1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/** |
4
|
|
|
* (c) Kitodo. Key to digital objects e.V. <[email protected]> |
5
|
|
|
* |
6
|
|
|
* This file is part of the Kitodo and TYPO3 projects. |
7
|
|
|
* |
8
|
|
|
* @license GNU General Public License version 3 or later. |
9
|
|
|
* For the full copyright and license information, please read the |
10
|
|
|
* LICENSE.txt file that was distributed with this source code. |
11
|
|
|
*/ |
12
|
|
|
|
13
|
|
|
namespace Kitodo\Dlf\Command; |
14
|
|
|
|
15
|
|
|
use Kitodo\Dlf\Common\AbstractDocument; |
16
|
|
|
use Kitodo\Dlf\Command\BaseCommand; |
17
|
|
|
use Kitodo\Dlf\Common\Indexer; |
18
|
|
|
use Kitodo\Dlf\Domain\Model\Document; |
19
|
|
|
use Symfony\Component\Console\Input\InputInterface; |
20
|
|
|
use Symfony\Component\Console\Input\InputOption; |
21
|
|
|
use Symfony\Component\Console\Output\OutputInterface; |
22
|
|
|
use Symfony\Component\Console\Style\SymfonyStyle; |
23
|
|
|
use TYPO3\CMS\Core\Utility\GeneralUtility; |
24
|
|
|
use TYPO3\CMS\Core\Utility\MathUtility; |
25
|
|
|
use Phpoaipmh\Endpoint; |
26
|
|
|
use Phpoaipmh\Exception\BaseOaipmhException; |
27
|
|
|
|
28
|
|
|
/** |
29
|
|
|
* CLI Command for harvesting OAI-PMH interfaces into database and Solr. |
30
|
|
|
* |
31
|
|
|
* @package TYPO3 |
32
|
|
|
* @subpackage dlf |
33
|
|
|
* |
34
|
|
|
* @access public |
35
|
|
|
*/ |
36
|
|
|
class HarvestCommand extends BaseCommand |
37
|
|
|
{ |
38
|
|
|
/** |
39
|
|
|
* Configure the command by defining the name, options and arguments |
40
|
|
|
* |
41
|
|
|
* @access public |
42
|
|
|
* |
43
|
|
|
* @return void |
44
|
|
|
*/ |
45
|
|
|
public function configure(): void |
46
|
|
|
{ |
47
|
|
|
$this |
48
|
|
|
->setDescription('Harvest OAI-PMH contents into database and Solr.') |
49
|
|
|
->setHelp('') |
50
|
|
|
->addOption( |
51
|
|
|
'dry-run', |
52
|
|
|
null, |
53
|
|
|
InputOption::VALUE_NONE, |
54
|
|
|
'If this option is set, the files will not actually be processed but the location URIs are shown.' |
55
|
|
|
) |
56
|
|
|
->addOption( |
57
|
|
|
'lib', |
58
|
|
|
'l', |
59
|
|
|
InputOption::VALUE_REQUIRED, |
60
|
|
|
'UID of the library to harvest.' |
61
|
|
|
) |
62
|
|
|
->addOption( |
63
|
|
|
'pid', |
64
|
|
|
'p', |
65
|
|
|
InputOption::VALUE_REQUIRED, |
66
|
|
|
'UID of the page the documents should be added to.' |
67
|
|
|
) |
68
|
|
|
->addOption( |
69
|
|
|
'solr', |
70
|
|
|
's', |
71
|
|
|
InputOption::VALUE_REQUIRED, |
72
|
|
|
'[UID|index_name] of the Solr core the document should be added to.' |
73
|
|
|
) |
74
|
|
|
->addOption( |
75
|
|
|
'from', |
76
|
|
|
null, |
77
|
|
|
InputOption::VALUE_OPTIONAL, |
78
|
|
|
'Datestamp (YYYY-MM-DD) to begin harvesting from.' |
79
|
|
|
) |
80
|
|
|
->addOption( |
81
|
|
|
'until', |
82
|
|
|
null, |
83
|
|
|
InputOption::VALUE_OPTIONAL, |
84
|
|
|
'Datestamp (YYYY-MM-DD) to end harvesting on.' |
85
|
|
|
) |
86
|
|
|
->addOption( |
87
|
|
|
'set', |
88
|
|
|
null, |
89
|
|
|
InputOption::VALUE_OPTIONAL, |
90
|
|
|
'Name of the set to limit harvesting to.' |
91
|
|
|
); |
92
|
|
|
} |
93
|
|
|
|
94
|
|
|
/** |
95
|
|
|
* Executes the command to index the given document to DB and SOLR. |
96
|
|
|
* |
97
|
|
|
* @access protected |
98
|
|
|
* |
99
|
|
|
* @param InputInterface $input The input parameters |
100
|
|
|
* @param OutputInterface $output The Symfony interface for outputs on console |
101
|
|
|
* |
102
|
|
|
* @return int |
103
|
|
|
*/ |
104
|
|
|
protected function execute(InputInterface $input, OutputInterface $output): int |
105
|
|
|
{ |
106
|
|
|
$dryRun = $input->getOption('dry-run') != false ? true : false; |
107
|
|
|
|
108
|
|
|
$io = new SymfonyStyle($input, $output); |
109
|
|
|
$io->title($this->getDescription()); |
110
|
|
|
|
111
|
|
|
$this->initializeRepositories($input->getOption('pid')); |
112
|
|
|
|
113
|
|
|
if ($this->storagePid == 0) { |
114
|
|
|
$io->error('ERROR: No valid PID (' . $this->storagePid . ') given.'); |
115
|
|
|
return BaseCommand::FAILURE; |
116
|
|
|
} |
117
|
|
|
|
118
|
|
|
if ( |
119
|
|
|
!empty($input->getOption('solr')) |
120
|
|
|
&& !is_array($input->getOption('solr')) |
121
|
|
|
) { |
122
|
|
|
$allSolrCores = $this->getSolrCores($this->storagePid); |
123
|
|
|
if (MathUtility::canBeInterpretedAsInteger($input->getOption('solr'))) { |
124
|
|
|
$solrCoreUid = MathUtility::forceIntegerInRange((int) $input->getOption('solr'), 0); |
125
|
|
|
} else { |
126
|
|
|
$solrCoreUid = $allSolrCores[$input->getOption('solr')]; |
127
|
|
|
} |
128
|
|
|
// Abort if solrCoreUid is empty or not in the array of allowed solr cores. |
129
|
|
|
if (empty($solrCoreUid) || !in_array($solrCoreUid, $allSolrCores)) { |
130
|
|
|
$output_solrCores = []; |
131
|
|
|
foreach ($allSolrCores as $index_name => $uid) { |
132
|
|
|
$output_solrCores[] = $uid . ' : ' . $index_name; |
133
|
|
|
} |
134
|
|
|
if (empty($output_solrCores)) { |
135
|
|
|
$io->error('ERROR: No valid Solr core ("' . $input->getOption('solr') . '") given. No valid cores found on PID ' . $this->storagePid . ".\n"); |
136
|
|
|
return BaseCommand::FAILURE; |
137
|
|
|
} else { |
138
|
|
|
$io->error('ERROR: No valid Solr core ("' . $input->getOption('solr') . '") given. ' . "Valid cores are (<uid>:<index_name>):\n" . implode("\n", $output_solrCores) . "\n"); |
139
|
|
|
return BaseCommand::FAILURE; |
140
|
|
|
} |
141
|
|
|
} |
142
|
|
|
} else { |
143
|
|
|
$io->error('ERROR: Required parameter --solr|-s is missing or array.'); |
144
|
|
|
return BaseCommand::FAILURE; |
145
|
|
|
} |
146
|
|
|
|
147
|
|
|
if (MathUtility::canBeInterpretedAsInteger($input->getOption('lib'))) { |
148
|
|
|
$this->owner = $this->libraryRepository->findByUid(MathUtility::forceIntegerInRange((int) $input->getOption('lib'), 1)); |
149
|
|
|
} |
150
|
|
|
|
151
|
|
|
if ($this->owner) { |
152
|
|
|
$baseUrl = $this->owner->getOaiBase(); |
153
|
|
|
} else { |
154
|
|
|
$io->error('ERROR: Required parameter --lib|-l is not a valid UID.'); |
155
|
|
|
return BaseCommand::FAILURE; |
156
|
|
|
} |
157
|
|
|
if (!GeneralUtility::isValidUrl($baseUrl)) { |
158
|
|
|
$io->error('ERROR: No valid OAI Base URL set for library with given UID ("' . $input->getOption('lib') . '").'); |
159
|
|
|
return BaseCommand::FAILURE; |
160
|
|
|
} else { |
161
|
|
|
try { |
162
|
|
|
$oai = Endpoint::build($baseUrl); |
163
|
|
|
} catch (BaseoaipmhException $e) { |
164
|
|
|
$this->handleOaiError($e, $io); |
165
|
|
|
} |
166
|
|
|
} |
167
|
|
|
|
168
|
|
|
if ( |
169
|
|
|
!is_array($input->getOption('from')) |
170
|
|
|
&& preg_match('/^\d{4}-\d{2}-\d{2}$/', $input->getOption('from')) |
171
|
|
|
) { |
172
|
|
|
$from = new \DateTime($input->getOption('from')); |
173
|
|
|
} else { |
174
|
|
|
$from = null; |
175
|
|
|
} |
176
|
|
|
|
177
|
|
|
if ( |
178
|
|
|
!is_array($input->getOption('until')) |
179
|
|
|
&& preg_match('/^\d{4}-\d{2}-\d{2}$/', $input->getOption('until')) |
180
|
|
|
) { |
181
|
|
|
$until = new \DateTime($input->getOption('until')); |
182
|
|
|
} else { |
183
|
|
|
$until = null; |
184
|
|
|
} |
185
|
|
|
|
186
|
|
|
$set = null; |
187
|
|
|
if ( |
188
|
|
|
!is_array($input->getOption('set')) |
189
|
|
|
&& !empty($input->getOption('set')) |
190
|
|
|
&& !empty($oai) |
191
|
|
|
) { |
192
|
|
|
$setsAvailable = $oai->listSets(); |
193
|
|
|
foreach ($setsAvailable as $setAvailable) { |
194
|
|
|
if ((string) $setAvailable->setSpec === $input->getOption('set')) { |
195
|
|
|
$set = $input->getOption('set'); |
196
|
|
|
break; |
197
|
|
|
} |
198
|
|
|
} |
199
|
|
|
if (empty($set)) { |
200
|
|
|
$io->error('ERROR: OAI interface does not provide a set with given setSpec ("' . $input->getOption('set') . '").'); |
201
|
|
|
return BaseCommand::FAILURE; |
202
|
|
|
} |
203
|
|
|
} |
204
|
|
|
|
205
|
|
|
$identifiers = []; |
206
|
|
|
// Get OAI record identifiers to process. |
207
|
|
|
try { |
208
|
|
|
if (!empty($oai)) { |
209
|
|
|
$identifiers = $oai->listIdentifiers('mets', $from, $until, $set); |
210
|
|
|
} else { |
211
|
|
|
$io->error('ERROR: OAI interface does not exist.'); |
212
|
|
|
} |
213
|
|
|
} catch (BaseoaipmhException $exception) { |
214
|
|
|
$this->handleOaiError($exception, $io); |
215
|
|
|
} |
216
|
|
|
|
217
|
|
|
// Process all identifiers. |
218
|
|
|
$baseLocation = $baseUrl . (parse_url($baseUrl, PHP_URL_QUERY) ? '&' : '?'); |
219
|
|
|
foreach ($identifiers as $identifier) { |
220
|
|
|
// Build OAI GetRecord URL... |
221
|
|
|
$params = [ |
222
|
|
|
'verb' => 'GetRecord', |
223
|
|
|
'metadataPrefix' => 'mets', |
224
|
|
|
'identifier' => (string) $identifier->identifier |
225
|
|
|
]; |
226
|
|
|
$docLocation = $baseLocation . http_build_query($params); |
227
|
|
|
// ...index the document... |
228
|
|
|
$document = null; |
229
|
|
|
$doc = AbstractDocument::getInstance($docLocation, ['storagePid' => $this->storagePid], true); |
230
|
|
|
|
231
|
|
|
if ($doc === null) { |
232
|
|
|
$io->warning('WARNING: Document "' . $docLocation . '" could not be loaded. Skip to next document.'); |
233
|
|
|
continue; |
234
|
|
|
} |
235
|
|
|
|
236
|
|
|
if ($doc->recordId) { |
237
|
|
|
$document = $this->documentRepository->findOneByRecordId($doc->recordId); |
|
|
|
|
238
|
|
|
} |
239
|
|
|
|
240
|
|
|
if ($document === null) { |
241
|
|
|
// create new Document object |
242
|
|
|
$document = GeneralUtility::makeInstance(Document::class); |
243
|
|
|
} |
244
|
|
|
|
245
|
|
|
$document->setLocation($docLocation); |
|
|
|
|
246
|
|
|
$document->setSolrcore($solrCoreUid); |
|
|
|
|
247
|
|
|
|
248
|
|
|
if ($dryRun) { |
249
|
|
|
$io->writeln('DRY RUN: Would index ' . $document->getUid() . ' ("' . $document->getLocation() . '") on PID ' . $this->storagePid . ' and Solr core ' . $solrCoreUid . '.'); |
|
|
|
|
250
|
|
|
} else { |
251
|
|
|
if ($io->isVerbose()) { |
252
|
|
|
$io->writeln(date('Y-m-d H:i:s') . ' Indexing ' . $document->getUid() . ' ("' . $document->getLocation() . '") on PID ' . $this->storagePid . ' and Solr core ' . $solrCoreUid . '.'); |
253
|
|
|
} |
254
|
|
|
$document->setCurrentDocument($doc); |
|
|
|
|
255
|
|
|
// save to database |
256
|
|
|
$this->saveToDatabase($document); |
257
|
|
|
// add to index |
258
|
|
|
Indexer::add($document, $this->documentRepository); |
259
|
|
|
} |
260
|
|
|
} |
261
|
|
|
|
262
|
|
|
$io->success('All done!'); |
263
|
|
|
|
264
|
|
|
return BaseCommand::SUCCESS; |
265
|
|
|
} |
266
|
|
|
|
267
|
|
|
/** |
268
|
|
|
* Handles OAI errors |
269
|
|
|
* |
270
|
|
|
* @access protected |
271
|
|
|
* |
272
|
|
|
* @param BaseoaipmhException $exception Instance of exception thrown |
273
|
|
|
* @param SymfonyStyle $io |
274
|
|
|
* |
275
|
|
|
* @return void |
276
|
|
|
*/ |
277
|
|
|
protected function handleOaiError(BaseoaipmhException $exception, SymfonyStyle $io): void |
278
|
|
|
{ |
279
|
|
|
$io->error('ERROR: Trying to retrieve data from OAI interface resulted in error:' . "\n " . $exception->getMessage()); |
280
|
|
|
} |
281
|
|
|
} |
282
|
|
|
|