+ */
+ $content = preg_replace("|body(\s*\{.*?\})|si", ".bodyclass\\1", $content);
+ $secremoveimg = "../images/" . _("sec_remove_eng.png");
+ /**
+ * Fix url('blah') declarations.
+ */
+ $content = preg_replace("|url\(([\'\"])\s*\S+script\s*:.*?([\'\"])\)|si",
+ "url(\\1$secremoveimg\\2)", $content);
+ /**
+ * Fix url('https*://.*) declarations but only if $view_unsafe_images
+ * is false.
+ */
+ if (!$view_unsafe_images){
+ $content = preg_replace("|url\(([\'\"])\s*https*:.*?([\'\"])\)|si",
+ "url(\\1$secremoveimg\\2)", $content);
+ }
+
+ /**
+ * Fix urls that refer to cid:
+ */
+ while (preg_match("|url\(([\'\"]\s*cid:.*?[\'\"])\)|si", $content,
+ $matches)){
+ $cidurl = $matches{1};
+ $httpurl = sq_cid2http($message, $id, $cidurl);
+ $content = preg_replace("|url\($cidurl\)|si",
+ "url($httpurl)", $content);
+ }
-/* This function trys to locate the entity_id of a specific mime element */
+ /**
+ * Fix stupid css declarations which lead to vulnerabilities
+ * in IE.
+ */
+ $match = Array('/expression/si',
+ '/behaviou*r/si',
+ '/binding/si');
+ $replace = Array('idiocy', 'idiocy', 'idiocy');
+ $content = preg_replace($match, $replace, $content);
+ return $content;
+}
-function find_ent_id( $id, $message ) {
+/**
+ * This function converts cid: url's into the ones that can be viewed in
+ * the browser.
+ *
+ * @param $message the message object
+ * @param $id the message id
+ * @param $cidurl the cid: url.
+ * @return a string with a http-friendly url
+ */
+function sq_cid2http($message, $id, $cidurl){
+ /**
+ * Get rid of quotes.
+ */
+ $quotchar = substr($cidurl, 0, 1);
+ $cidurl = str_replace($quotchar, "", $cidurl);
+ $cidurl = substr(trim($cidurl), 4);
+ $httpurl = $quotchar . "../src/download.php?absolute_dl=true&" .
+ "passed_id=$id&mailbox=" . urlencode($message->header->mailbox) .
+ "&passed_ent_id=" . find_ent_id($cidurl, $message) . $quotchar;
+ return $httpurl;
+}
- $ret = '';
- for ($i=0; $ret == '' && $i < count($message->entities); $i++) {
+/**
+ * This function changes the tag into a
tag since we
+ * can't really have a body-within-body.
+ *
+ * @param $attary an array of attributes and values of
+ * @return a modified array of attributes to be set for
+ */
+function sq_body2div($attary){
+ $me = "sq_body2div";
+ $divattary = Array("class"=>"'bodyclass'");
+ $bgcolor="#ffffff";
+ $text="#000000";
+ $styledef="";
+ if (is_array($attary) && sizeof($attary) > 0){
+ foreach ($attary as $attname=>$attvalue){
+ $quotchar = substr($attvalue, 0, 1);
+ $attvalue = str_replace($quotchar, "", $attvalue);
+ switch ($attname){
+ case "background":
+ $styledef .= "background-image: url('$attvalue'); ";
+ break;
+ case "bgcolor":
+ $styledef .= "background-color: $attvalue; ";
+ break;
+ case "text":
+ $styledef .= "color: $attvalue; ";
+ }
+ }
+ if (strlen($styledef) > 0){
+ $divattary{"style"} = "\"$styledef\"";
+ }
+ }
+ return $divattary;
+}
- if ( $message->entities[$i]->header->entity_id == '' ) {
- $ret = find_ent_id( $id, $message->entities[$i] );
+/**
+ * This is the main function and the one you should actually be calling.
+ * There are several variables you should be aware of an which need
+ * special description.
+ *
+ * Since the description is quite lengthy, see it here:
+ * http://www.mricon.com/html/phpfilter.html
+ *
+ * @param $body the string with HTML you wish to filter
+ * @param $tag_list see description above
+ * @param $rm_tags_with_content see description above
+ * @param $self_closing_tags see description above
+ * @param $force_tag_closing see description above
+ * @param $rm_attnames see description above
+ * @param $bad_attvals see description above
+ * @param $add_attr_to_tag see description above
+ * @param $message message object
+ * @param $id message id
+ * @return sanitized html safe to show on your pages.
+ */
+function sq_sanitize($body,
+ $tag_list,
+ $rm_tags_with_content,
+ $self_closing_tags,
+ $force_tag_closing,
+ $rm_attnames,
+ $bad_attvals,
+ $add_attr_to_tag,
+ $message,
+ $id
+ ){
+ $me = "sq_sanitize";
+ /**
+ * Normalize rm_tags and rm_tags_with_content.
+ */
+ @array_walk($rm_tags, 'sq_casenormalize');
+ @array_walk($rm_tags_with_content, 'sq_casenormalize');
+ @array_walk($self_closing_tags, 'sq_casenormalize');
+ /**
+ * See if tag_list is of tags to remove or tags to allow.
+ * false means remove these tags
+ * true means allow these tags
+ */
+ $rm_tags = array_shift($tag_list);
+ $curpos = 0;
+ $open_tags = Array();
+ $trusted = "\n";
+ $skip_content = false;
+ /**
+ * Take care of netscape's stupid javascript entities like
+ * &{alert('boo')};
+ */
+ $body = preg_replace("/&(\{.*?\};)/si", "&\\1", $body);
+
+ while (($curtag=sq_getnxtag($body, $curpos)) != FALSE){
+ list($tagname, $attary, $tagtype, $lt, $gt) = $curtag;
+ $free_content = substr($body, $curpos, $lt-$curpos);
+ /**
+ * Take care of . Edit the
+ * content before we apply it.
+ */
+ $free_content = sq_fixstyle($message, $id, $free_content);
+ }
+ if ($skip_content == false){
+ $trusted .= $free_content;
} else {
- if ( strcasecmp( $message->entities[$i]->header->id, $id ) == 0 )
- $ret = $message->entities[$i]->header->entity_id;
}
-
+ if ($tagname != FALSE){
+ if ($tagtype == 2){
+ if ($skip_content == $tagname){
+ /**
+ * Got to the end of tag we needed to remove.
+ */
+ $tagname = false;
+ $skip_content = false;
+ } else {
+ if ($skip_content == false){
+ if ($tagname == "body"){
+ $tagname = "div";
+ } else {
+ if (isset($open_tags{$tagname}) &&
+ $open_tags{$tagname} > 0){
+ $open_tags{$tagname}--;
+ } else {
+ $tagname = false;
+ }
+ }
+ } else {
+ }
+ }
+ } else {
+ /**
+ * $rm_tags_with_content
+ */
+ if ($skip_content == false){
+ /**
+ * See if this is a self-closing type and change
+ * tagtype appropriately.
+ */
+ if ($tagtype == 1
+ && in_array($tagname, $self_closing_tags)){
+ $tagtype=3;
+ }
+ /**
+ * See if we should skip this tag and any content
+ * inside it.
+ */
+ if ($tagtype == 1 &&
+ in_array($tagname, $rm_tags_with_content)){
+ $skip_content = $tagname;
+ } else {
+ if (($rm_tags == false
+ && in_array($tagname, $tag_list)) ||
+ ($rm_tags == true &&
+ !in_array($tagname, $tag_list))){
+ $tagname = false;
+ } else {
+ if ($tagtype == 1){
+ if (isset($open_tags{$tagname})){
+ $open_tags{$tagname}++;
+ } else {
+ $open_tags{$tagname}=1;
+ }
+ }
+ /**
+ * This is where we run other checks.
+ */
+ if (is_array($attary) && sizeof($attary) > 0){
+ $attary = sq_fixatts($tagname,
+ $attary,
+ $rm_attnames,
+ $bad_attvals,
+ $add_attr_to_tag,
+ $message,
+ $id
+ );
+ }
+ /**
+ * Convert body into div.
+ */
+ if ($tagname == "body"){
+ $tagname = "div";
+ $attary = sq_body2div($attary, $message, $id);
+ }
+ }
+ }
+ } else {
+ }
+ }
+ if ($tagname != false && $skip_content == false){
+ $trusted .= sq_tagprint($tagname, $attary, $tagtype);
+ }
+ } else {
+ }
+ $curpos = $gt+1;
+ }
+ $trusted .= substr($body, $curpos, strlen($body)-$curpos);
+ if ($force_tag_closing == true){
+ foreach ($open_tags as $tagname=>$opentimes){
+ while ($opentimes > 0){
+ $trusted .= '';
+ $opentimes--;
+ }
+ }
+ $trusted .= "\n";
}
+ $trusted .= "\n";
+ return $trusted;
+}
- return( $ret );
+/**
+ * This is a wrapper function to call html sanitizing routines.
+ *
+ * @param $body the body of the message
+ * @param $id the id of the message
+ * @return a string with html safe to display in the browser.
+ */
+function magicHTML($body, $id, $message){
+ global $attachment_common_show_images, $view_unsafe_images,
+ $has_unsafe_images;
+ /**
+ * Don't display attached images in HTML mode.
+ */
+ $attachment_common_show_images = false;
+ $tag_list = Array(
+ false,
+ "object",
+ "meta",
+ "html",
+ "head",
+ "base"
+ );
+
+ $rm_tags_with_content = Array(
+ "script",
+ "applet",
+ "embed",
+ "title"
+ );
+
+ $self_closing_tags = Array(
+ "img",
+ "br",
+ "hr",
+ "input"
+ );
+
+ $force_tag_closing = false;
+
+ $rm_attnames = Array(
+ "/.*/" =>
+ Array(
+ "/target/si",
+ "/^on.*/si",
+ "/^dynsrc/si",
+ "/^data.*/si"
+ )
+ );
+
+ $secremoveimg = "../images/" . _("sec_remove_eng.png");
+ $bad_attvals = Array(
+ "/.*/" =>
+ Array(
+ "/^src|background|href|action/i" =>
+ Array(
+ Array(
+ "|^([\'\"])\s*\.\./.*([\'\"])|si",
+ "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si",
+ "/^([\'\"])\s*mocha\s*:*.*([\'\"])/si",
+ "/^([\'\"])\s*about\s*:.*([\'\"])/si"
+ ),
+ Array(
+ "\\1$secremoveimg\\2",
+ "\\1$secremoveimg\\2",
+ "\\1$secremoveimg\\2",
+ "\\1$secremoveimg\\2"
+ )
+ ),
+ "/^style/si" =>
+ Array(
+ Array(
+ "/expression/si",
+ "/binding/si",
+ "/behaviou*r/si",
+ "|url\(([\'\"])\s*\.\./.*([\'\"])\)|si",
+ "/url\(([\'\"])\s*\S+script:.*([\'\"])\)/si"
+ ),
+ Array(
+ "idiocy",
+ "idiocy",
+ "idiocy",
+ "url(\\1$secremoveimg\\2)",
+ "url(\\1$secremoveimg\\2)"
+ )
+ )
+ )
+ );
+ if (!$view_unsafe_images){
+ /**
+ * Remove any references to http/https if view_unsafe_images set
+ * to false.
+ */
+ array_push($bad_attvals{'/.*/'}{'/^src|background|href|action/i'}[0],
+ '/^([\'\"])\s*https*:.*([\'\"])/si');
+ array_push($bad_attvals{'/.*/'}{'/^src|background|href|action/i'}[1],
+ "\\1$secremoveimg\\2");
+ array_push($bad_attvals{'/.*/'}{'/^style/si'}[0],
+ '/url\(([\'\"])\s*https*:.*([\'\"])\)/si');
+ array_push($bad_attvals{'/.*/'}{'/^style/si'}[1],
+ "url(\\1$secremoveimg\\2)");
+ }
+ $add_attr_to_tag = Array(
+ "/^a$/si" => Array('target'=>'"_new"')
+ );
+ $trusted = sq_sanitize($body,
+ $tag_list,
+ $rm_tags_with_content,
+ $self_closing_tags,
+ $force_tag_closing,
+ $rm_attnames,
+ $bad_attvals,
+ $add_attr_to_tag,
+ $message,
+ $id
+ );
+ if (preg_match("|$secremoveimg|si", $trusted)){
+ $has_unsafe_images = true;
+ }
+ return $trusted;
}
-?>
+?>
\ No newline at end of file