<?php
class Similarity
{
protected $data = null;
protected $distance = null;
public function __construct($data, $distance)
{
$this->data = (string)$data;
$this->distance = (int)$distance;
}
public function checkMatch($search, callable $checker=null, array $args=[], $return=false)
{
$data = preg_split('/\s+/', strtolower($this->data), -1, PREG_SPLIT_NO_EMPTY);
$search = trim(preg_replace('/\s+/', ' ', strtolower($search)));
foreach($this->getAssoc($data, substr_count($search, ' ')+1) as $assoc)
{
foreach($this->getPermutations($assoc) as $ordered)
{
$ordered = join(' ', $ordered);
$result = call_user_func_array($checker, array_merge([$ordered, $search], $args));
if($result<=$this->distance)
{
return $return?$ordered:true;
}
}
}
return $return?null:false;
}
protected function getPermutations(array $input)
{
if(count($input)==1)
{
return [$input];
}
$result = [];
foreach($input as $key=>$element)
{
foreach($this->getPermutations(array_diff_key($input, [$key=>0])) as $subarray)
{
$result[] = array_merge([$element], $subarray);
}
}
return $result;
}
protected function nextAssoc($assoc)
{
if(false !== ($pos = strrpos($assoc, '01')))
{
$assoc[$pos] = '1';
$assoc[$pos+1] = '0';
return substr($assoc, 0, $pos+2).
str_repeat('0', substr_count(substr($assoc, $pos+2), '0')).
str_repeat('1', substr_count(substr($assoc, $pos+2), '1'));
}
return false;
}
protected function getAssoc(array $data, $count=2)
{
if(count($data)<$count)
{
return null;
}
$assoc = str_repeat('0', count($data)-$count).str_repeat('1', $count);
$result = [];
do
{
$result[]=array_intersect_key($data, array_filter(str_split($assoc)));
}
while($assoc=$this->nextAssoc($assoc));
return $result;
}
}
$data = 'Yaya Faurskov Andersen';
$search = [
'Niels Andersen',
'Niels Faurskov',
'Niels Faurskov Andersen',
'Nils Faurskov Andersen',
'Nils Andersen',
'niels faurskov',
'niels Faurskov',
'niffddels Faurskovffre'
];
$checker = new Similarity($data, 2);
echo(sprintf('Testing "%s"'.PHP_EOL.PHP_EOL, $data));
foreach($search as $name)
{
echo(sprintf(
'Name "%s" has %s'.PHP_EOL,
$name,
($result=$checker->checkMatch($name, 'levenshtein', [], 1))
?sprintf('matched with "%s"', $result)
:'mismatched'
)
);
}
preferences:
41.71 ms | 402 KiB | 5 Q