Total Complexity | 111 |
Total Lines | 704 |
Duplicated Lines | 0 % |
Changes | 0 |
Complex classes like Lexer 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.
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 Lexer, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
7 | class Lexer implements LexerInterface |
||
8 | { |
||
9 | /** |
||
10 | * A map between punctuation character code and the corresponding token kind. |
||
11 | * |
||
12 | * @var array |
||
13 | */ |
||
14 | protected static $codeTokenKindMap = [ |
||
15 | 33 => TokenKindEnum::BANG, |
||
16 | 36 => TokenKindEnum::DOLLAR, |
||
17 | 38 => TokenKindEnum::AMP, |
||
18 | 40 => TokenKindEnum::PAREN_L, |
||
19 | 41 => TokenKindEnum::PAREN_R, |
||
20 | 58 => TokenKindEnum::COLON, |
||
21 | 61 => TokenKindEnum::EQUALS, |
||
22 | 64 => TokenKindEnum::AT, |
||
23 | 91 => TokenKindEnum::BRACKET_L, |
||
24 | 93 => TokenKindEnum::BRACKET_R, |
||
25 | 123 => TokenKindEnum::BRACE_L, |
||
26 | 124 => TokenKindEnum::PIPE, |
||
27 | 125 => TokenKindEnum::BRACE_R, |
||
28 | ]; |
||
29 | |||
30 | /** |
||
31 | * The source file for this lexer. |
||
32 | * |
||
33 | * @var Source |
||
34 | */ |
||
35 | protected $source; |
||
36 | |||
37 | /** |
||
38 | * The contents of the source file. |
||
39 | * |
||
40 | * @var string |
||
41 | */ |
||
42 | protected $body; |
||
43 | |||
44 | /** |
||
45 | * The total number of characters in the source file. |
||
46 | * |
||
47 | * @var int |
||
48 | */ |
||
49 | protected $bodyLength; |
||
50 | |||
51 | /** |
||
52 | * The options for this lexer. |
||
53 | * |
||
54 | * @var array |
||
55 | */ |
||
56 | protected $options = []; |
||
57 | |||
58 | /** |
||
59 | * The previously focused non-ignored token. |
||
60 | * |
||
61 | * @var Token |
||
62 | */ |
||
63 | protected $lastToken; |
||
64 | |||
65 | /** |
||
66 | * The currently focused non-ignored token. |
||
67 | * |
||
68 | * @var Token |
||
69 | */ |
||
70 | protected $token; |
||
71 | |||
72 | /** |
||
73 | * The current position. |
||
74 | * |
||
75 | * @var int |
||
76 | */ |
||
77 | protected $pos; |
||
78 | |||
79 | /** |
||
80 | * The (1-indexed) line containing the current token. |
||
81 | * |
||
82 | * @var int |
||
83 | */ |
||
84 | protected $line; |
||
85 | |||
86 | /** |
||
87 | * The character offset at which the current line begins. |
||
88 | * |
||
89 | * @var int |
||
90 | */ |
||
91 | protected $lineStart; |
||
92 | |||
93 | /** |
||
94 | * @var array |
||
95 | */ |
||
96 | protected static $charCodeCache = []; |
||
97 | |||
98 | /** |
||
99 | * Lexer constructor. |
||
100 | * @param Source|null $source |
||
101 | * @param array $options |
||
102 | */ |
||
103 | public function __construct(Source $source, array $options) |
||
104 | { |
||
105 | $startOfFileToken = $this->createStartOfFileToken(); |
||
106 | |||
107 | $this->lastToken = $startOfFileToken; |
||
108 | $this->token = $startOfFileToken; |
||
109 | $this->line = 1; |
||
110 | $this->lineStart = 0; |
||
111 | $this->body = $source->getBody(); |
||
112 | $this->bodyLength = \strlen($this->body); |
||
113 | $this->source = $source; |
||
114 | $this->options = $options; |
||
115 | } |
||
116 | |||
117 | /** |
||
118 | * @inheritdoc |
||
119 | * @throws SyntaxErrorException |
||
120 | */ |
||
121 | public function advance(): Token |
||
122 | { |
||
123 | $this->lastToken = $this->token; |
||
124 | return $this->token = $this->lookahead(); |
||
125 | } |
||
126 | |||
127 | /** |
||
128 | * @inheritdoc |
||
129 | * @throws SyntaxErrorException |
||
130 | */ |
||
131 | public function lookahead(): Token |
||
132 | { |
||
133 | $token = $this->token; |
||
134 | |||
135 | if (TokenKindEnum::EOF !== $token->getKind()) { |
||
136 | do { |
||
137 | $next = $this->readToken($token); |
||
138 | $token->setNext($next); |
||
139 | $token = $next; |
||
140 | } while (TokenKindEnum::COMMENT === $token->getKind()); |
||
141 | } |
||
142 | |||
143 | return $token; |
||
144 | } |
||
145 | |||
146 | /** |
||
147 | * @inheritdoc |
||
148 | */ |
||
149 | public function getOption(string $name, $default = null) |
||
150 | { |
||
151 | return $this->options[$name] ?? $default; |
||
152 | } |
||
153 | |||
154 | /** |
||
155 | * @inheritdoc |
||
156 | */ |
||
157 | public function getTokenKind(): string |
||
158 | { |
||
159 | return $this->token->getKind(); |
||
160 | } |
||
161 | |||
162 | /** |
||
163 | * @inheritdoc |
||
164 | */ |
||
165 | public function getTokenValue(): ?string |
||
166 | { |
||
167 | return $this->token->getValue(); |
||
168 | } |
||
169 | |||
170 | /** |
||
171 | * @inheritdoc |
||
172 | */ |
||
173 | public function getToken(): Token |
||
174 | { |
||
175 | return $this->token; |
||
176 | } |
||
177 | |||
178 | /** |
||
179 | * @inheritdoc |
||
180 | */ |
||
181 | public function getSource(): Source |
||
182 | { |
||
183 | return $this->source; |
||
184 | } |
||
185 | |||
186 | /** |
||
187 | * @inheritdoc |
||
188 | */ |
||
189 | public function getLastToken(): Token |
||
190 | { |
||
191 | return $this->lastToken; |
||
192 | } |
||
193 | |||
194 | /** |
||
195 | * Reads the token after the given token. |
||
196 | * |
||
197 | * @param Token $prev |
||
198 | * @return Token |
||
199 | * @throws SyntaxErrorException |
||
200 | */ |
||
201 | protected function readToken(Token $prev): Token |
||
202 | { |
||
203 | $this->pos = $prev->getEnd(); |
||
204 | |||
205 | $this->skipWhitespace(); |
||
206 | |||
207 | $line = $this->line; |
||
208 | $col = (1 + $this->pos) - $this->lineStart; |
||
209 | |||
210 | if ($this->pos >= $this->bodyLength) { |
||
211 | return $this->createEndOfFileToken($line, $col, $prev); |
||
212 | } |
||
213 | |||
214 | $code = $this->readCharCode($this->pos); |
||
215 | |||
216 | // Punctuation: [!$&:=@|()\[\]{}]{1} |
||
217 | if (33 === $code || 36 === $code || 38 === $code || 58 === $code || 61 === $code || 64 === $code || 124 === $code || |
||
218 | 40 === $code || 41 === $code || 91 === $code || 93 === $code || 123 === $code || 125 === $code) { |
||
219 | return $this->lexPunctuation($code, $line, $col, $prev); |
||
220 | } |
||
221 | |||
222 | // Comment: #[\u0009\u0020-\uFFFF]* |
||
223 | if (35 === $code) { |
||
224 | return $this->lexComment($line, $col, $prev); |
||
225 | } |
||
226 | |||
227 | // Int: -?(0|[1-9][0-9]*) |
||
228 | // Float: -?(0|[1-9][0-9]*)(\.[0-9]+)?((E|e)(+|-)?[0-9]+)? |
||
229 | if (45 === $code || isNumber($code)) { |
||
230 | return $this->lexNumber($code, $line, $col, $prev); |
||
231 | } |
||
232 | |||
233 | // Name: [_A-Za-z][_0-9A-Za-z]* |
||
234 | if (isAlphaNumeric($code)) { |
||
235 | return $this->lexName($line, $col, $prev); |
||
236 | } |
||
237 | |||
238 | // Spread: ... |
||
239 | if ($this->bodyLength >= 3 && $this->isSpread($code)) { |
||
240 | return $this->lexSpread($line, $col, $prev); |
||
241 | } |
||
242 | |||
243 | // String: "([^"\\\u000A\u000D]|(\\(u[0-9a-fA-F]{4}|["\\/bfnrt])))*" |
||
244 | if ($this->isString($code)) { |
||
245 | return $this->lexString($line, $col, $prev); |
||
246 | } |
||
247 | |||
248 | // Block String: """("?"?(\\"""|\\(?!=""")|[^"\\]))*""" |
||
249 | if ($this->bodyLength >= 3 && $this->isTripleQuote($code)) { |
||
250 | return $this->lexBlockString($line, $col, $prev); |
||
251 | } |
||
252 | |||
253 | throw $this->createSyntaxErrorException(); |
||
254 | } |
||
255 | |||
256 | /** |
||
257 | * @return Token |
||
258 | */ |
||
259 | protected function createStartOfFileToken(): Token |
||
262 | } |
||
263 | |||
264 | /** |
||
265 | * Creates an End Of File (EOF) token. |
||
266 | * |
||
267 | * @param int $line |
||
268 | * @param int $col |
||
269 | * @param Token $prev |
||
270 | * @return Token |
||
271 | */ |
||
272 | protected function createEndOfFileToken(int $line, int $col, Token $prev): Token |
||
273 | { |
||
274 | return new Token(TokenKindEnum::EOF, $this->bodyLength, $this->bodyLength, $line, $col, $prev); |
||
275 | } |
||
276 | |||
277 | /** |
||
278 | * Reads a punctuation token from the source file. |
||
279 | * |
||
280 | * @param int $code |
||
281 | * @param int $line |
||
282 | * @param int $col |
||
283 | * @param Token $prev |
||
284 | * @return Token |
||
285 | * @throws SyntaxErrorException |
||
286 | */ |
||
287 | protected function lexPunctuation(int $code, int $line, int $col, Token $prev): ?Token |
||
288 | { |
||
289 | if (!isset(self::$codeTokenKindMap[$code])) { |
||
290 | throw $this->createSyntaxErrorException(); |
||
291 | } |
||
292 | |||
293 | return new Token(self::$codeTokenKindMap[$code], $this->pos, $this->pos + 1, $line, $col, $prev); |
||
294 | } |
||
295 | |||
296 | /** |
||
297 | * Reads a name token from the source file. |
||
298 | * |
||
299 | * @param int $line |
||
300 | * @param int $col |
||
301 | * @param Token $prev |
||
302 | * @return Token |
||
303 | */ |
||
304 | protected function lexName(int $line, int $col, Token $prev): Token |
||
305 | { |
||
306 | $start = $this->pos; |
||
307 | |||
308 | ++$this->pos; |
||
309 | |||
310 | while ($this->pos !== $this->bodyLength && |
||
311 | ($code = $this->readCharCode($this->pos)) !== null && |
||
312 | isAlphaNumeric($code)) { |
||
313 | ++$this->pos; |
||
314 | } |
||
315 | |||
316 | $value = sliceString($this->body, $start, $this->pos); |
||
317 | |||
318 | return new Token(TokenKindEnum::NAME, $start, $this->pos, $line, $col, $prev, $value); |
||
319 | } |
||
320 | |||
321 | /** |
||
322 | * Reads a number (int or float) token from the source file. |
||
323 | * |
||
324 | * @param int $code |
||
325 | * @param int $line |
||
326 | * @param int $col |
||
327 | * @param Token $prev |
||
328 | * @return Token |
||
329 | * @throws SyntaxErrorException |
||
330 | */ |
||
331 | protected function lexNumber(int $code, int $line, int $col, Token $prev): Token |
||
385 | ); |
||
386 | } |
||
387 | |||
388 | /** |
||
389 | * Skips digits at the current position. |
||
390 | * |
||
391 | * @param int $code |
||
392 | * @throws SyntaxErrorException |
||
393 | */ |
||
394 | protected function skipDigits(int $code): void |
||
395 | { |
||
396 | if (isNumber($code)) { |
||
397 | do { |
||
398 | $code = $this->readCharCode(++$this->pos); |
||
399 | } while (isNumber($code)); |
||
400 | |||
401 | return; |
||
402 | } |
||
403 | |||
404 | throw $this->createSyntaxErrorException( |
||
405 | \sprintf('Invalid number, expected digit but got: %s.', printCharCode($code)) |
||
406 | ); |
||
407 | } |
||
408 | |||
409 | /** |
||
410 | * Reads a comment token from the source file. |
||
411 | * |
||
412 | * @param int $line |
||
413 | * @param int $col |
||
414 | * @param Token $prev |
||
415 | * @return Token |
||
416 | */ |
||
417 | protected function lexComment(int $line, int $col, Token $prev): Token |
||
418 | { |
||
419 | $start = $this->pos; |
||
420 | |||
421 | do { |
||
422 | $code = $this->readCharCode(++$this->pos); |
||
423 | } while ($code !== null && ($code > 0x001f || 0x0009 === $code)); // SourceCharacter but not LineTerminator |
||
424 | |||
425 | return new Token( |
||
426 | TokenKindEnum::COMMENT, |
||
427 | $start, |
||
428 | $this->pos, |
||
429 | $line, |
||
430 | $col, |
||
431 | $prev, |
||
432 | sliceString($this->body, $start + 1, $this->pos) |
||
433 | ); |
||
434 | } |
||
435 | |||
436 | /** |
||
437 | * Reads a spread token from the source. |
||
438 | * |
||
439 | * @param int $line |
||
440 | * @param int $col |
||
441 | * @param Token $prev |
||
442 | * @return Token |
||
443 | */ |
||
444 | protected function lexSpread(int $line, int $col, Token $prev): Token |
||
445 | { |
||
446 | return new Token(TokenKindEnum::SPREAD, $this->pos, $this->pos + 3, $line, $col, $prev); |
||
447 | } |
||
448 | |||
449 | /** |
||
450 | * Reads a string token from the source. |
||
451 | * |
||
452 | * @param int $line |
||
453 | * @param int $col |
||
454 | * @param Token $prev |
||
455 | * @return Token |
||
456 | * @throws SyntaxErrorException |
||
457 | */ |
||
458 | protected function lexString(int $line, int $col, Token $prev): Token |
||
459 | { |
||
460 | $start = $this->pos; |
||
461 | $chunkStart = ++$this->pos; // skip the quote |
||
462 | $value = ''; |
||
463 | |||
464 | while ($this->pos < $this->bodyLength && |
||
465 | ($code = $this->readCharCode($this->pos)) !== null && !isLineTerminator($code)) { |
||
466 | // Closing Quote (") |
||
467 | if (34 === $code) { |
||
468 | $value .= sliceString($this->body, $chunkStart, $this->pos); |
||
469 | return new Token(TokenKindEnum::STRING, $start, $this->pos + 1, $line, $col, $prev, $value); |
||
470 | } |
||
471 | |||
472 | if (isSourceCharacter($code)) { |
||
473 | throw $this->createSyntaxErrorException( |
||
474 | \sprintf('Invalid character within String: %s.', printCharCode($code)) |
||
475 | ); |
||
476 | } |
||
477 | |||
478 | ++$this->pos; |
||
479 | |||
480 | if (92 === $code) { |
||
481 | // \ |
||
482 | $value .= sliceString($this->body, $chunkStart, $this->pos - 1); |
||
483 | |||
484 | $code = $this->readCharCode($this->pos); |
||
485 | |||
486 | switch ($code) { |
||
487 | case 34: // " |
||
488 | $value .= '"'; |
||
489 | break; |
||
490 | case 47: // / |
||
491 | $value .= '/'; |
||
492 | break; |
||
493 | case 92: // \ |
||
494 | $value .= '\\'; |
||
495 | break; |
||
496 | case 98: // b |
||
497 | $value .= '\b'; |
||
498 | break; |
||
499 | case 102: // f |
||
500 | $value .= '\f'; |
||
501 | break; |
||
502 | case 110: // n |
||
503 | $value .= '\n'; |
||
504 | break; |
||
505 | case 114: // r |
||
506 | $value .= '\r'; |
||
507 | break; |
||
508 | case 116: // t |
||
509 | $value .= '\t'; |
||
510 | break; |
||
511 | case 117: // u |
||
512 | $unicodeString = sliceString($this->body, $this->pos + 1, $this->pos + 5); |
||
513 | |||
514 | if (!\preg_match('/[0-9A-Fa-f]{4}/', $unicodeString)) { |
||
515 | throw $this->createSyntaxErrorException( |
||
516 | \sprintf('Invalid character escape sequence: \\u%s.', $unicodeString) |
||
517 | ); |
||
518 | } |
||
519 | |||
520 | $value .= '\\u' . $unicodeString; |
||
521 | $this->pos += 4; |
||
522 | |||
523 | break; |
||
524 | default: |
||
525 | throw $this->createSyntaxErrorException( |
||
526 | \sprintf('Invalid character escape sequence: \\%s.', \chr($code)) |
||
527 | ); |
||
528 | } |
||
529 | |||
530 | ++$this->pos; |
||
531 | |||
532 | $chunkStart = $this->pos; |
||
533 | } |
||
534 | } |
||
535 | |||
536 | throw $this->createSyntaxErrorException('Unterminated string.'); |
||
537 | } |
||
538 | |||
539 | /** |
||
540 | * Reads a block string token from the source file. |
||
541 | * |
||
542 | * @param int $line |
||
543 | * @param int $col |
||
544 | * @param Token $prev |
||
545 | * @return Token |
||
546 | * @throws SyntaxErrorException |
||
547 | */ |
||
548 | protected function lexBlockString(int $line, int $col, Token $prev): Token |
||
586 | } |
||
587 | |||
588 | /** |
||
589 | * Skips whitespace at the current position. |
||
590 | */ |
||
591 | protected function skipWhitespace(): void |
||
592 | { |
||
593 | while ($this->pos < $this->bodyLength) { |
||
594 | $code = $this->readCharCode($this->pos); |
||
595 | |||
596 | if (9 === $code || 32 === $code || 44 === $code || 0xfeff === $code) { |
||
597 | // tab | space | comma | BOM |
||
598 | ++$this->pos; |
||
599 | } elseif (10 === $code) { |
||
600 | // new line (\n) |
||
601 | ++$this->pos; |
||
602 | ++$this->line; |
||
603 | $this->lineStart = $this->pos; |
||
604 | } elseif (13 === $code) { |
||
605 | // carriage return (\r) |
||
606 | if (10 === $this->readCharCode($this->pos + 1)) { |
||
607 | // carriage return and new line (\r\n) |
||
608 | $this->pos += 2; |
||
609 | } else { |
||
610 | ++$this->pos; |
||
611 | } |
||
612 | ++$this->line; |
||
613 | $this->lineStart = $this->pos; |
||
614 | } else { |
||
615 | break; |
||
616 | } |
||
617 | } |
||
618 | } |
||
619 | |||
620 | /** |
||
621 | * @param int $pos |
||
622 | * @return int |
||
623 | */ |
||
624 | protected function readCharCode(int $pos): int |
||
633 | } |
||
634 | |||
635 | /** |
||
636 | * Creates a `SyntaxErrorException` for the current position in the source. |
||
637 | * |
||
638 | * @param null|string $description |
||
639 | * @return SyntaxErrorException |
||
640 | */ |
||
641 | protected function createSyntaxErrorException(?string $description = null): SyntaxErrorException |
||
642 | { |
||
643 | return new SyntaxErrorException( |
||
644 | $this->source, |
||
645 | $this->pos, |
||
646 | $description ?? $this->unexpectedCharacterMessage($this->readCharCode($this->pos)) |
||
647 | ); |
||
648 | } |
||
649 | |||
650 | /** |
||
651 | * Report a message that an unexpected character was encountered. |
||
652 | * |
||
653 | * @param int $code |
||
654 | * @return string |
||
655 | */ |
||
656 | protected function unexpectedCharacterMessage(int $code): string |
||
657 | { |
||
658 | if (isSourceCharacter($code) && !isLineTerminator($code)) { |
||
659 | return \sprintf('Cannot contain the invalid character %s.', printCharCode($code)); |
||
660 | } |
||
661 | |||
662 | if ($code === 39) { |
||
663 | // ' |
||
664 | return 'Unexpected single quote character (\'), did you mean to use a double quote (")?'; |
||
665 | } |
||
666 | |||
667 | return \sprintf('Cannot parse the unexpected character %s.', printCharCode($code)); |
||
668 | } |
||
669 | |||
670 | /** |
||
671 | * @param int $code |
||
672 | * @return bool |
||
673 | */ |
||
674 | protected function isSpread(int $code): bool |
||
675 | { |
||
676 | return 46 === $code && |
||
677 | $this->readCharCode($this->pos + 1) === 46 && |
||
678 | $this->readCharCode($this->pos + 2) === 46; // ... |
||
679 | } |
||
680 | |||
681 | /** |
||
682 | * @param int $code |
||
683 | * @return bool |
||
684 | */ |
||
685 | protected function isString(int $code): bool |
||
686 | { |
||
687 | return 34 === $code && $this->readCharCode($this->pos + 1) !== 34; |
||
688 | } |
||
689 | |||
690 | /** |
||
691 | * @param int $code |
||
692 | * @return bool |
||
693 | */ |
||
694 | protected function isTripleQuote(int $code): bool |
||
695 | { |
||
696 | return 34 === $code && |
||
697 | 34 === $this->readCharCode($this->pos + 1) && |
||
698 | 34 === $this->readCharCode($this->pos + 2); // """ |
||
699 | } |
||
700 | |||
701 | /** |
||
702 | * @param int $code |
||
703 | * @return bool |
||
704 | */ |
||
705 | protected function isEscapedTripleQuote(int $code): bool |
||
711 | } |
||
712 | } |
||
713 |
This check compares calls to functions or methods with their respective definitions. If the call has less arguments than are defined, it raises an issue.
If a function is defined several times with a different number of parameters, the check may pick up the wrong definition and report false positives. One codebase where this has been known to happen is Wordpress. Please note the @ignore annotation hint above.