| Total Complexity | 46 |
| Total Lines | 326 |
| Duplicated Lines | 0 % |
| Changes | 0 | ||
Complex classes like TokenReader 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 TokenReader, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 7 | class TokenReader implements TokenReaderInterface |
||
| 8 | { |
||
| 9 | protected const PATTERN_COMMENT = "/#[\u{0009}\u{0020}-\u{FFFF}]*/A"; |
||
| 10 | protected const PATTERN_NAME = '/[_A-Za-z][_0-9A-Za-z]*/A'; |
||
| 11 | protected const PATTERN_INT = '/((?!\.)(-?(0|[1-9][0-9]*)))+$/A'; |
||
| 12 | protected const PATTERN_FLOAT = '/-?(0|[1-9][0-9]*)(\.[0-9]+)?((E|e)(\+|-)?[0-9]+)?/A'; |
||
| 13 | protected const PATTERN_SPREAD = '/\.\.\./A'; |
||
| 14 | protected const PATTERN_STRING = "/\"([^\"\\\u{000A}\u{000D}]|(\\([\u{0020}-\u{FFFF}]|[\"\\/bfnrt]))))*\"/As"; |
||
| 15 | protected const PATTERN_BLOCK_STRING = '/"""("?"?(\\"""|\\(?!=""")|[^"\\]))*"""/As'; |
||
| 16 | protected const PUNCTUATION = '!$&:=@|()[]{}'; |
||
| 17 | |||
| 18 | /** |
||
| 19 | * The lexer owning this token reader. |
||
| 20 | * |
||
| 21 | * @var LexerInterface |
||
| 22 | */ |
||
| 23 | protected $lexer; |
||
| 24 | |||
| 25 | /** |
||
| 26 | * @inheritdoc |
||
| 27 | */ |
||
| 28 | public function setLexer(LexerInterface $lexer) |
||
| 29 | { |
||
| 30 | $this->lexer = $lexer; |
||
| 31 | return $this; |
||
| 32 | } |
||
| 33 | |||
| 34 | /** |
||
| 35 | * @inheritdoc |
||
| 36 | */ |
||
| 37 | public function getLexer(): LexerInterface |
||
| 38 | { |
||
| 39 | return $this->lexer; |
||
| 40 | } |
||
| 41 | |||
| 42 | /** |
||
| 43 | * @inheritdoc |
||
| 44 | * @throws SyntaxErrorException |
||
| 45 | */ |
||
| 46 | public function read(string $body, int $pos, int $line, int $col, Token $prev): ?Token |
||
| 47 | { |
||
| 48 | if (false !== \strpos(self::PUNCTUATION, $body[$pos])) { |
||
| 49 | return $this->createPunctuation($body, $pos, $line, $col, $prev); |
||
| 50 | } |
||
| 51 | |||
| 52 | if (\preg_match(static::PATTERN_COMMENT, $body, $match, null, $pos)) { |
||
| 53 | return $this->createComment($pos, $pos + \mb_strlen($match[0]), $line, $col, $prev, $match[0]); |
||
| 54 | } |
||
| 55 | |||
| 56 | if (\preg_match(static::PATTERN_NAME, $body, $match, null, $pos)) { |
||
| 57 | return $this->createName($pos, $pos + \mb_strlen($match[0]), $line, $col, $prev, $match[0]); |
||
| 58 | } |
||
| 59 | |||
| 60 | if (\preg_match(static::PATTERN_INT, $body, $match, null, $pos)) { |
||
| 61 | return $this->createInt($pos, $pos + \mb_strlen($match[0]), $line, $col, $prev, $match[0]); |
||
| 62 | } |
||
| 63 | |||
| 64 | if (\preg_match(static::PATTERN_FLOAT, $body, $match, null, $pos)) { |
||
| 65 | return $this->createFloat($pos, $pos + \mb_strlen($match[0]), $line, $col, $prev, $match[0]); |
||
| 66 | } |
||
| 67 | |||
| 68 | if (\preg_match(static::PATTERN_SPREAD, $body, $match, null, $pos)) { |
||
| 69 | return $this->createSpread($pos, $pos + 3, $line, $col, $prev); |
||
| 70 | } |
||
| 71 | |||
| 72 | if (\preg_match(static::PATTERN_STRING, $body, $match, null, $pos)) { |
||
| 73 | return $this->createString($pos, $pos + \mb_strlen($match[0]), $line, $col, $prev, $match[0]); |
||
| 74 | } |
||
| 75 | |||
| 76 | if (\preg_match(static::PATTERN_BLOCK_STRING, $body, $match, null, $pos)) { |
||
| 77 | return $this->createBlockString($pos, $pos + \mb_strlen($match[0]), $line, $col, $prev, $match[0]); |
||
| 78 | } |
||
| 79 | |||
| 80 | return null; |
||
| 81 | } |
||
| 82 | |||
| 83 | /** |
||
| 84 | * @param string $kind |
||
| 85 | * @param int $start |
||
| 86 | * @param int $line |
||
| 87 | * @param int $col |
||
| 88 | * @param Token $prev |
||
| 89 | * @param null|string $value |
||
| 90 | * @return Token |
||
| 91 | */ |
||
| 92 | protected function createToken( |
||
| 93 | string $kind, |
||
| 94 | int $start, |
||
| 95 | int $end, |
||
| 96 | int $line, |
||
| 97 | int $col, |
||
| 98 | Token $prev, |
||
| 99 | ?string $value = null |
||
| 100 | ): Token { |
||
| 101 | return new Token($kind, $start, $end, $line, $col, $prev, $value); |
||
| 102 | } |
||
| 103 | |||
| 104 | /** |
||
| 105 | * @param string $body |
||
| 106 | * @param int $pos |
||
| 107 | * @param int $line |
||
| 108 | * @param int $col |
||
| 109 | * @param Token $prev |
||
| 110 | * @return Token |
||
| 111 | */ |
||
| 112 | protected function createPunctuation(string $body, int $pos, int $line, int $col, Token $prev): Token |
||
| 113 | { |
||
| 114 | $code = \ord($body[$pos]); |
||
| 115 | |||
| 116 | switch ($code) { |
||
| 117 | case 33: // ! |
||
| 118 | return $this->createBang($pos, $line, $col, $prev); |
||
| 119 | case 36: // $ |
||
| 120 | return $this->createDollar($pos, $line, $col, $prev); |
||
| 121 | case 38: // & |
||
| 122 | return $this->createAmp($pos, $line, $col, $prev); |
||
| 123 | case 58: // : |
||
| 124 | return $this->createColon($pos, $line, $col, $prev); |
||
| 125 | case 61: // = |
||
| 126 | return $this->createEquals($pos, $line, $col, $prev); |
||
| 127 | case 64: // @ |
||
| 128 | return $this->createAt($pos, $line, $col, $prev); |
||
| 129 | case 124: // | |
||
| 130 | return $this->createPipe($pos, $line, $col, $prev); |
||
| 131 | case 40: |
||
| 132 | case 41: // ( or )~ |
||
| 133 | return $this->createParenthesis($code, $pos, $line, $col, $prev); |
||
| 134 | case 91: |
||
| 135 | case 93: // [ or ] |
||
| 136 | return $this->createBracket($code, $pos, $line, $col, $prev); |
||
| 137 | case 123: |
||
| 138 | case 125: // { or } |
||
| 139 | return $this->createBrace($code, $pos, $line, $col, $prev); |
||
| 140 | } |
||
| 141 | } |
||
| 142 | |||
| 143 | /** |
||
| 144 | * @param int $pos |
||
| 145 | * @param int $line |
||
| 146 | * @param int $col |
||
| 147 | * @param Token $prev |
||
| 148 | * @return Token |
||
| 149 | */ |
||
| 150 | protected function createColon(int $pos, int $line, int $col, Token $prev): Token |
||
| 151 | { |
||
| 152 | return new Token(TokenKindEnum::COLON, $pos, $pos + 1, $line, $col, $prev); |
||
| 153 | } |
||
| 154 | |||
| 155 | /** |
||
| 156 | * @param int $pos |
||
| 157 | * @param int $line |
||
| 158 | * @param int $col |
||
| 159 | * @param Token $prev |
||
| 160 | * @return Token |
||
| 161 | */ |
||
| 162 | protected function createAmp(int $pos, int $line, int $col, Token $prev): Token |
||
| 163 | { |
||
| 164 | return new Token(TokenKindEnum::AMP, $pos, $pos + 1, $line, $col, $prev); |
||
| 165 | } |
||
| 166 | |||
| 167 | /** |
||
| 168 | * @param int $pos |
||
| 169 | * @param int $line |
||
| 170 | * @param int $col |
||
| 171 | * @param Token $prev |
||
| 172 | * @return Token |
||
| 173 | */ |
||
| 174 | protected function createBang(int $pos, int $line, int $col, Token $prev): Token |
||
| 175 | { |
||
| 176 | return new Token(TokenKindEnum::BANG, $pos, $pos + 1, $line, $col, $prev); |
||
| 177 | } |
||
| 178 | |||
| 179 | /** |
||
| 180 | * @param int $code |
||
| 181 | * @param int $pos |
||
| 182 | * @param int $line |
||
| 183 | * @param int $col |
||
| 184 | * @param Token $prev |
||
| 185 | * @return Token |
||
| 186 | */ |
||
| 187 | protected function createBrace(int $code, int $pos, int $line, int $col, Token $prev): Token |
||
| 188 | { |
||
| 189 | return $code === 123 |
||
| 190 | ? new Token(TokenKindEnum::BRACE_L, $pos, $pos + 1, $line, $col, $prev) |
||
| 191 | : new Token(TokenKindEnum::BRACE_R, $pos, $pos + 1, $line, $col, $prev); |
||
| 192 | } |
||
| 193 | |||
| 194 | /** |
||
| 195 | * @param int $code |
||
| 196 | * @param int $pos |
||
| 197 | * @param int $line |
||
| 198 | * @param int $col |
||
| 199 | * @param Token $prev |
||
| 200 | * @return Token |
||
| 201 | */ |
||
| 202 | protected function createBracket(int $code, int $pos, int $line, int $col, Token $prev): Token |
||
| 203 | { |
||
| 204 | return $code === 91 |
||
| 205 | ? new Token(TokenKindEnum::BRACKET_L, $pos, $pos + 1, $line, $col, $prev) |
||
| 206 | : new Token(TokenKindEnum::BRACKET_R, $pos, $pos + 1, $line, $col, $prev); |
||
| 207 | } |
||
| 208 | |||
| 209 | /** |
||
| 210 | * @param int $pos |
||
| 211 | * @param int $line |
||
| 212 | * @param int $col |
||
| 213 | * @param Token $prev |
||
| 214 | * @return Token |
||
| 215 | */ |
||
| 216 | protected function createDollar(int $pos, int $line, int $col, Token $prev): Token |
||
| 217 | { |
||
| 218 | return new Token(TokenKindEnum::DOLLAR, $pos, $pos + 1, $line, $col, $prev); |
||
| 219 | } |
||
| 220 | |||
| 221 | /** |
||
| 222 | * @param int $pos |
||
| 223 | * @param int $line |
||
| 224 | * @param int $col |
||
| 225 | * @param Token $prev |
||
| 226 | * @return Token |
||
| 227 | */ |
||
| 228 | protected function createPipe(int $pos, int $line, int $col, Token $prev): Token |
||
| 229 | { |
||
| 230 | return new Token(TokenKindEnum::PIPE, $pos, $pos + 1, $line, $col, $prev); |
||
| 231 | } |
||
| 232 | |||
| 233 | /** |
||
| 234 | * @param int $code |
||
| 235 | * @param int $pos |
||
| 236 | * @param int $line |
||
| 237 | * @param int $col |
||
| 238 | * @param Token $prev |
||
| 239 | * @return Token |
||
| 240 | */ |
||
| 241 | protected function createParenthesis(int $code, int $pos, int $line, int $col, Token $prev): Token |
||
| 242 | { |
||
| 243 | return $code === 40 |
||
| 244 | ? new Token(TokenKindEnum::PAREN_L, $pos, $pos + 1, $line, $col, $prev) |
||
| 245 | : new Token(TokenKindEnum::PAREN_R, $pos, $pos + 1, $line, $col, $prev); |
||
| 246 | } |
||
| 247 | |||
| 248 | /** |
||
| 249 | * @param int $pos |
||
| 250 | * @param int $line |
||
| 251 | * @param int $col |
||
| 252 | * @param Token $prev |
||
| 253 | * @return Token |
||
| 254 | */ |
||
| 255 | protected function createEquals(int $pos, int $line, int $col, Token $prev): Token |
||
| 256 | { |
||
| 257 | return new Token(TokenKindEnum::EQUALS, $pos, $pos + 1, $line, $col, $prev); |
||
| 258 | } |
||
| 259 | |||
| 260 | /** |
||
| 261 | * @param int $pos |
||
| 262 | * @param int $line |
||
| 263 | * @param int $col |
||
| 264 | * @param Token $prev |
||
| 265 | * @return Token |
||
| 266 | */ |
||
| 267 | protected function createAt(int $pos, int $line, int $col, Token $prev): Token |
||
| 268 | { |
||
| 269 | return new Token(TokenKindEnum::AT, $pos, $pos + 1, $line, $col, $prev); |
||
| 270 | } |
||
| 271 | |||
| 272 | /** |
||
| 273 | * @param array ...$args |
||
| 274 | * @return Token |
||
| 275 | */ |
||
| 276 | protected function createComment(...$args): Token |
||
| 277 | { |
||
| 278 | return $this->createToken(TokenKindEnum::COMMENT, ...$args); |
||
| 279 | } |
||
| 280 | |||
| 281 | /** |
||
| 282 | * @param array ...$args |
||
| 283 | * @return Token |
||
| 284 | */ |
||
| 285 | protected function createName(...$args): Token |
||
| 286 | { |
||
| 287 | return $this->createToken(TokenKindEnum::NAME, ...$args); |
||
| 288 | } |
||
| 289 | |||
| 290 | /** |
||
| 291 | * @param array ...$args |
||
| 292 | * @return Token |
||
| 293 | */ |
||
| 294 | protected function createInt(...$args): Token |
||
| 295 | { |
||
| 296 | return $this->createToken(TokenKindEnum::INT, ...$args); |
||
| 297 | } |
||
| 298 | |||
| 299 | /** |
||
| 300 | * @param array ...$args |
||
| 301 | * @return Token |
||
| 302 | */ |
||
| 303 | protected function createFloat(...$args): Token |
||
| 304 | { |
||
| 305 | return $this->createToken(TokenKindEnum::FLOAT, ...$args); |
||
| 306 | } |
||
| 307 | |||
| 308 | /** |
||
| 309 | * @param array ...$args |
||
| 310 | * @return Token |
||
| 311 | */ |
||
| 312 | protected function createSpread(...$args): Token |
||
| 315 | } |
||
| 316 | |||
| 317 | /** |
||
| 318 | * @param array ...$args |
||
| 319 | * @return Token |
||
| 320 | */ |
||
| 321 | protected function createString(...$args): Token |
||
| 322 | { |
||
| 323 | return $this->createToken(TokenKindEnum::STRING, ...$args); |
||
| 324 | } |
||
| 325 | |||
| 326 | /** |
||
| 327 | * @param array ...$args |
||
| 328 | * @return Token |
||
| 329 | */ |
||
| 330 | protected function createBlockString(...$args): Token |
||
| 331 | { |
||
| 332 | return $this->createToken(TokenKindEnum::BLOCK_STRING, ...$args); |
||
| 333 | } |
||
| 334 | |||
| 335 | // /** |
||
| 336 | // * @param string $body |
||
| 603 |