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 | protected $diffCaches = array(); |
||
59 | |||
60 | /** |
||
61 | * @var \HTMLPurifier |
||
62 | */ |
||
63 | protected $purifier; |
||
64 | |||
65 | /** |
||
66 | * AbstractDiff constructor. |
||
67 | * |
||
68 | * @param string $oldText |
||
69 | * @param string $newText |
||
70 | * @param string $encoding |
||
71 | * @param null|array $specialCaseTags |
||
72 | * @param null|bool $groupDiffs |
||
73 | */ |
||
74 | 12 | public function __construct($oldText, $newText, $encoding = 'UTF-8', $specialCaseTags = null, $groupDiffs = null) |
|
93 | |||
94 | /** |
||
95 | * @return bool|string |
||
96 | */ |
||
97 | abstract public function build(); |
||
98 | |||
99 | /** |
||
100 | * Initializes HTMLPurifier with cache location. |
||
101 | * |
||
102 | * @param null|string $defaultPurifierSerializerCache |
||
103 | */ |
||
104 | 12 | public function initPurifier($defaultPurifierSerializerCache = null) |
|
115 | |||
116 | /** |
||
117 | * @return DiffCache|null |
||
118 | */ |
||
119 | protected function getDiffCache() |
||
133 | |||
134 | /** |
||
135 | * @return bool |
||
136 | */ |
||
137 | 12 | protected function hasDiffCache() |
|
141 | |||
142 | /** |
||
143 | * @return HtmlDiffConfig |
||
144 | */ |
||
145 | 12 | public function getConfig() |
|
149 | |||
150 | /** |
||
151 | * @param HtmlDiffConfig $config |
||
152 | * |
||
153 | * @return AbstractDiff |
||
154 | */ |
||
155 | 12 | public function setConfig(HtmlDiffConfig $config) |
|
162 | |||
163 | /** |
||
164 | * @return int |
||
165 | * |
||
166 | * @deprecated since 0.1.0 |
||
167 | */ |
||
168 | public function getMatchThreshold() |
||
172 | |||
173 | /** |
||
174 | * @param int $matchThreshold |
||
175 | * |
||
176 | * @return AbstractDiff |
||
177 | * |
||
178 | * @deprecated since 0.1.0 |
||
179 | */ |
||
180 | public function setMatchThreshold($matchThreshold) |
||
186 | |||
187 | /** |
||
188 | * @param array $chars |
||
189 | * |
||
190 | * @deprecated since 0.1.0 |
||
191 | */ |
||
192 | public function setSpecialCaseChars(array $chars) |
||
196 | |||
197 | /** |
||
198 | * @return array|null |
||
199 | * |
||
200 | * @deprecated since 0.1.0 |
||
201 | */ |
||
202 | public function getSpecialCaseChars() |
||
206 | |||
207 | /** |
||
208 | * @param string $char |
||
209 | * |
||
210 | * @deprecated since 0.1.0 |
||
211 | */ |
||
212 | public function addSpecialCaseChar($char) |
||
216 | |||
217 | /** |
||
218 | * @param string $char |
||
219 | * |
||
220 | * @deprecated since 0.1.0 |
||
221 | */ |
||
222 | public function removeSpecialCaseChar($char) |
||
226 | |||
227 | /** |
||
228 | * @param array $tags |
||
229 | * |
||
230 | * @deprecated since 0.1.0 |
||
231 | */ |
||
232 | public function setSpecialCaseTags(array $tags = array()) |
||
236 | |||
237 | /** |
||
238 | * @param string $tag |
||
239 | * |
||
240 | * @deprecated since 0.1.0 |
||
241 | */ |
||
242 | public function addSpecialCaseTag($tag) |
||
246 | |||
247 | /** |
||
248 | * @param string $tag |
||
249 | * |
||
250 | * @deprecated since 0.1.0 |
||
251 | */ |
||
252 | public function removeSpecialCaseTag($tag) |
||
256 | |||
257 | /** |
||
258 | * @return array|null |
||
259 | * |
||
260 | * @deprecated since 0.1.0 |
||
261 | */ |
||
262 | public function getSpecialCaseTags() |
||
266 | |||
267 | /** |
||
268 | * @return string |
||
269 | */ |
||
270 | public function getOldHtml() |
||
274 | |||
275 | /** |
||
276 | * @return string |
||
277 | */ |
||
278 | public function getNewHtml() |
||
282 | |||
283 | /** |
||
284 | * @return string |
||
285 | */ |
||
286 | public function getDifference() |
||
290 | |||
291 | /** |
||
292 | * Clears the diff content. |
||
293 | * |
||
294 | * @return void |
||
295 | */ |
||
296 | public function clearContent() |
||
300 | |||
301 | /** |
||
302 | * @param bool $boolean |
||
303 | * |
||
304 | * @return $this |
||
305 | * |
||
306 | * @deprecated since 0.1.0 |
||
307 | */ |
||
308 | public function setGroupDiffs($boolean) |
||
314 | |||
315 | /** |
||
316 | * @return bool |
||
317 | * |
||
318 | * @deprecated since 0.1.0 |
||
319 | */ |
||
320 | public function isGroupDiffs() |
||
324 | |||
325 | /** |
||
326 | * @param string $tag |
||
327 | * |
||
328 | * @return string |
||
329 | */ |
||
330 | protected function getOpeningTag($tag) |
||
334 | |||
335 | /** |
||
336 | * @param string $tag |
||
337 | * |
||
338 | * @return string |
||
339 | */ |
||
340 | protected function getClosingTag($tag) |
||
344 | |||
345 | /** |
||
346 | * @param string $str |
||
347 | * @param string $start |
||
348 | * @param string $end |
||
349 | * |
||
350 | * @return string |
||
351 | */ |
||
352 | protected function getStringBetween($str, $start, $end) |
||
366 | |||
367 | /** |
||
368 | * @param string $html |
||
369 | * |
||
370 | * @return string |
||
371 | */ |
||
372 | 12 | protected function purifyHtml($html) |
|
385 | |||
386 | 12 | protected function splitInputsToWords() |
|
391 | |||
392 | /** |
||
393 | * @param string $text |
||
394 | * |
||
395 | * @return bool |
||
396 | */ |
||
397 | 12 | protected function isPartOfWord($text) |
|
401 | |||
402 | /** |
||
403 | * @param array $characterString |
||
404 | * |
||
405 | * @return array |
||
406 | */ |
||
407 | 12 | protected function convertHtmlToListOfWords($characterString) |
|
483 | |||
484 | /** |
||
485 | * @param string $val |
||
486 | * |
||
487 | * @return bool |
||
488 | */ |
||
489 | 12 | protected function isStartOfTag($val) |
|
493 | |||
494 | /** |
||
495 | * @param string $val |
||
496 | * |
||
497 | * @return bool |
||
498 | */ |
||
499 | 12 | protected function isEndOfTag($val) |
|
503 | |||
504 | /** |
||
505 | * @param string $value |
||
506 | * |
||
507 | * @return bool |
||
508 | */ |
||
509 | protected function isWhiteSpace($value) |
||
513 | |||
514 | /** |
||
515 | * @param string $value |
||
516 | * |
||
517 | * @return array |
||
518 | */ |
||
519 | 12 | protected function explode($value) |
|
524 | } |
||
525 |
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.