| Total Complexity | 104 |
| Total Lines | 562 |
| Duplicated Lines | 1.42 % |
| Changes | 0 | ||
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 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.
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 |
||
| 28 | class ExpressionLexer |
||
| 29 | { |
||
| 30 | /** |
||
| 31 | * Suffix for single literals. |
||
| 32 | * |
||
| 33 | * @var char |
||
| 34 | */ |
||
| 35 | const SINGLE_SUFFIX_LOWER = 'f'; |
||
| 36 | |||
| 37 | /** |
||
| 38 | * Suffix for single literals. |
||
| 39 | * |
||
| 40 | * @var char |
||
| 41 | */ |
||
| 42 | const SINGLE_SUFFIX_UPPER = 'F'; |
||
| 43 | |||
| 44 | /** |
||
| 45 | * Text being parsed. |
||
| 46 | * |
||
| 47 | * @var string |
||
| 48 | */ |
||
| 49 | private $text; |
||
| 50 | |||
| 51 | /** |
||
| 52 | * Length of text being parsed. |
||
| 53 | * |
||
| 54 | * @var int |
||
| 55 | */ |
||
| 56 | private $textLen; |
||
| 57 | |||
| 58 | /** |
||
| 59 | * Position on text being parsed. |
||
| 60 | * |
||
| 61 | * @var int |
||
| 62 | */ |
||
| 63 | private $textPos; |
||
| 64 | |||
| 65 | /** |
||
| 66 | * Character being processed. |
||
| 67 | * |
||
| 68 | * @var string |
||
| 69 | */ |
||
| 70 | private $ch; |
||
| 71 | |||
| 72 | /** |
||
| 73 | * ExpressionToken being processed. |
||
| 74 | * |
||
| 75 | * @var ExpressionToken |
||
| 76 | */ |
||
| 77 | private $token; |
||
| 78 | |||
| 79 | /** |
||
| 80 | * Initialize a new instance of ExpressionLexer. |
||
| 81 | * |
||
| 82 | * @param string $expression Expression to parse |
||
| 83 | */ |
||
| 84 | public function __construct($expression) |
||
| 85 | { |
||
| 86 | $this->text = $expression; |
||
| 87 | $this->textLen = strlen($this->text); |
||
| 88 | $this->token = new ExpressionToken(); |
||
| 89 | $this->setTextPos(0); |
||
| 90 | $this->nextToken(); |
||
| 91 | } |
||
| 92 | |||
| 93 | /** |
||
| 94 | * To get the expression token being processed. |
||
| 95 | * |
||
| 96 | * @return ExpressionToken |
||
| 97 | */ |
||
| 98 | public function getCurrentToken() |
||
| 99 | { |
||
| 100 | return $this->token; |
||
| 101 | } |
||
| 102 | |||
| 103 | /** |
||
| 104 | * To set the token being processed. |
||
| 105 | * |
||
| 106 | * @param ExpressionToken $token The expression token to set as current |
||
| 107 | */ |
||
| 108 | public function setCurrentToken(ExpressionToken $token) |
||
| 109 | { |
||
| 110 | $this->token = $token; |
||
| 111 | } |
||
| 112 | |||
| 113 | /** |
||
| 114 | * To get the text being parsed. |
||
| 115 | * |
||
| 116 | * @return string |
||
| 117 | */ |
||
| 118 | public function getExpressionText() |
||
| 119 | { |
||
| 120 | return $this->text; |
||
| 121 | } |
||
| 122 | |||
| 123 | /** |
||
| 124 | * Position of the current token in the text being parsed. |
||
| 125 | * |
||
| 126 | * @return int |
||
| 127 | */ |
||
| 128 | public function getPosition() |
||
| 129 | { |
||
| 130 | return $this->token->Position; |
||
| 131 | } |
||
| 132 | |||
| 133 | /** |
||
| 134 | * Whether the specified token identifier is a numeric literal. |
||
| 135 | * |
||
| 136 | * @param ExpressionTokenId $id Token identifier to check |
||
| 137 | * |
||
| 138 | * @return bool true if it's a numeric literal; false otherwise |
||
| 139 | */ |
||
| 140 | public static function isNumeric($id) |
||
| 141 | { |
||
| 142 | return |
||
| 143 | $id == ExpressionTokenId::INTEGER_LITERAL |
||
| 144 | || $id == ExpressionTokenId::DECIMAL_LITERAL |
||
| 145 | || $id == ExpressionTokenId::DOUBLE_LITERAL |
||
| 146 | || $id == ExpressionTokenId::INT64_LITERAL |
||
| 147 | || $id == ExpressionTokenId::SINGLE_LITERAL; |
||
| 148 | } |
||
| 149 | |||
| 150 | /** |
||
| 151 | * Reads the next token, skipping whitespace as necessary. |
||
| 152 | */ |
||
| 153 | public function nextToken() |
||
| 154 | { |
||
| 155 | while (Char::isWhiteSpace($this->ch)) { |
||
| 156 | $this->nextChar(); |
||
| 157 | } |
||
| 158 | |||
| 159 | $t = null; |
||
| 160 | $tokenPos = $this->textPos; |
||
| 161 | switch ($this->ch) { |
||
| 162 | case '(': |
||
| 163 | $this->nextChar(); |
||
| 164 | $t = ExpressionTokenId::OPENPARAM; |
||
| 165 | break; |
||
| 166 | case ')': |
||
| 167 | $this->nextChar(); |
||
| 168 | $t = ExpressionTokenId::CLOSEPARAM; |
||
| 169 | break; |
||
| 170 | case ',': |
||
| 171 | $this->nextChar(); |
||
| 172 | $t = ExpressionTokenId::COMMA; |
||
| 173 | break; |
||
| 174 | case '-': |
||
| 175 | $hasNext = $this->textPos + 1 < $this->textLen; |
||
| 176 | if ($hasNext && Char::isDigit($this->text[$this->textPos + 1])) { |
||
| 177 | $this->nextChar(); |
||
| 178 | $t = $this->parseFromDigit(); |
||
| 179 | if (self::isNumeric($t)) { |
||
| 180 | break; |
||
| 181 | } |
||
| 182 | } elseif ($hasNext && $this->text[$tokenPos + 1] == 'I') { |
||
| 183 | $this->nextChar(); |
||
| 184 | $this->parseIdentifier(); |
||
| 185 | $currentIdentifier = substr($this->text, $tokenPos + 1, $this->textPos - $tokenPos - 1); |
||
| 186 | |||
| 187 | if (self::isInfinityLiteralDouble($currentIdentifier)) { |
||
| 188 | $t = ExpressionTokenId::DOUBLE_LITERAL; |
||
| 189 | break; |
||
| 190 | } elseif (self::isInfinityLiteralSingle($currentIdentifier)) { |
||
| 191 | $t = ExpressionTokenId::SINGLE_LITERAL; |
||
| 192 | break; |
||
| 193 | } |
||
| 194 | |||
| 195 | // If it looked like '-INF' but wasn't we'll rewind and fall through to a simple '-' token. |
||
| 196 | } |
||
| 197 | $this->setTextPos($tokenPos); |
||
| 198 | $this->nextChar(); |
||
| 199 | $t = ExpressionTokenId::MINUS; |
||
| 200 | break; |
||
| 201 | case '=': |
||
| 202 | $this->nextChar(); |
||
| 203 | $t = ExpressionTokenId::EQUAL; |
||
| 204 | break; |
||
| 205 | case '/': |
||
| 206 | $this->nextChar(); |
||
| 207 | $t = ExpressionTokenId::SLASH; |
||
| 208 | break; |
||
| 209 | case '?': |
||
| 210 | $this->nextChar(); |
||
| 211 | $t = ExpressionTokenId::QUESTION; |
||
| 212 | break; |
||
| 213 | case '.': |
||
| 214 | $this->nextChar(); |
||
| 215 | $t = ExpressionTokenId::DOT; |
||
| 216 | break; |
||
| 217 | case '\'': |
||
| 218 | $quote = $this->ch; |
||
| 219 | do { |
||
| 220 | $this->nextChar(); |
||
| 221 | while ($this->textPos < $this->textLen && $this->ch != $quote) { |
||
| 222 | $this->nextChar(); |
||
| 223 | } |
||
| 224 | |||
| 225 | if ($this->textPos == $this->textLen) { |
||
| 226 | $this->parseError( |
||
| 227 | Messages::expressionLexerUnterminatedStringLiteral( |
||
| 228 | $this->textPos, |
||
| 229 | $this->text |
||
| 230 | ) |
||
| 231 | ); |
||
| 232 | } |
||
| 233 | |||
| 234 | $this->nextChar(); |
||
| 235 | } while ($this->ch == $quote); |
||
| 236 | $t = ExpressionTokenId::STRING_LITERAL; |
||
| 237 | break; |
||
| 238 | case '*': |
||
| 239 | $this->nextChar(); |
||
| 240 | $t = ExpressionTokenId::STAR; |
||
| 241 | break; |
||
| 242 | default: |
||
| 243 | if (Char::isLetter($this->ch) || $this->ch == '_') { |
||
| 244 | $this->parseIdentifier(); |
||
| 245 | $t = ExpressionTokenId::IDENTIFIER; |
||
| 246 | break; |
||
| 247 | } |
||
| 248 | |||
| 249 | if (Char::isDigit($this->ch)) { |
||
| 250 | $t = $this->parseFromDigit(); |
||
| 251 | break; |
||
| 252 | } |
||
| 253 | |||
| 254 | if ($this->textPos == $this->textLen) { |
||
| 255 | $t = ExpressionTokenId::END; |
||
| 256 | break; |
||
| 257 | } |
||
| 258 | |||
| 259 | $this->parseError( |
||
| 260 | Messages::expressionLexerInvalidCharacter( |
||
| 261 | $this->ch, |
||
| 262 | $this->textPos |
||
| 263 | ) |
||
| 264 | ); |
||
| 265 | } |
||
| 266 | |||
| 267 | $this->token->Id = $t; |
||
| 268 | $this->token->Text = substr($this->text, $tokenPos, $this->textPos - $tokenPos); |
||
| 269 | $this->token->Position = $tokenPos; |
||
| 270 | |||
| 271 | // Handle type-prefixed literals such as binary, datetime or guid. |
||
| 272 | $this->handleTypePrefixedLiterals(); |
||
| 273 | |||
| 274 | // Handle keywords. |
||
| 275 | if ($this->token->Id == ExpressionTokenId::IDENTIFIER) { |
||
| 276 | if (self::isInfinityOrNaNDouble($this->token->Text)) { |
||
| 277 | $this->token->Id = ExpressionTokenId::DOUBLE_LITERAL; |
||
| 278 | } elseif (self::isInfinityOrNanSingle($this->token->Text)) { |
||
| 279 | $this->token->Id = ExpressionTokenId::SINGLE_LITERAL; |
||
| 280 | } elseif ($this->token->Text == ODataConstants::KEYWORD_TRUE |
||
| 281 | || $this->token->Text == ODataConstants::KEYWORD_FALSE |
||
| 282 | ) { |
||
| 283 | $this->token->Id = ExpressionTokenId::BOOLEAN_LITERAL; |
||
| 284 | } elseif ($this->token->Text == ODataConstants::KEYWORD_NULL) { |
||
| 285 | $this->token->Id = ExpressionTokenId::NULL_LITERAL; |
||
| 286 | } |
||
| 287 | } |
||
| 288 | } |
||
| 289 | |||
| 290 | /** |
||
| 291 | * Returns the next token without advancing the lexer to next token. |
||
| 292 | * |
||
| 293 | * @return ExpressionToken |
||
| 294 | */ |
||
| 295 | public function peekNextToken() |
||
| 310 | } |
||
| 311 | |||
| 312 | /** |
||
| 313 | * Validates the current token is of the specified kind. |
||
| 314 | * |
||
| 315 | * @param ExpressionTokenId $tokenId Expected token kind |
||
| 316 | * |
||
| 317 | * @throws ODataException if current token is not of the |
||
| 318 | * specified kind |
||
| 319 | */ |
||
| 320 | public function validateToken($tokenId) |
||
| 321 | { |
||
| 322 | if ($this->token->Id != $tokenId) { |
||
| 323 | $this->parseError(Messages::expressionLexerSyntaxError($this->textPos)); |
||
| 324 | } |
||
| 325 | } |
||
| 326 | |||
| 327 | /** |
||
| 328 | * Starting from an identifier, reads alternate sequence of dots and identifiers |
||
| 329 | * and returns the text for it. |
||
| 330 | * |
||
| 331 | * @return string The dotted identifier starting at the current identifier |
||
| 332 | */ |
||
| 333 | public function readDottedIdentifier() |
||
| 334 | { |
||
| 335 | $this->validateToken(ExpressionTokenId::IDENTIFIER); |
||
| 336 | $identifier = $this->token->Text; |
||
| 337 | $this->nextToken(); |
||
| 338 | while ($this->token->Id == ExpressionTokenId::DOT) { |
||
| 339 | $this->nextToken(); |
||
| 340 | $this->validateToken(ExpressionTokenId::IDENTIFIER); |
||
| 341 | $identifier = $identifier . '.' . $this->token->Text; |
||
| 342 | $this->nextToken(); |
||
| 343 | } |
||
| 344 | |||
| 345 | return $identifier; |
||
| 346 | } |
||
| 347 | |||
| 348 | /** |
||
| 349 | * Check if the parameter ($tokenText) is INF or NaN. |
||
| 350 | * |
||
| 351 | * @param string $tokenText Text to look in |
||
| 352 | * |
||
| 353 | * @return bool true if match found, false otherwise |
||
| 354 | */ |
||
| 355 | private static function isInfinityOrNaNDouble($tokenText) |
||
| 356 | { |
||
| 357 | if (strlen($tokenText) == 3) { |
||
| 358 | if ($tokenText[0] == 'I') { |
||
| 359 | return self::isInfinityLiteralDouble($tokenText); |
||
| 360 | } elseif ($tokenText[0] == 'N') { |
||
| 361 | return strncmp($tokenText, ODataConstants::XML_NAN_LITERAL, 3) == 0; |
||
| 362 | } |
||
| 363 | } |
||
| 364 | |||
| 365 | return false; |
||
| 366 | } |
||
| 367 | |||
| 368 | /** |
||
| 369 | * Check if the parameter ($text) is INF. |
||
| 370 | * |
||
| 371 | * @param string $text Text to look in |
||
| 372 | * |
||
| 373 | * @return bool true if match found, false otherwise |
||
| 374 | */ |
||
| 375 | private static function isInfinityLiteralDouble($text) |
||
| 376 | { |
||
| 377 | return strcmp($text, ODataConstants::XML_INFINITY_LITERAL) == 0; |
||
| 378 | } |
||
| 379 | |||
| 380 | /** |
||
| 381 | * Checks if the parameter ($tokenText) is INFf/INFF or NaNf/NaNF. |
||
| 382 | * |
||
| 383 | * @param string $tokenText Input token |
||
| 384 | * |
||
| 385 | * @return bool true if match found, false otherwise |
||
| 386 | */ |
||
| 387 | private static function isInfinityOrNanSingle($tokenText) |
||
| 388 | { |
||
| 389 | if (strlen($tokenText) == 4) { |
||
| 390 | if ($tokenText[0] == 'I') { |
||
| 391 | return self::isInfinityLiteralSingle($tokenText); |
||
| 392 | } elseif ($tokenText[0] == 'N') { |
||
| 393 | return ($tokenText[3] == self::SINGLE_SUFFIX_LOWER |
||
| 394 | || $tokenText[3] == self::SINGLE_SUFFIX_UPPER) |
||
| 395 | && strncmp($tokenText, ODataConstants::XML_NAN_LITERAL, 3) == 0; |
||
| 396 | } |
||
| 397 | } |
||
| 398 | |||
| 399 | return false; |
||
| 400 | } |
||
| 401 | |||
| 402 | /** |
||
| 403 | * Checks whether parameter ($text) EQUALS to 'INFf' or 'INFF' at position. |
||
| 404 | * |
||
| 405 | * @param string $text Text to look in |
||
| 406 | * |
||
| 407 | * @return bool true if the substring is equal using an ordinal comparison; |
||
| 408 | * false otherwise |
||
| 409 | */ |
||
| 410 | private static function isInfinityLiteralSingle($text) |
||
| 411 | { |
||
| 412 | return strlen($text) == 4 |
||
| 413 | && ($text[3] == self::SINGLE_SUFFIX_LOWER |
||
| 414 | || $text[3] == self::SINGLE_SUFFIX_UPPER) |
||
| 415 | && strncmp($text, ODataConstants::XML_INFINITY_LITERAL, 3) == 0; |
||
| 416 | } |
||
| 417 | |||
| 418 | /** |
||
| 419 | * Handles the literals that are prefixed by types. |
||
| 420 | * This method modified the token field as necessary. |
||
| 421 | * |
||
| 422 | * |
||
| 423 | * @throws ODataException |
||
| 424 | */ |
||
| 425 | private function handleTypePrefixedLiterals() |
||
| 426 | { |
||
| 427 | $id = $this->token->Id; |
||
| 428 | if ($id != ExpressionTokenId::IDENTIFIER) { |
||
| 429 | return; |
||
| 430 | } |
||
| 431 | |||
| 432 | $quoteFollows = $this->ch == '\''; |
||
| 433 | if (!$quoteFollows) { |
||
| 434 | return; |
||
| 435 | } |
||
| 436 | |||
| 437 | $tokenText = $this->token->Text; |
||
| 438 | |||
| 439 | if (strcasecmp('datetime', $tokenText) == 0) { |
||
| 440 | $id = ExpressionTokenId::DATETIME_LITERAL; |
||
| 441 | } elseif (strcasecmp('guid', $tokenText) == 0) { |
||
| 442 | $id = ExpressionTokenId::GUID_LITERAL; |
||
| 443 | } elseif (strcasecmp('binary', $tokenText) == 0 |
||
| 444 | || strcasecmp('X', $tokenText) == 0 |
||
| 445 | || strcasecmp('x', $tokenText) == 0 |
||
| 446 | ) { |
||
| 447 | $id = ExpressionTokenId::BINARY_LITERAL; |
||
| 448 | } else { |
||
| 449 | return; |
||
| 450 | } |
||
| 451 | |||
| 452 | $tokenPos = $this->token->Position; |
||
| 453 | do { |
||
| 454 | $this->nextChar(); |
||
| 455 | } while ($this->ch != '\0' && $this->ch != '\''); |
||
| 456 | |||
| 457 | if ($this->ch == '\0') { |
||
| 458 | $this->parseError( |
||
| 459 | Messages::expressionLexerUnterminatedStringLiteral( |
||
| 460 | $this->textPos, |
||
| 461 | $this->text |
||
| 462 | ) |
||
| 463 | ); |
||
| 464 | } |
||
| 465 | |||
| 466 | $this->nextChar(); |
||
| 467 | $this->token->Id = $id; |
||
| 468 | $this->token->Text |
||
| 469 | = substr($this->text, $tokenPos, $this->textPos - $tokenPos); |
||
| 470 | } |
||
| 471 | |||
| 472 | /** |
||
| 473 | * Parses a token that starts with a digit. |
||
| 474 | * |
||
| 475 | * @return ExpressionTokenId The kind of token recognized |
||
| 476 | */ |
||
| 477 | private function parseFromDigit() |
||
| 531 | } |
||
| 532 | |||
| 533 | /** |
||
| 534 | * Parses an identifier by advancing the current character. |
||
| 535 | */ |
||
| 536 | private function parseIdentifier() |
||
| 537 | { |
||
| 538 | do { |
||
| 539 | $this->nextChar(); |
||
| 540 | } while (Char::isLetterOrDigit($this->ch) || $this->ch == '_'); |
||
| 541 | } |
||
| 542 | |||
| 543 | /** |
||
| 544 | * Advance to next character. |
||
| 545 | */ |
||
| 546 | private function nextChar() |
||
| 547 | { |
||
| 548 | if ($this->textPos < $this->textLen) { |
||
| 549 | ++$this->textPos; |
||
| 550 | } |
||
| 551 | |||
| 552 | $nextChar = $this->textPos < $this->textLen ? $this->text[$this->textPos] : '\0'; |
||
| 553 | assert(2 >= strlen($nextChar)); |
||
| 554 | $this->ch = $nextChar; |
||
| 555 | } |
||
| 556 | |||
| 557 | /** |
||
| 558 | * Set the text position. |
||
| 559 | * |
||
| 560 | * @param int $pos Value to position |
||
| 561 | */ |
||
| 562 | private function setTextPos($pos) |
||
| 563 | { |
||
| 564 | $this->textPos = $pos; |
||
| 565 | $nextChar = $this->textPos < $this->textLen ? $this->text[$this->textPos] : '\0'; |
||
| 566 | assert(2 >= strlen($nextChar)); |
||
| 567 | $this->ch = $nextChar; |
||
| 568 | } |
||
| 569 | |||
| 570 | /** |
||
| 571 | * Validate current character is a digit. |
||
| 572 | */ |
||
| 573 | private function validateDigit() |
||
| 577 | } |
||
| 578 | } |
||
| 579 | |||
| 580 | /** |
||
| 581 | * Throws parser error. |
||
| 582 | * |
||
| 583 | * @param string $message The error message |
||
| 584 | * |
||
| 585 | * @throws ODataException |
||
| 586 | */ |
||
| 587 | private function parseError($message) |
||
| 590 | } |
||
| 591 | } |
||
| 592 |
The issue could also be caused by a filter entry in the build configuration. If the path has been excluded in your configuration, e.g.
excluded_paths: ["lib/*"], you can move it to the dependency path list as follows:For further information see https://scrutinizer-ci.com/docs/tools/php/php-scrutinizer/#list-dependency-paths