Behat /
Gherkin
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:
Complex classes like Parser 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 Parser, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 34 | class Parser |
||
| 35 | { |
||
| 36 | private $lexer; |
||
| 37 | private $input; |
||
| 38 | private $file; |
||
| 39 | private $tags = array(); |
||
| 40 | private $languageSpecifierLine; |
||
| 41 | |||
| 42 | /** |
||
| 43 | * Initializes parser. |
||
| 44 | * |
||
| 45 | * @param Lexer $lexer Lexer instance |
||
| 46 | */ |
||
| 47 | 269 | public function __construct(Lexer $lexer) |
|
| 51 | |||
| 52 | /** |
||
| 53 | * Parses input & returns features array. |
||
| 54 | * |
||
| 55 | * @param string $input Gherkin string document |
||
| 56 | * @param string $file File name |
||
| 57 | * |
||
| 58 | * @return FeatureNode|null |
||
| 59 | * |
||
| 60 | * @throws ParserException |
||
| 61 | */ |
||
| 62 | 267 | public function parse($input, $file = null) |
|
| 63 | { |
||
| 64 | 267 | $this->languageSpecifierLine = null; |
|
| 65 | 267 | $this->input = $input; |
|
| 66 | 267 | $this->file = $file; |
|
| 67 | 267 | $this->tags = array(); |
|
| 68 | |||
| 69 | try { |
||
| 70 | 267 | $this->lexer->analyse($this->input, 'en'); |
|
| 71 | } catch (LexerException $e) { |
||
| 72 | throw new ParserException( |
||
| 73 | sprintf('Lexer exception "%s" thrown for file %s', $e->getMessage(), $file), |
||
| 74 | 0, |
||
| 75 | $e |
||
| 76 | ); |
||
| 77 | } |
||
| 78 | |||
| 79 | 267 | $feature = null; |
|
| 80 | 267 | while ('EOS' !== ($predicted = $this->predictTokenType())) { |
|
| 81 | 267 | $node = $this->parseExpression(); |
|
| 82 | |||
| 83 | 257 | if (null === $node || "\n" === $node) { |
|
| 84 | 7 | continue; |
|
| 85 | } |
||
| 86 | |||
| 87 | 255 | if (!$feature && $node instanceof FeatureNode) { |
|
| 88 | 252 | $feature = $node; |
|
| 89 | 252 | continue; |
|
| 90 | } |
||
| 91 | |||
| 92 | 3 | if ($feature && $node instanceof FeatureNode) { |
|
| 93 | throw new ParserException(sprintf( |
||
| 94 | 'Only one feature is allowed per feature file. But %s got multiple.', |
||
| 95 | $this->file |
||
| 96 | )); |
||
| 97 | } |
||
| 98 | |||
| 99 | 3 | View Code Duplication | if (is_string($node)) { |
|
|
|||
| 100 | 3 | throw new ParserException(sprintf( |
|
| 101 | 3 | 'Expected Feature, but got text: "%s"%s', |
|
| 102 | 3 | $node, |
|
| 103 | 3 | $this->file ? ' in file: ' . $this->file : '' |
|
| 104 | )); |
||
| 105 | } |
||
| 106 | |||
| 107 | if (!$node instanceof FeatureNode) { |
||
| 108 | throw new ParserException(sprintf( |
||
| 109 | 'Expected Feature, but got %s on line: %d%s', |
||
| 110 | $node->getKeyword(), |
||
| 111 | $node->getLine(), |
||
| 112 | $this->file ? ' in file: ' . $this->file : '' |
||
| 113 | )); |
||
| 114 | } |
||
| 115 | } |
||
| 116 | |||
| 117 | 253 | return $feature; |
|
| 118 | } |
||
| 119 | |||
| 120 | /** |
||
| 121 | * Returns next token if it's type equals to expected. |
||
| 122 | * |
||
| 123 | * @param string $type Token type |
||
| 124 | * |
||
| 125 | * @return array |
||
| 126 | * |
||
| 127 | * @throws Exception\ParserException |
||
| 128 | */ |
||
| 129 | 267 | protected function expectTokenType($type) |
|
| 146 | |||
| 147 | /** |
||
| 148 | * Returns next token if it's type equals to expected. |
||
| 149 | * |
||
| 150 | * @param string $type Token type |
||
| 151 | * |
||
| 152 | * @return null|array |
||
| 153 | */ |
||
| 154 | 242 | protected function acceptTokenType($type) |
|
| 162 | |||
| 163 | /** |
||
| 164 | * Returns next token type without real input reading (prediction). |
||
| 165 | * |
||
| 166 | * @return string |
||
| 167 | */ |
||
| 168 | 267 | protected function predictTokenType() |
|
| 174 | |||
| 175 | /** |
||
| 176 | * Parses current expression & returns Node. |
||
| 177 | * |
||
| 178 | * @return string|FeatureNode|BackgroundNode|ScenarioNode|OutlineNode|TableNode|StepNode |
||
| 179 | * |
||
| 180 | * @throws ParserException |
||
| 181 | */ |
||
| 182 | 267 | protected function parseExpression() |
|
| 217 | |||
| 218 | /** |
||
| 219 | * Parses feature token & returns it's node. |
||
| 220 | * |
||
| 221 | * @return FeatureNode |
||
| 222 | * |
||
| 223 | * @throws ParserException |
||
| 224 | */ |
||
| 225 | 262 | protected function parseFeature() |
|
| 290 | |||
| 291 | /** |
||
| 292 | * Parses background token & returns it's node. |
||
| 293 | * |
||
| 294 | * @return BackgroundNode |
||
| 295 | * |
||
| 296 | * @throws ParserException |
||
| 297 | */ |
||
| 298 | 202 | protected function parseBackground() |
|
| 355 | |||
| 356 | /** |
||
| 357 | * Parses scenario token & returns it's node. |
||
| 358 | * |
||
| 359 | * @return ScenarioNode |
||
| 360 | * |
||
| 361 | * @throws ParserException |
||
| 362 | */ |
||
| 363 | 240 | protected function parseScenario() |
|
| 412 | |||
| 413 | /** |
||
| 414 | * Parses scenario outline token & returns it's node. |
||
| 415 | * |
||
| 416 | * @return OutlineNode |
||
| 417 | * |
||
| 418 | * @throws ParserException |
||
| 419 | */ |
||
| 420 | 212 | protected function parseOutline() |
|
| 421 | { |
||
| 422 | 212 | $token = $this->expectTokenType('Outline'); |
|
| 423 | |||
| 424 | 212 | $title = trim($token['value']); |
|
| 425 | 212 | $tags = $this->popTags(); |
|
| 426 | 212 | $keyword = $token['keyword']; |
|
| 427 | 212 | $examples = null; |
|
| 428 | 212 | $line = $token['line']; |
|
| 429 | |||
| 430 | // Parse description, steps and examples |
||
| 431 | 212 | $steps = array(); |
|
| 432 | 212 | while (in_array($this->predictTokenType(), array('Step', 'Examples', 'Newline', 'Text', 'Comment'))) { |
|
| 433 | 211 | $node = $this->parseExpression(); |
|
| 434 | |||
| 435 | 211 | if ($node instanceof StepNode) { |
|
| 436 | 210 | $steps[] = $this->normalizeStepNodeKeywordType($node, $steps); |
|
| 437 | 210 | continue; |
|
| 438 | } |
||
| 439 | |||
| 440 | 210 | if ($node instanceof ExampleTableNode) { |
|
| 441 | 210 | $examples = $node; |
|
| 442 | 210 | continue; |
|
| 443 | } |
||
| 444 | |||
| 445 | 6 | View Code Duplication | if (!count($steps) && is_string($node)) { |
| 446 | 6 | $text = preg_replace('/^\s{0,' . ($token['indent'] + 2) . '}|\s*$/', '', $node); |
|
| 447 | 6 | $title .= "\n" . $text; |
|
| 448 | 6 | continue; |
|
| 449 | } |
||
| 450 | |||
| 451 | if ("\n" === $node) { |
||
| 452 | continue; |
||
| 453 | } |
||
| 454 | |||
| 455 | View Code Duplication | if (is_string($node)) { |
|
| 456 | throw new ParserException(sprintf( |
||
| 457 | 'Expected Step or Examples table, but got text: "%s"%s', |
||
| 458 | $node, |
||
| 459 | $this->file ? ' in file: ' . $this->file : '' |
||
| 460 | )); |
||
| 461 | } |
||
| 462 | |||
| 463 | View Code Duplication | if (!$node instanceof StepNode) { |
|
| 464 | throw new ParserException(sprintf( |
||
| 465 | 'Expected Step or Examples table, but got %s on line: %d%s', |
||
| 466 | $node->getNodeType(), |
||
| 467 | $node->getLine(), |
||
| 468 | $this->file ? ' in file: ' . $this->file : '' |
||
| 469 | )); |
||
| 470 | } |
||
| 471 | } |
||
| 472 | |||
| 473 | 212 | if (null === $examples) { |
|
| 474 | 2 | throw new ParserException(sprintf( |
|
| 475 | 2 | 'Outline should have examples table, but got none for outline "%s" on line: %d%s', |
|
| 476 | 2 | rtrim($title), |
|
| 477 | 2 | $line, |
|
| 478 | 2 | $this->file ? ' in file: ' . $this->file : '' |
|
| 479 | )); |
||
| 480 | } |
||
| 481 | |||
| 482 | 210 | return new OutlineNode(rtrim($title) ?: null, $tags, $steps, $examples, $keyword, $line); |
|
| 483 | } |
||
| 484 | |||
| 485 | /** |
||
| 486 | * Parses step token & returns it's node. |
||
| 487 | * |
||
| 488 | * @return StepNode |
||
| 489 | */ |
||
| 490 | 247 | protected function parseStep() |
|
| 515 | |||
| 516 | /** |
||
| 517 | * Parses examples table node. |
||
| 518 | * |
||
| 519 | * @return ExampleTableNode |
||
| 520 | */ |
||
| 521 | 210 | protected function parseExamples() |
|
| 529 | |||
| 530 | /** |
||
| 531 | * Parses table token & returns it's node. |
||
| 532 | * |
||
| 533 | * @return TableNode |
||
| 534 | */ |
||
| 535 | 7 | protected function parseTable() |
|
| 539 | |||
| 540 | /** |
||
| 541 | * Parses PyString token & returns it's node. |
||
| 542 | * |
||
| 543 | * @return PyStringNode |
||
| 544 | */ |
||
| 545 | 12 | protected function parsePyString() |
|
| 562 | |||
| 563 | /** |
||
| 564 | * Parses tags. |
||
| 565 | * |
||
| 566 | * @return BackgroundNode|FeatureNode|OutlineNode|ScenarioNode|StepNode|TableNode|string |
||
| 567 | */ |
||
| 568 | 6 | protected function parseTags() |
|
| 575 | |||
| 576 | /** |
||
| 577 | * Returns current set of tags and clears tag buffer. |
||
| 578 | * |
||
| 579 | * @return array |
||
| 580 | */ |
||
| 581 | 262 | protected function popTags() |
|
| 588 | |||
| 589 | /** |
||
| 590 | * Parses next text line & returns it. |
||
| 591 | * |
||
| 592 | * @return string |
||
| 593 | */ |
||
| 594 | 224 | protected function parseText() |
|
| 600 | |||
| 601 | /** |
||
| 602 | * Parses next newline & returns \n. |
||
| 603 | * |
||
| 604 | * @return string |
||
| 605 | */ |
||
| 606 | 258 | protected function parseNewline() |
|
| 612 | |||
| 613 | /** |
||
| 614 | * Parses next comment token & returns it's string content. |
||
| 615 | * |
||
| 616 | * @return BackgroundNode|FeatureNode|OutlineNode|ScenarioNode|StepNode|TableNode|string |
||
| 617 | */ |
||
| 618 | 8 | protected function parseComment() |
|
| 624 | |||
| 625 | /** |
||
| 626 | * Parses language block and updates lexer configuration based on it. |
||
| 627 | * |
||
| 628 | * @return BackgroundNode|FeatureNode|OutlineNode|ScenarioNode|StepNode|TableNode|string |
||
| 629 | * |
||
| 630 | * @throws ParserException |
||
| 631 | */ |
||
| 632 | 197 | protected function parseLanguage() |
|
| 650 | |||
| 651 | /** |
||
| 652 | * Parses the rows of a table |
||
| 653 | * |
||
| 654 | * @return string[][] |
||
| 655 | */ |
||
| 656 | 214 | private function parseTableRows() |
|
| 672 | |||
| 673 | /** |
||
| 674 | * Changes step node type for types But, And to type of previous step if it exists else sets to Given |
||
| 675 | * |
||
| 676 | * @param StepNode $node |
||
| 677 | * @param StepNode[] $steps |
||
| 678 | * @return StepNode |
||
| 679 | */ |
||
| 680 | 245 | private function normalizeStepNodeKeywordType(StepNode $node, array $steps = array()) |
|
| 699 | } |
||
| 700 |
Loading history...
Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation.
You can also find more detailed suggestions in the “Code” section of your repository.