X-Git-Url: https://vcs.fsf.org/?p=squirrelmail.git;a=blobdiff_plain;f=functions%2Fmime.php;h=35ce6e7c3e4771351162dc0c61b2b3c7c80386d4;hp=933523b55a66a179f2c35efcc18eeb737d329351;hb=9b94c54da2dbd7ff84e721712dfc0c75676377c8;hpb=5166f86aad45f37b514887adfc014dd305be0e0e diff --git a/functions/mime.php b/functions/mime.php index 933523b5..35ce6e7c 100644 --- a/functions/mime.php +++ b/functions/mime.php @@ -3,27 +3,53 @@ /** * mime.php * - * Copyright (c) 1999-2003 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 © 1999-2006 The SquirrelMail Project Team + * @license http://opensource.org/licenses/gpl-license.php GNU Public License + * @version $Id$ + * @package squirrelmail */ -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 */ /* -------------------------------------------------------------------------- */ -/* 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, $flags=array()) { /* Isolate the body structure and remove beginning and end parenthesis. */ @@ -32,12 +58,11 @@ function mime_structure ($bodystructure, $flags=array()) { $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, $color ); echo ''; @@ -92,8 +117,7 @@ function mime_structure ($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, $fetch_size=0) { /* Do a bit of error correction. If we couldn't find the entity id, just guess * that it is the first one. That is usually the case anyway. */ @@ -104,7 +128,9 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1) { $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', $topline)) ; @@ -116,7 +142,7 @@ function mime_fetch_body($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 = $regs[1]; @@ -129,21 +155,21 @@ function mime_fetch_body($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('', $data); @@ -152,12 +178,11 @@ function mime_fetch_body($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, $rStream='php://stdout') { /* Don't kill the connection if the browser is over a dialup * and it would take over 30 seconds to download it. - * Don´t call set_time_limit in safe mode. + * Don't call set_time_limit in safe mode. */ if (!ini_get('safe_mode')) { @@ -167,59 +192,36 @@ function mime_print_body_lines ($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,$uid_support,'sqimap_base64_decode','php://stdout',true); + sqimap_run_command($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); + } } - /* + /* 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 + 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. - */ - /* + 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); - $cnt++; -// break; - } -*/ } /* -[ END MIME DECODING ]----------------------------------------------------------- */ @@ -229,7 +231,7 @@ function mime_print_body_lines ($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[$i]); @@ -282,13 +284,13 @@ function translateText(&$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", ' ', $line); @@ -311,15 +313,9 @@ function translateText(&$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] = $line; @@ -327,19 +323,37 @@ function translateText(&$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, $unsafe_image_toggle_text; + + // workaround for not updated config.php + if (! isset($use_iframe)) $use_iframe = false; if( !sqgetGlobalVar('view_unsafe_images', $view_unsafe_images, SQ_GET) ) { $view_unsafe_images = false; @@ -349,14 +363,14 @@ function formatBody($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", $body); @@ -370,29 +384,71 @@ function formatBody($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('html_body', $html_body); + + $body = $oTemplate->fetch('read_html_iframe.tpl'); } else { + // old way of html rendering $body = magicHTML($body, $id, $message, $mailbox); + /** + * 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. + */ + $body = charset_decode($body_message->header->getParameter('charset'),$body,false,true); } } else { translateText($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 = 'read_body.php?passed_id=' . $id . '&ent_id='.$ent_num. - '&mailbox=' . $urlmailbox .'&sort=' . $sort . - '&startMessage=' . $startMessage . '&show_more=0'; + + $download_and_unsafe_link = ''; + + $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; } + $download_href = SM_PATH . 'src/download.php?absolute_dl=true&' . $link; + $download_and_unsafe_link .= ' | ' . _("Download this as a file") . ''; if ($view_unsafe_images) { $text = _("Hide Unsafe Images"); } else { @@ -403,37 +459,46 @@ function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $ma $text = ''; } } - $body .= '

'.$text. - '

' . "\n"; + if($text != '') { + $unsafe_image_toggle_href = SM_PATH . 'src/read_body.php?'.$link; + $unsafe_image_toggle_text = $text; + $download_and_unsafe_link .= ' | ' . $text . ''; + } } 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( $filename ) == '') { @@ -442,41 +507,20 @@ function formatAttachments($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 { @@ -491,62 +535,128 @@ 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. + * 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); + $startMessage, $id, $urlMailbox, $ent, $defaultlink, + $display_filename, $where, $what); +// FIXME: How does this code ever get executed? $hookresults[1] is $links +// from above, and should always be returned by do_hook(). I will +// test this and fix if needed (but it has been working, right???) +// and get rid of these comments (Paul) +// UPDATE: Preliminary testing shows that in fact I am correct that the +// following never gets executed (unless a strange plugin actually +// unsets the contents of the links)... how did this ever work??? +// Can someonen please show a plugin that worked here? if(count($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); } + $hookresults = do_hook("attachment */*", $hookresults[1], + $startMessage, $id, $urlMailbox, $ent, $hookresults[6], + $display_filename, $where, $what); $links = $hookresults[1]; $defaultlink = $hookresults[6]; - $attachments .= '' . - ''.decodeHeader($display_filename).' ' . - '' . show_readable_size($header->size) . - '  ' . - "[ $type0/$type1 ] " . - ''; - $attachments .= '' . $description . ''; - $attachments .= ' '; - - $skipspaces = 1; + $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); @@ -559,15 +669,16 @@ 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); } @@ -575,20 +686,28 @@ 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', $string); + function_exists($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 $string; } @@ -608,55 +727,86 @@ function decodeHeader ($string, $utfencode=true,$htmlsave=true) { $encoded = false; /* if encoded words are not separated by a linear-space-white we still catch them */ $j = $i-1; -// if ($chunk{0} === '=') { /* performance, saves an unnessecarry preg call */ + 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 .= ' '; + $ret .= ' '; } else { $ret .= ' '; } } $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"))', - $replace); - /* Only encode into entities by default. Some places - * don't need the encoding, like the compose form. - */ - if ($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]; $encoded = true; } -// } if (!$encoded) { if ($htmlsave) { - $ret .= ' '; + $ret .= ' '; } else { $ret .= ' '; - } + } } if (!$encoded && $htmlsave) { @@ -669,29 +819,52 @@ function decodeHeader ($string, $utfencode=true,$htmlsave=true) { /* remove the first added space */ if ($ret) { if ($htmlsave) { - $ret = substr($ret,6); + $ret = substr($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. + * + * 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', $string); } - if (strtolower($default_charset) == 'iso-8859-1') { - $string = str_replace("\240",' ',$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($default_charset,sq_mb_list_encodings())) { + // Add E_USER_NOTICE error here (can cause 'Cannot add header information' warning in compose.php) + // trigger_error('encodeHeader: Multibyte character set unsupported by mbstring extension.',E_USER_NOTICE); } // Encode only if the string contains 8-bit characters or =? @@ -704,43 +877,18 @@ function encodeHeader ($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 = $i; @@ -748,50 +896,75 @@ function encodeHeader ($string) { $ret = ''; $iEncStart = false; } else { - $ret .= '_'; + $ret .= sprintf("=%02X",ord($string{$i})); } - } - 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 > ($max_l-2)) { + break; + case '(': + case ')': + if ($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; } } @@ -807,6 +980,100 @@ 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); $i++) { @@ -815,8 +1082,17 @@ function find_ent_id($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; -// } + } } } } @@ -835,9 +1111,52 @@ 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 $tagname the name of the tag. @@ -881,7 +1200,7 @@ function sq_casenormalize(&$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 $offset the offset within the string where we should start * looking for the next non-whitespace character. @@ -985,7 +1304,7 @@ function sq_getnxtag($body, $offset){ * 2. Closing tag, e.g.: * * 3. XHTML-style content-less tag, e.g.: - * + * */ $tagtype = false; switch (substr($body, $pos, 1)){ @@ -1036,14 +1355,14 @@ function sq_getnxtag($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, $pos, 2) == "/>"){ @@ -1145,7 +1464,7 @@ function sq_getnxtag($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, $pos, 2) == "/>"){ @@ -1238,50 +1557,31 @@ function sq_getnxtag($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 $attvalue; } /** @@ -1296,8 +1596,8 @@ function sq_deent($attvalue){ * @param $id message id * @return Array with modified attributes. */ -function sq_fixatts($tagname, - $attary, +function sq_fixatts($tagname, + $attary, $rm_attnames, $bad_attvals, $add_attr_to_tag, @@ -1321,9 +1621,10 @@ function sq_fixatts($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. @@ -1341,7 +1642,7 @@ function sq_fixatts($tagname, * Second one is replacements */ list($valmatch, $valrepl) = $valary; - $newvalue = + $newvalue = preg_replace($valmatch, $valrepl, $attvalue); if ($newvalue != $attvalue){ $attary{$attname} = $newvalue; @@ -1350,12 +1651,33 @@ function sq_fixatts($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, $mailbox); + } + } /** * See if we need to append any attributes to this tag. @@ -1370,14 +1692,15 @@ function sq_fixatts($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 $mailbox the message mailbox * @return a string with edited content. */ -function sq_fixstyle($body, $pos, $message, $id){ +function sq_fixstyle($body, $pos, $message, $id, $mailbox){ global $view_unsafe_images; $me = 'sq_fixstyle'; $ret = sq_findnxreg($body, $pos, ''); @@ -1387,50 +1710,91 @@ function sq_fixstyle($body, $pos, $message, $id){ $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 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); - $content = preg_replace("|url\s*\(\s*$cidurl\s*\)|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); + // translate ur\l and variations (IE parses that) + $content = preg_replace("/(\\\\)?u(\\\\)?r(\\\\)?l(\\\\)?/i", 'url', $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); + + } else { + $content = preg_replace('/url/i',"u\0r\0l",$content); + } + break; + /** + * Fix urls that refer to cid: + */ + case 'cid': + $cidurl = 'cid:'. $matches[2]; + $httpurl = sq_cid2http($message, $id, $cidurl, $mailbox); + // escape parentheses that can modify the regular expression + $cidurl = str_replace(array('(',')'),array('\\(','\\)'),$cidurl); + $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; + } } + // 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); + $match = Array('/\/\*.*\*\//', + '/expression/i', + '/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, $newpos); } + /** * This function converts cid: url's into the ones that can be viewed in * the browser. @@ -1438,6 +1802,7 @@ function sq_fixstyle($body, $pos, $message, $id){ * @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, $mailbox){ @@ -1445,17 +1810,52 @@ function sq_cid2http($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 $httpurl; } @@ -1463,14 +1863,17 @@ function sq_cid2http($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){ @@ -1478,16 +1881,24 @@ 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\""; } @@ -1501,7 +1912,7 @@ 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 $tag_list see description above @@ -1515,8 +1926,8 @@ function sq_body2div($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, $force_tag_closing, @@ -1542,7 +1953,7 @@ function sq_sanitize($body, */ $curpos = 0; $open_tags = Array(); - $trusted = "\n"; + $trusted = "\n\n"; $skip_content = false; /** * Take care of netscape's stupid javascript entities like @@ -1557,8 +1968,8 @@ function sq_sanitize($body, * Take care of