$encoding = '', $size = 0, $to = array(), $from = '', $date = '',
$cc = array(), $bcc = array(), $reply_to = '', $subject = '',
$id = 0, $mailbox = '', $description = '', $filename = '',
- $entity_id = 0, $message_id = 0, $name = '', $priority = 3;
+ $entity_id = 0, $message_id = 0, $name = '', $priority = 3, $type = '';
}
class message {
*/
function mime_structure ($imap_stream, $header) {
- sqimap_messages_flag ($imap_stream, $header->id, $header->id, 'Seen');
$ssid = sqimap_session_id();
$lsid = strlen( $ssid );
$id = $header->id;
// isolate the body structure and remove beginning and end parenthesis
$read = trim(substr ($read, strpos(strtolower($read), 'bodystructure') + 13));
+
$read = trim(substr ($read, 0, -1));
$end = mime_match_parenthesis(0, $read);
while ($end == strlen($read)-1) {
* to mime_get_elements()
*/
function mime_parse_structure ($structure, $ent_id) {
-
+ global $mailbox;
+ $properties = array();
$msg = new message();
if ($structure{0} == '(') {
+ $old_ent_id = $ent_id;
$ent_id = mime_new_element_level($ent_id);
$start = $end = -1;
do {
$start = $end+1;
$end = mime_match_parenthesis ($start, $structure);
- $element = substr($structure, $start+1, ($end - $start)-1);
- $ent_id = mime_increment_id ($ent_id);
- $newmsg = mime_parse_structure ($element, $ent_id);
- $msg->addEntity ($newmsg);
+ /* check if we are dealing with a new entity-level */
+ $i = strrpos($ent_id,'.');
+ if ($i>0) {
+ $ent = substr($ent_id, $i+1);
+ } else {
+ $ent = '';
+ }
+ /* add "forgotten" parent entities (alternative and relative) */
+ if ($ent == '0') {
+ /* new entity levels have information about the type (type1) and
+ * the properties. This information is situated at the end of the
+ * structure string like for example (example between the brackets)
+ * [ "RELATED" ("BOUNDARY" "myboundary" "TYPE" "plain/html") ]
+ */
+
+ /* get the involved properties for parsing to mime_get_properties */
+ $startprop = strrpos($structure,'(');
+ $properties_str = substr($structure,$startprop);
+ $endprop = mime_match_parenthesis ($startprop, $structure);
+ $propstr = substr($structure, $startprop + 1, ($endprop - $startprop)-1);
+ /* cut off the used properties */
+ if ($startprop) {
+ $structure_end = substr($structure, $endprop+2);
+ $structure = trim(substr($structure,0,$startprop));
+ }
+
+ /* get type1 */
+ $pos = strrpos($structure,' ');
+ $type1 = strtolower(substr($structure, $pos+2, (count($structure)-2)));
+
+ /* cut off type1 */
+ if ($pos && $startprop) {
+ $structure = trim(substr($structure, 0, $pos));
+ }
+
+ /* process the found information */
+ $properties = mime_get_props($properties, $properties_str);
+ if (count($properties)>0) {
+ $msg->header->entity_id = $old_ent_id;
+ $msg->header->type0 = 'multipart';
+ $msg->header->type1 = $type1;
+ for ($i=0; $i < count($properties); $i++) {
+ $msg->header->{$properties[$i]['name']} = $properties[$i]['value'];
+ }
+ }
+ $structure = $structure . ' ' . $structure_end;
+ }
+ $element = substr($structure, $start+1, ($end - $start)-1);
+ $ent_id = mime_increment_id ($ent_id);
+ $newmsg = mime_parse_structure ($element, $ent_id);
+ /* set mailbox in case of message/rfc822 entities */
+ if (isset($newmsg->header->type0) && isset($newmsg->header->type1)) {
+ if ($newmsg->header->type0 == 'message' && $newmsg->header->type1 == 'rfc822') {
+ $newmsg->header->mailbox=$mailbox;
+ }
+ }
+ $msg->addEntity ($newmsg);
+
} while ($structure{$end+1} == '(');
} else {
// parse the elements
- $msg = mime_get_element ($structure, $msg, $ent_id);
+ $msg = mime_get_element ($structure, $msg, $ent_id);
}
return $msg;
}
+
/* Increments the element ID. An element id can look like any of
* the following: 1, 1.2, 4.3.2.4.1, etc. This function increments
* the last number of the element id, changing 1.2 to 1.3.
$msg->header = new msg_header();
$msg->header->entity_id = $ent_id;
$properties = array();
-
while (strlen($structure) > 0) {
$structure = trim($structure);
$char = $structure{0};
$text = "";
}
// loop through the additional properties and put those in the various headers
- if ($msg->header->type0 != 'message') {
- for ($i=0; $i < count($properties); $i++) {
- $msg->header->{$properties[$i]['name']} = $properties[$i]['value'];
- }
+ for ($i=0; $i < count($properties); $i++) {
+ $msg->header->{$properties[$i]['name']} = $properties[$i]['value'];
}
return $msg;
while (strlen($structure) > 0) {
$structure = trim($structure);
$char = $structure{0};
-
if ($char == '"') {
$pos = 1;
$tmp = '';
$value .= $char;
$pos++;
}
- $structure = trim(substr($structure, strlen($tmp) + 2));
-
+ $structure = trim(substr($structure, strlen($value) + 2));
$k = count($props);
$props[$k]['name'] = strtolower($tmp);
$props[$k]['value'] = $value;
+ if ($structure != '') {
+ mime_get_props($props, $structure);
+ } else {
+ return $props;
+ }
} else if ($char == '(') {
$end = mime_match_parenthesis (0, $structure);
$sub = substr($structure, 1, $end-1);
- if (! isset($props))
- $props = array();
- $props = mime_get_props($props, $sub);
- $structure = substr($structure, strlen($sub) + 2);
+ if (! isset($props))
+ $props = array();
+ $props = mime_get_props($props, $sub);
+ $structure = substr($structure, strlen($sub) + 2);
+ return $props;
}
- return $props;
} else if ($char == '(') {
$end = mime_match_parenthesis (0, $structure);
$sub = substr($structure, 1, $end-1);
$data = sqimap_run_command ($imap_stream, $cmd, true, $response, $message);
do {
- $topline = array_shift( $data );
- } while( $topline && $topline == '*' && !preg_match( '/\\* [0-9] FETCH.*/i', $topline )) ;
+ $topline = trim(array_shift( $data ));
+ } while( $topline && $topline[0] == '*' && !preg_match( '/\* [0-9]+ FETCH.*/i', $topline )) ;
$wholemessage = implode('', $data);
if (ereg('\\{([^\\}]*)\\}', $topline, $regs)) {
* if ( $base <> '' ) {
* $ret = "<base href=\"$base\">" . $ret;
* }
-* */
+* */
}
} else if (ereg('"([^"]*)"', $topline, $regs)) {
$ret = $regs[1];
// This is here for debugging purposese. It will print out a list
// of all the entity IDs that are in the $message object.
-/*
+
function listEntities ($message) {
if ($message) {
if ($message->header->entity_id)
}
}
}
-*/
+
/* returns a $message object for a particular entity id */
function getEntity ($message, $ent_id) {
if ($message) {
- if ($message->header->entity_id == $ent_id && strlen($ent_id) == strlen($message->header->entity_id)) {
+ if ($message->header->entity_id == $ent_id && strlen($ent_id) == strlen($message->header->entity_id))
+ {
return $message;
} else {
for ($i = 0; isset($message->entities[$i]); $i++) {
$msg = getEntity ($message->entities[$i], $ent_id);
if ($msg) {
return $msg;
- }
+ }
}
}
}
* figures out what entity to display and returns the $message object
* for that entity.
*/
-function findDisplayEntity ($message, $textOnly = 1) {
+function findDisplayEntity ($msg, $textOnly = 1) {
global $show_html_default;
$entity = 0;
- if ($message) {
- if ( $message->header->type0 == 'multipart' &&
- ( $message->header->type1 == 'alternative' ||
- $message->header->type1 == 'related' ) &&
+ if ($msg) {
+ if ( $msg->header->type0 == 'multipart' &&
+ ( $msg->header->type1 == 'alternative' ||
+ $msg->header->type1 == 'mixed' ||
+ $msg->header->type1 == 'related' ) &&
$show_html_default && ! $textOnly ) {
- $entity = findDisplayEntityHTML($message);
+ $entity = findDisplayEntityHTML($msg);
}
-
+
// Show text/plain or text/html -- the first one we find.
if ( $entity == 0 &&
- $message->header->type0 == 'text' &&
- ( $message->header->type1 == 'plain' ||
- $message->header->type1 == 'html' ) &&
- isset($message->header->entity_id) ) {
- $entity = $message->header->entity_id;
+ $msg->header->type0 == 'text' &&
+ ( $msg->header->type1 == 'plain' ||
+ $msg->header->type1 == 'html' ) &&
+ isset($msg->header->entity_id) ) {
+ $entity = $msg->header->entity_id;
}
$i = 0;
- while ($entity == 0 && isset($message->entities[$i]) ) {
- $entity = findDisplayEntity($message->entities[$i], $textOnly);
+ while ($entity == 0 && isset($msg->entities[$i]) ) {
+ $entity = findDisplayEntity($msg->entities[$i], $textOnly);
$i++;
}
}
return $message->header->entity_id;
}
for ($i = 0; isset($message->entities[$i]); $i ++) {
+ if ( $message->header->type0 == 'message' &&
+ $message->header->type1 == 'rfc822' &&
+ isset($message->header->entity_id)) {
+ return 0;
+ }
$entity = findDisplayEntityHTML($message->entities[$i]);
if ($entity != 0) {
return $entity;
}
}
-
+
return 0;
}
+/*
+ * translateText
+ * Extracted from strings.php 23/03/2002
+ */
+
+function translateText(&$body, $wrap_at, $charset) {
+ global $where, $what; /* from searching */
+ global $color; /* color theme */
+
+ require_once('../functions/url_parser.php');
+
+ $body_ary = explode("\n", $body);
+ $PriorQuotes = 0;
+ for ($i=0; $i < count($body_ary); $i++) {
+ $line = $body_ary[$i];
+ if (strlen($line) - 2 >= $wrap_at) {
+ sqWordWrap($line, $wrap_at);
+ }
+ $line = charset_decode($charset, $line);
+ $line = str_replace("\t", ' ', $line);
+
+ parseUrl ($line);
+
+ $Quotes = 0;
+ $pos = 0;
+ $j = strlen( $line );
+
+ while ( $pos < $j ) {
+ if ($line[$pos] == ' ') {
+ $pos ++;
+ } else if (strpos($line, '>', $pos) === $pos) {
+ $pos += 4;
+ $Quotes ++;
+ } else {
+ break;
+ }
+ }
+
+ if ($Quotes > 1) {
+ if (! isset($color[14])) {
+ $color[14] = '#FF0000';
+ }
+ $line = '<FONT COLOR="' . $color[14] . '">' . $line . '</FONT>';
+ } elseif ($Quotes) {
+ if (! isset($color[13])) {
+ $color[13] = '#800000';
+ }
+ $line = '<FONT COLOR="' . $color[13] . '">' . $line . '</FONT>';
+ }
+
+ $body_ary[$i] = $line;
+ }
+ $body = '<pre>' . implode("\n", $body_ary) . '</pre>';
+}
+
+/* debugfunction for looping through entities and displaying correct entities */
+function listMyEntities ($message) {
+
+if ($message) {
+ if ($message->header->entity_id) {
+ echo "<tt>" . $message->header->entity_id . ' : ' . $message->header->type0 . '/' . $message->header->type1 . '<br>';
+ }
+ if (!($message->header->type0 == 'message' && $message->header->type1 == 'rfc822')) {
+ if (isset($message->header->boundary) ) {
+ $ent_id = $message->header->entity_id;
+ $var = $message->header->boundary;
+ if ($var !='')
+ echo "<b>$ent_id boundary = $var</b><br>";
+ }
+ if (isset($message->header->type) ) {
+ $var = $message->header->type;
+ if ($var !='')
+ echo "<b>$ent_id type = $var</b><br>";
+ }
+ for ($i = 0; $message->entities[$i]; $i++) {
+ $msg = listMyEntities($message->entities[$i]);
+ }
+
+ if ($msg ) return $msg;
+ }
+}
+
+}
+
+
+
/* This returns a parsed string called $body. That string can then
be displayed as the actual message in the HTML. It contains
everything needed, including HTML Tags, Attachments at the
// this if statement checks for the entity to show as the
// primary message. To add more of them, just put them in the
// order that is their priority.
- global $startMessage, $username, $key, $imapServerAddress, $imapPort,
- $show_html_default;
-
+ global $startMessage, $username, $key, $imapServerAddress, $imapPort, $body,
+ $show_html_default, $has_unsafe_images, $view_unsafe_images, $sort;
+
+ $has_unsafe_images = 0;
+
$id = $message->header->id;
+
$urlmailbox = urlencode($message->header->mailbox);
-
// Get the right entity and redefine message to be this entity
// Pass the 0 to mean that we want the 'best' viewable one
$ent_num = findDisplayEntity ($message, 0);
$body_message = getEntity($message, $ent_num);
if (($body_message->header->type0 == 'text') ||
($body_message->header->type0 == 'rfc822')) {
-
$body = mime_fetch_body ($imap_stream, $id, $ent_num);
$body = decodeBody($body, $body_message->header->encoding);
$hookResults = do_hook("message_body", $body);
$body = $hookResults[1];
-
// If there are other types that shouldn't be formatted, add
// them here
if ($body_message->header->type1 == 'html') {
}
$body .= "<CENTER><SMALL><A HREF=\"../src/download.php?absolute_dl=true&passed_id=$id&passed_ent_id=$ent_num&mailbox=$urlmailbox&showHeaders=1\">". _("Download this as a file") ."</A></SMALL></CENTER><BR>";
+ if ($has_unsafe_images) {
+ if ($view_unsafe_images) {
+ $body .= "<CENTER><SMALL><A HREF=\"read_body.php?passed_id=$id&mailbox=$urlmailbox&sort=$sort&startMessage=$startMessage&show_more=0\">". _("Hide Unsafe Images") ."</A></SMALL></CENTER><BR>\n";
+ } else {
+ $body .= "<CENTER><SMALL><A HREF=\"read_body.php?passed_id=$id&mailbox=$urlmailbox&sort=$sort&startMessage=$startMessage&show_more=0&view_unsafe_images=1\">". _("View Unsafe Images") ."</A></SMALL></CENTER><BR>\n";
+ }
+ }
/** Display the ATTACHMENTS: message if there's more than one part **/
- if (isset($message->entities[0])) {
+ if (isset($message->entities[1])) {
$body .= formatAttachments ($message, $ent_num, $message->header->mailbox, $id);
}
} else {
"</TABLE></TD></TR></TABLE>";
} else if ($message) {
+ $header = $message->header;
+ $type0 = strtolower($header->type0);
+ $type1 = strtolower($header->type1);
+ $name = '';
+ if (isset($header->name)) {
+ $name = decodeHeader($header->name);
+ }
+ if ($type0 =='message' && $type1 == 'rfc822') {
+
+ $filename = decodeHeader($message->header->filename);
+ if (trim($filename) == '') {
+ if (trim($name) == '') {
+ $display_filename = 'untitled-[' . $message->header->entity_id . ']' ;
+ } else {
+ $display_filename = $name;
+ $filename = $name;
+ }
+ } else {
+ $display_filename = $filename;
+ }
+
+ $urlMailbox = urlencode($mailbox);
+ $ent = urlencode($message->header->entity_id);
+
+ $DefaultLink =
+ "../src/download.php?startMessage=$startMessage&passed_id=$id&mailbox=$urlMailbox&passed_ent_id=$ent";
+ if ($where && $what) {
+ $DefaultLink .= '&where=' . urlencode($where) . '&what=' . urlencode($what);
+ }
+ $Links['download link']['text'] = _("download");
+ $Links['download link']['href'] =
+ "../src/download.php?absolute_dl=true&passed_id=$id&mailbox=$urlMailbox&passed_ent_id=$ent";
+ $ImageURL = '';
+
+ /* this executes the attachment hook with a specific MIME-type.
+ * if that doens't have results, it tries if there's a rule
+ * for a more generic type. */
+ $HookResults = do_hook("attachment $type0/$type1", $Links,
+ $startMessage, $id, $urlMailbox, $ent, $DefaultLink, $display_filename, $where, $what);
+ if(count($HookResults[1]) <= 1) {
+ $HookResults = do_hook("attachment $type0/*", $Links,
+ $startMessage, $id, $urlMailbox, $ent, $DefaultLink,
+ $display_filename, $where, $what);
+ }
- if (!$message->entities) {
+ $Links = $HookResults[1];
+ $DefaultLink = $HookResults[6];
+
+ $body .= '<TR><TD> </TD><TD>' .
+ "<A HREF=\"$DefaultLink\">$display_filename</A> </TD>" .
+ '<TD><SMALL><b>' . show_readable_size($message->header->size) .
+ '</b> </small></TD>' .
+ "<TD><SMALL>[ $type0/$type1 ] </SMALL></TD>" .
+ '<TD><SMALL>';
+ if ($message->header->description) {
+ $body .= '<b>' . htmlspecialchars(_($message->header->description)) . '</b>';
+ }
+ $body .= '</SMALL></TD><TD><SMALL> ';
+
+
+ $SkipSpaces = 1;
+ foreach ($Links as $Val) {
+ if ($SkipSpaces) {
+ $SkipSpaces = 0;
+ } else {
+ $body .= ' | ';
+ }
+ $body .= '<a href="' . $Val['href'] . '">' . $Val['text'] . '</a>';
+ }
+
+ unset($Links);
+
+ $body .= "</SMALL></TD></TR>\n";
+
+ return( $body );
+
+ } elseif (!$message->entities) {
$type0 = strtolower($message->header->type0);
$type1 = strtolower($message->header->type1);
$DefaultLink =
"../src/download.php?startMessage=$startMessage&passed_id=$id&mailbox=$urlMailbox&passed_ent_id=$ent";
if ($where && $what) {
- $DefaultLink .= '&where=' . urlencode($where) . '&what=' . urlencode($what);
+ $DefaultLink = '&where='. urlencode($where).'&what='.urlencode($what);
}
$Links['download link']['text'] = _("download");
$Links['download link']['href'] =
/*
* This functions decode strings that is encoded according to
* RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text).
+ * Patched by Christian Schmidt <christian@ostenfeld.dk> 23/03/2002
*/
function decodeHeader ($string, $utfencode=true) {
+ if (is_array($string)) {
+ $string = implode("\n", $string);
+ }
+ $i = 0;
+ while (preg_match('/^(.{' . $i . '})(.*)=\?([^?]*)\?(Q|B)\?([^?]*)\?=/Ui',
+ $string, $res)) {
+ $prefix = $res[1];
+ // Ignore white-space between consecutive encoded-words
+ if (strspn($res[2], " \t") != strlen($res[2])) {
+ $prefix .= $res[2];
+ }
-if ( is_array( $string ) ) {
- $string = implode("\n", $string );
-}
-
-if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=',
- $string, $res)) {
- if (ucfirst($res[2]) == 'B') {
- $replace = base64_decode($res[3]);
- } else {
- $replace = str_replace('_', ' ', $res[3]);
- // Convert lowercase Quoted Printable to uppercase for
- // quoted_printable_decode to understand it.
- while (ereg("(=(([0-9][abcdef])|([abcdef][0-9])|([abcdef][abcdef])))",
- $replace, $res)) {
- $replace = str_replace($res[1], strtoupper($res[1]), $replace);
+ if (ucfirst($res[4]) == 'B') {
+ $replace = base64_decode($res[5]);
+ } else {
+ $replace = str_replace('_', ' ', $res[5]);
+ $replace = preg_replace('/=([0-9a-f]{2})/ie', 'chr(hexdec("\1"))',
+ $replace);
+ /* Only encode into entities by default. Some places
+ don't need the encoding, like the compose form. */
+ if ($utfencode) {
+ $replace = charset_decode($res[3], $replace);
+ }
}
- $replace = quoted_printable_decode($replace);
- }
- /* Only encode into entities by default. Some places
- don't need the encoding, like the compose form. */
- if ($utfencode){
- $replace = charset_decode ($res[1], $replace);
+ $string = $prefix . $replace . substr($string, strlen($res[0]));
+ $i = strlen($prefix) + strlen($replace);
}
-
- // Remove the name of the character set.
- $string = eregi_replace ('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=',
- $replace, $string);
-
- // In case there should be more encoding in the string: recurse
- $string = decodeHeader($string);
-}
-
-return ($string);
+ return( $string );
}
/*
return( $string );
}
-/*
- Strips dangerous tags from html messages.
-*/
-function MagicHTML( $body, $id ) {
-
- global $message, $HTTP_SERVER_VARS,
- $attachment_common_show_images;
-
- $attachment_common_show_images =
- FALSE; // Don't display attached images in HTML mode
- $j = strlen( $body ); // Legnth of the HTML
- $ret = ''; // Returned string
- $bgcolor = '#ffffff'; // Background style color (defaults to white)
- $textcolor = '#000000'; // Foreground style color (defaults to black)
- $leftmargin = ''; // Left margin style
- $title = ''; // HTML title if any
+/* This function trys to locate the entity_id of a specific mime element */
- $i = 0;
- while ( $i < $j ) {
- if ( $body{$i} == '<' ) {
- $pos = $i + 1;
- $tag = '';
- while ($body{$pos} == ' ' || $body{$pos} == "\t" ||
- $body{$pos} == "\n" ) {
- $pos ++;
- }
- while (strlen($tag) < 4 && $body{$pos} != ' ' &&
- $body{$pos} != "\t" && $body{$pos} != "\n" &&
- $pos < $j ) {
- $tag .= $body{$pos};
- $pos ++;
- }
- switch( strtoupper( $tag ) ) {
- // Strips the entire tag and contents
- case 'APPL':
- case 'EMBB':
- case 'FRAM':
- case 'SCRI':
- case 'OBJE':
- $etg = '/' . $tag;
- while ( $body{$i+1}.$body{$i+2}.$body{$i+3}.$body{$i+4}.$body{$i+5} <> $etg &&
- $i < $j ) $i++;
- while ( $i < $j && $body{++$i} <> '>' );
- // $ret .= "<!-- $tag removed -->";
- break;
- // Substitute Title
- case 'TITL':
- $i += 5;
- while ( $body{$i} <> '>' && // </title>
- $i < $j )
- $i++;
- $i++;
- $title = '';
- while ( $body{$i} <> '<' && // </title>
- $i < $j ) {
- $title .= $body{$i};
- $i++;
- }
- $i += 7;
- break;
- // Destroy these tags
- case 'HTML':
- case 'HEAD':
- case '/HTM':
- case '/HEA':
- case '!DOC':
- case 'META':
- //case 'DIV ':
- //case '/DIV':
- case '!-- ':
- $i += 4;
- while ( $body{$i} <> '>' &&
- $i < $j )
- $i++;
- // $i++;
- break;
- case 'STYL':
- $i += 5;
- while ( $body{$i} <> '>' && // </title>
- $i < $j )
- $i++;
- $i++;
- // We parse the style to look for interesting stuff
- $styleblk = '';
- while ( $body{$i} <> '>' &&
- $i < $j ) {
- // First we get the name of the style
- $style = '';
- while ( $body{$i} <> '>' &&
- $body{$i} <> '<' &&
- $body{$i} <> '{' &&
- $i < $j ) {
- if ( isnoSep( $body{$i} ) )
- $style .= $body{$i};
- $i++;
- }
- stripComments( $i, $j, $body );
- $style = strtoupper( trim( $style ) );
- if ( $style == 'BODY' ) {
- // Next we look into the definitions of the body style
- while ( $body{$i} <> '>' &&
- $body{$i} <> '}' &&
- $i < $j ) {
- // We look for the background color if any.
- if ( substr( $body, $i, 17 ) == 'BACKGROUND-COLOR:' ) {
- $i += 17;
- $bgcolor = getStyleData( $i, $j, $body );
- } elseif ( substr( $body, $i, 12 ) == 'MARGIN-LEFT:' ) {
- $i += 12;
- $leftmargin = getStyleData( $i, $j, $body );
- }
- $i++;
- }
- } else {
- // Other style are mantained
- $styleblk .= "$style ";
- while ( $body{$i} <> '>' &&
- $body{$i} <> '<' &&
- $body{$i} <> '}' &&
- $i < $j ) {
- $styleblk .= $body{$i};
- $i++;
- }
- $styleblk .= $body{$i};
- }
- stripComments( $i, $j, $body );
- if ( $body{$i} <> '>' )
- $i++;
- }
- if ( $styleblk <> '' )
- $ret .= "<style>$styleblk";
- break;
- case 'BODY':
- if ( $title <> '' )
- $ret .= '<b>' . _("Title:") . " </b>$title<br>\n";
- $ret .= "<TABLE";
- $i += 5;
- if (! isset($base)) {
- $base = '';
- }
- $ret .= stripEvent( $i, $j, $body, $id, $base );
- $ret .= " bgcolor=$bgcolor width=\"100%\"><tr>";
- if ( $leftmargin <> '' )
- $ret .= "<td width=$leftmargin> </td>";
- $ret .= '<td>';
- if (strtolower($bgcolor) == 'ffffff' ||
- strtolower($bgcolor) == '#ffffff')
- $ret .= '<font color=#000000>';
- break;
- case 'BASE':
- $i += 5;
- $base = '';
- while ( !isNoSep( $body{$i} ) &&
- $i < $j ) {
- $i++;
- }
- if ( strcasecmp( substr( $base, 0, 4 ), 'href' ) ) {
- $i += 5;
- while ( !isNoSep( $body{$i} ) &&
- $i < $j ) {
- $i++;
- }
- while ( $body{$i} <> '>' &&
- $i < $j ) {
- if ( $body{$i} <> '"' ) {
- $base .= $body{$i};
- }
- $i++;
- }
- // Debuging $ret .= "<!-- base == $base -->";
- if ( strcasecmp( substr( $base, 0, 4 ), 'file' ) <> 0 ) {
- $ret .= "\n<BASE HREF=\"$base\">\n";
- }
- }
- break;
- case '/BOD':
- $ret .= '</font></td></tr></TABLE>';
- $i += 6;
- break;
- default:
- // Following tags can contain some event handler, lets search it
- stripComments( $i, $j, $body );
- if (! isset($base)) {
- $base = '';
- }
- $ret .= stripEvent( $i, $j, $body, $id, $base ) . '>';
- // $ret .= "<!-- $tag detected -->";
- }
+function find_ent_id( $id, $message ) {
+ $ret = '';
+ for ($i=0; $ret == '' && $i < count($message->entities); $i++) {
+ if (( $message->entities[$i]->header->type1 == 'alternative') ||
+ ( $message->entities[$i]->header->type1 == 'related') ||
+ ( $message->entities[$i]->header->type1 == 'mixed')) {
+ $ret = find_ent_id( $id, $message->entities[$i] );
} else {
- $ret .= $body{$i};
+ if ( strcasecmp( $message->entities[$i]->header->id, $id ) == 0 )
+ $ret = $message->entities[$i]->header->entity_id;
}
- $i++;
- }
-return( "\n\n<!-- HTML Output ahead -->\n" .
- $ret .
- /* Base is illegal within HTML
- "\n<!-- END of HTML Output --><base href=\"".
- get_location() . '/'.
- "\">\n\n" );
- */
- "\n<!-- END of HTML Output -->\n\n" );
+ }
+ return( $ret );
}
-function isNoSep( $char ) {
+/**
+ ** HTMLFILTER ROUTINES
+ */
- switch( $char ) {
- case ' ':
- case "\n":
- case "\t":
- case "\r":
- case '>':
- case '"':
- return( FALSE );
- break;
- default:
- return( TRUE );
+/**
+ * This function returns the final tag out of the tag name, an array
+ * of attributes, and the type of the tag. This function is called by
+ * sq_sanitize internally.
+ *
+ * @param $tagname the name of the tag.
+ * @param $attary the array of attributes and their values
+ * @param $tagtype The type of the tag (see in comments).
+ * @return a string with the final tag representation.
+ */
+function sq_tagprint($tagname, $attary, $tagtype){
+ $me = "sq_tagprint";
+ if ($tagtype == 2){
+ $fulltag = '</' . $tagname . '>';
+ } else {
+ $fulltag = '<' . $tagname;
+ if (is_array($attary) && sizeof($attary)){
+ $atts = Array();
+ while (list($attname, $attvalue) = each($attary)){
+ array_push($atts, "$attname=$attvalue");
+ }
+ $fulltag .= ' ' . join(" ", $atts);
+ }
+ if ($tagtype == 3){
+ $fulltag .= " /";
+ }
+ $fulltag .= ">";
}
-
+ return $fulltag;
}
-/*
- The following function is usefull to remove extra data that can cause
- html not to display properly. Especialy with MS stuff.
-*/
-
-function stripComments( &$i, $j, &$body ) {
+/**
+ * A small helper function to use with array_walk. Modifies a by-ref
+ * value and makes it lowercase.
+ *
+ * @param $val a value passed by-ref.
+ * @return void since it modifies a by-ref value.
+ */
+function sq_casenormalize(&$val){
+ $val = strtolower($val);
+}
- while ( $body{$i}.$body{$i+1}.$body{$i+2}.$body{$i+3} == '<!--' &&
- $i < $j ) {
- $i += 5;
- while ( $body{$i-2}.$body{$i-1}.$body{$i} <> '-->' &&
- $i < $j )
- $i++;
- $i++;
+/**
+ * This function skips any whitespace from the current position within
+ * a string and to the next non-whitespace value.
+ *
+ * @param $body the string
+ * @param $offset the offset within the string where we should start
+ * looking for the next non-whitespace character.
+ * @return the location within the $body where the next
+ * non-whitespace char is located.
+ */
+function sq_skipspace($body, $offset){
+ $me = "sq_skipspace";
+ preg_match("/^(\s*)/s", substr($body, $offset), $matches);
+ if (sizeof($matches{1})){
+ $count = strlen($matches{1});
+ $offset += $count;
}
-
- return;
-
+ return $offset;
}
-/* Gets the style data of a specific style */
-
-function getStyleData( &$i, $j, &$body ) {
-
- // We skip spaces
- while ( $body{$i} <> '>' && !isNoSep( $body{$i} ) &&
- $i < $j ) {
- $i++;
- }
- // And get the color
- $ret = '';
- while ( isNoSep( $body{$i} ) &&
- $i < $j ) {
- $ret .= $body{$i};
- $i++;
+/**
+ * This function looks for the next character within a string. It's
+ * really just a glorified "strpos", except it catches if failures
+ * nicely.
+ *
+ * @param $body The string to look for needle in.
+ * @param $offset Start looking from this position.
+ * @param $needle The character/string to look for.
+ * @return location of the next occurance of the needle, or
+ * strlen($body) if needle wasn't found.
+ */
+function sq_findnxstr($body, $offset, $needle){
+ $me = "sq_findnxstr";
+ $pos = strpos($body, $needle, $offset);
+ if ($pos === FALSE){
+ $pos = strlen($body);
}
-
- return( $ret );
+ return $pos;
}
-/*
-Private function for strip_dangerous_tag. Look for event based coded and "remove" it
-change on with no (onload -> noload)
-*/
-
-function stripEvent( &$i, $j, &$body, $id, $base ) {
-
- global $message, $base_uri;
+/**
+ * This function takes a PCRE-style regexp and tries to match it
+ * within the string.
+ *
+ * @param $body The string to look for needle in.
+ * @param $offset Start looking from here.
+ * @param $reg A PCRE-style regex to match.
+ * @return Returns a false if no matches found, or an array
+ * with the following members:
+ * - integer with the location of the match within $body
+ * - string with whatever content between offset and the match
+ * - string with whatever it is we matched
+ */
+function sq_findnxreg($body, $offset, $reg){
+ $me = "sq_findnxreg";
+ $matches = Array();
+ $retarr = Array();
+ preg_match("%^(.*?)($reg)%s", substr($body, $offset), $matches);
+ if (!$matches{0}){
+ $retarr = false;
+ } else {
+ $retarr{0} = $offset + strlen($matches{1});
+ $retarr{1} = $matches{1};
+ $retarr{2} = $matches{2};
+ }
+ return $retarr;
+}
- $ret = '';
+/**
+ * This function looks for the next tag.
+ *
+ * @param $body String where to look for the next tag.
+ * @param $offset Start looking from here.
+ * @return false if no more tags exist in the body, or
+ * an array with the following members:
+ * - string with the name of the tag
+ * - array with attributes and their values
+ * - integer with tag type (1, 2, or 3)
+ * - integer where the tag starts (starting "<")
+ * - integer where the tag ends (ending ">")
+ * first three members will be false, if the tag is invalid.
+ */
+function sq_getnxtag($body, $offset){
+ $me = "sq_getnxtag";
+ if ($offset > strlen($body)){
+ return false;
+ }
+ $lt = sq_findnxstr($body, $offset, "<");
+ if ($lt == strlen($body)){
+ return false;
+ }
+ /**
+ * We are here:
+ * blah blah <tag attribute="value">
+ * \---------^
+ */
+ $pos = sq_skipspace($body, $lt+1);
+ if ($pos >= strlen($body)){
+ return Array(false, false, false, $lt, strlen($body));
+ }
+ /**
+ * There are 3 kinds of tags:
+ * 1. Opening tag, e.g.:
+ * <a href="blah">
+ * 2. Closing tag, e.g.:
+ * </a>
+ * 3. XHTML-style content-less tag, e.g.:
+ * <img src="blah"/>
+ */
+ $tagtype = false;
+ switch (substr($body, $pos, 1)){
+ case "/":
+ $tagtype = 2;
+ $pos++;
+ break;
+ case "!":
+ /**
+ * A comment or an SGML declaration.
+ */
+ if (substr($body, $pos+1, 2) == "--"){
+ $gt = strpos($body, "-->", $pos)+2;
+ if ($gt === false){
+ $gt = strlen($body);
+ }
+ return Array(false, false, false, $lt, $gt);
+ } else {
+ $gt = sq_findnxstr($body, $pos, ">");
+ return Array(false, false, false, $lt, $gt);
+ }
+ break;
+ default:
+ /**
+ * Assume tagtype 1 for now. If it's type 3, we'll switch values
+ * later.
+ */
+ $tagtype = 1;
+ break;
+ }
- while ( $body{$i} <> '>' &&
- $i < $j ) {
- $etg = strtolower($body{$i}.$body{$i+1}.$body{$i+2});
- switch( $etg ) {
- case 'src':
- // This is probably a src specification
- $k = $i + 3;
- while( !isNoSep( $body{$k} )) {
- $k++;
+ $tag_start = $pos;
+ $tagname = '';
+ /**
+ * Look for next [\W-_], which will indicate the end of the tag name.
+ */
+ $regary = sq_findnxreg($body, $pos, "[^\w\-_]");
+ if ($regary == false){
+ return Array(false, false, false, $lt, strlen($body));
+ }
+ list($pos, $tagname, $match) = $regary;
+ $tagname = strtolower($tagname);
+
+ /**
+ * $match can be either of these:
+ * '>' indicating the end of the tag entirely.
+ * '\s' indicating the end of the tag name.
+ * '/' indicating that this is type-3 xhtml tag.
+ *
+ * Whatever else we find there indicates an invalid tag.
+ */
+ switch ($match){
+ case "/":
+ /**
+ * This is an xhtml-style tag with a closing / at the
+ * end, like so: <img src="blah"/>. Check if it's followed
+ * by the closing bracket. If not, then this tag is invalid
+ */
+ if (substr($body, $pos, 2) == "/>"){
+ $pos++;
+ $tagtype = 3;
+ } else {
+ $gt = sq_findnxstr($body, $pos, ">");
+ $retary = Array(false, false, false, $lt, $gt);
+ return $retary;
+ }
+ case ">":
+ return Array($tagname, false, $tagtype, $lt, $pos);
+ break;
+ default:
+ /**
+ * Check if it's whitespace
+ */
+ if (preg_match("/\s/", $match)){
+ } else {
+ /**
+ * This is an invalid tag! Look for the next closing ">".
+ */
+ $gt = sq_findnxstr($body, $offset, ">");
+ return Array(false, false, false, $lt, $gt);
+ }
+ }
+
+ /**
+ * At this point we're here:
+ * <tagname attribute='blah'>
+ * \-------^
+ *
+ * At this point we loop in order to find all attributes.
+ */
+ $attname = '';
+ $atttype = false;
+ $attary = Array();
+
+ while ($pos <= strlen($body)){
+ $pos = sq_skipspace($body, $pos);
+ if ($pos == strlen($body)){
+ /**
+ * Non-closed tag.
+ */
+ return Array(false, false, false, $lt, $pos);
+ }
+ /**
+ * See if we arrived at a ">" or "/>", which means that we reached
+ * the end of the tag.
+ */
+ $matches = Array();
+ if (preg_match("%^(\s*)(>|/>)%s", substr($body, $pos), $matches)) {
+ /**
+ * Yep. So we did.
+ */
+ $pos += strlen($matches{1});
+ if ($matches{2} == "/>"){
+ $tagtype = 3;
+ $pos++;
}
- if ( $body{$k} == '=' ) {
- /* It is indeed */
- $k++;
- while( !isNoSep( $body{$k} ) &&
- $k < $j ) {
- $k++;
- }
- $src = '';
- while ( $body{$k} <> '>' && isNoSep( $body{$k} ) &&
- $k < $j ) {
- $src .= $body{$k};
- $k++;
- }
- while( !isNoSep( $body{$k} ) &&
- $k < $j ) {
- $k++;
- }
- if ( strtolower( substr( $src, 0, 4 ) ) == 'cid:' ) {
- $src = substr( $src, 4 );
- $src = "../src/download.php?absolute_dl=true&passed_id=$id&mailbox=" .
- urlencode( $message->header->mailbox ) .
- "&passed_ent_id=" . find_ent_id( $src, $message );
- } else if ( strtolower( substr( $src, 0, 4 ) ) <> 'http' ||
- stristr( $src, $base_uri ) ) {
- /* Javascript and local urls goes out */
- $src = '../images/' . _("sec_remove_eng.png");
- }
- $ret .= 'src="' . $src . '" ';
- $i = $k - 2;
+ return Array($tagname, $attary, $tagtype, $lt, $pos);
+ }
+
+ /**
+ * There are several types of attributes, with optional
+ * [:space:] between members.
+ * Type 1:
+ * attrname[:space:]=[:space:]'CDATA'
+ * Type 2:
+ * attrname[:space:]=[:space:]"CDATA"
+ * Type 3:
+ * attr[:space:]=[:space:]CDATA
+ * Type 4:
+ * attrname
+ *
+ * We leave types 1 and 2 the same, type 3 we check for
+ * '"' and convert to """ if needed, then wrap in
+ * double quotes. Type 4 we convert into:
+ * attrname="yes".
+ */
+ $regary = sq_findnxreg($body, $pos, "[^\w\-_]");
+ if ($regary == false){
+ /**
+ * Looks like body ended before the end of tag.
+ */
+ return Array(false, false, false, $lt, strlen($body));
+ }
+ list($pos, $attname, $match) = $regary;
+ $attname = strtolower($attname);
+ /**
+ * We arrived at the end of attribute name. Several things possible
+ * here:
+ * '>' means the end of the tag and this is attribute type 4
+ * '/' if followed by '>' means the same thing as above
+ * '\s' means a lot of things -- look what it's followed by.
+ * anything else means the attribute is invalid.
+ */
+ switch($match){
+ case "/":
+ /**
+ * This is an xhtml-style tag with a closing / at the
+ * end, like so: <img src="blah"/>. Check if it's followed
+ * by the closing bracket. If not, then this tag is invalid
+ */
+ if (substr($body, $pos, 2) == "/>"){
+ $pos++;
+ $tagtype = 3;
} else {
- $ret .= 'src';
- $i = $i + 3;
+ $gt = sq_findnxstr($body, $pos, ">");
+ $retary = Array(false, false, false, $lt, $gt);
+ return $retary;
}
-
+ case ">":
+ $attary{$attname} = '"yes"';
+ return Array($tagname, $attary, $tagtype, $lt, $pos);
break;
- case '../':
- // Retrolinks are not allowed without a base because they mess with SM security
- if ( $base == '' ) {
- $i += 2;
+ default:
+ /**
+ * Skip whitespace and see what we arrive at.
+ */
+ $pos = sq_skipspace($body, $pos);
+ $char = substr($body, $pos, 1);
+ /**
+ * Two things are valid here:
+ * '=' means this is attribute type 1 2 or 3.
+ * \w means this was attribute type 4.
+ * anything else we ignore and re-loop. End of tag and
+ * invalid stuff will be caught by our checks at the beginning
+ * of the loop.
+ */
+ if ($char == "="){
+ $pos++;
+ $pos = sq_skipspace($body, $pos);
+ /**
+ * Here are 3 possibilities:
+ * "'" attribute type 1
+ * '"' attribute type 2
+ * everything else is the content of tag type 3
+ */
+ $quot = substr($body, $pos, 1);
+ if ($quot == "'"){
+ $regary = sq_findnxreg($body, $pos+1, "\'");
+ if ($regary == false){
+ return Array(false, false, false, $lt, strlen($body));
+ }
+ list($pos, $attval, $match) = $regary;
+ $pos++;
+ $attary{$attname} = "'" . $attval . "'";
+ } else if ($quot == '"'){
+ $regary = sq_findnxreg($body, $pos+1, '\"');
+ if ($regary == false){
+ return Array(false, false, false, $lt, strlen($body));
+ }
+ list($pos, $attval, $match) = $regary;
+ $pos++;
+ $attary{$attname} = '"' . $attval . '"';
+ } else {
+ /**
+ * These are hateful. Look for \s, or >.
+ */
+ $regary = sq_findnxreg($body, $pos, "[\s>]");
+ if ($regary == false){
+ return Array(false, false, false, $lt, strlen($body));
+ }
+ list($pos, $attval, $match) = $regary;
+ /**
+ * If it's ">" it will be caught at the top.
+ */
+ $attval = preg_replace("/\"/s", """, $attval);
+ $attary{$attname} = '"' . $attval . '"';
+ }
+ } else if (preg_match("|[\w/>]|", $char)) {
+ /**
+ * That was attribute type 4.
+ */
+ $attary{$attname} = '"yes"';
} else {
- $ret .= '.';
+ /**
+ * An illegal character. Find next '>' and return.
+ */
+ $gt = sq_findnxstr($body, $pos, ">");
+ return Array(false, false, false, $lt, $gt);
}
- break;
- case 'cid':
- // Internal link
- $k = $i-1;
- if ( $body{$i+3} == ':') {
- $i +=4;
- $name = '';
- while ( isNoSep( $body{$i} ) &&
- $i < $j ) {
- $name .= $body{$i++};
- }
- if ( $name <> '' ) {
- $ret .= "../src/download.php?absolute_dl=true&passed_id=$id&mailbox=" .
- urlencode( $message->header->mailbox ) .
- "&passed_ent_id=" . find_ent_id( $name, $message );
- if ( $body{$k} == '"' )
- $ret .= '" ';
- else
- $ret .= ' ';
+ }
+ }
+ /**
+ * The fact that we got here indicates that the tag end was never
+ * found. Return invalid tag indication so it gets stripped.
+ */
+ return Array(false, false, false, $lt, strlen($body));
+}
+
+/**
+ * This function checks attribute values for entity-encoded values
+ * and returns them translated into 8-bit strings so we can run
+ * checks on them.
+ *
+ * @param $attvalue A string to run entity check against.
+ * @return Translated value.
+ */
+function sq_deent($attvalue){
+ $me="sq_deent";
+ /**
+ * See if we have to run the checks first. All entities must start
+ * with "&".
+ */
+ if (strpos($attvalue, "&") === false){
+ return $attvalue;
+ }
+ /**
+ * Check named entities first.
+ */
+ $trans = get_html_translation_table(HTML_ENTITIES);
+ /**
+ * Leave " in, as it can mess us up.
+ */
+ $trans = array_flip($trans);
+ unset($trans{"""});
+ while (list($ent, $val) = each($trans)){
+ $attvalue = preg_replace("/$ent*(\W)/si", "$val\\1", $attvalue);
+ }
+ /**
+ * Now translate numbered entities from 1 to 255 if needed.
+ */
+ if (strpos($attvalue, "#") !== false){
+ $omit = Array(34, 39);
+ for ($asc=1; $asc<256; $asc++){
+ if (!in_array($asc, $omit)){
+ $chr = chr($asc);
+ $attvalue = preg_replace("/\�*$asc;*(\D)/si", "$chr\\1",
+ $attvalue);
+ $attvalue = preg_replace("/\�*".dechex($asc).";*(\W)/si",
+ "$chr\\1", $attvalue);
+ }
+ }
+ }
+ return $attvalue;
+}
+
+/**
+ * This function runs various checks against the attributes.
+ *
+ * @param $tagname String with the name of the tag.
+ * @param $attary Array with all tag attributes.
+ * @param $rm_attnames See description for sq_sanitize
+ * @param $bad_attvals See description for sq_sanitize
+ * @param $add_attr_to_tag See description for sq_sanitize
+ * @param $message message object
+ * @param $id message id
+ * @return Array with modified attributes.
+ */
+function sq_fixatts($tagname,
+ $attary,
+ $rm_attnames,
+ $bad_attvals,
+ $add_attr_to_tag,
+ $message,
+ $id
+ ){
+ $me = "sq_fixatts";
+ while (list($attname, $attvalue) = each($attary)){
+ /**
+ * See if this attribute should be removed.
+ */
+ foreach ($rm_attnames as $matchtag=>$matchattrs){
+ if (preg_match($matchtag, $tagname)){
+ foreach ($matchattrs as $matchattr){
+ if (preg_match($matchattr, $attname)){
+ unset($attary{$attname});
+ continue;
+ }
}
- if ( $body{$i} == '>' )
- $i -= 1;
}
- break;
- case ' on':
- case "\non":
- case "\ron":
- case "\ton":
- $ret .= ' no';
- $i += 2;
- break;
- case 'pt:':
- if ( strcasecmp( $body{$i-4}.$body{$i-3}.$body{$i-2}.$body{$i-1}.$body{$i}.$body{$i+1}.$body{$i+2}, 'script:') == 0 ) {
- $ret .= '_no/';
- } else {
- $ret .= $etg;
+ }
+ /**
+ * Remove any entities.
+ */
+ $attvalue = sq_deent($attvalue);
+
+ /**
+ * Now let's run checks on the attvalues.
+ * I don't expect anyone to comprehend this. If you do,
+ * get in touch with me so I can drive to where you live and
+ * shake your hand personally. :)
+ */
+ foreach ($bad_attvals as $matchtag=>$matchattrs){
+ if (preg_match($matchtag, $tagname)){
+ foreach ($matchattrs as $matchattr=>$valary){
+ if (preg_match($matchattr, $attname)){
+ /**
+ * There are two arrays in valary.
+ * First is matches.
+ * Second one is replacements
+ */
+ list($valmatch, $valrepl) = $valary;
+ $newvalue =
+ preg_replace($valmatch, $valrepl, $attvalue);
+ if ($newvalue != $attvalue){
+ $attary{$attname} = $newvalue;
+ }
+ }
+ }
}
- $i += 2;
- break;
- default:
- $ret .= $body{$i};
}
- $i++;
+ /**
+ * Turn cid: urls into http-friendly ones.
+ */
+ if (preg_match("/^[\'\"]\s*cid:/si", $attvalue)){
+ $attary{$attname} = sq_cid2http($message, $id, $attvalue);
+ }
}
- return( $ret );
+ /**
+ * See if we need to append any attributes to this tag.
+ */
+ foreach ($add_attr_to_tag as $matchtag=>$addattary){
+ if (preg_match($matchtag, $tagname)){
+ $attary = array_merge($attary, $addattary);
+ }
+ }
+ return $attary;
}
+/**
+ * This function edits the style definition to make them friendly and
+ * usable in squirrelmail.
+ *
+ * @param $message the message object
+ * @param $id the message id
+ * @param $content a string with whatever is between <style> and </style>
+ * @return a string with edited content.
+ */
+function sq_fixstyle($message, $id, $content){
+ global $view_unsafe_images;
+ $me = "sq_fixstyle";
+ /**
+ * First look for general BODY style declaration, which would be
+ * like so:
+ * body {background: blah-blah}
+ * and change it to .bodyclass so we can just assign it to a <div>
+ */
+ $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 expression: declarations which lead to vulnerabilities
+ * in IE.
+ */
+ $content = preg_replace("/expression\s*:/si", "idiocy:", $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 <body> tag into a <div> tag since we
+ * can't really have a body-within-body.
+ *
+ * @param $attary an array of attributes and values of <body>
+ * @return a modified array of attributes to be set for <div>
+ */
+function sq_body2div($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 = "<!-- begin sanitized html -->\n";
+ $skip_content = false;
+
+ while (($curtag=sq_getnxtag($body, $curpos)) != FALSE){
+ list($tagname, $attary, $tagtype, $lt, $gt) = $curtag;
+ $free_content = substr($body, $curpos, $lt-$curpos);
+ /**
+ * Take care of <style>
+ */
+ if ($tagname == "style" && $tagtype == 2){
+ /**
+ * This is a closing </style>. 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 .= '</' . $tagname . '>';
+ $opentimes--;
+ }
+ }
+ $trusted .= "\n";
+ }
+ $trusted .= "<!-- end sanitized html -->\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){
+ global $attachment_common_show_images, $view_unsafe_images,
+ $has_unsafe_images, $message;
+ /**
+ * 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"
+ )
+ );
+
+ $secremoveimg = "../images/" . _("sec_remove_eng.png");
+ $bad_attvals = Array(
+ "/.*/" =>
+ Array(
+ "/^src|background|href|action/i" =>
+ Array(
+ Array(
+ "|^([\'\"])\s*\.\./.*([\'\"])|si",
+ "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si"
+ ),
+ Array(
+ "\\1$secremoveimg\\2",
+ "\\1$secremoveimg\\2"
+ )
+ ),
+ "/^style/si" =>
+ Array(
+ Array(
+ "/expression\s*:/si",
+ "|url\(([\'\"])\s*\.\./.*([\'\"])\)|si",
+ "/url\(([\'\"])\s*\S+script:.*([\'\"])\)/si"
+ ),
+ Array(
+ "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.
+ */
+ $addendum = Array(
+ "/.*/" =>
+ Array(
+ "/^src|background/i" =>
+ Array(
+ Array(
+ "/^([\'\"])\s*https*:.*([\'\"])/si"
+ ),
+ Array(
+ "\\1$secremoveimg\\2"
+ )
+ ),
+ "/^style/si" =>
+ Array(
+ Array(
+ "/url\(([\'\"])\s*https*:.*([\'\"])\)/si"
+ ),
+ Array(
+ "url(\\1$secremoveimg\\2)"
+ )
+ )
+ )
+ );
+ $bad_attvals = array_merge($bad_attvals, $addendum);
+ }
+ $add_attr_to_tag = Array(
+ "/^a$/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