note 100389 deleted from function.htmlentities by danbrown
| From: | danbrown@php.net | Date: | Wed, 13 Oct 2010 22:08:53 +0000 |
| Subject: | note 100389 deleted from function.htmlentities by danbrown | ||
| References: | 1 | Groups: | php.notes |
| Request: | Send a blank email to php-notes+get-173198@lists.php.net to get a copy of this message | ||
Note Submitter: php dot net at softmoon-webware dot com
----
Special thanks to all those whose comments, concerns, and contributions went into this code, as well
as all those on this site.
You will need the arrays I posted in my earlier note:
$HTML_ENTS, $HTML_TAGS, and $Xchars
<?php /* encode to XHTML
for instructions, fully commented sourcecode, and test example, see:
http://softmoon-webware.com/php_functions-instructions.php/
http://softmoon-webware.com/php_functions.zip/
// this will encode all 'stray' (X)HTML entites as needed
// without effecting 'valid' existing markup. It will also
// apply nl2br 'intelegently', and format spaces to your liking.
/*note this alternative format for passing in options*/
Function XHTMLencode( $S, // array(userOpt=>value, ...) )
$nl_to_br=TRUE, $allowJS=TRUE, $collapse_spaces='toXHTML',
$xhtml=TRUE, $strip_formatting=TRUE, $charset='ISO-8859-1',
$tabspacing=2, $hardspace=" ", $skip_Quotes=FALSE ) {
if (func_num_args()==2 and is_array($nl_to_br)) {
$userArgs=$nl_to_br; $nl_to_br=TRUE;
$userOpts=array("nl_to_br", "allowJS", "collapse_spaces",
"xhtml",
"strip_formatting", "charset", "tabspacing",
"hardspace", "skip_DQuotes");
foreach ($userArgs as $var => $value) {
if (in_array($var, $userOpts)) $$var=$value; } }
$sl=strlen($S); $build=""; $SPflag=FALSE; $PREflag=TRUE; $inQuotes=FALSE;
$line_term=(strpos($S, chr(10))!==FALSE) ? 10 : 13;
$tagRegEx=($xhtml) ?
'/^<\/?([a-z]{1,10})([ \t\n\r]+[a-z]{2,12}=[ \t\n\r]*'
.'("[^\x00-\x1F"<>]*"|\'[^\x00-\x1F\'<>]*\'))*(
\/)?>/'
: '/^<\/?([a-z]{1,10})([ \t\n\r]+[^<>]*)?>/i';
for ($i=0; $i<$sl; $i++) { $cc=ord($sS=substr($S, $i));
if ($nl_to_br and $cc==0x0D and $PREflag) {
$build.=(($xhtml) ? "<br />" : "<br>"); $SPflag=FALSE; }
if ($collapse_spaces!==TRUE and $cc==0x09 and $tabspacing
and $PREflag and ($inQuotes or !$skip_Quotes)) {
$build.=( ($collapse_spaces==="toXHTML") ?
str_repeat((($SPflag) ? "$hardspace " : " $hardspace"), $tabspacing/2)
: str_repeat(" ", $tabspacing) );
continue; }
if ($strip_formatting and $cc<0x20 and $PREflag) continue;
if ($cc==0x20 and $collapse_spaces and $SPflag and $PREflag) {
if ($collapse_spaces==="toXHTML") {
if ($inQuotes or !$skip_Quotes) {$build.=$hardspace; $SPflag=FALSE;}
else $build.=" "; }
continue; }
if ($SPflag=($cc==0x20 or $cc==$line_term )) {
$build.=chr($cc); continue; }
if ($skip_Quotes and ($cc==0x22 or $cc==0x27)) {
$build.=chr($cc);
$inQuotes=($inQuotes===$cc) ? FALSE :
(($inQuotes===FALSE) ? $cc : $inQuotes);
continue; }
if ($xhtml and $cc>0x7F and $cc<0xA0) {
$build.=($Xchars[$cc]) ? $Xchars[$cc] : " "; continue; }
if (preg_match("/^&(#?[a-z0-9]{2,8});/i", $sS, $susp)
and (in_array($susp[1], $HTML_ENTS)
or preg_match('/^#(x[0-9a-f]{2,4}|[0-9]{2,4})$/i', $susp[1]))) {
$build.=$susp[0]; $i+=strlen($susp[0])-1; $SPflag=FALSE; continue; }
if (preg_match($tagRegEx, $sS, $susp)
and in_array($susp[1], $HTML_TAGS)) {
$sS=substr($susp[0], 1, strlen($susp[0])-2);
$build.="<"
.XHTMLencode(($allowJS) ? $sS : preg_replace(
'/on(click|dblclick|keydown|keypress|keyup|mousedown|'
.'mousemove|mouseout|mouseover|mouseup|'
.'focus|blur)[ \t\n\r]*=[ \t\n\r]*([\'"]).*\2/i',
"", preg_replace(
'/(href|src)[ \t\n\r]*=[ \t\n\r]*([\'"])javascript:.*\2/i',
"$1=''", $sS)),
FALSE, $allowJS, $collapse_spaces, $xhtml, $strip_formatting,
$charset, $tabspacing, $hardspace, TRUE)
.">";
$i+=strlen($susp[0])-1; $SPflag=FALSE;
if ($nl_to_br
and ($x=strpos($sS, "pre"))!==FALSE and $x<2) $PREflag=(boolean)$x;
continue; }
$build.=htmlentities(substr($sS, 0, 1), ENT_QUOTES, $charset); }
return $build; }
?>