manuwhat /
similar-text
| Total Complexity | 54 |
| Total Lines | 206 |
| Duplicated Lines | 0 % |
| Changes | 0 | ||
Complex classes like distance 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 distance, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 15 | class distance extends complexCommonTextSimilarities |
||
| 16 | { |
||
| 17 | public static function jaroWinkler($a, $b, $round=2) |
||
| 18 | { |
||
| 19 | if (!is_string($a)||!is_string($b)) { |
||
| 20 | return false; |
||
| 21 | } |
||
| 22 | static $distance=array(); |
||
| 23 | static $previous=array(); |
||
| 24 | if (array($a,$b)===$previous) { |
||
| 25 | return $distance; |
||
| 26 | } |
||
| 27 | $previous=array($a,$b); |
||
| 28 | return self::getJWDistance($a, $b, $distance, $round); |
||
| 29 | } |
||
| 30 | |||
| 31 | |||
| 32 | |||
| 33 | private static function getJWDistance(&$a, &$b, &$distance, $round) |
||
| 49 | } |
||
| 50 | |||
| 51 | private static function prepareJaroWinkler(&$a, &$b) |
||
| 63 | } |
||
| 64 | |||
| 65 | private static function jwMatches(&$a, &$b, &$transpositions, $Δ) |
||
| 66 | { |
||
| 67 | foreach ($a as $ind=>$chr) { |
||
| 68 | foreach ($b as $index=>$char) { |
||
| 69 | self::_jwMatches($chr, $char, $index, $ind, $transpositions, $Δ); |
||
| 70 | } |
||
| 71 | } |
||
| 72 | } |
||
| 73 | |||
| 74 | private static function _jwMatches($chr, $char, $index, $ind, &$transpositions, $Δ) |
||
| 86 | } |
||
| 87 | } |
||
| 88 | |||
| 89 | |||
| 90 | public static function hamming($a, $b) |
||
| 105 | } |
||
| 106 | |||
| 107 | public static function dice($a, $b, $round=2) |
||
| 108 | { |
||
| 109 | if ($distance=in_array(self::handleVeryCommonDiceCases($a, $b), array(false,0.0,1.0), true)) { |
||
| 110 | return $distance; |
||
| 111 | } |
||
| 112 | static $distance=0; |
||
| 113 | static $previous=array(); |
||
| 114 | if (array($a,$b)===$previous) { |
||
| 115 | return $distance; |
||
| 116 | } |
||
| 117 | $previous=array($a,$b); |
||
| 118 | $a=self::split($a, 2); |
||
| 119 | $b=self::split($b, 2); |
||
| 120 | return self::getDiceDistance($distance, $a, $b, $round); |
||
| 121 | } |
||
| 122 | |||
| 123 | private static function handleVeryCommonDiceCases(&$a, &$b) |
||
| 124 | { |
||
| 125 | if (!is_string($a)||!is_string($b)) { |
||
| 126 | return false; |
||
| 127 | } |
||
| 128 | if (empty($a)||empty($b)) { |
||
| 129 | return 0.0; |
||
| 130 | } |
||
| 131 | if ($a===$b) { |
||
| 132 | return 1.0; |
||
| 133 | } |
||
| 134 | } |
||
| 135 | |||
| 136 | private static function getDiceDistance(&$distance, &$a, &$b, $round) |
||
| 137 | { |
||
| 138 | $ca=($caGrams=count($a))*2-self::getEndStrLen($a); |
||
| 139 | $cb=($cbGrams=count($b))*2-self::getEndStrLen($b); |
||
| 140 | $distance=round(2*count($caGrams>$cbGrams?array_intersect($a, $b):array_intersect($b, $a))/($ca+$cb), $round); |
||
| 141 | } |
||
| 142 | |||
| 143 | private static function getEndStrLen($a) |
||
| 144 | { |
||
| 145 | if (function_exists('array_key_last')) { |
||
| 146 | $end=array_key_last($a); |
||
| 147 | $end=(isset($end[1]))?0:1; |
||
| 148 | } else { |
||
| 149 | $end=end($a); |
||
| 150 | $end=(isset($end[1]))?0:1; |
||
| 151 | reset($a); |
||
| 152 | } |
||
| 153 | return $end; |
||
| 154 | } |
||
| 155 | |||
| 156 | public static function levenshtein($a, $b) |
||
| 157 | { |
||
| 158 | if (!is_string($a)||!is_string($b)) { |
||
| 159 | return false; |
||
| 160 | } |
||
| 161 | |||
| 162 | |||
| 163 | static $distance=0; |
||
| 164 | static $previous=array(); |
||
| 165 | if (array($a,$b)===$previous) { |
||
| 166 | return $distance; |
||
| 167 | } |
||
| 168 | $previous=array($a,$b); |
||
| 169 | $a=self::split($a); |
||
| 170 | $b=self::split($b); |
||
| 171 | $ca = count($a); |
||
| 172 | $cb = count($b); |
||
| 173 | $dis = range(0, $cb); |
||
| 174 | self::BuildLevenshteinCostMatrix($a, $b, $ca, $cb, $dis); |
||
| 175 | |||
| 176 | return $distance=$dis[$cb]; |
||
| 177 | } |
||
| 178 | |||
| 179 | |||
| 180 | public static function levenshteinDamerau($a, $b) |
||
| 181 | { |
||
| 182 | if (!is_string($a)||!is_string($b)) { |
||
| 183 | return false; |
||
| 184 | } |
||
| 185 | |||
| 186 | static $distance=0; |
||
| 187 | static $previous=array(); |
||
| 188 | if (array($a,$b)===$previous) { |
||
| 189 | return $distance; |
||
| 190 | } |
||
| 191 | $previous=array($a,$b); |
||
| 192 | $a=self::split($a); |
||
| 193 | $b=self::split($b); |
||
| 194 | $ca = count($a); |
||
| 195 | $cb = count($b); |
||
| 196 | $dis = range(0, $cb); |
||
| 197 | self::BuildLevenshteinCostMatrix($a, $b, $ca, $cb, $dis, true); |
||
| 198 | |||
| 199 | return $distance=$dis[$cb]; |
||
| 200 | } |
||
| 201 | |||
| 202 | private static function BuildLevenshteinCostMatrix($a, $b, $ca, $cb, &$dis, $damerau=false) |
||
| 211 | } |
||
| 212 | } |
||
| 213 | |||
| 214 | private static function costMatrix(&$a, &$b, &$dis_new, &$dis, $damerau, $x, $y) |
||
| 215 | { |
||
| 221 | } |
||
| 222 | } |
||
| 223 | } |
||
| 228 |
Loading history...