thunderer /
Shortcode
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 RegularParser 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 RegularParser, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 12 | final class RegularParser implements ParserInterface |
||
| 13 | { |
||
| 14 | private $lexerRegex; |
||
| 15 | private $tokens; |
||
| 16 | private $tokensCount; |
||
| 17 | private $position; |
||
| 18 | private $backtracks; |
||
| 19 | |||
| 20 | const TOKEN_OPEN = 1; |
||
| 21 | const TOKEN_CLOSE = 2; |
||
| 22 | const TOKEN_MARKER = 3; |
||
| 23 | const TOKEN_SEPARATOR = 4; |
||
| 24 | const TOKEN_DELIMITER = 5; |
||
| 25 | const TOKEN_STRING = 6; |
||
| 26 | const TOKEN_WS = 7; |
||
| 27 | |||
| 28 | 4 | public function __construct(SyntaxInterface $syntax = null) |
|
| 32 | |||
| 33 | /** |
||
| 34 | * @param string $text |
||
| 35 | * |
||
| 36 | * @return ParsedShortcode[] |
||
| 37 | */ |
||
| 38 | 40 | public function parse($text) |
|
| 39 | { |
||
| 40 | 40 | $this->tokens = $this->tokenize($text); |
|
| 41 | 40 | $this->backtracks = array(); |
|
| 42 | 40 | $this->position = 0; |
|
| 43 | 40 | $this->tokensCount = count($this->tokens); |
|
| 44 | |||
| 45 | 40 | $shortcodes = array(); |
|
| 46 | 40 | while($this->position < $this->tokensCount) { |
|
| 47 | 39 | while($this->position < $this->tokensCount && !$this->lookahead(self::TOKEN_OPEN)) { |
|
| 48 | 16 | $this->position++; |
|
| 49 | } |
||
| 50 | 39 | $names = array(); |
|
| 51 | 39 | $this->beginBacktrack(); |
|
| 52 | 39 | $matches = $this->shortcode($names); |
|
| 53 | 39 | if(is_array($matches)) { |
|
| 54 | 32 | foreach($matches as $shortcode) { |
|
| 55 | 32 | $shortcodes[] = $shortcode; |
|
| 56 | } |
||
| 57 | } |
||
| 58 | } |
||
| 59 | |||
| 60 | 40 | return $shortcodes; |
|
| 61 | } |
||
| 62 | |||
| 63 | 32 | private function getObject($name, $parameters, $bbCode, $offset, $content, $text) |
|
| 67 | |||
| 68 | /* --- RULES ----------------------------------------------------------- */ |
||
| 69 | |||
| 70 | 39 | private function shortcode(array &$names) |
|
| 116 | |||
| 117 | 23 | private function content(array &$names) |
|
| 118 | { |
||
| 119 | 23 | $content = null; |
|
| 120 | 23 | $shortcodes = array(); |
|
| 121 | 23 | $closingName = null; |
|
| 122 | $appendContent = function(array $token) use(&$content) { $content .= $token[1]; }; |
||
| 123 | |||
| 124 | 23 | while($this->position < $this->tokensCount) { |
|
| 125 | 15 | while($this->match(array(self::TOKEN_STRING, self::TOKEN_WS), $appendContent)) { |
|
| 126 | 14 | continue; |
|
| 127 | } |
||
| 128 | |||
| 129 | 15 | $this->beginBacktrack(); |
|
| 130 | 15 | $matchedShortcodes = $this->shortcode($names); |
|
| 131 | 15 | if(is_string($matchedShortcodes)) { |
|
| 132 | 1 | $closingName = $matchedShortcodes; |
|
| 133 | 1 | break; |
|
| 134 | } |
||
| 135 | 15 | if(false !== $matchedShortcodes) { |
|
| 136 | 6 | $shortcodes = array_merge($shortcodes, $matchedShortcodes); |
|
| 137 | 6 | continue; |
|
| 138 | } |
||
| 139 | 13 | $this->backtrack(); |
|
| 140 | |||
| 141 | 13 | $this->beginBacktrack(); |
|
| 142 | 13 | if(false !== ($closingName = $this->close($names))) { |
|
| 143 | 10 | if(null === $content) { $content = ''; } |
|
| 144 | 10 | $this->backtrack(); |
|
| 145 | 10 | $shortcodes = array(); |
|
| 146 | 10 | break; |
|
| 147 | } |
||
| 148 | 4 | $closingName = null; |
|
| 149 | 4 | $this->backtrack(); |
|
| 150 | 4 | if($this->position < $this->tokensCount) { |
|
| 151 | 1 | $shortcodes = array(); |
|
| 152 | 1 | break; |
|
| 153 | } |
||
| 154 | |||
| 155 | 3 | $this->match(null, $appendContent); |
|
| 156 | } |
||
| 157 | |||
| 158 | 23 | return array($this->position < $this->tokensCount ? $content : false, $shortcodes, $closingName); |
|
| 159 | } |
||
| 160 | |||
| 161 | 13 | private function close(array &$names) |
|
| 173 | |||
| 174 | 35 | private function bbCode() |
|
| 178 | |||
| 179 | 35 | private function parameters() |
|
| 180 | { |
||
| 181 | 35 | $parameters = array(); |
|
| 182 | $setName = function(array $token) use(&$name) { $name = $token[1]; }; |
||
| 183 | |||
| 184 | 35 | while(true) { |
|
| 185 | 35 | $name = null; |
|
|
|
|||
| 186 | |||
| 187 | 35 | $this->match(self::TOKEN_WS); |
|
| 188 | 35 | if($this->lookahead(array(self::TOKEN_MARKER, self::TOKEN_CLOSE))) { break; } |
|
| 189 | 22 | if(!$this->match(self::TOKEN_STRING, $setName, true)) { return false; } |
|
| 190 | 21 | if(!$this->match(self::TOKEN_SEPARATOR, null, true)) { $parameters[$name] = null; continue; } |
|
| 191 | 20 | if(false === ($value = $this->value())) { return false; } |
|
| 192 | 19 | $this->match(self::TOKEN_WS); |
|
| 193 | |||
| 194 | 19 | $parameters[$name] = $value; |
|
| 195 | } |
||
| 196 | |||
| 197 | 33 | return $parameters; |
|
| 198 | } |
||
| 199 | |||
| 200 | 21 | private function value() |
|
| 201 | { |
||
| 202 | 21 | $value = ''; |
|
| 203 | $appendValue = function(array $token) use(&$value) { $value .= $token[1]; }; |
||
| 204 | |||
| 205 | 21 | if($this->match(self::TOKEN_DELIMITER)) { |
|
| 206 | 18 | while($this->position < $this->tokensCount && !$this->lookahead(self::TOKEN_DELIMITER)) { |
|
| 207 | 18 | $this->match(null, $appendValue); |
|
| 208 | } |
||
| 209 | |||
| 210 | 18 | return $this->match(self::TOKEN_DELIMITER) ? $value : false; |
|
| 211 | } |
||
| 212 | |||
| 213 | 8 | return $this->match(self::TOKEN_STRING, $appendValue) ? $value : false; |
|
| 214 | } |
||
| 215 | |||
| 216 | /* --- PARSER ---------------------------------------------------------- */ |
||
| 217 | |||
| 218 | 39 | private function beginBacktrack() |
|
| 222 | |||
| 223 | private function getBacktrack() |
||
| 228 | |||
| 229 | 23 | private function backtrack($modifyPosition = true) |
|
| 230 | { |
||
| 231 | 23 | $tokens = array_pop($this->backtracks); |
|
| 232 | 23 | $count = count($tokens); |
|
| 233 | 23 | if($modifyPosition) { |
|
| 234 | 13 | $this->position -= $count; |
|
| 235 | } |
||
| 236 | |||
| 237 | 23 | foreach($this->backtracks as &$backtrack) { |
|
| 238 | // array_pop() in loop is much faster than array_slice() because |
||
| 239 | // it operates directly on the passed array |
||
| 240 | 23 | for($i = 0; $i < $count; $i++) { |
|
| 241 | 15 | array_pop($backtrack); |
|
| 242 | } |
||
| 243 | } |
||
| 244 | |||
| 245 | return implode('', array_map(function(array $token) { return $token[1]; }, $tokens)); |
||
| 246 | } |
||
| 247 | |||
| 248 | 39 | private function lookahead($type, $callback = null) |
|
| 265 | |||
| 266 | 39 | private function match($type, $callbacks = null, $ws = false) |
|
| 267 | { |
||
| 268 | 39 | if($this->position >= $this->tokensCount) { |
|
| 269 | 14 | return false; |
|
| 270 | } |
||
| 290 | |||
| 291 | /* --- LEXER ----------------------------------------------------------- */ |
||
| 292 | |||
| 293 | 40 | private function tokenize($text) |
|
| 315 | |||
| 316 | private function getTokenizerRegex(SyntaxInterface $syntax) |
||
| 334 | } |
||
| 335 |
Loading history...
It seems like you are assigning to a variable which was imported through a
usestatement which was not imported by reference.For clarity, we suggest to use a different name or import by reference depending on whether you would like to have the change visibile in outer-scope.
Change not visible in outer-scope
Change visible in outer-scope