diff options
author | Kevin Decherf <kevin@kdecherf.com> | 2019-08-11 23:55:52 +0200 |
---|---|---|
committer | Kevin Decherf <kevin@kdecherf.com> | 2020-04-25 15:59:23 +0200 |
commit | b22eb276232b5c15a6fbadc9dd10144e709faec3 (patch) | |
tree | 7c5b96a42f5b7d926c90b74b1bd949889dce5f70 | |
parent | 2495b197614d82b99eed6bbec4562078f4429ad7 (diff) | |
download | wallabag-b22eb276232b5c15a6fbadc9dd10144e709faec3.tar.gz wallabag-b22eb276232b5c15a6fbadc9dd10144e709faec3.tar.zst wallabag-b22eb276232b5c15a6fbadc9dd10144e709faec3.zip |
ContentProxy: replace ignoreUrl with new RuleBasedIgnoreOriginProcessor
Signed-off-by: Kevin Decherf <kevin@kdecherf.com>
-rw-r--r-- | src/Wallabag/CoreBundle/Helper/ContentProxy.php | 41 | ||||
-rw-r--r-- | tests/Wallabag/CoreBundle/Helper/ContentProxyTest.php | 127 |
2 files changed, 108 insertions, 60 deletions
diff --git a/src/Wallabag/CoreBundle/Helper/ContentProxy.php b/src/Wallabag/CoreBundle/Helper/ContentProxy.php index 9c6fa8db..7e93249d 100644 --- a/src/Wallabag/CoreBundle/Helper/ContentProxy.php +++ b/src/Wallabag/CoreBundle/Helper/ContentProxy.php | |||
@@ -19,6 +19,7 @@ class ContentProxy | |||
19 | { | 19 | { |
20 | protected $graby; | 20 | protected $graby; |
21 | protected $tagger; | 21 | protected $tagger; |
22 | protected $ignoreOriginProcessor; | ||
22 | protected $validator; | 23 | protected $validator; |
23 | protected $logger; | 24 | protected $logger; |
24 | protected $mimeGuesser; | 25 | protected $mimeGuesser; |
@@ -26,10 +27,11 @@ class ContentProxy | |||
26 | protected $eventDispatcher; | 27 | protected $eventDispatcher; |
27 | protected $storeArticleHeaders; | 28 | protected $storeArticleHeaders; |
28 | 29 | ||
29 | public function __construct(Graby $graby, RuleBasedTagger $tagger, ValidatorInterface $validator, LoggerInterface $logger, $fetchingErrorMessage, $storeArticleHeaders = false) | 30 | public function __construct(Graby $graby, RuleBasedTagger $tagger, RuleBasedIgnoreOriginProcessor $ignoreOriginProcessor, ValidatorInterface $validator, LoggerInterface $logger, $fetchingErrorMessage, $storeArticleHeaders = false) |
30 | { | 31 | { |
31 | $this->graby = $graby; | 32 | $this->graby = $graby; |
32 | $this->tagger = $tagger; | 33 | $this->tagger = $tagger; |
34 | $this->ignoreOriginProcessor = $ignoreOriginProcessor; | ||
33 | $this->validator = $validator; | 35 | $this->validator = $validator; |
34 | $this->logger = $logger; | 36 | $this->logger = $logger; |
35 | $this->mimeGuesser = new MimeTypeExtensionGuesser(); | 37 | $this->mimeGuesser = new MimeTypeExtensionGuesser(); |
@@ -356,7 +358,7 @@ class ContentProxy | |||
356 | $diff_keys = array_keys($diff); | 358 | $diff_keys = array_keys($diff); |
357 | sort($diff_keys); | 359 | sort($diff_keys); |
358 | 360 | ||
359 | if ($this->ignoreUrl($entry->getUrl())) { | 361 | if ($this->ignoreOriginProcessor->process($entry)) { |
360 | $entry->setUrl($url); | 362 | $entry->setUrl($url); |
361 | 363 | ||
362 | return false; | 364 | return false; |
@@ -396,41 +398,6 @@ class ContentProxy | |||
396 | } | 398 | } |
397 | 399 | ||
398 | /** | 400 | /** |
399 | * Check entry url against an ignore list to replace with content url. | ||
400 | * | ||
401 | * XXX: move the ignore list in the database to let users handle it | ||
402 | * | ||
403 | * @param string $url url to test | ||
404 | * | ||
405 | * @return bool true if url matches ignore list otherwise false | ||
406 | */ | ||
407 | private function ignoreUrl($url) | ||
408 | { | ||
409 | $ignored_hosts = ['feedproxy.google.com', 'feeds.reuters.com']; | ||
410 | $ignored_patterns = ['https?://www\.lemonde\.fr/tiny.*']; | ||
411 | |||
412 | $parsed_url = parse_url($url); | ||
413 | |||
414 | $filtered = array_filter($ignored_hosts, function ($var) use ($parsed_url) { | ||
415 | return $var === $parsed_url['host']; | ||
416 | }); | ||
417 | |||
418 | if ([] !== $filtered) { | ||
419 | return true; | ||
420 | } | ||
421 | |||
422 | $filtered = array_filter($ignored_patterns, function ($var) use ($url) { | ||
423 | return preg_match("`$var`i", $url); | ||
424 | }); | ||
425 | |||
426 | if ([] !== $filtered) { | ||
427 | return true; | ||
428 | } | ||
429 | |||
430 | return false; | ||
431 | } | ||
432 | |||
433 | /** | ||
434 | * Validate that the given content has at least a title, an html and a url. | 401 | * Validate that the given content has at least a title, an html and a url. |
435 | * | 402 | * |
436 | * @return bool true if valid otherwise false | 403 | * @return bool true if valid otherwise false |
diff --git a/tests/Wallabag/CoreBundle/Helper/ContentProxyTest.php b/tests/Wallabag/CoreBundle/Helper/ContentProxyTest.php index 9ce72c79..a65ac17c 100644 --- a/tests/Wallabag/CoreBundle/Helper/ContentProxyTest.php +++ b/tests/Wallabag/CoreBundle/Helper/ContentProxyTest.php | |||
@@ -12,6 +12,7 @@ use Symfony\Component\Validator\ConstraintViolationList; | |||
12 | use Symfony\Component\Validator\Validator\RecursiveValidator; | 12 | use Symfony\Component\Validator\Validator\RecursiveValidator; |
13 | use Wallabag\CoreBundle\Entity\Entry; | 13 | use Wallabag\CoreBundle\Entity\Entry; |
14 | use Wallabag\CoreBundle\Helper\ContentProxy; | 14 | use Wallabag\CoreBundle\Helper\ContentProxy; |
15 | use Wallabag\CoreBundle\Helper\RuleBasedIgnoreOriginProcessor; | ||
15 | use Wallabag\CoreBundle\Helper\RuleBasedTagger; | 16 | use Wallabag\CoreBundle\Helper\RuleBasedTagger; |
16 | use Wallabag\UserBundle\Entity\User; | 17 | use Wallabag\UserBundle\Entity\User; |
17 | 18 | ||
@@ -25,6 +26,8 @@ class ContentProxyTest extends TestCase | |||
25 | $tagger->expects($this->once()) | 26 | $tagger->expects($this->once()) |
26 | ->method('tag'); | 27 | ->method('tag'); |
27 | 28 | ||
29 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
30 | |||
28 | $graby = $this->getMockBuilder('Graby\Graby') | 31 | $graby = $this->getMockBuilder('Graby\Graby') |
29 | ->setMethods(['fetchContent']) | 32 | ->setMethods(['fetchContent']) |
30 | ->disableOriginalConstructor() | 33 | ->disableOriginalConstructor() |
@@ -42,7 +45,7 @@ class ContentProxyTest extends TestCase | |||
42 | 'language' => '', | 45 | 'language' => '', |
43 | ]); | 46 | ]); |
44 | 47 | ||
45 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 48 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
46 | $entry = new Entry(new User()); | 49 | $entry = new Entry(new User()); |
47 | $proxy->updateEntry($entry, 'http://user@:80'); | 50 | $proxy->updateEntry($entry, 'http://user@:80'); |
48 | 51 | ||
@@ -62,6 +65,8 @@ class ContentProxyTest extends TestCase | |||
62 | $tagger->expects($this->once()) | 65 | $tagger->expects($this->once()) |
63 | ->method('tag'); | 66 | ->method('tag'); |
64 | 67 | ||
68 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
69 | |||
65 | $graby = $this->getMockBuilder('Graby\Graby') | 70 | $graby = $this->getMockBuilder('Graby\Graby') |
66 | ->setMethods(['fetchContent']) | 71 | ->setMethods(['fetchContent']) |
67 | ->disableOriginalConstructor() | 72 | ->disableOriginalConstructor() |
@@ -79,7 +84,7 @@ class ContentProxyTest extends TestCase | |||
79 | 'language' => '', | 84 | 'language' => '', |
80 | ]); | 85 | ]); |
81 | 86 | ||
82 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 87 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
83 | $entry = new Entry(new User()); | 88 | $entry = new Entry(new User()); |
84 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 89 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
85 | 90 | ||
@@ -99,6 +104,8 @@ class ContentProxyTest extends TestCase | |||
99 | $tagger->expects($this->once()) | 104 | $tagger->expects($this->once()) |
100 | ->method('tag'); | 105 | ->method('tag'); |
101 | 106 | ||
107 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
108 | |||
102 | $graby = $this->getMockBuilder('Graby\Graby') | 109 | $graby = $this->getMockBuilder('Graby\Graby') |
103 | ->setMethods(['fetchContent']) | 110 | ->setMethods(['fetchContent']) |
104 | ->disableOriginalConstructor() | 111 | ->disableOriginalConstructor() |
@@ -118,7 +125,7 @@ class ContentProxyTest extends TestCase | |||
118 | 'description' => 'desc', | 125 | 'description' => 'desc', |
119 | ]); | 126 | ]); |
120 | 127 | ||
121 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 128 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
122 | $entry = new Entry(new User()); | 129 | $entry = new Entry(new User()); |
123 | $proxy->updateEntry($entry, 'http://domain.io'); | 130 | $proxy->updateEntry($entry, 'http://domain.io'); |
124 | 131 | ||
@@ -139,6 +146,10 @@ class ContentProxyTest extends TestCase | |||
139 | $tagger->expects($this->once()) | 146 | $tagger->expects($this->once()) |
140 | ->method('tag'); | 147 | ->method('tag'); |
141 | 148 | ||
149 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
150 | $ruleBasedIgnoreOriginProcessor->expects($this->once()) | ||
151 | ->method('process'); | ||
152 | |||
142 | $graby = $this->getMockBuilder('Graby\Graby') | 153 | $graby = $this->getMockBuilder('Graby\Graby') |
143 | ->setMethods(['fetchContent']) | 154 | ->setMethods(['fetchContent']) |
144 | ->disableOriginalConstructor() | 155 | ->disableOriginalConstructor() |
@@ -159,7 +170,7 @@ class ContentProxyTest extends TestCase | |||
159 | ], | 170 | ], |
160 | ]); | 171 | ]); |
161 | 172 | ||
162 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 173 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
163 | $entry = new Entry(new User()); | 174 | $entry = new Entry(new User()); |
164 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 175 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
165 | 176 | ||
@@ -180,6 +191,10 @@ class ContentProxyTest extends TestCase | |||
180 | $tagger->expects($this->once()) | 191 | $tagger->expects($this->once()) |
181 | ->method('tag'); | 192 | ->method('tag'); |
182 | 193 | ||
194 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
195 | $ruleBasedIgnoreOriginProcessor->expects($this->once()) | ||
196 | ->method('process'); | ||
197 | |||
183 | $graby = $this->getMockBuilder('Graby\Graby') | 198 | $graby = $this->getMockBuilder('Graby\Graby') |
184 | ->setMethods(['fetchContent']) | 199 | ->setMethods(['fetchContent']) |
185 | ->disableOriginalConstructor() | 200 | ->disableOriginalConstructor() |
@@ -200,7 +215,7 @@ class ContentProxyTest extends TestCase | |||
200 | ], | 215 | ], |
201 | ]); | 216 | ]); |
202 | 217 | ||
203 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 218 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
204 | $entry = new Entry(new User()); | 219 | $entry = new Entry(new User()); |
205 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 220 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
206 | 221 | ||
@@ -221,6 +236,10 @@ class ContentProxyTest extends TestCase | |||
221 | $tagger->expects($this->once()) | 236 | $tagger->expects($this->once()) |
222 | ->method('tag'); | 237 | ->method('tag'); |
223 | 238 | ||
239 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
240 | $ruleBasedIgnoreOriginProcessor->expects($this->once()) | ||
241 | ->method('process'); | ||
242 | |||
224 | $graby = $this->getMockBuilder('Graby\Graby') | 243 | $graby = $this->getMockBuilder('Graby\Graby') |
225 | ->setMethods(['fetchContent']) | 244 | ->setMethods(['fetchContent']) |
226 | ->disableOriginalConstructor() | 245 | ->disableOriginalConstructor() |
@@ -240,7 +259,7 @@ class ContentProxyTest extends TestCase | |||
240 | 'image' => null, | 259 | 'image' => null, |
241 | ]); | 260 | ]); |
242 | 261 | ||
243 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 262 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
244 | $entry = new Entry(new User()); | 263 | $entry = new Entry(new User()); |
245 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 264 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
246 | 265 | ||
@@ -261,6 +280,10 @@ class ContentProxyTest extends TestCase | |||
261 | $tagger->expects($this->once()) | 280 | $tagger->expects($this->once()) |
262 | ->method('tag'); | 281 | ->method('tag'); |
263 | 282 | ||
283 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
284 | $ruleBasedIgnoreOriginProcessor->expects($this->once()) | ||
285 | ->method('process'); | ||
286 | |||
264 | $graby = $this->getMockBuilder('Graby\Graby') | 287 | $graby = $this->getMockBuilder('Graby\Graby') |
265 | ->setMethods(['fetchContent']) | 288 | ->setMethods(['fetchContent']) |
266 | ->disableOriginalConstructor() | 289 | ->disableOriginalConstructor() |
@@ -280,7 +303,7 @@ class ContentProxyTest extends TestCase | |||
280 | 'image' => 'http://3.3.3.3/cover.jpg', | 303 | 'image' => 'http://3.3.3.3/cover.jpg', |
281 | ]); | 304 | ]); |
282 | 305 | ||
283 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 306 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
284 | $entry = new Entry(new User()); | 307 | $entry = new Entry(new User()); |
285 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 308 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
286 | 309 | ||
@@ -301,6 +324,10 @@ class ContentProxyTest extends TestCase | |||
301 | $tagger->expects($this->once()) | 324 | $tagger->expects($this->once()) |
302 | ->method('tag'); | 325 | ->method('tag'); |
303 | 326 | ||
327 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
328 | $ruleBasedIgnoreOriginProcessor->expects($this->once()) | ||
329 | ->method('process'); | ||
330 | |||
304 | $validator = $this->getValidator(false); | 331 | $validator = $this->getValidator(false); |
305 | $validator->expects($this->once()) | 332 | $validator->expects($this->once()) |
306 | ->method('validate') | 333 | ->method('validate') |
@@ -324,7 +351,7 @@ class ContentProxyTest extends TestCase | |||
324 | ], | 351 | ], |
325 | ]); | 352 | ]); |
326 | 353 | ||
327 | $proxy = new ContentProxy($graby, $tagger, $validator, $this->getLogger(), $this->fetchingErrorMessage); | 354 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $validator, $this->getLogger(), $this->fetchingErrorMessage); |
328 | $entry = new Entry(new User()); | 355 | $entry = new Entry(new User()); |
329 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 356 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
330 | 357 | ||
@@ -344,6 +371,10 @@ class ContentProxyTest extends TestCase | |||
344 | $tagger->expects($this->once()) | 371 | $tagger->expects($this->once()) |
345 | ->method('tag'); | 372 | ->method('tag'); |
346 | 373 | ||
374 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
375 | $ruleBasedIgnoreOriginProcessor->expects($this->once()) | ||
376 | ->method('process'); | ||
377 | |||
347 | $validator = $this->getValidator(false); | 378 | $validator = $this->getValidator(false); |
348 | $validator->expects($this->exactly(2)) | 379 | $validator->expects($this->exactly(2)) |
349 | ->method('validate') | 380 | ->method('validate') |
@@ -372,7 +403,7 @@ class ContentProxyTest extends TestCase | |||
372 | 'image' => 'https://', | 403 | 'image' => 'https://', |
373 | ]); | 404 | ]); |
374 | 405 | ||
375 | $proxy = new ContentProxy($graby, $tagger, $validator, $this->getLogger(), $this->fetchingErrorMessage); | 406 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $validator, $this->getLogger(), $this->fetchingErrorMessage); |
376 | $entry = new Entry(new User()); | 407 | $entry = new Entry(new User()); |
377 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 408 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
378 | 409 | ||
@@ -393,7 +424,11 @@ class ContentProxyTest extends TestCase | |||
393 | $tagger->expects($this->once()) | 424 | $tagger->expects($this->once()) |
394 | ->method('tag'); | 425 | ->method('tag'); |
395 | 426 | ||
396 | $proxy = new ContentProxy((new Graby()), $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage, true); | 427 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); |
428 | $ruleBasedIgnoreOriginProcessor->expects($this->once()) | ||
429 | ->method('process'); | ||
430 | |||
431 | $proxy = new ContentProxy((new Graby()), $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage, true); | ||
397 | $entry = new Entry(new User()); | 432 | $entry = new Entry(new User()); |
398 | $proxy->updateEntry( | 433 | $proxy->updateEntry( |
399 | $entry, | 434 | $entry, |
@@ -433,10 +468,12 @@ class ContentProxyTest extends TestCase | |||
433 | $tagger->expects($this->once()) | 468 | $tagger->expects($this->once()) |
434 | ->method('tag'); | 469 | ->method('tag'); |
435 | 470 | ||
471 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
472 | |||
436 | $logHandler = new TestHandler(); | 473 | $logHandler = new TestHandler(); |
437 | $logger = new Logger('test', [$logHandler]); | 474 | $logger = new Logger('test', [$logHandler]); |
438 | 475 | ||
439 | $proxy = new ContentProxy((new Graby()), $tagger, $this->getValidator(), $logger, $this->fetchingErrorMessage); | 476 | $proxy = new ContentProxy((new Graby()), $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $logger, $this->fetchingErrorMessage); |
440 | $entry = new Entry(new User()); | 477 | $entry = new Entry(new User()); |
441 | $proxy->updateEntry( | 478 | $proxy->updateEntry( |
442 | $entry, | 479 | $entry, |
@@ -469,11 +506,13 @@ class ContentProxyTest extends TestCase | |||
469 | $tagger->expects($this->once()) | 506 | $tagger->expects($this->once()) |
470 | ->method('tag'); | 507 | ->method('tag'); |
471 | 508 | ||
509 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
510 | |||
472 | $logger = new Logger('foo'); | 511 | $logger = new Logger('foo'); |
473 | $handler = new TestHandler(); | 512 | $handler = new TestHandler(); |
474 | $logger->pushHandler($handler); | 513 | $logger->pushHandler($handler); |
475 | 514 | ||
476 | $proxy = new ContentProxy((new Graby()), $tagger, $this->getValidator(), $logger, $this->fetchingErrorMessage); | 515 | $proxy = new ContentProxy((new Graby()), $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $logger, $this->fetchingErrorMessage); |
477 | $entry = new Entry(new User()); | 516 | $entry = new Entry(new User()); |
478 | $proxy->updateEntry( | 517 | $proxy->updateEntry( |
479 | $entry, | 518 | $entry, |
@@ -512,7 +551,9 @@ class ContentProxyTest extends TestCase | |||
512 | ->method('tag') | 551 | ->method('tag') |
513 | ->will($this->throwException(new \Exception())); | 552 | ->will($this->throwException(new \Exception())); |
514 | 553 | ||
515 | $proxy = new ContentProxy((new Graby()), $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 554 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); |
555 | |||
556 | $proxy = new ContentProxy((new Graby()), $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | ||
516 | $entry = new Entry(new User()); | 557 | $entry = new Entry(new User()); |
517 | $proxy->updateEntry( | 558 | $proxy->updateEntry( |
518 | $entry, | 559 | $entry, |
@@ -554,7 +595,9 @@ class ContentProxyTest extends TestCase | |||
554 | $tagger->expects($this->once()) | 595 | $tagger->expects($this->once()) |
555 | ->method('tag'); | 596 | ->method('tag'); |
556 | 597 | ||
557 | $proxy = new ContentProxy((new Graby()), $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 598 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); |
599 | |||
600 | $proxy = new ContentProxy((new Graby()), $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | ||
558 | $entry = new Entry(new User()); | 601 | $entry = new Entry(new User()); |
559 | $proxy->updateEntry( | 602 | $proxy->updateEntry( |
560 | $entry, | 603 | $entry, |
@@ -590,6 +633,8 @@ class ContentProxyTest extends TestCase | |||
590 | $tagger->expects($this->once()) | 633 | $tagger->expects($this->once()) |
591 | ->method('tag'); | 634 | ->method('tag'); |
592 | 635 | ||
636 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
637 | |||
593 | $graby = $this->getMockBuilder('Graby\Graby') | 638 | $graby = $this->getMockBuilder('Graby\Graby') |
594 | ->setMethods(['fetchContent']) | 639 | ->setMethods(['fetchContent']) |
595 | ->disableOriginalConstructor() | 640 | ->disableOriginalConstructor() |
@@ -607,7 +652,7 @@ class ContentProxyTest extends TestCase | |||
607 | ], | 652 | ], |
608 | ]); | 653 | ]); |
609 | 654 | ||
610 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 655 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
611 | $entry = new Entry(new User()); | 656 | $entry = new Entry(new User()); |
612 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 657 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
613 | 658 | ||
@@ -631,6 +676,8 @@ class ContentProxyTest extends TestCase | |||
631 | $tagger->expects($this->once()) | 676 | $tagger->expects($this->once()) |
632 | ->method('tag'); | 677 | ->method('tag'); |
633 | 678 | ||
679 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
680 | |||
634 | $graby = $this->getMockBuilder('Graby\Graby') | 681 | $graby = $this->getMockBuilder('Graby\Graby') |
635 | ->setMethods(['fetchContent']) | 682 | ->setMethods(['fetchContent']) |
636 | ->disableOriginalConstructor() | 683 | ->disableOriginalConstructor() |
@@ -648,7 +695,7 @@ class ContentProxyTest extends TestCase | |||
648 | 'language' => '', | 695 | 'language' => '', |
649 | ]); | 696 | ]); |
650 | 697 | ||
651 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 698 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
652 | $entry = new Entry(new User()); | 699 | $entry = new Entry(new User()); |
653 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 700 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
654 | 701 | ||
@@ -668,6 +715,8 @@ class ContentProxyTest extends TestCase | |||
668 | $tagger->expects($this->once()) | 715 | $tagger->expects($this->once()) |
669 | ->method('tag'); | 716 | ->method('tag'); |
670 | 717 | ||
718 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
719 | |||
671 | $graby = $this->getMockBuilder('Graby\Graby') | 720 | $graby = $this->getMockBuilder('Graby\Graby') |
672 | ->setMethods(['fetchContent']) | 721 | ->setMethods(['fetchContent']) |
673 | ->disableOriginalConstructor() | 722 | ->disableOriginalConstructor() |
@@ -685,7 +734,7 @@ class ContentProxyTest extends TestCase | |||
685 | 'language' => '', | 734 | 'language' => '', |
686 | ]); | 735 | ]); |
687 | 736 | ||
688 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 737 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
689 | $entry = new Entry(new User()); | 738 | $entry = new Entry(new User()); |
690 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 739 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
691 | 740 | ||
@@ -704,6 +753,8 @@ class ContentProxyTest extends TestCase | |||
704 | $tagger->expects($this->once()) | 753 | $tagger->expects($this->once()) |
705 | ->method('tag'); | 754 | ->method('tag'); |
706 | 755 | ||
756 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
757 | |||
707 | $graby = $this->getMockBuilder('Graby\Graby') | 758 | $graby = $this->getMockBuilder('Graby\Graby') |
708 | ->setMethods(['fetchContent']) | 759 | ->setMethods(['fetchContent']) |
709 | ->disableOriginalConstructor() | 760 | ->disableOriginalConstructor() |
@@ -721,7 +772,7 @@ class ContentProxyTest extends TestCase | |||
721 | 'language' => '', | 772 | 'language' => '', |
722 | ]); | 773 | ]); |
723 | 774 | ||
724 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 775 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
725 | $entry = new Entry(new User()); | 776 | $entry = new Entry(new User()); |
726 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 777 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
727 | 778 | ||
@@ -740,6 +791,8 @@ class ContentProxyTest extends TestCase | |||
740 | $tagger->expects($this->once()) | 791 | $tagger->expects($this->once()) |
741 | ->method('tag'); | 792 | ->method('tag'); |
742 | 793 | ||
794 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
795 | |||
743 | $graby = $this->getMockBuilder('Graby\Graby') | 796 | $graby = $this->getMockBuilder('Graby\Graby') |
744 | ->setMethods(['fetchContent']) | 797 | ->setMethods(['fetchContent']) |
745 | ->disableOriginalConstructor() | 798 | ->disableOriginalConstructor() |
@@ -757,7 +810,7 @@ class ContentProxyTest extends TestCase | |||
757 | 'language' => '', | 810 | 'language' => '', |
758 | ]); | 811 | ]); |
759 | 812 | ||
760 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 813 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
761 | $entry = new Entry(new User()); | 814 | $entry = new Entry(new User()); |
762 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 815 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
763 | 816 | ||
@@ -776,6 +829,8 @@ class ContentProxyTest extends TestCase | |||
776 | $tagger->expects($this->once()) | 829 | $tagger->expects($this->once()) |
777 | ->method('tag'); | 830 | ->method('tag'); |
778 | 831 | ||
832 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
833 | |||
779 | $graby = $this->getMockBuilder('Graby\Graby') | 834 | $graby = $this->getMockBuilder('Graby\Graby') |
780 | ->setMethods(['fetchContent']) | 835 | ->setMethods(['fetchContent']) |
781 | ->disableOriginalConstructor() | 836 | ->disableOriginalConstructor() |
@@ -793,7 +848,7 @@ class ContentProxyTest extends TestCase | |||
793 | 'language' => '', | 848 | 'language' => '', |
794 | ]); | 849 | ]); |
795 | 850 | ||
796 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 851 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
797 | $entry = new Entry(new User()); | 852 | $entry = new Entry(new User()); |
798 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 853 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
799 | 854 | ||
@@ -813,6 +868,8 @@ class ContentProxyTest extends TestCase | |||
813 | $tagger->expects($this->once()) | 868 | $tagger->expects($this->once()) |
814 | ->method('tag'); | 869 | ->method('tag'); |
815 | 870 | ||
871 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); | ||
872 | |||
816 | $graby = $this->getMockBuilder('Graby\Graby') | 873 | $graby = $this->getMockBuilder('Graby\Graby') |
817 | ->setMethods(['fetchContent']) | 874 | ->setMethods(['fetchContent']) |
818 | ->disableOriginalConstructor() | 875 | ->disableOriginalConstructor() |
@@ -830,7 +887,7 @@ class ContentProxyTest extends TestCase | |||
830 | 'language' => '', | 887 | 'language' => '', |
831 | ]); | 888 | ]); |
832 | 889 | ||
833 | $proxy = new ContentProxy($graby, $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); | 890 | $proxy = new ContentProxy($graby, $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage); |
834 | $entry = new Entry(new User()); | 891 | $entry = new Entry(new User()); |
835 | $proxy->updateEntry($entry, 'http://0.0.0.0'); | 892 | $proxy->updateEntry($entry, 'http://0.0.0.0'); |
836 | 893 | ||
@@ -850,6 +907,7 @@ class ContentProxyTest extends TestCase | |||
850 | * $expected_entry_url | 907 | * $expected_entry_url |
851 | * $expected_origin_url | 908 | * $expected_origin_url |
852 | * $expected_domain | 909 | * $expected_domain |
910 | * $processor_result | ||
853 | */ | 911 | */ |
854 | public function dataForChangedUrl() | 912 | public function dataForChangedUrl() |
855 | { | 913 | { |
@@ -861,6 +919,7 @@ class ContentProxyTest extends TestCase | |||
861 | 'http://1.1.1.1', | 919 | 'http://1.1.1.1', |
862 | 'http://0.0.0.0', | 920 | 'http://0.0.0.0', |
863 | '1.1.1.1', | 921 | '1.1.1.1', |
922 | false, | ||
864 | ], | 923 | ], |
865 | 'origin already set' => [ | 924 | 'origin already set' => [ |
866 | 'http://0.0.0.0', | 925 | 'http://0.0.0.0', |
@@ -869,6 +928,7 @@ class ContentProxyTest extends TestCase | |||
869 | 'http://1.1.1.1', | 928 | 'http://1.1.1.1', |
870 | 'http://hello', | 929 | 'http://hello', |
871 | '1.1.1.1', | 930 | '1.1.1.1', |
931 | false, | ||
872 | ], | 932 | ], |
873 | 'trailing slash' => [ | 933 | 'trailing slash' => [ |
874 | 'https://example.com/hello-world', | 934 | 'https://example.com/hello-world', |
@@ -877,6 +937,7 @@ class ContentProxyTest extends TestCase | |||
877 | 'https://example.com/hello-world/', | 937 | 'https://example.com/hello-world/', |
878 | null, | 938 | null, |
879 | 'example.com', | 939 | 'example.com', |
940 | false, | ||
880 | ], | 941 | ], |
881 | 'query string in fetched content' => [ | 942 | 'query string in fetched content' => [ |
882 | 'https://example.org/hello', | 943 | 'https://example.org/hello', |
@@ -885,6 +946,7 @@ class ContentProxyTest extends TestCase | |||
885 | 'https://example.org/hello?world=1', | 946 | 'https://example.org/hello?world=1', |
886 | 'https://example.org/hello', | 947 | 'https://example.org/hello', |
887 | 'example.org', | 948 | 'example.org', |
949 | false, | ||
888 | ], | 950 | ], |
889 | 'fragment in fetched content' => [ | 951 | 'fragment in fetched content' => [ |
890 | 'https://example.org/hello', | 952 | 'https://example.org/hello', |
@@ -893,6 +955,7 @@ class ContentProxyTest extends TestCase | |||
893 | 'https://example.org/hello', | 955 | 'https://example.org/hello', |
894 | null, | 956 | null, |
895 | 'example.org', | 957 | 'example.org', |
958 | false, | ||
896 | ], | 959 | ], |
897 | 'fragment and query string in fetched content' => [ | 960 | 'fragment and query string in fetched content' => [ |
898 | 'https://example.org/hello', | 961 | 'https://example.org/hello', |
@@ -901,6 +964,7 @@ class ContentProxyTest extends TestCase | |||
901 | 'https://example.org/hello?foo#world', | 964 | 'https://example.org/hello?foo#world', |
902 | 'https://example.org/hello', | 965 | 'https://example.org/hello', |
903 | 'example.org', | 966 | 'example.org', |
967 | false, | ||
904 | ], | 968 | ], |
905 | 'different path and query string in fetch content' => [ | 969 | 'different path and query string in fetch content' => [ |
906 | 'https://example.org/hello', | 970 | 'https://example.org/hello', |
@@ -909,6 +973,7 @@ class ContentProxyTest extends TestCase | |||
909 | 'https://example.org/world?foo', | 973 | 'https://example.org/world?foo', |
910 | 'https://example.org/hello', | 974 | 'https://example.org/hello', |
911 | 'example.org', | 975 | 'example.org', |
976 | false, | ||
912 | ], | 977 | ], |
913 | 'feedproxy ignore list test' => [ | 978 | 'feedproxy ignore list test' => [ |
914 | 'http://feedproxy.google.com/~r/Wallabag/~3/helloworld', | 979 | 'http://feedproxy.google.com/~r/Wallabag/~3/helloworld', |
@@ -917,6 +982,7 @@ class ContentProxyTest extends TestCase | |||
917 | 'https://example.org/hello-wallabag', | 982 | 'https://example.org/hello-wallabag', |
918 | null, | 983 | null, |
919 | 'example.org', | 984 | 'example.org', |
985 | true, | ||
920 | ], | 986 | ], |
921 | 'feedproxy ignore list test with origin url already set' => [ | 987 | 'feedproxy ignore list test with origin url already set' => [ |
922 | 'http://feedproxy.google.com/~r/Wallabag/~3/helloworld', | 988 | 'http://feedproxy.google.com/~r/Wallabag/~3/helloworld', |
@@ -925,6 +991,7 @@ class ContentProxyTest extends TestCase | |||
925 | 'https://example.org/hello-wallabag', | 991 | 'https://example.org/hello-wallabag', |
926 | 'https://example.org/this-is-source', | 992 | 'https://example.org/this-is-source', |
927 | 'example.org', | 993 | 'example.org', |
994 | true, | ||
928 | ], | 995 | ], |
929 | 'lemonde ignore pattern test' => [ | 996 | 'lemonde ignore pattern test' => [ |
930 | 'http://www.lemonde.fr/tiny/url', | 997 | 'http://www.lemonde.fr/tiny/url', |
@@ -933,6 +1000,7 @@ class ContentProxyTest extends TestCase | |||
933 | 'http://example.com/hello-world', | 1000 | 'http://example.com/hello-world', |
934 | null, | 1001 | null, |
935 | 'example.com', | 1002 | 'example.com', |
1003 | true, | ||
936 | ], | 1004 | ], |
937 | ]; | 1005 | ]; |
938 | } | 1006 | } |
@@ -940,13 +1008,18 @@ class ContentProxyTest extends TestCase | |||
940 | /** | 1008 | /** |
941 | * @dataProvider dataForChangedUrl | 1009 | * @dataProvider dataForChangedUrl |
942 | */ | 1010 | */ |
943 | public function testWithChangedUrl($entry_url, $origin_url, $content_url, $expected_entry_url, $expected_origin_url, $expected_domain) | 1011 | public function testWithChangedUrl($entry_url, $origin_url, $content_url, $expected_entry_url, $expected_origin_url, $expected_domain, $processor_result) |
944 | { | 1012 | { |
945 | $tagger = $this->getTaggerMock(); | 1013 | $tagger = $this->getTaggerMock(); |
946 | $tagger->expects($this->once()) | 1014 | $tagger->expects($this->once()) |
947 | ->method('tag'); | 1015 | ->method('tag'); |
948 | 1016 | ||
949 | $proxy = new ContentProxy((new Graby()), $tagger, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage, true); | 1017 | $ruleBasedIgnoreOriginProcessor = $this->getRuleBasedIgnoreOriginProcessorMock(); |
1018 | $ruleBasedIgnoreOriginProcessor->expects($this->once()) | ||
1019 | ->method('process') | ||
1020 | ->willReturn($processor_result); | ||
1021 | |||
1022 | $proxy = new ContentProxy((new Graby()), $tagger, $ruleBasedIgnoreOriginProcessor, $this->getValidator(), $this->getLogger(), $this->fetchingErrorMessage, true); | ||
950 | $entry = new Entry(new User()); | 1023 | $entry = new Entry(new User()); |
951 | $entry->setOriginUrl($origin_url); | 1024 | $entry->setOriginUrl($origin_url); |
952 | $proxy->updateEntry( | 1025 | $proxy->updateEntry( |
@@ -1015,6 +1088,14 @@ class ContentProxyTest extends TestCase | |||
1015 | ->getMock(); | 1088 | ->getMock(); |
1016 | } | 1089 | } |
1017 | 1090 | ||
1091 | private function getRuleBasedIgnoreOriginProcessorMock() | ||
1092 | { | ||
1093 | return $this->getMockBuilder(RuleBasedIgnoreOriginProcessor::class) | ||
1094 | ->setMethods(['process']) | ||
1095 | ->disableOriginalConstructor() | ||
1096 | ->getMock(); | ||
1097 | } | ||
1098 | |||
1018 | private function getLogger() | 1099 | private function getLogger() |
1019 | { | 1100 | { |
1020 | return new NullLogger(); | 1101 | return new NullLogger(); |