Created
March 18, 2013 23:51
-
-
Save tot-ra/5192145 to your computer and use it in GitHub Desktop.
UTF - Win1251 conversion
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
function win1251_utf8($s){ | |
$t=''; | |
for($i=0, $m=strlen($s); $i<$m; $i++) | |
{ | |
$c=ord($s[$i]); | |
if ($c<=127) {$t.=chr($c); continue; } | |
if ($c>=192 && $c<=207) {$t.=chr(208).chr($c-48); continue; } | |
if ($c>=208 && $c<=239) {$t.=chr(208).chr($c-48); continue; } | |
if ($c>=240 && $c<=255) {$t.=chr(209).chr($c-112); continue; } | |
if ($c==184) { $t.=chr(209).chr(209); continue; }; | |
if ($c==168) { $t.=chr(208).chr(129); continue; }; | |
} | |
return $t; | |
} | |
function utf2win1251($content) | |
{ | |
$newcontent = ""; | |
for ($i = 0; $i < strlen($content); $i++) | |
{ | |
$c1 = substr($content, $i, 1); | |
$byte1 = ord($c1); | |
if ($byte1>>5 == 6) | |
{ | |
$i++; | |
$c2 = substr($content, $i, 1); | |
$byte2 = ord($c2); | |
$byte1 &= 31; | |
$byte2 &= 63; | |
$byte2 |= (($byte1 & 3) << 6); | |
$byte1 >>= 2; | |
$word = ($byte1<<8) + $byte2; | |
if ($word == 1025) $newcontent .= chr(168); | |
else if ($word == 1105) $newcontent .= chr(184); | |
else if ($word >= 0x0410 && $word <= 0x044F) $newcontent .= chr($word-848); | |
else | |
{ | |
$a = dechex($byte1); | |
$a = str_pad($a, 2, "0", STR_PAD_LEFT); | |
$b = dechex($byte2); | |
$b = str_pad($b, 2, "0", STR_PAD_LEFT); | |
$newcontent .= "".$a.$b.";"; | |
} | |
} | |
else | |
$newcontent .= $c1; | |
} | |
return $newcontent; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment