1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588 |
- <?php
- /**
- * mime.php
- *
- * Copyright (c) 1999-2002 The SquirrelMail Project Team
- * Licensed under the GNU GPL. For full terms see the file COPYING.
- *
- * This contains the functions necessary to detect and decode MIME
- * messages.
- *
- * $Id$
- */
- require_once('../functions/imap.php');
- require_once('../functions/attachment_common.php');
- /* --------------------------------------------------------------------------------- */
- /* MIME DECODING */
- /* --------------------------------------------------------------------------------- */
- /* This function gets the structure of a message and stores it in the "message" class.
- * It will return this object for use with all relevant header information and
- * fully parsed into the standard "message" object format.
- */
- function mime_structure ($bodystructure, $flags=array()) {
- // isolate the body structure and remove beginning and end parenthesis
- $read = trim(substr ($bodystructure, strpos(strtolower($bodystructure), 'bodystructure') + 13));
- $msg = &new message();
- $read = trim(substr ($read, 0, -1));
- $msg = $msg->parseStructure($read,0);
- $msg->setEnt('0');
- if (count($flags)) {
- foreach ($flags as $flag) {
- $char = strtoupper($flag{1});
- switch ($char) {
- case 'S':
- if (strtolower($flag) == '\\seen') {
- $msg->is_seen = true;
- }
- break;
- case 'A':
- if (strtolower($flag) == '\\answered') {
- $msg->is_answered = true;
- }
- break;
- case 'D':
- if (strtolower($flag) == '\\deleted') {
- $msg->is_deleted = true;
- }
- break;
- case 'F':
- if (strtolower($flag) == '\\flagged') {
- $msg->is_flagged = true;
- }
- break;
- case 'M':
- if (strtolower($flag) == '$mdnsent') {
- $msg->is_mdnsent = true;
- }
- break;
- default:
- break;
- }
- }
- }
- // listEntities($msg);
- return( $msg );
- }
- /* this starts the parsing of a particular structure. It is called recursively,
- * so it can be passed different structures. It returns an object of type
- * $message.
- * First, it checks to see if it is a multipart message. If it is, then it
- * handles that as it sees is necessary. If it is just a regular entity,
- * then it parses it and adds the necessary header information (by calling out
- * to mime_get_elements()
- */
- function mime_fetch_body($imap_stream, $id, $ent_id) {
- global $uid_support;
- /*
- * do a bit of error correction. If we couldn't find the entity id, just guess
- * that it is the first one. That is usually the case anyway.
- */
- if (!$ent_id) {
- $ent_id = 1;
- }
- $cmd = "FETCH $id BODY[$ent_id]";
-
- $data = sqimap_run_command ($imap_stream, $cmd, true, $response, $message, $uid_support);
- do {
- $topline = trim(array_shift( $data ));
- } while( $topline && $topline[0] == '*' && !preg_match( '/\* [0-9]+ FETCH.*/i', $topline )) ;
- $wholemessage = implode('', $data);
- if (ereg('\\{([^\\}]*)\\}', $topline, $regs)) {
- $ret = substr( $wholemessage, 0, $regs[1] );
- /*
- There is some information in the content info header that could be important
- in order to parse html messages. Let's get them here.
- */
- if ( $ret{0} == '<' ) {
- $data = sqimap_run_command ($imap_stream, "FETCH $id BODY[$ent_id.MIME]", true, $response, $message, $uid_support);
- }
- } else if (ereg('"([^"]*)"', $topline, $regs)) {
- $ret = $regs[1];
- } else {
- global $where, $what, $mailbox, $passed_id, $startMessage;
- $par = 'mailbox=' . urlencode($mailbox) . "&passed_id=$passed_id";
- if (isset($where) && isset($what)) {
- $par .= '&where='. urlencode($where) . "&what=" . urlencode($what);
- } else {
- $par .= "&startMessage=$startMessage&show_more=0";
- }
- $par .= '&response=' . urlencode($response) .
- '&message=' . urlencode($message).
- '&topline=' . urlencode($topline);
- echo '<tt><br>' .
- '<table width="80%"><tr>' .
- '<tr><td colspan=2>' .
- _("Body retrieval error. The reason for this is most probably that the message is malformed. Please help us making future versions better by submitting this message to the developers knowledgebase!") .
- " <A HREF=\"../src/retrievalerror.php?$par\"><br>" .
- _("Submit message") . '</A><BR> ' .
- '</td></tr>' .
- '<td><b>' . _("Command:") . "</td><td>$cmd</td></tr>" .
- '<td><b>' . _("Response:") . "</td><td>$response</td></tr>" .
- '<td><b>' . _("Message:") . "</td><td>$message</td></tr>" .
- '<td><b>' . _("FETCH line:") . "</td><td>$topline</td></tr>" .
- "</table><BR></tt></font><hr>";
- $data = sqimap_run_command ($imap_stream, "FETCH $passed_id BODY[]", true, $response, $message, $uid_support);
- array_shift($data);
- $wholemessage = implode('', $data);
- $ret = $wholemessage;
- }
- return( $ret );
- }
- function mime_print_body_lines ($imap_stream, $id, $ent_id, $encoding) {
- global $uid_support;
- // do a bit of error correction. If we couldn't find the entity id, just guess
- // that it is the first one. That is usually the case anyway.
- if (!$ent_id) {
- $ent_id = 1;
- }
- $sid = sqimap_session_id($uid_support);
- // Don't kill the connection if the browser is over a dialup
- // and it would take over 30 seconds to download it.
- // don´t call set_time_limit in safe mode.
- if (!ini_get("safe_mode")) {
- set_time_limit(0);
- }
- if ($uid_support) {
- $sid_s = substr($sid,0,strpos($sid, ' '));
- } else {
- $sid_s = $sid;
- }
- fputs ($imap_stream, "$sid FETCH $id BODY[$ent_id]\r\n");
- $cnt = 0;
- $continue = true;
- $read = fgets ($imap_stream,8192);
- // This could be bad -- if the section has sqimap_session_id() . ' OK'
- // or similar, it will kill the download.
- while (!ereg("^".$sid_s." (OK|BAD|NO)(.*)$", $read, $regs)) {
- if (trim($read) == ')==') {
- $read1 = $read;
- $read = fgets ($imap_stream,4096);
- if (ereg("^".$sid." (OK|BAD|NO)(.*)$", $read, $regs)) {
- return;
- } else {
- echo decodeBody($read1, $encoding) .
- decodeBody($read, $encoding);
- }
- } else if ($cnt) {
- echo decodeBody($read, $encoding);
- }
- $read = fgets ($imap_stream,4096);
- $cnt++;
- // break;
- }
- }
- /* -[ END MIME DECODING ]----------------------------------------------------------- */
- // 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) {
- echo "<tt>" . $message->entity_id . ' : ' . $message->type0 . '/' . $message->type1 . ' parent = '. $message->parent->entity_id. '<br>';
- for ($i = 0;isset($message->entities[$i]); $i++) {
- echo "$i : ";
- $msg = listEntities($message->entities[$i]);
-
- if ($msg) {
- echo "return: ";
- return $msg;
- }
- }
- }
- }
- function getPriorityStr($priority) {
- $priority_level = substr($priority,0,1);
- switch($priority_level) {
- /* check for a higher then normal priority. */
- case '1':
- case '2':
- $priority_string = _("High");
- break;
- /* check for a lower then normal priority. */
- case '4':
- case '5':
- $priority_string = _("Low");
- break;
- /* check for a normal priority. */
- case '3':
- default:
- $priority_level = '3';
- $priority_string = _("Normal");
- break;
- }
- return $priority_string;
- }
- /* returns a $message object for a particular entity id */
- function getEntity ($message, $ent_id) {
- return $message->getEntity($ent_id);
- }
- /*
- * 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>';
- }
- /* This returns a parsed string called $body. That string can then
- be displayed as the actual message in the HTML. It contains
- everything needed, including HTML Tags, Attachments at the
- bottom, etc.
- */
- function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $mailbox='INBOX') {
- // 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, $has_unsafe_images, $view_unsafe_images, $sort;
- $has_unsafe_images= 0;
- $body = '';
- $urlmailbox = urlencode($mailbox);
- $body_message = getEntity($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') {
- if ( $show_html_default <> 1 ) {
- $body = strip_tags( $body );
- translateText($body, $wrap_at, $body_message->header->charset);
- } else {
- $body = magicHTML( $body, $id, $message, $mailbox );
- }
- } else {
- translateText($body, $wrap_at, $body_message->header->charset);
- }
- if ($has_unsafe_images) {
- if ($view_unsafe_images) {
- $body .= "<CENTER><SMALL><A HREF=\"read_body.php?passed_id=$id&passed_ent_id=".$message->entity_id."&mailbox=$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&passed_ent_id=".$message->entity_id."&mailbox=$urlmailbox&sort=$sort&startMessage=$startMessage&show_more=0&view_unsafe_images=1\">". _("View Unsafe Images") ."</A></SMALL></CENTER><BR>\n";
- }
- }
- }
- return ($body);
- }
- function formatAttachments($message, $exclude_id, $mailbox, $id) {
- global $where, $what;
- global $startMessage, $color;
- static $ShownHTML = 0;
- $att_ar = $message->getAttachments($exclude_id);
- if (!count($att_ar)) return '';
-
- $attachments = "<TABLE WIDTH=\"100%\" CELLSPACING=0 CELLPADDING=2 BORDER=0 BGCOLOR=\"$color[0]\"><TR>\n" .
- "<TH ALIGN=\"left\" BGCOLOR=\"$color[9]\"><B>\n" .
- _("Attachments") . ':' .
- "</B></TH></TR><TR><TD>\n" .
- "<TABLE CELLSPACING=0 CELLPADDING=1 BORDER=0>\n";
-
- $urlMailbox = urlencode($mailbox);
- foreach ($att_ar as $att) {
-
- $ent = urlencode($att->entity_id);
- $header = $att->header;
- $type0 = strtolower($header->type0);
- $type1 = strtolower($header->type1);
- $name = '';
- if ($type0 =='message' && $type1 == 'rfc822') {
- $filename = decodeHeader($header->subject);
- $display_filename = $filename;
-
- $DefaultLink =
- "../src/read_body.php?startMessage=$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);
- }
- $Links = $HookResults[1];
- $DefaultLink = $HookResults[6];
- $attachments .= '<TR><TD> </TD><TD>' .
- "<A HREF=\"$DefaultLink\">$display_filename</A> </TD>" .
- '<TD><SMALL><b>' . show_readable_size($header->size) .
- '</b> </small></TD>' .
- "<TD><SMALL>[ $type0/$type1 ] </SMALL></TD>" .
- '<TD><SMALL>';
- $from_o = $header->from;
- if (is_object($from_o)) {
- $from_name = $from_o->getAddress(false);
- } else {
- $from_name = _("Unknown sender");
- }
- $from_name = decodeHeader(htmlspecialchars($from_name));
- $attachments .= '<b>' . $from_name . '</b>';
- $attachments .= '</SMALL></TD><TD><SMALL> ';
- $SkipSpaces = 1;
- foreach ($Links as $Val) {
- if ($SkipSpaces) {
- $SkipSpaces = 0;
- } else {
- $attachments .= ' | ';
- }
- $attachments .= '<a href="' . $Val['href'] . '">' . $Val['text'] . '</a>';
- }
- unset($Links);
- } else {
- $filename = decodeHeader($header->filename);
- if (trim($filename) == '') {
- $name = decodeHeader($header->name);
- if (trim($name) == '') {
- if ( trim( $header->id ) == '' )
- $display_filename = 'untitled-[' . $ent . ']' ;
- else
- $display_filename = 'cid: ' . $header->id;
- } else {
- $display_filename = $name;
- $filename = $name;
- }
- } else {
- $display_filename = $filename;
- }
- $DefaultLink =
- "../src/download.php?startMessage=$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);
- }
- $Links = $HookResults[1];
- $DefaultLink = $HookResults[6];
- $attachments .= '<TR><TD> </TD><TD>' .
- "<A HREF=\"$DefaultLink\">$display_filename</A> </TD>" .
- '<TD><SMALL><b>' . show_readable_size($header->size) .
- '</b> </small></TD>' .
- "<TD><SMALL>[ $type0/$type1 ] </SMALL></TD>" .
- '<TD><SMALL>';
- if ($message->header->description) {
- $attachments .= '<b>' . htmlspecialchars(_($header->description)) . '</b>';
- }
- $attachments .= '</SMALL></TD><TD><SMALL> ';
- $SkipSpaces = 1;
- foreach ($Links as $Val) {
- if ($SkipSpaces) {
- $SkipSpaces = 0;
- } else {
- $attachments .= ' | ';
- }
- $attachments .= '<a href="' . $Val['href'] . '">' . $Val['text'] . '</a>';
- }
- unset($Links);
- }
-
- }
- $attachments .= "</SMALL></TD></TR>\n";
-
- $attachments .= "</TABLE></TD></TR></TABLE>";
-
- return $attachments;
- }
- /** this function decodes the body depending on the encoding type. **/
- function decodeBody($body, $encoding) {
- $body = str_replace("\r\n", "\n", $body);
- $encoding = strtolower($encoding);
- global $show_html_default;
- if ($encoding == 'quoted-printable' ||
- $encoding == 'quoted_printable') {
- $body = quoted_printable_decode($body);
- while (ereg("=\n", $body))
- $body = ereg_replace ("=\n", "", $body);
- } else if ($encoding == 'base64') {
- $body = base64_decode($body);
- }
- // All other encodings are returned raw.
- return $body;
- }
- /*
- * This functions decode strings that is encoded according to
- * RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text).
- * Patched by Christian Schmidt <christian@ostenfeld.dk> 23/03/2002
- */
- function decodeHeader ($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 .= $res[2];
- }
- if (ucfirst($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);
- }
- }
- $string = $prefix . $replace . substr($string, strlen($res[0]));
- $i = strlen($prefix) + strlen($replace);
- }
- return( $string );
- }
- /*
- * Encode a string according to RFC 1522 for use in headers if it
- * contains 8-bit characters or anything that looks like it should
- * be encoded.
- */
- function encodeHeader ($string) {
- global $default_charset;
- // Encode only if the string contains 8-bit characters or =?
- $j = strlen( $string );
- $l = strstr($string, '=?'); // Must be encoded ?
- $ret = '';
- for( $i=0; $i < $j; ++$i) {
- switch( $string{$i} ) {
- case '=':
- $ret .= '=3D';
- break;
- case '?':
- $ret .= '=3F';
- break;
- case '_':
- $ret .= '=5F';
- break;
- case ' ':
- $ret .= '_';
- break;
- default:
- $k = ord( $string{$i} );
- if ( $k > 126 ) {
- $ret .= sprintf("=%02X", $k);
- $l = TRUE;
- } else
- $ret .= $string{$i};
- }
- }
- if ( $l ) {
- $string = "=?$default_charset?Q?$ret?=";
- }
- return( $string );
- }
- /* This function trys to locate the entity_id of a specific mime element */
- function find_ent_id( $id, $message ) {
- $ret = '';
- for ($i=0; $ret == '' && $i < count($message->entities); $i++) {
- if ( $message->entities[$i]->header->type0 == 'multipart') {
- $ret = find_ent_id( $id, $message->entities[$i] );
- } else {
- if ( strcasecmp( $message->entities[$i]->header->id, $id ) == 0 )
- $ret = $message->entities[$i]->entity_id;
- }
- }
- return( $ret );
- }
- /**
- ** HTMLFILTER ROUTINES
- */
- /**
- * 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;
- }
- /**
- * 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);
- }
- /**
- * 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 $offset;
- }
- /**
- * 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 $pos;
- }
- /**
- * 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;
- }
- /**
- * 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, "-->", $pos);
- if ($gt === false){
- $gt = strlen($body);
- } else {
- $gt += 2;
- }
- 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;
- }
- $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;
- $pos++;
- }
- return Array($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 {
- $gt = sq_findnxstr($body, $pos, ">");
- $retary = Array(false, false, false, $lt, $gt);
- return $retary;
- }
- case ">":
- $attary{$attname} = '"yes"';
- return Array($tagname, $attary, $tagtype, $lt, $pos);
- break;
- 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 {
- /**
- * An illegal character. Find next '>' and return.
- */
- $gt = sq_findnxstr($body, $pos, ">");
- return Array(false, false, false, $lt, $gt);
- }
- }
- }
- /**
- * 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,
- $mailbox
- ){
- $me = "sq_fixatts";
- while (list($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;
- }
- }
- }
- }
- /**
- * 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;
- }
- }
- }
- }
- }
- /**
- * Turn cid: urls into http-friendly ones.
- */
- if (preg_match("/^[\'\"]\s*cid:/si", $attvalue)){
- $attary{$attname} = sq_cid2http($message, $id, $attvalue, $mailbox);
- }
- }
- /**
- * See if we need to append any attributes to this tag.
- */
- foreach ($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);
- }
- /**
- * 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;
- }
- /**
- * 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, $mailbox){
- /**
- * 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($mailbox) .
- "&passed_ent_id=" . find_ent_id($cidurl, $message) . $quotchar;
- return $httpurl;
- }
- /**
- * 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;
- }
- /**
- * 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,
- $mailbox
- ){
- $me = "sq_sanitize";
- /**
- * Normalize rm_tags and rm_tags_with_content.
- */
- @array_walk($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;
- /**
- * 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 <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 .= $free_content;
- } else {
- }
- if ($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,
- $mailbox
- );
- }
- /**
- * Convert body into div.
- */
- if ($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;
- }
- /**
- * 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, $mailbox = 'INBOX'){
- 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",
- "link"
- );
- $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");
- $bad_attvals = Array(
- "/.*/" =>
- Array(
- "/^src|background/i" =>
- Array(
- Array(
- "|^([\'\"])\s*\.\./.*([\'\"])|si",
- "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si",
- "/^([\'\"])\s*mocha\s*:*.*([\'\"])/si",
- "/^([\'\"])\s*about\s*:.*([\'\"])/si"
- ),
- Array(
- "\\1$secremoveimg\\2",
- "\\1$secremoveimg\\2",
- "\\1$secremoveimg\\2",
- "\\1$secremoveimg\\2"
- )
- ),
- "/^href|action/i" =>
- Array(
- Array(
- "|^([\'\"])\s*\.\./.*([\'\"])|si",
- "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si",
- "/^([\'\"])\s*mocha\s*:*.*([\'\"])/si",
- "/^([\'\"])\s*about\s*:.*([\'\"])/si"
- ),
- Array(
- "\\1#\\2",
- "\\1#\\2",
- "\\1#\\2",
- "\\1#\\2"
- )
- ),
- "/^style/si" =>
- Array(
- Array(
- "/expression/si",
- "/binding/si",
- "/behaviou*r/si",
- "|url\(([\'\"])\s*\.\./.*([\'\"])\)|si",
- "/url\(([\'\"])\s*\S+script\s*:.*([\'\"])\)/si",
- "/url\(([\'\"])\s*mocha\s*:.*([\'\"])\)/si",
- "/url\(([\'\"])\s*about\s*:.*([\'\"])\)/si"
- ),
- Array(
- "idiocy",
- "idiocy",
- "idiocy",
- "url(\\1#\\2)",
- "url(\\1#\\2)",
- "url(\\1#\\2)",
- "url(\\1#\\2)"
- )
- )
- )
- );
- if (!$view_unsafe_images){
- /**
- * Remove any references to http/https if view_unsafe_images set
- * to false.
- */
- array_push($bad_attvals{'/.*/'}{'/^src|background/i'}[0],
- '/^([\'\"])\s*https*:.*([\'\"])/si');
- array_push($bad_attvals{'/.*/'}{'/^src|background/i'}[1],
- "\\1$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,
- $mailbox
- );
- if (preg_match("|$secremoveimg|si", $trusted)){
- $has_unsafe_images = true;
- }
- return $trusted;
- }
- ?>
|