1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/* |
4
|
|
|
* This file is part of the ONGR package. |
5
|
|
|
* |
6
|
|
|
* (c) NFQ Technologies UAB <[email protected]> |
7
|
|
|
* |
8
|
|
|
* For the full copyright and license information, please view the LICENSE |
9
|
|
|
* file that was distributed with this source code. |
10
|
|
|
*/ |
11
|
|
|
|
12
|
|
|
declare(strict_types=1); |
13
|
|
|
|
14
|
|
|
namespace ONGR\ElasticsearchDSL; |
15
|
|
|
|
16
|
|
|
use ONGR\ElasticsearchDSL\Aggregation\AbstractAggregation; |
17
|
|
|
use ONGR\ElasticsearchDSL\Highlight\Highlight; |
18
|
|
|
use ONGR\ElasticsearchDSL\InnerHit\NestedInnerHit; |
19
|
|
|
use ONGR\ElasticsearchDSL\Query\Compound\BoolQuery; |
20
|
|
|
use ONGR\ElasticsearchDSL\SearchEndpoint\AbstractSearchEndpoint; |
21
|
|
|
use ONGR\ElasticsearchDSL\SearchEndpoint\AggregationsEndpoint; |
22
|
|
|
use ONGR\ElasticsearchDSL\SearchEndpoint\HighlightEndpoint; |
23
|
|
|
use ONGR\ElasticsearchDSL\SearchEndpoint\InnerHitsEndpoint; |
24
|
|
|
use ONGR\ElasticsearchDSL\SearchEndpoint\PostFilterEndpoint; |
25
|
|
|
use ONGR\ElasticsearchDSL\SearchEndpoint\QueryEndpoint; |
26
|
|
|
use ONGR\ElasticsearchDSL\SearchEndpoint\SearchEndpointFactory; |
27
|
|
|
use ONGR\ElasticsearchDSL\SearchEndpoint\SearchEndpointInterface; |
28
|
|
|
use ONGR\ElasticsearchDSL\SearchEndpoint\SortEndpoint; |
29
|
|
|
use ONGR\ElasticsearchDSL\Serializer\Normalizer\CustomReferencedNormalizer; |
30
|
|
|
use ONGR\ElasticsearchDSL\Serializer\OrderedSerializer; |
31
|
|
|
use Symfony\Component\Serializer\Normalizer\CustomNormalizer; |
32
|
|
|
use ONGR\ElasticsearchDSL\SearchEndpoint\SuggestEndpoint; |
33
|
|
|
|
34
|
|
|
/** |
35
|
|
|
* Search object that can be executed by a manager. |
36
|
|
|
*/ |
37
|
|
|
class Search |
38
|
|
|
{ |
39
|
|
|
/** |
40
|
|
|
* If you don’t need to track the total number of hits at all you can improve |
41
|
|
|
* query times by setting this option to false. Defaults to true. |
42
|
|
|
*/ |
43
|
|
|
private ?bool $trackTotalHits = null; |
|
|
|
|
44
|
|
|
|
45
|
|
|
/** |
46
|
|
|
* To retrieve hits from a certain offset. Defaults to 0. |
47
|
|
|
* |
48
|
|
|
*/ |
49
|
|
|
private ?int $from = null; |
50
|
|
|
|
51
|
|
|
/** |
52
|
|
|
* The number of hits to return. Defaults to 10. If you do not care about getting some |
53
|
|
|
* hits back but only about the number of matches and/or aggregations, setting the value |
54
|
|
|
* to 0 will help performance. |
55
|
|
|
*/ |
56
|
|
|
private ?int $size = null; |
57
|
|
|
|
58
|
|
|
/** |
59
|
|
|
* Allows to control how the _source field is returned with every hit. By default |
60
|
|
|
* operations return the contents of the _source field unless you have used the |
61
|
|
|
* stored_fields parameter or if the _source field is disabled. |
62
|
|
|
*/ |
63
|
|
|
private ?bool $source = null; |
64
|
|
|
|
65
|
|
|
/** |
66
|
|
|
* Allows to selectively load specific stored fields for each document represented by a search hit. |
67
|
|
|
*/ |
68
|
|
|
private ?array $storedFields = null; |
69
|
|
|
|
70
|
|
|
/** |
71
|
|
|
* Allows to return a script evaluation (based on different fields) for each hit. |
72
|
|
|
* Script fields can work on fields that are not stored, and allow to return custom |
73
|
|
|
* values to be returned (the evaluated value of the script). Script fields can |
74
|
|
|
* also access the actual _source document indexed and extract specific elements |
75
|
|
|
* to be returned from it (can be an "object" type). |
76
|
|
|
*/ |
77
|
|
|
private ?array $scriptFields = null; |
78
|
|
|
|
79
|
|
|
/** |
80
|
|
|
* Allows to return the doc value representation of a field for each hit. Doc value |
81
|
|
|
* fields can work on fields that are not stored. Note that if the fields parameter |
82
|
|
|
* specifies fields without docvalues it will try to load the value from the fielddata |
83
|
|
|
* cache causing the terms for that field to be loaded to memory (cached), which will |
84
|
|
|
* result in more memory consumption. |
85
|
|
|
*/ |
86
|
|
|
private ?array $docValueFields = null; |
87
|
|
|
|
88
|
|
|
/** |
89
|
|
|
* Enables explanation for each hit on how its score was computed. |
90
|
|
|
*/ |
91
|
|
|
private ?bool $explain = null; |
92
|
|
|
|
93
|
|
|
/** |
94
|
|
|
* Returns a version for each search hit. |
95
|
|
|
*/ |
96
|
|
|
private ?bool $version = null; |
97
|
|
|
|
98
|
|
|
/** |
99
|
|
|
* Allows to configure different boost level per index when searching across more |
100
|
|
|
* than one indices. This is very handy when hits coming from one index matter more |
101
|
|
|
* than hits coming from another index (think social graph where each user has an index). |
102
|
|
|
*/ |
103
|
|
|
private ?array $indicesBoost = null; |
104
|
|
|
|
105
|
|
|
/** |
106
|
|
|
* Exclude documents which have a _score less than the minimum specified in min_score. |
107
|
|
|
*/ |
108
|
|
|
private ?int $minScore = null; |
109
|
|
|
|
110
|
|
|
/** |
111
|
|
|
* Pagination of results can be done by using the from and size but the cost becomes |
112
|
|
|
* prohibitive when the deep pagination is reached. The index.max_result_window which |
113
|
|
|
* defaults to 10,000 is a safeguard, search requests take heap memory and time |
114
|
|
|
* proportional to from + size. The Scroll api is recommended for efficient deep |
115
|
|
|
* scrolling but scroll contexts are costly and it is not recommended to use it for |
116
|
|
|
* real time user requests. The search_after parameter circumvents this problem by |
117
|
|
|
* providing a live cursor. The idea is to use the results from the previous page to |
118
|
|
|
* help the retrieval of the next page. |
119
|
|
|
*/ |
120
|
|
|
private ?array $searchAfter = null; |
121
|
|
|
|
122
|
|
|
/** |
123
|
|
|
* URI parameters alongside Request body search. |
124
|
|
|
* |
125
|
|
|
* @link https://www.elastic.co/guide/en/elasticsearch/reference/current/search-uri-request.html |
126
|
|
|
*/ |
127
|
|
|
private array $uriParams = []; |
128
|
|
|
|
129
|
|
|
/** |
130
|
|
|
* While a search request returns a single “page” of results, the scroll API can be used to retrieve |
131
|
|
|
* large numbers of results (or even all results) from a single search request, in much the same way |
132
|
|
|
* as you would use a cursor on a traditional database. Scrolling is not intended for real time user |
133
|
|
|
* requests, but rather for processing large amounts of data, e.g. in order to reindex the contents |
134
|
|
|
* of one index into a new index with a different configuration. |
135
|
|
|
*/ |
136
|
|
|
private ?string $scroll = null; |
137
|
|
|
|
138
|
|
|
private static ?OrderedSerializer $serializer = null; |
139
|
|
|
|
140
|
|
|
private array $endpoints = []; |
141
|
|
|
|
142
|
|
|
public function __construct() |
143
|
|
|
{ |
144
|
|
|
$this->initializeSerializer(); |
145
|
|
|
} |
146
|
|
|
|
147
|
|
|
public function __wakeup() |
148
|
|
|
{ |
149
|
|
|
$this->initializeSerializer(); |
150
|
|
|
} |
151
|
|
|
|
152
|
|
|
private function initializeSerializer(): void |
153
|
|
|
{ |
154
|
|
|
if (static::$serializer === null) { |
155
|
|
|
static::$serializer = new OrderedSerializer( |
156
|
|
|
[ |
157
|
|
|
new CustomReferencedNormalizer(), |
158
|
|
|
new CustomNormalizer(), |
159
|
|
|
] |
160
|
|
|
); |
161
|
|
|
} |
162
|
|
|
} |
163
|
|
|
|
164
|
|
|
public function destroyEndpoint(string $type): void |
165
|
|
|
{ |
166
|
|
|
unset($this->endpoints[$type]); |
167
|
|
|
} |
168
|
|
|
|
169
|
|
|
public function addQuery(BuilderInterface $query, string $boolType = BoolQuery::MUST, ?string $key = null): static |
170
|
|
|
{ |
171
|
|
|
$endpoint = $this->getEndpoint(QueryEndpoint::NAME); |
172
|
|
|
$endpoint->addToBool($query, $boolType, $key); |
173
|
|
|
|
174
|
|
|
return $this; |
175
|
|
|
} |
176
|
|
|
|
177
|
|
|
private function getEndpoint(string $type): SearchEndpointInterface |
178
|
|
|
{ |
179
|
|
|
if (!array_key_exists($type, $this->endpoints)) { |
180
|
|
|
$this->endpoints[$type] = SearchEndpointFactory::get($type); |
181
|
|
|
} |
182
|
|
|
|
183
|
|
|
return $this->endpoints[$type]; |
184
|
|
|
} |
185
|
|
|
|
186
|
|
|
public function getQueries(): BoolQuery |
187
|
|
|
{ |
188
|
|
|
$endpoint = $this->getEndpoint(QueryEndpoint::NAME); |
189
|
|
|
|
190
|
|
|
return $endpoint->getBool(); |
191
|
|
|
} |
192
|
|
|
|
193
|
|
|
public function setQueryParameters(array $parameters): static |
194
|
|
|
{ |
195
|
|
|
$this->setEndpointParameters(QueryEndpoint::NAME, $parameters); |
196
|
|
|
|
197
|
|
|
return $this; |
198
|
|
|
} |
199
|
|
|
|
200
|
|
|
public function setEndpointParameters(string $endpointName, array $parameters): static |
201
|
|
|
{ |
202
|
|
|
/** @var AbstractSearchEndpoint $endpoint */ |
203
|
|
|
$endpoint = $this->getEndpoint($endpointName); |
204
|
|
|
$endpoint->setParameters($parameters); |
205
|
|
|
|
206
|
|
|
return $this; |
207
|
|
|
} |
208
|
|
|
|
209
|
|
|
public function addPostFilter( |
210
|
|
|
BuilderInterface $filter, |
211
|
|
|
string $boolType = BoolQuery::MUST, |
212
|
|
|
?string $key = null |
213
|
|
|
): static { |
214
|
|
|
$this |
215
|
|
|
->getEndpoint(PostFilterEndpoint::NAME) |
216
|
|
|
->addToBool($filter, $boolType, $key); |
217
|
|
|
|
218
|
|
|
return $this; |
219
|
|
|
} |
220
|
|
|
|
221
|
|
|
public function getPostFilters(): BoolQuery |
222
|
|
|
{ |
223
|
|
|
$endpoint = $this->getEndpoint(PostFilterEndpoint::NAME); |
224
|
|
|
|
225
|
|
|
return $endpoint->getBool(); |
226
|
|
|
} |
227
|
|
|
|
228
|
|
|
public function setPostFilterParameters(array $parameters): static |
229
|
|
|
{ |
230
|
|
|
$this->setEndpointParameters(PostFilterEndpoint::NAME, $parameters); |
231
|
|
|
|
232
|
|
|
return $this; |
233
|
|
|
} |
234
|
|
|
|
235
|
|
|
public function addAggregation(AbstractAggregation $aggregation): static |
236
|
|
|
{ |
237
|
|
|
$this->getEndpoint(AggregationsEndpoint::NAME)->add($aggregation, $aggregation->getName()); |
238
|
|
|
|
239
|
|
|
return $this; |
240
|
|
|
} |
241
|
|
|
|
242
|
|
|
public function getAggregations(): array |
243
|
|
|
{ |
244
|
|
|
return $this->getEndpoint(AggregationsEndpoint::NAME)->getAll(); |
245
|
|
|
} |
246
|
|
|
|
247
|
|
|
public function addInnerHit(NestedInnerHit $innerHit): static |
248
|
|
|
{ |
249
|
|
|
$this->getEndpoint(InnerHitsEndpoint::NAME)->add($innerHit, $innerHit->getName()); |
250
|
|
|
|
251
|
|
|
return $this; |
252
|
|
|
} |
253
|
|
|
|
254
|
|
|
public function getInnerHits(): array |
255
|
|
|
{ |
256
|
|
|
return $this->getEndpoint(InnerHitsEndpoint::NAME)->getAll(); |
257
|
|
|
} |
258
|
|
|
|
259
|
|
|
public function addSort(BuilderInterface $sort): static |
260
|
|
|
{ |
261
|
|
|
$this->getEndpoint(SortEndpoint::NAME)->add($sort); |
262
|
|
|
|
263
|
|
|
return $this; |
264
|
|
|
} |
265
|
|
|
|
266
|
|
|
public function getSorts(): array |
267
|
|
|
{ |
268
|
|
|
return $this->getEndpoint(SortEndpoint::NAME)->getAll(); |
269
|
|
|
} |
270
|
|
|
|
271
|
|
|
public function addHighlight(Highlight $highlight): static |
272
|
|
|
{ |
273
|
|
|
$this->getEndpoint(HighlightEndpoint::NAME)->add($highlight); |
274
|
|
|
|
275
|
|
|
return $this; |
276
|
|
|
} |
277
|
|
|
|
278
|
|
|
public function getHighlights(): BuilderInterface |
279
|
|
|
{ |
280
|
|
|
/** @var HighlightEndpoint $highlightEndpoint */ |
281
|
|
|
$highlightEndpoint = $this->getEndpoint(HighlightEndpoint::NAME); |
282
|
|
|
|
283
|
|
|
return $highlightEndpoint->getHighlight(); |
284
|
|
|
} |
285
|
|
|
|
286
|
|
|
public function addSuggest(NamedBuilderInterface $suggest): static |
287
|
|
|
{ |
288
|
|
|
$this->getEndpoint(SuggestEndpoint::NAME)->add($suggest, $suggest->getName()); |
289
|
|
|
|
290
|
|
|
return $this; |
291
|
|
|
} |
292
|
|
|
|
293
|
|
|
public function getSuggests(): array |
294
|
|
|
{ |
295
|
|
|
return $this->getEndpoint(SuggestEndpoint::NAME)->getAll(); |
296
|
|
|
} |
297
|
|
|
|
298
|
|
|
public function getFrom(): ?int |
299
|
|
|
{ |
300
|
|
|
return $this->from; |
301
|
|
|
} |
302
|
|
|
|
303
|
|
|
public function setFrom(?int $from): static |
304
|
|
|
{ |
305
|
|
|
$this->from = $from; |
306
|
|
|
|
307
|
|
|
return $this; |
308
|
|
|
} |
309
|
|
|
|
310
|
|
|
public function isTrackTotalHits(): bool |
311
|
|
|
{ |
312
|
|
|
return $this->trackTotalHits; |
313
|
|
|
} |
314
|
|
|
|
315
|
|
|
public function setTrackTotalHits(bool $trackTotalHits): static |
316
|
|
|
{ |
317
|
|
|
$this->trackTotalHits = $trackTotalHits; |
318
|
|
|
|
319
|
|
|
return $this; |
320
|
|
|
} |
321
|
|
|
|
322
|
|
|
public function getSize(): ?int |
323
|
|
|
{ |
324
|
|
|
return $this->size; |
325
|
|
|
} |
326
|
|
|
|
327
|
|
|
public function setSize(?int $size): static |
328
|
|
|
{ |
329
|
|
|
$this->size = $size; |
330
|
|
|
|
331
|
|
|
return $this; |
332
|
|
|
} |
333
|
|
|
|
334
|
|
|
public function isSource(): ?bool |
335
|
|
|
{ |
336
|
|
|
return $this->source; |
337
|
|
|
} |
338
|
|
|
|
339
|
|
|
public function setSource(?bool $source): static |
340
|
|
|
{ |
341
|
|
|
$this->source = $source; |
342
|
|
|
|
343
|
|
|
return $this; |
344
|
|
|
} |
345
|
|
|
|
346
|
|
|
public function getStoredFields(): ?array |
347
|
|
|
{ |
348
|
|
|
return $this->storedFields; |
349
|
|
|
} |
350
|
|
|
|
351
|
|
|
public function setStoredFields(?array $storedFields): static |
352
|
|
|
{ |
353
|
|
|
$this->storedFields = $storedFields; |
354
|
|
|
|
355
|
|
|
return $this; |
356
|
|
|
} |
357
|
|
|
|
358
|
|
|
public function getScriptFields(): ?array |
359
|
|
|
{ |
360
|
|
|
return $this->scriptFields; |
361
|
|
|
} |
362
|
|
|
|
363
|
|
|
public function setScriptFields(?array $scriptFields): static |
364
|
|
|
{ |
365
|
|
|
$this->scriptFields = $scriptFields; |
366
|
|
|
|
367
|
|
|
return $this; |
368
|
|
|
} |
369
|
|
|
|
370
|
|
|
public function getDocValueFields(): ?array |
371
|
|
|
{ |
372
|
|
|
return $this->docValueFields; |
373
|
|
|
} |
374
|
|
|
|
375
|
|
|
public function setDocValueFields(?array $docValueFields): static |
376
|
|
|
{ |
377
|
|
|
$this->docValueFields = $docValueFields; |
378
|
|
|
|
379
|
|
|
return $this; |
380
|
|
|
} |
381
|
|
|
|
382
|
|
|
public function isExplain(): ?bool |
383
|
|
|
{ |
384
|
|
|
return $this->explain; |
385
|
|
|
} |
386
|
|
|
|
387
|
|
|
public function setExplain(?bool $explain): static |
388
|
|
|
{ |
389
|
|
|
$this->explain = $explain; |
390
|
|
|
|
391
|
|
|
return $this; |
392
|
|
|
} |
393
|
|
|
|
394
|
|
|
public function isVersion(): ?bool |
395
|
|
|
{ |
396
|
|
|
return $this->version; |
397
|
|
|
} |
398
|
|
|
|
399
|
|
|
public function setVersion(?bool $version): static |
400
|
|
|
{ |
401
|
|
|
$this->version = $version; |
402
|
|
|
|
403
|
|
|
return $this; |
404
|
|
|
} |
405
|
|
|
|
406
|
|
|
public function getIndicesBoost(): ?array |
407
|
|
|
{ |
408
|
|
|
return $this->indicesBoost; |
409
|
|
|
} |
410
|
|
|
|
411
|
|
|
public function setIndicesBoost(?array $indicesBoost): static |
412
|
|
|
{ |
413
|
|
|
$this->indicesBoost = $indicesBoost; |
414
|
|
|
|
415
|
|
|
return $this; |
416
|
|
|
} |
417
|
|
|
|
418
|
|
|
public function getMinScore(): ?int |
419
|
|
|
{ |
420
|
|
|
return $this->minScore; |
421
|
|
|
} |
422
|
|
|
|
423
|
|
|
public function setMinScore(?int $minScore): static |
424
|
|
|
{ |
425
|
|
|
$this->minScore = $minScore; |
426
|
|
|
|
427
|
|
|
return $this; |
428
|
|
|
} |
429
|
|
|
|
430
|
|
|
public function getSearchAfter(): ?array |
431
|
|
|
{ |
432
|
|
|
return $this->searchAfter; |
433
|
|
|
} |
434
|
|
|
|
435
|
|
|
public function setSearchAfter(?array $searchAfter): static |
436
|
|
|
{ |
437
|
|
|
$this->searchAfter = $searchAfter; |
438
|
|
|
|
439
|
|
|
return $this; |
440
|
|
|
} |
441
|
|
|
|
442
|
|
|
public function getScroll(): ?string |
443
|
|
|
{ |
444
|
|
|
return $this->scroll; |
445
|
|
|
} |
446
|
|
|
|
447
|
|
|
public function setScroll(?string $scroll = '5m'): static |
448
|
|
|
{ |
449
|
|
|
$this->scroll = $scroll; |
450
|
|
|
|
451
|
|
|
$this->addUriParam('scroll', $this->scroll); |
452
|
|
|
|
453
|
|
|
return $this; |
454
|
|
|
} |
455
|
|
|
|
456
|
|
|
public function addUriParam(string $name, string|array|bool $value): static |
457
|
|
|
{ |
458
|
|
|
if (in_array( |
459
|
|
|
$name, |
460
|
|
|
[ |
461
|
|
|
'q', |
462
|
|
|
'df', |
463
|
|
|
'analyzer', |
464
|
|
|
'analyze_wildcard', |
465
|
|
|
'default_operator', |
466
|
|
|
'lenient', |
467
|
|
|
'explain', |
468
|
|
|
'_source', |
469
|
|
|
'_source_exclude', |
470
|
|
|
'_source_include', |
471
|
|
|
'stored_fields', |
472
|
|
|
'sort', |
473
|
|
|
'track_scores', |
474
|
|
|
'timeout', |
475
|
|
|
'terminate_after', |
476
|
|
|
'from', |
477
|
|
|
'size', |
478
|
|
|
'search_type', |
479
|
|
|
'scroll', |
480
|
|
|
'allow_no_indices', |
481
|
|
|
'ignore_unavailable', |
482
|
|
|
'typed_keys', |
483
|
|
|
'pre_filter_shard_size', |
484
|
|
|
'ignore_unavailable', |
485
|
|
|
] |
486
|
|
|
)) { |
487
|
|
|
$this->uriParams[$name] = $value; |
488
|
|
|
} else { |
489
|
|
|
throw new \InvalidArgumentException(sprintf('Parameter %s is not supported.', $value)); |
490
|
|
|
} |
491
|
|
|
|
492
|
|
|
return $this; |
493
|
|
|
} |
494
|
|
|
|
495
|
|
|
public function getUriParams(): array |
496
|
|
|
{ |
497
|
|
|
return $this->uriParams; |
498
|
|
|
} |
499
|
|
|
|
500
|
|
|
public function toArray(): array |
501
|
|
|
{ |
502
|
|
|
$output = array_filter(static::$serializer->normalize($this->endpoints)); |
503
|
|
|
|
504
|
|
|
$params = [ |
505
|
|
|
'from' => 'from', |
506
|
|
|
'size' => 'size', |
507
|
|
|
'source' => '_source', |
508
|
|
|
'storedFields' => 'stored_fields', |
509
|
|
|
'scriptFields' => 'script_fields', |
510
|
|
|
'docValueFields' => 'docvalue_fields', |
511
|
|
|
'explain' => 'explain', |
512
|
|
|
'version' => 'version', |
513
|
|
|
'indicesBoost' => 'indices_boost', |
514
|
|
|
'minScore' => 'min_score', |
515
|
|
|
'searchAfter' => 'search_after', |
516
|
|
|
'trackTotalHits' => 'track_total_hits', |
517
|
|
|
]; |
518
|
|
|
|
519
|
|
|
foreach ($params as $field => $param) { |
520
|
|
|
if ($this->$field !== null) { |
521
|
|
|
$output[$param] = $this->$field; |
522
|
|
|
} |
523
|
|
|
} |
524
|
|
|
|
525
|
|
|
return $output; |
526
|
|
|
} |
527
|
|
|
} |
528
|
|
|
|