This project does not seem to handle request data directly as such no vulnerable execution paths were found.
include
, or for example
via PHP's auto-loading mechanism.
These results are based on our legacy PHP analysis, consider migrating to our new PHP analysis engine instead. Learn more
1 | <?php |
||
2 | |||
3 | namespace Wikibase\Repo\Dumpers; |
||
4 | |||
5 | use InvalidArgumentException; |
||
6 | use LogicException; |
||
7 | use Onoi\MessageReporter\MessageReporter; |
||
8 | use Onoi\MessageReporter\NullMessageReporter; |
||
9 | use Wikibase\DataModel\Entity\EntityId; |
||
10 | use Wikibase\DataModel\Services\Entity\EntityPrefetcher; |
||
11 | use Wikibase\DataModel\Services\EntityId\EntityIdPager; |
||
12 | use Wikibase\DataModel\Services\Lookup\EntityLookupException; |
||
13 | use Wikibase\Lib\Reporting\ExceptionHandler; |
||
14 | use Wikibase\Lib\Reporting\RethrowingExceptionHandler; |
||
15 | use Wikibase\Lib\Store\StorageException; |
||
16 | use Wikibase\Repo\Store\Sql\SqlEntityIdPager; |
||
17 | |||
18 | /** |
||
19 | * DumpGenerator generates a dump of a given set of entities, excluding |
||
20 | * redirects. |
||
21 | * |
||
22 | * @license GPL-2.0-or-later |
||
23 | * @author Daniel Kinzler |
||
24 | */ |
||
25 | abstract class DumpGenerator { |
||
26 | |||
27 | /** |
||
28 | * @var int The max number of entities to process in a single batch. |
||
29 | * Also controls the interval for progress reports. |
||
30 | */ |
||
31 | protected $batchSize = 100; |
||
32 | |||
33 | /** |
||
34 | * @var resource File handle for output |
||
35 | */ |
||
36 | protected $out; |
||
37 | |||
38 | /** |
||
39 | * @var int Total number of shards a request should be split into |
||
40 | */ |
||
41 | protected $shardingFactor = 1; |
||
42 | |||
43 | /** |
||
44 | * @var int Number of the requested shard |
||
45 | */ |
||
46 | protected $shard = 0; |
||
47 | |||
48 | /** |
||
49 | * @var MessageReporter |
||
50 | */ |
||
51 | protected $progressReporter; |
||
52 | |||
53 | /** |
||
54 | * @var ExceptionHandler |
||
55 | */ |
||
56 | protected $exceptionHandler; |
||
57 | |||
58 | /** |
||
59 | * @var EntityPrefetcher |
||
60 | */ |
||
61 | protected $entityPrefetcher; |
||
62 | |||
63 | /** |
||
64 | * @var int[] String to int map of types to include. |
||
65 | */ |
||
66 | protected $entityTypes; |
||
67 | |||
68 | /** |
||
69 | * Entity count limit - dump will generate this many |
||
70 | * |
||
71 | * @var int |
||
72 | */ |
||
73 | protected $limit = 0; |
||
74 | |||
75 | /** |
||
76 | * @param resource $out |
||
77 | * @param EntityPrefetcher $entityPrefetcher |
||
78 | * |
||
79 | * @throws InvalidArgumentException |
||
80 | */ |
||
81 | public function __construct( $out, EntityPrefetcher $entityPrefetcher ) { |
||
82 | if ( !is_resource( $out ) ) { |
||
83 | throw new InvalidArgumentException( '$out must be a file handle!' ); |
||
84 | } |
||
85 | |||
86 | $this->out = $out; |
||
87 | |||
88 | $this->entityPrefetcher = $entityPrefetcher; |
||
89 | $this->progressReporter = new NullMessageReporter(); |
||
90 | $this->exceptionHandler = new RethrowingExceptionHandler(); |
||
91 | } |
||
92 | |||
93 | /** |
||
94 | * Set maximum number of entities produced |
||
95 | * |
||
96 | * @param int $limit |
||
97 | */ |
||
98 | public function setLimit( $limit ) { |
||
99 | $this->limit = (int)$limit; |
||
100 | } |
||
101 | |||
102 | /** |
||
103 | * Sets the batch size for processing. The batch size is used as the limit |
||
104 | * when listing IDs via the EntityIdPager::getNextBatchOfIds() method, and |
||
105 | * also controls the interval of progress reports. |
||
106 | * |
||
107 | * @param int $batchSize |
||
108 | * |
||
109 | * @throws InvalidArgumentException |
||
110 | */ |
||
111 | public function setBatchSize( $batchSize ) { |
||
112 | if ( !is_int( $batchSize ) || $batchSize < 1 ) { |
||
113 | throw new InvalidArgumentException( '$batchSize must be an integer >= 1' ); |
||
114 | } |
||
115 | |||
116 | $this->batchSize = $batchSize; |
||
117 | } |
||
118 | |||
119 | public function setProgressReporter( MessageReporter $progressReporter ) { |
||
120 | $this->progressReporter = $progressReporter; |
||
121 | } |
||
122 | |||
123 | public function setExceptionHandler( ExceptionHandler $exceptionHandler ) { |
||
124 | $this->exceptionHandler = $exceptionHandler; |
||
125 | } |
||
126 | |||
127 | /** |
||
128 | * Set the sharding factor and desired shard. |
||
129 | * For instance, to generate four dumps in parallel, use setShardingFilter( 4, 0 ) |
||
130 | * for the first dump, setShardingFilter( 4, 1 ) for the second dump, etc. |
||
131 | * |
||
132 | * @param int $shardingFactor |
||
133 | * @param int $shard |
||
134 | * |
||
135 | * @throws InvalidArgumentException |
||
136 | */ |
||
137 | public function setShardingFilter( $shardingFactor, $shard ) { |
||
138 | if ( !is_int( $shardingFactor ) || $shardingFactor < 1 ) { |
||
139 | throw new InvalidArgumentException( '$shardingFactor must be a positive integer.' ); |
||
140 | } |
||
141 | |||
142 | if ( !is_int( $shard ) || $shard < 0 ) { |
||
143 | throw new InvalidArgumentException( '$shard must be a non-negative integer.' ); |
||
144 | } |
||
145 | |||
146 | if ( $shard >= $shardingFactor ) { |
||
147 | throw new InvalidArgumentException( '$shard must be smaller than $shardingFactor.' ); |
||
148 | } |
||
149 | |||
150 | $this->shardingFactor = $shardingFactor; |
||
151 | $this->shard = $shard; |
||
152 | } |
||
153 | |||
154 | /** |
||
155 | * Set the entity types to be included in the output. |
||
156 | * |
||
157 | * @param string[]|null $types The desired types (use null for any type). |
||
158 | */ |
||
159 | public function setEntityTypesFilter( $types ) { |
||
160 | if ( is_array( $types ) ) { |
||
161 | $types = array_flip( $types ); |
||
162 | } |
||
163 | $this->entityTypes = $types; |
||
164 | } |
||
165 | |||
166 | private function idMatchesFilters( EntityId $entityId ) { |
||
167 | return $this->idMatchesShard( $entityId ) && $this->idMatchesType( $entityId ); |
||
168 | } |
||
169 | |||
170 | private function idMatchesShard( EntityId $entityId ) { |
||
171 | // Shorten out |
||
172 | if ( $this->shardingFactor === 1 ) { |
||
173 | return true; |
||
174 | } |
||
175 | |||
176 | $hash = sha1( $entityId->getSerialization() ); |
||
177 | $shard = (int)hexdec( substr( $hash, 0, 8 ) ); // 4 bytes of the hash |
||
178 | $shard = abs( $shard ); // avoid negative numbers on 32 bit systems |
||
179 | $shard %= $this->shardingFactor; // modulo number of shards |
||
180 | |||
181 | return $shard === $this->shard; |
||
182 | } |
||
183 | |||
184 | private function idMatchesType( EntityId $entityId ) { |
||
185 | return $this->entityTypes === null || ( array_key_exists( $entityId->getEntityType(), $this->entityTypes ) ); |
||
186 | } |
||
187 | |||
188 | /** |
||
189 | * Writers the given string to the output provided to the constructor. |
||
190 | * |
||
191 | * @param string $data |
||
192 | */ |
||
193 | protected function writeToDump( $data ) { |
||
194 | //TODO: use output stream object |
||
195 | fwrite( $this->out, $data ); |
||
196 | } |
||
197 | |||
198 | /** |
||
199 | * Do something before dumping data |
||
200 | */ |
||
201 | protected function preDump() { |
||
202 | // Nothing by default |
||
203 | } |
||
204 | |||
205 | /** |
||
206 | * Do something after dumping data |
||
207 | */ |
||
208 | protected function postDump() { |
||
209 | // Nothing by default |
||
210 | } |
||
211 | |||
212 | /** |
||
213 | * Do something before dumping a batch of entities |
||
214 | * @param EntityId[] $entities |
||
215 | */ |
||
216 | protected function preBatchDump( $entities ) { |
||
217 | $this->entityPrefetcher->prefetch( $entities ); |
||
218 | } |
||
219 | |||
220 | /** |
||
221 | * Do something before dumping entity |
||
222 | * |
||
223 | * @param int $dumpCount |
||
224 | */ |
||
225 | protected function preEntityDump( $dumpCount ) { |
||
226 | // Nothing by default |
||
227 | } |
||
228 | |||
229 | /** |
||
230 | * Do something after dumping entity |
||
231 | * |
||
232 | * @param int $dumpCount |
||
233 | */ |
||
234 | protected function postEntityDump( $dumpCount ) { |
||
0 ignored issues
–
show
|
|||
235 | // Nothing by default |
||
236 | } |
||
237 | |||
238 | /** |
||
239 | * Generates a dump, writing to the file handle provided to the constructor. |
||
240 | * |
||
241 | * @param EntityIdPager $idPager |
||
242 | */ |
||
243 | public function generateDump( EntityIdPager $idPager ) { |
||
244 | $dumpCount = 0; |
||
245 | |||
246 | $this->preDump(); |
||
247 | |||
248 | // Iterate over batches of IDs, maintaining the current position of the pager in the $position variable. |
||
249 | while ( true ) { |
||
250 | if ( $this->limit && ( $dumpCount + $this->batchSize ) > $this->limit ) { |
||
251 | // Try not to overrun $limit in order to make sure pager's position can be used for continuing. |
||
252 | $limit = $this->limit - $dumpCount; |
||
253 | } else { |
||
254 | $limit = $this->batchSize; |
||
255 | } |
||
256 | |||
257 | $ids = $idPager->fetchIds( $limit ); |
||
258 | if ( !$ids ) { |
||
259 | break; |
||
260 | } |
||
261 | |||
262 | $this->dumpEntities( $ids, $dumpCount ); |
||
263 | |||
264 | $this->progressReporter->reportMessage( 'Processed ' . $dumpCount . ' entities.' ); |
||
265 | |||
266 | if ( $this->limit && $dumpCount >= $this->limit ) { |
||
267 | $this->progressReporter->reportMessage( 'Reached entity dump limit of ' . $this->limit . '.' ); |
||
268 | |||
269 | if ( $idPager instanceof SqlEntityIdPager ) { |
||
270 | // This message is possibly being parsed for continuation purposes, thus avoid changing it. |
||
271 | $this->progressReporter->reportMessage( 'Last SqlEntityIdPager position: ' . $idPager->getPosition() . '.' ); |
||
272 | } |
||
273 | |||
274 | break; |
||
275 | } |
||
276 | } |
||
277 | |||
278 | $this->postDump(); |
||
279 | } |
||
280 | |||
281 | /** |
||
282 | * Dump list of entities |
||
283 | * |
||
284 | * @param EntityId[] $entityIds |
||
285 | * @param int &$dumpCount The number of entities already dumped (will be updated). |
||
286 | */ |
||
287 | private function dumpEntities( array $entityIds, &$dumpCount ) { |
||
288 | $toLoad = []; |
||
289 | foreach ( $entityIds as $entityId ) { |
||
290 | if ( $this->idMatchesFilters( $entityId ) ) { |
||
291 | $toLoad[] = $entityId; |
||
292 | } |
||
293 | } |
||
294 | |||
295 | $this->preBatchDump( $toLoad ); |
||
296 | |||
297 | foreach ( $toLoad as $entityId ) { |
||
298 | try { |
||
299 | $data = $this->generateDumpForEntityId( $entityId ); |
||
300 | if ( !$data ) { |
||
0 ignored issues
–
show
The expression
$data of type string|null is loosely compared to false ; this is ambiguous if the string can be empty. You might want to explicitly use === null instead.
In PHP, under loose comparison (like For '' == false // true
'' == null // true
'ab' == false // false
'ab' == null // false
// It is often better to use strict comparison
'' === false // false
'' === null // false
Loading history...
|
|||
301 | continue; |
||
302 | } |
||
303 | |||
304 | $this->preEntityDump( $dumpCount ); |
||
305 | $this->writeToDump( $data ); |
||
306 | $this->postEntityDump( $dumpCount ); |
||
307 | |||
308 | $dumpCount++; |
||
309 | if ( $this->limit && $dumpCount >= $this->limit ) { |
||
310 | break; |
||
311 | } |
||
312 | } catch ( EntityLookupException $ex ) { |
||
313 | $this->exceptionHandler->handleException( $ex, 'failed-to-dump', 'Failed to dump ' . $entityId ); |
||
314 | } catch ( StorageException $ex ) { |
||
315 | $this->exceptionHandler->handleException( $ex, 'failed-to-dump', 'Failed to dump ' . $entityId ); |
||
316 | } catch ( LogicException $ex ) { |
||
317 | $this->exceptionHandler->handleException( $ex, 'failed-to-dump', 'Failed to dump ' . $entityId ); |
||
318 | } |
||
319 | } |
||
320 | } |
||
321 | |||
322 | /** |
||
323 | * Produce dump data for specific entity |
||
324 | * |
||
325 | * @param EntityId $entityId |
||
326 | * |
||
327 | * @throws EntityLookupException |
||
328 | * @throws StorageException |
||
329 | * @return string|null |
||
330 | */ |
||
331 | abstract protected function generateDumpForEntityId( EntityId $entityId ); |
||
332 | |||
333 | } |
||
334 |
This check looks from parameters that have been defined for a function or method, but which are not used in the method body.