp
|
---|
30 | # Graphics document: .odg, template: .otg
|
---|
31 | # Formulas document: .odf, template: .otf (not supported)
|
---|
32 |
|
---|
33 | #This basically extracts any text out of the document, but not much else.
|
---|
34 |
|
---|
35 | # this inherits ReadXMLFile, and therefore offers -xslt option, but does
|
---|
36 | # nothing with it.
|
---|
37 |
|
---|
38 | package OpenDocumentPlugin;
|
---|
39 |
|
---|
40 | use strict;
|
---|
41 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
42 |
|
---|
43 | use ReadXMLFile;
|
---|
44 | use XML::XPath;
|
---|
45 | use XML::XPath::XMLParser;
|
---|
46 | use Cwd;
|
---|
47 | use util;
|
---|
48 | use ghtml;
|
---|
49 |
|
---|
50 | sub BEGIN {
|
---|
51 | @OpenDocumentPlugin::ISA = ('ReadXMLFile');
|
---|
52 | }
|
---|
53 |
|
---|
54 | our @filesProcess = ( "content.xml" , "meta.xml" );
|
---|
55 |
|
---|
56 | my $arguments = [
|
---|
57 | { 'name' => "process_exp",
|
---|
58 | 'desc' => "{BasPlug.process_exp}",
|
---|
59 | 'type' => "regexp",
|
---|
60 | 'deft' => &get_default_process_exp() }
|
---|
61 | ];
|
---|
62 |
|
---|
63 | my $options = { 'name' => "OpenDocumentPlugin",
|
---|
64 | 'desc' => "{OpenDocumentPlugin.desc}",
|
---|
65 | 'abstract' => "no",
|
---|
66 | 'inherits' => "yes",
|
---|
67 | 'args' => $arguments};
|
---|
68 |
|
---|
69 | sub get_default_process_exp { return q^(?i)\.o(?:d|t)(?:t|s|p|g)$^; }
|
---|
70 |
|
---|
71 | sub new {
|
---|
72 | my ($class) = shift (@_);
|
---|
73 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
74 | push(@$pluginlist, $class);
|
---|
75 |
|
---|
76 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
77 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
78 |
|
---|
79 | my $self = new ReadXMLFile($pluginlist, $inputargs, $hashArgOptLists);
|
---|
80 |
|
---|
81 | $self->{'section'} = "";
|
---|
82 | $self->{'office:meta'} = "";
|
---|
83 |
|
---|
84 | return bless $self, $class;
|
---|
85 | }
|
---|
86 |
|
---|
87 | sub get_doctype {
|
---|
88 | my $self = shift(@_);
|
---|
89 |
|
---|
90 | return "manifest:manifest";
|
---|
91 | }
|
---|
92 |
|
---|
93 | sub xml_doctype {
|
---|
94 | my $self = shift(@_);
|
---|
95 | my ($expat, $name, $sysid, $pubid, $internal) = @_;
|
---|
96 | die "The only valid doctype is manifest, $name is not valid" if ($name ne "manifest:manifest");
|
---|
97 | }
|
---|
98 |
|
---|
99 | # Called for every start tag. The $_ variable will contain a copy of the
|
---|
100 | # tag and the %_ variable will contain the element's attributes.
|
---|
101 | sub xml_start_tag {
|
---|
102 | my $self = shift(@_);
|
---|
103 | my ($expat, $element) = @_;
|
---|
104 | my %atts = %_;
|
---|
105 | $self->{'office:meta'} = $element if $self->{'office:meta'} eq "Start";
|
---|
106 | if($element eq 'office:text') {
|
---|
107 | $self->{'collectedText'} = "";
|
---|
108 | }elsif($element eq 'office:meta') {
|
---|
109 | $self->{'collectedText'} = "";
|
---|
110 | $self->{'office:meta'} = "Start";
|
---|
111 | }elsif($element eq 'meta:document-statistic'){
|
---|
112 | foreach my $att (keys %atts) {
|
---|
113 | $self->{'doc_obj'}->add_utf8_metadata("",$att,$atts{$att});
|
---|
114 | }
|
---|
115 |
|
---|
116 | }
|
---|
117 | }
|
---|
118 |
|
---|
119 | sub xml_end_tag {
|
---|
120 | my $self = shift(@_);
|
---|
121 | my ($expat, $element) = @_;
|
---|
122 |
|
---|
123 | if($element eq 'office:text') {
|
---|
124 | $self->{'doc_obj'}->add_utf8_text("",$self->{'collectedText'});
|
---|
125 | $self->{'collectedText'} = "";
|
---|
126 | }elsif($element eq $self->{'office:meta'}) {
|
---|
127 | if( $self->{'collectedText'} ne "") {
|
---|
128 | $self->{'doc_obj'}->add_utf8_metadata("",$self->{'office:meta'},$self->{'collectedText'});
|
---|
129 | $self->{'doc_obj'}->add_utf8_metadata("","Title",$self->{'collectedText'}) if $self->{'office:meta'} =~ m/:title$/;
|
---|
130 | $self->{'doc_obj'}->add_utf8_metadata("","Language",$self->{'collectedText'}) if $self->{'office:meta'} =~ m/:language$/;
|
---|
131 | $self->{'doc_obj'}->add_utf8_metadata("","GENERATOR",$self->{'collectedText'}) if $self->{'office:meta'} =~ m/:generator$/;
|
---|
132 |
|
---|
133 | }
|
---|
134 | $self->{'collectedText'} = "";
|
---|
135 | $self->{'office:meta'} = "Start";
|
---|
136 | }elsif($element eq 'office:meta'){
|
---|
137 | $self->{'office:meta'} = "";
|
---|
138 | }elsif($element eq 'office:body'){
|
---|
139 | #some documents have text in other places that should probably be indexed if we can't find any doc text
|
---|
140 |
|
---|
141 | if( defined $self->{'collectedText'} && $self->{'collectedText'} ne "" && $self->{'doc_obj'}->get_text("") eq "") {
|
---|
142 | $self->{'doc_obj'}->add_utf8_text("",$self->{'collectedText'});
|
---|
143 | }
|
---|
144 | }
|
---|
145 | }
|
---|
146 |
|
---|
147 | sub xml_text {
|
---|
148 | my $self = shift(@_);
|
---|
149 | my ($expat) = @_;
|
---|
150 | if($_ =~ m/\w/i) {
|
---|
151 | $self->{'collectedText'} .= "<br/>" if $self->{'collectedText'} ne "";
|
---|
152 | $self->{'collectedText'} .= "$_";
|
---|
153 | }
|
---|
154 | }
|
---|
155 |
|
---|
156 | #trap start and end document so we do not get our doc_obj closed too soon
|
---|
157 | sub xml_start_document {}
|
---|
158 | sub xml_end_document {}
|
---|
159 |
|
---|
160 | sub read {
|
---|
161 | my $self = shift (@_);
|
---|
162 |
|
---|
163 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
---|
164 |
|
---|
165 | # check process and block exps, smart block, associate_ext etc
|
---|
166 | my ($block_status,$filename) = $self->read_block(@_);
|
---|
167 | return $block_status if ((!defined $block_status) || ($block_status==0));
|
---|
168 |
|
---|
169 | $file =~ s/^[\/\\]+//; # $file often begins with / so we'll tidy it up
|
---|
170 | $self->{'file'} = $file;
|
---|
171 | $self->{'filename'} = $filename;
|
---|
172 | $self->{'processor'} = $processor;
|
---|
173 | $self->{'metadata'} = $metadata;
|
---|
174 |
|
---|
175 | eval{
|
---|
176 | my ($file_only) = $file =~ /([^\\\/]*)$/;
|
---|
177 | my $tmpdir = &util::get_tmp_filename ();
|
---|
178 | &util::mk_all_dir ($tmpdir);
|
---|
179 |
|
---|
180 | $self->open_document();
|
---|
181 |
|
---|
182 | # save current working directory
|
---|
183 | my $cwd = getcwd();
|
---|
184 | chdir ($tmpdir) || die "Unable to change to $tmpdir";
|
---|
185 | &util::cp ($filename, $tmpdir);
|
---|
186 |
|
---|
187 | $self->unzip ("\"$file_only\"");
|
---|
188 | foreach my $xmlFile (@OpenDocumentPlugin::filesProcess) {
|
---|
189 | if (-e $xmlFile) {
|
---|
190 | $self->{'parser'}->parsefile($xmlFile);
|
---|
191 | }
|
---|
192 | }
|
---|
193 | $self->close_document($filename,$file_only);
|
---|
194 |
|
---|
195 | chdir ($cwd) || die "Unable to change back to $cwd";
|
---|
196 | &util::rm_r ($tmpdir);
|
---|
197 |
|
---|
198 | };
|
---|
199 |
|
---|
200 | if ($@) {
|
---|
201 |
|
---|
202 | # parsefile may either croak somewhere in XML::Parser (e.g. because
|
---|
203 | # the document is not well formed) or die somewhere in ReadXMLFile or a
|
---|
204 | # derived plugin (e.g. because we're attempting to process a
|
---|
205 | # document whose DOCTYPE is not meant for this plugin). For the
|
---|
206 | # first case we'll print a warning and continue, for the second
|
---|
207 | # we'll just continue quietly
|
---|
208 |
|
---|
209 | print STDERR "**** Error is: $@\n";
|
---|
210 |
|
---|
211 | my ($msg) = $@ =~ /Carp::croak\(\'(.*?)\'\)/;
|
---|
212 | if (defined $msg) {
|
---|
213 | my $outhandle = $self->{'outhandle'};
|
---|
214 | my $plugin_name = ref ($self);
|
---|
215 | print $outhandle "$plugin_name failed to process $file ($msg)\n";
|
---|
216 | }
|
---|
217 |
|
---|
218 | # reset ourself for the next document
|
---|
219 | print STDERR "<ProcessingError n='$file'>\n" if ($gli);
|
---|
220 | return -1; # error during processing
|
---|
221 | }
|
---|
222 |
|
---|
223 | return 1;
|
---|
224 | }
|
---|
225 |
|
---|
226 | sub unzip {
|
---|
227 | my $self = shift (@_);
|
---|
228 | my ($file) = @_;
|
---|
229 |
|
---|
230 | system ("unzip $file");
|
---|
231 | &util::rm ($file) if -e $file;
|
---|
232 | }
|
---|
233 |
|
---|
234 | sub close_document() {
|
---|
235 | my $self = shift(@_);
|
---|
236 | my ($filename,$file_only) = @_;
|
---|
237 |
|
---|
238 | my $doc_obj = $self->{'doc_obj'};
|
---|
239 |
|
---|
240 | my $mimetype = $self->get_mimetype();
|
---|
241 |
|
---|
242 | $doc_obj->associate_file($filename, $file_only, $mimetype, "");
|
---|
243 | $doc_obj->associate_file("Thumbnails/thumbnail.png", "thumbnail.png", "image/png", "");
|
---|
244 | my $doc_ext = $filename;
|
---|
245 | $doc_ext =~ s/.*\.od(.)/od$1/;
|
---|
246 |
|
---|
247 | # We use set instead of add here because we only want one value
|
---|
248 | $doc_obj->set_utf8_metadata_element("", "FileFormat", "Open Document");
|
---|
249 |
|
---|
250 | #setup to doclink thingi
|
---|
251 | my $doclink = "<a href=\"_httpprefix_/collect/[collection]/index/assoc/[archivedir]/$file_only\">";
|
---|
252 | $doc_obj->add_utf8_metadata ("", "srclink", $doclink);
|
---|
253 | $doc_obj->add_utf8_metadata ("", "srcicon", "<img border=\"0\" align=\"absmiddle\" src=\"_httpprefix_/collect/[collection]/index/assoc/[archivedir]/thumbnail.png\" alt=\"View the Open document\" title=\"View the Open document\">");
|
---|
254 | $doc_obj->add_utf8_metadata ("", "/srclink", "</a>");
|
---|
255 | $self->set_Source_metadata($doc_obj, $file_only);
|
---|
256 | $doc_obj->set_utf8_metadata_element("", "FileSize", (-s $filename));
|
---|
257 |
|
---|
258 | # include any metadata passed in from previous plugins
|
---|
259 | # note that this metadata is associated with the top level section
|
---|
260 | $self->extra_metadata ($doc_obj,
|
---|
261 | $doc_obj->get_top_section(),
|
---|
262 | $self->{'metadata'});
|
---|
263 |
|
---|
264 | # add a Title if none has been found yet
|
---|
265 | $self->title_fallback($doc_obj,"",$file_only);
|
---|
266 |
|
---|
267 | # add an OID
|
---|
268 | $self->add_OID($doc_obj);
|
---|
269 |
|
---|
270 | $doc_obj->add_utf8_metadata("", "Plugin", "$self->{'plugin_type'}");
|
---|
271 |
|
---|
272 | # process the document
|
---|
273 | $self->{'processor'}->process($doc_obj);
|
---|
274 |
|
---|
275 | $self->{'num_processed'} ++;
|
---|
276 | return 1;
|
---|
277 | }
|
---|
278 |
|
---|
279 | sub get_mimetype(){
|
---|
280 | my $filename = "mimetype";
|
---|
281 | if (!open (FILEIN,"<$filename")){
|
---|
282 | print STDERR "Warning: unable to open the $filename\n";
|
---|
283 | return "Unknown OpenDocument Format";
|
---|
284 | }
|
---|
285 | else {
|
---|
286 | my $text = "";
|
---|
287 | while (defined (my $line = <FILEIN>)) {
|
---|
288 | $text .= $line;
|
---|
289 | }
|
---|
290 | return $text;
|
---|
291 | }
|
---|
292 | }
|
---|
293 | 1;
|
---|
294 |
|
---|
295 |
|
---|
296 |
|
---|
297 |
|
---|