PHP判断字符串编码了类型

搜集的两个function

第一个在我的测试中发现不够好，大部分还是准的

  
    

   
     //
   
      Returns true if $string is valid UTF-8 and false otherwise. 
   
     

   
     function
   
      is_utf8_bak(
   
     $word
   
     ) { 
 
   
     if
   
      (
   
     preg_match
   
     (
   
     "
   
     /^([
   
     "
   
     .
   
     chr
   
     (
   
     228
   
     )
   
     .
   
     "
   
     -
   
     "
   
     .
   
     chr
   
     (
   
     233
   
     )
   
     .
   
     "
   
     ]{1}[
   
     "
   
     .
   
     chr
   
     (
   
     128
   
     )
   
     .
   
     "
   
     -
   
     "
   
     .
   
     chr
   
     (
   
     191
   
     )
   
     .
   
     "
   
     ]{1}[
   
     "
   
     .
   
     chr
   
     (
   
     128
   
     )
   
     .
   
     "
   
     -
   
     "
   
     .
   
     chr
   
     (
   
     191
   
     )
   
     .
   
     "
   
     ]{1}){1}/
   
     "
   
     ,
   
     $word
   
     ) 
   
     ==
   
      
   
     true
   
      
   
     ||
   
      
   
     preg_match
   
     (
   
     "
   
     /([
   
     "
   
     .
   
     chr
   
     (
   
     228
   
     )
   
     .
   
     "
   
     -
   
     "
   
     .
   
     chr
   
     (
   
     233
   
     )
   
     .
   
     "
   
     ]{1}[
   
     "
   
     .
   
     chr
   
     (
   
     128
   
     )
   
     .
   
     "
   
     -
   
     "
   
     .
   
     chr
   
     (
   
     191
   
     )
   
     .
   
     "
   
     ]{1}[
   
     "
   
     .
   
     chr
   
     (
   
     128
   
     )
   
     .
   
     "
   
     -
   
     "
   
     .
   
     chr
   
     (
   
     191
   
     )
   
     .
   
     "
   
     ]{1}){1}$/
   
     "
   
     ,
   
     $word
   
     ) 
   
     ==
   
      
   
     true
   
      
   
     ||
   
      
   
     preg_match
   
     (
   
     "
   
     /([
   
     "
   
     .
   
     chr
   
     (
   
     228
   
     )
   
     .
   
     "
   
     -
   
     "
   
     .
   
     chr
   
     (
   
     233
   
     )
   
     .
   
     "
   
     ]{1}[
   
     "
   
     .
   
     chr
   
     (
   
     128
   
     )
   
     .
   
     "
   
     -
   
     "
   
     .
   
     chr
   
     (
   
     191
   
     )
   
     .
   
     "
   
     ]{1}[
   
     "
   
     .
   
     chr
   
     (
   
     128
   
     )
   
     .
   
     "
   
     -
   
     "
   
     .
   
     chr
   
     (
   
     191
   
     )
   
     .
   
     "
   
     ]{1}){2,}/
   
     "
   
     ,
   
     $word
   
     ) 
   
     ==
   
      
   
     true
   
     ) 
 { 
 
   
     return
   
      
   
     true
   
     ; 
 } 
   
     else
   
      { 
 
   
     return
   
      
   
     false
   
     ; 
 } 
} 
  
    

第二个测试中比第一个好一些

  
    

   
     //
   
      Returns true if $string is valid UTF-8 and false otherwise.
   
     

   
     function
   
      is_utf8(
   
     $string
   
     ) {
 
 
   
     //
   
      From http://w3.org/International/questions/qa-forms-utf-8.html
   
     

   
      
   
     return
   
      
   
     preg_match
   
     (
   
     '
   
     %^(?:
 [\x09\x0A\x0D\x20-\x7E] # ASCII
 | [\xC2-\xDF][\x80-\xBF] # non-overlong 2-byte
 | \xE0[\xA0-\xBF][\x80-\xBF] # excluding overlongs
 | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} # straight 3-byte
 | \xED[\x80-\x9F][\x80-\xBF] # excluding surrogates
 | \xF0[\x90-\xBF][\x80-\xBF]{2} # planes 1-3
 | [\xF1-\xF3][\x80-\xBF]{3} # planes 4-15
 | \xF4[\x80-\x8F][\x80-\xBF]{2} # plane 16
 )*$%xs
   
     '
   
     ,
   
      
   
     $string
   
     );
 
} 
   
     //
   
      function is_utf8