X-Git-Url: https://vcs.fsf.org/?p=squirrelmail.git;a=blobdiff_plain;f=functions%2Fmime.php;h=05747945d1627c0e03014201cdc8e1769cbca21b;hp=b2fb5e2afbb9e9f7c45dfdee2e80708b324c8639;hb=a7ba71a6f38178abe02e1e9a144cf5955defe422;hpb=6b04287c4dd57388719ce6a4b79ff10d215515ff diff --git a/functions/mime.php b/functions/mime.php index b2fb5e2a..05747945 100644 --- a/functions/mime.php +++ b/functions/mime.php @@ -3,27 +3,33 @@ /** * mime.php * - * Copyright (c) 1999-2003 The SquirrelMail Project Team + * Copyright (c) 1999-2005 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. * - * $Id$ + * @version $Id$ + * @package squirrelmail */ +/** The typical includes... */ require_once(SM_PATH . 'functions/imap.php'); require_once(SM_PATH . 'functions/attachment_common.php'); +/** add sqm_baseuri()*/ +include_once(SM_PATH . 'functions/display_messages.php'); -/* --------------------------------------------------------------------------------- */ -/* MIME DECODING */ -/* --------------------------------------------------------------------------------- */ +/* -------------------------------------------------------------------------- */ +/* MIME DECODING */ +/* -------------------------------------------------------------------------- */ -/* This function gets the structure of a message and stores it in the "message" class. +/** + * Get the MIME structure + * + * 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, $flags=array()) { /* Isolate the body structure and remove beginning and end parenthesis. */ @@ -36,11 +42,9 @@ function mime_structure ($bodystructure, $flags=array()) { global $color, $mailbox; /* removed urldecode because $_GET is auto urldecoded ??? */ displayPageHeader( $color, $mailbox ); - echo "\n\n" . - '
'; $errormessage = _("SquirrelMail could not decode the bodystructure of the message"); - $errormessage .= '
'._("the provided bodystructure by your imap-server").':

'; - $errormessage .= '
' . htmlspecialchars($read) . '
'; + $errormessage .= '
'._("The bodystructure provided by your IMAP server:").'

'; + $errormessage .= '
' . htmlspecialchars($read) . '
'; plain_error_message( $errormessage, $color ); echo ''; exit; @@ -94,18 +98,20 @@ function mime_structure ($bodystructure, $flags=array()) { * to mime_get_elements() */ -function mime_fetch_body($imap_stream, $id, $ent_id=1) { - global $uid_support; +function mime_fetch_body($imap_stream, $id, $ent_id=1, $fetch_size=0) { /* Do a bit of error correction. If we couldn't find the entity id, just guess * that it is the first one. That is usually the case anyway. */ + if (!$ent_id) { - $cmd = "FETCH $id BODY[]"; + $cmd = "FETCH $id BODY[]"; } else { - $cmd = "FETCH $id BODY[$ent_id]"; + $cmd = "FETCH $id BODY[$ent_id]"; } - $data = sqimap_run_command ($imap_stream, $cmd, true, $response, $message, $uid_support); + if ($fetch_size!=0) $cmd .= "<0.$fetch_size>"; + + $data = sqimap_run_command ($imap_stream, $cmd, true, $response, $message, TRUE); do { $topline = trim(array_shift($data)); } while($topline && ($topline[0] == '*') && !preg_match('/\* [0-9]+ FETCH.*/i', $topline)) ; @@ -117,7 +123,7 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1) { * in order to parse html messages. Let's get them here. */ // if ($ret{0} == '<') { -// $data = sqimap_run_command ($imap_stream, "FETCH $id BODY[$ent_id.MIME]", true, $response, $message, $uid_support); +// $data = sqimap_run_command ($imap_stream, "FETCH $id BODY[$ent_id.MIME]", true, $response, $message, TRUE); // } } else if (ereg('"([^"]*)"', $topline, $regs)) { $ret = $regs[1]; @@ -130,21 +136,21 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1) { $par .= '&startMessage=' . $startMessage . '&show_more=0'; } $par .= '&response=' . urlencode($response) . - '&message=' . urlencode($message) . - '&topline=' . urlencode($topline); - - echo '
' . - '' . - '' . - '" . - '" . - '" . - '" . - "
' . - _("Body retrieval error. The reason for this is most probably that the message is malformed.") . - '
' . _("Command:") . "$cmd
' . _("Response:") . "$response
' . _("Message:") . "$message
' . _("FETCH line:") . "$topline


"; - - $data = sqimap_run_command ($imap_stream, "FETCH $passed_id BODY[]", true, $response, $message, $uid_support); + '&message=' . urlencode($message) . + '&topline=' . urlencode($topline); + + echo '
' . + '' . + '' . + '" . + '" . + '" . + '" . + "
' . + _("Body retrieval error. The reason for this is most probably that the message is malformed.") . + '
' . _("Command:") . "$cmd
' . _("Response:") . "$response
' . _("Message:") . "$message
' . _("FETCH line:") . "$topline


"; + + $data = sqimap_run_command ($imap_stream, "FETCH $passed_id BODY[]", true, $response, $message, TRUE); array_shift($data); $wholemessage = implode('', $data); @@ -153,54 +159,50 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1) { return $ret; } -function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding) { - global $uid_support; +function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding, $rStream='php://stdout') { - $sid = sqimap_session_id($uid_support); /* Don't kill the connection if the browser is over a dialup * and it would take over 30 seconds to download it. - * DonĀ“t call set_time_limit in safe mode. + * 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($sid, ' ')); + /* in case of base64 encoded attachments, do not buffer them. + Instead, echo the decoded attachment directly to screen */ + if (strtolower($encoding) == 'base64') { + if (!$ent_id) { + $query = "FETCH $id BODY[]"; + } else { + $query = "FETCH $id BODY[$ent_id]"; + } + sqimap_run_command($imap_stream,$query,true,$response,$message,TRUE,'sqimap_base64_decode',$rStream,true); } else { - $sid_s = $sid; + $body = mime_fetch_body ($imap_stream, $id, $ent_id); + if (is_resource($rStream)) { + fputs($rStream,decodeBody($body,$encoding)); + } else { + echo decodeBody($body, $encoding); + } } - $body = mime_fetch_body ($imap_stream, $id, $ent_id); - echo decodeBody($body, $encoding); + /* + TODO, use the same method for quoted printable. + However, I assume that quoted printable attachments aren't that large + so the performancegain / memory usage drop will be minimal. + If we decide to add that then we need to adapt sqimap_fread because + we need to split te result on \n and fread doesn't stop at \n. That + means we also should provide $results from sqimap_fread (by ref) to + te function and set $no_return to false. The $filter function for + quoted printable should handle unsetting of $results. + */ + /* + TODO 2: find out how we write to the output stream php://stdout. fwrite + doesn't work because 'php://stdout isn't a stream. + */ + return; -/* - fputs ($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); - $cnt++; -// break; - } -*/ } /* -[ END MIME DECODING ]----------------------------------------------------------- */ @@ -210,7 +212,7 @@ function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding) { */ function listEntities ($message) { if ($message) { - echo "" . $message->entity_id . ' : ' . $message->type0 . '/' . $message->type1 . ' parent = '. $message->parent->entity_id. '
'; + echo "" . $message->entity_id . ' : ' . $message->type0 . '/' . $message->type1 . ' parent = '. $message->parent->entity_id. '
'; for ($i = 0; isset($message->entities[$i]); $i++) { echo "$i : "; $msg = listEntities($message->entities[$i]); @@ -269,7 +271,7 @@ function translateText(&$body, $wrap_at, $charset) { for ($i=0; $i < count($body_ary); $i++) { $line = $body_ary[$i]; if (strlen($line) - 2 >= $wrap_at) { - sqWordWrap($line, $wrap_at); + sqWordWrap($line, $wrap_at, $charset); } $line = charset_decode($charset, $line); $line = str_replace("\t", ' ', $line); @@ -308,19 +310,35 @@ function translateText(&$body, $wrap_at, $charset) { $body = '
' . implode("\n", $body_ary) . '
'; } -/* This returns a parsed string called $body. That string can then +/** + * 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. + * + * Since 1.2.0 function uses message_body hook. + * Till 1.3.0 function included output of formatAttachments(). + * + * @param resource $imap_stream imap connection resource + * @param object $message squirrelmail message object + * @param array $color squirrelmail color theme array + * @param integer $wrap_at number of characters per line + * @param string $ent_num (since 1.3.0) message part id + * @param integer $id (since 1.3.0) message id + * @param string $mailbox (since 1.3.0) imap folder name + * @param boolean $clean (since 1.5.1 and 1.4.6) Do not output stuff that's irrelevant for the printable version. + * @return string html formated message text */ -function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $mailbox='INBOX') { +function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $mailbox='INBOX', $clean=FALSE) { /* 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, $sort, $has_unsafe_images, $passed_ent_id; - global $languages, $squirrelmail_language; + global $startMessage, $languages, $squirrelmail_language, + $show_html_default, $sort, $has_unsafe_images, $passed_ent_id, $use_iframe,$iframe_height; + + // workaround for not updated config.php + if (! isset($use_iframe)) $use_iframe = false; if( !sqgetGlobalVar('view_unsafe_images', $view_unsafe_images, SQ_GET) ) { $view_unsafe_images = false; @@ -330,14 +348,14 @@ function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $ma $urlmailbox = urlencode($mailbox); $body_message = getEntity($message, $ent_num); if (($body_message->header->type0 == 'text') || - ($body_message->header->type0 == 'rfc822')) { + ($body_message->header->type0 == 'rfc822')) { $body = mime_fetch_body ($imap_stream, $id, $ent_num); $body = decodeBody($body, $body_message->header->encoding); if (isset($languages[$squirrelmail_language]['XTRA_CODE']) && - function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) { + function_exists($languages[$squirrelmail_language]['XTRA_CODE'] . '_decode')) { if (mb_detect_encoding($body) != 'ASCII') { - $body = $languages[$squirrelmail_language]['XTRA_CODE']('decode', $body); + $body = call_user_func($languages[$squirrelmail_language]['XTRA_CODE'] . '_decode',$body); } } $hookResults = do_hook("message_body", $body); @@ -351,49 +369,118 @@ function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $ma if ($show_html_default <> 1) { $entity_conv = array(' ' => ' ', '

' => "\n", - '
' => "\n", '

' => "\n", + '
' => "\n", '
' => "\n", + '
' => "\n", + '
' => "\n", '>' => '>', '<' => '<'); $body = strtr($body, $entity_conv); $body = strip_tags($body); $body = trim($body); translateText($body, $wrap_at, - $body_message->header->getParameter('charset')); + $body_message->header->getParameter('charset')); + } elseif ($use_iframe && ! $clean) { + // $clean is used to remove iframe in printable view. + + /** + * If we don't add html message between iframe tags, + * we must detect unsafe images and modify $has_unsafe_images. + */ + $html_body = magicHTML($body, $id, $message, $mailbox); + + // creating iframe url + $iframeurl=sqm_baseuri().'src/view_html.php?' + . 'mailbox=' . $urlmailbox + . '&passed_id=' . $id + . '&ent_id=' . $ent_num + . '&view_unsafe_images=' . (int) $view_unsafe_images; + + // adding warning message + $body = html_tag('div',_("Viewing HTML formatted email"),'center'); + + /** + * height can't be set to 100%, because it does not work as expected when + * iframe is inside the table. Browsers do not create full height objects + * even when iframe is not nested. Maybe there is some way to get full size + * with CSS. Tested in firefox 1.02 and opera 7.53 + * + * width="100%" does not work as expected, when table width is not set (automatic) + * + * tokul: I think \n"; } else { + // old way of html rendering $body = magicHTML($body, $id, $message, $mailbox); } } else { translateText($body, $wrap_at, - $body_message->header->getParameter('charset')); + $body_message->header->getParameter('charset')); + } + + // if this is the clean display (i.e. printer friendly), stop here. + if ( $clean ) { + return $body; + } + + $link = 'passed_id=' . $id . '&ent_id='.$ent_num. + '&mailbox=' . $urlmailbox .'&sort=' . $sort . + '&startMessage=' . $startMessage . '&show_more=0'; + if (isset($passed_ent_id)) { + $link .= '&passed_ent_id='.$passed_ent_id; } - $link = 'read_body.php?passed_id=' . $id . '&ent_id='.$ent_num. - '&mailbox=' . $urlmailbox .'&sort=' . $sort . - '&startMessage=' . $startMessage . '&show_more=0'; - if (isset($passed_ent_id)) { - $link .= '&passed_ent_id='.$passed_ent_id; - } + $body .= '

' . _("Download this as a file") . ''; if ($view_unsafe_images) { $text = _("Hide Unsafe Images"); } else { - if (isset($has_unsafe_images) && $has_unsafe_images) { - $link .= '&view_unsafe_images=1'; - $text = _("View Unsafe Images"); - } else { - $text = ''; - } + if (isset($has_unsafe_images) && $has_unsafe_images) { + $link .= '&view_unsafe_images=1'; + $text = _("View Unsafe Images"); + } else { + $text = ''; + } + } + if($text != '') { + $body .= ' | ' . $text . ''; } - $body .= '
'.$text. - '

' . "\n"; + $body .= '

' . "\n"; } return $body; } - +/** + * Displays attachment links and information + * + * Since 1.3.0 function is not included in formatBody() call. + * + * Since 1.0.2 uses attachment $type0/$type1 hook. + * Since 1.2.5 uses attachment $type0/* hook. + * Since 1.5.0 uses attachments_bottom hook. + * + * @param object $message SquirrelMail message object + * @param array $exclude_id message parts that are not attachments. + * @param string $mailbox mailbox name + * @param integer $id message id + * @return string html formated attachment information. + */ function formatAttachments($message, $exclude_id, $mailbox, $id) { - global $where, $what, $startMessage, $color; - static $ShownHTML = 0; + global $where, $what, $startMessage, $color, $passed_ent_id; $att_ar = $message->getAttachments($exclude_id); @@ -409,56 +496,26 @@ function formatAttachments($message, $exclude_id, $mailbox, $id) { $type0 = strtolower($header->type0); $type1 = strtolower($header->type1); $name = ''; - $links['download link']['text'] = _("download"); - $links['download link']['href'] = SM_PATH . - "src/download.php?absolute_dl=true&passed_id=$id&mailbox=$urlMailbox&ent_id=$ent"; - $ImageURL = ''; + $links['download link']['text'] = _("Download"); + $links['download link']['href'] = sqm_baseuri() . + "src/download.php?absolute_dl=true&passed_id=$id&mailbox=$urlMailbox&ent_id=$ent"; if ($type0 =='message' && $type1 == 'rfc822') { - $default_page = SM_PATH . 'src/read_body.php'; + $default_page = sqm_baseuri() . 'src/read_body.php'; $rfc822_header = $att->rfc822_header; $filename = $rfc822_header->subject; if (trim( $filename ) == '') { $filename = 'untitled-[' . $ent . ']' ; - } + } $from_o = $rfc822_header->from; if (is_object($from_o)) { - $from_name = $from_o->getAddress(false); + $from_name = decodeHeader($from_o->getAddress(false)); } else { $from_name = _("Unknown sender"); } - $from_name = decodeHeader(($from_name)); $description = $from_name; } else { - $default_page = SM_PATH . 'src/download.php'; - if (is_object($header->disposition)) { - $filename = $header->disposition->getProperty('filename'); - if (trim($filename) == '') { - $name = decodeHeader($header->disposition->getProperty('name')); - if (trim($name) == '') { - $name = $header->getParameter('name'); - if(trim($name) == '') { - if (trim( $header->id ) == '') { - $filename = 'untitled-[' . $ent . ']' ; - } else { - $filename = 'cid: ' . $header->id; - } - } else { - $filename = $name; - } - } else { - $filename = $name; - } - } - } else { - $filename = $header->getParameter('name'); - if (!trim($filename)) { - if (trim( $header->id ) == '') { - $filename = 'untitled-[' . $ent . ']' ; - } else { - $filename = 'cid: ' . $header->id; - } - } - } + $default_page = sqm_baseuri() . 'src/download.php'; + $filename = $att->getFilename(); if ($header->description) { $description = decodeHeader($header->description); } else { @@ -473,35 +530,36 @@ function formatAttachments($message, $exclude_id, $mailbox, $id) { $passed_ent_id_link = ''; } $defaultlink = $default_page . "?startMessage=$startMessage" - . "&passed_id=$id&mailbox=$urlMailbox" - . '&ent_id='.$ent.$passed_ent_id_link; + . "&passed_id=$id&mailbox=$urlMailbox" + . '&ent_id='.$ent.$passed_ent_id_link; if ($where && $what) { - $defaultlink .= '&where='. urlencode($where).'&what='.urlencode($what); + $defaultlink .= '&where='. urlencode($where).'&what='.urlencode($what); } + /* This executes the attachment hook with a specific MIME-type. * If that doesn'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); + $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); + $startMessage, $id, $urlMailbox, $ent, $defaultlink, + $display_filename, $where, $what); } $links = $hookresults[1]; $defaultlink = $hookresults[6]; - $attachments .= '' . - ''.decodeHeader($display_filename).' ' . - '' . show_readable_size($header->size) . - '  ' . - "[ $type0/$type1 ] " . - ''; + $attachments .= '' . + ''.decodeHeader($display_filename).' ' . + '' . show_readable_size($header->size) . + '  ' . + '[ '.htmlspecialchars($type0).'/'.htmlspecialchars($type1).' ] ' . + ''; $attachments .= '' . $description . ''; - $attachments .= ' '; + $attachments .= ' '; $skipspaces = 1; foreach ($links as $val) { @@ -510,14 +568,45 @@ function formatAttachments($message, $exclude_id, $mailbox, $id) { } else { $attachments .= '  |  '; } - $attachments .= '' . $val['text'] . ''; + $attachments .= '' + . (isset($val['text']) && !empty($val['text']) ? $val['text'] : '') + . (isset($val['extra']) && !empty($val['extra']) ? $val['extra'] : '') + . ''; } unset($links); - $attachments .= "\n"; + $attachments .= "\n"; } + $attachmentadd = do_hook_function('attachments_bottom',$attachments); + if ($attachmentadd != '') + $attachments = $attachmentadd; return $attachments; } +function sqimap_base64_decode(&$string) { + + // Base64 encoded data goes in pairs of 4 bytes. To achieve on the + // fly decoding (to reduce memory usage) you have to check if the + // data has incomplete pairs + + // Remove the noise in order to check if the 4 bytes pairs are complete + $string = str_replace(array("\r\n","\n", "\r", " "),array('','','',''),$string); + + $sStringRem = ''; + $iMod = strlen($string) % 4; + if ($iMod) { + $sStringRem = substr($string,-$iMod); + // Check if $sStringRem contains padding characters + if (substr($sStringRem,-1) != '=') { + $string = substr($string,0,-$iMod); + } else { + $sStringRem = ''; + } + } + $string = base64_decode($string); + return $sStringRem; +} + + /* This function decodes the body depending on the encoding type. */ function decodeBody($body, $encoding) { global $show_html_default; @@ -525,8 +614,16 @@ function decodeBody($body, $encoding) { $body = str_replace("\r\n", "\n", $body); $encoding = strtolower($encoding); - if ($encoding == 'quoted-printable' || - $encoding == 'quoted_printable') { + $encoding_handler = do_hook_function('decode_body', $encoding); + + + // plugins get first shot at decoding the body + // + if (!empty($encoding_handler) && function_exists($encoding_handler)) { + $body = $encoding_handler('decode', $body); + + } else if ($encoding == 'quoted-printable' || + $encoding == 'quoted_printable') { $body = quoted_printable_decode($body); while (ereg("=\n", $body)) { @@ -541,87 +638,180 @@ function decodeBody($body, $encoding) { return $body; } -/* +/** + * Decodes headers + * * This functions decode strings that is encoded according to * RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text). * Patched by Christian Schmidt 23/03/2002 + * + * @param string $string header string that has to be made readable + * @param boolean $utfencode change message in order to be readable on user's charset. defaults to true + * @param boolean $htmlsave preserve spaces and sanitize html special characters. defaults to true + * @param boolean $decide decide if string can be utfencoded. defaults to false + * @return string decoded header string */ -function decodeHeader ($string, $utfencode=true,$htmlsave=true) { - global $languages, $squirrelmail_language; +function decodeHeader ($string, $utfencode=true,$htmlsave=true,$decide=false) { + global $languages, $squirrelmail_language,$default_charset; if (is_array($string)) { $string = implode("\n", $string); } - + if (isset($languages[$squirrelmail_language]['XTRA_CODE']) && - function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) { - $string = $languages[$squirrelmail_language]['XTRA_CODE']('decodeheader', $string); - // Do we need to return at this point? - // return $string; + function_exists($languages[$squirrelmail_language]['XTRA_CODE'] . '_decodeheader')) { + $string = call_user_func($languages[$squirrelmail_language]['XTRA_CODE'] . '_decodeheader', $string); + // Do we need to return at this point? + // return $string; } $i = 0; + $iLastMatch = -2; + $encoded = true; + $aString = explode(' ',$string); + $ret = ''; foreach ($aString as $chunk) { + if ($encoded && $chunk === '') { + continue; + } elseif ($chunk === '') { + $ret .= ' '; + continue; + } $encoded = false; - $aString[$i] = ''; - while (preg_match('/^(.*)=\?([^?]*)\?(Q|B)\?([^?]*)\?=(.*)$/Ui',$chunk,$res)) { - $aString[$i] .= $res[1]; - //echo "$chunk match ". $res[5] . "
"; + /* if encoded words are not separated by a linear-space-white we still catch them */ + $j = $i-1; + + while ($match = preg_match('/^(.*)=\?([^?]*)\?(Q|B)\?([^?]*)\?=(.*)$/Ui',$chunk,$res)) { + /* if the last chunk isn't an encoded string then put back the space, otherwise don't */ + if ($iLastMatch !== $j) { + if ($htmlsave) { + $ret .= ' '; + } else { + $ret .= ' '; + } + } + $iLastMatch = $i; + $j = $i; + if ($htmlsave) { + $ret .= htmlspecialchars($res[1]); + } else { + $ret .= $res[1]; + } $encoding = ucfirst($res[3]); + + /* decide about valid decoding */ + if ($decide && is_conversion_safe($res[2])) { + $utfencode=true; + $can_be_encoded=true; + } else { + $can_be_encoded=false; + } switch ($encoding) { - case 'B': - $replace = base64_decode($res[4]); - $aString[$i] .= charset_decode($res[2],$replace); - break; - case 'Q': - $replace = str_replace('_', ' ', $res[4]); - $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[2], $replace); - } else { - if ($htmlsave) { - $replace = htmlspecialchars($replace); + case 'B': + $replace = base64_decode($res[4]); + if ($utfencode) { + if ($can_be_encoded) { + /* convert string to different charset, + * if functions asks for it (usually in compose) + */ + $ret .= charset_convert($res[2],$replace,$default_charset); + } else { + // convert string to html codes in order to display it + $ret .= charset_decode($res[2],$replace); + } + } else { + if ($htmlsave) { + $replace = htmlspecialchars($replace); + } + $ret.= $replace; } - } - $aString[$i] .= $replace; - break; - default: - break; + break; + case 'Q': + $replace = str_replace('_', ' ', $res[4]); + $replace = preg_replace('/=([0-9a-f]{2})/ie', 'chr(hexdec("\1"))', + $replace); + if ($utfencode) { + if ($can_be_encoded) { + /* convert string to different charset, + * if functions asks for it (usually in compose) + */ + $replace = charset_convert($res[2], $replace,$default_charset); + } else { + // convert string to html codes in order to display it + $replace = charset_decode($res[2], $replace); + } + } else { + if ($htmlsave) { + $replace = htmlspecialchars($replace); + } + } + $ret .= $replace; + break; + default: + break; } $chunk = $res[5]; $encoded = true; - } + } + if (!$encoded) { + if ($htmlsave) { + $ret .= ' '; + } else { + $ret .= ' '; + } + } + if (!$encoded && $htmlsave) { - $aString[$i] = htmlspecialchars($chunk); + $ret .= htmlspecialchars($chunk); } else { - $aString[$i] .= $chunk; + $ret .= $chunk; } ++$i; } - return implode (' ',$aString); + /* remove the first added space */ + if ($ret) { + if ($htmlsave) { + $ret = substr($ret,5); + } else { + $ret = substr($ret,1); + } + } + return $ret; } -/* - * 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. +/** + * Encodes header + * + * Function uses XTRA_CODE _encodeheader function, if such function exists. + * + * mb_encode_mimeheader is used, if function is present, 50% or more bytes + * are 8bit and multibyte character set is used. + * + * Function uses Q encoding by default and encodes 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. + * + * @param string $string header string, that has to be encoded + * @return string quoted-printable encoded string */ function encodeHeader ($string) { global $default_charset, $languages, $squirrelmail_language; if (isset($languages[$squirrelmail_language]['XTRA_CODE']) && - function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) { - return $languages[$squirrelmail_language]['XTRA_CODE']('encodeheader', $string); - } - if (strtolower($default_charset) == 'iso-8859-1') { - $string = str_replace("\240",' ',$string); + function_exists($languages[$squirrelmail_language]['XTRA_CODE'] . '_encodeheader')) { + return call_user_func($languages[$squirrelmail_language]['XTRA_CODE'] . '_encodeheader', $string); } + // Use B encoding for multibyte charsets + /* + $mb_charsets = array('utf-8','big-5','gb2313','euc-kr'); + if (function_exists('mb_encode_mimeheader') && + in_array($default_charset,$mb_charsets) && + in_array($default_charset,sq_mb_list_encodings())) { + return mb_encode_mimeheader($string,$default_charset,'B',"\r\n"); + }*/ + // Encode only if the string contains 8-bit characters or =? $j = strlen($string); $max_l = 75 - strlen($default_charset) - 7; @@ -632,89 +822,94 @@ function encodeHeader ($string) { for($i = 0; $i < $j; ++$i) { switch($string{$i}) { - case '=': - case '<': - case '>': - case ',': - case '?': - case '_': - if ($iEncStart === false) { - $iEncStart = $i; - } - $cur_l+=3; - if ($cur_l > ($max_l-2)) { - $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset); - $aRet[] = "=?$default_charset?Q?$ret?="; - $iOffset = $i; - $cur_l = 0; - $ret = ''; - $iEncStart = false; - } else { - $ret .= sprintf("=%02X",ord($string{$i})); - } - break; - case '(': - case ')': - if ($iEncStart !== false) { - $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset); - $aRet[] = "=?$default_charset?Q?$ret?="; - $iOffset = $i; - $cur_l = 0; - $ret = ''; - $iEncStart = false; - } - break; - case ' ': - if ($iEncStart !== false) { - $cur_l++; - if ($cur_l > $max_l) { - $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset); + case '=': + case '<': + case '>': + case ',': + case '?': + case '_': + if ($iEncStart === false) { + $iEncStart = $i; + } + $cur_l+=3; + if ($cur_l > ($max_l-2)) { + /* if there is an stringpart that doesn't need encoding, add it */ + $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset); $aRet[] = "=?$default_charset?Q?$ret?="; $iOffset = $i; $cur_l = 0; $ret = ''; $iEncStart = false; - } else { - $ret .= '_'; - } - } - break; - default: - $k = ord($string{$i}); - if ($k > 126) { - if ($iEncStart === false) { - $iEncStart = $i; + } else { + $ret .= sprintf("=%02X",ord($string{$i})); } - $cur_l += 3; - if ($cur_l > ($max_l-2)) { - if ($iEncStart !== false) { - $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset); - $aRet[] = "=?$default_charset?Q?$ret?="; - } else { - $aRet[] = substr($string,$iOffset,$i-$iOffset); - } - $cur_l = 3; - $ret = ''; + break; + case '(': + case ')': + if ($iEncStart !== false) { + $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset); + $aRet[] = "=?$default_charset?Q?$ret?="; $iOffset = $i; + $cur_l = 0; + $ret = ''; + $iEncStart = false; } - $enc_init = true; - $ret .= sprintf("=%02X", $k); - } else { + break; + case ' ': if ($iEncStart !== false) { $cur_l++; if ($cur_l > $max_l) { - $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset); + $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset); $aRet[] = "=?$default_charset?Q?$ret?="; - $iEncStart = false; $iOffset = $i; $cur_l = 0; $ret = ''; - } else { - $ret .= $string{$i}; + $iEncStart = false; + } else { + $ret .= '_'; } } - } - break; + break; + default: + $k = ord($string{$i}); + if ($k > 126) { + if ($iEncStart === false) { + // do not start encoding in the middle of a string, also take the rest of the word. + $sLeadString = substr($string,0,$i); + $aLeadString = explode(' ',$sLeadString); + $sToBeEncoded = array_pop($aLeadString); + $iEncStart = $i - strlen($sToBeEncoded); + $ret .= $sToBeEncoded; + $cur_l += strlen($sToBeEncoded); + } + $cur_l += 3; + /* first we add the encoded string that reached it's max size */ + if ($cur_l > ($max_l-2)) { + $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset); + $aRet[] = "=?$default_charset?Q?$ret?= "; /* the next part is also encoded => separate by space */ + $cur_l = 3; + $ret = ''; + $iOffset = $i; + $iEncStart = $i; + } + $enc_init = true; + $ret .= sprintf("=%02X", $k); + } else { + if ($iEncStart !== false) { + $cur_l++; + if ($cur_l > $max_l) { + $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset); + $aRet[] = "=?$default_charset?Q?$ret?="; + $iEncStart = false; + $iOffset = $i; + $cur_l = 0; + $ret = ''; + } else { + $ret .= $string{$i}; + } + } + } + break; } } @@ -738,8 +933,17 @@ function find_ent_id($id, $message) { } else { if (strcasecmp($message->entities[$i]->header->id, $id) == 0) { // if (sq_check_save_extension($message->entities[$i])) { + return $message->entities[$i]->entity_id; +// } + } elseif (!empty($message->entities[$i]->header->parameters['name'])) { + /** + * This is part of a fix for Outlook Express 6.x generating + * cid URLs without creating content-id headers + * @@JA - 20050207 + */ + if (strcasecmp($message->entities[$i]->header->parameters['name'], $id) == 0) { return $message->entities[$i]->entity_id; -// } + } } } } @@ -758,9 +962,52 @@ function sq_check_save_extension($message) { ** HTMLFILTER ROUTINES */ +/** + * 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 $attvalue A string to run entity check against. + * @return Nothing, modifies a reference value. + */ +function sq_defang(&$attvalue){ + $me = 'sq_defang'; + /** + * Skip this if there aren't ampersands or backslashes. + */ + if (strpos($attvalue, '&') === false + && strpos($attvalue, '\\') === false){ + return; + } + $m = false; + do { + $m = false; + $m = $m || sq_deent($attvalue, '/\�*(\d+);*/s'); + $m = $m || sq_deent($attvalue, '/\�*((\d|[a-f])+);*/si', true); + $m = $m || sq_deent($attvalue, '/\\\\(\d+)/s', true); + } while ($m == true); + $attvalue = stripslashes($attvalue); +} + +/** + * Kill any tabs, newlines, or carriage returns. Our friends the + * makers of the browser with 95% market value decided that it'd + * be funny to make "java[tab]script" be just as good as "javascript". + * + * @param attvalue The attribute value before extraneous spaces removed. + * @return attvalue Nothing, modifies a reference value. + */ +function sq_unspace(&$attvalue){ + $me = 'sq_unspace'; + if (strcspn($attvalue, "\t\r\n\0 ") != strlen($attvalue)){ + $attvalue = str_replace(Array("\t", "\r", "\n", "\0", " "), + Array('', '', '', '', ''), $attvalue); + } +} + /** * 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 + * of attributes, and the type of the tag. This function is called by * sq_sanitize internally. * * @param $tagname the name of the tag. @@ -804,7 +1051,7 @@ function sq_casenormalize(&$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 $offset the offset within the string where we should start * looking for the next non-whitespace character. @@ -858,8 +1105,8 @@ function sq_findnxreg($body, $offset, $reg){ $me = 'sq_findnxreg'; $matches = Array(); $retarr = Array(); - preg_match("%^(.*?)($reg)%s", substr($body, $offset), $matches); - if (!$matches{0}){ + preg_match("%^(.*?)($reg)%si", substr($body, $offset), $matches); + if (!isset($matches{0}) || !$matches{0}){ $retarr = false; } else { $retarr{0} = $offset + strlen($matches{1}); @@ -908,7 +1155,7 @@ function sq_getnxtag($body, $offset){ * 2. Closing tag, e.g.: * * 3. XHTML-style content-less tag, e.g.: - * + * */ $tagtype = false; switch (substr($body, $pos, 1)){ @@ -959,14 +1206,14 @@ function sq_getnxtag($body, $offset){ * '>' indicating the end of the tag entirely. * '\s' indicating the end of the tag name. * '/' indicating that this is type-3 xhtml tag. - * + * * Whatever else we find there indicates an invalid tag. */ switch ($match){ case '/': /** * This is an xhtml-style tag with a closing / at the - * end, like so: . Check if it's followed + * end, like so: . Check if it's followed * by the closing bracket. If not, then this tag is invalid */ if (substr($body, $pos, 2) == "/>"){ @@ -988,7 +1235,7 @@ function sq_getnxtag($body, $offset){ /** * This is an invalid tag! Look for the next closing ">". */ - $gt = sq_findnxstr($body, $offset, ">"); + $gt = sq_findnxstr($body, $lt, ">"); return Array(false, false, false, $lt, $gt); } break; @@ -1047,7 +1294,7 @@ function sq_getnxtag($body, $offset){ * double quotes. Type 4 we convert into: * attrname="yes". */ - $regary = sq_findnxreg($body, $pos, "[^\w\-_]"); + $regary = sq_findnxreg($body, $pos, "[^:\w\-_]"); if ($regary == false){ /** * Looks like body ended before the end of tag. @@ -1068,7 +1315,7 @@ function sq_getnxtag($body, $offset){ case '/': /** * This is an xhtml-style tag with a closing / at the - * end, like so: . Check if it's followed + * end, like so: . Check if it's followed * by the closing bracket. If not, then this tag is invalid */ if (substr($body, $pos, 2) == "/>"){ @@ -1161,50 +1408,31 @@ function sq_getnxtag($body, $offset){ } /** - * This function checks attribute values for entity-encoded values - * and returns them translated into 8-bit strings so we can run - * checks on them. + * Translates entities into literal values so they can be checked. * - * @param $attvalue A string to run entity check against. - * @return Translated value. + * @param $attvalue the by-ref value to check. + * @param $regex the regular expression to check against. + * @param $hex whether the entites are hexadecimal. + * @return True or False depending on whether there were matches. */ -function sq_deent($attvalue){ +function sq_deent(&$attvalue, $regex, $hex=false){ $me = 'sq_deent'; - /** - * See if we have to run the checks first. All entities must start - * with "&". - */ - if (strpos($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); + $ret_match = false; + preg_match_all($regex, $attvalue, $matches); + if (is_array($matches) && sizeof($matches[0]) > 0){ + $repl = Array(); + for ($i = 0; $i < sizeof($matches[0]); $i++){ + $numval = $matches[1][$i]; + if ($hex){ + $numval = hexdec($numval); } + $repl{$matches[0][$i]} = chr($numval); } + $attvalue = strtr($attvalue, $repl); + return true; + } else { + return false; } - return $attvalue; } /** @@ -1219,8 +1447,8 @@ function sq_deent($attvalue){ * @param $id message id * @return Array with modified attributes. */ -function sq_fixatts($tagname, - $attary, +function sq_fixatts($tagname, + $attary, $rm_attnames, $bad_attvals, $add_attr_to_tag, @@ -1244,9 +1472,10 @@ function sq_fixatts($tagname, } } /** - * Remove any entities. + * Remove any backslashes, entities, and extraneous whitespace. */ - $attvalue = sq_deent($attvalue); + sq_defang($attvalue); + sq_unspace($attvalue); /** * Now let's run checks on the attvalues. @@ -1264,7 +1493,7 @@ function sq_fixatts($tagname, * Second one is replacements */ list($valmatch, $valrepl) = $valary; - $newvalue = + $newvalue = preg_replace($valmatch, $valrepl, $attvalue); if ($newvalue != $attvalue){ $attary{$attname} = $newvalue; @@ -1273,12 +1502,33 @@ function sq_fixatts($tagname, } } } + + /** + * Replace empty src tags with the blank image. src is only used + * for frames, images, and image inputs. Doing a replace should + * not affect them working as should be, however it will stop + * IE from being kicked off when src for img tags are not set + */ + if (($attname == 'src') && ($attvalue == '""')) { + $attary{$attname} = '"' . SM_PATH . 'images/blank.png"'; + } + /** * Turn cid: urls into http-friendly ones. */ if (preg_match("/^[\'\"]\s*cid:/si", $attvalue)){ $attary{$attname} = sq_cid2http($message, $id, $attvalue, $mailbox); } + + /** + * "Hack" fix for Outlook using propriatary outbind:// protocol in img tags. + * One day MS might actually make it match something useful, for now, falling + * back to using cid2http, so we can grab the blank.png. + */ + if (preg_match("/^[\'\"]\s*outbind:\/\//si", $attvalue)) { + $attary{$attname} = sq_cid2http($message, $id, $attvalue, $mailbox); + } + } /** * See if we need to append any attributes to this tag. @@ -1293,61 +1543,102 @@ function sq_fixatts($tagname, /** * This function edits the style definition to make them friendly and - * usable in squirrelmail. - * + * usable in SquirrelMail. + * * @param $message the message object * @param $id the message id * @param $content a string with whatever is between + * @param $mailbox the message mailbox * @return a string with edited content. */ -function sq_fixstyle($message, $id, $content){ +function sq_fixstyle($body, $pos, $message, $id, $mailbox){ global $view_unsafe_images; $me = 'sq_fixstyle'; + $ret = sq_findnxreg($body, $pos, ''); + if ($ret == FALSE){ + return array(FALSE, strlen($body)); + } + $newpos = $ret[0] + strlen($ret[2]); + $content = $ret[1]; /** - * 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
- */ + * 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
+ */ $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 url('blah') declarations. + */ + // $content = preg_replace("|url\s*\(\s*([\'\"])\s*\S+script\s*:.*?([\'\"])\s*\)|si", + // "url(\\1$secremoveimg\\2)", $content); + // remove NUL + $content = str_replace("\0", "", $content); + // NB I insert NUL characters to keep to avoid an infinite loop. They are removed after the loop. + while (preg_match("/url\s*\(\s*[\'\"]?([^:]+):(.*)?[\'\"]?\s*\)/si", $content, $matches)) { + $sProto = strtolower($matches[1]); + switch ($sProto) { + /** + * Fix url('https*://.*) declarations but only if $view_unsafe_images + * is false. + */ + case 'https': + case 'http': + if (!$view_unsafe_images){ + $sExpr = "/url\s*\(\s*([\'\"])\s*$sProto*:.*?([\'\"])\s*\)/si"; + $content = preg_replace($sExpr, "u\0r\0l(\\1$secremoveimg\\2)", $content); + } + break; + /** + * Fix urls that refer to cid: + */ + case 'cid': + $cidurl = 'cid:'. $matches[2]; + $httpurl = sq_cid2http($message, $id, $cidurl, $mailbox); + $content = preg_replace("|url\s*\(\s*$cidurl\s*\)|si", + "u\0r\0l($httpurl)", $content); + break; + default: + /** + * replace url with protocol other then the white list + * http,https and cid by an empty string. + */ + $content = preg_replace("/url\s*\(\s*[\'\"]?([^:]+):(.*)?[\'\"]?\s*\)/si", + "", $content); + break; + } + break; } + // remove NUL + $content = str_replace("\0", "", $content); + + /** + * Remove any backslashes, entities, and extraneous whitespace. + */ + $contentTemp = $content; + sq_defang($contentTemp); + sq_unspace($contentTemp); /** * Fix stupid css declarations which lead to vulnerabilities * in IE. */ $match = Array('/expression/i', - '/behaviou*r/i', - '/binding/i'); - $replace = Array('idiocy', 'idiocy', 'idiocy'); - $content = preg_replace($match, $replace, $content); - return $content; + '/behaviou*r/i', + '/binding/i', + '/include-source/i'); + $replace = Array('idiocy', 'idiocy', 'idiocy', 'idiocy'); + $contentNew = preg_replace($match, $replace, $contentTemp); + if ($contentNew !== $contentTemp) { + // insecure css declarations are used. From now on we don't care + // anymore if the css is destroyed by sq_deent, sq_unspace or sq_unbackslash + $content = $contentNew; + } + return array($content, $newpos); } + /** * This function converts cid: url's into the ones that can be viewed in * the browser. @@ -1355,6 +1646,7 @@ function sq_fixstyle($message, $id, $content){ * @param $message the message object * @param $id the message id * @param $cidurl the cid: url. + * @param $mailbox the message mailbox * @return a string with a http-friendly url */ function sq_cid2http($message, $id, $cidurl, $mailbox){ @@ -1362,17 +1654,52 @@ function sq_cid2http($message, $id, $cidurl, $mailbox){ * Get rid of quotes. */ $quotchar = substr($cidurl, 0, 1); - $cidurl = str_replace($quotchar, "", $cidurl); + if ($quotchar == '"' || $quotchar == "'"){ + $cidurl = str_replace($quotchar, "", $cidurl); + } else { + $quotchar = ''; + } $cidurl = substr(trim($cidurl), 4); + + $match_str = '/\{.*?\}\//'; + $str_rep = ''; + $cidurl = preg_replace($match_str, $str_rep, $cidurl); + $linkurl = find_ent_id($cidurl, $message); /* in case of non-save cid links $httpurl should be replaced by a sort of unsave link image */ $httpurl = ''; - if ($linkurl) { + + /** + * This is part of a fix for Outlook Express 6.x generating + * cid URLs without creating content-id headers. These images are + * not part of the multipart/related html mail. The html contains + * references to + * attached images with as goal to render them inline although + * the attachment disposition property is not inline. + */ + + if (empty($linkurl)) { + if (preg_match('/{.*}\//', $cidurl)) { + $cidurl = preg_replace('/{.*}\//','', $cidurl); + if (!empty($cidurl)) { + $linkurl = find_ent_id($cidurl, $message); + } + } + } + + if (!empty($linkurl)) { $httpurl = $quotchar . SM_PATH . 'src/download.php?absolute_dl=true&' . - "passed_id=$id&mailbox=" . urlencode($mailbox) . - '&ent_id=' . $linkurl . $quotchar; + "passed_id=$id&mailbox=" . urlencode($mailbox) . + '&ent_id=' . $linkurl . $quotchar; + } else { + /** + * If we couldn't generate a proper img url, drop in a blank image + * instead of sending back empty, otherwise it causes unusual behaviour + */ + $httpurl = $quotchar . SM_PATH . 'images/blank.png' . $quotchar; } + return $httpurl; } @@ -1380,14 +1707,17 @@ function sq_cid2http($message, $id, $cidurl, $mailbox){ * This function changes the tag into a
tag since we * can't really have a body-within-body. * - * @param $attary an array of attributes and values of - * @return a modified array of attributes to be set for
+ * @param $attary an array of attributes and values of + * @param $mailbox mailbox we're currently reading (for cid2http) + * @param $message current message (for cid2http) + * @param $id current message id (for cid2http) + * @return a modified array of attributes to be set for
*/ -function sq_body2div($attary){ +function sq_body2div($attary, $mailbox, $message, $id){ $me = 'sq_body2div'; $divattary = Array('class' => "'bodyclass'"); - $bgcolor = '#ffffff'; $text = '#000000'; + $has_bgc_stl = $has_txt_stl = false; $styledef = ''; if (is_array($attary) && sizeof($attary) > 0){ foreach ($attary as $attname=>$attvalue){ @@ -1395,16 +1725,24 @@ function sq_body2div($attary){ $attvalue = str_replace($quotchar, "", $attvalue); switch ($attname){ case 'background': + $attvalue = sq_cid2http($message, $id, $attvalue, $mailbox); $styledef .= "background-image: url('$attvalue'); "; break; case 'bgcolor': + $has_bgc_stl = true; $styledef .= "background-color: $attvalue; "; break; case 'text': + $has_txt_stl = true; $styledef .= "color: $attvalue; "; break; } } + // Outlook defines a white bgcolor and no text color. This can lead to + // white text on a white bg with certain themes. + if ($has_bgc_stl && !$has_txt_stl) { + $styledef .= "color: $text; "; + } if (strlen($styledef) > 0){ $divattary{"style"} = "\"$styledef\""; } @@ -1418,7 +1756,7 @@ function sq_body2div($attary){ * special description. * * Since the description is quite lengthy, see it here: - * http://www.mricon.com/html/phpfilter.html + * http://linux.duke.edu/projects/mini/htmlfilter/ * * @param $body the string with HTML you wish to filter * @param $tag_list see description above @@ -1432,8 +1770,8 @@ function sq_body2div($attary){ * @param $id message id * @return sanitized html safe to show on your pages. */ -function sq_sanitize($body, - $tag_list, +function sq_sanitize($body, + $tag_list, $rm_tags_with_content, $self_closing_tags, $force_tag_closing, @@ -1445,10 +1783,11 @@ function sq_sanitize($body, $mailbox ){ $me = 'sq_sanitize'; + $rm_tags = array_shift($tag_list); /** * Normalize rm_tags and rm_tags_with_content. */ - @array_walk($rm_tags, 'sq_casenormalize'); + @array_walk($tag_list, 'sq_casenormalize'); @array_walk($rm_tags_with_content, 'sq_casenormalize'); @array_walk($self_closing_tags, 'sq_casenormalize'); /** @@ -1456,10 +1795,9 @@ function sq_sanitize($body, * false means remove these tags * true means allow these tags */ - $rm_tags = array_shift($tag_list); $curpos = 0; $open_tags = Array(); - $trusted = "\n"; + $trusted = "\n\n"; $skip_content = false; /** * Take care of netscape's stupid javascript entities like @@ -1467,18 +1805,21 @@ function sq_sanitize($body, */ $body = preg_replace("/&(\{.*?\};)/si", "&\\1", $body); - while (($curtag=sq_getnxtag($body, $curpos)) != FALSE){ + while (($curtag = sq_getnxtag($body, $curpos)) != FALSE){ list($tagname, $attary, $tagtype, $lt, $gt) = $curtag; $free_content = substr($body, $curpos, $lt-$curpos); /** * Take care of . Edit the - * content before we apply it. - */ - $free_content = sq_fixstyle($message, $id, $free_content); + if ($tagname == "style" && $tagtype == 1){ + list($free_content, $curpos) = + sq_fixstyle($body, $gt+1, $message, $id, $mailbox); + if ($free_content != FALSE){ + $trusted .= sq_tagprint($tagname, $attary, $tagtype); + $trusted .= $free_content; + $trusted .= sq_tagprint($tagname, false, 2); + } + continue; } if ($skip_content == false){ $trusted .= $free_content; @@ -1495,13 +1836,12 @@ function sq_sanitize($body, if ($skip_content == false){ if ($tagname == "body"){ $tagname = "div"; - } else { - if (isset($open_tags{$tagname}) && + } + if (isset($open_tags{$tagname}) && $open_tags{$tagname} > 0){ - $open_tags{$tagname}--; - } else { - $tagname = false; - } + $open_tags{$tagname}--; + } else { + $tagname = false; } } } @@ -1515,23 +1855,31 @@ function sq_sanitize($body, * tagtype appropriately. */ if ($tagtype == 1 - && in_array($tagname, $self_closing_tags)){ - $tagtype=3; + && in_array($tagname, $self_closing_tags)){ + $tagtype = 3; } /** * See if we should skip this tag and any content * inside it. */ if ($tagtype == 1 && - in_array($tagname, $rm_tags_with_content)){ + in_array($tagname, $rm_tags_with_content)){ $skip_content = $tagname; } else { - if (($rm_tags == false - && in_array($tagname, $tag_list)) || - ($rm_tags == true && - !in_array($tagname, $tag_list))){ + if (($rm_tags == false + && in_array($tagname, $tag_list)) || + ($rm_tags == true && + !in_array($tagname, $tag_list))){ $tagname = false; } else { + /** + * Convert body into div. + */ + if ($tagname == "body"){ + $tagname = "div"; + $attary = sq_body2div($attary, $mailbox, + $message, $id); + } if ($tagtype == 1){ if (isset($open_tags{$tagname})){ $open_tags{$tagname}++; @@ -1553,13 +1901,6 @@ function sq_sanitize($body, $mailbox ); } - /** - * Convert body into div. - */ - if ($tagname == "body"){ - $tagname = "div"; - $attary = sq_body2div($attary, $message, $id); - } } } } @@ -1589,9 +1930,18 @@ function sq_sanitize($body, * * @param $body the body of the message * @param $id the id of the message + + * @param $message + * @param $mailbox + * @param boolean $take_mailto_links When TRUE, converts mailto: links + * into internal SM compose links + * (optional; default = TRUE) * @return a string with html safe to display in the browser. */ -function magicHTML($body, $id, $message, $mailbox = 'INBOX') { +function magicHTML($body, $id, $message, $mailbox = 'INBOX', $take_mailto_links =true) { + + require_once(SM_PATH . 'functions/url_parser.php'); // for $MailTo_PReg_Match + global $attachment_common_show_images, $view_unsafe_images, $has_unsafe_images; /** @@ -1599,124 +1949,137 @@ function magicHTML($body, $id, $message, $mailbox = 'INBOX') { */ $attachment_common_show_images = false; $tag_list = Array( - false, - "object", - "meta", - "html", - "head", - "base", - "link", - "frame", - "iframe" - ); + false, + "object", + "meta", + "html", + "head", + "base", + "link", + "frame", + "iframe", + "plaintext", + "marquee" + ); $rm_tags_with_content = Array( - "script", - "applet", - "embed", - "title" - ); + "script", + "applet", + "embed", + "title", + "frameset", + "xmp", + "xml" + ); $self_closing_tags = Array( - "img", - "br", - "hr", - "input" - ); + "img", + "br", + "hr", + "input", + "outbind" + ); - $force_tag_closing = false; + $force_tag_closing = true; $rm_attnames = Array( - "/.*/" => - Array( - "/target/i", - "/^on.*/i", - "/^dynsrc/i", - "/^data.*/i", - "/^lowsrc.*/i" - ) - ); + "/.*/" => + Array( + "/target/i", + "/^on.*/i", + "/^dynsrc/i", + "/^data.*/i", + "/^lowsrc.*/i" + ) + ); $secremoveimg = "../images/" . _("sec_remove_eng.png"); $bad_attvals = Array( - "/.*/" => + "/.*/" => Array( "/^src|background/i" => + Array( Array( - Array( - "|^([\'\"])\s*\.\./.*([\'\"])|si", - "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si", - "/^([\'\"])\s*mocha\s*:*.*([\'\"])/si", - "/^([\'\"])\s*about\s*:.*([\'\"])/si" - ), - Array( - "\\1$secremoveimg\\2", - "\\1$secremoveimg\\2", - "\\1$secremoveimg\\2", - "\\1$secremoveimg\\2" - ) + "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si", + "/^([\'\"])\s*mocha\s*:*.*([\'\"])/si", + "/^([\'\"])\s*about\s*:.*([\'\"])/si" ), + Array( + "\\1$secremoveimg\\2", + "\\1$secremoveimg\\2", + "\\1$secremoveimg\\2", + "\\1$secremoveimg\\2" + ) + ), "/^href|action/i" => + Array( Array( - 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" - ) + "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si", + "/^([\'\"])\s*mocha\s*:*.*([\'\"])/si", + "/^([\'\"])\s*about\s*:.*([\'\"])/si" ), - "/^style/i" => Array( - Array( - "/expression/i", - "/binding/i", - "/behaviou*r/i", - "|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)" - ) - ) + "\\1#\\1", + "\\1#\\1", + "\\1#\\1", + "\\1#\\1" + ) + ), + "/^style/i" => + Array( + Array( + "/expression/i", + "/binding/i", + "/behaviou*r/i", + "/include-source/i", + "/position\s*:\s*absolute/i", + "/url\s*\(\s*([\'\"])\s*\S+script\s*:.*([\'\"])\s*\)/si", + "/url\s*\(\s*([\'\"])\s*mocha\s*:.*([\'\"])\s*\)/si", + "/url\s*\(\s*([\'\"])\s*about\s*:.*([\'\"])\s*\)/si", + "/(.*)\s*:\s*url\s*\(\s*([\'\"]*)\s*\S+script\s*:.*([\'\"]*)\s*\)/si" + ), + Array( + "idiocy", + "idiocy", + "idiocy", + "idiocy", + "", + "url(\\1#\\1)", + "url(\\1#\\1)", + "url(\\1#\\1)", + "url(\\1#\\1)", + "url(\\1#\\1)", + "\\1:url(\\2#\\3)" + ) ) + ) ); if( !sqgetGlobalVar('view_unsafe_images', $view_unsafe_images, SQ_GET) ) { - $view_unsafe_images = false; + $view_unsafe_images = false; } if (!$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/i'}[0], - '/url\(([\'\"])\s*https*:.*([\'\"])\)/si'); - array_push($bad_attvals{'/.*/'}{'/^style/i'}[1], - "url(\\1$secremoveimg\\2)"); + array_push($bad_attvals{'/.*/'}{'/^src|background/i'}[0], + '/^([\'\"])\s*https*:.*([\'\"])/si'); + array_push($bad_attvals{'/.*/'}{'/^src|background/i'}[1], + "\\1$secremoveimg\\1"); + array_push($bad_attvals{'/.*/'}{'/^style/i'}[0], + '/url\(([\'\"])\s*https*:.*([\'\"])\)/si'); + array_push($bad_attvals{'/.*/'}{'/^style/i'}[1], + "url(\\1$secremoveimg\\1)"); } $add_attr_to_tag = Array( - "/^a$/i" => Array('target'=>'"_new"') - ); - $trusted = sq_sanitize($body, - $tag_list, + "/^a$/i" => + Array('target'=>'"_blank"', + 'title'=>'"'._("This external link will open in a new window").'"' + ) + ); + $trusted = sq_sanitize($body, + $tag_list, $rm_tags_with_content, $self_closing_tags, $force_tag_closing, @@ -1729,8 +2092,169 @@ function magicHTML($body, $id, $message, $mailbox = 'INBOX') { ); if (preg_match("|$secremoveimg|i", $trusted)){ $has_unsafe_images = true; - } + } + + // we want to parse mailto's in HTML output, change to SM compose links + // this is a modified version of code from url_parser.php... but Marc is + // right: we need a better filtering implementation; adding this randomly + // here is not a great solution + // + if ($take_mailto_links) { + // parseUrl($trusted); // this even parses URLs inside of tags... too aggressive + global $MailTo_PReg_Match; + $MailTo_PReg_Match = '/mailto:' . substr($MailTo_PReg_Match, 1); + if ((preg_match_all($MailTo_PReg_Match, $trusted, $regs)) && ($regs[0][0] != '')) { + foreach ($regs[0] as $i => $mailto_before) { + $mailto_params = $regs[10][$i]; + // get rid of any tailing quote since we have to add send_to to the end + // + if (substr($mailto_before, strlen($mailto_before) - 1) == '"') + $mailto_before = substr($mailto_before, 0, strlen($mailto_before) - 1); + if (substr($mailto_params, strlen($mailto_params) - 1) == '"') + $mailto_params = substr($mailto_params, 0, strlen($mailto_params) - 1); + + if ($regs[1][$i]) { //if there is an email addr before '?', we need to merge it with the params + $to = 'to=' . $regs[1][$i]; + if (strpos($mailto_params, 'to=') > -1) //already a 'to=' + $mailto_params = str_replace('to=', $to . '%2C%20', $mailto_params); + else { + if ($mailto_params) //already some params, append to them + $mailto_params .= '&' . $to; + else + $mailto_params .= '?' . $to; + } + } + + $url_str = preg_replace(array('/to=/i', '/(?\|;]', '_', str_replace(' ', ' ', $filename)); + } + + // A Pox on Microsoft and it's Internet Explorer! + // + // IE has lots of bugs with file downloads. + // It also has problems with SSL. Both of these cause problems + // for us in this function. + // + // See this article on Cache Control headers and SSL + // http://support.microsoft.com/default.aspx?scid=kb;en-us;323308 + // + // The best thing you can do for IE is to upgrade to the latest + // version + //set all the Cache Control Headers for IE + if ($isIE) { + $filename=rawurlencode($filename); + header ("Pragma: public"); + header ("Cache-Control: no-store, max-age=0, no-cache, must-revalidate"); // HTTP/1.1 + header ("Cache-Control: post-check=0, pre-check=0", false); + header ("Cache-Control: private"); + + //set the inline header for IE, we'll add the attachment header later if we need it + header ("Content-Disposition: inline; filename=$filename"); + } + + if (!$force) { + // Try to show in browser window + header ("Content-Disposition: inline; filename=\"$filename\""); + header ("Content-Type: $type0/$type1; name=\"$filename\""); + } else { + // Try to pop up the "save as" box + + // IE makes this hard. It pops up 2 save boxes, or none. + // http://support.microsoft.com/support/kb/articles/Q238/5/88.ASP + // http://support.microsoft.com/default.aspx?scid=kb;EN-US;260519 + // But, according to Microsoft, it is "RFC compliant but doesn't + // take into account some deviations that allowed within the + // specification." Doesn't that mean RFC non-compliant? + // http://support.microsoft.com/support/kb/articles/Q258/4/52.ASP + + // all browsers need the application/octet-stream header for this + header ("Content-Type: application/octet-stream; name=\"$filename\""); + + // http://support.microsoft.com/support/kb/articles/Q182/3/15.asp + // Do not have quotes around filename, but that applied to + // "attachment"... does it apply to inline too? + header ("Content-Disposition: attachment; filename=\"$filename\""); + + if ($isIE && !$isIE6) { + // This combination seems to work mostly. IE 5.5 SP 1 has + // known issues (see the Microsoft Knowledge Base) + + // This works for most types, but doesn't work with Word files + header ("Content-Type: application/download; name=\"$filename\""); + + // These are spares, just in case. :-) + //header("Content-Type: $type0/$type1; name=\"$filename\""); + //header("Content-Type: application/x-msdownload; name=\"$filename\""); + //header("Content-Type: application/octet-stream; name=\"$filename\""); + } else { + // another application/octet-stream forces download for Netscape + header ("Content-Type: application/octet-stream; name=\"$filename\""); + } + } + + //send the content-length header if the calling function provides it + if ($filesize > 0) { + header("Content-Length: $filesize"); + } + +} // end fn SendDownloadHeaders + ?>