Complex classes like Cursor 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 Cursor, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
14 | class Cursor |
||
15 | { |
||
16 | const INDENT_LEVEL = 4; |
||
17 | |||
18 | /** |
||
19 | * @var string |
||
20 | */ |
||
21 | private $line; |
||
22 | |||
23 | /** |
||
24 | * @var int |
||
25 | */ |
||
26 | private $length; |
||
27 | |||
28 | /** |
||
29 | * @var int |
||
30 | * |
||
31 | * It's possible for this to be 1 char past the end, meaning we've parsed all chars and have |
||
32 | * reached the end. In this state, any character-returning method MUST return null. |
||
33 | */ |
||
34 | private $currentPosition = 0; |
||
35 | |||
36 | /** |
||
37 | * @var int |
||
38 | */ |
||
39 | private $column = 0; |
||
40 | |||
41 | /** |
||
42 | * @var int |
||
43 | */ |
||
44 | private $indent = 0; |
||
45 | |||
46 | /** |
||
47 | * @var int |
||
48 | */ |
||
49 | private $previousPosition = 0; |
||
50 | |||
51 | /** |
||
52 | * @var int|null |
||
53 | */ |
||
54 | private $nextNonSpaceCache; |
||
55 | |||
56 | /** |
||
57 | * @var bool |
||
58 | */ |
||
59 | private $partiallyConsumedTab = false; |
||
60 | |||
61 | /** |
||
62 | * @var string |
||
63 | */ |
||
64 | private $encoding; |
||
65 | |||
66 | /** |
||
67 | * @var bool |
||
68 | */ |
||
69 | private $lineContainsTabs; |
||
70 | |||
71 | /** |
||
72 | * @var bool |
||
73 | */ |
||
74 | private $isMultibyte; |
||
75 | |||
76 | /** |
||
77 | * @var array<int, string> |
||
78 | */ |
||
79 | private $charCache = []; |
||
80 | |||
81 | /** |
||
82 | * @param string $line The line being parsed |
||
83 | * @param string $encoding The encoding of that line |
||
84 | */ |
||
85 | 2478 | public function __construct(string $line, string $encoding = 'UTF-8') |
|
93 | |||
94 | 60 | public function getEncoding(): string |
|
98 | |||
99 | /** |
||
100 | * Returns the position of the next character which is not a space (or tab) |
||
101 | * |
||
102 | * @return int |
||
103 | */ |
||
104 | 2208 | public function getNextNonSpacePosition(): int |
|
130 | |||
131 | /** |
||
132 | * Returns the next character which isn't a space (or tab) |
||
133 | * |
||
134 | * @return string |
||
135 | */ |
||
136 | 2001 | public function getNextNonSpaceCharacter(): ?string |
|
140 | |||
141 | /** |
||
142 | * Calculates the current indent (number of spaces after current position) |
||
143 | * |
||
144 | * @return int |
||
145 | */ |
||
146 | 2088 | public function getIndent(): int |
|
154 | |||
155 | /** |
||
156 | * Whether the cursor is indented to INDENT_LEVEL |
||
157 | * |
||
158 | * @return bool |
||
159 | */ |
||
160 | 2028 | public function isIndented(): bool |
|
164 | |||
165 | /** |
||
166 | * @param int|null $index |
||
167 | * |
||
168 | * @return string|null |
||
169 | */ |
||
170 | 2262 | public function getCharacter(?int $index = null): ?string |
|
187 | |||
188 | /** |
||
189 | * Returns the next character (or null, if none) without advancing forwards |
||
190 | * |
||
191 | * @param int $offset |
||
192 | * |
||
193 | * @return string|null |
||
194 | */ |
||
195 | 1065 | public function peek(int $offset = 1): ?string |
|
199 | |||
200 | /** |
||
201 | * Whether the remainder is blank |
||
202 | * |
||
203 | * @return bool |
||
204 | */ |
||
205 | 2046 | public function isBlank(): bool |
|
209 | |||
210 | /** |
||
211 | * Move the cursor forwards |
||
212 | */ |
||
213 | 846 | public function advance() |
|
217 | |||
218 | /** |
||
219 | * Move the cursor forwards |
||
220 | * |
||
221 | * @param int $characters Number of characters to advance by |
||
222 | * @param bool $advanceByColumns Whether to advance by columns instead of spaces |
||
223 | */ |
||
224 | 2334 | public function advanceBy(int $characters, bool $advanceByColumns = false) |
|
278 | |||
279 | /** |
||
280 | * Advances the cursor by a single space or tab, if present |
||
281 | * |
||
282 | * @return bool |
||
283 | */ |
||
284 | 348 | public function advanceBySpaceOrTab(): bool |
|
296 | |||
297 | /** |
||
298 | * Parse zero or more space/tab characters |
||
299 | * |
||
300 | * @return int Number of positions moved |
||
301 | */ |
||
302 | 1935 | public function advanceToNextNonSpaceOrTab(): int |
|
310 | |||
311 | /** |
||
312 | * Parse zero or more space characters, including at most one newline. |
||
313 | * |
||
314 | * Tab characters are not parsed with this function. |
||
315 | * |
||
316 | * @return int Number of positions moved |
||
317 | */ |
||
318 | 477 | public function advanceToNextNonSpaceOrNewline(): int |
|
335 | |||
336 | /** |
||
337 | * Move the position to the very end of the line |
||
338 | * |
||
339 | * @return int The number of characters moved |
||
340 | */ |
||
341 | 84 | public function advanceToEnd(): int |
|
350 | |||
351 | /** |
||
352 | * @return string |
||
353 | */ |
||
354 | 2130 | public function getRemainder(): string |
|
370 | |||
371 | /** |
||
372 | * @return string |
||
373 | */ |
||
374 | 1977 | public function getLine(): string |
|
378 | |||
379 | /** |
||
380 | * @return bool |
||
381 | */ |
||
382 | 447 | public function isAtEnd(): bool |
|
386 | |||
387 | /** |
||
388 | * Try to match a regular expression |
||
389 | * |
||
390 | * Returns the matching text and advances to the end of that match |
||
391 | * |
||
392 | * @param string $regex |
||
393 | * |
||
394 | * @return string|null |
||
395 | */ |
||
396 | 1998 | public function match(string $regex): ?string |
|
422 | |||
423 | /** |
||
424 | * Encapsulates the current state of this cursor in case you need to rollback later. |
||
425 | * |
||
426 | * WARNING: Do not parse or use the return value for ANYTHING except for |
||
427 | * passing it back into restoreState(), as the number of values and their |
||
428 | * contents may change in any future release without warning. |
||
429 | * |
||
430 | * @return array |
||
431 | */ |
||
432 | 1077 | public function saveState() |
|
443 | |||
444 | /** |
||
445 | * Restore the cursor to a previous state. |
||
446 | * |
||
447 | * Pass in the value previously obtained by calling saveState(). |
||
448 | * |
||
449 | * @param array $state |
||
450 | */ |
||
451 | 843 | public function restoreState($state) |
|
462 | |||
463 | /** |
||
464 | * @return int |
||
465 | */ |
||
466 | 699 | public function getPosition(): int |
|
470 | |||
471 | /** |
||
472 | * @return string |
||
473 | */ |
||
474 | 921 | public function getPreviousText(): string |
|
478 | |||
479 | /** |
||
480 | * @return int |
||
481 | */ |
||
482 | 249 | public function getColumn(): int |
|
486 | } |
||
487 |