[Summary view] [Print] [Text view]

   1  <?php
   2  /**
   3  * @version $Id: core.php,v 1.5 2006/02/28 22:12:25 harryf Exp $
   4  * @package utf8
   5  * @subpackage strings
   6  */
   7  
   8  /**
   9  * Define UTF8_CORE as required
  10  */
  11  if ( !defined('UTF8_CORE') ) {
  12      define('UTF8_CORE',TRUE);
  13  }
  14  
  15  //--------------------------------------------------------------------
  16  /**
  17  * Wrapper round mb_strlen
  18  * Assumes you have mb_internal_encoding to UTF-8 already
  19  * Note: this function does not count bad bytes in the string - these
  20  * are simply ignored
  21  * @param string UTF-8 string
  22  * @return int number of UTF-8 characters in string
  23  * @package utf8
  24  * @subpackage strings
  25  */
  26  function utf8_strlen($str){
  27      return mb_strlen($str);
  28  }
  29  
  30  
  31  //--------------------------------------------------------------------
  32  /**
  33  * Assumes mbstring internal encoding is set to UTF-8
  34  * Wrapper around mb_strpos
  35  * Find position of first occurrence of a string
  36  * @param string haystack
  37  * @param string needle (you should validate this with utf8_is_valid)
  38  * @param integer offset in characters (from left)
  39  * @return mixed integer position or FALSE on failure
  40  * @package utf8
  41  * @subpackage strings
  42  */
  43  function utf8_strpos($str, $search, $offset = FALSE){
  44      if ( $offset === FALSE ) {
  45          return mb_strpos($str, $search);
  46      } else {
  47          return mb_strpos($str, $search, $offset);
  48      }
  49  }
  50  
  51  //--------------------------------------------------------------------
  52  /**
  53  * Assumes mbstring internal encoding is set to UTF-8
  54  * Wrapper around mb_strrpos
  55  * Find position of last occurrence of a char in a string
  56  * @param string haystack
  57  * @param string needle (you should validate this with utf8_is_valid)
  58  * @param integer (optional) offset (from left)
  59  * @return mixed integer position or FALSE on failure
  60  * @package utf8
  61  * @subpackage strings
  62  */
  63  function utf8_strrpos($str, $search, $offset = FALSE){
  64      if ( $offset === FALSE ) {
  65          # Emulate behaviour of strrpos rather than raising warning
  66          if ( empty($str) ) {
  67              return FALSE;
  68          }
  69          return mb_strrpos($str, $search);
  70      } else {
  71          if ( !is_int($offset) ) {
  72              trigger_error('utf8_strrpos expects parameter 3 to be long',E_USER_WARNING);
  73              return FALSE;
  74          }
  75          
  76          $str = mb_substr($str, $offset);
  77          
  78          if ( FALSE !== ( $pos = mb_strrpos($str, $search) ) ) {
  79              return $pos + $offset;
  80          }
  81          
  82          return FALSE;
  83      }
  84  }
  85  
  86  //--------------------------------------------------------------------
  87  /**
  88  * Assumes mbstring internal encoding is set to UTF-8
  89  * Wrapper around mb_substr
  90  * Return part of a string given character offset (and optionally length)
  91  * @param string
  92  * @param integer number of UTF-8 characters offset (from left)
  93  * @param integer (optional) length in UTF-8 characters from offset
  94  * @return mixed string or FALSE if failure
  95  * @package utf8
  96  * @subpackage strings
  97  */
  98  function utf8_substr($str, $offset, $length = FALSE){
  99      if ( $length === FALSE ) {
 100          return mb_substr($str, $offset);
 101      } else {
 102          return mb_substr($str, $offset, $length);
 103      }
 104  }
 105  
 106  //--------------------------------------------------------------------
 107  /**
 108  * Assumes mbstring internal encoding is set to UTF-8
 109  * Wrapper around mb_strtolower
 110  * Make a string lowercase
 111  * Note: The concept of a characters "case" only exists is some alphabets
 112  * such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does
 113  * not exist in the Chinese alphabet, for example. See Unicode Standard
 114  * Annex #21: Case Mappings
 115  * @param string
 116  * @return mixed either string in lowercase or FALSE is UTF-8 invalid
 117  * @package utf8
 118  * @subpackage strings
 119  */
 120  function utf8_strtolower($str){
 121      return mb_strtolower($str);
 122  }
 123  
 124  //--------------------------------------------------------------------
 125  /**
 126  * Assumes mbstring internal encoding is set to UTF-8
 127  * Wrapper around mb_strtoupper
 128  * Make a string uppercase
 129  * Note: The concept of a characters "case" only exists is some alphabets
 130  * such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does
 131  * not exist in the Chinese alphabet, for example. See Unicode Standard
 132  * Annex #21: Case Mappings
 133  * @param string
 134  * @return mixed either string in lowercase or FALSE is UTF-8 invalid
 135  * @package utf8
 136  * @subpackage strings
 137  */
 138  function utf8_strtoupper($str){
 139      return mb_strtoupper($str);
 140  }