note 92105 added to function.htmlentities
| From: | montana at osu1 dot php dot net | Date: | Thu, 09 Jul 2009 04:54:15 +0000 |
| Subject: | note 92105 added to function.htmlentities | ||
| Groups: | php.notes | ||
| Request: | Send a blank email to php-notes+get-158090@lists.php.net to get a copy of this message | ||
under what circumstances would someone want a ntilde [ñ] to be converted into
"ñ" as htmlentities does?
the correct method of translation should return the accurate NCR for the multibyte unicode sequence
which in this case is ñ
<?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>baño baño baño</strong>æ¥æ¬èª = nihongo
da ze.<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>";
?>
----
Server IP: 208.69.120.35
Probable Submitter: 76.14.99.95
----
Manual Page -- http://www.php.net/manual/en/function.htmlentities.php
Edit -- https://master.php.net/note/edit/92105
Del: integrated -- https://master.php.net/note/delete/92105/integrated
Del: useless -- https://master.php.net/note/delete/92105/useless
Del: bad code -- https://master.php.net/note/delete/92105/bad+code
Del: spam -- https://master.php.net/note/delete/92105/spam
Del: non-english -- https://master.php.net/note/delete/92105/non-english
Del: in docs -- https://master.php.net/note/delete/92105/in+docs
Del: other reasons-- https://master.php.net/note/delete/92105
Reject -- https://master.php.net/note/reject/92105
Search -- https://master.php.net/manage/user-notes.php