1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # OAIPlug.pm -- basic Open Archives Initiative (OAI) plugin
|
---|
4 | #
|
---|
5 | # A component of the Greenstone digital library software
|
---|
6 | # from the New Zealand Digital Library Project at the
|
---|
7 | # University of Waikato, New Zealand.
|
---|
8 | #
|
---|
9 | # Copyright (C) 1999 New Zealand Digital Library Project
|
---|
10 | #
|
---|
11 | # This program is free software; you can redistribute it and/or modify
|
---|
12 | # it under the terms of the GNU General Public License as published by
|
---|
13 | # the Free Software Foundation; either version 2 of the License, or
|
---|
14 | # (at your option) any later version.
|
---|
15 | #
|
---|
16 | # This program is distributed in the hope that it will be useful,
|
---|
17 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
18 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
19 | # GNU General Public License for more details.
|
---|
20 | #
|
---|
21 | # You should have received a copy of the GNU General Public License
|
---|
22 | # along with this program; if not, write to the Free Software
|
---|
23 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
24 | #
|
---|
25 | ###########################################################################
|
---|
26 |
|
---|
27 | package OAIPlugin;
|
---|
28 |
|
---|
29 | use unicode;
|
---|
30 | use util;
|
---|
31 |
|
---|
32 | use strict;
|
---|
33 | no strict 'refs'; # allow filehandles to be variables and viceversa
|
---|
34 |
|
---|
35 | use ReadXMLFile;
|
---|
36 | use ReadTextFile; # needed for subroutine textcat_get_language_encoding
|
---|
37 | use metadatautil;
|
---|
38 |
|
---|
39 | sub BEGIN {
|
---|
40 | @OAIPlugin::ISA = ('ReadXMLFile', 'ReadTextFile');
|
---|
41 | }
|
---|
42 |
|
---|
43 |
|
---|
44 | my $arguments =
|
---|
45 | [ { 'name' => "process_exp",
|
---|
46 | 'desc' => "{BasePlugin.process_exp}",
|
---|
47 | 'type' => "regexp",
|
---|
48 | 'reqd' => "no",
|
---|
49 | 'deft' => &get_default_process_exp() }
|
---|
50 | ];
|
---|
51 |
|
---|
52 | my $options = { 'name' => "OAIPlugin",
|
---|
53 | 'desc' => "{OAIPlugin.desc}",
|
---|
54 | 'abstract' => "no",
|
---|
55 | 'inherits' => "yes",
|
---|
56 | 'explodes' => "yes",
|
---|
57 | 'args' => $arguments };
|
---|
58 |
|
---|
59 |
|
---|
60 | sub new {
|
---|
61 | my ($class) = shift (@_);
|
---|
62 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
63 | push(@$pluginlist, $class);
|
---|
64 |
|
---|
65 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
66 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
67 |
|
---|
68 | new ReadTextFile($pluginlist, $inputargs, $hashArgOptLists,1);
|
---|
69 | my $self = new ReadXMLFile($pluginlist, $inputargs, $hashArgOptLists);
|
---|
70 |
|
---|
71 | return bless $self, $class;
|
---|
72 | }
|
---|
73 |
|
---|
74 | sub get_default_process_exp {
|
---|
75 | my $self = shift (@_);
|
---|
76 |
|
---|
77 | return q^(?i)(\.oai)$^;
|
---|
78 | }
|
---|
79 |
|
---|
80 | sub get_doctype {
|
---|
81 | my $self = shift(@_);
|
---|
82 |
|
---|
83 | return "OAI-PMH";
|
---|
84 | }
|
---|
85 |
|
---|
86 | sub xml_start_document {
|
---|
87 | my $self = shift (@_);
|
---|
88 | $self->{'in_metadata_node'} = 0;
|
---|
89 | $self->{'rawxml'} = "";
|
---|
90 | }
|
---|
91 |
|
---|
92 | sub xml_end_document {
|
---|
93 | }
|
---|
94 |
|
---|
95 | sub xml_doctype {
|
---|
96 | my $self = shift(@_);
|
---|
97 |
|
---|
98 | my ($expat, $name, $sysid, $pubid, $internal) = @_;
|
---|
99 |
|
---|
100 | ##die "" if ($name !~ /^OAI-PMH$/);
|
---|
101 |
|
---|
102 | my $outhandle = $self->{'outhandle'};
|
---|
103 | print $outhandle "OAIPlugin: processing $self->{'file'}\n" if $self->{'verbosity'} > 1;
|
---|
104 | print STDERR "<Processing n='$self->{'file'}' p='OAIPlugin'>\n" if $self->{'gli'};
|
---|
105 |
|
---|
106 | }
|
---|
107 |
|
---|
108 |
|
---|
109 | sub xml_start_tag {
|
---|
110 | my $self = shift(@_);
|
---|
111 | my ($expat,$element) = @_;
|
---|
112 |
|
---|
113 | my %attr_hash = %_;
|
---|
114 |
|
---|
115 | my $attr = "";
|
---|
116 | map { $attr .= " $_=$attr_hash{$_}"; } keys %attr_hash;
|
---|
117 |
|
---|
118 | $self->{'rawxml'} .= "<$element$attr>";
|
---|
119 |
|
---|
120 | if ($element eq "metadata") {
|
---|
121 | $self->{'in_metadata_node'} = 1;
|
---|
122 | $self->{'metadata_xml'} = "";
|
---|
123 | }
|
---|
124 |
|
---|
125 | if ($self->{'in_metadata_node'}) {
|
---|
126 | $self->{'metadata_xml'} .= "<$element$attr>";
|
---|
127 | }
|
---|
128 | }
|
---|
129 |
|
---|
130 | sub xml_end_tag {
|
---|
131 | my $self = shift(@_);
|
---|
132 | my ($expat, $element) = @_;
|
---|
133 |
|
---|
134 | $self->{'rawxml'} .= "</$element>";
|
---|
135 |
|
---|
136 | if ($self->{'in_metadata_node'}) {
|
---|
137 | $self->{'metadata_xml'} .= "</$element>";
|
---|
138 | }
|
---|
139 |
|
---|
140 | if ($element eq "metadata") {
|
---|
141 | my $textref = \$self->{'metadata_xml'};
|
---|
142 | my $metadata = $self->{'metadata'};
|
---|
143 | $self->extract_oai_metadata($textref,$metadata);
|
---|
144 |
|
---|
145 | $self->{'in_metadata_node'} = 0;
|
---|
146 | }
|
---|
147 |
|
---|
148 |
|
---|
149 | }
|
---|
150 |
|
---|
151 | sub xml_text {
|
---|
152 | my $self = shift(@_);
|
---|
153 | my ($expat) = @_;
|
---|
154 |
|
---|
155 | $self->{'rawxml'} .= $_;
|
---|
156 |
|
---|
157 | if ($self->{'in_metadata_node'}) {
|
---|
158 | $self->{'metadata_xml'} .= $_;
|
---|
159 | }
|
---|
160 | }
|
---|
161 |
|
---|
162 |
|
---|
163 | sub metadata_read {
|
---|
164 | my $self = shift (@_);
|
---|
165 |
|
---|
166 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $extrametakeys, $extrametadata, $processor, $maxdocs, $gli) = @_;
|
---|
167 |
|
---|
168 | # can we process this file??
|
---|
169 | my ($filename_full_path, $filename_no_path) = &util::get_full_filenames($base_dir, $file);
|
---|
170 | return undef unless $self->can_process_this_file($filename_full_path);
|
---|
171 |
|
---|
172 | my $total_count = 0; # is total count used?
|
---|
173 | if ($self->SUPER::read($pluginfo,$base_dir,$file,$block_hash,$metadata,$processor,$maxdocs,$total_count, $gli)) {
|
---|
174 | # calling "SUPER::read" at this point sets up $metadata
|
---|
175 | # data-structure. We can then, later, in OAIPlug::read decide
|
---|
176 | # whether this $metadata will stick to an accompanying file,
|
---|
177 | # or else needs a new doc object to be formed that contains
|
---|
178 | # purely metadata
|
---|
179 |
|
---|
180 | $self->{'metadata'} = undef;
|
---|
181 |
|
---|
182 | #my $url_array = $metadata->{'gi.Sourcedoc'};
|
---|
183 | my $url_array = $metadata->{'dc.Identifier'};
|
---|
184 | my $num_urls = (defined $url_array) ? scalar(@$url_array) : 0;
|
---|
185 |
|
---|
186 | my $srcdoc_exists = 0;
|
---|
187 | my $srcdoc_pos = 0;
|
---|
188 | my $filename_dir = &util::filename_head($filename_full_path);
|
---|
189 |
|
---|
190 | for (my $i=0; $i<$num_urls; $i++) {
|
---|
191 |
|
---|
192 | if ($url_array->[$i] !~ m/^(https?|ftp):/) {
|
---|
193 |
|
---|
194 | my $src_filename = &util::filename_cat($filename_dir, $url_array->[$i]);
|
---|
195 |
|
---|
196 | if (-e $src_filename) {
|
---|
197 | $srcdoc_pos = $i;
|
---|
198 | $srcdoc_exists = 1;
|
---|
199 | last;
|
---|
200 | }
|
---|
201 | }
|
---|
202 | }
|
---|
203 |
|
---|
204 |
|
---|
205 | if ($srcdoc_exists)
|
---|
206 | {
|
---|
207 | $self->{'oai-files'}->{$file}->{'srcdoc_exists'} = 1;
|
---|
208 |
|
---|
209 | ### print STDERR "**** storing OAI file: $file\n";
|
---|
210 |
|
---|
211 | # Make pretty print metadata table stick with src filename
|
---|
212 | my $ppmd_table = $self->{'ppmd_table'};
|
---|
213 |
|
---|
214 | $metadata->{'prettymd'} = [ $ppmd_table ];
|
---|
215 | $self->{'ppmd_table'} = undef;
|
---|
216 |
|
---|
217 | }
|
---|
218 | else {
|
---|
219 | $self->{'oai-files'}->{$file}->{'srcdoc_exists'} = 0;
|
---|
220 | }
|
---|
221 |
|
---|
222 | }
|
---|
223 | else {
|
---|
224 | return undef;
|
---|
225 | }
|
---|
226 | }
|
---|
227 |
|
---|
228 |
|
---|
229 | sub read {
|
---|
230 | my $self = shift (@_);
|
---|
231 |
|
---|
232 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
---|
233 |
|
---|
234 |
|
---|
235 | ### print STDERR "**** checking OAI read: $file\n";
|
---|
236 |
|
---|
237 | if (defined $self->{'oai-files'}->{$file}) {
|
---|
238 |
|
---|
239 | my $srcdoc_exists = $self->{'oai-files'}->{$file}->{'srcdoc_exists'};
|
---|
240 |
|
---|
241 | # no more need to access details of this $file => tidy up as you go
|
---|
242 | delete $self->{'oai-files'}->{$file};
|
---|
243 |
|
---|
244 | ### print STDERR "**** !!!!! srcdoc_exists = $srcdoc_exists\n";
|
---|
245 | if (!$srcdoc_exists)
|
---|
246 | {
|
---|
247 |
|
---|
248 | my $filename = $file;
|
---|
249 | $filename = &util::filename_cat ($base_dir, $file) if $base_dir =~ /\w/;
|
---|
250 |
|
---|
251 | # Do encoding stuff on metadata
|
---|
252 | my ($language, $encoding) = $self->textcat_get_language_encoding ($filename);
|
---|
253 |
|
---|
254 | # create a new document
|
---|
255 | my $doc_obj = new doc ($filename, "indexed_doc");
|
---|
256 | my $top_section = $doc_obj->get_top_section;
|
---|
257 | my $plugin_type = $self->{'plugin_type'};
|
---|
258 |
|
---|
259 | $doc_obj->add_utf8_metadata($top_section, "Language", $language);
|
---|
260 | $doc_obj->add_utf8_metadata($top_section, "Encoding", $encoding);
|
---|
261 | $doc_obj->add_utf8_metadata($top_section, "Plugin", $plugin_type);
|
---|
262 | $doc_obj->add_metadata($top_section, "FileFormat", "OAI");
|
---|
263 | $doc_obj->add_metadata($top_section, "FileSize", (-s $filename));
|
---|
264 |
|
---|
265 | # include any metadata passed in from previous plugins
|
---|
266 | # note that this metadata is associated with the top level section
|
---|
267 | $self->extra_metadata ($doc_obj, $doc_obj->get_top_section(), $metadata);
|
---|
268 |
|
---|
269 | # do plugin specific processing of doc_obj
|
---|
270 | my $textref = \$self->{'rawxml'};
|
---|
271 | unless (defined ($self->process($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj))) {
|
---|
272 | print STDERR "<ProcessingError n='$file'>\n" if ($gli);
|
---|
273 | return -1;
|
---|
274 | }
|
---|
275 |
|
---|
276 | # do any automatic metadata extraction
|
---|
277 | $self->auto_extract_metadata ($doc_obj);
|
---|
278 |
|
---|
279 | # add an OID
|
---|
280 | $self->add_OID($doc_obj);
|
---|
281 |
|
---|
282 | my $prettymds = $self->{'prettymd'};
|
---|
283 | foreach my $prettymd (@$prettymds) {
|
---|
284 | $doc_obj->add_utf8_metadata($top_section,"prettymd",$prettymd);
|
---|
285 | }
|
---|
286 | $self->{'prettymd'} = undef;
|
---|
287 |
|
---|
288 | # process the document
|
---|
289 | $processor->process($doc_obj);
|
---|
290 |
|
---|
291 | $self->{'num_processed'} ++;
|
---|
292 |
|
---|
293 | return 1; # processed the file
|
---|
294 | }
|
---|
295 | }
|
---|
296 | else {
|
---|
297 | return undef;
|
---|
298 | }
|
---|
299 | }
|
---|
300 |
|
---|
301 |
|
---|
302 | sub read_old {
|
---|
303 | my $self = shift (@_);
|
---|
304 |
|
---|
305 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
---|
306 |
|
---|
307 | my $outhandle = $self->{'outhandle'};
|
---|
308 |
|
---|
309 | my $filename = $file;
|
---|
310 | $filename = &util::filename_cat ($base_dir, $file) if $base_dir =~ /\w/;
|
---|
311 |
|
---|
312 | # block the srcdocs dir - we will process files in them when we find an OAI record for them
|
---|
313 | return 0 if ((-d $filename) && ($filename =~ m/srcdocs$/));
|
---|
314 | if ($self->SUPER::read(@_)) {
|
---|
315 | # Do encoding stuff
|
---|
316 | my ($language, $encoding) = $self->textcat_get_language_encoding ($filename);
|
---|
317 |
|
---|
318 | my $url_array = $metadata->{'dc.Identifier'};
|
---|
319 | my $num_urls = (defined $url_array) ? scalar(@$url_array) : 0;
|
---|
320 |
|
---|
321 | my $srcdoc_exists = 0;
|
---|
322 | my $srcdoc_pos = 0;
|
---|
323 | my $filename_dir = &util::filename_head($filename);
|
---|
324 |
|
---|
325 | for (my $i=0; $i<$num_urls; $i++) {
|
---|
326 | if ($url_array->[$i] !~ m/^(http|ftp):/) {
|
---|
327 |
|
---|
328 | my $src_filename = &util::filename_cat($filename_dir, $url_array->[$i]);
|
---|
329 | if (-e $src_filename) {
|
---|
330 | $srcdoc_pos = $i;
|
---|
331 | $srcdoc_exists = 1;
|
---|
332 | }
|
---|
333 | }
|
---|
334 | }
|
---|
335 |
|
---|
336 | if ($srcdoc_exists)
|
---|
337 | {
|
---|
338 | print $outhandle "OAIPlugin: passing metadata on to $url_array->[0]\n"
|
---|
339 | if ($self->{'verbosity'}>1);
|
---|
340 |
|
---|
341 |
|
---|
342 | # Make pretty print metadata table stick with src filename
|
---|
343 | my $ppmd_table = $self->{'ppmd_table'};
|
---|
344 | $metadata->{'prettymd'} = [ $ppmd_table ];
|
---|
345 | $self->{'ppmd_table'} = undef;
|
---|
346 |
|
---|
347 | return &plugin::read ($pluginfo, $filename_dir, $url_array->[0],
|
---|
348 | $block_hash, $metadata, $processor, $maxdocs,
|
---|
349 | $total_count, $gli);
|
---|
350 | }
|
---|
351 | else
|
---|
352 | {
|
---|
353 | # create a new document
|
---|
354 | my $doc_obj = new doc ($filename, "indexed_doc");
|
---|
355 | my $top_section = $doc_obj->get_top_section;
|
---|
356 | my $plugin_type = $self->{'plugin_type'};
|
---|
357 |
|
---|
358 | $doc_obj->add_utf8_metadata($top_section, "Language", $language);
|
---|
359 | $doc_obj->add_utf8_metadata($top_section, "Encoding", $encoding);
|
---|
360 | $doc_obj->add_utf8_metadata($top_section, "Plugin", $plugin_type);
|
---|
361 | $doc_obj->add_metadata($top_section, "FileFormat", "OAI");
|
---|
362 | $doc_obj->add_metadata($top_section, "FileSize", (-s $filename));
|
---|
363 |
|
---|
364 | # include any metadata passed in from previous plugins
|
---|
365 | # note that this metadata is associated with the top level section
|
---|
366 | $self->extra_metadata ($doc_obj, $doc_obj->get_top_section(), $metadata);
|
---|
367 |
|
---|
368 | # do plugin specific processing of doc_obj
|
---|
369 | my $textref = \$self->{'rawxml'};
|
---|
370 | unless (defined ($self->process($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj))) {
|
---|
371 | print STDERR "<ProcessingError n='$file'>\n" if ($gli);
|
---|
372 | return -1;
|
---|
373 | }
|
---|
374 |
|
---|
375 | # do any automatic metadata extraction
|
---|
376 | $self->auto_extract_metadata ($doc_obj);
|
---|
377 |
|
---|
378 | # add an OID
|
---|
379 | $self->add_OID($doc_obj);
|
---|
380 |
|
---|
381 | my $ppmd_table = $self->{'ppmd_table'};
|
---|
382 | $doc_obj->add_utf8_metadata($top_section,"prettymd",$ppmd_table);
|
---|
383 | $self->{'ppmd_table'} = undef;
|
---|
384 |
|
---|
385 | # process the document
|
---|
386 | $processor->process($doc_obj);
|
---|
387 |
|
---|
388 | $self->{'num_processed'} ++;
|
---|
389 |
|
---|
390 | return 1; # processed the file
|
---|
391 | }
|
---|
392 | }
|
---|
393 | else {
|
---|
394 | return undef;
|
---|
395 | }
|
---|
396 | }
|
---|
397 |
|
---|
398 |
|
---|
399 | # do plugin specific processing of doc_obj
|
---|
400 | sub process {
|
---|
401 | my $self = shift (@_);
|
---|
402 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
---|
403 | my $outhandle = $self->{'outhandle'};
|
---|
404 |
|
---|
405 | print STDERR "<Processing n='$file' p='OAIPlugin'>\n" if ($gli);
|
---|
406 | print $outhandle "OAIPlugin: processing $file\n"
|
---|
407 | if $self->{'verbosity'} > 1;
|
---|
408 |
|
---|
409 | my $cursection = $doc_obj->get_top_section();
|
---|
410 |
|
---|
411 | ## $self->extract_metadata ($textref, $metadata, $doc_obj, $cursection);
|
---|
412 |
|
---|
413 | # add text to document object
|
---|
414 |
|
---|
415 | # $$textref =~ s/<(.*?)>/$1 /g;
|
---|
416 | $$textref =~ s/</</g;
|
---|
417 | $$textref =~ s/>/>/g;
|
---|
418 | $$textref =~ s/\[/[/g;
|
---|
419 | $$textref =~ s/\]/]/g;
|
---|
420 |
|
---|
421 | ## print STDERR "*** adding text: $$textref\n";
|
---|
422 |
|
---|
423 | $doc_obj->add_utf8_text($cursection, $$textref);
|
---|
424 |
|
---|
425 | return 1;
|
---|
426 | }
|
---|
427 |
|
---|
428 |
|
---|
429 | # Improvement is to merge this with newer version in MetadataPass
|
---|
430 |
|
---|
431 | sub open_prettyprint_metadata_table
|
---|
432 | {
|
---|
433 | my $self = shift(@_);
|
---|
434 |
|
---|
435 | my $att = "width=100% cellspacing=2";
|
---|
436 | my $style = "style=\'border-bottom: 4px solid #000080\'";
|
---|
437 |
|
---|
438 | $self->{'ppmd_table'} = "\n<table $att $style>";
|
---|
439 | }
|
---|
440 |
|
---|
441 | sub add_prettyprint_metadata_line
|
---|
442 | {
|
---|
443 | my $self = shift(@_);
|
---|
444 | my ($metaname, $metavalue_utf8) = @_;
|
---|
445 |
|
---|
446 | ### $metavalue_utf8 =~ s/hdl\.handle\.net/mcgonagall.cs.waikato.ac.nz:8080\/dspace\/handle/;
|
---|
447 | $metavalue_utf8 = &util::hyperlink_text($metavalue_utf8);
|
---|
448 |
|
---|
449 | $self->{'ppmd_table'} .= " <tr bgcolor=#b5d3cd>\n";
|
---|
450 | $self->{'ppmd_table'} .= " <td width=30%>\n";
|
---|
451 | $self->{'ppmd_table'} .= " $metaname\n";
|
---|
452 | $self->{'ppmd_table'} .= " </td>\n";
|
---|
453 | $self->{'ppmd_table'} .= " <td>\n";
|
---|
454 | $self->{'ppmd_table'} .= " $metavalue_utf8\n";
|
---|
455 | $self->{'ppmd_table'} .= " </td>\n";
|
---|
456 | $self->{'ppmd_table'} .= " </tr>\n";
|
---|
457 |
|
---|
458 | }
|
---|
459 |
|
---|
460 | sub close_prettyprint_metadata_table
|
---|
461 | {
|
---|
462 | my $self = shift(@_);
|
---|
463 |
|
---|
464 | $self->{'ppmd_table'} .= "</table>\n";
|
---|
465 | }
|
---|
466 |
|
---|
467 |
|
---|
468 | sub remap_dcterms_metadata
|
---|
469 | {
|
---|
470 | my $self = shift(@_);
|
---|
471 |
|
---|
472 | my ($metaname) = @_;
|
---|
473 |
|
---|
474 | my $dcterm_mapping = {
|
---|
475 | "alternative" => "dc.title",
|
---|
476 | "tableOfContents" => "dc.description",
|
---|
477 | "abstract" => "dc.description",
|
---|
478 | "created" => "dc.date",
|
---|
479 | "valid" => "dc.date",
|
---|
480 | "available" => "dc.date",
|
---|
481 | "issued" => "dc.date",
|
---|
482 | "modified" => "dc.date",
|
---|
483 | "dateAccepted" => "dc.date",
|
---|
484 | "dateCopyrighted" => "dc.date",
|
---|
485 | "dateSubmitted" => "dc.date",
|
---|
486 | "extent" => "dc.format",
|
---|
487 | "medium" => "dc.format",
|
---|
488 | "isVersionOf" => "dc.relation",
|
---|
489 | "hasVersion" => "dc.relation",
|
---|
490 | "isReplacedBy" => "dc.relation",
|
---|
491 | "replaces" => "dc.relation",
|
---|
492 | "isRequiredBy" => "dc.relation",
|
---|
493 | "requires" => "dc.relation",
|
---|
494 | "isPartOf" => "dc.relation",
|
---|
495 | "hasPart" => "dc.relation",
|
---|
496 | "isReferencedBy" => "dc.relation",
|
---|
497 | "references" => "dc.relation",
|
---|
498 | "isFormatOf" => "dc.relation",
|
---|
499 | "hasFormat" => "dc.relation",
|
---|
500 | "conformsTo" => "dc.relation",
|
---|
501 | "spatial" => "dc.coverage",
|
---|
502 | "temporal" => "dc.coverage",
|
---|
503 | "audience" => "dc.any",
|
---|
504 | "accrualMethod" => "dc.any",
|
---|
505 | "accrualPeriodicity" => "dc.any",
|
---|
506 | "accrualPolicy" => "dc.any",
|
---|
507 | "instructionalMethod" => "dc.any",
|
---|
508 | "provenance" => "dc.any",
|
---|
509 | "rightsHolder" => "dc.any",
|
---|
510 | "mediator" => "audience",
|
---|
511 | "educationLevel" => "audience",
|
---|
512 | "accessRights" => "dc.rights",
|
---|
513 | "license" => "dc.rights",
|
---|
514 | "bibliographicCitation" => "dc.identifier"
|
---|
515 | };
|
---|
516 |
|
---|
517 | my ($prefix,$name) = ($metaname =~ m/^(.*?)\.(.*?)$/);
|
---|
518 |
|
---|
519 | if ($prefix eq "dcterms")
|
---|
520 | {
|
---|
521 | if (defined $dcterm_mapping->{$name})
|
---|
522 | {
|
---|
523 | return $dcterm_mapping->{$name}."^".$name;
|
---|
524 | }
|
---|
525 |
|
---|
526 | }
|
---|
527 | return $metaname; # didn't get a match, return param passed in unchanged
|
---|
528 | }
|
---|
529 |
|
---|
530 |
|
---|
531 | sub extract_oai_metadata {
|
---|
532 | my $self = shift (@_);
|
---|
533 | my ($textref, $metadata) = @_;
|
---|
534 | my $outhandle = $self->{'outhandle'};
|
---|
535 |
|
---|
536 | # Only handles DC metadata
|
---|
537 |
|
---|
538 | $self->open_prettyprint_metadata_table();
|
---|
539 |
|
---|
540 | if ($$textref =~ m/<metadata\s*>(.*?)<\/metadata\s*>/s)
|
---|
541 | {
|
---|
542 | my $metadata_text = $1;
|
---|
543 |
|
---|
544 | # locate and remove outermost tag (ignoring any attribute information in top-level tag)
|
---|
545 | my ($wrapper_metadata_xml,$inner_metadata_text) = ($metadata_text =~ m/<([^ >]+).*?>(.*?)<\/\1>/s);
|
---|
546 |
|
---|
547 | # split tag into namespace and tag name
|
---|
548 | my($namespace,$top_level_prefix) = ($wrapper_metadata_xml =~ m/^(.*?):(.*?)$/);
|
---|
549 |
|
---|
550 | # sometimes, the dc namespace is not specified as the prefix in each element (like <dc:title>)
|
---|
551 | # but is rather defined in the wrapper element containing the various dc meta elements,
|
---|
552 | # like <dc><title></title><creator></creator></dc>.
|
---|
553 | # In such a case, we use this wrapper element as the top_level_prefix
|
---|
554 | if(!defined $top_level_prefix && defined $wrapper_metadata_xml && $wrapper_metadata_xml =~ m/dc$/) {
|
---|
555 | $top_level_prefix = $wrapper_metadata_xml;
|
---|
556 | }
|
---|
557 |
|
---|
558 | if ($top_level_prefix !~ m/dc$/) {
|
---|
559 | print $outhandle "Warning: OAIPlugin currently only designed for Dublin Core (or variant) metadata\n";
|
---|
560 | print $outhandle " This recorded metadata section '$top_level_prefix' does not appear to match.\n";
|
---|
561 | print $outhandle " Metadata assumed to be in form: <prefix:tag>value</prefix:tag> and will be converted\n";
|
---|
562 | print $outhandle " into Greenstone metadata as prefix.tag = value\n";
|
---|
563 | }
|
---|
564 |
|
---|
565 | while ($inner_metadata_text =~ m/<([^ >]+).*?>(.*?)<\/\1>(.*)/s)
|
---|
566 | {
|
---|
567 | # if URL given for document as identifier metadata, store it ...
|
---|
568 | # $doc_obj->add_utf8_metadata($cursection, "URL", $web_url);
|
---|
569 |
|
---|
570 | my $metaname = $1;
|
---|
571 | my $metavalue = $2;
|
---|
572 | $inner_metadata_text = $3;
|
---|
573 |
|
---|
574 | # print STDERR "*** metaname = $metaname\n";
|
---|
575 | # print STDERR "*** metavalue = $metavalue\n";
|
---|
576 |
|
---|
577 | # $metaname =~ s/^(dc:)?(.)/\u$2/; # strip of optional prefix and uppercase first letter
|
---|
578 | $metaname =~ s/:/\./;
|
---|
579 | if ($metaname !~ m/\./)
|
---|
580 | {
|
---|
581 | $metaname = "$top_level_prefix.$metaname";
|
---|
582 | # print STDERR "*** metaname = $metaname\tmetavalue = $metavalue\n";
|
---|
583 | }
|
---|
584 | $metaname =~ s/\.(.)/\.\u$1/;
|
---|
585 |
|
---|
586 | $metaname = $self->remap_dcterms_metadata($metaname);
|
---|
587 |
|
---|
588 | $metavalue =~ s/\[/[/g;
|
---|
589 | $metavalue =~ s/\]/]/g;
|
---|
590 |
|
---|
591 |
|
---|
592 | # if ($metaname eq "Identifier")
|
---|
593 | # {
|
---|
594 | # # name clashes with GSDL reserved metadata name for hash id
|
---|
595 | # $metaname = "URL";
|
---|
596 | # }
|
---|
597 |
|
---|
598 | if (defined $metadata->{$metaname})
|
---|
599 | {
|
---|
600 | push(@{$metadata->{$metaname}},$metavalue);
|
---|
601 |
|
---|
602 | }
|
---|
603 | else
|
---|
604 | {
|
---|
605 | $metadata->{$metaname} = [ $metavalue ];
|
---|
606 | }
|
---|
607 |
|
---|
608 | $self->add_prettyprint_metadata_line($metaname, $metavalue);
|
---|
609 |
|
---|
610 | }
|
---|
611 | }
|
---|
612 |
|
---|
613 | $self->close_prettyprint_metadata_table();
|
---|
614 | }
|
---|
615 |
|
---|
616 | ## we know from the file extension, so doesn't need to check the doctype
|
---|
617 | sub check_doctype {
|
---|
618 |
|
---|
619 | return 1;
|
---|
620 | }
|
---|
621 |
|
---|
622 | 1;
|
---|