1
|
|
|
<?php |
2
|
|
|
declare(strict_types=1); |
3
|
|
|
|
4
|
|
|
|
5
|
|
|
/** |
6
|
|
|
* FullTextSearch - Full text search framework for Nextcloud |
7
|
|
|
* |
8
|
|
|
* This file is licensed under the Affero General Public License version 3 or |
9
|
|
|
* later. See the COPYING file. |
10
|
|
|
* |
11
|
|
|
* @author Maxence Lange <[email protected]> |
12
|
|
|
* @copyright 2018 |
13
|
|
|
* @license GNU AGPL version 3 or any later version |
14
|
|
|
* |
15
|
|
|
* This program is free software: you can redistribute it and/or modify |
16
|
|
|
* it under the terms of the GNU Affero General Public License as |
17
|
|
|
* published by the Free Software Foundation, either version 3 of the |
18
|
|
|
* License, or (at your option) any later version. |
19
|
|
|
* |
20
|
|
|
* This program is distributed in the hope that it will be useful, |
21
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
22
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
23
|
|
|
* GNU Affero General Public License for more details. |
24
|
|
|
* |
25
|
|
|
* You should have received a copy of the GNU Affero General Public License |
26
|
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>. |
27
|
|
|
* |
28
|
|
|
*/ |
29
|
|
|
|
30
|
|
|
|
31
|
|
|
namespace OC\FullTextSearch\Model; |
32
|
|
|
|
33
|
|
|
|
34
|
|
|
use JsonSerializable; |
35
|
|
|
use OCP\FullTextSearch\Model\IDocumentAccess; |
36
|
|
|
use OCP\FullTextSearch\Model\IIndex; |
37
|
|
|
use OCP\FullTextSearch\Model\IIndexDocument; |
38
|
|
|
|
39
|
|
|
|
40
|
|
|
/** |
41
|
|
|
* Class IndexDocument |
42
|
|
|
* |
43
|
|
|
* This is one of the main class of the FullTextSearch, used as a data transfer |
44
|
|
|
* object. An IndexDocument is created to manage documents around FullTextSearch, |
45
|
|
|
* during an index and during a search. |
46
|
|
|
* The uniqueness of an IndexDocument is made by the Id of the Content Provider |
47
|
|
|
* and the Id of the original document within the Content Provider. |
48
|
|
|
* |
49
|
|
|
* We will call original document the source from which the IndexDocument is |
50
|
|
|
* generated. As an example, an original document can be a file, a mail, ... |
51
|
|
|
* |
52
|
|
|
* @since 15.0.0 |
53
|
|
|
* |
54
|
|
|
* @package OC\FullTextSearch\Model |
55
|
|
|
*/ |
56
|
|
|
class IndexDocument implements IIndexDocument, JsonSerializable { |
57
|
|
|
|
58
|
|
|
|
59
|
|
|
/** @var string */ |
60
|
|
|
protected $id = ''; |
61
|
|
|
|
62
|
|
|
/** @var string */ |
63
|
|
|
protected $providerId = ''; |
64
|
|
|
|
65
|
|
|
/** @var DocumentAccess */ |
66
|
|
|
protected $access; |
67
|
|
|
|
68
|
|
|
/** @var IIndex */ |
69
|
|
|
protected $index; |
70
|
|
|
|
71
|
|
|
/** @var int */ |
72
|
|
|
protected $modifiedTime = 0; |
73
|
|
|
|
74
|
|
|
/** @var string */ |
75
|
|
|
protected $source = ''; |
76
|
|
|
|
77
|
|
|
/** @var array */ |
78
|
|
|
protected $tags = []; |
79
|
|
|
|
80
|
|
|
/** @var array */ |
81
|
|
|
protected $metaTags = []; |
82
|
|
|
|
83
|
|
|
/** @var array */ |
84
|
|
|
protected $subTags = []; |
85
|
|
|
|
86
|
|
|
/** @var string */ |
87
|
|
|
protected $title = ''; |
88
|
|
|
|
89
|
|
|
/** @var string */ |
90
|
|
|
protected $content = ''; |
91
|
|
|
|
92
|
|
|
/** @var string */ |
93
|
|
|
protected $hash = ''; |
94
|
|
|
|
95
|
|
|
/** @var array */ |
96
|
|
|
protected $parts = []; |
97
|
|
|
|
98
|
|
|
/** @var string */ |
99
|
|
|
protected $link = ''; |
100
|
|
|
|
101
|
|
|
/** @var array */ |
102
|
|
|
protected $more = []; |
103
|
|
|
|
104
|
|
|
/** @var array */ |
105
|
|
|
protected $excerpts = []; |
106
|
|
|
|
107
|
|
|
/** @var string */ |
108
|
|
|
protected $score = ''; |
109
|
|
|
|
110
|
|
|
/** @var array */ |
111
|
|
|
protected $info = []; |
112
|
|
|
|
113
|
|
|
/** @var int */ |
114
|
|
|
protected $contentEncoded = 0; |
115
|
|
|
|
116
|
|
|
|
117
|
|
|
/** |
118
|
|
|
* IIndexDocument constructor. |
119
|
|
|
* |
120
|
|
|
* On creation, we assure the uniqueness of the object using the providerId |
121
|
|
|
* and the Id of the original document. |
122
|
|
|
* |
123
|
|
|
* @since 15.0.0 |
124
|
|
|
* |
125
|
|
|
* @param string $providerId |
126
|
|
|
* @param string $documentId |
127
|
|
|
*/ |
128
|
|
|
public function __construct(string $providerId, string $documentId) { |
129
|
|
|
$this->providerId = $providerId; |
130
|
|
|
$this->id = $documentId; |
131
|
|
|
} |
132
|
|
|
|
133
|
|
|
|
134
|
|
|
/** |
135
|
|
|
* Returns the Id of the original document. |
136
|
|
|
* |
137
|
|
|
* @since 15.0.0 |
138
|
|
|
* |
139
|
|
|
* @return string |
140
|
|
|
*/ |
141
|
|
|
final public function getId(): string { |
142
|
|
|
return $this->id; |
143
|
|
|
} |
144
|
|
|
|
145
|
|
|
|
146
|
|
|
/** |
147
|
|
|
* Returns the Id of the provider. |
148
|
|
|
* |
149
|
|
|
* @since 15.0.0 |
150
|
|
|
* |
151
|
|
|
* @return string |
152
|
|
|
*/ |
153
|
|
|
final public function getProviderId(): string { |
154
|
|
|
return $this->providerId; |
155
|
|
|
} |
156
|
|
|
|
157
|
|
|
|
158
|
|
|
/** |
159
|
|
|
* Set the Index related to the IIndexDocument. |
160
|
|
|
* |
161
|
|
|
* @see IIndex |
162
|
|
|
* |
163
|
|
|
* @since 15.0.0 |
164
|
|
|
* |
165
|
|
|
* @param IIndex $index |
166
|
|
|
* |
167
|
|
|
* @return IIndexDocument |
168
|
|
|
*/ |
169
|
|
|
final public function setIndex(IIndex $index): IIndexDocument { |
170
|
|
|
$this->index = $index; |
171
|
|
|
|
172
|
|
|
return $this; |
173
|
|
|
} |
174
|
|
|
|
175
|
|
|
/** |
176
|
|
|
* Get the Index. |
177
|
|
|
* |
178
|
|
|
* @since 15.0.0 |
179
|
|
|
* |
180
|
|
|
* @return IIndex |
181
|
|
|
*/ |
182
|
|
|
final public function getIndex(): IIndex { |
183
|
|
|
return $this->index; |
184
|
|
|
} |
185
|
|
|
|
186
|
|
|
/** |
187
|
|
|
* return if Index is defined. |
188
|
|
|
* |
189
|
|
|
* @since 16.0.0 |
190
|
|
|
* |
191
|
|
|
* @return bool |
192
|
|
|
*/ |
193
|
|
|
final public function hasIndex(): bool { |
194
|
|
|
return ($this->index !== null); |
195
|
|
|
} |
196
|
|
|
|
197
|
|
|
|
198
|
|
|
/** |
199
|
|
|
* Set the modified time of the original document. |
200
|
|
|
* |
201
|
|
|
* @since 15.0.0 |
202
|
|
|
* |
203
|
|
|
* @param int $modifiedTime |
204
|
|
|
* |
205
|
|
|
* @return IIndexDocument |
206
|
|
|
*/ |
207
|
|
|
final public function setModifiedTime(int $modifiedTime): IIndexDocument { |
208
|
|
|
$this->modifiedTime = $modifiedTime; |
209
|
|
|
|
210
|
|
|
return $this; |
211
|
|
|
} |
212
|
|
|
|
213
|
|
|
/** |
214
|
|
|
* Get the modified time of the original document. |
215
|
|
|
* |
216
|
|
|
* @since 15.0.0 |
217
|
|
|
* |
218
|
|
|
* @return int |
219
|
|
|
*/ |
220
|
|
|
final public function getModifiedTime(): int { |
221
|
|
|
return $this->modifiedTime; |
222
|
|
|
} |
223
|
|
|
|
224
|
|
|
/** |
225
|
|
|
* Check if the original document of the IIndexDocument is older than $time. |
226
|
|
|
* |
227
|
|
|
* @since 15.0.0 |
228
|
|
|
* |
229
|
|
|
* @param int $time |
230
|
|
|
* |
231
|
|
|
* @return bool |
232
|
|
|
*/ |
233
|
|
|
final public function isOlderThan(int $time): bool { |
234
|
|
|
return ($this->modifiedTime < $time); |
235
|
|
|
} |
236
|
|
|
|
237
|
|
|
|
238
|
|
|
/** |
239
|
|
|
* Set the read rights of the original document using a IDocumentAccess. |
240
|
|
|
* |
241
|
|
|
* @see IDocumentAccess |
242
|
|
|
* |
243
|
|
|
* @since 15.0.0 |
244
|
|
|
* |
245
|
|
|
* @param IDocumentAccess $access |
246
|
|
|
* |
247
|
|
|
* @return $this |
248
|
|
|
*/ |
249
|
|
|
final public function setAccess(IDocumentAccess $access): IIndexDocument { |
250
|
|
|
$this->access = $access; |
|
|
|
|
251
|
|
|
|
252
|
|
|
return $this; |
253
|
|
|
} |
254
|
|
|
|
255
|
|
|
/** |
256
|
|
|
* Get the IDocumentAccess related to the original document. |
257
|
|
|
* |
258
|
|
|
* @since 15.0.0 |
259
|
|
|
* |
260
|
|
|
* @return IDocumentAccess |
261
|
|
|
*/ |
262
|
|
|
final public function getAccess(): IDocumentAccess { |
263
|
|
|
return $this->access; |
264
|
|
|
} |
265
|
|
|
|
266
|
|
|
|
267
|
|
|
/** |
268
|
|
|
* Add a tag to the list. |
269
|
|
|
* |
270
|
|
|
* @since 15.0.0 |
271
|
|
|
* |
272
|
|
|
* @param string $tag |
273
|
|
|
* |
274
|
|
|
* @return IIndexDocument |
275
|
|
|
*/ |
276
|
|
|
final public function addTag(string $tag): IIndexDocument { |
277
|
|
|
$this->tags[] = $tag; |
278
|
|
|
|
279
|
|
|
return $this; |
280
|
|
|
} |
281
|
|
|
|
282
|
|
|
/** |
283
|
|
|
* Set the list of tags assigned to the original document. |
284
|
|
|
* |
285
|
|
|
* @since 15.0.0 |
286
|
|
|
* |
287
|
|
|
* @param array $tags |
288
|
|
|
* |
289
|
|
|
* @return IIndexDocument |
290
|
|
|
*/ |
291
|
|
|
final public function setTags(array $tags): IIndexDocument { |
292
|
|
|
$this->tags = $tags; |
293
|
|
|
|
294
|
|
|
return $this; |
295
|
|
|
} |
296
|
|
|
|
297
|
|
|
/** |
298
|
|
|
* Get the list of tags assigned to the original document. |
299
|
|
|
* |
300
|
|
|
* @since 15.0.0 |
301
|
|
|
* |
302
|
|
|
* @return array |
303
|
|
|
*/ |
304
|
|
|
final public function getTags(): array { |
305
|
|
|
return $this->tags; |
306
|
|
|
} |
307
|
|
|
|
308
|
|
|
|
309
|
|
|
/** |
310
|
|
|
* Add a meta tag to the list. |
311
|
|
|
* |
312
|
|
|
* @since 15.0.0 |
313
|
|
|
* |
314
|
|
|
* @param string $tag |
315
|
|
|
* |
316
|
|
|
* @return IIndexDocument |
317
|
|
|
*/ |
318
|
|
|
final public function addMetaTag(string $tag): IIndexDocument { |
319
|
|
|
$this->metaTags[] = $tag; |
320
|
|
|
|
321
|
|
|
return $this; |
322
|
|
|
} |
323
|
|
|
|
324
|
|
|
/** |
325
|
|
|
* Set the list of meta tags assigned to the original document. |
326
|
|
|
* |
327
|
|
|
* @since 15.0.0 |
328
|
|
|
* |
329
|
|
|
* @param array $tags |
330
|
|
|
* |
331
|
|
|
* @return IIndexDocument |
332
|
|
|
*/ |
333
|
|
|
final public function setMetaTags(array $tags): IIndexDocument { |
334
|
|
|
$this->metaTags = $tags; |
335
|
|
|
|
336
|
|
|
return $this; |
337
|
|
|
} |
338
|
|
|
|
339
|
|
|
/** |
340
|
|
|
* Get the list of meta tags assigned to the original document. |
341
|
|
|
* |
342
|
|
|
* @since 15.0.0 |
343
|
|
|
* |
344
|
|
|
* @return array |
345
|
|
|
*/ |
346
|
|
|
final public function getMetaTags(): array { |
347
|
|
|
return $this->metaTags; |
348
|
|
|
} |
349
|
|
|
|
350
|
|
|
|
351
|
|
|
/** |
352
|
|
|
* Add a sub tag to the list. |
353
|
|
|
* |
354
|
|
|
* @since 15.0.0 |
355
|
|
|
* |
356
|
|
|
* @param string $sub |
357
|
|
|
* @param string $tag |
358
|
|
|
* |
359
|
|
|
* @return IIndexDocument |
360
|
|
|
*/ |
361
|
|
|
final public function addSubTag(string $sub, string $tag): IIndexDocument { |
362
|
|
|
$this->subTags[$sub] = $tag; |
363
|
|
|
|
364
|
|
|
return $this; |
365
|
|
|
} |
366
|
|
|
|
367
|
|
|
/** |
368
|
|
|
* Set the list of sub tags assigned to the original document. |
369
|
|
|
* |
370
|
|
|
* @since 15.0.0 |
371
|
|
|
* |
372
|
|
|
* @param array $tags |
373
|
|
|
* |
374
|
|
|
* @return IIndexDocument |
375
|
|
|
*/ |
376
|
|
|
final public function setSubTags(array $tags): IIndexDocument { |
377
|
|
|
$this->subTags = $tags; |
378
|
|
|
|
379
|
|
|
return $this; |
380
|
|
|
} |
381
|
|
|
|
382
|
|
|
/** |
383
|
|
|
* Get the list of sub tags assigned to the original document. |
384
|
|
|
* If $formatted is true, the result will be formatted in a one |
385
|
|
|
* dimensional array. |
386
|
|
|
* |
387
|
|
|
* @since 15.0.0 |
388
|
|
|
* |
389
|
|
|
* @param bool $formatted |
390
|
|
|
* |
391
|
|
|
* @return array |
392
|
|
|
*/ |
393
|
|
|
final public function getSubTags(bool $formatted = false): array { |
394
|
|
|
if ($formatted === false) { |
395
|
|
|
return $this->subTags; |
396
|
|
|
} |
397
|
|
|
|
398
|
|
|
$subTags = []; |
399
|
|
|
$ak = array_keys($this->subTags); |
400
|
|
|
foreach ($ak as $source) { |
401
|
|
|
$tags = $this->subTags[$source]; |
402
|
|
|
foreach ($tags as $tag) { |
403
|
|
|
$subTags[] = $source . '_' . $tag; |
404
|
|
|
} |
405
|
|
|
} |
406
|
|
|
|
407
|
|
|
return $subTags; |
408
|
|
|
} |
409
|
|
|
|
410
|
|
|
|
411
|
|
|
/** |
412
|
|
|
* Set the source of the original document. |
413
|
|
|
* |
414
|
|
|
* @since 15.0.0 |
415
|
|
|
* |
416
|
|
|
* @param string $source |
417
|
|
|
* |
418
|
|
|
* @return IIndexDocument |
419
|
|
|
*/ |
420
|
|
|
final public function setSource(string $source): IIndexDocument { |
421
|
|
|
$this->source = $source; |
422
|
|
|
|
423
|
|
|
return $this; |
424
|
|
|
} |
425
|
|
|
|
426
|
|
|
/** |
427
|
|
|
* Get the source of the original document. |
428
|
|
|
* |
429
|
|
|
* @since 15.0.0 |
430
|
|
|
* |
431
|
|
|
* @return string |
432
|
|
|
*/ |
433
|
|
|
final public function getSource(): string { |
434
|
|
|
return $this->source; |
435
|
|
|
} |
436
|
|
|
|
437
|
|
|
|
438
|
|
|
/** |
439
|
|
|
* Set the title of the original document. |
440
|
|
|
* |
441
|
|
|
* @since 15.0.0 |
442
|
|
|
* |
443
|
|
|
* @param string $title |
444
|
|
|
* |
445
|
|
|
* @return IIndexDocument |
446
|
|
|
*/ |
447
|
|
|
final public function setTitle(string $title): IIndexDocument { |
448
|
|
|
$this->title = $title; |
449
|
|
|
|
450
|
|
|
return $this; |
451
|
|
|
} |
452
|
|
|
|
453
|
|
|
/** |
454
|
|
|
* Get the title of the original document. |
455
|
|
|
* |
456
|
|
|
* @since 15.0.0 |
457
|
|
|
* |
458
|
|
|
* @return string |
459
|
|
|
*/ |
460
|
|
|
final public function getTitle(): string { |
461
|
|
|
return $this->title; |
462
|
|
|
} |
463
|
|
|
|
464
|
|
|
|
465
|
|
|
/** |
466
|
|
|
* Set the content of the document. |
467
|
|
|
* $encoded can be NOT_ENCODED or ENCODED_BASE64 if the content is raw or |
468
|
|
|
* encoded in base64. |
469
|
|
|
* |
470
|
|
|
* @since 15.0.0 |
471
|
|
|
* |
472
|
|
|
* @param string $content |
473
|
|
|
* @param int $encoded |
474
|
|
|
* |
475
|
|
|
* @return IIndexDocument |
476
|
|
|
*/ |
477
|
|
|
final public function setContent(string $content, int $encoded = 0): IIndexDocument { |
478
|
|
|
$this->content = $content; |
479
|
|
|
$this->contentEncoded = $encoded; |
480
|
|
|
|
481
|
|
|
return $this; |
482
|
|
|
} |
483
|
|
|
|
484
|
|
|
/** |
485
|
|
|
* Get the content of the original document. |
486
|
|
|
* |
487
|
|
|
* @since 15.0.0 |
488
|
|
|
* |
489
|
|
|
* @return string |
490
|
|
|
*/ |
491
|
|
|
final public function getContent(): string { |
492
|
|
|
return $this->content; |
493
|
|
|
} |
494
|
|
|
|
495
|
|
|
/** |
496
|
|
|
* Returns the type of the encoding on the content. |
497
|
|
|
* |
498
|
|
|
* @since 15.0.0 |
499
|
|
|
* |
500
|
|
|
* @return int |
501
|
|
|
*/ |
502
|
|
|
final public function isContentEncoded(): int { |
503
|
|
|
return $this->contentEncoded; |
504
|
|
|
} |
505
|
|
|
|
506
|
|
|
/** |
507
|
|
|
* Return the size of the content. |
508
|
|
|
* |
509
|
|
|
* @since 15.0.0 |
510
|
|
|
* |
511
|
|
|
* @return int |
512
|
|
|
*/ |
513
|
|
|
final public function getContentSize(): int { |
514
|
|
|
return strlen($this->getContent()); |
515
|
|
|
} |
516
|
|
|
|
517
|
|
|
|
518
|
|
|
/** |
519
|
|
|
* Generate an hash, based on the content of the original document. |
520
|
|
|
* |
521
|
|
|
* @since 15.0.0 |
522
|
|
|
* |
523
|
|
|
* @return IIndexDocument |
524
|
|
|
*/ |
525
|
|
|
final public function initHash(): IIndexDocument { |
526
|
|
|
if ($this->getContent() === '' || is_null($this->getContent())) { |
527
|
|
|
return $this; |
528
|
|
|
} |
529
|
|
|
|
530
|
|
|
$this->hash = hash("md5", $this->getContent()); |
531
|
|
|
|
532
|
|
|
return $this; |
533
|
|
|
} |
534
|
|
|
|
535
|
|
|
/** |
536
|
|
|
* Set the hash of the original document. |
537
|
|
|
* |
538
|
|
|
* @since 15.0.0 |
539
|
|
|
* |
540
|
|
|
* @param string $hash |
541
|
|
|
* |
542
|
|
|
* @return IIndexDocument |
543
|
|
|
*/ |
544
|
|
|
final public function setHash(string $hash): IIndexDocument { |
545
|
|
|
$this->hash = $hash; |
546
|
|
|
|
547
|
|
|
return $this; |
548
|
|
|
} |
549
|
|
|
|
550
|
|
|
/** |
551
|
|
|
* Get the hash of the original document. |
552
|
|
|
* |
553
|
|
|
* @since 15.0.0 |
554
|
|
|
* |
555
|
|
|
* @return string |
556
|
|
|
*/ |
557
|
|
|
final public function getHash(): string { |
558
|
|
|
return $this->hash; |
559
|
|
|
} |
560
|
|
|
|
561
|
|
|
|
562
|
|
|
/** |
563
|
|
|
* Add a part, identified by a string, and its content. |
564
|
|
|
* |
565
|
|
|
* It is strongly advised to use alphanumerical chars with no space in the |
566
|
|
|
* $part string. |
567
|
|
|
* |
568
|
|
|
* @since 15.0.0 |
569
|
|
|
* |
570
|
|
|
* @param string $part |
571
|
|
|
* @param string $content |
572
|
|
|
* |
573
|
|
|
* @return IIndexDocument |
574
|
|
|
*/ |
575
|
|
|
final public function addPart(string $part, string $content): IIndexDocument { |
576
|
|
|
$this->parts[$part] = $content; |
577
|
|
|
|
578
|
|
|
return $this; |
579
|
|
|
} |
580
|
|
|
|
581
|
|
|
/** |
582
|
|
|
* Set all parts and their content. |
583
|
|
|
* |
584
|
|
|
* @since 15.0.0 |
585
|
|
|
* |
586
|
|
|
* @param array $parts |
587
|
|
|
* |
588
|
|
|
* @return IIndexDocument |
589
|
|
|
*/ |
590
|
|
|
final public function setParts(array $parts): IIndexDocument { |
591
|
|
|
$this->parts = $parts; |
592
|
|
|
|
593
|
|
|
return $this; |
594
|
|
|
} |
595
|
|
|
|
596
|
|
|
/** |
597
|
|
|
* Get all parts of the IIndexDocument. |
598
|
|
|
* |
599
|
|
|
* @since 15.0.0 |
600
|
|
|
* |
601
|
|
|
* @return array |
602
|
|
|
*/ |
603
|
|
|
final public function getParts(): array { |
604
|
|
|
return $this->parts; |
605
|
|
|
} |
606
|
|
|
|
607
|
|
|
|
608
|
|
|
/** |
609
|
|
|
* Add a link, usable by the frontend. |
610
|
|
|
* |
611
|
|
|
* @since 15.0.0 |
612
|
|
|
* |
613
|
|
|
* @param string $link |
614
|
|
|
* |
615
|
|
|
* @return IIndexDocument |
616
|
|
|
*/ |
617
|
|
|
final public function setLink(string $link): IIndexDocument { |
618
|
|
|
$this->link = $link; |
619
|
|
|
|
620
|
|
|
return $this; |
621
|
|
|
} |
622
|
|
|
|
623
|
|
|
/** |
624
|
|
|
* Get the link. |
625
|
|
|
* |
626
|
|
|
* @since 15.0.0 |
627
|
|
|
* |
628
|
|
|
* @return string |
629
|
|
|
*/ |
630
|
|
|
final public function getLink(): string { |
631
|
|
|
return $this->link; |
632
|
|
|
} |
633
|
|
|
|
634
|
|
|
|
635
|
|
|
/** |
636
|
|
|
* Set more information that couldn't be set using other method. |
637
|
|
|
* |
638
|
|
|
* @since 15.0.0 |
639
|
|
|
* |
640
|
|
|
* @param array $more |
641
|
|
|
* |
642
|
|
|
* @return IIndexDocument |
643
|
|
|
*/ |
644
|
|
|
final public function setMore(array $more): IIndexDocument { |
645
|
|
|
$this->more = $more; |
646
|
|
|
|
647
|
|
|
return $this; |
648
|
|
|
} |
649
|
|
|
|
650
|
|
|
/** |
651
|
|
|
* Get more information. |
652
|
|
|
* |
653
|
|
|
* @since 15.0.0 |
654
|
|
|
* |
655
|
|
|
* @return array |
656
|
|
|
*/ |
657
|
|
|
final public function getMore(): array { |
658
|
|
|
return $this->more; |
659
|
|
|
} |
660
|
|
|
|
661
|
|
|
|
662
|
|
|
/** |
663
|
|
|
* Add some excerpt of the content of the original document, usually based |
664
|
|
|
* on the search request. |
665
|
|
|
* |
666
|
|
|
* @since 16.0.0 |
667
|
|
|
* |
668
|
|
|
* @param string $source |
669
|
|
|
* @param string $excerpt |
670
|
|
|
* |
671
|
|
|
* @return IIndexDocument |
672
|
|
|
*/ |
673
|
|
|
final public function addExcerpt(string $source, string $excerpt): IIndexDocument { |
674
|
|
|
$this->excerpts[] = |
675
|
|
|
[ |
676
|
|
|
'source' => $source, |
677
|
|
|
'excerpt' => $this->cleanExcerpt($excerpt) |
678
|
|
|
]; |
679
|
|
|
|
680
|
|
|
return $this; |
681
|
|
|
} |
682
|
|
|
|
683
|
|
|
|
684
|
|
|
/** |
685
|
|
|
* Set all excerpts of the content of the original document. |
686
|
|
|
* |
687
|
|
|
* @since 16.0.0 |
688
|
|
|
* |
689
|
|
|
* @param array $excerpts |
690
|
|
|
* |
691
|
|
|
* @return IIndexDocument |
692
|
|
|
*/ |
693
|
|
|
final public function setExcerpts(array $excerpts): IIndexDocument { |
694
|
|
|
$new = []; |
695
|
|
|
foreach ($excerpts as $entry) { |
696
|
|
|
$new[] = [ |
697
|
|
|
'source' => $entry['source'], |
698
|
|
|
'excerpt' => $this->cleanExcerpt($entry['excerpt']) |
699
|
|
|
]; |
700
|
|
|
} |
701
|
|
|
|
702
|
|
|
$this->excerpts = $new; |
703
|
|
|
|
704
|
|
|
return $this; |
705
|
|
|
} |
706
|
|
|
|
707
|
|
|
/** |
708
|
|
|
* Get all excerpts of the content of the original document. |
709
|
|
|
* |
710
|
|
|
* @since 15.0.0 |
711
|
|
|
* |
712
|
|
|
* @return array |
713
|
|
|
*/ |
714
|
|
|
final public function getExcerpts(): array { |
715
|
|
|
return $this->excerpts; |
716
|
|
|
} |
717
|
|
|
|
718
|
|
|
/** |
719
|
|
|
* Clean excerpt. |
720
|
|
|
* |
721
|
|
|
* @since 16.0.0 |
722
|
|
|
* |
723
|
|
|
* @param string $excerpt |
724
|
|
|
* @return string |
725
|
|
|
*/ |
726
|
|
|
final private function cleanExcerpt(string $excerpt): string { |
727
|
|
|
$excerpt = str_replace("\\n", ' ', $excerpt); |
728
|
|
|
$excerpt = str_replace("\\r", ' ', $excerpt); |
729
|
|
|
$excerpt = str_replace("\\t", ' ', $excerpt); |
730
|
|
|
$excerpt = str_replace("\n", ' ', $excerpt); |
731
|
|
|
$excerpt = str_replace("\r", ' ', $excerpt); |
732
|
|
|
$excerpt = str_replace("\t", ' ', $excerpt); |
733
|
|
|
|
734
|
|
|
return $excerpt; |
735
|
|
|
} |
736
|
|
|
|
737
|
|
|
|
738
|
|
|
/** |
739
|
|
|
* Set the score to the result assigned to this document during a search |
740
|
|
|
* request. |
741
|
|
|
* |
742
|
|
|
* @since 15.0.0 |
743
|
|
|
* |
744
|
|
|
* @param string $score |
745
|
|
|
* |
746
|
|
|
* @return IIndexDocument |
747
|
|
|
*/ |
748
|
|
|
final public function setScore(string $score): IIndexDocument { |
749
|
|
|
$this->score = $score; |
750
|
|
|
|
751
|
|
|
return $this; |
752
|
|
|
} |
753
|
|
|
|
754
|
|
|
/** |
755
|
|
|
* Get the score. |
756
|
|
|
* |
757
|
|
|
* @since 15.0.0 |
758
|
|
|
* |
759
|
|
|
* @return string |
760
|
|
|
*/ |
761
|
|
|
final public function getScore(): string { |
762
|
|
|
return $this->score; |
763
|
|
|
} |
764
|
|
|
|
765
|
|
|
|
766
|
|
|
/** |
767
|
|
|
* Set some information about the original document that will be available |
768
|
|
|
* to the front-end when displaying search result. (as string) |
769
|
|
|
* Because this information will not be indexed, this method can also be |
770
|
|
|
* used to manage some data while filling the IIndexDocument before its |
771
|
|
|
* indexing. |
772
|
|
|
* |
773
|
|
|
* @since 15.0.0 |
774
|
|
|
* |
775
|
|
|
* @param string $info |
776
|
|
|
* @param string $value |
777
|
|
|
* |
778
|
|
|
* @return IIndexDocument |
779
|
|
|
*/ |
780
|
|
|
final public function setInfo(string $info, string $value): IIndexDocument { |
781
|
|
|
$this->info[$info] = $value; |
782
|
|
|
|
783
|
|
|
return $this; |
784
|
|
|
} |
785
|
|
|
|
786
|
|
|
/** |
787
|
|
|
* Get an information about a document. (string) |
788
|
|
|
* |
789
|
|
|
* @since 15.0.0 |
790
|
|
|
* |
791
|
|
|
* @param string $info |
792
|
|
|
* @param string $default |
793
|
|
|
* |
794
|
|
|
* @return string |
795
|
|
|
*/ |
796
|
|
|
final public function getInfo(string $info, string $default = ''): string { |
797
|
|
|
if (!key_exists($info, $this->info)) { |
798
|
|
|
return $default; |
799
|
|
|
} |
800
|
|
|
|
801
|
|
|
return $this->info[$info]; |
802
|
|
|
} |
803
|
|
|
|
804
|
|
|
/** |
805
|
|
|
* Set some information about the original document that will be available |
806
|
|
|
* to the front-end when displaying search result. (as array) |
807
|
|
|
* Because this information will not be indexed, this method can also be |
808
|
|
|
* used to manage some data while filling the IIndexDocument before its |
809
|
|
|
* indexing. |
810
|
|
|
* |
811
|
|
|
* @since 15.0.0 |
812
|
|
|
* |
813
|
|
|
* @param string $info |
814
|
|
|
* @param array $value |
815
|
|
|
* |
816
|
|
|
* @return IIndexDocument |
817
|
|
|
*/ |
818
|
|
|
final public function setInfoArray(string $info, array $value): IIndexDocument { |
819
|
|
|
$this->info[$info] = $value; |
820
|
|
|
|
821
|
|
|
return $this; |
822
|
|
|
} |
823
|
|
|
|
824
|
|
|
/** |
825
|
|
|
* Get an information about a document. (array) |
826
|
|
|
* |
827
|
|
|
* @since 15.0.0 |
828
|
|
|
* |
829
|
|
|
* @param string $info |
830
|
|
|
* @param array $default |
831
|
|
|
* |
832
|
|
|
* @return array |
833
|
|
|
*/ |
834
|
|
|
final public function getInfoArray(string $info, array $default = []): array { |
835
|
|
|
if (!key_exists($info, $this->info)) { |
836
|
|
|
return $default; |
837
|
|
|
} |
838
|
|
|
|
839
|
|
|
return $this->info[$info]; |
840
|
|
|
} |
841
|
|
|
|
842
|
|
|
/** |
843
|
|
|
* Set some information about the original document that will be available |
844
|
|
|
* to the front-end when displaying search result. (as int) |
845
|
|
|
* Because this information will not be indexed, this method can also be |
846
|
|
|
* used to manage some data while filling the IIndexDocument before its |
847
|
|
|
* indexing. |
848
|
|
|
* |
849
|
|
|
* @since 15.0.0 |
850
|
|
|
* |
851
|
|
|
* @param string $info |
852
|
|
|
* @param int $value |
853
|
|
|
* |
854
|
|
|
* @return IIndexDocument |
855
|
|
|
*/ |
856
|
|
|
final public function setInfoInt(string $info, int $value): IIndexDocument { |
857
|
|
|
$this->info[$info] = $value; |
858
|
|
|
|
859
|
|
|
return $this; |
860
|
|
|
} |
861
|
|
|
|
862
|
|
|
/** |
863
|
|
|
* Get an information about a document. (int) |
864
|
|
|
* |
865
|
|
|
* @since 15.0.0 |
866
|
|
|
* |
867
|
|
|
* @param string $info |
868
|
|
|
* @param int $default |
869
|
|
|
* |
870
|
|
|
* @return int |
871
|
|
|
*/ |
872
|
|
|
final public function getInfoInt(string $info, int $default = 0): int { |
873
|
|
|
if (!key_exists($info, $this->info)) { |
874
|
|
|
return $default; |
875
|
|
|
} |
876
|
|
|
|
877
|
|
|
return $this->info[$info]; |
878
|
|
|
} |
879
|
|
|
|
880
|
|
|
/** |
881
|
|
|
* Set some information about the original document that will be available |
882
|
|
|
* to the front-end when displaying search result. (as bool) |
883
|
|
|
* Because this information will not be indexed, this method can also be |
884
|
|
|
* used to manage some data while filling the IIndexDocument before its |
885
|
|
|
* indexing. |
886
|
|
|
* |
887
|
|
|
* @since 15.0.0 |
888
|
|
|
* |
889
|
|
|
* @param string $info |
890
|
|
|
* @param bool $value |
891
|
|
|
* |
892
|
|
|
* @return IIndexDocument |
893
|
|
|
*/ |
894
|
|
|
final public function setInfoBool(string $info, bool $value): IIndexDocument { |
895
|
|
|
$this->info[$info] = $value; |
896
|
|
|
|
897
|
|
|
return $this; |
898
|
|
|
} |
899
|
|
|
|
900
|
|
|
/** |
901
|
|
|
* Get an information about a document. (bool) |
902
|
|
|
* |
903
|
|
|
* @since 15.0.0 |
904
|
|
|
* |
905
|
|
|
* @param string $info |
906
|
|
|
* @param bool $default |
907
|
|
|
* |
908
|
|
|
* @return bool |
909
|
|
|
*/ |
910
|
|
|
final public function getInfoBool(string $info, bool $default = false): bool { |
911
|
|
|
if (!key_exists($info, $this->info)) { |
912
|
|
|
return $default; |
913
|
|
|
} |
914
|
|
|
|
915
|
|
|
return $this->info[$info]; |
916
|
|
|
} |
917
|
|
|
|
918
|
|
|
/** |
919
|
|
|
* Get all info. |
920
|
|
|
* |
921
|
|
|
* @since 15.0.0 |
922
|
|
|
* |
923
|
|
|
* @return array |
924
|
|
|
*/ |
925
|
|
|
final public function getInfoAll(): array { |
926
|
|
|
|
927
|
|
|
$info = []; |
928
|
|
|
foreach ($this->info as $k => $v) { |
929
|
|
|
if (substr($k, 0, 1) === '_') { |
930
|
|
|
continue; |
931
|
|
|
} |
932
|
|
|
|
933
|
|
|
$info[$k] = $v; |
934
|
|
|
} |
935
|
|
|
|
936
|
|
|
return $info; |
937
|
|
|
} |
938
|
|
|
|
939
|
|
|
|
940
|
|
|
/** |
941
|
|
|
* @since 15.0.0 |
942
|
|
|
* |
943
|
|
|
* On some version of PHP, it is better to force destruct the object. |
944
|
|
|
* And during the index, the number of generated IIndexDocument can be |
945
|
|
|
* _huge_. |
946
|
|
|
*/ |
947
|
|
|
public function __destruct() { |
948
|
|
|
unset($this->id); |
949
|
|
|
unset($this->providerId); |
950
|
|
|
unset($this->access); |
951
|
|
|
unset($this->modifiedTime); |
952
|
|
|
unset($this->title); |
953
|
|
|
unset($this->content); |
954
|
|
|
unset($this->hash); |
955
|
|
|
unset($this->link); |
956
|
|
|
unset($this->source); |
957
|
|
|
unset($this->tags); |
958
|
|
|
unset($this->metaTags); |
959
|
|
|
unset($this->subTags); |
960
|
|
|
unset($this->more); |
961
|
|
|
unset($this->excerpts); |
962
|
|
|
unset($this->score); |
963
|
|
|
unset($this->info); |
964
|
|
|
unset($this->contentEncoded); |
965
|
|
|
} |
966
|
|
|
|
967
|
|
|
/** |
968
|
|
|
* @since 15.0.0 |
969
|
|
|
* |
970
|
|
|
* @return array |
971
|
|
|
*/ |
972
|
|
|
public function jsonSerialize() { |
973
|
|
|
return [ |
974
|
|
|
'id' => $this->getId(), |
975
|
|
|
'providerId' => $this->getProviderId(), |
976
|
|
|
'access' => $this->access, |
977
|
|
|
'modifiedTime' => $this->getModifiedTime(), |
978
|
|
|
'title' => $this->getTitle(), |
979
|
|
|
'link' => $this->getLink(), |
980
|
|
|
'index' => $this->index, |
981
|
|
|
'source' => $this->getSource(), |
982
|
|
|
'info' => $this->getInfoAll(), |
983
|
|
|
'hash' => $this->getHash(), |
984
|
|
|
'contentSize' => $this->getContentSize(), |
985
|
|
|
'tags' => $this->getTags(), |
986
|
|
|
'metatags' => $this->getMetaTags(), |
987
|
|
|
'subtags' => $this->getSubTags(), |
988
|
|
|
'more' => $this->getMore(), |
989
|
|
|
'excerpts' => $this->getExcerpts(), |
990
|
|
|
'score' => $this->getScore() |
991
|
|
|
]; |
992
|
|
|
} |
993
|
|
|
|
994
|
|
|
} |
995
|
|
|
|
996
|
|
|
|
Our type inference engine has found a suspicous assignment of a value to a property. This check raises an issue when a value that can be of a given class or a super-class is assigned to a property that is type hinted more strictly.
Either this assignment is in error or an instanceof check should be added for that assignment.