Complex classes like AbstractDiff often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes. You can also have a look at the cohesion graph to spot any un-connected, or weakly-connected components.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use AbstractDiff, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 8 | abstract class AbstractDiff |
||
| 9 | { |
||
| 10 | /** |
||
| 11 | * @var array |
||
| 12 | * |
||
| 13 | * @deprecated since 0.1.0 |
||
| 14 | */ |
||
| 15 | public static $defaultSpecialCaseTags = array('strong', 'b', 'i', 'big', 'small', 'u', 'sub', 'sup', 'strike', 's', 'p'); |
||
|
|
|||
| 16 | /** |
||
| 17 | * @var array |
||
| 18 | * |
||
| 19 | * @deprecated since 0.1.0 |
||
| 20 | */ |
||
| 21 | public static $defaultSpecialCaseChars = array('.', ',', '(', ')', '\''); |
||
| 22 | /** |
||
| 23 | * @var bool |
||
| 24 | * |
||
| 25 | * @deprecated since 0.1.0 |
||
| 26 | */ |
||
| 27 | public static $defaultGroupDiffs = true; |
||
| 28 | |||
| 29 | /** |
||
| 30 | * @var HtmlDiffConfig |
||
| 31 | */ |
||
| 32 | protected $config; |
||
| 33 | |||
| 34 | /** |
||
| 35 | * @var string |
||
| 36 | */ |
||
| 37 | protected $content; |
||
| 38 | /** |
||
| 39 | * @var string |
||
| 40 | */ |
||
| 41 | protected $oldText; |
||
| 42 | /** |
||
| 43 | * @var string |
||
| 44 | */ |
||
| 45 | protected $newText; |
||
| 46 | /** |
||
| 47 | * @var array |
||
| 48 | */ |
||
| 49 | protected $oldWords = array(); |
||
| 50 | /** |
||
| 51 | * @var array |
||
| 52 | */ |
||
| 53 | protected $newWords = array(); |
||
| 54 | |||
| 55 | /** |
||
| 56 | * @var DiffCache[] |
||
| 57 | */ |
||
| 58 | private $diffCaches = array(); |
||
| 59 | |||
| 60 | /** |
||
| 61 | * AbstractDiff constructor. |
||
| 62 | * |
||
| 63 | * @param string $oldText |
||
| 64 | * @param string $newText |
||
| 65 | * @param string $encoding |
||
| 66 | * @param null|array $specialCaseTags |
||
| 67 | * @param null|bool $groupDiffs |
||
| 68 | */ |
||
| 69 | 11 | public function __construct($oldText, $newText, $encoding = 'UTF-8', $specialCaseTags = null, $groupDiffs = null) |
|
| 87 | |||
| 88 | /** |
||
| 89 | * @return bool|string |
||
| 90 | */ |
||
| 91 | abstract public function build(); |
||
| 92 | |||
| 93 | /** |
||
| 94 | * @return DiffCache|null |
||
| 95 | */ |
||
| 96 | protected function getDiffCache() |
||
| 110 | |||
| 111 | /** |
||
| 112 | * @return bool |
||
| 113 | */ |
||
| 114 | 11 | protected function hasDiffCache() |
|
| 118 | |||
| 119 | /** |
||
| 120 | * @return HtmlDiffConfig |
||
| 121 | */ |
||
| 122 | 11 | public function getConfig() |
|
| 126 | |||
| 127 | /** |
||
| 128 | * @param HtmlDiffConfig $config |
||
| 129 | * |
||
| 130 | * @return AbstractDiff |
||
| 131 | */ |
||
| 132 | 8 | public function setConfig(HtmlDiffConfig $config) |
|
| 138 | |||
| 139 | /** |
||
| 140 | * @return int |
||
| 141 | * |
||
| 142 | * @deprecated since 0.1.0 |
||
| 143 | */ |
||
| 144 | public function getMatchThreshold() |
||
| 148 | |||
| 149 | /** |
||
| 150 | * @param int $matchThreshold |
||
| 151 | * |
||
| 152 | * @return AbstractDiff |
||
| 153 | * |
||
| 154 | * @deprecated since 0.1.0 |
||
| 155 | */ |
||
| 156 | public function setMatchThreshold($matchThreshold) |
||
| 162 | |||
| 163 | /** |
||
| 164 | * @param array $chars |
||
| 165 | * |
||
| 166 | * @deprecated since 0.1.0 |
||
| 167 | */ |
||
| 168 | public function setSpecialCaseChars(array $chars) |
||
| 172 | |||
| 173 | /** |
||
| 174 | * @return array|null |
||
| 175 | * |
||
| 176 | * @deprecated since 0.1.0 |
||
| 177 | */ |
||
| 178 | public function getSpecialCaseChars() |
||
| 182 | |||
| 183 | /** |
||
| 184 | * @param string $char |
||
| 185 | * |
||
| 186 | * @deprecated since 0.1.0 |
||
| 187 | */ |
||
| 188 | public function addSpecialCaseChar($char) |
||
| 192 | |||
| 193 | /** |
||
| 194 | * @param string $char |
||
| 195 | * |
||
| 196 | * @deprecated since 0.1.0 |
||
| 197 | */ |
||
| 198 | public function removeSpecialCaseChar($char) |
||
| 202 | |||
| 203 | /** |
||
| 204 | * @param array $tags |
||
| 205 | * |
||
| 206 | * @deprecated since 0.1.0 |
||
| 207 | */ |
||
| 208 | public function setSpecialCaseTags(array $tags = array()) |
||
| 212 | |||
| 213 | /** |
||
| 214 | * @param string $tag |
||
| 215 | * |
||
| 216 | * @deprecated since 0.1.0 |
||
| 217 | */ |
||
| 218 | public function addSpecialCaseTag($tag) |
||
| 222 | |||
| 223 | /** |
||
| 224 | * @param string $tag |
||
| 225 | * |
||
| 226 | * @deprecated since 0.1.0 |
||
| 227 | */ |
||
| 228 | public function removeSpecialCaseTag($tag) |
||
| 232 | |||
| 233 | /** |
||
| 234 | * @return array|null |
||
| 235 | * |
||
| 236 | * @deprecated since 0.1.0 |
||
| 237 | */ |
||
| 238 | public function getSpecialCaseTags() |
||
| 242 | |||
| 243 | /** |
||
| 244 | * @return string |
||
| 245 | */ |
||
| 246 | public function getOldHtml() |
||
| 250 | |||
| 251 | /** |
||
| 252 | * @return string |
||
| 253 | */ |
||
| 254 | public function getNewHtml() |
||
| 258 | |||
| 259 | /** |
||
| 260 | * @return string |
||
| 261 | */ |
||
| 262 | public function getDifference() |
||
| 266 | |||
| 267 | /** |
||
| 268 | * Clears the diff content. |
||
| 269 | * |
||
| 270 | * @return void |
||
| 271 | */ |
||
| 272 | public function clearContent() |
||
| 276 | |||
| 277 | /** |
||
| 278 | * @param bool $boolean |
||
| 279 | * |
||
| 280 | * @return $this |
||
| 281 | * |
||
| 282 | * @deprecated since 0.1.0 |
||
| 283 | */ |
||
| 284 | public function setGroupDiffs($boolean) |
||
| 290 | |||
| 291 | /** |
||
| 292 | * @return bool |
||
| 293 | * |
||
| 294 | * @deprecated since 0.1.0 |
||
| 295 | */ |
||
| 296 | public function isGroupDiffs() |
||
| 300 | |||
| 301 | /** |
||
| 302 | * @param string $tag |
||
| 303 | * |
||
| 304 | * @return string |
||
| 305 | */ |
||
| 306 | protected function getOpeningTag($tag) |
||
| 310 | |||
| 311 | /** |
||
| 312 | * @param string $tag |
||
| 313 | * |
||
| 314 | * @return string |
||
| 315 | */ |
||
| 316 | protected function getClosingTag($tag) |
||
| 320 | |||
| 321 | /** |
||
| 322 | * @param string $str |
||
| 323 | * @param string $start |
||
| 324 | * @param string $end |
||
| 325 | * |
||
| 326 | * @return string |
||
| 327 | */ |
||
| 328 | protected function getStringBetween($str, $start, $end) |
||
| 342 | |||
| 343 | /** |
||
| 344 | * @param string $html |
||
| 345 | * |
||
| 346 | * @return string |
||
| 347 | */ |
||
| 348 | 11 | protected function purifyHtml($html) |
|
| 361 | |||
| 362 | 11 | protected function splitInputsToWords() |
|
| 367 | |||
| 368 | /** |
||
| 369 | * @param string $text |
||
| 370 | * |
||
| 371 | * @return bool |
||
| 372 | */ |
||
| 373 | 11 | protected function isPartOfWord($text) |
|
| 377 | |||
| 378 | /** |
||
| 379 | * @param array $characterString |
||
| 380 | * |
||
| 381 | * @return array |
||
| 382 | */ |
||
| 383 | 11 | protected function convertHtmlToListOfWords($characterString) |
|
| 458 | |||
| 459 | /** |
||
| 460 | * @param string $val |
||
| 461 | * |
||
| 462 | * @return bool |
||
| 463 | */ |
||
| 464 | 11 | protected function isStartOfTag($val) |
|
| 468 | |||
| 469 | /** |
||
| 470 | * @param string $val |
||
| 471 | * |
||
| 472 | * @return bool |
||
| 473 | */ |
||
| 474 | 11 | protected function isEndOfTag($val) |
|
| 478 | |||
| 479 | /** |
||
| 480 | * @param string $value |
||
| 481 | * |
||
| 482 | * @return bool |
||
| 483 | */ |
||
| 484 | protected function isWhiteSpace($value) |
||
| 488 | |||
| 489 | /** |
||
| 490 | * @param string $value |
||
| 491 | * |
||
| 492 | * @return array |
||
| 493 | */ |
||
| 494 | 11 | protected function explode($value) |
|
| 499 | } |
||
| 500 |
Overly long lines are hard to read on any screen. Most code styles therefor impose a maximum limit on the number of characters in a line.