note 91956 added to function.htmlentities
| From: | montana | Date: | Thu, 02 Jul 2009 19:11:37 +0000 |
| Subject: | note 91956 added to function.htmlentities | ||
| Groups: | php.notes | ||
| Request: | Send a blank email to php-notes+get-157840@lists.php.net to get a copy of this message | ||
<?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 ) { //taken from mb_split page...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 $array;
}
//reworked slightly from Miguel Perez post on ord page
public function unicode_entity_replace($c) {
$h = ord($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 />";
//test various approaches to maintaining characters...
$result = htmlentities($content);
echo "htmlentities: ugh, not really what we're looking for:";
echo $result; //FAIL
$result = htmlentities($content,ENT_QUOTES, "UTF-8");
echo "<br /><br />";
echo "htmlentities UTF-8: not even close:";
echo $result; //FAIL
$result = htmlspecialchars($content);
echo "<br /><br />";
echo "htmlspecialcharacters: nope:";
echo $result; //FAIL
//mb convert encoding doesn't connect entities at all so that definitely won't work.
//what I want is for the characters to be maintained regardless of what the user enters...
$oUnicodeReplace = new unicode_replace_entities();
$content = $oUnicodeReplace->UTF8entities($content);
echo "<br /><br />unicode_replace_entities: this will work:<br /><br
/>";
echo $content;
echo "<br /><br />Hmmmn, Entities get replaced with 'literals' in
textarea FF3<br /><br />";
echo "<textarea style='width:300px;height:150px;'>";
echo $content; //still can't really submit this into the db like this
echo "</textarea>";
//for editing NCR's in a textarea
echo "<br /><br />";
echo "hack to maintain NCR's in textarea<br />";
echo "<textarea style='width:300px;height:150px;'>";
echo preg_replace("/(&#)+/","&#",$content);
echo "</textarea>";
----
Server IP: 209.41.74.194
Probable Submitter: 76.14.99.95
----
Manual Page -- http://www.php.net/manual/en/function.htmlentities.php
Edit -- https://master.php.net/note/edit/91956
Del: integrated -- https://master.php.net/note/delete/91956/integrated
Del: useless -- https://master.php.net/note/delete/91956/useless
Del: bad code -- https://master.php.net/note/delete/91956/bad+code
Del: spam -- https://master.php.net/note/delete/91956/spam
Del: non-english -- https://master.php.net/note/delete/91956/non-english
Del: in docs -- https://master.php.net/note/delete/91956/in+docs
Del: other reasons-- https://master.php.net/note/delete/91956
Reject -- https://master.php.net/note/reject/91956
Search -- https://master.php.net/manage/user-notes.php