XaBerr /
JATE
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 Scanner 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 Scanner, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 8 | abstract class Scanner extends MixinScanner |
||
| 9 | { |
||
| 10 | /** |
||
| 11 | * Helper to create tokens. |
||
| 12 | */ |
||
| 13 | protected function scan($regex, $type, $captureIndex = 1) |
||
| 14 | { |
||
| 15 | if (preg_match($regex, $this->input, $matches)) { |
||
| 16 | $this->consume($matches[0]); |
||
| 17 | |||
| 18 | return $this->token($type, isset($matches[$captureIndex]) && strlen($matches[$captureIndex]) > 0 ? $matches[$captureIndex] : ''); |
||
| 19 | } |
||
| 20 | } |
||
| 21 | |||
| 22 | /** |
||
| 23 | * Scan comment from input & return it if found. |
||
| 24 | * |
||
| 25 | * @return object|null |
||
| 26 | */ |
||
| 27 | protected function scanComment() |
||
| 28 | { |
||
| 29 | $indent = count($this->indentStack) ? $this->indentStack[0] : 0; |
||
| 30 | if (preg_match('/^ *\/\/(-)?([^\n]*(\n+[ \t]{' . ($indent + 1) . ',}[^\n]*)*)/', $this->input, $matches)) { |
||
| 31 | $this->consume($matches[0]); |
||
| 32 | $value = isset($matches[2]) ? $matches[2] : ''; |
||
| 33 | if (isset($matches[3])) { |
||
| 34 | $value .= "\n"; |
||
| 35 | } |
||
| 36 | $token = $this->token('comment', $value); |
||
| 37 | $token->buffer = '-' !== $matches[1]; |
||
| 38 | |||
| 39 | return $token; |
||
| 40 | } |
||
| 41 | } |
||
| 42 | |||
| 43 | /** |
||
| 44 | * @return object |
||
| 45 | */ |
||
| 46 | protected function scanInterpolation() |
||
| 47 | { |
||
| 48 | return $this->scan('/^#{(.*?)}/', 'interpolation'); |
||
| 49 | } |
||
| 50 | |||
| 51 | /** |
||
| 52 | * @return object |
||
| 53 | */ |
||
| 54 | protected function scanTag() |
||
| 55 | { |
||
| 56 | if (preg_match('/^(\w[-:\w]*)(\/?)/', $this->input, $matches)) { |
||
| 57 | $this->consume($matches[0]); |
||
| 58 | $name = $matches[1]; |
||
| 59 | |||
| 60 | if (':' === substr($name, -1) && ':' !== substr($name, -2, 1)) { |
||
| 61 | $name = substr($name, 0, -1); |
||
| 62 | $this->defer($this->token(':')); |
||
| 63 | |||
| 64 | while (' ' === substr($this->input, 0, 1)) { |
||
| 65 | $this->consume(' '); |
||
| 66 | } |
||
| 67 | } |
||
| 68 | |||
| 69 | $token = $this->token('tag', $name); |
||
| 70 | $token->selfClosing = ($matches[2] === '/'); |
||
| 71 | |||
| 72 | return $token; |
||
| 73 | } |
||
| 74 | } |
||
| 75 | |||
| 76 | /** |
||
| 77 | * @return object |
||
| 78 | */ |
||
| 79 | protected function scanFilter() |
||
| 80 | { |
||
| 81 | return $this->scan('/^(?<!:):(?!:)(\w+(?:-\w+)*)/', 'filter'); |
||
| 82 | } |
||
| 83 | |||
| 84 | /** |
||
| 85 | * @return object |
||
| 86 | */ |
||
| 87 | protected function scanDoctype() |
||
| 88 | { |
||
| 89 | return $this->scan('/^(?:!!!|doctype) *([^\n]+)?/', 'doctype'); |
||
| 90 | } |
||
| 91 | |||
| 92 | /** |
||
| 93 | * @return object |
||
| 94 | */ |
||
| 95 | protected function scanId() |
||
| 96 | { |
||
| 97 | return $this->scan('/^#([\w-]+)/', 'id'); |
||
| 98 | } |
||
| 99 | |||
| 100 | /** |
||
| 101 | * @return object |
||
| 102 | */ |
||
| 103 | protected function scanClassName() |
||
| 104 | { |
||
| 105 | // http://www.w3.org/TR/CSS21/grammar.html#scanner |
||
| 106 | // |
||
| 107 | // ident: |
||
| 108 | // -?{nmstart}{nmchar}* |
||
| 109 | // nmstart: |
||
| 110 | // [_a-z]|{nonascii}|{escape} |
||
| 111 | // nonascii: |
||
| 112 | // [\240-\377] |
||
| 113 | // escape: |
||
| 114 | // {unicode}|\\[^\r\n\f0-9a-f] |
||
| 115 | // unicode: |
||
| 116 | // \\{h}{1,6}(\r\n|[ \t\r\n\f])? |
||
| 117 | // nmchar: |
||
| 118 | // [_a-z0-9-]|{nonascii}|{escape} |
||
| 119 | // |
||
| 120 | // /^(-?(?!=[0-9-])(?:[_a-z0-9-]|[\240-\377]|\\{h}{1,6}(?:\r\n|[ \t\r\n\f])?|\\[^\r\n\f0-9a-f])+)/ |
||
| 121 | return $this->scan('/^\.([\w-]+)/', 'class'); |
||
| 122 | } |
||
| 123 | |||
| 124 | /** |
||
| 125 | * @return object |
||
| 126 | */ |
||
| 127 | protected function scanText() |
||
| 128 | { |
||
| 129 | return $this->scan('/^(?:\| ?| ?)?([^\n]+)/', 'text'); |
||
| 130 | } |
||
| 131 | |||
| 132 | /** |
||
| 133 | * @return object |
||
| 134 | */ |
||
| 135 | protected function scanAssignment() |
||
| 136 | { |
||
| 137 | if (preg_match('/^(\$?\w+) += *([^;\n]+|\'[^\']+\'|"[^"]+")( *;? *)/', $this->input, $matches)) { |
||
| 138 | $this->consume($matches[0]); |
||
| 139 | |||
| 140 | return $this->token('code', (substr($matches[1], 0, 1) === '$' ? '' : '$') . $matches[1] . '=' . $matches[2]); |
||
| 141 | } |
||
| 142 | } |
||
| 143 | |||
| 144 | /** |
||
| 145 | * @return object |
||
| 146 | */ |
||
| 147 | protected function scanConditional() |
||
| 148 | { |
||
| 149 | if (preg_match('/^(if|unless|else if|elseif|else|while)\b([^\n]*)/', $this->input, $matches)) { |
||
| 150 | $this->consume($matches[0]); |
||
| 151 | |||
| 152 | /*switch ($matches[1]) { |
||
| 153 | case 'if': $code = 'if (' . $matches[2] . '):'; break; |
||
| 154 | case 'unless': $code = 'if (!(' . $matches[2] . ')):'; break; |
||
| 155 | case 'else if': $code = 'elseif (' . $matches[2] . '):'; break; |
||
| 156 | case 'else': $code = 'else (' . $matches[2] . '):'; break; |
||
| 157 | }*/ |
||
| 158 | $code = $this->normalizeCode($matches[0]); |
||
| 159 | $token = $this->token('code', $code); |
||
| 160 | $token->buffer = false; |
||
| 161 | |||
| 162 | return $token; |
||
| 163 | } |
||
| 164 | } |
||
| 165 | |||
| 166 | /** |
||
| 167 | * @return object |
||
| 168 | */ |
||
| 169 | protected function scanEach() |
||
| 170 | { |
||
| 171 | if (preg_match('/^(?:- *)?(?:each|for) +(\w+)(?: *, *(\w+))? +in *([^\n]+)/', $this->input, $matches)) { |
||
| 172 | $this->consume($matches[0]); |
||
| 173 | |||
| 174 | $token = $this->token('each', $matches[1]); |
||
| 175 | $token->key = $matches[2]; |
||
| 176 | $token->code = $this->normalizeCode($matches[3]); |
||
| 177 | |||
| 178 | return $token; |
||
| 179 | } |
||
| 180 | } |
||
| 181 | |||
| 182 | /** |
||
| 183 | * @return object |
||
| 184 | */ |
||
| 185 | protected function scanCustomKeyword() |
||
| 186 | { |
||
| 187 | if ( |
||
| 188 | count($this->customKeywords) && |
||
| 189 | preg_match('/^([\w-]+)([^\n]*)/', $this->input, $matches) && |
||
| 190 | isset($this->customKeywords[$matches[1]]) && |
||
| 191 | is_callable($this->customKeywords[$matches[1]]) |
||
| 192 | ) { |
||
| 193 | $this->consume($matches[0]); |
||
| 194 | |||
| 195 | $token = $this->token('customKeyword', $matches[1]); |
||
| 196 | $token->args = trim($matches[2]); |
||
| 197 | |||
| 198 | return $token; |
||
| 199 | } |
||
| 200 | } |
||
| 201 | |||
| 202 | /** |
||
| 203 | * @return object |
||
| 204 | */ |
||
| 205 | protected function scanCode() |
||
| 206 | { |
||
| 207 | if (preg_match('/^(!?=|-)([^\n]+)/', $this->input, $matches)) { |
||
| 208 | $this->consume($matches[0]); |
||
| 209 | $flags = $matches[1]; |
||
| 210 | $code = $this->normalizeCode($matches[2]); |
||
| 211 | |||
| 212 | $token = $this->token('code', $code); |
||
| 213 | $token->escape = $flags[0] === '='; |
||
| 214 | $token->buffer = '=' === $flags[0] || (isset($flags[1]) && '=' === $flags[1]); |
||
| 215 | |||
| 216 | return $token; |
||
| 217 | } |
||
| 218 | } |
||
| 219 | |||
| 220 | /** |
||
| 221 | * @throws \ErrorException |
||
| 222 | * |
||
| 223 | * @return object |
||
| 224 | */ |
||
| 225 | protected function scanAttributes() |
||
| 226 | { |
||
| 227 | if (substr($this->input, 0, 1) === '(') { |
||
| 228 | // cant use ^ anchor in the regex because the pattern is recursive |
||
| 229 | // but this restriction is asserted by the if above |
||
| 230 | //$this->input = preg_replace('/([a-zA-Z0-9\'"\\]\\}\\)])([\t ]+[a-zA-Z])/', '$1,$2', $this->input); |
||
| 231 | if (!preg_match('/\((?:"(?:\\\\.|[^"\\\\])*"|\'(?:\\\\.|[^\'\\\\])*\'|[^()\'"]++|(?R))*+\)/', $this->input, $matches)) { |
||
| 232 | throw new \ErrorException('Unable to find attributes closing parenthesis.', 21); |
||
| 233 | } |
||
| 234 | $this->consume($matches[0]); |
||
| 235 | |||
| 236 | //$str = preg_replace('/()([a-zA-Z0-9_\\x7f-\\xff\\)\\]\\}"\'])(\s+[a-zA-Z_])/', '$1,$2', $str); |
||
| 237 | |||
| 238 | $token = $this->token('attributes'); |
||
| 239 | $token->attributes = array(); |
||
| 240 | $token->escaped = array(); |
||
| 241 | $token->selfClosing = false; |
||
| 242 | |||
| 243 | $parser = new Attributes($token); |
||
| 244 | $parser->parseWith(substr($matches[0], 1, strlen($matches[0]) - 2)); |
||
| 245 | |||
| 246 | if ($this->length() && '/' === $this->input[0]) { |
||
| 247 | $this->consume(1); |
||
| 248 | $token->selfClosing = true; |
||
| 249 | } |
||
| 250 | |||
| 251 | return $token; |
||
| 252 | } |
||
| 253 | } |
||
| 254 | |||
| 255 | /** |
||
| 256 | * @return object |
||
| 257 | */ |
||
| 258 | protected function scanPipelessText() |
||
| 259 | { |
||
| 260 | if ($this->pipeless && "\n" !== substr($this->input, 0, 1)) { |
||
| 261 | $pos = strpos($this->input, "\n"); |
||
| 262 | |||
| 263 | if ($pos === false) { |
||
| 264 | $pos = $this->length(); |
||
| 265 | } |
||
| 266 | |||
| 267 | $str = substr($this->input, 0, $pos); // do not include the \n char |
||
| 268 | |||
| 269 | $this->consume($str); |
||
| 270 | |||
| 271 | return $this->token('text', ltrim($str)); |
||
| 272 | } |
||
| 273 | } |
||
| 274 | |||
| 275 | /** |
||
| 276 | * @return object |
||
| 277 | */ |
||
| 278 | protected function scanColon() |
||
| 279 | { |
||
| 280 | return $this->scan('/^:(?!:) */', ':'); |
||
| 281 | } |
||
| 282 | |||
| 283 | /** |
||
| 284 | * @return object |
||
| 285 | */ |
||
| 286 | protected function scanAndAttributes() |
||
| 287 | { |
||
| 288 | return $this->scan('/^&attributes(\(((?>[^()]+|(?1))*)\))/', '&attributes', 2); |
||
| 289 | } |
||
| 290 | } |
||
| 291 |
