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 | { 'name' => "xxx",
|
---|
51 | 'desc' => "{OAIPlugin.xxx}",
|
---|
52 | 'type' => "metadata",
|
---|
53 | 'reqd' => "no",
|
---|
54 | 'deft' => "gi.Sourcedoc" }
|
---|
55 | ];
|
---|
56 |
|
---|
57 | my $options = { 'name' => "OAIPlugin",
|
---|
58 | 'desc' => "{OAIPlugin.desc}",
|
---|
59 | 'abstract' => "no",
|
---|
60 | 'inherits' => "yes",
|
---|
61 | 'explodes' => "yes",
|
---|
62 | 'args' => $arguments };
|
---|
63 |
|
---|
64 |
|
---|
65 | sub new {
|
---|
66 | my ($class) = shift (@_);
|
---|
67 | my ($pluginlist,$inputargs,$hashArgOptLists) = @_;
|
---|
68 | push(@$pluginlist, $class);
|
---|
69 |
|
---|
70 | push(@{$hashArgOptLists->{"ArgList"}},@{$arguments});
|
---|
71 | push(@{$hashArgOptLists->{"OptList"}},$options);
|
---|
72 |
|
---|
73 | new ReadTextFile($pluginlist, $inputargs, $hashArgOptLists,1);
|
---|
74 | my $self = new ReadXMLFile($pluginlist, $inputargs, $hashArgOptLists);
|
---|
75 |
|
---|
76 | return bless $self, $class;
|
---|
77 | }
|
---|
78 |
|
---|
79 | sub get_default_process_exp {
|
---|
80 | my $self = shift (@_);
|
---|
81 |
|
---|
82 | return q^(?i)(\.oai)$^;
|
---|
83 | }
|
---|
84 |
|
---|
85 | sub get_doctype {
|
---|
86 | my $self = shift(@_);
|
---|
87 |
|
---|
88 | return "OAI-PMH";
|
---|
89 | }
|
---|
90 |
|
---|
91 | sub xml_start_document {
|
---|
92 | my $self = shift (@_);
|
---|
93 | $self->{'in_metadata_node'} = 0;
|
---|
94 | $self->{'rawxml'} = "";
|
---|
95 | $self->{'saved_metadata'} = {};
|
---|
96 | }
|
---|
97 |
|
---|
98 | sub xml_end_document {
|
---|
99 | }
|
---|
100 |
|
---|
101 | sub xml_doctype {
|
---|
102 | my $self = shift(@_);
|
---|
103 |
|
---|
104 | my ($expat, $name, $sysid, $pubid, $internal) = @_;
|
---|
105 |
|
---|
106 | ##die "" if ($name !~ /^OAI-PMH$/);
|
---|
107 |
|
---|
108 | my $outhandle = $self->{'outhandle'};
|
---|
109 | print $outhandle "OAIPlugin: processing $self->{'file'}\n" if $self->{'verbosity'} > 1;
|
---|
110 | print STDERR "<Processing n='$self->{'file'}' p='OAIPlugin'>\n" if $self->{'gli'};
|
---|
111 |
|
---|
112 | }
|
---|
113 |
|
---|
114 |
|
---|
115 | sub xml_start_tag {
|
---|
116 | my $self = shift(@_);
|
---|
117 | my ($expat,$element) = @_;
|
---|
118 |
|
---|
119 | my %attr_hash = %_;
|
---|
120 |
|
---|
121 | my $attr = "";
|
---|
122 | map { $attr .= " $_=$attr_hash{$_}"; } keys %attr_hash;
|
---|
123 |
|
---|
124 | $self->{'rawxml'} .= "<$element$attr>";
|
---|
125 |
|
---|
126 | if ($element eq "metadata") {
|
---|
127 | $self->{'in_metadata_node'} = 1;
|
---|
128 | $self->{'metadata_xml'} = "";
|
---|
129 | }
|
---|
130 |
|
---|
131 | if ($self->{'in_metadata_node'}) {
|
---|
132 | $self->{'metadata_xml'} .= "<$element$attr>";
|
---|
133 | }
|
---|
134 | }
|
---|
135 |
|
---|
136 | sub xml_end_tag {
|
---|
137 | my $self = shift(@_);
|
---|
138 | my ($expat, $element) = @_;
|
---|
139 |
|
---|
140 | $self->{'rawxml'} .= "</$element>";
|
---|
141 |
|
---|
142 | if ($self->{'in_metadata_node'}) {
|
---|
143 | $self->{'metadata_xml'} .= "</$element>";
|
---|
144 | }
|
---|
145 |
|
---|
146 | if ($element eq "metadata") {
|
---|
147 | my $textref = \$self->{'metadata_xml'};
|
---|
148 | #my $metadata = $self->{'metadata'};
|
---|
149 | my $metadata = $self->{'saved_metadata'};
|
---|
150 | $self->extract_oai_metadata($textref,$metadata);
|
---|
151 |
|
---|
152 | $self->{'in_metadata_node'} = 0;
|
---|
153 | }
|
---|
154 |
|
---|
155 |
|
---|
156 | }
|
---|
157 |
|
---|
158 | sub xml_text {
|
---|
159 | my $self = shift(@_);
|
---|
160 | my ($expat) = @_;
|
---|
161 |
|
---|
162 | $self->{'rawxml'} .= $_;
|
---|
163 |
|
---|
164 | if ($self->{'in_metadata_node'}) {
|
---|
165 | $self->{'metadata_xml'} .= $_;
|
---|
166 | }
|
---|
167 | }
|
---|
168 |
|
---|
169 |
|
---|
170 | sub metadata_read {
|
---|
171 | my $self = shift (@_);
|
---|
172 |
|
---|
173 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $extrametakeys, $extrametadata, $processor, $maxdocs, $gli) = @_;
|
---|
174 |
|
---|
175 | # can we process this file??
|
---|
176 | my ($filename_full_path, $filename_no_path) = &util::get_full_filenames($base_dir, $file);
|
---|
177 | return undef unless $self->can_process_this_file($filename_full_path);
|
---|
178 | # print STDERR "initial\n";
|
---|
179 | # foreach my $k (keys %$metadata) {
|
---|
180 | # print STDERR "$k=".join (", ", @{$metadata->{$k}})."; ";
|
---|
181 | # }
|
---|
182 | # print STDERR "\n";
|
---|
183 |
|
---|
184 | my $total_count = 0; # is total count used?
|
---|
185 | if (!$self->parse_file($filename_full_path, $file, $gli)) {
|
---|
186 | $self->{'saved_metadata'} = undef;
|
---|
187 | return undef;
|
---|
188 | }
|
---|
189 |
|
---|
190 | my $new_metadata = $self->{'saved_metadata'};
|
---|
191 | $self->{'saved_metadata'} = undef;
|
---|
192 | # add the pretty metadata table as metadata
|
---|
193 | my $ppmd_table = $self->{'ppmd_table'};
|
---|
194 | $new_metadata->{'prettymd'} = $ppmd_table;
|
---|
195 | $self->{'ppmd_table'} = undef;
|
---|
196 |
|
---|
197 | print STDERR "after parse\n";
|
---|
198 | foreach my $k (keys %$new_metadata) {
|
---|
199 | print STDERR "$k=".join (", ", @{$new_metadata->{$k}})."; ";
|
---|
200 | }
|
---|
201 | print STDERR "\n";
|
---|
202 |
|
---|
203 |
|
---|
204 | # if ($self->SUPER::read($pluginfo,$base_dir,$file,$block_hash,$new_metadata,$processor,$maxdocs,$total_count, $gli)) {
|
---|
205 | # calling "SUPER::read" at this point sets up $metadata
|
---|
206 | # data-structure. We can then, later, in OAIPlug::read decide
|
---|
207 | # whether this $metadata will stick to an accompanying file,
|
---|
208 | # or else needs a new doc object to be formed that contains
|
---|
209 | # purely metadata
|
---|
210 |
|
---|
211 | # $self->{'metadata'} = undef;
|
---|
212 | # print STDERR "after erad\n";
|
---|
213 | # foreach my $k (keys %$metadata) {
|
---|
214 | # print STDERR "$k=".join (", ", @{$metadata->{$k}})."; ";
|
---|
215 | # }
|
---|
216 | # print STDERR "\n";
|
---|
217 | my $url_array = $new_metadata->{'dc.Identifier'};
|
---|
218 | my $num_urls = (defined $url_array) ? scalar(@$url_array) : 0;
|
---|
219 | print STDERR "$num_urls urls for $file\n";
|
---|
220 | my $srcdoc_exists = 0;
|
---|
221 | my $srcdoc_pos = 0;
|
---|
222 | my $filename_dir = &util::filename_head($filename_full_path);
|
---|
223 | my $filename_for_metadata = $file;
|
---|
224 | for (my $i=0; $i<$num_urls; $i++) {
|
---|
225 |
|
---|
226 | if ($url_array->[$i] !~ m/^(https?|ftp):/) {
|
---|
227 |
|
---|
228 | my $src_filename = &util::filename_cat($filename_dir, $url_array->[$i]);
|
---|
229 |
|
---|
230 | if (-e $src_filename) {
|
---|
231 | $srcdoc_pos = $i;
|
---|
232 | $srcdoc_exists = 1;
|
---|
233 | $filename_for_metadata = $url_array->[$i];
|
---|
234 | last;
|
---|
235 | }
|
---|
236 | }
|
---|
237 | }
|
---|
238 |
|
---|
239 |
|
---|
240 | if ($srcdoc_exists)
|
---|
241 | {
|
---|
242 | $self->{'oai-files'}->{$file}->{'srcdoc_exists'} = 1;
|
---|
243 | }
|
---|
244 | else {
|
---|
245 | # save the rawxml for the source document
|
---|
246 | $self->{'oai-files'}->{$file}->{'srcdoc_exists'} = 0;
|
---|
247 | $self->{'oai-files'}->{$file}->{'rawxml'} = $self->{'rawxml'};
|
---|
248 | $self->{'rawxml'} = "";
|
---|
249 | print STDERR "raw xml = $self->{'oai-files'}->{$file}->{'rawxml'}\n";
|
---|
250 | }
|
---|
251 |
|
---|
252 | ### print STDERR "**** storing OAI file: $file\n";
|
---|
253 |
|
---|
254 | # return all the metadata we have extracted to the caller.
|
---|
255 | # Directory plug will pass it back in at read time, so we don't need to extract it again.
|
---|
256 | $extrametadata->{$filename_for_metadata} = $new_metadata;
|
---|
257 | push(@$extrametakeys, $filename_for_metadata);
|
---|
258 |
|
---|
259 | return 1;
|
---|
260 |
|
---|
261 | }
|
---|
262 |
|
---|
263 |
|
---|
264 | sub read {
|
---|
265 | my $self = shift (@_);
|
---|
266 |
|
---|
267 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
---|
268 |
|
---|
269 |
|
---|
270 | ### print STDERR "**** checking OAI read: $file\n";
|
---|
271 |
|
---|
272 | if (!defined $self->{'oai-files'}->{$file}) {
|
---|
273 | return undef;
|
---|
274 | }
|
---|
275 |
|
---|
276 |
|
---|
277 | my $srcdoc_exists = $self->{'oai-files'}->{$file}->{'srcdoc_exists'};
|
---|
278 | if ($srcdoc_exists) {
|
---|
279 | # do nothing more
|
---|
280 | # no more need to access details of this $file => tidy up as you go
|
---|
281 | delete $self->{'oai-files'}->{$file};
|
---|
282 | return 0; # not processed here, but don't pass on to rest of plugins
|
---|
283 | }
|
---|
284 |
|
---|
285 | ### print STDERR "**** !!!!! srcdoc_exists = $srcdoc_exists\n";
|
---|
286 |
|
---|
287 | my $filename = $file;
|
---|
288 | $filename = &util::filename_cat ($base_dir, $file) if $base_dir =~ /\w/;
|
---|
289 |
|
---|
290 | # Do encoding stuff on metadata
|
---|
291 | my ($language, $encoding) = $self->textcat_get_language_encoding ($filename);
|
---|
292 |
|
---|
293 | # create a new document
|
---|
294 | my $doc_obj = new doc ($filename, "indexed_doc");
|
---|
295 | my $top_section = $doc_obj->get_top_section;
|
---|
296 | my $plugin_type = $self->{'plugin_type'};
|
---|
297 |
|
---|
298 | $doc_obj->add_utf8_metadata($top_section, "Language", $language);
|
---|
299 | $doc_obj->add_utf8_metadata($top_section, "Encoding", $encoding);
|
---|
300 | $doc_obj->add_utf8_metadata($top_section, "Plugin", $plugin_type);
|
---|
301 | $doc_obj->add_metadata($top_section, "FileFormat", "OAI");
|
---|
302 | $doc_obj->add_metadata($top_section, "FileSize", (-s $filename));
|
---|
303 |
|
---|
304 | # include any metadata passed in from previous plugins
|
---|
305 | # note that this metadata is associated with the top level section
|
---|
306 | $self->extra_metadata ($doc_obj, $doc_obj->get_top_section(), $metadata);
|
---|
307 |
|
---|
308 | # do plugin specific processing of doc_obj
|
---|
309 | print STDERR "raw xml 2 = $self->{'oai-files'}->{$file}->{'rawxml'}\n";
|
---|
310 | my $text = $self->{'oai-files'}->{$file}->{'rawxml'};
|
---|
311 | delete $self->{'oai-files'}->{$file};
|
---|
312 |
|
---|
313 | unless (defined ($self->process(\$text, $pluginfo, $base_dir, $file, $metadata, $doc_obj))) {
|
---|
314 | print STDERR "<ProcessingError n='$file'>\n" if ($gli);
|
---|
315 | return -1;
|
---|
316 | }
|
---|
317 |
|
---|
318 | # do any automatic metadata extraction
|
---|
319 | $self->auto_extract_metadata ($doc_obj);
|
---|
320 |
|
---|
321 | # add an OID
|
---|
322 | $self->add_OID($doc_obj);
|
---|
323 |
|
---|
324 | # process the document
|
---|
325 | $processor->process($doc_obj);
|
---|
326 |
|
---|
327 | $self->{'num_processed'} ++;
|
---|
328 |
|
---|
329 | return 1; # processed the file
|
---|
330 | }
|
---|
331 |
|
---|
332 |
|
---|
333 | sub read_old {
|
---|
334 | my $self = shift (@_);
|
---|
335 |
|
---|
336 | my ($pluginfo, $base_dir, $file, $block_hash, $metadata, $processor, $maxdocs, $total_count, $gli) = @_;
|
---|
337 |
|
---|
338 | my $outhandle = $self->{'outhandle'};
|
---|
339 |
|
---|
340 | my $filename = $file;
|
---|
341 | $filename = &util::filename_cat ($base_dir, $file) if $base_dir =~ /\w/;
|
---|
342 |
|
---|
343 | # block the srcdocs dir - we will process files in them when we find an OAI record for them
|
---|
344 | return 0 if ((-d $filename) && ($filename =~ m/srcdocs$/));
|
---|
345 | if ($self->SUPER::read(@_)) {
|
---|
346 | # Do encoding stuff
|
---|
347 | my ($language, $encoding) = $self->textcat_get_language_encoding ($filename);
|
---|
348 |
|
---|
349 | my $url_array = $metadata->{'dc.Identifier'};
|
---|
350 | my $num_urls = (defined $url_array) ? scalar(@$url_array) : 0;
|
---|
351 |
|
---|
352 | my $srcdoc_exists = 0;
|
---|
353 | my $srcdoc_pos = 0;
|
---|
354 | my $filename_dir = &util::filename_head($filename);
|
---|
355 |
|
---|
356 | for (my $i=0; $i<$num_urls; $i++) {
|
---|
357 | if ($url_array->[$i] !~ m/^(http|ftp):/) {
|
---|
358 |
|
---|
359 | my $src_filename = &util::filename_cat($filename_dir, $url_array->[$i]);
|
---|
360 | if (-e $src_filename) {
|
---|
361 | $srcdoc_pos = $i;
|
---|
362 | $srcdoc_exists = 1;
|
---|
363 | }
|
---|
364 | }
|
---|
365 | }
|
---|
366 |
|
---|
367 | if ($srcdoc_exists)
|
---|
368 | {
|
---|
369 | print $outhandle "OAIPlugin: passing metadata on to $url_array->[0]\n"
|
---|
370 | if ($self->{'verbosity'}>1);
|
---|
371 |
|
---|
372 |
|
---|
373 | # Make pretty print metadata table stick with src filename
|
---|
374 | my $ppmd_table = $self->{'ppmd_table'};
|
---|
375 | $metadata->{'prettymd'} = [ $ppmd_table ];
|
---|
376 | $self->{'ppmd_table'} = undef;
|
---|
377 |
|
---|
378 | return &plugin::read ($pluginfo, $filename_dir, $url_array->[0],
|
---|
379 | $block_hash, $metadata, $processor, $maxdocs,
|
---|
380 | $total_count, $gli);
|
---|
381 | }
|
---|
382 | else
|
---|
383 | {
|
---|
384 | # create a new document
|
---|
385 | my $doc_obj = new doc ($filename, "indexed_doc");
|
---|
386 | my $top_section = $doc_obj->get_top_section;
|
---|
387 | my $plugin_type = $self->{'plugin_type'};
|
---|
388 |
|
---|
389 | $doc_obj->add_utf8_metadata($top_section, "Language", $language);
|
---|
390 | $doc_obj->add_utf8_metadata($top_section, "Encoding", $encoding);
|
---|
391 | $doc_obj->add_utf8_metadata($top_section, "Plugin", $plugin_type);
|
---|
392 | $doc_obj->add_metadata($top_section, "FileFormat", "OAI");
|
---|
393 | $doc_obj->add_metadata($top_section, "FileSize", (-s $filename));
|
---|
394 |
|
---|
395 | # include any metadata passed in from previous plugins
|
---|
396 | # note that this metadata is associated with the top level section
|
---|
397 | $self->extra_metadata ($doc_obj, $doc_obj->get_top_section(), $metadata);
|
---|
398 |
|
---|
399 | # do plugin specific processing of doc_obj
|
---|
400 | my $textref = \$self->{'rawxml'};
|
---|
401 | unless (defined ($self->process($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj))) {
|
---|
402 | print STDERR "<ProcessingError n='$file'>\n" if ($gli);
|
---|
403 | return -1;
|
---|
404 | }
|
---|
405 |
|
---|
406 | # do any automatic metadata extraction
|
---|
407 | $self->auto_extract_metadata ($doc_obj);
|
---|
408 |
|
---|
409 | # add an OID
|
---|
410 | $self->add_OID($doc_obj);
|
---|
411 |
|
---|
412 | my $ppmd_table = $self->{'ppmd_table'};
|
---|
413 | $doc_obj->add_utf8_metadata($top_section,"prettymd",$ppmd_table);
|
---|
414 | $self->{'ppmd_table'} = undef;
|
---|
415 |
|
---|
416 | # process the document
|
---|
417 | $processor->process($doc_obj);
|
---|
418 |
|
---|
419 | $self->{'num_processed'} ++;
|
---|
420 |
|
---|
421 | return 1; # processed the file
|
---|
422 | }
|
---|
423 | }
|
---|
424 | else {
|
---|
425 | return undef;
|
---|
426 | }
|
---|
427 | }
|
---|
428 |
|
---|
429 |
|
---|
430 | # do plugin specific processing of doc_obj
|
---|
431 | sub process {
|
---|
432 | my $self = shift (@_);
|
---|
433 | my ($textref, $pluginfo, $base_dir, $file, $metadata, $doc_obj, $gli) = @_;
|
---|
434 | my $outhandle = $self->{'outhandle'};
|
---|
435 |
|
---|
436 | print STDERR "<Processing n='$file' p='OAIPlugin'>\n" if ($gli);
|
---|
437 | print $outhandle "OAIPlugin: processing $file\n"
|
---|
438 | if $self->{'verbosity'} > 1;
|
---|
439 |
|
---|
440 | my $cursection = $doc_obj->get_top_section();
|
---|
441 |
|
---|
442 | ## $self->extract_metadata ($textref, $metadata, $doc_obj, $cursection);
|
---|
443 |
|
---|
444 | # add text to document object
|
---|
445 |
|
---|
446 | # $$textref =~ s/<(.*?)>/$1 /g;
|
---|
447 | $$textref =~ s/</</g;
|
---|
448 | $$textref =~ s/>/>/g;
|
---|
449 | $$textref =~ s/\[/[/g;
|
---|
450 | $$textref =~ s/\]/]/g;
|
---|
451 |
|
---|
452 | ## print STDERR "*** adding text: $$textref\n";
|
---|
453 |
|
---|
454 | $doc_obj->add_utf8_text($cursection, $$textref);
|
---|
455 |
|
---|
456 | return 1;
|
---|
457 | }
|
---|
458 |
|
---|
459 |
|
---|
460 | # Improvement is to merge this with newer version in MetadataPass
|
---|
461 |
|
---|
462 | sub open_prettyprint_metadata_table
|
---|
463 | {
|
---|
464 | my $self = shift(@_);
|
---|
465 |
|
---|
466 | my $att = "width=100% cellspacing=2";
|
---|
467 | my $style = "style=\'border-bottom: 4px solid #000080\'";
|
---|
468 |
|
---|
469 | $self->{'ppmd_table'} = "\n<table $att $style>";
|
---|
470 | }
|
---|
471 |
|
---|
472 | sub add_prettyprint_metadata_line
|
---|
473 | {
|
---|
474 | my $self = shift(@_);
|
---|
475 | my ($metaname, $metavalue_utf8) = @_;
|
---|
476 |
|
---|
477 | ### $metavalue_utf8 =~ s/hdl\.handle\.net/mcgonagall.cs.waikato.ac.nz:8080\/dspace\/handle/;
|
---|
478 | $metavalue_utf8 = &util::hyperlink_text($metavalue_utf8);
|
---|
479 |
|
---|
480 | $self->{'ppmd_table'} .= " <tr bgcolor=#b5d3cd>\n";
|
---|
481 | $self->{'ppmd_table'} .= " <td width=30%>\n";
|
---|
482 | $self->{'ppmd_table'} .= " $metaname\n";
|
---|
483 | $self->{'ppmd_table'} .= " </td>\n";
|
---|
484 | $self->{'ppmd_table'} .= " <td>\n";
|
---|
485 | $self->{'ppmd_table'} .= " $metavalue_utf8\n";
|
---|
486 | $self->{'ppmd_table'} .= " </td>\n";
|
---|
487 | $self->{'ppmd_table'} .= " </tr>\n";
|
---|
488 |
|
---|
489 | }
|
---|
490 |
|
---|
491 | sub close_prettyprint_metadata_table
|
---|
492 | {
|
---|
493 | my $self = shift(@_);
|
---|
494 |
|
---|
495 | $self->{'ppmd_table'} .= "</table>\n";
|
---|
496 | }
|
---|
497 |
|
---|
498 |
|
---|
499 | sub remap_dcterms_metadata
|
---|
500 | {
|
---|
501 | my $self = shift(@_);
|
---|
502 |
|
---|
503 | my ($metaname) = @_;
|
---|
504 |
|
---|
505 | my $dcterm_mapping = {
|
---|
506 | "alternative" => "dc.title",
|
---|
507 | "tableOfContents" => "dc.description",
|
---|
508 | "abstract" => "dc.description",
|
---|
509 | "created" => "dc.date",
|
---|
510 | "valid" => "dc.date",
|
---|
511 | "available" => "dc.date",
|
---|
512 | "issued" => "dc.date",
|
---|
513 | "modified" => "dc.date",
|
---|
514 | "dateAccepted" => "dc.date",
|
---|
515 | "dateCopyrighted" => "dc.date",
|
---|
516 | "dateSubmitted" => "dc.date",
|
---|
517 | "extent" => "dc.format",
|
---|
518 | "medium" => "dc.format",
|
---|
519 | "isVersionOf" => "dc.relation",
|
---|
520 | "hasVersion" => "dc.relation",
|
---|
521 | "isReplacedBy" => "dc.relation",
|
---|
522 | "replaces" => "dc.relation",
|
---|
523 | "isRequiredBy" => "dc.relation",
|
---|
524 | "requires" => "dc.relation",
|
---|
525 | "isPartOf" => "dc.relation",
|
---|
526 | "hasPart" => "dc.relation",
|
---|
527 | "isReferencedBy" => "dc.relation",
|
---|
528 | "references" => "dc.relation",
|
---|
529 | "isFormatOf" => "dc.relation",
|
---|
530 | "hasFormat" => "dc.relation",
|
---|
531 | "conformsTo" => "dc.relation",
|
---|
532 | "spatial" => "dc.coverage",
|
---|
533 | "temporal" => "dc.coverage",
|
---|
534 | "audience" => "dc.any",
|
---|
535 | "accrualMethod" => "dc.any",
|
---|
536 | "accrualPeriodicity" => "dc.any",
|
---|
537 | "accrualPolicy" => "dc.any",
|
---|
538 | "instructionalMethod" => "dc.any",
|
---|
539 | "provenance" => "dc.any",
|
---|
540 | "rightsHolder" => "dc.any",
|
---|
541 | "mediator" => "audience",
|
---|
542 | "educationLevel" => "audience",
|
---|
543 | "accessRights" => "dc.rights",
|
---|
544 | "license" => "dc.rights",
|
---|
545 | "bibliographicCitation" => "dc.identifier"
|
---|
546 | };
|
---|
547 |
|
---|
548 | my ($prefix,$name) = ($metaname =~ m/^(.*?)\.(.*?)$/);
|
---|
549 |
|
---|
550 | if ($prefix eq "dcterms")
|
---|
551 | {
|
---|
552 | if (defined $dcterm_mapping->{$name})
|
---|
553 | {
|
---|
554 | return $dcterm_mapping->{$name}."^".$name;
|
---|
555 | }
|
---|
556 |
|
---|
557 | }
|
---|
558 | return $metaname; # didn't get a match, return param passed in unchanged
|
---|
559 | }
|
---|
560 |
|
---|
561 |
|
---|
562 | sub extract_oai_metadata {
|
---|
563 | my $self = shift (@_);
|
---|
564 | my ($textref, $metadata) = @_;
|
---|
565 | my $outhandle = $self->{'outhandle'};
|
---|
566 |
|
---|
567 | # Only handles DC metadata
|
---|
568 |
|
---|
569 | $self->open_prettyprint_metadata_table();
|
---|
570 |
|
---|
571 | if ($$textref =~ m/<metadata\s*>(.*?)<\/metadata\s*>/s)
|
---|
572 | {
|
---|
573 | my $metadata_text = $1;
|
---|
574 |
|
---|
575 | # locate and remove outermost tag (ignoring any attribute information in top-level tag)
|
---|
576 | my ($wrapper_metadata_xml,$inner_metadata_text) = ($metadata_text =~ m/<([^ >]+).*?>(.*?)<\/\1>/s);
|
---|
577 |
|
---|
578 | # split tag into namespace and tag name
|
---|
579 | my($namespace,$top_level_prefix) = ($wrapper_metadata_xml =~ m/^(.*?):(.*?)$/);
|
---|
580 |
|
---|
581 | # sometimes, the dc namespace is not specified as the prefix in each element (like <dc:title>)
|
---|
582 | # but is rather defined in the wrapper element containing the various dc meta elements,
|
---|
583 | # like <dc><title></title><creator></creator></dc>.
|
---|
584 | # In such a case, we use this wrapper element as the top_level_prefix
|
---|
585 | if(!defined $top_level_prefix && defined $wrapper_metadata_xml && $wrapper_metadata_xml =~ m/dc$/) {
|
---|
586 | $top_level_prefix = $wrapper_metadata_xml;
|
---|
587 | }
|
---|
588 |
|
---|
589 | if ($top_level_prefix !~ m/dc$/) {
|
---|
590 | print $outhandle "Warning: OAIPlugin currently only designed for Dublin Core (or variant) metadata\n";
|
---|
591 | print $outhandle " This recorded metadata section '$top_level_prefix' does not appear to match.\n";
|
---|
592 | print $outhandle " Metadata assumed to be in form: <prefix:tag>value</prefix:tag> and will be converted\n";
|
---|
593 | print $outhandle " into Greenstone metadata as prefix.tag = value\n";
|
---|
594 | }
|
---|
595 |
|
---|
596 | while ($inner_metadata_text =~ m/<([^ >]+).*?>(.*?)<\/\1>(.*)/s)
|
---|
597 | {
|
---|
598 | # if URL given for document as identifier metadata, store it ...
|
---|
599 | # $doc_obj->add_utf8_metadata($cursection, "URL", $web_url);
|
---|
600 |
|
---|
601 | my $metaname = $1;
|
---|
602 | my $metavalue = $2;
|
---|
603 | $inner_metadata_text = $3;
|
---|
604 |
|
---|
605 | # print STDERR "*** metaname = $metaname\n";
|
---|
606 | # print STDERR "*** metavalue = $metavalue\n";
|
---|
607 |
|
---|
608 | # $metaname =~ s/^(dc:)?(.)/\u$2/; # strip of optional prefix and uppercase first letter
|
---|
609 | $metaname =~ s/:/\./;
|
---|
610 | if ($metaname !~ m/\./)
|
---|
611 | {
|
---|
612 | $metaname = "$top_level_prefix.$metaname";
|
---|
613 | # print STDERR "*** metaname = $metaname\tmetavalue = $metavalue\n";
|
---|
614 | }
|
---|
615 | $metaname =~ s/\.(.)/\.\u$1/;
|
---|
616 |
|
---|
617 | $metaname = $self->remap_dcterms_metadata($metaname);
|
---|
618 |
|
---|
619 | $metavalue =~ s/\[/[/g;
|
---|
620 | $metavalue =~ s/\]/]/g;
|
---|
621 |
|
---|
622 |
|
---|
623 | # if ($metaname eq "Identifier")
|
---|
624 | # {
|
---|
625 | # # name clashes with GSDL reserved metadata name for hash id
|
---|
626 | # $metaname = "URL";
|
---|
627 | # }
|
---|
628 |
|
---|
629 | if (defined $metadata->{$metaname})
|
---|
630 | {
|
---|
631 | push(@{$metadata->{$metaname}},$metavalue);
|
---|
632 |
|
---|
633 | }
|
---|
634 | else
|
---|
635 | {
|
---|
636 | $metadata->{$metaname} = [ $metavalue ];
|
---|
637 | }
|
---|
638 |
|
---|
639 | $self->add_prettyprint_metadata_line($metaname, $metavalue);
|
---|
640 |
|
---|
641 | }
|
---|
642 | }
|
---|
643 |
|
---|
644 | $self->close_prettyprint_metadata_table();
|
---|
645 | }
|
---|
646 |
|
---|
647 | ## we know from the file extension, so doesn't need to check the doctype
|
---|
648 | sub check_doctype {
|
---|
649 |
|
---|
650 | return 1;
|
---|
651 | }
|
---|
652 |
|
---|
653 | 1;
|
---|