[Summary view] [Print] [Text view]

   1  <?php
   2  /**
   3  * @package utf8
   4  */
   5  
   6  /**
   7  * Define UTF8_CORE as required
   8  */
   9  if ( !defined('UTF8_CORE') ) {
  10      define('UTF8_CORE',TRUE);
  11  }
  12  
  13  //--------------------------------------------------------------------
  14  /**
  15  * Wrapper round mb_strlen
  16  * Assumes you have mb_internal_encoding to UTF-8 already
  17  * Note: this function does not count bad bytes in the string - these
  18  * are simply ignored
  19  * @param string UTF-8 string
  20  * @return int number of UTF-8 characters in string
  21  * @package utf8
  22  */
  23  function utf8_strlen($str){
  24      return mb_strlen($str);
  25  }
  26  
  27  
  28  //--------------------------------------------------------------------
  29  /**
  30  * Assumes mbstring internal encoding is set to UTF-8
  31  * Wrapper around mb_strpos
  32  * Find position of first occurrence of a string
  33  * @param string haystack
  34  * @param string needle (you should validate this with utf8_is_valid)
  35  * @param integer offset in characters (from left)
  36  * @return mixed integer position or FALSE on failure
  37  * @package utf8
  38  */
  39  function utf8_strpos($str, $search, $offset = FALSE){
  40      if ( $offset === FALSE ) {
  41          return mb_strpos($str, $search);
  42      } else {
  43          return mb_strpos($str, $search, $offset);
  44      }
  45  }
  46  
  47  //--------------------------------------------------------------------
  48  /**
  49  * Assumes mbstring internal encoding is set to UTF-8
  50  * Wrapper around mb_strrpos
  51  * Find position of last occurrence of a char in a string
  52  * @param string haystack
  53  * @param string needle (you should validate this with utf8_is_valid)
  54  * @param integer (optional) offset (from left)
  55  * @return mixed integer position or FALSE on failure
  56  * @package utf8
  57  */
  58  function utf8_strrpos($str, $search, $offset = FALSE){
  59      if ( $offset === FALSE ) {
  60          # Emulate behaviour of strrpos rather than raising warning
  61          if ( empty($str) ) {
  62              return FALSE;
  63          }
  64          return mb_strrpos($str, $search);
  65      } else {
  66          if ( !is_int($offset) ) {
  67              trigger_error('utf8_strrpos expects parameter 3 to be long',E_USER_WARNING);
  68              return FALSE;
  69          }
  70  
  71          $str = mb_substr($str, $offset);
  72  
  73          if ( FALSE !== ( $pos = mb_strrpos($str, $search) ) ) {
  74              return $pos + $offset;
  75          }
  76  
  77          return FALSE;
  78      }
  79  }
  80  
  81  //--------------------------------------------------------------------
  82  /**
  83  * Assumes mbstring internal encoding is set to UTF-8
  84  * Wrapper around mb_substr
  85  * Return part of a string given character offset (and optionally length)
  86  * @param string
  87  * @param integer number of UTF-8 characters offset (from left)
  88  * @param integer (optional) length in UTF-8 characters from offset
  89  * @return mixed string or FALSE if failure
  90  * @package utf8
  91  */
  92  function utf8_substr($str, $offset, $length = FALSE){
  93      if ( $length === FALSE ) {
  94          return mb_substr($str, $offset);
  95      } else {
  96          return mb_substr($str, $offset, $length);
  97      }
  98  }
  99  
 100  //--------------------------------------------------------------------
 101  /**
 102  * Assumes mbstring internal encoding is set to UTF-8
 103  * Wrapper around mb_strtolower
 104  * Make a string lowercase
 105  * Note: The concept of a characters "case" only exists is some alphabets
 106  * such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does
 107  * not exist in the Chinese alphabet, for example. See Unicode Standard
 108  * Annex #21: Case Mappings
 109  * @param string
 110  * @return mixed either string in lowercase or FALSE is UTF-8 invalid
 111  * @package utf8
 112  */
 113  function utf8_strtolower($str){
 114      return mb_strtolower($str);
 115  }
 116  
 117  //--------------------------------------------------------------------
 118  /**
 119  * Assumes mbstring internal encoding is set to UTF-8
 120  * Wrapper around mb_strtoupper
 121  * Make a string uppercase
 122  * Note: The concept of a characters "case" only exists is some alphabets
 123  * such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does
 124  * not exist in the Chinese alphabet, for example. See Unicode Standard
 125  * Annex #21: Case Mappings
 126  * @param string
 127  * @return mixed either string in lowercase or FALSE is UTF-8 invalid
 128  * @package utf8
 129  */
 130  function utf8_strtoupper($str){
 131      return mb_strtoupper($str);
 132  }