<?php
$map = array();
var_dump(levenshtein(utf8_to_extended_ascii('прив', $map), utf8_to_extended_ascii('привет', $map)));
function utf8_to_extended_ascii($str, &$map)
{
// find all multibyte characters (cf. utf-8 encoding specs)
$matches = array();
if (!preg_match_all('/[\xC0-\xF7][\x80-\xBF]+/', $str, $matches))
return $str; // plain ascii string
// update the encoding map with the characters not already met
foreach ($matches[0] as $mbc)
if (!isset($map[$mbc]))
$map[$mbc] = chr(128 + count($map));
// finally remap non-ascii characters
return strtr($str, $map);
}
- Output for 4.3.0 - 4.3.11, 4.4.0 - 4.4.9, 5.0.0 - 5.0.5, 5.1.0 - 5.1.6, 5.2.0 - 5.2.17, 5.3.0 - 5.3.29, 5.4.0 - 5.4.45, 5.5.0 - 5.5.38, 5.6.0 - 5.6.40, 7.0.0 - 7.0.33, 7.1.0 - 7.1.33, 7.2.0 - 7.2.33, 7.3.0 - 7.3.33, 7.4.0 - 7.4.33, 8.0.0 - 8.0.30, 8.1.0 - 8.1.28, 8.2.0 - 8.2.18, 8.3.0 - 8.3.6
- int(2)
preferences:
339.58 ms | 406 KiB | 457 Q