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
|
|
|
|
26
|
|
|
/** |
27
|
|
|
* CLI Command for indexing single documents into database and Solr. |
28
|
|
|
* |
29
|
|
|
* @package TYPO3 |
30
|
|
|
* @subpackage dlf |
31
|
|
|
* |
32
|
|
|
* @access public |
33
|
|
|
*/ |
34
|
|
|
class IndexCommand extends BaseCommand |
35
|
|
|
{ |
36
|
|
|
|
37
|
|
|
/** |
38
|
|
|
* Configure the command by defining the name, options and arguments |
39
|
|
|
* |
40
|
|
|
* @access public |
41
|
|
|
* |
42
|
|
|
* @return void |
43
|
|
|
*/ |
44
|
|
|
public function configure(): void |
45
|
|
|
{ |
46
|
|
|
$this |
47
|
|
|
->setDescription('Index single document into database and Solr.') |
48
|
|
|
->setHelp('') |
49
|
|
|
->addOption( |
50
|
|
|
'dry-run', |
51
|
|
|
null, |
52
|
|
|
InputOption::VALUE_NONE, |
53
|
|
|
'If this option is set, the files will not actually be processed but the location URI is shown.' |
54
|
|
|
) |
55
|
|
|
->addOption( |
56
|
|
|
'doc', |
57
|
|
|
'd', |
58
|
|
|
InputOption::VALUE_REQUIRED, |
59
|
|
|
'UID or URL of the document.' |
60
|
|
|
) |
61
|
|
|
->addOption( |
62
|
|
|
'pid', |
63
|
|
|
'p', |
64
|
|
|
InputOption::VALUE_REQUIRED, |
65
|
|
|
'UID of the page the document should be added to.' |
66
|
|
|
) |
67
|
|
|
->addOption( |
68
|
|
|
'solr', |
69
|
|
|
's', |
70
|
|
|
InputOption::VALUE_REQUIRED, |
71
|
|
|
'[UID|index_name] of the Solr core the document should be added to.' |
72
|
|
|
) |
73
|
|
|
->addOption( |
74
|
|
|
'owner', |
75
|
|
|
'o', |
76
|
|
|
InputOption::VALUE_OPTIONAL, |
77
|
|
|
'[UID|index_name] of the Library which should be set as owner of the document.' |
78
|
|
|
); |
79
|
|
|
} |
80
|
|
|
|
81
|
|
|
/** |
82
|
|
|
* Executes the command to index the given document to DB and SOLR. |
83
|
|
|
* |
84
|
|
|
* @access protected |
85
|
|
|
* |
86
|
|
|
* @param InputInterface $input The input parameters |
87
|
|
|
* @param OutputInterface $output The Symfony interface for outputs on console |
88
|
|
|
* |
89
|
|
|
* @return int |
90
|
|
|
*/ |
91
|
|
|
protected function execute(InputInterface $input, OutputInterface $output): int |
92
|
|
|
{ |
93
|
|
|
$dryRun = $input->getOption('dry-run') != false ? true : false; |
94
|
|
|
|
95
|
|
|
$io = new SymfonyStyle($input, $output); |
96
|
|
|
$io->title($this->getDescription()); |
97
|
|
|
|
98
|
|
|
$this->initializeRepositories($input->getOption('pid')); |
99
|
|
|
|
100
|
|
|
if ($this->storagePid == 0) { |
101
|
|
|
$io->error('ERROR: No valid PID (' . $this->storagePid . ') given.'); |
102
|
|
|
return BaseCommand::FAILURE; |
103
|
|
|
} |
104
|
|
|
|
105
|
|
|
if ( |
106
|
|
|
!empty($input->getOption('solr')) |
107
|
|
|
&& !is_array($input->getOption('solr')) |
108
|
|
|
) { |
109
|
|
|
$allSolrCores = $this->getSolrCores($this->storagePid); |
110
|
|
|
$solrCoreUid = $this->getSolrCoreUid($allSolrCores, $input->getOption('solr')); |
111
|
|
|
|
112
|
|
|
// Abort if solrCoreUid is empty or not in the array of allowed solr cores. |
113
|
|
|
if (empty($solrCoreUid) || !in_array($solrCoreUid, $allSolrCores)) { |
114
|
|
|
$output_solrCores = []; |
115
|
|
|
foreach ($allSolrCores as $index_name => $uid) { |
116
|
|
|
$output_solrCores[] = $uid . ' : ' . $index_name; |
117
|
|
|
} |
118
|
|
|
if (empty($output_solrCores)) { |
119
|
|
|
$io->error('ERROR: No valid Solr core ("' . $input->getOption('solr') . '") given. No valid cores found on PID ' . $this->storagePid . ".\n"); |
120
|
|
|
return BaseCommand::FAILURE; |
121
|
|
|
} else { |
122
|
|
|
$io->error('ERROR: No valid Solr core ("' . $input->getOption('solr') . '") given. ' . "Valid cores are (<uid>:<index_name>):\n" . implode("\n", $output_solrCores) . "\n"); |
123
|
|
|
return BaseCommand::FAILURE; |
124
|
|
|
} |
125
|
|
|
} |
126
|
|
|
} else { |
127
|
|
|
$io->error('ERROR: Required parameter --solr|-s is missing or array.'); |
128
|
|
|
return BaseCommand::FAILURE; |
129
|
|
|
} |
130
|
|
|
|
131
|
|
|
if ( |
132
|
|
|
empty($input->getOption('doc')) |
133
|
|
|
|| is_array($input->getOption('doc')) |
134
|
|
|
|| ( |
135
|
|
|
!MathUtility::canBeInterpretedAsInteger($input->getOption('doc')) |
136
|
|
|
&& !GeneralUtility::isValidUrl($input->getOption('doc')) |
137
|
|
|
) |
138
|
|
|
) { |
139
|
|
|
$io->error('ERROR: Required parameter --doc|-d is not a valid document UID or URL.'); |
140
|
|
|
return BaseCommand::FAILURE; |
141
|
|
|
} |
142
|
|
|
|
143
|
|
|
if (!empty($input->getOption('owner'))) { |
144
|
|
|
if (MathUtility::canBeInterpretedAsInteger($input->getOption('owner'))) { |
145
|
|
|
$this->owner = $this->libraryRepository->findByUid(MathUtility::forceIntegerInRange((int) $input->getOption('owner'), 1)); |
146
|
|
|
} else { |
147
|
|
|
$this->owner = $this->libraryRepository->findOneByIndexName((string) $input->getOption('owner')); |
|
|
|
|
148
|
|
|
} |
149
|
|
|
} else { |
150
|
|
|
$this->owner = null; |
151
|
|
|
} |
152
|
|
|
|
153
|
|
|
$document = null; |
154
|
|
|
$doc = null; |
155
|
|
|
|
156
|
|
|
// Try to find existing document in database |
157
|
|
|
if (MathUtility::canBeInterpretedAsInteger($input->getOption('doc'))) { |
158
|
|
|
|
159
|
|
|
$document = $this->documentRepository->findByUid($input->getOption('doc')); |
160
|
|
|
|
161
|
|
|
if ($document === null) { |
162
|
|
|
$io->error('ERROR: Document with UID "' . $input->getOption('doc') . '" could not be found on PID ' . $this->storagePid . ' .'); |
163
|
|
|
exit(1); |
|
|
|
|
164
|
|
|
} else { |
165
|
|
|
$doc = AbstractDocument::getInstance($document->getLocation(), ['storagePid' => $this->storagePid], true); |
166
|
|
|
} |
167
|
|
|
|
168
|
|
|
} else if (GeneralUtility::isValidUrl($input->getOption('doc'))) { |
169
|
|
|
$doc = AbstractDocument::getInstance($input->getOption('doc'), ['storagePid' => $this->storagePid], true); |
170
|
|
|
|
171
|
|
|
$document = $this->getDocumentFromUrl($doc, $input->getOption('doc')); |
172
|
|
|
} |
173
|
|
|
|
174
|
|
|
if ($doc === null) { |
175
|
|
|
$io->error('ERROR: Document "' . $input->getOption('doc') . '" could not be loaded.'); |
176
|
|
|
return BaseCommand::FAILURE; |
177
|
|
|
} |
178
|
|
|
|
179
|
|
|
$document->setSolrcore($solrCoreUid); |
180
|
|
|
|
181
|
|
|
if ($dryRun) { |
182
|
|
|
$io->section('DRY RUN: Would index ' . $document->getUid() . ' ("' . $document->getLocation() . '") on PID ' . $this->storagePid . ' and Solr core ' . $solrCoreUid . '.'); |
183
|
|
|
} else { |
184
|
|
|
if ($io->isVerbose()) { |
185
|
|
|
$io->section('Indexing ' . $document->getUid() . ' ("' . $document->getLocation() . '") on PID ' . $this->storagePid . ' and Solr core ' . $solrCoreUid . '.'); |
186
|
|
|
} |
187
|
|
|
$document->setCurrentDocument($doc); |
188
|
|
|
// save to database |
189
|
|
|
$this->saveToDatabase($document); |
|
|
|
|
190
|
|
|
// add to index |
191
|
|
|
Indexer::add($document, $this->documentRepository); |
|
|
|
|
192
|
|
|
} |
193
|
|
|
|
194
|
|
|
$io->success('All done!'); |
195
|
|
|
|
196
|
|
|
return BaseCommand::SUCCESS; |
197
|
|
|
} |
198
|
|
|
|
199
|
|
|
/** |
200
|
|
|
* Get document from given URL. Find it in database, if not found create the new one. |
201
|
|
|
* |
202
|
|
|
* @access private |
203
|
|
|
* |
204
|
|
|
* @param AbstractDocument $doc |
205
|
|
|
* @param string $url |
206
|
|
|
* |
207
|
|
|
* @return Document |
208
|
|
|
*/ |
209
|
|
|
private function getDocumentFromUrl($doc, string $url): Document |
210
|
|
|
{ |
211
|
|
|
$document = null; |
212
|
|
|
|
213
|
|
|
if ($doc->recordId) { |
214
|
|
|
$document = $this->documentRepository->findOneByRecordId($doc->recordId); |
|
|
|
|
215
|
|
|
} else { |
216
|
|
|
$document = $this->documentRepository->findOneByLocation($url); |
|
|
|
|
217
|
|
|
} |
218
|
|
|
|
219
|
|
|
if ($document === null) { |
220
|
|
|
// create new Document object |
221
|
|
|
$document = GeneralUtility::makeInstance(Document::class); |
222
|
|
|
} |
223
|
|
|
|
224
|
|
|
// now there must exist a document object |
225
|
|
|
if ($document) { |
226
|
|
|
$document->setLocation($url); |
|
|
|
|
227
|
|
|
} |
228
|
|
|
|
229
|
|
|
return $document; |
230
|
|
|
} |
231
|
|
|
} |
232
|
|
|
|