[Summary view] [Print] [Text view]

   1  <?php
   2  /**
   3  * Tools to help with ASCII in UTF-8
   4  *
   5  * @package utf8
   6  */
   7  
   8  //--------------------------------------------------------------------
   9  /**
  10  * Tests whether a string contains only 7bit ASCII bytes.
  11  * You might use this to conditionally check whether a string
  12  * needs handling as UTF-8 or not, potentially offering performance
  13  * benefits by using the native PHP equivalent if it's just ASCII e.g.;
  14  *
  15  * <code>
  16  * if ( utf8_is_ascii($someString) ) {
  17  *     // It's just ASCII - use the native PHP version
  18  *     $someString = strtolower($someString);
  19  * } else {
  20  *     $someString = utf8_strtolower($someString);
  21  * }
  22  * </code>
  23  *
  24  * @param string
  25  * @return boolean TRUE if it's all ASCII
  26  * @package utf8
  27  * @see utf8_is_ascii_ctrl
  28  */
  29  function utf8_is_ascii($str) {
  30      // Search for any bytes which are outside the ASCII range...
  31      return (preg_match('/(?:[^\x00-\x7F])/',$str) !== 1);
  32  }
  33  
  34  //--------------------------------------------------------------------
  35  /**
  36  * Tests whether a string contains only 7bit ASCII bytes with device
  37  * control codes omitted. The device control codes can be found on the
  38  * second table here: http://www.w3schools.com/tags/ref_ascii.asp
  39  *
  40  * @param string
  41  * @return boolean TRUE if it's all ASCII without device control codes
  42  * @package utf8
  43  * @see utf8_is_ascii
  44  */
  45  function utf8_is_ascii_ctrl($str) {
  46      if ( strlen($str) > 0 ) {
  47          // Search for any bytes which are outside the ASCII range,
  48          // or are device control codes
  49          return (preg_match('/[^\x09\x0A\x0D\x20-\x7E]/',$str) !== 1);
  50      }
  51      return FALSE;
  52  }
  53  
  54  //--------------------------------------------------------------------
  55  /**
  56  * Strip out all non-7bit ASCII bytes
  57  * If you need to transmit a string to system which you know can only
  58  * support 7bit ASCII, you could use this function.
  59  * @param string
  60  * @return string with non ASCII bytes removed
  61  * @package utf8
  62  * @see utf8_strip_non_ascii_ctrl
  63  */
  64  function utf8_strip_non_ascii($str) {
  65      ob_start();
  66      while ( preg_match(
  67          '/^([\x00-\x7F]+)|([^\x00-\x7F]+)/S',
  68              $str, $matches) ) {
  69          if ( !isset($matches[2]) ) {
  70              echo $matches[0];
  71          }
  72          $str = substr($str, strlen($matches[0]));
  73      }
  74      $result = ob_get_contents();
  75      ob_end_clean();
  76      return $result;
  77  }
  78  
  79  //--------------------------------------------------------------------
  80  /**
  81  * Strip out device control codes in the ASCII range
  82  * which are not permitted in XML. Note that this leaves
  83  * multi-byte characters untouched - it only removes device
  84  * control codes
  85  * @see http://hsivonen.iki.fi/producing-xml/#controlchar
  86  * @param string
  87  * @return string control codes removed
  88  */
  89  function utf8_strip_ascii_ctrl($str) {
  90      ob_start();
  91      while ( preg_match(
  92          '/^([^\x00-\x08\x0B\x0C\x0E-\x1F\x7F]+)|([\x00-\x08\x0B\x0C\x0E-\x1F\x7F]+)/S',
  93              $str, $matches) ) {
  94          if ( !isset($matches[2]) ) {
  95              echo $matches[0];
  96          }
  97          $str = substr($str, strlen($matches[0]));
  98      }
  99      $result = ob_get_contents();
 100      ob_end_clean();
 101      return $result;
 102  }
 103  
 104  //--------------------------------------------------------------------
 105  /**
 106  * Strip out all non 7bit ASCII bytes and ASCII device control codes.
 107  * For a list of ASCII device control codes see the 2nd table here:
 108  * http://www.w3schools.com/tags/ref_ascii.asp
 109  *
 110  * @param string
 111  * @return boolean TRUE if it's all ASCII
 112  * @package utf8
 113  */
 114  function utf8_strip_non_ascii_ctrl($str) {
 115      ob_start();
 116      while ( preg_match(
 117          '/^([\x09\x0A\x0D\x20-\x7E]+)|([^\x09\x0A\x0D\x20-\x7E]+)/S',
 118              $str, $matches) ) {
 119          if ( !isset($matches[2]) ) {
 120              echo $matches[0];
 121          }
 122          $str = substr($str, strlen($matches[0]));
 123      }
 124      $result = ob_get_contents();
 125      ob_end_clean();
 126      return $result;
 127  }
 128  
 129  //---------------------------------------------------------------
 130  /**
 131  * Replace accented UTF-8 characters by unaccented ASCII-7 "equivalents".
 132  * The purpose of this function is to replace characters commonly found in Latin
 133  * alphabets with something more or less equivalent from the ASCII range. This can
 134  * be useful for converting a UTF-8 to something ready for a filename, for example.
 135  * Following the use of this function, you would probably also pass the string
 136  * through utf8_strip_non_ascii to clean out any other non-ASCII chars
 137  * Use the optional parameter to just deaccent lower ($case = -1) or upper ($case = 1)
 138  * letters. Default is to deaccent both cases ($case = 0)
 139  *
 140  * For a more complete implementation of transliteration, see the utf8_to_ascii package
 141  * available from the phputf8 project downloads:
 142  * http://prdownloads.sourceforge.net/phputf8
 143  *
 144  * @param string UTF-8 string
 145  * @param int (optional) -1 lowercase only, +1 uppercase only, 1 both cases
 146  * @param string UTF-8 with accented characters replaced by ASCII chars
 147  * @return string accented chars replaced with ascii equivalents
 148  * @author Andreas Gohr <[email protected]>
 149  * @package utf8
 150  */
 151  function utf8_accents_to_ascii( $str, $case=0 ){
 152  
 153      static $UTF8_LOWER_ACCENTS = NULL;
 154      static $UTF8_UPPER_ACCENTS = NULL;
 155  
 156      if($case <= 0){
 157  
 158          if ( is_null($UTF8_LOWER_ACCENTS) ) {
 159              $UTF8_LOWER_ACCENTS = array(
 160    'à' => 'a', 'ô' => 'o', 'ď' => 'd', 'ḟ' => 'f', 'ë' => 'e', 'š' => 's', 'ơ' => 'o',
 161    'ß' => 'ss', 'ă' => 'a', 'ř' => 'r', 'ț' => 't', 'ň' => 'n', 'ā' => 'a', 'ķ' => 'k',
 162    'ŝ' => 's', 'ỳ' => 'y', 'ņ' => 'n', 'ĺ' => 'l', 'ħ' => 'h', 'ṗ' => 'p', 'ó' => 'o',
 163    'ú' => 'u', 'ě' => 'e', 'é' => 'e', 'ç' => 'c', 'ẁ' => 'w', 'ċ' => 'c', 'õ' => 'o',
 164    'ṡ' => 's', 'ø' => 'o', 'ģ' => 'g', 'ŧ' => 't', 'ș' => 's', 'ė' => 'e', 'ĉ' => 'c',
 165    'ś' => 's', 'î' => 'i', 'ű' => 'u', 'ć' => 'c', 'ę' => 'e', 'ŵ' => 'w', 'ṫ' => 't',
 166    'ū' => 'u', 'č' => 'c', 'ö' => 'oe', 'è' => 'e', 'ŷ' => 'y', 'ą' => 'a', 'ł' => 'l',
 167    'ų' => 'u', 'ů' => 'u', 'ş' => 's', 'ğ' => 'g', 'ļ' => 'l', 'ƒ' => 'f', 'ž' => 'z',
 168    'ẃ' => 'w', 'ḃ' => 'b', 'å' => 'a', 'ì' => 'i', 'ï' => 'i', 'ḋ' => 'd', 'ť' => 't',
 169    'ŗ' => 'r', 'ä' => 'ae', 'í' => 'i', 'ŕ' => 'r', 'ê' => 'e', 'ü' => 'ue', 'ò' => 'o',
 170    'ē' => 'e', 'ñ' => 'n', 'ń' => 'n', 'ĥ' => 'h', 'ĝ' => 'g', 'đ' => 'd', 'ĵ' => 'j',
 171    'ÿ' => 'y', 'ũ' => 'u', 'ŭ' => 'u', 'ư' => 'u', 'ţ' => 't', 'ý' => 'y', 'ő' => 'o',
 172    'â' => 'a', 'ľ' => 'l', 'ẅ' => 'w', 'ż' => 'z', 'ī' => 'i', 'ã' => 'a', 'ġ' => 'g',
 173    'ṁ' => 'm', 'ō' => 'o', 'ĩ' => 'i', 'ù' => 'u', 'į' => 'i', 'ź' => 'z', 'á' => 'a',
 174    'û' => 'u', 'þ' => 'th', 'ð' => 'dh', 'æ' => 'ae', 'µ' => 'u', 'ĕ' => 'e',
 175              );
 176          }
 177  
 178          $str = str_replace(
 179                  array_keys($UTF8_LOWER_ACCENTS),
 180                  array_values($UTF8_LOWER_ACCENTS),
 181                  $str
 182              );
 183      }
 184  
 185      if($case >= 0){
 186          if ( is_null($UTF8_UPPER_ACCENTS) ) {
 187              $UTF8_UPPER_ACCENTS = array(
 188    'À' => 'A', 'Ô' => 'O', 'Ď' => 'D', 'Ḟ' => 'F', 'Ë' => 'E', 'Š' => 'S', 'Ơ' => 'O',
 189    'Ă' => 'A', 'Ř' => 'R', 'Ț' => 'T', 'Ň' => 'N', 'Ā' => 'A', 'Ķ' => 'K',
 190    'Ŝ' => 'S', 'Ỳ' => 'Y', 'Ņ' => 'N', 'Ĺ' => 'L', 'Ħ' => 'H', 'Ṗ' => 'P', 'Ó' => 'O',
 191    'Ú' => 'U', 'Ě' => 'E', 'É' => 'E', 'Ç' => 'C', 'Ẁ' => 'W', 'Ċ' => 'C', 'Õ' => 'O',
 192    'Ṡ' => 'S', 'Ø' => 'O', 'Ģ' => 'G', 'Ŧ' => 'T', 'Ș' => 'S', 'Ė' => 'E', 'Ĉ' => 'C',
 193    'Ś' => 'S', 'Î' => 'I', 'Ű' => 'U', 'Ć' => 'C', 'Ę' => 'E', 'Ŵ' => 'W', 'Ṫ' => 'T',
 194    'Ū' => 'U', 'Č' => 'C', 'Ö' => 'Oe', 'È' => 'E', 'Ŷ' => 'Y', 'Ą' => 'A', 'Ł' => 'L',
 195    'Ų' => 'U', 'Ů' => 'U', 'Ş' => 'S', 'Ğ' => 'G', 'Ļ' => 'L', 'Ƒ' => 'F', 'Ž' => 'Z',
 196    'Ẃ' => 'W', 'Ḃ' => 'B', 'Å' => 'A', 'Ì' => 'I', 'Ï' => 'I', 'Ḋ' => 'D', 'Ť' => 'T',
 197    'Ŗ' => 'R', 'Ä' => 'Ae', 'Í' => 'I', 'Ŕ' => 'R', 'Ê' => 'E', 'Ü' => 'Ue', 'Ò' => 'O',
 198    'Ē' => 'E', 'Ñ' => 'N', 'Ń' => 'N', 'Ĥ' => 'H', 'Ĝ' => 'G', 'Đ' => 'D', 'Ĵ' => 'J',
 199    'Ÿ' => 'Y', 'Ũ' => 'U', 'Ŭ' => 'U', 'Ư' => 'U', 'Ţ' => 'T', 'Ý' => 'Y', 'Ő' => 'O',
 200    'Â' => 'A', 'Ľ' => 'L', 'Ẅ' => 'W', 'Ż' => 'Z', 'Ī' => 'I', 'Ã' => 'A', 'Ġ' => 'G',
 201    'Ṁ' => 'M', 'Ō' => 'O', 'Ĩ' => 'I', 'Ù' => 'U', 'Į' => 'I', 'Ź' => 'Z', 'Á' => 'A',
 202    'Û' => 'U', 'Þ' => 'Th', 'Ð' => 'Dh', 'Æ' => 'Ae', 'Ĕ' => 'E',
 203              );
 204          }
 205          $str = str_replace(
 206                  array_keys($UTF8_UPPER_ACCENTS),
 207                  array_values($UTF8_UPPER_ACCENTS),
 208                  $str
 209              );
 210      }
 211  
 212      return $str;
 213  
 214  }