Complex classes like ExpressionLexer 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 ExpressionLexer, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 30 | class ExpressionLexer |
||
| 31 | { |
||
| 32 | /** |
||
| 33 | * Suffix for single literals |
||
| 34 | * |
||
| 35 | * @var char |
||
| 36 | */ |
||
| 37 | const SINGLE_SUFFIX_LOWER = 'f'; |
||
| 38 | |||
| 39 | /** |
||
| 40 | * Suffix for single literals |
||
| 41 | * |
||
| 42 | * @var char |
||
| 43 | */ |
||
| 44 | const SINGLE_SUFFIX_UPPER = 'F'; |
||
| 45 | |||
| 46 | /** |
||
| 47 | * Text being parsed |
||
| 48 | * |
||
| 49 | * @var char[] |
||
| 50 | */ |
||
| 51 | private $_text; |
||
| 52 | |||
| 53 | /** |
||
| 54 | * Length of text being parsed |
||
| 55 | * |
||
| 56 | * @var int |
||
| 57 | */ |
||
| 58 | private $_textLen; |
||
| 59 | |||
| 60 | /** |
||
| 61 | * Position on text being parsed |
||
| 62 | * |
||
| 63 | * @var int |
||
| 64 | */ |
||
| 65 | private $_textPos; |
||
| 66 | |||
| 67 | /** |
||
| 68 | * Character being processed |
||
| 69 | * |
||
| 70 | * @var char |
||
| 71 | */ |
||
| 72 | private $_ch; |
||
| 73 | |||
| 74 | /** |
||
| 75 | * ExpressionToken being processed |
||
| 76 | * |
||
| 77 | * @var ExpressionToken |
||
| 78 | */ |
||
| 79 | private $_token; |
||
| 80 | |||
| 81 | /** |
||
| 82 | * Initialize a new instance of ExpressionLexer |
||
| 83 | * |
||
| 84 | * @param string $expression Expression to parse |
||
| 85 | */ |
||
| 86 | public function __construct($expression) |
||
| 94 | |||
| 95 | /** |
||
| 96 | * To get the expression token being processed |
||
| 97 | * |
||
| 98 | * @return ExpressionToken |
||
| 99 | */ |
||
| 100 | public function getCurrentToken() |
||
| 104 | |||
| 105 | /** |
||
| 106 | * To set the token being processed |
||
| 107 | * |
||
| 108 | * @param ExpressionToken $token The expression token to set as current |
||
| 109 | * |
||
| 110 | * @return void |
||
| 111 | */ |
||
| 112 | public function setCurrentToken($token) |
||
| 116 | |||
| 117 | /** |
||
| 118 | * To get the text being parsed |
||
| 119 | * |
||
| 120 | * @return string |
||
| 121 | */ |
||
| 122 | public function getExpressionText() |
||
| 126 | |||
| 127 | /** |
||
| 128 | * Position of the current token in the text being parsed |
||
| 129 | * |
||
| 130 | * @return int |
||
| 131 | */ |
||
| 132 | public function getPosition() |
||
| 136 | |||
| 137 | /** |
||
| 138 | * Whether the specified token identifier is a numeric literal |
||
| 139 | * |
||
| 140 | * @param ExpressionTokenId $id Token identifier to check |
||
| 141 | * |
||
| 142 | * @return bool true if it's a numeric literal; false otherwise |
||
| 143 | */ |
||
| 144 | public static function isNumeric($id) |
||
| 153 | |||
| 154 | /** |
||
| 155 | * Reads the next token, skipping whitespace as necessary. |
||
| 156 | * |
||
| 157 | * @return void |
||
| 158 | */ |
||
| 159 | public function nextToken() |
||
| 298 | |||
| 299 | /** |
||
| 300 | * Returns the next token without advancing the lexer to next token |
||
| 301 | * |
||
| 302 | * @return ExpressionToken |
||
| 303 | */ |
||
| 304 | public function peekNextToken() |
||
| 318 | |||
| 319 | /** |
||
| 320 | * Validates the current token is of the specified kind |
||
| 321 | * |
||
| 322 | * @param ExpressionTokenId $tokenId Expected token kind |
||
| 323 | * |
||
| 324 | * @return void |
||
| 325 | * |
||
| 326 | * @throws ODataException if current token is not of the |
||
| 327 | * specified kind. |
||
| 328 | */ |
||
| 329 | public function validateToken($tokenId) |
||
| 339 | |||
| 340 | /** |
||
| 341 | * Starting from an identifier, reads alternate sequence of dots and identifiers |
||
| 342 | * and returns the text for it |
||
| 343 | * |
||
| 344 | * @return string The dotted identifier starting at the current identifier |
||
| 345 | */ |
||
| 346 | public function readDottedIdentifier() |
||
| 360 | |||
| 361 | /** |
||
| 362 | * Check if the parameter ($tokenText) is INF or NaN |
||
| 363 | * |
||
| 364 | * @param string $tokenText Text to look in |
||
| 365 | * |
||
| 366 | * @return boolean true if match found, false otherwise |
||
| 367 | */ |
||
| 368 | private static function _isInfinityOrNaNDouble($tokenText) |
||
| 380 | |||
| 381 | /** |
||
| 382 | * Check if the parameter ($text) is INF |
||
| 383 | * |
||
| 384 | * @param string $text Text to look in |
||
| 385 | * |
||
| 386 | * @return boolean true if match found, false otherwise |
||
| 387 | */ |
||
| 388 | private static function _isInfinityLiteralDouble($text) |
||
| 392 | |||
| 393 | /** |
||
| 394 | * Checks if the parameter ($tokenText) is INFf/INFF or NaNf/NaNF. |
||
| 395 | * |
||
| 396 | * @param string $tokenText Input token |
||
| 397 | * |
||
| 398 | * @return bool true if match found, false otherwise |
||
| 399 | */ |
||
| 400 | private static function _isInfinityOrNanSingle($tokenText) |
||
| 414 | |||
| 415 | /** |
||
| 416 | * Checks whether parameter ($text) EQUALS to 'INFf' or 'INFF' at position |
||
| 417 | * |
||
| 418 | * @param string $text Text to look in |
||
| 419 | * |
||
| 420 | * @return bool true if the substring is equal using an ordinal comparison; |
||
| 421 | * false otherwise |
||
| 422 | */ |
||
| 423 | private static function _isInfinityLiteralSingle($text) |
||
| 430 | |||
| 431 | /** |
||
| 432 | * Handles the literals that are prefixed by types. |
||
| 433 | * This method modified the token field as necessary. |
||
| 434 | * |
||
| 435 | * @return void |
||
| 436 | * |
||
| 437 | * @throws ODataException |
||
| 438 | */ |
||
| 439 | private function _handleTypePrefixedLiterals() |
||
| 484 | |||
| 485 | /** |
||
| 486 | * Parses a token that starts with a digit |
||
| 487 | * |
||
| 488 | * @return ExpressionTokenId The kind of token recognized. |
||
| 489 | */ |
||
| 490 | private function _parseFromDigit() |
||
| 546 | |||
| 547 | /** |
||
| 548 | * Parses an identifier by advancing the current character. |
||
| 549 | * |
||
| 550 | * @return void |
||
| 551 | */ |
||
| 552 | private function _parseIdentifier() |
||
| 558 | |||
| 559 | /** |
||
| 560 | * Advance to next character. |
||
| 561 | * |
||
| 562 | * @return void |
||
| 563 | */ |
||
| 564 | private function _nextChar() |
||
| 574 | |||
| 575 | /** |
||
| 576 | * Set the text position. |
||
| 577 | * |
||
| 578 | * @param int $pos Value to position. |
||
| 579 | * |
||
| 580 | * @return void |
||
| 581 | */ |
||
| 582 | private function _setTextPos($pos) |
||
| 589 | |||
| 590 | /** |
||
| 591 | * Validate current character is a digit. |
||
| 592 | * |
||
| 593 | * @return void |
||
| 594 | */ |
||
| 595 | private function _validateDigit() |
||
| 605 | |||
| 606 | /** |
||
| 607 | * Throws parser error. |
||
| 608 | * |
||
| 609 | * @param string $message The error message. |
||
| 610 | * |
||
| 611 | * @return void |
||
| 612 | * |
||
| 613 | * @throws ODataException |
||
| 614 | */ |
||
| 615 | private function _parseError($message) |
||
| 619 | } |
Our type inference engine has found an assignment to a property that is incompatible with the declared type of that property.
Either this assignment is in error or the assigned type should be added to the documentation/type hint for that property..