@@ -1,6 +1,6 @@ discard block |
||
1 | 1 | <?php |
2 | 2 | |
3 | -declare( strict_types = 1 ); |
|
3 | +declare(strict_types=1); |
|
4 | 4 | |
5 | 5 | namespace WikibaseQuality\ConstraintReport\ConstraintCheck\Helper; |
6 | 6 | |
@@ -146,73 +146,73 @@ discard block |
||
146 | 146 | $this->defaultUserAgent = $defaultUserAgent; |
147 | 147 | $this->requestFactory = $requestFactory; |
148 | 148 | $this->entityPrefixes = []; |
149 | - foreach ( $rdfVocabulary->entityNamespaceNames as $namespaceName ) { |
|
150 | - $this->entityPrefixes[] = $rdfVocabulary->getNamespaceURI( $namespaceName ); |
|
149 | + foreach ($rdfVocabulary->entityNamespaceNames as $namespaceName) { |
|
150 | + $this->entityPrefixes[] = $rdfVocabulary->getNamespaceURI($namespaceName); |
|
151 | 151 | } |
152 | 152 | |
153 | - $this->primaryEndpoint = $config->get( 'WBQualityConstraintsSparqlEndpoint' ); |
|
154 | - $this->additionalEndpoints = $config->get( 'WBQualityConstraintsAdditionalSparqlEndpoints' ) ?: []; |
|
155 | - $this->maxQueryTimeMillis = $config->get( 'WBQualityConstraintsSparqlMaxMillis' ); |
|
156 | - $this->subclassOfId = $config->get( 'WBQualityConstraintsSubclassOfId' ); |
|
157 | - $this->cacheMapSize = $config->get( 'WBQualityConstraintsFormatCacheMapSize' ); |
|
153 | + $this->primaryEndpoint = $config->get('WBQualityConstraintsSparqlEndpoint'); |
|
154 | + $this->additionalEndpoints = $config->get('WBQualityConstraintsAdditionalSparqlEndpoints') ?: []; |
|
155 | + $this->maxQueryTimeMillis = $config->get('WBQualityConstraintsSparqlMaxMillis'); |
|
156 | + $this->subclassOfId = $config->get('WBQualityConstraintsSubclassOfId'); |
|
157 | + $this->cacheMapSize = $config->get('WBQualityConstraintsFormatCacheMapSize'); |
|
158 | 158 | $this->timeoutExceptionClasses = $config->get( |
159 | 159 | 'WBQualityConstraintsSparqlTimeoutExceptionClasses' |
160 | 160 | ); |
161 | 161 | $this->sparqlHasWikibaseSupport = $config->get( |
162 | 162 | 'WBQualityConstraintsSparqlHasWikibaseSupport' |
163 | 163 | ); |
164 | - $this->sparqlThrottlingFallbackDuration = (int)$config->get( |
|
164 | + $this->sparqlThrottlingFallbackDuration = (int) $config->get( |
|
165 | 165 | 'WBQualityConstraintsSparqlThrottlingFallbackDuration' |
166 | 166 | ); |
167 | 167 | |
168 | - $this->prefixes = $this->getQueryPrefixes( $rdfVocabulary ); |
|
168 | + $this->prefixes = $this->getQueryPrefixes($rdfVocabulary); |
|
169 | 169 | } |
170 | 170 | |
171 | - private function getQueryPrefixes( RdfVocabulary $rdfVocabulary ): string { |
|
171 | + private function getQueryPrefixes(RdfVocabulary $rdfVocabulary): string { |
|
172 | 172 | // TODO: it would probably be smarter that RdfVocabulary exposed these prefixes somehow |
173 | 173 | $prefixes = ''; |
174 | - foreach ( $rdfVocabulary->entityNamespaceNames as $sourceName => $namespaceName ) { |
|
174 | + foreach ($rdfVocabulary->entityNamespaceNames as $sourceName => $namespaceName) { |
|
175 | 175 | $prefixes .= <<<END |
176 | -PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI( $namespaceName )}>\n |
|
176 | +PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI($namespaceName)}>\n |
|
177 | 177 | END; |
178 | 178 | } |
179 | 179 | $prefixes .= <<<END |
180 | -PREFIX wds: <{$rdfVocabulary->getNamespaceURI( RdfVocabulary::NS_STATEMENT )}> |
|
181 | -PREFIX wdv: <{$rdfVocabulary->getNamespaceURI( RdfVocabulary::NS_VALUE )}>\n |
|
180 | +PREFIX wds: <{$rdfVocabulary->getNamespaceURI(RdfVocabulary::NS_STATEMENT)}> |
|
181 | +PREFIX wdv: <{$rdfVocabulary->getNamespaceURI(RdfVocabulary::NS_VALUE)}>\n |
|
182 | 182 | END; |
183 | 183 | |
184 | - foreach ( $rdfVocabulary->propertyNamespaceNames as $sourceName => $sourceNamespaces ) { |
|
184 | + foreach ($rdfVocabulary->propertyNamespaceNames as $sourceName => $sourceNamespaces) { |
|
185 | 185 | $namespaceName = $sourceNamespaces[RdfVocabulary::NSP_DIRECT_CLAIM]; |
186 | 186 | $prefixes .= <<<END |
187 | -PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI( $namespaceName )}>\n |
|
187 | +PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI($namespaceName)}>\n |
|
188 | 188 | END; |
189 | 189 | $namespaceName = $sourceNamespaces[RdfVocabulary::NSP_CLAIM]; |
190 | 190 | $prefixes .= <<<END |
191 | -PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI( $namespaceName )}>\n |
|
191 | +PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI($namespaceName)}>\n |
|
192 | 192 | END; |
193 | 193 | $namespaceName = $sourceNamespaces[RdfVocabulary::NSP_CLAIM_STATEMENT]; |
194 | 194 | $prefixes .= <<<END |
195 | -PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI( $namespaceName )}>\n |
|
195 | +PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI($namespaceName)}>\n |
|
196 | 196 | END; |
197 | 197 | $namespaceName = $sourceNamespaces[RdfVocabulary::NSP_QUALIFIER]; |
198 | 198 | $prefixes .= <<<END |
199 | -PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI( $namespaceName )}>\n |
|
199 | +PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI($namespaceName)}>\n |
|
200 | 200 | END; |
201 | 201 | $namespaceName = $sourceNamespaces[RdfVocabulary::NSP_QUALIFIER_VALUE]; |
202 | 202 | $prefixes .= <<<END |
203 | -PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI( $namespaceName )}>\n |
|
203 | +PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI($namespaceName)}>\n |
|
204 | 204 | END; |
205 | 205 | $namespaceName = $sourceNamespaces[RdfVocabulary::NSP_REFERENCE]; |
206 | 206 | $prefixes .= <<<END |
207 | -PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI( $namespaceName )}>\n |
|
207 | +PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI($namespaceName)}>\n |
|
208 | 208 | END; |
209 | 209 | $namespaceName = $sourceNamespaces[RdfVocabulary::NSP_REFERENCE_VALUE]; |
210 | 210 | $prefixes .= <<<END |
211 | -PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI( $namespaceName )}>\n |
|
211 | +PREFIX {$namespaceName}: <{$rdfVocabulary->getNamespaceURI($namespaceName)}>\n |
|
212 | 212 | END; |
213 | 213 | } |
214 | 214 | $prefixes .= <<<END |
215 | -PREFIX wikibase: <{$rdfVocabulary->getNamespaceURI( RdfVocabulary::NS_ONTOLOGY )}>\n |
|
215 | +PREFIX wikibase: <{$rdfVocabulary->getNamespaceURI(RdfVocabulary::NS_ONTOLOGY)}>\n |
|
216 | 216 | END; |
217 | 217 | return $prefixes; |
218 | 218 | } |
@@ -224,21 +224,20 @@ discard block |
||
224 | 224 | * @return CachedBool |
225 | 225 | * @throws SparqlHelperException if the query times out or some other error occurs |
226 | 226 | */ |
227 | - public function hasType( string $id, array $classes ): CachedBool { |
|
227 | + public function hasType(string $id, array $classes): CachedBool { |
|
228 | 228 | // TODO hint:gearing is a workaround for T168973 and can hopefully be removed eventually |
229 | 229 | $gearingHint = $this->sparqlHasWikibaseSupport ? |
230 | - ' hint:Prior hint:gearing "forward".' : |
|
231 | - ''; |
|
230 | + ' hint:Prior hint:gearing "forward".' : ''; |
|
232 | 231 | |
233 | 232 | $metadatas = []; |
234 | 233 | |
235 | - foreach ( array_chunk( $classes, 20 ) as $classesChunk ) { |
|
236 | - $classesValues = implode( ' ', array_map( |
|
237 | - static function ( $class ) { |
|
238 | - return 'wd:' . $class; |
|
234 | + foreach (array_chunk($classes, 20) as $classesChunk) { |
|
235 | + $classesValues = implode(' ', array_map( |
|
236 | + static function($class) { |
|
237 | + return 'wd:'.$class; |
|
239 | 238 | }, |
240 | 239 | $classesChunk |
241 | - ) ); |
|
240 | + )); |
|
242 | 241 | |
243 | 242 | $query = <<<EOF |
244 | 243 | ASK { |
@@ -248,19 +247,19 @@ discard block |
||
248 | 247 | } |
249 | 248 | EOF; |
250 | 249 | |
251 | - $result = $this->runQuery( $query, $this->primaryEndpoint ); |
|
250 | + $result = $this->runQuery($query, $this->primaryEndpoint); |
|
252 | 251 | $metadatas[] = $result->getMetadata(); |
253 | - if ( $result->getArray()['boolean'] ) { |
|
252 | + if ($result->getArray()['boolean']) { |
|
254 | 253 | return new CachedBool( |
255 | 254 | true, |
256 | - Metadata::merge( $metadatas ) |
|
255 | + Metadata::merge($metadatas) |
|
257 | 256 | ); |
258 | 257 | } |
259 | 258 | } |
260 | 259 | |
261 | 260 | return new CachedBool( |
262 | 261 | false, |
263 | - Metadata::merge( $metadatas ) |
|
262 | + Metadata::merge($metadatas) |
|
264 | 263 | ); |
265 | 264 | } |
266 | 265 | |
@@ -268,7 +267,7 @@ discard block |
||
268 | 267 | * Helper function used by findEntitiesWithSameStatement to filter |
269 | 268 | * out entities with different qualifiers or no qualifier value. |
270 | 269 | */ |
271 | - private function nestedSeparatorFilter( PropertyId $separator ): string { |
|
270 | + private function nestedSeparatorFilter(PropertyId $separator): string { |
|
272 | 271 | $filter = <<<EOF |
273 | 272 | MINUS { |
274 | 273 | ?statement pq:$separator ?qualifier. |
@@ -305,14 +304,14 @@ discard block |
||
305 | 304 | * @return CachedEntityIds |
306 | 305 | * @throws SparqlHelperException if the query times out or some other error occurs |
307 | 306 | */ |
308 | - public function findEntitiesWithSameStatement( Statement $statement, array $separators ): CachedEntityIds { |
|
307 | + public function findEntitiesWithSameStatement(Statement $statement, array $separators): CachedEntityIds { |
|
309 | 308 | $pid = $statement->getPropertyId()->getSerialization(); |
310 | 309 | $guid = $statement->getGuid(); |
311 | 310 | '@phan-var string $guid'; // statement must have a non-null GUID |
312 | - $guidForRdf = str_replace( '$', '-', $guid ); |
|
311 | + $guidForRdf = str_replace('$', '-', $guid); |
|
313 | 312 | |
314 | - $separatorFilters = array_map( [ $this, 'nestedSeparatorFilter' ], $separators ); |
|
315 | - $finalSeparatorFilter = implode( "\n", $separatorFilters ); |
|
313 | + $separatorFilters = array_map([$this, 'nestedSeparatorFilter'], $separators); |
|
314 | + $finalSeparatorFilter = implode("\n", $separatorFilters); |
|
316 | 315 | |
317 | 316 | $query = <<<EOF |
318 | 317 | SELECT DISTINCT ?otherEntity WHERE { |
@@ -330,12 +329,12 @@ discard block |
||
330 | 329 | LIMIT 10 |
331 | 330 | EOF; |
332 | 331 | |
333 | - $results = [ $this->runQuery( $query, $this->primaryEndpoint ) ]; |
|
334 | - foreach ( $this->additionalEndpoints as $endpoint ) { |
|
335 | - $results[] = $this->runQuery( $query, $endpoint ); |
|
332 | + $results = [$this->runQuery($query, $this->primaryEndpoint)]; |
|
333 | + foreach ($this->additionalEndpoints as $endpoint) { |
|
334 | + $results[] = $this->runQuery($query, $endpoint); |
|
336 | 335 | } |
337 | 336 | |
338 | - return $this->getOtherEntities( $results ); |
|
337 | + return $this->getOtherEntities($results); |
|
339 | 338 | } |
340 | 339 | |
341 | 340 | /** |
@@ -360,16 +359,15 @@ discard block |
||
360 | 359 | $dataType = $this->propertyDataTypeLookup->getDataTypeIdForProperty( |
361 | 360 | $snak->getPropertyId() |
362 | 361 | ); |
363 | - [ $value, $isFullValue ] = $this->getRdfLiteral( $dataType, $dataValue ); |
|
364 | - if ( $isFullValue ) { |
|
362 | + [$value, $isFullValue] = $this->getRdfLiteral($dataType, $dataValue); |
|
363 | + if ($isFullValue) { |
|
365 | 364 | $prefix .= 'v'; |
366 | 365 | } |
367 | 366 | $path = $type === Context::TYPE_QUALIFIER ? |
368 | - "$prefix:$pid" : |
|
369 | - "prov:wasDerivedFrom/$prefix:$pid"; |
|
367 | + "$prefix:$pid" : "prov:wasDerivedFrom/$prefix:$pid"; |
|
370 | 368 | |
371 | 369 | $deprecatedFilter = ''; |
372 | - if ( $ignoreDeprecatedStatements ) { |
|
370 | + if ($ignoreDeprecatedStatements) { |
|
373 | 371 | $deprecatedFilter = <<< EOF |
374 | 372 | MINUS { ?otherStatement wikibase:rank wikibase:DeprecatedRank. } |
375 | 373 | EOF; |
@@ -389,19 +387,19 @@ discard block |
||
389 | 387 | LIMIT 10 |
390 | 388 | EOF; |
391 | 389 | |
392 | - $results = [ $this->runQuery( $query, $this->primaryEndpoint ) ]; |
|
393 | - foreach ( $this->additionalEndpoints as $endpoint ) { |
|
394 | - $results[] = $this->runQuery( $query, $endpoint ); |
|
390 | + $results = [$this->runQuery($query, $this->primaryEndpoint)]; |
|
391 | + foreach ($this->additionalEndpoints as $endpoint) { |
|
392 | + $results[] = $this->runQuery($query, $endpoint); |
|
395 | 393 | } |
396 | 394 | |
397 | - return $this->getOtherEntities( $results ); |
|
395 | + return $this->getOtherEntities($results); |
|
398 | 396 | } |
399 | 397 | |
400 | 398 | /** |
401 | 399 | * Return SPARQL code for a string literal with $text as content. |
402 | 400 | */ |
403 | - private function stringLiteral( string $text ): string { |
|
404 | - return '"' . strtr( $text, [ '"' => '\\"', '\\' => '\\\\' ] ) . '"'; |
|
401 | + private function stringLiteral(string $text): string { |
|
402 | + return '"'.strtr($text, ['"' => '\\"', '\\' => '\\\\']).'"'; |
|
405 | 403 | } |
406 | 404 | |
407 | 405 | /** |
@@ -411,26 +409,26 @@ discard block |
||
411 | 409 | * |
412 | 410 | * @return CachedEntityIds |
413 | 411 | */ |
414 | - private function getOtherEntities( array $results ): CachedEntityIds { |
|
412 | + private function getOtherEntities(array $results): CachedEntityIds { |
|
415 | 413 | $allResultBindings = []; |
416 | 414 | $metadatas = []; |
417 | 415 | |
418 | - foreach ( $results as $result ) { |
|
416 | + foreach ($results as $result) { |
|
419 | 417 | $metadatas[] = $result->getMetadata(); |
420 | - $allResultBindings = array_merge( $allResultBindings, $result->getArray()['results']['bindings'] ); |
|
418 | + $allResultBindings = array_merge($allResultBindings, $result->getArray()['results']['bindings']); |
|
421 | 419 | } |
422 | 420 | |
423 | 421 | $entityIds = array_map( |
424 | - function ( $resultBindings ) { |
|
422 | + function($resultBindings) { |
|
425 | 423 | $entityIRI = $resultBindings['otherEntity']['value']; |
426 | - foreach ( $this->entityPrefixes as $entityPrefix ) { |
|
427 | - $entityPrefixLength = strlen( $entityPrefix ); |
|
428 | - if ( substr( $entityIRI, 0, $entityPrefixLength ) === $entityPrefix ) { |
|
424 | + foreach ($this->entityPrefixes as $entityPrefix) { |
|
425 | + $entityPrefixLength = strlen($entityPrefix); |
|
426 | + if (substr($entityIRI, 0, $entityPrefixLength) === $entityPrefix) { |
|
429 | 427 | try { |
430 | 428 | return $this->entityIdParser->parse( |
431 | - substr( $entityIRI, $entityPrefixLength ) |
|
429 | + substr($entityIRI, $entityPrefixLength) |
|
432 | 430 | ); |
433 | - } catch ( EntityIdParsingException $e ) { |
|
431 | + } catch (EntityIdParsingException $e) { |
|
434 | 432 | // fall through |
435 | 433 | } |
436 | 434 | } |
@@ -444,8 +442,8 @@ discard block |
||
444 | 442 | ); |
445 | 443 | |
446 | 444 | return new CachedEntityIds( |
447 | - array_values( array_filter( array_unique( $entityIds ) ) ), |
|
448 | - Metadata::merge( $metadatas ) |
|
445 | + array_values(array_filter(array_unique($entityIds))), |
|
446 | + Metadata::merge($metadatas) |
|
449 | 447 | ); |
450 | 448 | } |
451 | 449 | |
@@ -456,50 +454,50 @@ discard block |
||
456 | 454 | * @return array the literal or IRI as a string in SPARQL syntax, |
457 | 455 | * and a boolean indicating whether it refers to a full value node or not |
458 | 456 | */ |
459 | - private function getRdfLiteral( string $dataType, DataValue $dataValue ): array { |
|
460 | - switch ( $dataType ) { |
|
457 | + private function getRdfLiteral(string $dataType, DataValue $dataValue): array { |
|
458 | + switch ($dataType) { |
|
461 | 459 | case 'string': |
462 | 460 | case 'external-id': |
463 | - return [ $this->stringLiteral( $dataValue->getValue() ), false ]; |
|
461 | + return [$this->stringLiteral($dataValue->getValue()), false]; |
|
464 | 462 | case 'commonsMedia': |
465 | - $url = $this->rdfVocabulary->getMediaFileURI( $dataValue->getValue() ); |
|
466 | - return [ '<' . $url . '>', false ]; |
|
463 | + $url = $this->rdfVocabulary->getMediaFileURI($dataValue->getValue()); |
|
464 | + return ['<'.$url.'>', false]; |
|
467 | 465 | case 'geo-shape': |
468 | - $url = $this->rdfVocabulary->getGeoShapeURI( $dataValue->getValue() ); |
|
469 | - return [ '<' . $url . '>', false ]; |
|
466 | + $url = $this->rdfVocabulary->getGeoShapeURI($dataValue->getValue()); |
|
467 | + return ['<'.$url.'>', false]; |
|
470 | 468 | case 'tabular-data': |
471 | - $url = $this->rdfVocabulary->getTabularDataURI( $dataValue->getValue() ); |
|
472 | - return [ '<' . $url . '>', false ]; |
|
469 | + $url = $this->rdfVocabulary->getTabularDataURI($dataValue->getValue()); |
|
470 | + return ['<'.$url.'>', false]; |
|
473 | 471 | case 'url': |
474 | 472 | $url = $dataValue->getValue(); |
475 | - if ( !preg_match( '/^[^<>"{}\\\\|^`\\x00-\\x20]*$/D', $url ) ) { |
|
473 | + if (!preg_match('/^[^<>"{}\\\\|^`\\x00-\\x20]*$/D', $url)) { |
|
476 | 474 | // not a valid URL for SPARQL (see SPARQL spec, production 139 IRIREF) |
477 | 475 | // such an URL should never reach us, so just throw |
478 | - throw new InvalidArgumentException( 'invalid URL: ' . $url ); |
|
476 | + throw new InvalidArgumentException('invalid URL: '.$url); |
|
479 | 477 | } |
480 | - return [ '<' . $url . '>', false ]; |
|
478 | + return ['<'.$url.'>', false]; |
|
481 | 479 | case 'wikibase-item': |
482 | 480 | case 'wikibase-property': |
483 | 481 | /** @var EntityIdValue $dataValue */ |
484 | 482 | '@phan-var EntityIdValue $dataValue'; |
485 | - return [ 'wd:' . $dataValue->getEntityId()->getSerialization(), false ]; |
|
483 | + return ['wd:'.$dataValue->getEntityId()->getSerialization(), false]; |
|
486 | 484 | case 'monolingualtext': |
487 | 485 | /** @var MonolingualTextValue $dataValue */ |
488 | 486 | '@phan-var MonolingualTextValue $dataValue'; |
489 | 487 | $lang = $dataValue->getLanguageCode(); |
490 | - if ( !preg_match( '/^[a-zA-Z]+(-[a-zA-Z0-9]+)*$/D', $lang ) ) { |
|
488 | + if (!preg_match('/^[a-zA-Z]+(-[a-zA-Z0-9]+)*$/D', $lang)) { |
|
491 | 489 | // not a valid language tag for SPARQL (see SPARQL spec, production 145 LANGTAG) |
492 | 490 | // such a language tag should never reach us, so just throw |
493 | - throw new InvalidArgumentException( 'invalid language tag: ' . $lang ); |
|
491 | + throw new InvalidArgumentException('invalid language tag: '.$lang); |
|
494 | 492 | } |
495 | - return [ $this->stringLiteral( $dataValue->getText() ) . '@' . $lang, false ]; |
|
493 | + return [$this->stringLiteral($dataValue->getText()).'@'.$lang, false]; |
|
496 | 494 | case 'globe-coordinate': |
497 | 495 | case 'quantity': |
498 | 496 | case 'time': |
499 | 497 | // @phan-suppress-next-line PhanUndeclaredMethod |
500 | - return [ 'wdv:' . $dataValue->getHash(), true ]; |
|
498 | + return ['wdv:'.$dataValue->getHash(), true]; |
|
501 | 499 | default: |
502 | - throw new InvalidArgumentException( 'unknown data type: ' . $dataType ); |
|
500 | + throw new InvalidArgumentException('unknown data type: '.$dataType); |
|
503 | 501 | } |
504 | 502 | } |
505 | 503 | // phpcs:enable |
@@ -508,43 +506,43 @@ discard block |
||
508 | 506 | * @throws SparqlHelperException if the query times out or some other error occurs |
509 | 507 | * @throws ConstraintParameterException if the $regex is invalid |
510 | 508 | */ |
511 | - public function matchesRegularExpression( string $text, string $regex ): bool { |
|
509 | + public function matchesRegularExpression(string $text, string $regex): bool { |
|
512 | 510 | // caching wrapper around matchesRegularExpressionWithSparql |
513 | 511 | |
514 | - $textHash = hash( 'sha256', $text ); |
|
512 | + $textHash = hash('sha256', $text); |
|
515 | 513 | $cacheKey = $this->cache->makeKey( |
516 | 514 | 'WikibaseQualityConstraints', // extension |
517 | 515 | 'regex', // action |
518 | 516 | 'WDQS-Java', // regex flavor |
519 | - hash( 'sha256', $regex ) |
|
517 | + hash('sha256', $regex) |
|
520 | 518 | ); |
521 | 519 | |
522 | 520 | $cacheMapArray = $this->cache->getWithSetCallback( |
523 | 521 | $cacheKey, |
524 | 522 | WANObjectCache::TTL_DAY, |
525 | - function ( $cacheMapArray ) use ( $text, $regex, $textHash ) { |
|
523 | + function($cacheMapArray) use ($text, $regex, $textHash) { |
|
526 | 524 | // Initialize the cache map if not set |
527 | - if ( $cacheMapArray === false ) { |
|
525 | + if ($cacheMapArray === false) { |
|
528 | 526 | $key = 'wikibase.quality.constraints.regex.cache.refresh.init'; |
529 | - $this->dataFactory->increment( $key ); |
|
527 | + $this->dataFactory->increment($key); |
|
530 | 528 | return []; |
531 | 529 | } |
532 | 530 | |
533 | 531 | $key = 'wikibase.quality.constraints.regex.cache.refresh'; |
534 | - $this->dataFactory->increment( $key ); |
|
535 | - $cacheMap = MapCacheLRU::newFromArray( $cacheMapArray, $this->cacheMapSize ); |
|
536 | - if ( $cacheMap->has( $textHash ) ) { |
|
532 | + $this->dataFactory->increment($key); |
|
533 | + $cacheMap = MapCacheLRU::newFromArray($cacheMapArray, $this->cacheMapSize); |
|
534 | + if ($cacheMap->has($textHash)) { |
|
537 | 535 | $key = 'wikibase.quality.constraints.regex.cache.refresh.hit'; |
538 | - $this->dataFactory->increment( $key ); |
|
539 | - $cacheMap->get( $textHash ); // ping cache |
|
536 | + $this->dataFactory->increment($key); |
|
537 | + $cacheMap->get($textHash); // ping cache |
|
540 | 538 | } else { |
541 | 539 | $key = 'wikibase.quality.constraints.regex.cache.refresh.miss'; |
542 | - $this->dataFactory->increment( $key ); |
|
540 | + $this->dataFactory->increment($key); |
|
543 | 541 | try { |
544 | - $matches = $this->matchesRegularExpressionWithSparql( $text, $regex ); |
|
545 | - } catch ( ConstraintParameterException $e ) { |
|
546 | - $matches = $this->serializeConstraintParameterException( $e ); |
|
547 | - } catch ( SparqlHelperException $e ) { |
|
542 | + $matches = $this->matchesRegularExpressionWithSparql($text, $regex); |
|
543 | + } catch (ConstraintParameterException $e) { |
|
544 | + $matches = $this->serializeConstraintParameterException($e); |
|
545 | + } catch (SparqlHelperException $e) { |
|
548 | 546 | // don’t cache this |
549 | 547 | return $cacheMap->toArray(); |
550 | 548 | } |
@@ -568,42 +566,42 @@ discard block |
||
568 | 566 | ] |
569 | 567 | ); |
570 | 568 | |
571 | - if ( isset( $cacheMapArray[$textHash] ) ) { |
|
569 | + if (isset($cacheMapArray[$textHash])) { |
|
572 | 570 | $key = 'wikibase.quality.constraints.regex.cache.hit'; |
573 | - $this->dataFactory->increment( $key ); |
|
571 | + $this->dataFactory->increment($key); |
|
574 | 572 | $matches = $cacheMapArray[$textHash]; |
575 | - if ( is_bool( $matches ) ) { |
|
573 | + if (is_bool($matches)) { |
|
576 | 574 | return $matches; |
577 | - } elseif ( is_array( $matches ) && |
|
578 | - $matches['type'] == ConstraintParameterException::class ) { |
|
579 | - throw $this->deserializeConstraintParameterException( $matches ); |
|
575 | + } elseif (is_array($matches) && |
|
576 | + $matches['type'] == ConstraintParameterException::class) { |
|
577 | + throw $this->deserializeConstraintParameterException($matches); |
|
580 | 578 | } else { |
581 | 579 | throw new UnexpectedValueException( |
582 | - 'Value of unknown type in object cache (' . |
|
583 | - 'cache key: ' . $cacheKey . ', ' . |
|
584 | - 'cache map key: ' . $textHash . ', ' . |
|
585 | - 'value type: ' . get_debug_type( $matches ) . ')' |
|
580 | + 'Value of unknown type in object cache ('. |
|
581 | + 'cache key: '.$cacheKey.', '. |
|
582 | + 'cache map key: '.$textHash.', '. |
|
583 | + 'value type: '.get_debug_type($matches).')' |
|
586 | 584 | ); |
587 | 585 | } |
588 | 586 | } else { |
589 | 587 | $key = 'wikibase.quality.constraints.regex.cache.miss'; |
590 | - $this->dataFactory->increment( $key ); |
|
591 | - return $this->matchesRegularExpressionWithSparql( $text, $regex ); |
|
588 | + $this->dataFactory->increment($key); |
|
589 | + return $this->matchesRegularExpressionWithSparql($text, $regex); |
|
592 | 590 | } |
593 | 591 | } |
594 | 592 | |
595 | - private function serializeConstraintParameterException( ConstraintParameterException $cpe ): array { |
|
593 | + private function serializeConstraintParameterException(ConstraintParameterException $cpe): array { |
|
596 | 594 | return [ |
597 | 595 | 'type' => ConstraintParameterException::class, |
598 | - 'violationMessage' => $this->violationMessageSerializer->serialize( $cpe->getViolationMessage() ), |
|
596 | + 'violationMessage' => $this->violationMessageSerializer->serialize($cpe->getViolationMessage()), |
|
599 | 597 | ]; |
600 | 598 | } |
601 | 599 | |
602 | - private function deserializeConstraintParameterException( array $serialization ): ConstraintParameterException { |
|
600 | + private function deserializeConstraintParameterException(array $serialization): ConstraintParameterException { |
|
603 | 601 | $message = $this->violationMessageDeserializer->deserialize( |
604 | 602 | $serialization['violationMessage'] |
605 | 603 | ); |
606 | - return new ConstraintParameterException( $message ); |
|
604 | + return new ConstraintParameterException($message); |
|
607 | 605 | } |
608 | 606 | |
609 | 607 | /** |
@@ -613,25 +611,25 @@ discard block |
||
613 | 611 | * @throws SparqlHelperException if the query times out or some other error occurs |
614 | 612 | * @throws ConstraintParameterException if the $regex is invalid |
615 | 613 | */ |
616 | - public function matchesRegularExpressionWithSparql( string $text, string $regex ): bool { |
|
617 | - $textStringLiteral = $this->stringLiteral( $text ); |
|
618 | - $regexStringLiteral = $this->stringLiteral( '^(?:' . $regex . ')$' ); |
|
614 | + public function matchesRegularExpressionWithSparql(string $text, string $regex): bool { |
|
615 | + $textStringLiteral = $this->stringLiteral($text); |
|
616 | + $regexStringLiteral = $this->stringLiteral('^(?:'.$regex.')$'); |
|
619 | 617 | |
620 | 618 | $query = <<<EOF |
621 | 619 | SELECT (REGEX($textStringLiteral, $regexStringLiteral) AS ?matches) {} |
622 | 620 | EOF; |
623 | 621 | |
624 | - $result = $this->runQuery( $query, $this->primaryEndpoint, false ); |
|
622 | + $result = $this->runQuery($query, $this->primaryEndpoint, false); |
|
625 | 623 | |
626 | 624 | $vars = $result->getArray()['results']['bindings'][0]; |
627 | - if ( array_key_exists( 'matches', $vars ) ) { |
|
625 | + if (array_key_exists('matches', $vars)) { |
|
628 | 626 | // true or false ⇒ regex okay, text matches or not |
629 | 627 | return $vars['matches']['value'] === 'true'; |
630 | 628 | } else { |
631 | 629 | // empty result: regex broken |
632 | 630 | throw new ConstraintParameterException( |
633 | - ( new ViolationMessage( 'wbqc-violation-message-parameter-regex' ) ) |
|
634 | - ->withInlineCode( $regex, Role::CONSTRAINT_PARAMETER_VALUE ) |
|
631 | + (new ViolationMessage('wbqc-violation-message-parameter-regex')) |
|
632 | + ->withInlineCode($regex, Role::CONSTRAINT_PARAMETER_VALUE) |
|
635 | 633 | ); |
636 | 634 | } |
637 | 635 | } |
@@ -639,14 +637,14 @@ discard block |
||
639 | 637 | /** |
640 | 638 | * Check whether the text content of an error response indicates a query timeout. |
641 | 639 | */ |
642 | - public function isTimeout( string $responseContent ): bool { |
|
643 | - $timeoutRegex = implode( '|', array_map( |
|
644 | - static function ( $fqn ) { |
|
645 | - return preg_quote( $fqn, '/' ); |
|
640 | + public function isTimeout(string $responseContent): bool { |
|
641 | + $timeoutRegex = implode('|', array_map( |
|
642 | + static function($fqn) { |
|
643 | + return preg_quote($fqn, '/'); |
|
646 | 644 | }, |
647 | 645 | $this->timeoutExceptionClasses |
648 | - ) ); |
|
649 | - return (bool)preg_match( '/' . $timeoutRegex . '/', $responseContent ); |
|
646 | + )); |
|
647 | + return (bool) preg_match('/'.$timeoutRegex.'/', $responseContent); |
|
650 | 648 | } |
651 | 649 | |
652 | 650 | /** |
@@ -658,17 +656,17 @@ discard block |
||
658 | 656 | * @return int|boolean the max-age (in seconds) |
659 | 657 | * or a plain boolean if no max-age can be determined |
660 | 658 | */ |
661 | - public function getCacheMaxAge( array $responseHeaders ) { |
|
659 | + public function getCacheMaxAge(array $responseHeaders) { |
|
662 | 660 | if ( |
663 | - array_key_exists( 'x-cache-status', $responseHeaders ) && |
|
664 | - preg_match( '/^hit(?:-.*)?$/', $responseHeaders['x-cache-status'][0] ) |
|
661 | + array_key_exists('x-cache-status', $responseHeaders) && |
|
662 | + preg_match('/^hit(?:-.*)?$/', $responseHeaders['x-cache-status'][0]) |
|
665 | 663 | ) { |
666 | 664 | $maxage = []; |
667 | 665 | if ( |
668 | - array_key_exists( 'cache-control', $responseHeaders ) && |
|
669 | - preg_match( '/\bmax-age=(\d+)\b/', $responseHeaders['cache-control'][0], $maxage ) |
|
666 | + array_key_exists('cache-control', $responseHeaders) && |
|
667 | + preg_match('/\bmax-age=(\d+)\b/', $responseHeaders['cache-control'][0], $maxage) |
|
670 | 668 | ) { |
671 | - return intval( $maxage[1] ); |
|
669 | + return intval($maxage[1]); |
|
672 | 670 | } else { |
673 | 671 | return true; |
674 | 672 | } |
@@ -689,34 +687,34 @@ discard block |
||
689 | 687 | * or SparlHelper::EMPTY_RETRY_AFTER if there is an empty Retry-After |
690 | 688 | * or SparlHelper::INVALID_RETRY_AFTER if there is something wrong with the format |
691 | 689 | */ |
692 | - public function getThrottling( MWHttpRequest $request ) { |
|
693 | - $retryAfterValue = $request->getResponseHeader( 'Retry-After' ); |
|
694 | - if ( $retryAfterValue === null ) { |
|
690 | + public function getThrottling(MWHttpRequest $request) { |
|
691 | + $retryAfterValue = $request->getResponseHeader('Retry-After'); |
|
692 | + if ($retryAfterValue === null) { |
|
695 | 693 | return self::NO_RETRY_AFTER; |
696 | 694 | } |
697 | 695 | |
698 | - $trimmedRetryAfterValue = trim( $retryAfterValue ); |
|
699 | - if ( $trimmedRetryAfterValue === '' ) { |
|
696 | + $trimmedRetryAfterValue = trim($retryAfterValue); |
|
697 | + if ($trimmedRetryAfterValue === '') { |
|
700 | 698 | return self::EMPTY_RETRY_AFTER; |
701 | 699 | } |
702 | 700 | |
703 | - if ( is_numeric( $trimmedRetryAfterValue ) ) { |
|
704 | - $delaySeconds = (int)$trimmedRetryAfterValue; |
|
705 | - if ( $delaySeconds >= 0 ) { |
|
706 | - return $this->getTimestampInFuture( new DateInterval( 'PT' . $delaySeconds . 'S' ) ); |
|
701 | + if (is_numeric($trimmedRetryAfterValue)) { |
|
702 | + $delaySeconds = (int) $trimmedRetryAfterValue; |
|
703 | + if ($delaySeconds >= 0) { |
|
704 | + return $this->getTimestampInFuture(new DateInterval('PT'.$delaySeconds.'S')); |
|
707 | 705 | } |
708 | 706 | } else { |
709 | - $return = strtotime( $trimmedRetryAfterValue ); |
|
710 | - if ( $return !== false ) { |
|
711 | - return new ConvertibleTimestamp( $return ); |
|
707 | + $return = strtotime($trimmedRetryAfterValue); |
|
708 | + if ($return !== false) { |
|
709 | + return new ConvertibleTimestamp($return); |
|
712 | 710 | } |
713 | 711 | } |
714 | 712 | return self::INVALID_RETRY_AFTER; |
715 | 713 | } |
716 | 714 | |
717 | - private function getTimestampInFuture( DateInterval $delta ) { |
|
715 | + private function getTimestampInFuture(DateInterval $delta) { |
|
718 | 716 | $now = new ConvertibleTimestamp(); |
719 | - return new ConvertibleTimestamp( $now->timestamp->add( $delta ) ); |
|
717 | + return new ConvertibleTimestamp($now->timestamp->add($delta)); |
|
720 | 718 | } |
721 | 719 | |
722 | 720 | /** |
@@ -731,64 +729,63 @@ discard block |
||
731 | 729 | * |
732 | 730 | * @throws SparqlHelperException if the query times out or some other error occurs |
733 | 731 | */ |
734 | - protected function runQuery( string $query, string $endpoint, bool $needsPrefixes = true ): CachedQueryResults { |
|
735 | - if ( $this->throttlingLock->isLocked( self::EXPIRY_LOCK_ID ) ) { |
|
736 | - $this->dataFactory->increment( 'wikibase.quality.constraints.sparql.throttling' ); |
|
732 | + protected function runQuery(string $query, string $endpoint, bool $needsPrefixes = true): CachedQueryResults { |
|
733 | + if ($this->throttlingLock->isLocked(self::EXPIRY_LOCK_ID)) { |
|
734 | + $this->dataFactory->increment('wikibase.quality.constraints.sparql.throttling'); |
|
737 | 735 | throw new TooManySparqlRequestsException(); |
738 | 736 | } |
739 | 737 | |
740 | - if ( $this->sparqlHasWikibaseSupport ) { |
|
738 | + if ($this->sparqlHasWikibaseSupport) { |
|
741 | 739 | $needsPrefixes = false; |
742 | 740 | } |
743 | 741 | |
744 | - if ( $needsPrefixes ) { |
|
745 | - $query = $this->prefixes . $query; |
|
742 | + if ($needsPrefixes) { |
|
743 | + $query = $this->prefixes.$query; |
|
746 | 744 | } |
747 | - $query = "#wbqc\n" . $query; |
|
745 | + $query = "#wbqc\n".$query; |
|
748 | 746 | |
749 | - $url = $endpoint . '?' . http_build_query( |
|
747 | + $url = $endpoint.'?'.http_build_query( |
|
750 | 748 | [ |
751 | 749 | 'query' => $query, |
752 | 750 | 'format' => 'json', |
753 | 751 | 'maxQueryTimeMillis' => $this->maxQueryTimeMillis, |
754 | 752 | ], |
755 | - '', ini_get( 'arg_separator.output' ), |
|
753 | + '', ini_get('arg_separator.output'), |
|
756 | 754 | // encode spaces with %20, not + |
757 | 755 | PHP_QUERY_RFC3986 |
758 | 756 | ); |
759 | 757 | |
760 | 758 | $options = [ |
761 | 759 | 'method' => 'GET', |
762 | - 'timeout' => (int)round( ( $this->maxQueryTimeMillis + 1000 ) / 1000 ), |
|
760 | + 'timeout' => (int) round(($this->maxQueryTimeMillis + 1000) / 1000), |
|
763 | 761 | 'connectTimeout' => 'default', |
764 | 762 | 'userAgent' => $this->defaultUserAgent, |
765 | 763 | ]; |
766 | - $request = $this->requestFactory->create( $url, $options, __METHOD__ ); |
|
767 | - $startTime = microtime( true ); |
|
764 | + $request = $this->requestFactory->create($url, $options, __METHOD__); |
|
765 | + $startTime = microtime(true); |
|
768 | 766 | $requestStatus = $request->execute(); |
769 | - $endTime = microtime( true ); |
|
767 | + $endTime = microtime(true); |
|
770 | 768 | $this->dataFactory->timing( |
771 | 769 | 'wikibase.quality.constraints.sparql.timing', |
772 | - ( $endTime - $startTime ) * 1000 |
|
770 | + ($endTime - $startTime) * 1000 |
|
773 | 771 | ); |
774 | 772 | |
775 | - $this->guardAgainstTooManyRequestsError( $request ); |
|
773 | + $this->guardAgainstTooManyRequestsError($request); |
|
776 | 774 | |
777 | - $maxAge = $this->getCacheMaxAge( $request->getResponseHeaders() ); |
|
778 | - if ( $maxAge ) { |
|
779 | - $this->dataFactory->increment( 'wikibase.quality.constraints.sparql.cached' ); |
|
775 | + $maxAge = $this->getCacheMaxAge($request->getResponseHeaders()); |
|
776 | + if ($maxAge) { |
|
777 | + $this->dataFactory->increment('wikibase.quality.constraints.sparql.cached'); |
|
780 | 778 | } |
781 | 779 | |
782 | - if ( $requestStatus->isOK() ) { |
|
780 | + if ($requestStatus->isOK()) { |
|
783 | 781 | $json = $request->getContent(); |
784 | - $jsonStatus = FormatJson::parse( $json, FormatJson::FORCE_ASSOC ); |
|
785 | - if ( $jsonStatus->isOK() ) { |
|
782 | + $jsonStatus = FormatJson::parse($json, FormatJson::FORCE_ASSOC); |
|
783 | + if ($jsonStatus->isOK()) { |
|
786 | 784 | return new CachedQueryResults( |
787 | 785 | $jsonStatus->getValue(), |
788 | 786 | Metadata::ofCachingMetadata( |
789 | 787 | $maxAge ? |
790 | - CachingMetadata::ofMaximumAgeInSeconds( $maxAge ) : |
|
791 | - CachingMetadata::fresh() |
|
788 | + CachingMetadata::ofMaximumAgeInSeconds($maxAge) : CachingMetadata::fresh() |
|
792 | 789 | ) |
793 | 790 | ); |
794 | 791 | } else { |
@@ -805,9 +802,9 @@ discard block |
||
805 | 802 | // fall through to general error handling |
806 | 803 | } |
807 | 804 | |
808 | - $this->dataFactory->increment( 'wikibase.quality.constraints.sparql.error' ); |
|
805 | + $this->dataFactory->increment('wikibase.quality.constraints.sparql.error'); |
|
809 | 806 | |
810 | - if ( $this->isTimeout( $request->getContent() ) ) { |
|
807 | + if ($this->isTimeout($request->getContent())) { |
|
811 | 808 | $this->dataFactory->increment( |
812 | 809 | 'wikibase.quality.constraints.sparql.error.timeout' |
813 | 810 | ); |
@@ -822,29 +819,29 @@ discard block |
||
822 | 819 | * @param MWHttpRequest $request |
823 | 820 | * @throws TooManySparqlRequestsException |
824 | 821 | */ |
825 | - private function guardAgainstTooManyRequestsError( MWHttpRequest $request ): void { |
|
826 | - if ( $request->getStatus() !== self::HTTP_TOO_MANY_REQUESTS ) { |
|
822 | + private function guardAgainstTooManyRequestsError(MWHttpRequest $request): void { |
|
823 | + if ($request->getStatus() !== self::HTTP_TOO_MANY_REQUESTS) { |
|
827 | 824 | return; |
828 | 825 | } |
829 | 826 | |
830 | 827 | $fallbackBlockDuration = $this->sparqlThrottlingFallbackDuration; |
831 | 828 | |
832 | - if ( $fallbackBlockDuration < 0 ) { |
|
833 | - throw new InvalidArgumentException( 'Fallback duration must be positive int but is: ' . |
|
834 | - $fallbackBlockDuration ); |
|
829 | + if ($fallbackBlockDuration < 0) { |
|
830 | + throw new InvalidArgumentException('Fallback duration must be positive int but is: '. |
|
831 | + $fallbackBlockDuration); |
|
835 | 832 | } |
836 | 833 | |
837 | - $this->dataFactory->increment( 'wikibase.quality.constraints.sparql.throttling' ); |
|
838 | - $throttlingUntil = $this->getThrottling( $request ); |
|
839 | - if ( !( $throttlingUntil instanceof ConvertibleTimestamp ) ) { |
|
840 | - $this->loggingHelper->logSparqlHelperTooManyRequestsRetryAfterInvalid( $request ); |
|
834 | + $this->dataFactory->increment('wikibase.quality.constraints.sparql.throttling'); |
|
835 | + $throttlingUntil = $this->getThrottling($request); |
|
836 | + if (!($throttlingUntil instanceof ConvertibleTimestamp)) { |
|
837 | + $this->loggingHelper->logSparqlHelperTooManyRequestsRetryAfterInvalid($request); |
|
841 | 838 | $this->throttlingLock->lock( |
842 | 839 | self::EXPIRY_LOCK_ID, |
843 | - $this->getTimestampInFuture( new DateInterval( 'PT' . $fallbackBlockDuration . 'S' ) ) |
|
840 | + $this->getTimestampInFuture(new DateInterval('PT'.$fallbackBlockDuration.'S')) |
|
844 | 841 | ); |
845 | 842 | } else { |
846 | - $this->loggingHelper->logSparqlHelperTooManyRequestsRetryAfterPresent( $throttlingUntil, $request ); |
|
847 | - $this->throttlingLock->lock( self::EXPIRY_LOCK_ID, $throttlingUntil ); |
|
843 | + $this->loggingHelper->logSparqlHelperTooManyRequestsRetryAfterPresent($throttlingUntil, $request); |
|
844 | + $this->throttlingLock->lock(self::EXPIRY_LOCK_ID, $throttlingUntil); |
|
848 | 845 | } |
849 | 846 | throw new TooManySparqlRequestsException(); |
850 | 847 | } |