| Total Complexity | 57 |
| Total Lines | 536 |
| Duplicated Lines | 0 % |
| Changes | 7 | ||
| Bugs | 0 | Features | 0 |
Complex classes like Mailcode_Parser_Statement_Tokenizer 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 Mailcode_Parser_Statement_Tokenizer, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 27 | class Mailcode_Parser_Statement_Tokenizer |
||
| 28 | { |
||
| 29 | public const ERROR_TOKENIZE_METHOD_MISSING = 49801; |
||
| 30 | public const ERROR_INVALID_TOKEN_CREATED = 49802; |
||
| 31 | public const ERROR_INVALID_TOKEN_CLASS = 49803; |
||
| 32 | public const ERROR_TARGET_INSERT_TOKEN_NOT_FOUND = 49804; |
||
| 33 | |||
| 34 | /** |
||
| 35 | * @var string[] |
||
| 36 | */ |
||
| 37 | protected array $tokenClasses = array( |
||
| 38 | Mailcode_Parser_Statement_Tokenizer_Process_LegacySyntaxConversion::class, |
||
| 39 | Mailcode_Parser_Statement_Tokenizer_Process_Variables::class, |
||
| 40 | Mailcode_Parser_Statement_Tokenizer_Process_NormalizeQuotes::class, |
||
| 41 | Mailcode_Parser_Statement_Tokenizer_Process_EncodeSpecialChars::class, |
||
| 42 | Mailcode_Parser_Statement_Tokenizer_Process_Keywords::class, |
||
| 43 | // Must be before named parameters to exclude equal signs in strings |
||
| 44 | Mailcode_Parser_Statement_Tokenizer_Process_StringLiterals::class, |
||
| 45 | // Must be before numbers, because named parameters can contain numbers |
||
| 46 | Mailcode_Parser_Statement_Tokenizer_Process_NamedParameters::class, |
||
| 47 | Mailcode_Parser_Statement_Tokenizer_Process_Numbers::class, |
||
| 48 | Mailcode_Parser_Statement_Tokenizer_Process_Operands::class, |
||
| 49 | Mailcode_Parser_Statement_Tokenizer_Process_ExtractTokens::class, |
||
| 50 | // Must be at the end when all tokens have been determined |
||
| 51 | Mailcode_Parser_Statement_Tokenizer_Process_SetNames::class, |
||
| 52 | ); |
||
| 53 | |||
| 54 | /** |
||
| 55 | * @var Mailcode_Parser_Statement |
||
| 56 | */ |
||
| 57 | protected Mailcode_Parser_Statement $statement; |
||
| 58 | |||
| 59 | /** |
||
| 60 | * @var string |
||
| 61 | */ |
||
| 62 | protected string $tokenized = ''; |
||
| 63 | |||
| 64 | /** |
||
| 65 | * @var Mailcode_Parser_Statement_Tokenizer_Token[] |
||
| 66 | */ |
||
| 67 | protected array $tokensOrdered = array(); |
||
| 68 | |||
| 69 | /** |
||
| 70 | * @var string[] |
||
| 71 | */ |
||
| 72 | protected static array $ids = array(); |
||
| 73 | |||
| 74 | /** |
||
| 75 | * @var callable[] |
||
| 76 | */ |
||
| 77 | protected array $changeHandlers = array(); |
||
| 78 | |||
| 79 | private EventHandler $eventHandler; |
||
| 80 | |||
| 81 | public function __construct(Mailcode_Parser_Statement $statement) |
||
| 82 | { |
||
| 83 | $this->statement = $statement; |
||
| 84 | $this->eventHandler = new EventHandler($this); |
||
| 85 | |||
| 86 | $this->tokenize($statement->getStatementString()); |
||
| 87 | } |
||
| 88 | |||
| 89 | public function getSourceCommand() : ?Mailcode_Commands_Command |
||
| 90 | { |
||
| 91 | return $this->statement->getSourceCommand(); |
||
| 92 | } |
||
| 93 | |||
| 94 | /** |
||
| 95 | * Retrieves all tokens detected in the statement string, in |
||
| 96 | * the order they were found. |
||
| 97 | * |
||
| 98 | * @return Mailcode_Parser_Statement_Tokenizer_Token[] |
||
| 99 | */ |
||
| 100 | public function getTokens() : array |
||
| 101 | { |
||
| 102 | return $this->tokensOrdered; |
||
| 103 | } |
||
| 104 | |||
| 105 | public function hasTokens() : bool |
||
| 106 | { |
||
| 107 | return !empty($this->tokensOrdered); |
||
| 108 | } |
||
| 109 | |||
| 110 | /** |
||
| 111 | * Whether there were any unknown tokens in the statement. |
||
| 112 | * |
||
| 113 | * @return bool |
||
| 114 | */ |
||
| 115 | public function hasUnknown() : bool |
||
| 116 | { |
||
| 117 | $unknown = $this->getUnknown(); |
||
| 118 | |||
| 119 | return !empty($unknown); |
||
| 120 | } |
||
| 121 | |||
| 122 | /** |
||
| 123 | * Retrieves all unknown content tokens, if any. |
||
| 124 | * |
||
| 125 | * @return Mailcode_Parser_Statement_Tokenizer_Token_Unknown[] |
||
| 126 | */ |
||
| 127 | public function getUnknown() : array |
||
| 128 | { |
||
| 129 | $result = array(); |
||
| 130 | |||
| 131 | foreach($this->tokensOrdered as $token) |
||
| 132 | { |
||
| 133 | if($token instanceof Mailcode_Parser_Statement_Tokenizer_Token_Unknown) |
||
| 134 | { |
||
| 135 | $result[] = $token; |
||
| 136 | } |
||
| 137 | } |
||
| 138 | |||
| 139 | return $result; |
||
| 140 | } |
||
| 141 | |||
| 142 | public function getFirstUnknown() : ?Mailcode_Parser_Statement_Tokenizer_Token_Unknown |
||
| 143 | { |
||
| 144 | $unknown = $this->getUnknown(); |
||
| 145 | |||
| 146 | if(!empty($unknown)) |
||
| 147 | { |
||
| 148 | return array_shift($unknown); |
||
| 149 | } |
||
| 150 | |||
| 151 | return null; |
||
| 152 | } |
||
| 153 | |||
| 154 | public function getNormalized() : string |
||
| 155 | { |
||
| 156 | $parts = array(); |
||
| 157 | |||
| 158 | foreach($this->tokensOrdered as $token) |
||
| 159 | { |
||
| 160 | $string = $token->getNormalized(); |
||
| 161 | |||
| 162 | if($string === '') { |
||
| 163 | continue; |
||
| 164 | } |
||
| 165 | |||
| 166 | // Only add spaces between tokens if they require spacing |
||
| 167 | if($token->hasSpacing()) { |
||
| 168 | $string .= ' '; |
||
| 169 | } |
||
| 170 | |||
| 171 | $parts[] = $string; |
||
| 172 | } |
||
| 173 | |||
| 174 | return trim(implode('', $parts)); |
||
| 175 | } |
||
| 176 | |||
| 177 | /** |
||
| 178 | * Goes through all tokenization processors, in the order that |
||
| 179 | * they are defined in the tokenCategories property. This filters |
||
| 180 | * the statement string, and extracts the tokens contained within. |
||
| 181 | * |
||
| 182 | * @param string $statement |
||
| 183 | * |
||
| 184 | * @throws Mailcode_Parser_Exception |
||
| 185 | * |
||
| 186 | * @see Mailcode_Parser_Statement_Tokenizer_Process |
||
| 187 | */ |
||
| 188 | protected function tokenize(string $statement) : void |
||
| 189 | { |
||
| 190 | $statement = trim($statement); |
||
| 191 | $tokens = array(); |
||
| 192 | |||
| 193 | foreach($this->tokenClasses as $tokenClass) |
||
| 194 | { |
||
| 195 | $processor = $this->createProcessor($tokenClass, $statement, $tokens); |
||
| 196 | $processor->process(); |
||
| 197 | |||
| 198 | $statement = $processor->getStatement(); |
||
| 199 | $tokens = $processor->getTokens(); |
||
| 200 | } |
||
| 201 | |||
| 202 | $this->tokenized = $statement; |
||
| 203 | $this->tokensOrdered = $tokens; |
||
| 204 | } |
||
| 205 | |||
| 206 | /** |
||
| 207 | * @param string $className |
||
| 208 | * @param string $statement |
||
| 209 | * @param Mailcode_Parser_Statement_Tokenizer_Token[] $tokens |
||
| 210 | * @return Mailcode_Parser_Statement_Tokenizer_Process |
||
| 211 | * @throws Mailcode_Parser_Exception |
||
| 212 | */ |
||
| 213 | protected function createProcessor(string $className, string $statement, array $tokens) : Mailcode_Parser_Statement_Tokenizer_Process |
||
| 214 | { |
||
| 215 | $instance = new $className($this, $statement, $tokens); |
||
| 216 | |||
| 217 | if($instance instanceof Mailcode_Parser_Statement_Tokenizer_Process) |
||
| 218 | { |
||
| 219 | return $instance; |
||
| 220 | } |
||
| 221 | |||
| 222 | throw new Mailcode_Parser_Exception( |
||
| 223 | 'Unknown statement token.', |
||
| 224 | sprintf( |
||
| 225 | 'The tokenize class [%s] does not extend the base process class.', |
||
| 226 | $className |
||
| 227 | ), |
||
| 228 | self::ERROR_TOKENIZE_METHOD_MISSING |
||
| 229 | ); |
||
| 230 | } |
||
| 231 | |||
| 232 | /** |
||
| 233 | * @param string $type |
||
| 234 | * @param string $matchedText |
||
| 235 | * @param mixed $subject |
||
| 236 | * @return Mailcode_Parser_Statement_Tokenizer_Token |
||
| 237 | */ |
||
| 238 | public function createToken(string $type, string $matchedText, $subject=null) : Mailcode_Parser_Statement_Tokenizer_Token |
||
| 239 | { |
||
| 240 | $tokenID = $this->generateID(); |
||
| 241 | |||
| 242 | $class = Mailcode_Parser_Statement_Tokenizer_Token::class.'_'.$type; |
||
| 243 | |||
| 244 | $token = new $class($tokenID, $matchedText, $subject, $this->getSourceCommand()); |
||
| 245 | |||
| 246 | if($token instanceof Mailcode_Parser_Statement_Tokenizer_Token) |
||
| 247 | { |
||
| 248 | return $token; |
||
| 249 | } |
||
| 250 | |||
| 251 | throw new Mailcode_Parser_Exception( |
||
| 252 | 'Invalid token class', |
||
| 253 | sprintf( |
||
| 254 | 'The class [%s] does not extend the base token class.', |
||
| 255 | get_class($token) |
||
| 256 | ), |
||
| 257 | self::ERROR_INVALID_TOKEN_CLASS |
||
| 258 | ); |
||
| 259 | } |
||
| 260 | |||
| 261 | private function createVariable(Mailcode_Variables_Variable $variable) : Mailcode_Parser_Statement_Tokenizer_Token_Variable |
||
| 262 | { |
||
| 263 | return ClassHelper::requireObjectInstanceOf( |
||
| 264 | Mailcode_Parser_Statement_Tokenizer_Token_Variable::class, |
||
| 265 | $this->createToken('Variable', dollarize($variable->getFullName()), $variable) |
||
| 266 | ); |
||
| 267 | } |
||
| 268 | |||
| 269 | private function createKeyword(string $name) : Mailcode_Parser_Statement_Tokenizer_Token_Keyword |
||
| 270 | { |
||
| 271 | $name = rtrim($name, ':').':'; |
||
| 272 | |||
| 273 | $token = $this->createToken('Keyword', $name); |
||
| 274 | |||
| 275 | if($token instanceof Mailcode_Parser_Statement_Tokenizer_Token_Keyword) |
||
|
|
|||
| 276 | { |
||
| 277 | return $token; |
||
| 278 | } |
||
| 279 | |||
| 280 | throw new Mailcode_Parser_Exception( |
||
| 281 | 'Invalid token created', |
||
| 282 | '', |
||
| 283 | self::ERROR_INVALID_TOKEN_CREATED |
||
| 284 | ); |
||
| 285 | } |
||
| 286 | |||
| 287 | public function appendKeyword(string $name) : Mailcode_Parser_Statement_Tokenizer_Token_Keyword |
||
| 288 | { |
||
| 289 | $token = $this->createKeyword($name); |
||
| 290 | |||
| 291 | $this->appendToken($token); |
||
| 292 | |||
| 293 | return $token; |
||
| 294 | } |
||
| 295 | |||
| 296 | private function createStringLiteral(string $text) : Mailcode_Parser_Statement_Tokenizer_Token_StringLiteral |
||
| 297 | { |
||
| 298 | $token = $this->createToken('StringLiteral', SpecialChars::encodeAll($text)); |
||
| 299 | |||
| 300 | if($token instanceof Mailcode_Parser_Statement_Tokenizer_Token_StringLiteral) |
||
| 301 | { |
||
| 302 | return $token; |
||
| 303 | } |
||
| 304 | |||
| 305 | throw new Mailcode_Parser_Exception( |
||
| 306 | 'Invalid token created', |
||
| 307 | '', |
||
| 308 | self::ERROR_INVALID_TOKEN_CREATED |
||
| 309 | ); |
||
| 310 | } |
||
| 311 | |||
| 312 | private function createNumber(string $number) : Mailcode_Parser_Statement_Tokenizer_Token_Number |
||
| 313 | { |
||
| 314 | $token = $this->createToken('Number', $number); |
||
| 315 | |||
| 316 | if($token instanceof Mailcode_Parser_Statement_Tokenizer_Token_Number) |
||
| 317 | { |
||
| 318 | return $token; |
||
| 319 | } |
||
| 320 | |||
| 321 | throw new Mailcode_Parser_Exception( |
||
| 322 | 'Invalid token created', |
||
| 323 | '', |
||
| 324 | self::ERROR_INVALID_TOKEN_CREATED |
||
| 325 | ); |
||
| 326 | } |
||
| 327 | |||
| 328 | public function appendStringLiteral(string $text) : Mailcode_Parser_Statement_Tokenizer_Token_StringLiteral |
||
| 329 | { |
||
| 330 | $token = $this->createStringLiteral($text); |
||
| 331 | |||
| 332 | $this->appendToken($token); |
||
| 333 | |||
| 334 | return $token; |
||
| 335 | } |
||
| 336 | |||
| 337 | public function appendNumber(string $number) : Mailcode_Parser_Statement_Tokenizer_Token_Number |
||
| 338 | { |
||
| 339 | $token = $this->createNumber($number); |
||
| 340 | |||
| 341 | $this->appendToken($token); |
||
| 342 | |||
| 343 | return $token; |
||
| 344 | } |
||
| 345 | |||
| 346 | public function prependStringLiteral(string $text) : Mailcode_Parser_Statement_Tokenizer_Token_StringLiteral |
||
| 347 | { |
||
| 348 | $token = $this->createStringLiteral($text); |
||
| 349 | |||
| 350 | $this->prependToken($token); |
||
| 351 | |||
| 352 | return $token; |
||
| 353 | } |
||
| 354 | |||
| 355 | public function removeToken(Mailcode_Parser_Statement_Tokenizer_Token $token) : Mailcode_Parser_Statement_Tokenizer |
||
| 356 | { |
||
| 357 | $name = $this->findNameToken($token); |
||
| 358 | if($name !== null) { |
||
| 359 | $this->removeToken($name); |
||
| 360 | } |
||
| 361 | |||
| 362 | $keep = array(); |
||
| 363 | $tokenID = $token->getID(); |
||
| 364 | $removed = false; |
||
| 365 | |||
| 366 | foreach ($this->tokensOrdered as $checkToken) |
||
| 367 | { |
||
| 368 | if($checkToken->getID() === $tokenID) |
||
| 369 | { |
||
| 370 | $removed = true; |
||
| 371 | continue; |
||
| 372 | } |
||
| 373 | |||
| 374 | $keep[] = $checkToken; |
||
| 375 | } |
||
| 376 | |||
| 377 | $this->tokensOrdered = $keep; |
||
| 378 | |||
| 379 | if($removed) |
||
| 380 | { |
||
| 381 | $this->eventHandler->handleTokenRemoved($token); |
||
| 382 | } |
||
| 383 | |||
| 384 | return $this; |
||
| 385 | } |
||
| 386 | |||
| 387 | /** |
||
| 388 | * @param Mailcode_Parser_Statement_Tokenizer_Token $token |
||
| 389 | * @return $this |
||
| 390 | */ |
||
| 391 | protected function appendToken(Mailcode_Parser_Statement_Tokenizer_Token $token) : self |
||
| 392 | { |
||
| 393 | $this->tokensOrdered[] = $token; |
||
| 394 | |||
| 395 | $this->eventHandler->handleTokenAppended($token); |
||
| 396 | |||
| 397 | return $this; |
||
| 398 | } |
||
| 399 | |||
| 400 | /** |
||
| 401 | * @param Mailcode_Parser_Statement_Tokenizer_Token $token |
||
| 402 | * @return $this |
||
| 403 | */ |
||
| 404 | protected function prependToken(Mailcode_Parser_Statement_Tokenizer_Token $token) : self |
||
| 405 | { |
||
| 406 | array_unshift($this->tokensOrdered, $token); |
||
| 407 | |||
| 408 | $this->eventHandler->handleTokenPrepended($token); |
||
| 409 | |||
| 410 | return $this; |
||
| 411 | } |
||
| 412 | |||
| 413 | /** |
||
| 414 | * Generates a unique alphabet-based ID without numbers |
||
| 415 | * to use as token name, to avoid conflicts with the |
||
| 416 | * numbers detection. |
||
| 417 | * |
||
| 418 | * @return string |
||
| 419 | */ |
||
| 420 | protected function generateID() : string |
||
| 421 | { |
||
| 422 | static $alphas; |
||
| 423 | |||
| 424 | if(!isset($alphas)) |
||
| 425 | { |
||
| 426 | $alphas = range('A', 'Z'); |
||
| 427 | } |
||
| 428 | |||
| 429 | $amount = 12; |
||
| 430 | |||
| 431 | $result = ''; |
||
| 432 | |||
| 433 | for($i=0; $i < $amount; $i++) |
||
| 434 | { |
||
| 435 | $result .= $alphas[array_rand($alphas)]; |
||
| 436 | } |
||
| 437 | |||
| 438 | if(!in_array($result, self::$ids)) |
||
| 439 | { |
||
| 440 | self::$ids[] = $result; |
||
| 441 | return $result; |
||
| 442 | } |
||
| 443 | |||
| 444 | return $this->generateID(); |
||
| 445 | } |
||
| 446 | |||
| 447 | /** |
||
| 448 | * @param callable $callback |
||
| 449 | */ |
||
| 450 | public function onTokensChanged(callable $callback) : void |
||
| 451 | { |
||
| 452 | $this->changeHandlers[] = $callback; |
||
| 453 | } |
||
| 454 | |||
| 455 | /** |
||
| 456 | * @return EventHandler |
||
| 457 | */ |
||
| 458 | public function getEventHandler() : EventHandler |
||
| 461 | } |
||
| 462 | |||
| 463 | public function appendVariable(Mailcode_Variables_Variable $variable) : Mailcode_Parser_Statement_Tokenizer_Token_Variable |
||
| 464 | { |
||
| 465 | $token = $this->createVariable($variable); |
||
| 466 | $this->appendToken($token); |
||
| 467 | return $token; |
||
| 468 | } |
||
| 469 | |||
| 470 | public function findNameToken(Mailcode_Parser_Statement_Tokenizer_Token $targetToken) : ?Mailcode_Parser_Statement_Tokenizer_Token_ParamName |
||
| 487 | } |
||
| 488 | |||
| 489 | /** |
||
| 490 | * Injects a parameter name token into the statement, before |
||
| 491 | * the target token. Existing parameter names are replaced. |
||
| 492 | * |
||
| 493 | * @param Mailcode_Parser_Statement_Tokenizer_Token $targetToken |
||
| 494 | * @param string $name |
||
| 495 | * @return Mailcode_Parser_Statement_Tokenizer_Token_ParamName |
||
| 496 | * |
||
| 497 | * @throws Mailcode_Parser_Exception {@see self::ERROR_TARGET_INSERT_TOKEN_NOT_FOUND} |
||
| 498 | * @throws BaseClassHelperException |
||
| 499 | */ |
||
| 500 | public function injectParamName(Mailcode_Parser_Statement_Tokenizer_Token $targetToken, string $name) : Mailcode_Parser_Statement_Tokenizer_Token_ParamName |
||
| 516 | } |
||
| 517 | |||
| 518 | public function insertBefore(Mailcode_Parser_Statement_Tokenizer_Token $targetToken, Mailcode_Parser_Statement_Tokenizer_Token $newToken) : self |
||
| 519 | { |
||
| 520 | $targetID = $targetToken->getID(); |
||
| 521 | $tokens = array(); |
||
| 522 | $found = false; |
||
| 523 | |||
| 524 | foreach($this->tokensOrdered as $token) |
||
| 525 | { |
||
| 526 | if($token->getID() === $targetID) |
||
| 527 | { |
||
| 528 | $tokens[] = $newToken; |
||
| 529 | $found = true; |
||
| 530 | } |
||
| 531 | |||
| 532 | $tokens[] = $token; |
||
| 533 | } |
||
| 534 | |||
| 535 | if($found) { |
||
| 536 | $this->tokensOrdered = $tokens; |
||
| 537 | |||
| 538 | return $this; |
||
| 539 | } |
||
| 540 | |||
| 541 | throw new Mailcode_Parser_Exception( |
||
| 542 | 'Could not find target token for insertion.', |
||
| 543 | sprintf( |
||
| 544 | 'The token [%s] was not found in the statement [%s].', |
||
| 545 | $targetToken->getNormalized(), |
||
| 546 | $this->getNormalized() |
||
| 547 | ), |
||
| 548 | self::ERROR_TARGET_INSERT_TOKEN_NOT_FOUND |
||
| 549 | ); |
||
| 550 | } |
||
| 551 | |||
| 552 | private function dumpTokens() : void |
||
| 563 | } |
||
| 564 | } |
||
| 565 | } |
||
| 566 |