X-Git-Url: https://vcs.fsf.org/?p=squirrelmail.git;a=blobdiff_plain;f=functions%2Fmime.php;h=c151ecf6f5cb2d6d30c52a7426fad33f3827ccc0;hp=1f0e1467d5d1921d1ae2b989a595102134581bb4;hb=515547081d52328045a174ded166ef2c3cbf55f5;hpb=6201339c4c48f41291e01617f70b732210860eee diff --git a/functions/mime.php b/functions/mime.php index 1f0e1467..c151ecf6 100644 --- a/functions/mime.php +++ b/functions/mime.php @@ -3,19 +3,41 @@ /** * mime.php * - * Copyright (c) 1999-2004 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. * - * $Id$ + * @copyright © 1999-2007 The SquirrelMail Project Team + * @license http://opensource.org/licenses/gpl-license.php GNU Public License + * @version $Id$ * @package squirrelmail */ -/** The typical includes... */ -require_once(SM_PATH . 'functions/imap.php'); -require_once(SM_PATH . 'functions/attachment_common.php'); +/** + * dependency information + functions dependency + mime_structure + class/mime/Message.class.php + Message::parseStructure + functions/page_header.php + displayPageHeader + functions/display_messages.php + plain_error_message + mime_fetch_body + functions/imap_general.php + sqimap_run_command + mime_print_body_lines + + + +functions/imap.php +functions/attachment_common.php +functions/display_messages.php + +magicHtml => url_parser +translateText => url_parser + +*/ + /* -------------------------------------------------------------------------- */ /* MIME DECODING */ @@ -35,20 +57,20 @@ function mime_structure ($bodystructure, $flags=array()) { $read = trim(substr ($read, 0, -1)); $i = 0; $msg = Message::parseStructure($read,$i); + if (!is_object($msg)) { - include_once(SM_PATH . 'functions/display_messages.php'); global $color, $mailbox; - /* removed urldecode because $_GET is auto urldecoded ??? */ displayPageHeader( $color, $mailbox ); $errormessage = _("SquirrelMail could not decode the bodystructure of the message"); - $errormessage .= '
'._("the provided bodystructure by your imap-server").':

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

'; $errormessage .= '
' . htmlspecialchars($read) . '
'; - plain_error_message( $errormessage, $color ); + plain_error_message( $errormessage ); echo ''; exit; } if (count($flags)) { foreach ($flags as $flag) { +//FIXME: please document why it is we have to check the first char of the flag but we then go ahead and do a full string comparison anyway. Is this a speed enhancement? If not, let's keep it simple and just compare the full string and forget the switch block. $char = strtoupper($flag{1}); switch ($char) { case 'S': @@ -125,6 +147,8 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1, $fetch_size=0) { // } } else if (ereg('"([^"]*)"', $topline, $regs)) { $ret = $regs[1]; + } else if ((stristr($topline, 'nil') !== false) && (empty($wholemessage))) { + $ret = $wholemessage; } else { global $where, $what, $mailbox, $passed_id, $startMessage; $par = 'mailbox=' . urlencode($mailbox) . '&passed_id=' . $passed_id; @@ -134,19 +158,19 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1, $fetch_size=0) { $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


"; + '&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); @@ -157,11 +181,11 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1, $fetch_size=0) { return $ret; } -function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding) { +function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding, $rStream='php://stdout') { /* Don't kill the connection if the browser is over a dialup * and it would take over 30 seconds to download it. - * Dont call set_time_limit in safe mode. + * Don't call set_time_limit in safe mode. */ if (!ini_get('safe_mode')) { @@ -171,14 +195,18 @@ function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding) { Instead, echo the decoded attachment directly to screen */ if (strtolower($encoding) == 'base64') { if (!$ent_id) { - $query = "FETCH $id BODY[]"; + $query = "FETCH $id BODY[]"; } else { - $query = "FETCH $id BODY[$ent_id]"; + $query = "FETCH $id BODY[$ent_id]"; } - sqimap_run_command($imap_stream,$query,true,$response,$message,TRUE,'sqimap_base64_decode','php://stdout',true); + sqimap_run_command($imap_stream,$query,true,$response,$message,TRUE,'sqimap_base64_decode',$rStream,true); } else { - $body = mime_fetch_body ($imap_stream, $id, $ent_id); - echo decodeBody($body, $encoding); + $body = mime_fetch_body ($imap_stream, $id, $ent_id); + if (is_resource($rStream)) { + fputs($rStream,decodeBody($body,$encoding)); + } else { + echo decodeBody($body, $encoding); + } } /* @@ -190,40 +218,13 @@ function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding) { 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); - $cnt++; -// break; - } -*/ } /* -[ END MIME DECODING ]----------------------------------------------------------- */ @@ -233,7 +234,7 @@ function mime_print_body_lines ($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[$i]); @@ -286,13 +287,13 @@ function translateText(&$body, $wrap_at, $charset) { global $where, $what; /* from searching */ global $color; /* color theme */ - require_once(SM_PATH . 'functions/url_parser.php'); + // require_once(SM_PATH . 'functions/url_parser.php'); $body_ary = explode("\n", $body); for ($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", ' ', $line); @@ -315,15 +316,9 @@ function translateText(&$body, $wrap_at, $charset) { } if ($quotes % 2) { - if (!isset($color[13])) { - $color[13] = '#800000'; - } - $line = '' . $line . ''; + $line = '' . $line . ''; } elseif ($quotes) { - if (!isset($color[14])) { - $color[14] = '#FF0000'; - } - $line = '' . $line . ''; + $line = '' . $line . ''; } $body_ary[$i] = $line; @@ -331,19 +326,38 @@ function translateText(&$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 $clean (since 1.5.1) Do not output stuff that's irrelevant for the printable version. + * @return string html formated message text */ -function formatBody($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, $download_and_unsafe_link, + $download_href, $unsafe_image_toggle_href, $unsafe_image_toggle_text, + $oTemplate, $nbsp; + + // workaround for not updated config.php + if (! isset($use_iframe)) $use_iframe = false; if( !sqgetGlobalVar('view_unsafe_images', $view_unsafe_images, SQ_GET) ) { $view_unsafe_images = false; @@ -353,18 +367,19 @@ function formatBody($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); - $body = $hookResults[1]; + + /* As of 1.5.2, $body is passed (and modified) by reference */ + do_hook('message_body', $body); /* If there are other types that shouldn't be formatted, add * them here. @@ -374,31 +389,76 @@ function formatBody($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); + // Convert character set in order to display html mails in different character set + $html_body = charset_decode($body_message->header->getParameter('charset'),$html_body,false,true); + + // 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; + + global $oTemplate; + $oTemplate->assign('iframe_url', $iframeurl); + $oTemplate->assign('iframe_height', $iframe_height); + $oTemplate->assign('html_body', $html_body); + + $body = $oTemplate->fetch('read_html_iframe.tpl'); } else { + // old way of html rendering + /** + * convert character set. charset_decode does not remove html special chars + * applied by magicHTML functions and does not sanitize them second time if + * fourth argument is true. + */ + $charset = $body_message->header->getParameter('charset'); + if (!empty($charset)) { + $body = charset_decode($charset,$body,false,true); + } $body = magicHTML($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; } + + $download_and_unsafe_link = ''; + $link = 'passed_id=' . $id . '&ent_id='.$ent_num. - '&mailbox=' . $urlmailbox .'&sort=' . $sort . - '&startMessage=' . $startMessage . '&show_more=0'; + '&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") . ''; + $download_href = SM_PATH . 'src/download.php?absolute_dl=true&' . $link; + $download_and_unsafe_link .= "$nbsp|$nbsp" + . create_hyperlink($download_href, _("Download this as a file")); if ($view_unsafe_images) { $text = _("Hide Unsafe Images"); } else { @@ -410,38 +470,46 @@ function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $ma } } if($text != '') { - $body .= ' | ' . $text . ''; + $unsafe_image_toggle_href = SM_PATH . 'src/read_body.php?'.$link; + $unsafe_image_toggle_text = $text; + $download_and_unsafe_link .= "$nbsp|$nbsp" + . create_hyperlink($unsafe_image_toggle_href, $text); } - $body .= '

' . "\n"; } return $body; } - -function formatAttachments($message, $exclude_id, $mailbox, $id) { - global $where, $what, $startMessage, $color; - static $ShownHTML = 0; +/** + * Generate attachments array for passing to templates. Separated from + * formatAttachments() below so that the same array can be given to the + * print-friendly version. + * + * @since 1.5.2 + * @param object $message SquirrelMail message object + * @param array $exclude_id message parts that are not attachments. + * @param string $mailbox mailbox name + * @param integer $id message id + */ +function buildAttachmentArray($message, $exclude_id, $mailbox, $id) { + global $where, $what, $startMessage, $color, $passed_ent_id, $base_uri; $att_ar = $message->getAttachments($exclude_id); - - if (!count($att_ar)) return ''; - - $attachments = ''; - $urlMailbox = urlencode($mailbox); + $attachments = array(); foreach ($att_ar as $att) { $ent = $att->entity_id; $header = $att->header; $type0 = strtolower($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 = array(); + $links['download link']['text'] = _("Download"); + $links['download link']['href'] = $base_uri . + "src/download.php?absolute_dl=true&passed_id=$id&mailbox=$urlMailbox&ent_id=$ent"; + if ($type0 =='message' && $type1 == 'rfc822') { - $default_page = SM_PATH . 'src/read_body.php'; + $default_page = $base_uri . 'src/read_body.php'; $rfc822_header = $att->rfc822_header; $filename = $rfc822_header->subject; if (trim( $filename ) == '') { @@ -450,41 +518,20 @@ function formatAttachments($message, $exclude_id, $mailbox, $id) { $from_o = $rfc822_header->from; if (is_object($from_o)) { $from_name = decodeHeader($from_o->getAddress(false)); + } elseif (is_array($from_o) && count($from_o) && is_object($from_o[0])) { + // something weird happens when a digest message is opened and you return to the digest + // now the from object is part of an array. Probably the parseHeader call overwrites the info + // retrieved from the bodystructure in a different way. We need to fix this later. + // possible starting point, do not fetch header we already have and inspect how + // the rfc822_header object behaves. + $from_name = decodeHeader($from_o[0]->getAddress(false)); } else { $from_name = _("Unknown sender"); } - $description = $from_name; + $description = _("From").': '.$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 = $base_uri . 'src/download.php'; + $filename = $att->getFilename(); if ($header->description) { $description = decodeHeader($header->description); } else { @@ -499,67 +546,151 @@ 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($what); + } + // IE does make use of mime content sniffing. Forcing a download + // prohibit execution of XSS inside an application/octet-stream attachment + if ($type0 == 'application' && $type1 == 'octet-stream') { + $defaultlink .= '&absolute_dl=true'; } + /* 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. + * for a more generic type. Finally, a hook for ALL attachment + * types is run as well. */ - $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); + // First remember the default link. + $defaultlink_orig = $defaultlink; + + /* The API for this hook has changed as of 1.5.2 so that all plugin + arguments are passed in an array instead of each their own plugin + argument, and arguments are passed by reference, so instead of + returning any changes, changes should simply be made to the original + arguments themselves. */ + $temp = array(&$links, &$startMessage, &$id, &$urlMailbox, &$ent, + &$defaultlink, &$display_filename, &$where, &$what); + do_hook("attachment $type0/$type1", $temp); + if(count($links) <= 1 && $defaultlink == $defaultlink_orig) { + /* The API for this hook has changed as of 1.5.2 so that all plugin + arguments are passed in an array instead of each their own plugin + argument, and arguments are passed by reference, so instead of + returning any changes, changes should simply be made to the original + arguments themselves. */ + $temp = array(&$links, &$startMessage, &$id, &$urlMailbox, &$ent, + &$defaultlink, &$display_filename, &$where, &$what); + do_hook("attachment $type0/*", $temp); } - - $links = $hookresults[1]; - $defaultlink = $hookresults[6]; - - $attachments .= '' . - ''.decodeHeader($display_filename).' ' . - '' . show_readable_size($header->size) . - '  ' . - "[ $type0/$type1 ] " . - ''; - $attachments .= '' . $description . ''; - $attachments .= ' '; - - $skipspaces = 1; + /* The API for this hook has changed as of 1.5.2 so that all plugin + arguments are passed in an array instead of each their own plugin + argument, and arguments are passed by reference, so instead of + returning any changes, changes should simply be made to the original + arguments themselves. */ + $temp = array(&$links, &$startMessage, &$id, &$urlMailbox, &$ent, + &$defaultlink, &$display_filename, &$where, &$what); + // Do not let a generic plugin change the default link if a more + // specialized one already did it... + if ($defaultlink != $defaultlink_orig) { + $dummy = ''; + $temp[5] = &$dummy; + } + do_hook("attachment */*", $temp); + + $this_attachment = array(); + $this_attachment['Name'] = decodeHeader($display_filename); + $this_attachment['Description'] = $description; + $this_attachment['DefaultHREF'] = $defaultlink; + $this_attachment['DownloadHREF'] = $links['download link']['href']; + $this_attachment['ViewHREF'] = isset($links['attachment_common']) ? $links['attachment_common']['href'] : ''; + $this_attachment['Size'] = $header->size; + $this_attachment['ContentType'] = htmlspecialchars($type0 .'/'. $type1); + $this_attachment['OtherLinks'] = array(); foreach ($links as $val) { - if ($skipspaces) { - $skipspaces = 0; - } else { - $attachments .= '  |  '; - } - $attachments .= '' . $val['text'] . ''; + if ($val['text']==_("Download") || $val['text'] == _("View")) + continue; + if (empty($val['text']) && empty($val['extra'])) + continue; + + $temp = array(); + $temp['HREF'] = $val['href']; + $temp['Text'] = (empty($val['text']) ? '' : $val['text']) . (empty($val['extra']) ? '' : $val['extra']); + $this_attachment['OtherLinks'][] = $temp; } + $attachments[] = $this_attachment; + unset($links); - $attachments .= "\n"; } - $attachmentadd = do_hook_function('attachments_bottom',$attachments); - if ($attachmentadd != '') - $attachments = $attachmentadd; + return $attachments; } +/** + * 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. + * Since 1.5.2 uses templates and does *not* return a value. + * + * @param object $message SquirrelMail message object + * @param array $exclude_id message parts that are not attachments. + * @param string $mailbox mailbox name + * @param integer $id message id + */ +function formatAttachments($message, $exclude_id, $mailbox, $id) { + global $oTemplate; + + $attach = buildAttachmentArray($message, $exclude_id, $mailbox, $id); + + $oTemplate->assign('attachments', $attach); + $oTemplate->display('read_attachments.tpl'); +} + function sqimap_base64_decode(&$string) { - $string = str_replace("\r\n", "\n", $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. */ +/** + * Decodes encoded message body + * + * This function decodes the body depending on the encoding type. + * Currently quoted-printable and base64 encodings are supported. + * decode_body hook was added to this function in 1.4.2/1.5.0 + * @param string $body encoded message body + * @param string $encoding used encoding + * @return string decoded string + * @since 1.0 + */ function decodeBody($body, $encoding) { - global $show_html_default; $body = str_replace("\r\n", "\n", $body); $encoding = strtolower($encoding); - $encoding_handler = do_hook_function('decode_body', $encoding); + $encoding_handler = do_hook('decode_body', $encoding); // plugins get first shot at decoding the body @@ -567,15 +698,16 @@ function decodeBody($body, $encoding) { if (!empty($encoding_handler) && function_exists($encoding_handler)) { $body = $encoding_handler('decode', $body); - } else if ($encoding == 'quoted-printable' || - $encoding == 'quoted_printable') { + } elseif ($encoding == 'quoted-printable' || + $encoding == 'quoted_printable') { + /** + * quoted_printable_decode() function is broken in older + * php versions. Text with \r\n decoding was fixed only + * in php 4.3.0. Minimal code requirement 4.0.4 + + * str_replace("\r\n", "\n", $body); call. + */ $body = quoted_printable_decode($body); - - while (ereg("=\n", $body)) { - $body = ereg_replace ("=\n", '', $body); - } - - } else if ($encoding == 'base64') { + } elseif ($encoding == 'base64') { $body = base64_decode($body); } @@ -586,7 +718,7 @@ function decodeBody($body, $encoding) { /** * Decodes headers * - * This functions decode strings that is encoded according to + * This function decodes strings that are encoded according to * RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text). * Patched by Christian Schmidt 23/03/2002 * @@ -597,14 +729,14 @@ function decodeBody($body, $encoding) { * @return string decoded header string */ function decodeHeader ($string, $utfencode=true,$htmlsave=true,$decide=false) { - global $languages, $squirrelmail_language; + 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', $string); + function_exists($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 $string; } @@ -636,39 +768,64 @@ function decodeHeader ($string, $utfencode=true,$htmlsave=true,$decide=false) { } $iLastMatch = $i; $j = $i; - $ret .= $res[1]; + if ($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]); - $ret .= charset_decode($res[2],$replace); - break; - case 'Q': - $replace = str_replace('_', ' ', $res[4]); - $replace = preg_replace('/=([0-9a-f]{2})/ie', 'chr(hexdec("\1"))', - $replace); - /* decide about valid decoding */ - if ($decide && is_conversion_safe($res[2])) { - $utfencode=true; - $can_be_decoded=true; - } else { - $can_be_decoded=false; - } - /* Only encode into entities by default. Some places - * don't need the encoding, like the compose form. - */ - if ($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,$htmlsave); + } 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; } - } - $ret .= $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,$htmlsave); + } 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]; $encoded = true; @@ -701,26 +858,43 @@ function decodeHeader ($string, $utfencode=true,$htmlsave=true,$decide=false) { } /** - * Encodes header as quoted-printable + * Encodes header + * + * Function uses XTRA_CODE _encodeheader function, if such function exists. * - * 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 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. + * + * Function switches to B encoding and encodeHeaderBase64() function, if + * string is 8bit and multibyte character set supported by mbstring extension + * is used. It can cause E_USER_NOTICE errors, if interface is used with + * multibyte character set unsupported by mbstring extension. * * @param string $string header string, that has to be encoded * @return string quoted-printable encoded string + * @todo make $mb_charsets system wide constant */ function encodeHeader ($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', $string); + function_exists($languages[$squirrelmail_language]['XTRA_CODE'] . '_encodeheader')) { + return call_user_func($languages[$squirrelmail_language]['XTRA_CODE'] . '_encodeheader', $string); + } + + // Use B encoding for multibyte charsets + $mb_charsets = array('utf-8','big5','gb2313','euc-kr'); + if (in_array($default_charset,$mb_charsets) && + in_array($default_charset,sq_mb_list_encodings()) && + sq_is8bit($string)) { + return encodeHeaderBase64($string,$default_charset); + } elseif (in_array($default_charset,$mb_charsets) && + sq_is8bit($string) && + ! in_array($default_charset,sq_mb_list_encodings())) { + // Add E_USER_NOTICE error here (can cause 'Cannot add header information' warning in compose.php) + // trigger_error('encodeHeader: Multibyte character set unsupported by mbstring extension.',E_USER_NOTICE); } - // instead of removing nbsp here, we don't add it in decodeHeader - // if (strtolower($default_charset) == 'iso-8859-1') { - // $string = str_replace("\240",' ',$string); - //} // Encode only if the string contains 8-bit characters or =? $j = strlen($string); @@ -732,43 +906,18 @@ 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)) { - /* 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 { - $ret .= sprintf("=%02X",ord($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 > $max_l) { + case '=': + case '<': + case '>': + case ',': + case '?': + case '_': + if ($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 = $i; @@ -776,50 +925,75 @@ function encodeHeader ($string) { $ret = ''; $iEncStart = false; } else { - $ret .= '_'; - } - } - 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); + $ret .= sprintf("=%02X",ord($string{$i})); } - $cur_l += 3; - /* first we add the encoded string that reached it's max size */ - if ($cur_l > ($max_l-2)) { + break; + case '(': + case ')': + if ($iEncStart !== false) { $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset); - $aRet[] = "=?$default_charset?Q?$ret?= "; /* the next part is also encoded => separate by space */ - $cur_l = 3; - $ret = ''; + $aRet[] = "=?$default_charset?Q?$ret?="; $iOffset = $i; - $iEncStart = $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); $aRet[] = "=?$default_charset?Q?$ret?="; - $iEncStart = false; $iOffset = $i; $cur_l = 0; $ret = ''; + $iEncStart = false; } else { - $ret .= $string{$i}; + $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; } } @@ -835,6 +1009,100 @@ function encodeHeader ($string) { return $string; } +/** + * Encodes string according to rfc2047 B encoding header formating rules + * + * It is recommended way to encode headers with character sets that store + * symbols in more than one byte. + * + * Function requires mbstring support. If required mbstring functions are missing, + * function returns false and sets E_USER_WARNING level error message. + * + * Minimal requirements - php 4.0.6 with mbstring extension. Please note, + * that mbstring functions will generate E_WARNING errors, if unsupported + * character set is used. mb_encode_mimeheader function provided by php + * mbstring extension is not used in order to get better control of header + * encoding. + * + * Used php code functions - function_exists(), trigger_error(), strlen() + * (is used with charset names and base64 strings). Used php mbstring + * functions - mb_strlen and mb_substr. + * + * Related documents: rfc 2045 (BASE64 encoding), rfc 2047 (mime header + * encoding), rfc 2822 (header folding) + * + * @param string $string header string that must be encoded + * @param string $charset character set. Must be supported by mbstring extension. + * Use sq_mb_list_encodings() to detect supported charsets. + * @return string string encoded according to rfc2047 B encoding formating rules + * @since 1.5.1 + * @todo First header line can be wrapped to $iMaxLength - $HeaderFieldLength - 1 + * @todo Do we want to control max length of header? + * @todo Do we want to control EOL (end-of-line) marker? + * @todo Do we want to translate error message? + */ +function encodeHeaderBase64($string,$charset) { + /** + * Check mbstring function requirements. + */ + if (! function_exists('mb_strlen') || + ! function_exists('mb_substr')) { + // set E_USER_WARNING + trigger_error('encodeHeaderBase64: Required mbstring functions are missing.',E_USER_WARNING); + // return false + return false; + } + + // initial return array + $aRet = array(); + + /** + * header length = 75 symbols max (same as in encodeHeader) + * remove $charset length + * remove =? ? ?= (5 chars) + * remove 2 more chars (\r\n ?) + */ + $iMaxLength = 75 - strlen($charset) - 7; + + // set first character position + $iStartCharNum = 0; + + // loop through all characters. count characters and not bytes. + for ($iCharNum=1; $iCharNum<=mb_strlen($string,$charset); $iCharNum++) { + // encode string from starting character to current character. + $encoded_string = base64_encode(mb_substr($string,$iStartCharNum,$iCharNum-$iStartCharNum,$charset)); + + // Check encoded string length + if(strlen($encoded_string)>$iMaxLength) { + // if string exceeds max length, reduce number of encoded characters and add encoded string part to array + $aRet[] = base64_encode(mb_substr($string,$iStartCharNum,$iCharNum-$iStartCharNum-1,$charset)); + + // set new starting character + $iStartCharNum = $iCharNum-1; + + // encode last char (in case it is last character in string) + $encoded_string = base64_encode(mb_substr($string,$iStartCharNum,$iCharNum-$iStartCharNum,$charset)); + } // if string is shorter than max length - add next character + } + + // add last encoded string to array + $aRet[] = $encoded_string; + + // set initial return string + $sRet = ''; + + // loop through encoded strings + foreach($aRet as $string) { + // TODO: Do we want to control EOL (end-of-line) marker + if ($sRet!='') $sRet.= " "; + + // add header tags and encoded string to return string + $sRet.= '=?'.$charset.'?B?'.$string.'?='; + } + + return $sRet; +} + /* This function trys to locate the entity_id of a specific mime element */ function find_ent_id($id, $message) { for ($i = 0, $ret = ''; $ret == '' && $i < count($message->entities); $i++) { @@ -843,8 +1111,17 @@ function find_ent_id($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; + 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; + } } } } @@ -864,23 +1141,35 @@ function sq_check_save_extension($message) { */ /** - * This function is more or less a wrapper around stripslashes. Apparently - * Explorer is stupid enough to just remove the backslashes and then - * execute the content of the attribute as if nothing happened. - * Who does that? + * 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 The value of the attribute - * @return attvalue The value of the attribute stripslashed. + * @param $attvalue A string to run entity check against. + * @return Nothing, modifies a reference value. */ -function sq_unbackslash($attvalue){ +function sq_defang(&$attvalue){ + $me = 'sq_defang'; /** - * Remove any backslashes. See if there are any first. + * Skip this if there aren't ampersands or backslashes. */ - - if (strstr($attvalue, '\\') !== false){ - $attvalue = stripslashes($attvalue); + if (strpos($attvalue, '&') === false + && strpos($attvalue, '\\') === false){ + return; } - return $attvalue; + $m = false; + // before deent, translate the dangerous unicode characters and ... to safe values + // otherwise the regular expressions do not match. + + + + 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); } /** @@ -889,14 +1178,91 @@ function sq_unbackslash($attvalue){ * be funny to make "java[tab]script" be just as good as "javascript". * * @param attvalue The attribute value before extraneous spaces removed. - * @return attvalue The attribute value after extraneous spaces removed. + * @return attvalue Nothing, modifies a reference value. */ -function sq_unspace($attvalue){ - if (strcspn($attvalue, "\t\r\n") != strlen($attvalue)){ - $attvalue = str_replace(Array("\t", "\r", "\n"), Array('', '', ''), - $attvalue); +function sq_unspace(&$attvalue){ + $me = 'sq_unspace'; + if (strcspn($attvalue, "\t\r\n\0 ") != strlen($attvalue)){ + $attvalue = str_replace(Array("\t", "\r", "\n", "\0", " "), + Array('', '', '', '', ''), $attvalue); } - return $attvalue; +} + +/** + * Translate all dangerous Unicode or Shift_JIS characters which are accepted by + * IE as regular characters. + * + * @param attvalue The attribute value before dangerous characters are translated. + * @return attvalue Nothing, modifies a reference value. + * @author Marc Groot Koerkamp. + */ +function sq_fixIE_idiocy(&$attvalue) { + // remove NUL + $attvalue = str_replace("\0", "", $attvalue); + // remove comments + $attvalue = preg_replace("/(\/\*.*?\*\/)/","",$attvalue); + + // IE has the evil habit of accepting every possible value for the attribute expression. + // The table below contains characters which are parsed by IE if they are used in the "expression" + // attribute value. + $aDangerousCharsReplacementTable = array( + array('ʟ', 'ʟ' ,/* L UNICODE IPA Extension */ + 'ʀ', 'ʀ' ,/* R UNICODE IPA Extension */ + 'ɴ', 'ɴ' ,/* N UNICODE IPA Extension */ + 'E', 'E' ,/* Unicode FULLWIDTH LATIN CAPITAL LETTER E */ + 'e', 'e' ,/* Unicode FULLWIDTH LATIN SMALL LETTER E */ + 'X', 'X',/* Unicode FULLWIDTH LATIN CAPITAL LETTER X */ + 'x', 'x',/* Unicode FULLWIDTH LATIN SMALL LETTER X */ + 'P', 'P',/* Unicode FULLWIDTH LATIN CAPITAL LETTER P */ + 'p', 'p',/* Unicode FULLWIDTH LATIN SMALL LETTER P */ + 'R', 'R',/* Unicode FULLWIDTH LATIN CAPITAL LETTER R */ + 'r', 'r',/* Unicode FULLWIDTH LATIN SMALL LETTER R */ + 'S', 'S',/* Unicode FULLWIDTH LATIN CAPITAL LETTER S */ + 's', 's',/* Unicode FULLWIDTH LATIN SMALL LETTER S */ + 'I', 'I',/* Unicode FULLWIDTH LATIN CAPITAL LETTER I */ + 'i', 'i',/* Unicode FULLWIDTH LATIN SMALL LETTER I */ + 'O', 'O',/* Unicode FULLWIDTH LATIN CAPITAL LETTER O */ + 'o', 'o',/* Unicode FULLWIDTH LATIN SMALL LETTER O */ + 'N', 'N',/* Unicode FULLWIDTH LATIN CAPITAL LETTER N */ + 'n', 'n',/* Unicode FULLWIDTH LATIN SMALL LETTER N */ + 'L', 'L',/* Unicode FULLWIDTH LATIN CAPITAL LETTER L */ + 'l', 'l',/* Unicode FULLWIDTH LATIN SMALL LETTER L */ + 'U', 'U',/* Unicode FULLWIDTH LATIN CAPITAL LETTER U */ + 'u', 'u',/* Unicode FULLWIDTH LATIN SMALL LETTER U */ + 'ⁿ', 'ⁿ' ,/* Unicode SUPERSCRIPT LATIN SMALL LETTER N */ + "\xEF\xBC\xA5", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER E */ // in unicode this is some Chinese char range + "\xEF\xBD\x85", /* Shift JIS FULLWIDTH LATIN SMALL LETTER E */ + "\xEF\xBC\xB8", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER X */ + "\xEF\xBD\x98", /* Shift JIS FULLWIDTH LATIN SMALL LETTER X */ + "\xEF\xBC\xB0", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER P */ + "\xEF\xBD\x90", /* Shift JIS FULLWIDTH LATIN SMALL LETTER P */ + "\xEF\xBC\xB2", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER R */ + "\xEF\xBD\x92", /* Shift JIS FULLWIDTH LATIN SMALL LETTER R */ + "\xEF\xBC\xB3", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER S */ + "\xEF\xBD\x93", /* Shift JIS FULLWIDTH LATIN SMALL LETTER S */ + "\xEF\xBC\xA9", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER I */ + "\xEF\xBD\x89", /* Shift JIS FULLWIDTH LATIN SMALL LETTER I */ + "\xEF\xBC\xAF", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER O */ + "\xEF\xBD\x8F", /* Shift JIS FULLWIDTH LATIN SMALL LETTER O */ + "\xEF\xBC\xAE", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER N */ + "\xEF\xBD\x8E", /* Shift JIS FULLWIDTH LATIN SMALL LETTER N */ + "\xEF\xBC\xAC", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER L */ + "\xEF\xBD\x8C", /* Shift JIS FULLWIDTH LATIN SMALL LETTER L */ + "\xEF\xBC\xB5", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER U */ + "\xEF\xBD\x95", /* Shift JIS FULLWIDTH LATIN SMALL LETTER U */ + "\xE2\x81\xBF", /* Shift JIS FULLWIDTH SUPERSCRIPT N */ + "\xCA\x9F", /* L UNICODE IPA Extension */ + "\xCA\x80", /* R UNICODE IPA Extension */ + "\xC9\xB4"), /* N UNICODE IPA Extension */ + array('l', 'l', 'r','r','n','n', + 'E','E','e','e','X','X','x','x','P','P','p','p','R','R','r','r','S','S','s','s','I','I', + 'i','i','O','O','o','o','N','N','n','n','L','L','l','l','U','U','u','u','n','n', + 'E','e','X','x','P','p','R','r','S','s','I','i','O','o','N','n','L','l','U','u','n','l','r','n')); + $attvalue = str_replace($aDangerousCharsReplacementTable[0],$aDangerousCharsReplacementTable[1],$attvalue); + + // Escapes are useful for special characters like "{}[]()'&. In other cases they are + // used for XSS. + $attvalue = preg_replace("/(\\\\)([a-zA-Z]{1})/",'$2',$attvalue); } /** @@ -1049,7 +1415,7 @@ function sq_getnxtag($body, $offset){ * 2. Closing tag, e.g.: * * 3. XHTML-style content-less tag, e.g.: - * + * */ $tagtype = false; switch (substr($body, $pos, 1)){ @@ -1107,7 +1473,7 @@ function sq_getnxtag($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, $pos, 2) == "/>"){ @@ -1209,7 +1575,7 @@ function sq_getnxtag($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, $pos, 2) == "/>"){ @@ -1302,51 +1668,33 @@ function sq_getnxtag($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 . '*/si', $val, $attvalue); - } - /** - * Now translate numbered entities from 1 to 255 if needed. - */ - if (strpos($attvalue, '#') !== false){ - $omit = Array(34, 39); - for ($asc = 256; $asc >= 0; $asc--){ - if (!in_array($asc, $omit)){ - $chr = chr($asc); - $octrule = '/\�*' . $asc . ';*/si'; - $hexrule = '/\�*' . dechex($asc) . ';*/si'; - $attvalue = preg_replace($octrule, $chr, $attvalue); - $attvalue = preg_replace($hexrule, $chr, $attvalue); + $ret_match = false; + // remove comments + //$attvalue = preg_replace("/(\/\*.*\*\/)/","",$attvalue); + preg_match_all($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 $attvalue; } /** @@ -1386,17 +1734,23 @@ function sq_fixatts($tagname, } } /** - * Remove any backslashes, entities, and extraneous whitespace. + * Workaround for IE quirks */ - $attvalue = sq_unbackslash($attvalue); - $attvalue = sq_deent($attvalue); - $attvalue = sq_unspace($attvalue); + sq_fixIE_idiocy($attvalue); /** - * Remove \r \n \t \0 " " "\\" + * Remove any backslashes, entities, and extraneous whitespace. */ - $attvalue = str_replace(Array("\r", "\n", "\t", "\0", " ", "\\"), - Array('', '','','','',''), $attvalue); + + $oldattvalue = $attvalue; + sq_defang($attvalue); + if ($attname == 'style' && $attvalue !== $oldattvalue) { + // entities are used in the attribute value. In 99% of the cases it's there as XSS + // i.e.
+ $attvalue = "idiocy"; + $attary{$attname} = $attvalue; + } + sq_unspace($attvalue); /** * Now let's run checks on the attvalues. @@ -1418,16 +1772,33 @@ function sq_fixatts($tagname, preg_replace($valmatch, $valrepl, $attvalue); if ($newvalue != $attvalue){ $attary{$attname} = $newvalue; + $attvalue = $newvalue; } } } } } + if ($attname == 'style') { + if (preg_match('/[\0-\37\200-\377]+/',$attvalue)) { + // 8bit and control characters in style attribute values can be used for XSS, remove them + $attary{$attname} = '"disallowed character"'; + } + preg_match_all("/url\s*\((.+)\)/si",$attvalue,$aMatch); + if (count($aMatch)) { + foreach($aMatch[1] as $sMatch) { + // url value + $urlvalue = $sMatch; + sq_fix_url($attname, $urlvalue, $message, $id, $mailbox,"'"); + $attary{$attname} = str_replace($sMatch,$urlvalue,$attvalue); + } + } + } /** - * Turn cid: urls into http-friendly ones. + * Use white list based filtering on attributes which can contain url's */ - if (preg_match("/^[\'\"]\s*cid:/si", $attvalue)){ - $attary{$attname} = sq_cid2http($message, $id, $attvalue, $mailbox); + else if ($attname == 'href' || $attname == 'src' || $attname == 'background') { + sq_fix_url($attname, $attvalue, $message, $id, $mailbox); + $attary{$attname} = $attvalue; } } /** @@ -1441,9 +1812,102 @@ function sq_fixatts($tagname, return $attary; } +/** + * This function filters url's + * + * @param $attvalue String with attribute value to filter + * @param $message message object + * @param $id message id + * @param $mailbox mailbox + * @param $sQuote quoting characters around url's + */ +function sq_fix_url($attname, &$attvalue, $message, $id, $mailbox,$sQuote = '"') { + $attvalue = trim($attvalue); + if ($attvalue && ($attvalue[0] =='"'|| $attvalue[0] == "'")) { + // remove the double quotes + $sQuote = $attvalue[0]; + $attvalue = trim(substr($attvalue,1,-1)); + } + + if( !sqgetGlobalVar('view_unsafe_images', $view_unsafe_images, SQ_GET) ) { + $view_unsafe_images = false; + } + $secremoveimg = '../images/' . _("sec_remove_eng.png"); + + /** + * Replace empty src tags with the blank image. src is only used + * for frames, images, and image inputs. Doing a replace should + * not affect them working as should be, however it will stop + * IE from being kicked off when src for img tags are not set + */ + if ($attvalue == '') { + $attvalue = '"' . SM_PATH . 'images/blank.png"'; + } else { + // first, disallow 8 bit characters and control characters + if (preg_match('/[\0-\37\200-\377]+/',$attvalue)) { + switch ($attname) { + case 'href': + $attvalue = $sQuote . 'http://invalid-stuff-detected.example.com' . $sQuote; + break; + default: + $attvalue = $sQuote . SM_PATH . 'images/blank.png'. $sQuote; + break; + } + } else { + $aUrl = parse_url($attvalue); + if (isset($aUrl['scheme'])) { + switch(strtolower($aUrl['scheme'])) { + case 'mailto': + case 'http': + case 'https': + case 'ftp': + if ($attname != 'href') { + if ($view_unsafe_images == false) { + $attvalue = $sQuote . $secremoveimg . $sQuote; + } else { + if (isset($aUrl['path'])) { + // validate image extension. + $ext = strtolower(substr($aUrl['path'],strrpos($aUrl['path'],'.'))); + if (!in_array($ext,array('.jpeg','.jpg','xjpeg','.gif','.bmp','.jpe','.png','.xbm'))) { + $attvalue = $sQuote . SM_PATH . 'images/blank.png'. $sQuote; + } + } else { + $attvalue = $sQuote . SM_PATH . 'images/blank.png'. $sQuote; + } + } + } + break; + case 'outbind': + /** + * "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. + */ + $attvalue = sq_cid2http($message, $id, $attvalue, $mailbox); + break; + case 'cid': + /** + * Turn cid: urls into http-friendly ones. + */ + $attvalue = sq_cid2http($message, $id, $attvalue, $mailbox); + break; + default: + $attvalue = $sQuote . SM_PATH . 'images/blank.png' . $sQuote; + break; + } + } else { + if (!(isset($aUrl['path']) && $aUrl['path'] == $secremoveimg)) { + // parse_url did not lead to satisfying result + $attvalue = $sQuote . SM_PATH . 'images/blank.png' . $sQuote; + } + } + } + } +} + /** * This function edits the style definition to make them friendly and - * usable in squirrelmail. + * usable in SquirrelMail. * * @param $message the message object * @param $id the message id @@ -1452,60 +1916,142 @@ function sq_fixatts($tagname, * @return a string with edited content. */ function sq_fixstyle($body, $pos, $message, $id, $mailbox){ - global $view_unsafe_images; $me = 'sq_fixstyle'; - $ret = sq_findnxreg($body, $pos, ''); - if ($ret == FALSE){ + // workaround for in between comments + $iCurrentPos = $pos; + $content = ''; + $sToken = ''; + $bSucces = false; + $bEndTag = false; + for ($i=$pos,$iCount=strlen($body);$i<$iCount;++$i) { + $char = $body{$i}; + switch ($char) { + case '<': + $sToken .= $char; + break; + case '/': + if ($sToken == '<') { + $sToken .= $char; + $bEndTag = true; + } else { + $content .= $char; + } + break; + case '>': + if ($bEndTag) { + $sToken .= $char; + if (preg_match('/\<\/\s*style\s*\>/i',$sToken,$aMatch)) { + $newpos = $i + 1; + $bSucces = true; + break 2; + } else { + $content .= $sToken; + } + $bEndTag = false; + } else { + $content .= $char; + } + break; + case '!': + if ($sToken == '<') { + // possible comment + if (isset($body{$i+2}) && substr($body,$i,3) == '!--') { + $i = strpos($body,'-->',$i+3); + if ($i === false) { // no end comment + $i = strlen($body); + } + $sToken = ''; + } + } else { + $content .= $char; + } + break; + default: + if ($bEndTag) { + $sToken .= $char; + } else { + $content .= $char; + } + break; + } + } + if ($bSucces == 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*\(\s*([\'\"])\s*\S+script\s*:.*?([\'\"])\s*\)|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*\(\s*([\'\"])\s*https*:.*?([\'\"])\s*\)|si", - "url(\\1$secremoveimg\\2)", $content); + * Fix url('blah') declarations. + */ + // $content = preg_replace("|url\s*\(\s*([\'\"])\s*\S+script\s*:.*?([\'\"])\s*\)|si", + // "url(\\1$secremoveimg\\2)", $content); + + // first check for 8bit sequences and disallowed control characters + if (preg_match('/[\16-\37\200-\377]+/',$content)) { + $content = ''; + return array($content, $newpos); } - /** - * Fix urls that refer to cid: - */ - while (preg_match("|url\s*\(\s*([\'\"]\s*cid:.*?[\'\"])\s*\)|si", - $content, $matches)){ - $cidurl = $matches{1}; - $httpurl = sq_cid2http($message, $id, $cidurl, $mailbox); - $content = preg_replace("|url\s*\(\s*$cidurl\s*\)|si", - "url($httpurl)", $content); + // IE Sucks hard. We have a special function for it. + sq_fixIE_idiocy($content); + + // remove @import line + $content = preg_replace("/^\s*(@import.*)$/mi","\n\n",$content); + + // translate ur\l and variations (IE parses that) + // TODO check if the sq_fixIE_idiocy function already handles this. + $content = preg_replace("/(\\\\)?u(\\\\)?r(\\\\)?l(\\\\)?/i", 'url', $content); + preg_match_all("/url\s*\((.+)\)/si",$content,$aMatch); + if (count($aMatch)) { + $aValue = $aReplace = array(); + foreach($aMatch[1] as $sMatch) { + // url value + $urlvalue = $sMatch; + sq_fix_url('style',$urlvalue, $message, $id, $mailbox,"'"); + $aValue[] = $sMatch; + $aReplace[] = $urlvalue; + } + $content = str_replace($aValue,$aReplace,$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', - '/include-source/i'); - $replace = Array('idiocy', 'idiocy', 'idiocy', 'idiocy'); - $content = preg_replace($match, $replace, $content); + $match = Array('/\/\*.*\*\//', + '/expression/i', + '/behaviou*r/i', + '/binding/i', + '/include-source/i', + '/javascript/i', + '/script/i'); + $replace = Array('','idiocy', 'idiocy', '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, $newpos); } + /** * This function converts cid: url's into the ones that can be viewed in * the browser. @@ -1527,15 +2073,46 @@ function sq_cid2http($message, $id, $cidurl, $mailbox){ $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 $httpurl; } @@ -1552,7 +2129,6 @@ function sq_cid2http($message, $id, $cidurl, $mailbox){ function sq_body2div($attary, $mailbox, $message, $id){ $me = 'sq_body2div'; $divattary = Array('class' => "'bodyclass'"); - $bgcolor = '#ffffff'; $text = '#000000'; $has_bgc_stl = $has_txt_stl = false; $styledef = ''; @@ -1562,8 +2138,7 @@ function sq_body2div($attary, $mailbox, $message, $id){ $attvalue = str_replace($quotchar, "", $attvalue); switch ($attname){ case 'background': - $attvalue = sq_cid2http($message, $id, - $attvalue, $mailbox); + $attvalue = sq_cid2http($message, $id, $attvalue, $mailbox); $styledef .= "background-image: url('$attvalue'); "; break; case 'bgcolor': @@ -1594,7 +2169,7 @@ function sq_body2div($attary, $mailbox, $message, $id){ * 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 $tag_list see description above @@ -1676,7 +2251,7 @@ function sq_sanitize($body, $tagname = "div"; } if (isset($open_tags{$tagname}) && - $open_tags{$tagname} > 0){ + $open_tags{$tagname} > 0){ $open_tags{$tagname}--; } else { $tagname = false; @@ -1693,7 +2268,7 @@ function sq_sanitize($body, * tagtype appropriately. */ if ($tagtype == 1 - && in_array($tagname, $self_closing_tags)){ + && in_array($tagname, $self_closing_tags)){ $tagtype = 3; } /** @@ -1701,13 +2276,13 @@ function sq_sanitize($body, * 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, $tag_list))){ + && in_array($tagname, $tag_list)) || + ($rm_tags == true && + !in_array($tagname, $tag_list))){ $tagname = false; } else { /** @@ -1716,7 +2291,7 @@ function sq_sanitize($body, if ($tagname == "body"){ $tagname = "div"; $attary = sq_body2div($attary, $mailbox, - $message, $id); + $message, $id); } if ($tagtype == 1){ if (isset($open_tags{$tagname})){ @@ -1768,115 +2343,131 @@ 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; /** * Don't display attached images in HTML mode. + * + * SB: why? */ $attachment_common_show_images = false; $tag_list = Array( - false, - "object", - "meta", - "html", - "head", - "base", - "link", - "frame", - "iframe", - "plaintext", - "marquee" - ); + false, + "object", + "meta", + "html", + "head", + "base", + "link", + "frame", + "iframe", + "plaintext", + "marquee" + ); $rm_tags_with_content = Array( - "script", - "applet", - "embed", - "title", - "frameset", - "xml" - ); + "script", + "applet", + "embed", + "title", + "frameset", + "xmp", + "xml" + ); $self_closing_tags = Array( - "img", - "br", - "hr", - "input" - ); + "img", + "br", + "hr", + "input", + "outbind" + ); $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"); $bad_attvals = Array( - "/.*/" => + "/.*/" => Array( "/^src|background/i" => + Array( Array( - Array( - "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si", - "/^([\'\"])\s*mocha\s*:*.*([\'\"])/si", - "/^([\'\"])\s*about\s*:.*([\'\"])/si" - ), - Array( - "\\1$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", + ) + ), "/^href|action/i" => + Array( Array( - Array( - "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si", - "/^([\'\"])\s*mocha\s*:*.*([\'\"])/si", - "/^([\'\"])\s*about\s*:.*([\'\"])/si" - ), - Array( - "\\1#\\1", - "\\1#\\1", - "\\1#\\1", - "\\1#\\1" - ) + "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si", + "/^([\'\"])\s*mocha\s*:*.*([\'\"])/si", + "/^([\'\"])\s*about\s*:.*([\'\"])/si" ), - "/^style/i" => Array( - Array( - "/expression/i", - "/binding/i", - "/behaviou*r/i", - "/include-source/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)", - "\\1:url(\\2#\\3)" - ) - ) + "\\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", + "/(\\\\)?u(\\\\)?r(\\\\)?l(\\\\)?/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", + "idiocy", + "url", + "url(\\1#\\1)", + "url(\\1#\\1)", + "url(\\1#\\1)", + "\\1:url(\\2#\\3)" + ) ) + ) ); if( !sqgetGlobalVar('view_unsafe_images', $view_unsafe_images, SQ_GET) ) { $view_unsafe_images = false; @@ -1886,22 +2477,22 @@ function magicHTML($body, $id, $message, $mailbox = 'INBOX') { * Remove any references to http/https if view_unsafe_images set * to false. */ - array_push($bad_attvals{'/.*/'}{'/^src|background/i'}[0], - '/^([\'\"])\s*https*:.*([\'\"])/si'); - array_push($bad_attvals{'/.*/'}{'/^src|background/i'}[1], - "\\1$secremoveimg\\1"); - array_push($bad_attvals{'/.*/'}{'/^style/i'}[0], - '/url\(([\'\"])\s*https*:.*([\'\"])\)/si'); - array_push($bad_attvals{'/.*/'}{'/^style/i'}[1], - "url(\\1$secremoveimg\\1)"); + 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\([\'\"]?https?:[^\)]*[\'\"]?\)/si'); + array_push($bad_attvals{'/.*/'}{'/^style/i'}[1], + "url(\\1$secremoveimg\\1)"); } $add_attr_to_tag = Array( - "/^a$/i" => - Array('target'=>'"_new"', - 'title'=>'"'._("This external link will open in a new window").'"' - ) - ); + "/^a$/i" => + Array('target'=>'"_blank"', + 'title'=>'"'._("This external link will open in a new window").'"' + ) + ); $trusted = sq_sanitize($body, $tag_list, $rm_tags_with_content, @@ -1914,9 +2505,62 @@ function magicHTML($body, $id, $message, $mailbox = 'INBOX') { $id, $mailbox ); - if (preg_match("|$secremoveimg|i", $trusted)){ + if (strpos($trusted,$secremoveimg)){ $has_unsafe_images = true; } + + // we want to parse mailto's in HTML output, change to SM compose links + // this is a modified version of code from url_parser.php... but Marc is + // right: we need a better filtering implementation; adding this randomly + // here is not a great solution + // + if ($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; + } + } + + $url_str = preg_replace(array('/to=/i', '/(?= 6 && strstr($HTTP_USER_AGENT, 'Opera') === false) { + $isIE6plus = true; + } + + if (isset($languages[$squirrelmail_language]['XTRA_CODE']) && + function_exists($languages[$squirrelmail_language]['XTRA_CODE'] . '_downloadfilename')) { + $filename = + call_user_func($languages[$squirrelmail_language]['XTRA_CODE'] . '_downloadfilename', $filename, $HTTP_USER_AGENT); + } else { $filename = ereg_replace('[\\/:\*\?"<>\|;]', '_', str_replace(' ', ' ', $filename)); - } - - // A Pox on Microsoft and it's Office! - if (!$force) { - // Try to show in browser window - header("Content-Disposition: inline; filename=\"$filename\""); - header("Content-Type: $type0/$type1; name=\"$filename\""); - } else { - // Try to pop up the "save as" box - // IE makes this hard. It pops up 2 save boxes, or none. - // http://support.microsoft.com/support/kb/articles/Q238/5/88.ASP - // But, accordint to Microsoft, it is "RFC compliant but doesn't - // take into account some deviations that allowed within the - // specification." Doesn't that mean RFC non-compliant? - // http://support.microsoft.com/support/kb/articles/Q258/4/52.ASP - // - // The best thing you can do for IE is to upgrade to the latest - // version - if ($isIE && !$isIE6) { - // http://support.microsoft.com/support/kb/articles/Q182/3/15.asp - // Do not have quotes around filename, but that applied to - // "attachment"... does it apply to inline too? - // - // This combination seems to work mostly. IE 5.5 SP 1 has - // known issues (see the Microsoft Knowledge Base) - header("Content-Disposition: inline; filename=$filename"); - // 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=\"$filename\""); - } else { - header("Content-Disposition: attachment; filename=\"$filename\""); - // 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: $filesize"); - } + } - } // end fn SendDownlaodHeaders + // A Pox on Microsoft and it's Internet Explorer! + // + // IE has lots of bugs with file downloads. + // It also has problems with SSL. Both of these cause problems + // for us in this function. + // + // See this article on Cache Control headers and SSL + // http://support.microsoft.com/default.aspx?scid=kb;en-us;323308 + // + // The best thing you can do for IE is to upgrade to the latest + // version + //set all the Cache Control Headers for IE + if ($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 && !$isIE6plus) { + // This combination seems to work mostly. IE 5.5 SP 1 has + // known issues (see the Microsoft Knowledge Base) + + // This works for most types, but doesn't work with Word files + header ("Content-Type: application/download; name=\"$filename\""); + header ("Content-Type: application/force-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=\"$filename\""); + } else if ($isIE) { + // This is to prevent IE for MIME sniffing and auto open a file in IE + header ("Content-Type: application/force-download; 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