Файл: Dvig/tst.php
Строк: 98
<?php
//simple task: convert everything from utf-8 into an NCR[numeric character reference]
class unicode_replace_entities {
public function UTF8entities($content="") {
$contents = $this->unicode_string_to_array($content);
$swap = "";
$iCount = count($contents);
for ($o=0;$o<$iCount;$o++) {
$contents[$o] = $this->unicode_entity_replace($contents[$o]);
$swap .= $contents[$o];
}
return mb_convert_encoding($swap,"UTF-8"); //not really necessary, but why not.
}
public function unicode_string_to_array( $string ) { //adjwilli
$strlen = mb_strlen($string);
while ($strlen) {
$array[] = mb_substr( $string, 0, 1, "UTF-8" );
$string = mb_substr( $string, 1, $strlen, "UTF-8" );
$strlen = mb_strlen( $string );
}
return $array;
}
public function unicode_entity_replace($c) { //m. perez
$h = ord($c{0});
if ($h <= 0x7F) {
return $c;
} else if ($h < 0xC2) {
return $c;
}
if ($h <= 0xDF) {
$h = ($h & 0x1F) << 6 | (ord($c{1}) & 0x3F);
$h = "&#" . $h . ";";
return $h;
} else if ($h <= 0xEF) {
$h = ($h & 0x0F) << 12 | (ord($c{1}) & 0x3F) << 6 | (ord($c{2}) & 0x3F);
$h = "&#" . $h . ";";
return $h;
} else if ($h <= 0xF4) {
$h = ($h & 0x0F) << 18 | (ord($c{1}) & 0x3F) << 12 | (ord($c{2}) & 0x3F) << 6 | (ord($c{3}) & 0x3F);
$h = "&#" . $h . ";";
return $h;
}
}
}//
//utf-8 environment
$content = "<strong>дизайн<br />";
$oUnicodeReplace = new unicode_replace_entities();
$content = $oUnicodeReplace->UTF8entities($content);
echo "<br />Result:<br />";
echo $content;
$source = htmlentities($content);
echo "<br />htmlentities of resulting data:<br />";
echo $source;
echo "<br /><br />Note: Entities get replaced with 'literals' in textarea FF3<br /><br />";
echo "<textarea style='width:300px;height:150px;'>";
echo $content;
echo "</textarea>";
echo "<br /><br />For editing NCR's rather than 'literals' in a textarea<br /><br />";
echo "<textarea style='width:300px;height:150px;'>";
echo preg_replace("/(&#)+/","&#",$content);
echo "</textarea>";
?>