note 19686 added to function.utf8-encode
| From: | ronen at greyzone dot com | Date: | Thu, 07 Mar 2002 17:01:23 +0000 |
| Subject: | note 19686 added to function.utf8-encode | ||
| Groups: | php.notes | ||
| Request: | Send a blank email to php-notes+get-27482@lists.php.net to get a copy of this message | ||
The following function will utf-8 encode unicode entities &#nnn(nn); with n={0..9}
/**
* takes a string of unicode entities and converts it to a utf-8 encoded string
* each unicode entitiy has the form &#nnn(nn); n={0..9} and can be displayed by utf-8 supporting
* browsers. Ascii will not be modified.
* @param $source string of unicode entities [STRING]
* @return a utf-8 encoded string [STRING]
* @access public
*/
function utf8Encode ($source) {
$utf8Str = '';
$entityArray = explode ("&#", $source);
$size = count ($entityArray);
for ($i = 0; $i < $size; $i++) {
$subStr = $entityArray[$i];
$nonEntity = strstr ($subStr, ';');
if ($nonEntity !== false) {
$unicode = intval (substr ($subStr, 0, (strpos ($subStr, ';') + 1)));
// determine how many chars are needed to reprsent this unicode char
if ($unicode < 128) {
$utf8Substring = chr ($unicode);
}
else if ($unicode >= 128 && $unicode < 2048) {
$binVal = str_pad (decbin ($unicode), 11, "0", STR_PAD_LEFT);
$binPart1 = substr ($binVal, 0, 5);
$binPart2 = substr ($binVal, 5);
$char1 = chr (192 + bindec ($binPart1));
$char2 = chr (128 + bindec ($binPart2));
$utf8Substring = $char1 . $char2;
}
else if ($unicode >= 2048 && $unicode < 65536) {
$binVal = str_pad (decbin ($unicode), 16, "0", STR_PAD_LEFT);
$binPart1 = substr ($binVal, 0, 4);
$binPart2 = substr ($binVal, 4, 6);
$binPart3 = substr ($binVal, 10);
$char1 = chr (224 + bindec ($binPart1));
$char2 = chr (128 + bindec ($binPart2));
$char3 = chr (128 + bindec ($binPart3));
$utf8Substring = $char1 . $char2 . $char3;
}
else {
$binVal = str_pad (decbin ($unicode), 21, "0", STR_PAD_LEFT);
$binPart1 = substr ($binVal, 0, 3);
$binPart2 = substr ($binVal, 3, 6);
$binPart3 = substr ($binVal, 9, 6);
$binPart4 = substr ($binVal, 15);
$char1 = chr (240 + bindec ($binPart1));
$char2 = chr (128 + bindec ($binPart2));
$char3 = chr (128 + bindec ($binPart3));
$char4 = chr (128 + bindec ($binPart4));
$utf8Substring = $char1 . $char2 . $char3 . $char4;
}
if (strlen ($nonEntity) > 1)
$nonEntity = substr ($nonEntity, 1); // chop the first char (';')
else
$nonEntity = '';
$utf8Str .= $utf8Substring . $nonEntity;
}
else {
$utf8Str .= $subStr;
}
}
return $utf8Str;
}
Ronen.
--
http://www.php.net/manual/en/function.utf8-encode.php
http://master.php.net/manage/user-notes.php?action=edit+19686
http://master.php.net/manage/user-notes.php?action=delete+19686
http://master.php.net/manage/user-notes.php?action=reject+19686