Duplicate code is one of the most pungent code smells. A rule that is often used is to re-structure code once it is duplicated in three or more places.
Common duplication problems, and corresponding solutions are:
| 1 | <?php |
||
| 15 | class SpiderTest extends TestCase |
||
| 16 | { |
||
| 17 | /** |
||
| 18 | * @var Spider |
||
| 19 | */ |
||
| 20 | protected $spider; |
||
| 21 | |||
| 22 | /** |
||
| 23 | * @var StatsHandler |
||
| 24 | */ |
||
| 25 | protected $statsHandler; |
||
| 26 | |||
| 27 | /** |
||
| 28 | * @var PHPUnit_Framework_MockObject_MockObject |
||
| 29 | */ |
||
| 30 | protected $requestHandler; |
||
| 31 | |||
| 32 | /** @var FilterableUri */ |
||
| 33 | protected $linkA; |
||
| 34 | /** @var FilterableUri */ |
||
| 35 | protected $linkB; |
||
| 36 | /** @var FilterableUri */ |
||
| 37 | protected $linkC; |
||
| 38 | /** @var FilterableUri */ |
||
| 39 | protected $linkD; |
||
| 40 | /** @var FilterableUri */ |
||
| 41 | protected $linkE; |
||
| 42 | /** @var FilterableUri */ |
||
| 43 | protected $linkF; |
||
| 44 | /** @var FilterableUri */ |
||
| 45 | protected $linkG; |
||
| 46 | |||
| 47 | /** @var Response */ |
||
| 48 | protected $responseA; |
||
| 49 | /** @var Response */ |
||
| 50 | protected $responseB; |
||
| 51 | /** @var Response */ |
||
| 52 | protected $responseC; |
||
| 53 | /** @var Response */ |
||
| 54 | protected $responseD; |
||
| 55 | /** @var Response */ |
||
| 56 | protected $responseE; |
||
| 57 | /** @var Response */ |
||
| 58 | protected $responseF; |
||
| 59 | /** @var Response */ |
||
| 60 | protected $responseG; |
||
| 61 | |||
| 62 | /** @var string */ |
||
| 63 | protected $hrefA; |
||
| 64 | protected $hrefB; |
||
| 65 | protected $hrefC; |
||
| 66 | protected $hrefD; |
||
| 67 | protected $hrefE; |
||
| 68 | protected $hrefF; |
||
| 69 | protected $hrefG; |
||
| 70 | |||
| 71 | /** |
||
| 72 | * Sets up the fixture, for example, opens a network connection. |
||
| 73 | * This method is called before a test is executed. |
||
| 74 | */ |
||
| 75 | protected function setUp() |
||
| 135 | |||
| 136 | /** |
||
| 137 | * @return Resource |
||
| 138 | * @throws \ErrorException |
||
| 139 | */ |
||
| 140 | public function doTestRequest() |
||
| 163 | |||
| 164 | /** |
||
| 165 | * @covers VDB\Spider\Spider::crawl |
||
| 166 | * |
||
| 167 | * Behaviour as explained here: https://en.wikipedia.org/wiki/Depth-first_search#Example |
||
| 168 | */ |
||
| 169 | View Code Duplication | public function testCrawlDFSDefaultBehaviour() |
|
|
1 ignored issue
–
show
|
|||
| 170 | { |
||
| 171 | $this->spider->getQueueManager()->maxDepth = 10; |
||
| 172 | |||
| 173 | $this->spider->crawl(); |
||
| 174 | |||
| 175 | $expected = array( |
||
| 176 | $this->linkA, |
||
| 177 | $this->linkE, |
||
| 178 | $this->linkF, |
||
| 179 | $this->linkC, |
||
| 180 | $this->linkG, |
||
| 181 | $this->linkB, |
||
| 182 | $this->linkD |
||
| 183 | ); |
||
| 184 | |||
| 185 | $this->assertEquals($expected, $this->statsHandler->getPersisted()); |
||
| 186 | } |
||
| 187 | |||
| 188 | /** |
||
| 189 | * @covers VDB\Spider\Spider::crawl |
||
| 190 | * |
||
| 191 | */ |
||
| 192 | View Code Duplication | public function testCrawlBFSDefaultBehaviour() |
|
|
1 ignored issue
–
show
|
|||
| 193 | { |
||
| 194 | $this->spider->getQueueManager()->setTraversalAlgorithm(InMemoryQueueManager::ALGORITHM_BREADTH_FIRST); |
||
| 195 | $this->spider->getQueueManager()->maxDepth = 1000; |
||
| 196 | |||
| 197 | $this->spider->crawl(); |
||
| 198 | |||
| 199 | $expected = array( |
||
| 200 | $this->linkA, |
||
| 201 | $this->linkB, |
||
| 202 | $this->linkC, |
||
| 203 | $this->linkE, |
||
| 204 | $this->linkD, |
||
| 205 | $this->linkF, |
||
| 206 | $this->linkG |
||
| 207 | ); |
||
| 208 | |||
| 209 | $this->assertEquals($expected, $this->statsHandler->getPersisted()); |
||
| 210 | } |
||
| 211 | |||
| 212 | /** |
||
| 213 | * @covers VDB\Spider\Spider::crawl |
||
| 214 | * |
||
| 215 | * Behaviour as explained here: https://en.wikipedia.org/wiki/Depth-first_search#Example |
||
| 216 | */ |
||
| 217 | public function testCrawlDFSMaxDepthOne() |
||
| 232 | |||
| 233 | public function testCrawlBFSMaxDepthOne() |
||
| 249 | |||
| 250 | /** |
||
| 251 | * @covers VDB\Spider\Spider::crawl |
||
| 252 | */ |
||
| 253 | View Code Duplication | public function testCrawlDFSMaxQueueSize() |
|
|
1 ignored issue
–
show
|
|||
| 254 | { |
||
| 255 | $this->spider->getQueueManager()->maxDepth = 1000; |
||
| 256 | $this->spider->downloadLimit = 3; |
||
| 257 | |||
| 258 | $this->spider->crawl(); |
||
| 259 | |||
| 260 | $expected = array( |
||
| 261 | $this->linkA, |
||
| 262 | $this->linkE, |
||
| 263 | $this->linkF, |
||
| 264 | ); |
||
| 265 | |||
| 266 | $this->assertEquals($expected, $this->statsHandler->getPersisted()); |
||
| 267 | } |
||
| 268 | |||
| 269 | View Code Duplication | public function testCrawlBFSMaxQueueSize() |
|
|
1 ignored issue
–
show
|
|||
| 270 | { |
||
| 271 | $this->spider->getQueueManager()->setTraversalAlgorithm(InMemoryQueueManager::ALGORITHM_BREADTH_FIRST); |
||
| 272 | $this->spider->getQueueManager()->maxDepth = 1000; |
||
| 273 | $this->spider->downloadLimit = 3; |
||
| 274 | |||
| 275 | $this->spider->crawl(); |
||
| 276 | |||
| 277 | $expected = array( |
||
| 278 | $this->linkA, |
||
| 279 | $this->linkB, |
||
| 280 | $this->linkC, |
||
| 281 | ); |
||
| 282 | |||
| 283 | $this->assertEquals($expected, $this->statsHandler->getPersisted()); |
||
| 284 | } |
||
| 285 | |||
| 286 | /** |
||
| 287 | * @covers VDB\Spider\Spider::crawl |
||
| 288 | */ |
||
| 289 | public function testCrawlFailedRequest() |
||
| 305 | } |
||
| 306 |
In PHP it is possible to write to properties without declaring them. For example, the following is perfectly valid PHP code:
Generally, it is a good practice to explictly declare properties to avoid accidental typos and provide IDE auto-completion: