1
|
|
|
<?php |
2
|
|
|
/** |
3
|
|
|
* FullTextSearch_ElasticSearch - Use Elasticsearch to index the content of your nextcloud |
4
|
|
|
* |
5
|
|
|
* This file is licensed under the Affero General Public License version 3 or |
6
|
|
|
* later. See the COPYING file. |
7
|
|
|
* |
8
|
|
|
* @author Maxence Lange <[email protected]> |
9
|
|
|
* @copyright 2018 |
10
|
|
|
* @license GNU AGPL version 3 or any later version |
11
|
|
|
* |
12
|
|
|
* This program is free software: you can redistribute it and/or modify |
13
|
|
|
* it under the terms of the GNU Affero General Public License as |
14
|
|
|
* published by the Free Software Foundation, either version 3 of the |
15
|
|
|
* License, or (at your option) any later version. |
16
|
|
|
* |
17
|
|
|
* This program is distributed in the hope that it will be useful, |
18
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
19
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
20
|
|
|
* GNU Affero General Public License for more details. |
21
|
|
|
* |
22
|
|
|
* You should have received a copy of the GNU Affero General Public License |
23
|
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>. |
24
|
|
|
* |
25
|
|
|
*/ |
26
|
|
|
|
27
|
|
|
namespace OCA\FullTextSearch_ElasticSearch\Platform; |
28
|
|
|
|
29
|
|
|
use Elasticsearch\Client; |
30
|
|
|
use Elasticsearch\ClientBuilder; |
31
|
|
|
use Elasticsearch\Common\Exceptions\Curl\CouldNotConnectToHost; |
32
|
|
|
use Elasticsearch\Common\Exceptions\MaxRetriesException; |
33
|
|
|
use Exception; |
34
|
|
|
use OCA\FullTextSearch\Exceptions\InterruptException; |
35
|
|
|
use OCA\FullTextSearch\Exceptions\TickDoesNotExistException; |
36
|
|
|
use OCA\FullTextSearch\IFullTextSearchPlatform; |
37
|
|
|
use OCA\FullTextSearch\IFullTextSearchProvider; |
38
|
|
|
use OCA\FullTextSearch\Model\DocumentAccess; |
39
|
|
|
use OCA\FullTextSearch\Model\Index; |
40
|
|
|
use OCA\FullTextSearch\Model\IndexDocument; |
41
|
|
|
use OCA\FullTextSearch\Model\Runner; |
42
|
|
|
use OCA\FullTextSearch_ElasticSearch\AppInfo\Application; |
43
|
|
|
use OCA\FullTextSearch_ElasticSearch\Exceptions\ConfigurationException; |
44
|
|
|
use OCA\FullTextSearch_ElasticSearch\Service\ConfigService; |
45
|
|
|
use OCA\FullTextSearch_ElasticSearch\Service\IndexService; |
46
|
|
|
use OCA\FullTextSearch_ElasticSearch\Service\MiscService; |
47
|
|
|
use OCA\FullTextSearch_ElasticSearch\Service\SearchService; |
48
|
|
|
use OCP\AppFramework\QueryException; |
49
|
|
|
|
50
|
|
|
|
51
|
|
|
class ElasticSearchPlatform implements IFullTextSearchPlatform { |
52
|
|
|
|
53
|
|
|
/** @var ConfigService */ |
54
|
|
|
private $configService; |
55
|
|
|
|
56
|
|
|
/** @var IndexService */ |
57
|
|
|
private $indexService; |
58
|
|
|
|
59
|
|
|
/** @var SearchService */ |
60
|
|
|
private $searchService; |
61
|
|
|
|
62
|
|
|
/** @var MiscService */ |
63
|
|
|
private $miscService; |
64
|
|
|
|
65
|
|
|
/** @var Client */ |
66
|
|
|
private $client; |
67
|
|
|
|
68
|
|
|
/** @var Runner */ |
69
|
|
|
private $runner; |
70
|
|
|
|
71
|
|
|
|
72
|
|
|
/** |
73
|
|
|
* return a unique Id of the platform. |
74
|
|
|
*/ |
75
|
|
|
public function getId() { |
76
|
|
|
return 'elastic_search'; |
77
|
|
|
} |
78
|
|
|
|
79
|
|
|
/** |
80
|
|
|
* return a unique Id of the platform. |
81
|
|
|
*/ |
82
|
|
|
public function getName() { |
83
|
|
|
return 'Elasticsearch'; |
84
|
|
|
} |
85
|
|
|
|
86
|
|
|
|
87
|
|
|
/** |
88
|
|
|
* @return string |
89
|
|
|
*/ |
90
|
|
|
public function getVersion() { |
91
|
|
|
return $this->configService->getAppValue('installed_version'); |
92
|
|
|
} |
93
|
|
|
|
94
|
|
|
// public function getClient() { |
|
|
|
|
95
|
|
|
// return $this->client; |
96
|
|
|
// } |
97
|
|
|
|
98
|
|
|
|
99
|
|
|
/** |
100
|
|
|
* @param Runner $runner |
101
|
|
|
*/ |
102
|
|
|
public function setRunner(Runner $runner) { |
103
|
|
|
$this->runner = $runner; |
104
|
|
|
} |
105
|
|
|
|
106
|
|
|
/** |
107
|
|
|
* @param $action |
108
|
|
|
* |
109
|
|
|
* @throws InterruptException |
110
|
|
|
* @throws TickDoesNotExistException |
111
|
|
|
*/ |
112
|
|
|
private function updateRunner($action) { |
113
|
|
|
if ($this->runner === null) { |
114
|
|
|
return; |
115
|
|
|
} |
116
|
|
|
|
117
|
|
|
$this->runner->update($action); |
118
|
|
|
} |
119
|
|
|
|
120
|
|
|
|
121
|
|
|
/** |
122
|
|
|
* @param $line |
123
|
|
|
*/ |
124
|
|
|
private function outputRunner($line) { |
125
|
|
|
if ($this->runner === null) { |
126
|
|
|
return; |
127
|
|
|
} |
128
|
|
|
|
129
|
|
|
$this->runner->output($line); |
130
|
|
|
} |
131
|
|
|
|
132
|
|
|
|
133
|
|
|
/** |
134
|
|
|
* Called when loading the platform. |
135
|
|
|
* |
136
|
|
|
* Loading some container and connect to ElasticSearch. |
137
|
|
|
* |
138
|
|
|
* @throws ConfigurationException |
139
|
|
|
* @throws QueryException |
140
|
|
|
*/ |
141
|
|
|
public function loadPlatform() { |
142
|
|
|
$app = new Application(); |
143
|
|
|
|
144
|
|
|
$container = $app->getContainer(); |
145
|
|
|
$this->configService = $container->query(ConfigService::class); |
146
|
|
|
$this->indexService = $container->query(IndexService::class); |
147
|
|
|
$this->searchService = $container->query(SearchService::class); |
148
|
|
|
$this->miscService = $container->query(MiscService::class); |
149
|
|
|
|
150
|
|
|
try { |
151
|
|
|
$this->connectToElastic($this->configService->getElasticHost()); |
152
|
|
|
} catch (ConfigurationException $e) { |
153
|
|
|
throw $e; |
154
|
|
|
} |
155
|
|
|
} |
156
|
|
|
|
157
|
|
|
|
158
|
|
|
/** |
159
|
|
|
* not used yet. |
160
|
|
|
*/ |
161
|
|
|
public function testPlatform() { |
162
|
|
|
} |
163
|
|
|
|
164
|
|
|
|
165
|
|
|
/** |
166
|
|
|
* called before any index |
167
|
|
|
* |
168
|
|
|
* We create a general index. |
169
|
|
|
* |
170
|
|
|
* @param IFullTextSearchProvider $provider |
171
|
|
|
* |
172
|
|
|
* @throws ConfigurationException |
173
|
|
|
*/ |
174
|
|
|
public function initializeIndex(IFullTextSearchProvider $provider) { |
175
|
|
|
$this->indexService->initializeIndex($this->client); |
176
|
|
|
|
177
|
|
|
$provider->onInitializingIndex($this); |
178
|
|
|
} |
179
|
|
|
|
180
|
|
|
|
181
|
|
|
/** |
182
|
|
|
* resetIndex(); |
183
|
|
|
* |
184
|
|
|
* Called when admin wants to remove an index specific to a $provider. |
185
|
|
|
* $provider can be null, meaning a reset of the whole index. |
186
|
|
|
* |
187
|
|
|
* @param IFullTextSearchProvider|null $provider |
188
|
|
|
* |
189
|
|
|
* @throws ConfigurationException |
190
|
|
|
*/ |
191
|
|
|
public function resetIndex($provider) { |
192
|
|
|
|
193
|
|
|
if ($provider instanceof IFullTextSearchProvider) { |
|
|
|
|
194
|
|
|
// TODO: need to specify the map to remove |
195
|
|
|
// TODO: need to remove entries with type=providerId |
196
|
|
|
$provider->onResettingIndex($this); |
197
|
|
|
} |
198
|
|
|
|
199
|
|
|
$this->indexService->resetIndex($this->client); |
200
|
|
|
} |
201
|
|
|
|
202
|
|
|
|
203
|
|
|
/** |
204
|
|
|
* {@inheritdoc} |
205
|
|
|
*/ |
206
|
|
|
public function indexDocuments(IFullTextSearchProvider $provider, $documents) { |
207
|
|
|
$indexes = []; |
208
|
|
|
foreach ($documents as $document) { |
209
|
|
|
$index = $this->indexDocument($provider, $document); |
210
|
|
|
if ($index !== null) { |
211
|
|
|
$indexes[] = $index; |
212
|
|
|
} |
213
|
|
|
} |
214
|
|
|
|
215
|
|
|
return $indexes; |
216
|
|
|
} |
217
|
|
|
|
218
|
|
|
|
219
|
|
|
/** |
220
|
|
|
* {@inheritdoc} |
221
|
|
|
*/ |
222
|
|
|
public function indexDocument(IFullTextSearchProvider $provider, IndexDocument $document) { |
223
|
|
|
|
224
|
|
|
$this->updateRunner('indexDocument'); |
225
|
|
|
$this->outputRunner(' . Indexing: ' . $document->getTitle()); |
226
|
|
|
|
227
|
|
|
try { |
228
|
|
|
$result = $this->indexService->indexDocument($this, $this->client, $provider, $document); |
229
|
|
|
$this->outputRunner(' result: ' . json_encode($result)); |
230
|
|
|
|
231
|
|
|
return $this->indexService->parseIndexResult($document->getIndex(), $result); |
|
|
|
|
232
|
|
|
} catch (Exception $e) { |
233
|
|
|
return $this->indexDocumentError($provider, $document, $e); |
234
|
|
|
} |
235
|
|
|
|
236
|
|
|
} |
237
|
|
|
|
238
|
|
|
|
239
|
|
|
/** |
240
|
|
|
* @param IFullTextSearchProvider $provider |
241
|
|
|
* @param IndexDocument $document |
242
|
|
|
* @param Exception $e |
243
|
|
|
* |
244
|
|
|
* @return Index |
245
|
|
|
* @throws ConfigurationException |
246
|
|
|
*/ |
247
|
|
|
private function indexDocumentError( |
248
|
|
|
IFullTextSearchProvider $provider, IndexDocument $document, Exception $e |
249
|
|
|
) { |
250
|
|
|
$message = [ |
251
|
|
|
'exception' => get_class($e), |
252
|
|
|
'message' => $e->getMessage() |
253
|
|
|
]; |
254
|
|
|
|
255
|
|
|
$document->setContent(null); |
256
|
|
|
$index = $document->getIndex(); |
257
|
|
|
$index->unsetStatus(Index::INDEX_CONTENT); |
258
|
|
|
$index->setMessage(json_encode($message)); |
259
|
|
|
|
260
|
|
|
$result = $this->indexService->indexDocument($this, $this->client, $provider, $document); |
261
|
|
|
$this->outputRunner(' result with no content: ' . json_encode($result)); |
262
|
|
|
|
263
|
|
|
return $this->indexService->parseIndexResult($document->getIndex(), $result); |
|
|
|
|
264
|
|
|
} |
265
|
|
|
|
266
|
|
|
|
267
|
|
|
/** |
268
|
|
|
* {@inheritdoc} |
269
|
|
|
*/ |
270
|
|
|
public function deleteIndexes($indexes) { |
271
|
|
|
try { |
272
|
|
|
$this->indexService->deleteIndexes($this->client, $indexes); |
273
|
|
|
} catch (ConfigurationException $e) { |
274
|
|
|
throw $e; |
275
|
|
|
} |
276
|
|
|
} |
277
|
|
|
|
278
|
|
|
|
279
|
|
|
/** |
280
|
|
|
* {@inheritdoc} |
281
|
|
|
*/ |
282
|
|
|
public function searchDocuments(IFullTextSearchProvider $provider, DocumentAccess $access, $request |
283
|
|
|
) { |
284
|
|
|
try { |
285
|
|
|
return $this->searchService->searchDocuments( |
286
|
|
|
$this, $this->client, $provider, $access, $request |
287
|
|
|
); |
288
|
|
|
} catch (ConfigurationException $e) { |
289
|
|
|
throw $e; |
290
|
|
|
} |
291
|
|
|
} |
292
|
|
|
|
293
|
|
|
|
294
|
|
|
/** |
295
|
|
|
* @param string $host |
296
|
|
|
*/ |
297
|
|
|
private function connectToElastic($host) { |
298
|
|
|
|
299
|
|
|
try { |
300
|
|
|
$hosts = [MiscService::noEndSlash($host)]; |
301
|
|
|
$this->client = ClientBuilder::create() |
302
|
|
|
->setHosts($hosts) |
303
|
|
|
->setRetries(2) |
304
|
|
|
->build(); |
305
|
|
|
|
306
|
|
|
} catch (CouldNotConnectToHost $e) { |
307
|
|
|
echo 'CouldNotConnectToHost'; |
308
|
|
|
$previous = $e->getPrevious(); |
309
|
|
|
if ($previous instanceof MaxRetriesException) { |
310
|
|
|
echo "Max retries!"; |
311
|
|
|
} |
312
|
|
|
} catch (Exception $e) { |
313
|
|
|
echo ' ElasticSearchPlatform::load() Exception --- ' . $e->getMessage() . "\n"; |
314
|
|
|
} |
315
|
|
|
} |
316
|
|
|
|
317
|
|
|
|
318
|
|
|
} |
Sometimes obsolete code just ends up commented out instead of removed. In this case it is better to remove the code once you have checked you do not need it.
The code might also have been commented out for debugging purposes. In this case it is vital that someone uncomments it again or your project may behave in very unexpected ways in production.
This check looks for comments that seem to be mostly valid code and reports them.