• 首页
  • vue
  • TypeScript
  • JavaScript
  • scss
  • css3
  • html5
  • php
  • MySQL
  • redis
  • jQuery
    •
    位置： php 中文手册 -> php 内置函数 -> php 字符串函数

    convert_cyr_string()

    (PHP 4, PHP 5, PHP 7)

    将字符由一种 Cyrillic 字符转换成另一种

    说明

    convert_cyr_string(string $str, string $from, string $to) : string

    此函数将给定的字符串从一种 Cyrillic 字符转换成另一种，返回转换之后的字符串。

    参数

    $str

    要转换的字符。

    $from

    单个字符，代表源 Cyrillic 字符集。

    $to

    单个字符，代表了目标 Cyrillic 字符集。

    支持的类型有：

    • k - koi8-r
    • w - windows-1251
    • i - iso8859-5
    • a - x-cp866
    • d - x-cp866
    • m - x-mac-cyrillic

    返回值

    返回转换后的字符串。

    注释

    Note:此函数可安全用于二进制对象。

    Only this code works OK for me, for translating win-1251 to utf-8 for macedonian letters!
// Modificated by tapin13
// Corrected by Timuretis
// Corrected by Sote for macedonian cyrillic
// Convert win-1251 to utf-8
function unicode_mk_cyr($str) {
   $encode = "";
   for ($ii=0;$ii<strlen($str);$ii++) {
     $xchr=substr($str,$ii,1);
     echo "<p>".ord($xchr)."</p>\n";
     if (ord($xchr)>191) {
       $xchr=ord($xchr)+848;
       $xchr="&#" . $xchr . ";";
     }
     if(ord($xchr) == 129) {
        $xchr = "&#1027;"; 
     } 
     if(ord($xchr) == 163) {
        $xchr = "&#1032;"; 
     }    
     if(ord($xchr) == 138) {
        $xchr = "&#1033;"; 
     }
     if(ord($xchr) == 140) {
        $xchr = "&#1034;"; 
     }
     if(ord($xchr) == 143) {
        $xchr = "&#1039;"; 
     }
     if(ord($xchr) == 141) {
        $xchr = "&#1036;"; 
     }  
     if(ord($xchr) == 189) {
        $xchr = "&#1029;"; 
     }                 
      
     if(ord($xchr) == 188) {
        $xchr = "&#1112;"; 
     }
     if(ord($xchr) == 131) {
        $xchr = "&#1107;"; 
     }
     if(ord($xchr) == 190) {
        $xchr = "&#1109;"; 
     }
     if(ord($xchr) == 154) {
        $xchr = "&#1113;"; 
     }
     if(ord($xchr) == 156) {
        $xchr = "&#1114;"; 
     }
     if(ord($xchr) == 159) {
        $xchr = "&#1119;"; 
     }
     if(ord($xchr) == 157) {
        $xchr = "&#1116;"; 
     }                           
     $encode=$encode . $xchr;
  }
   return $encode;
}
    He is improved function to decode win1251->UTF8
<?php
    function win2utf($s){ 
      $c209 = chr(209); $c208 = chr(208); $c129 = chr(129);
      for($i=0; $i<strlen($s); $i++)  { 
        $c=ord($s[$i]);
        if ($c>=192 and $c<=239) $t.=$c208.chr($c-48);
        elseif ($c>239) $t.=$c209.chr($c-112);
        elseif ($c==184) $t.=$c209.$c209;
        elseif ($c==168)  $t.=$c208.$c129;
        else $t.=$s[$i];
      } 
      return $t;
    }
?>
    To: mihailsbo at lycos dot ru
Transliteration could be done easier:
<?
function transliterate($cyrstr)
  {
    $ru = array('A', 'a',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?',
          '?', '?');
    $en = array('A', 'a',
          'B', 'b',
          'V', 'v',
          'G', 'g',
          'D', 'd',
          'E', 'e',
          'E', 'e',
          'Zh', 'zh',
          'Z', 'z',
          'I', 'i',
          'J', 'j',
          'K', 'k',
          'L', 'l',
          'M', 'm',
          'N', 'n',
          'O', 'o',
          'P', 'p',
          'R', 'r',
          'S', 's',
          'T', 't',
          'U', 'u',
          'F', 'f',
          'H', 'h',
          'C', 'c',
          'Ch', 'ch',
          'Sh', 'sh',
          'Sch', 'sch',
          '\'', '\'',
          'Y', 'y', 
          '\'', '\'',
          'E', 'e',
          'Ju', 'ju',
          'Ja', 'ja');
    return str_replace($ru, $en, $cyrstr);
  }
?>
    cathody at mail dot ru(27-Jul-2005 06:41)
You function doesn't work on my PC..
It's work:
function Encode2($str,$type)
{
  $conv=array();
  for($x=192;$x<=239;$x++)
    $conv[u][chr($x)]=chr(208).chr($x-48);
  for($x=240;$x<=255;$x++)
    $conv[u][chr($x)]=chr(209).chr($x-112);
  $conv[u][chr(168)]=chr(208).chr(129);
  $conv[u][chr(184)]=chr(209).chr(209);
  $conv[w]=array_reverse($conv[u]);
  if($type=='w'  ||  $type=='u')
    return strtr($str,$conv[$type]);
  else
    return $str;
}
    Check this code -- exelent to convert win-1251 to UTF-8 
just one fix!!!
    if ($c==184) { $t.=chr(209).chr(145); continue; }; 
Anything more it is not necessary.
It is grateful to threed [at] koralsoft.com
28-Jul-2003 03:37 
i tried all functions here to convert from cp1251 to unicode, but they don't work. i think that this work : 
<?php 
function win3utf($s)  { 
  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 $t; 
} 
?>
    i tried all functions here to convert from cp1251 to unicode, but they don't work. i think that this work :
<?php
function win3utf($s)  {
  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 $t;
}
?>
    A better function to convert cp1251 string to utf8.
Works with russian and ukrainian text.
function unicod($str) {
  $conv=array();
  for($x=128;$x<=143;$x++) $conv[$x+112]=chr(209).chr($x);
  for($x=144;$x<=191;$x++) $conv[$x+48]=chr(208).chr($x);
  $conv[184]=chr(209).chr(145); #ё
  $conv[168]=chr(208).chr(129); #Ё
  $conv[179]=chr(209).chr(150); #і
  $conv[178]=chr(208).chr(134); #І
  $conv[191]=chr(209).chr(151); #ї
  $conv[175]=chr(208).chr(135); #ї
  $conv[186]=chr(209).chr(148); #є
  $conv[170]=chr(208).chr(132); #Є
  $conv[180]=chr(210).chr(145); #ґ
  $conv[165]=chr(210).chr(144); #Ґ
  $conv[184]=chr(209).chr(145); #Ґ
  $ar=str_split($str);
  foreach($ar as $b) if(isset($conv[ord($b)])) $nstr.=$conv[ord($b)]; else $nstr.=$b;
  return $nstr;
}
    //I've also built the same way for hebrew to utf converting
function heb2utf($s) {
  for($i=0, $m=strlen($s); $i<$m; $i++)  { 
    $c=ord($s[$i]); 
    if ($c<=127) {$t.=chr($c); continue; } 
    if ($c>=224 )  {$t.=chr(215).chr($c-80); continue; } 
   
  } 
  return $t; 
}
//Simple unicoder and decoder for hebrew and russian:
function unicode_hebrew($str) {
  for ($ii=0;$ii<strlen($str);$ii++) {
    $xchr=substr($str,$ii,1);
    if (ord($xchr)>223) {
      $xchr=ord($xchr)+1264;
      $xchr="&#" . $xchr . ";";
    }
    $encode=$encode . $xchr;
  }
  return $encode;
}
function unicode_russian($str) {
  for ($ii=0;$ii<strlen($str);$ii++) {
    $xchr=substr($str,$ii,1);
    if (ord($xchr)>191) {
      $xchr=ord($xchr)+848;
      $xchr="&#" . $xchr . ";";
    }
    $encode=$encode . $xchr;
  }
  return $encode;
}
function decode_unicoded_hebrew($str) {
  $decode="";
  $ar=split("&#",$str);
  foreach ($ar as $value ) {
    $in1=strpos($value,";"); //end of code
    if ($in1>0) {// unicode
      $code=substr($value,0,$in1);
        
      if ($code>=1456 and $code<=1514) { //hebrew
          $code=$code-1264;
        $xchr=chr($code);
        } else { //other unicode
        $xchr="&#" . $code . ";";
       } 
      $xchr=$xchr . substr($value,$in1+1);  
    } else //not unicode
       $xchr = $value;
    
    $decode=$decode . $xchr;
  }
  return $decode;
}
function decode_unicoded_russian($str) {
  $decode="";
  $ar=split("&#",$str);
  foreach ($ar as $value ) {
    $in1=strpos($value,";"); //end of code
    if ($in1>0) {// unicode
      $code=substr($value,0,$in1);
        
      if ($code>=1040 and $code<=1103) {
          $code=$code-848;
        $xchr=chr($code);
        } else {
        $xchr="&#" . $code . ";";
       } 
      $xchr=$xchr . substr($value,$in1+1);  
    } else
       $xchr = $value;
    
    $decode=$decode . $xchr;
  }
  return $decode;
}
    Not all of cyrilic characters are supported by this function. Cyrilic chars from Macedonian Alphabet like Sh, kj, dz' ,nj are not supported.
    :) what about NUMBER!!!???
  function Utf8Win($str,$type="w")
  {
    static $conv='';
    if (!is_array($conv))
    {
      $conv = array();
      for($x=128;$x<=143;$x++)
      {
        $conv['u'][]=chr(209).chr($x);
        $conv['w'][]=chr($x+112);
      }
      for($x=144;$x<=191;$x++)
      {
        $conv['u'][]=chr(208).chr($x);
        $conv['w'][]=chr($x+48);
      }
      $conv['u'][]=chr(208).chr(129); // Ё
      $conv['w'][]=chr(168);
      $conv['u'][]=chr(209).chr(145); // ё
      $conv['w'][]=chr(184);
      $conv['u'][]=chr(208).chr(135); // Ї
      $conv['w'][]=chr(175);
      $conv['u'][]=chr(209).chr(151); // ї
      $conv['w'][]=chr(191);
      $conv['u'][]=chr(208).chr(134); // І
      $conv['w'][]=chr(178);
      $conv['u'][]=chr(209).chr(150); // і
      $conv['w'][]=chr(179);
      $conv['u'][]=chr(210).chr(144); // Ґ
      $conv['w'][]=chr(165);
      $conv['u'][]=chr(210).chr(145); // ґ
      $conv['w'][]=chr(180);
      $conv['u'][]=chr(208).chr(132); // Є
      $conv['w'][]=chr(170);
      $conv['u'][]=chr(209).chr(148); // є
      $conv['w'][]=chr(186);
      $conv['u'][]=chr(226).chr(132).chr(150); // №
      $conv['w'][]=chr(185);
    }
    if ($type == 'w') { return str_replace($conv['u'],$conv['w'],$str); }
    elseif ($type == 'u') { return str_replace($conv['w'], $conv['u'],$str); }
    else { return $str; }
  }
    Sorry for my previous post. NOT array_reverce, array_flip is actual function. Correct function:
function Encode($str,$type=u)
{
  $conv=array();
  for($x=192;$x<=239;$x++)
    $conv[u][chr($x)]=chr(208).chr($x-48);
  for($x=240;$x<=255;$x++)
    $conv[u][chr($x)]=chr(209).chr($x-112);
  $conv[u][chr(168)]=chr(208).chr(129);
  $conv[u][chr(184)]=chr(209).chr(209);
  $conv[w]=array_flip($conv[u]);
  if($type=='w'  ||  $type=='u')
    return strtr($str,$conv[$type]);
  else
    return $str;
}
Sorry for my English ;)
    threed's function works great, but the replacement for the letter small io (&#1105;) needs to be changed from 
<?php
if ($c==184) { $t.=chr(209).chr(209); continue; };
?>
to
<?php
if ($c==184) { $t.=chr(209).chr(145); continue; };
?>
so, the final working result should look like this:
<?php
function win3utf($s) {
  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 $t;
}
?>
    I have made mistake remove this test line:
     echo "<p>".ord($xchr)."</p>\n";
code should be like this:
// Modificated by tapin13
// Corrected by Timuretis
// Corrected by Sote for macedonian cyrillic
// Convert win-1251 to utf-8
function unicode_mk_cyr($str) {
   $encode = "";
   for ($ii=0;$ii<strlen($str);$ii++) {
     $xchr=substr($str,$ii,1);
     if (ord($xchr)>191) {
       $xchr=ord($xchr)+848;
       $xchr="&#" . $xchr . ";";
     }
     if(ord($xchr) == 129) {
        $xchr = "&#1027;";
     }
     if(ord($xchr) == 163) {
        $xchr = "&#1032;";
     }   
     if(ord($xchr) == 138) {
        $xchr = "&#1033;";
     }
     if(ord($xchr) == 140) {
        $xchr = "&#1034;";
     }
     if(ord($xchr) == 143) {
        $xchr = "&#1039;";
     }
     if(ord($xchr) == 141) {
        $xchr = "&#1036;";
     }  
     if(ord($xchr) == 189) {
        $xchr = "&#1029;";
     }                
     
     if(ord($xchr) == 188) {
        $xchr = "&#1112;";
     }
     if(ord($xchr) == 131) {
        $xchr = "&#1107;";
     }
     if(ord($xchr) == 190) {
        $xchr = "&#1109;";
     }
     if(ord($xchr) == 154) {
        $xchr = "&#1113;";
     }
     if(ord($xchr) == 156) {
        $xchr = "&#1114;";
     }
     if(ord($xchr) == 159) {
        $xchr = "&#1119;";
     }
     if(ord($xchr) == 157) {
        $xchr = "&#1116;";
     }                          
     $encode=$encode . $xchr;
  }
   return $encode;
}
    previous bit of code (grmaxim's win_to_utf8 function) didn't work for me, so I wrote my own func to convert from win1251 to utf8:
<?php
function win2utf($s) {
  for($i=0,$m=strlen($s);$i<$m;$i++) {
    $c=ord($s[$i]);
    if ($c>127) // convert only special chars
      if   ($c==184)  $t.=chr(209).chr(209); // small io
      elseif ($c==168)  $t.=chr(208).chr(129); // capital io
      else       $t.=($c>239?chr(209): chr(208)).chr($c-48);
    else $t.=$s[$i];
  }
  return $t;
}
?>
Hope this helps
    Unfortunately input data must be a string only. But it is may be changed! ;) 
To convert multi-dimensional array I use this recursive function:
<?php
function convert_cyr_array($array,$from,$to){
  foreach($array as $key=>$value){
    if(is_array($value)) {
      $result[$key] = convert_cyr_array($value,$from,$to);
      continue;
    }
    $result[$key] = convert_cyr_string($value,$from,$to);
  }
  return $result;
}
?>
An example:
<?php
$array[0] = "сВМПЛП";
$array[1] = "зТХЫБ";
$array[2] = array("пЗХТЕГ","рПНЙДПТ");
$array[3] = array(
           array("бРЕМШУЙО","нБОДБТЙО"),
           array("бВТЙЛПУ","рЕТУЙЛ")
        );
$result = convert_cyr_array($array,"k","w");
/* Returns:
Array
(
 [0] => Яблоко
 [1] => Груша
 [2] => Array
  (
   [0] => Огурец
   [1] => Помидор
  )
 [3] => Array
  (
   [0] => Array
    (
     [0] => Апельсин
     [1] => Мандарин
    )
   [1] => Array
    (
     [0] => Абрикос
     [1] => Персик
    )
  )
)*/
?>
    Praising other people for their efforts to write a convenient UTF8 to Win-1251 functions may I mention that, since str_replace allows arrays as parameters, the function may be rewritten in a slightly efficient way (moreover, the array generated may be stored for performance improvement):
<?php 
 function Encode ( $str, $type )
{
 // $type: 
// 'w' - encodes from UTF to win 
 // 'u' - encodes from win to UTF 
  static $conv='';
  if (!is_array ( $conv ))
  {  
    $conv=array ();
    for ( $x=128; $x <=143; $x++ )
    {
     $conv['utf'][]=chr(209).chr($x);
     $conv['win'][]=chr($x+112);
    }
    for ( $x=144; $x <=191; $x++ )
    {
        $conv['utf'][]=chr(208).chr($x);
        $conv['win'][]=chr($x+48);
    }
 
    $conv['utf'][]=chr(208).chr(129);
    $conv['win'][]=chr(168);
    $conv['utf'][]=chr(209).chr(145);
    $conv['win'][]=chr(184);
   }
   if ( $type=='w' )
     return str_replace ( $conv['utf'], $conv['win'], $str );
   elseif ( $type=='u' )
     return str_replace ( $conv['win'], $conv['utf'], $str );
   else
    return $str;
 }
?>

    上篇：chunk_split()

    下篇：convert_uudecode()