X-Git-Url: https://vcs.fsf.org/?p=squirrelmail.git;a=blobdiff_plain;f=functions%2Fmime.php;h=00469acebd13974eff9707f46fbe376c1b9a8f13;hp=9f7692b09e54c474cf86b789c433c9c4e302d1ad;hb=5a6fde9e7a1b7494f27a621d8944f7de968bb66d;hpb=80b4debd1dafcedd50ba876abb246d73ce1f5b62 diff --git a/functions/mime.php b/functions/mime.php index 9f7692b0..00469ace 100644 --- a/functions/mime.php +++ b/functions/mime.php @@ -1,17 +1,19 @@ '._("the provided bodystructure by your imap-server").':

'; + $errormessage .= '
'._("the provided bodystructure by your imap-server").':

'; $errormessage .= '
' . htmlspecialchars($read) . '
'; plain_error_message( $errormessage, $color ); echo ''; @@ -84,19 +88,18 @@ function mime_structure ($bodystructure, $flags=array()) { /* This starts the parsing of a particular structure. It is called recursively, - * so it can be passed different structures. It returns an object of type - * $message. - * First, it checks to see if it is a multipart message. If it is, then it - * handles that as it sees is necessary. If it is just a regular entity, - * then it parses it and adds the necessary header information (by calling out - * to mime_get_elements() - */ +* so it can be passed different structures. It returns an object of type +* $message. +* First, it checks to see if it is a multipart message. If it is, then it +* handles that as it sees is necessary. If it is just a regular entity, +* then it parses it and adds the necessary header information (by calling out +* to mime_get_elements() +*/ function mime_fetch_body($imap_stream, $id, $ent_id=1, $fetch_size=0) { - global $uid_support; /* Do a bit of error correction. If we couldn't find the entity id, just guess - * that it is the first one. That is usually the case anyway. - */ + * that it is the first one. That is usually the case anyway. + */ if (!$ent_id) { $cmd = "FETCH $id BODY[]"; @@ -105,8 +108,8 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1, $fetch_size=0) { } if ($fetch_size!=0) $cmd .= "<0.$fetch_size>"; - - $data = sqimap_run_command ($imap_stream, $cmd, true, $response, $message, $uid_support); + + $data = sqimap_run_command ($imap_stream, $cmd, true, $response, $message, TRUE); do { $topline = trim(array_shift($data)); } while($topline && ($topline[0] == '*') && !preg_match('/\* [0-9]+ FETCH.*/i', $topline)) ; @@ -115,10 +118,10 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1, $fetch_size=0) { if (ereg('\\{([^\\}]*)\\}', $topline, $regs)) { $ret = substr($wholemessage, 0, $regs[1]); /* There is some information in the content info header that could be important - * in order to parse html messages. Let's get them here. - */ + * in order to parse html messages. Let's get them here. + */ // if ($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 = $regs[1]; @@ -134,18 +137,18 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1, $fetch_size=0) { '&message=' . urlencode($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, $uid_support); + echo '
' . + '' . + '' . + '" . + '" . + '" . + '" . + "
' . + _("Body retrieval error. The reason for this is most probably that the message is malformed.") . + '
' . _("Command:") . "$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('', $data); @@ -155,43 +158,42 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1, $fetch_size=0) { } function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding) { - global $uid_support; /* Don't kill the connection if the browser is over a dialup - * and it would take over 30 seconds to download it. - * Don´t call set_time_limit in safe mode. - */ + * and it would take over 30 seconds to download it. + * Don't call set_time_limit in safe mode. + */ if (!ini_get('safe_mode')) { set_time_limit(0); } /* in case of base64 encoded attachments, do not buffer them. - Instead, echo the decoded attachment directly to screen */ + Instead, echo the decoded attachment directly to screen */ if (strtolower($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','php://stdout',true); } else { - $body = mime_fetch_body ($imap_stream, $id, $ent_id); - echo decodeBody($body, $encoding); + $body = mime_fetch_body ($imap_stream, $id, $ent_id); + echo decodeBody($body, $encoding); } - /* - TODO, use the same method for quoted printable. - However, I assume that quoted printable attachments aren't that large - so the performancegain / memory usage drop will be minimal. - If we decide to add that then we need to adapt sqimap_fread because - we need to split te result on \n and fread doesn't stop at \n. That - means we also should provide $results from sqimap_fread (by ref) to - te function and set $no_return to false. The $filter function for - quoted printable should handle unsetting of $results. + /* + TODO, use the same method for quoted printable. + However, I assume that quoted printable attachments aren't that large + so the performancegain / memory usage drop will be minimal. + If we decide to add that then we need to adapt sqimap_fread because + we need to split te result on \n and fread doesn't stop at \n. That + means we also should provide $results from sqimap_fread (by ref) to + te function and set $no_return to false. The $filter function for + quoted printable should handle unsetting of $results. */ - /* - TODO 2: find out how we write to the output stream php://stdout. fwrite - doesn't work because 'php://stdout isn't a stream. + /* + TODO 2: find out how we write to the output stream php://stdout. fwrite + doesn't work because 'php://stdout isn't a stream. */ return; @@ -212,7 +214,7 @@ function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding) { return; } else { echo decodeBody($read1, $encoding) . - decodeBody($read, $encoding); + decodeBody($read, $encoding); } } else if ($cnt) { echo decodeBody($read, $encoding); @@ -227,11 +229,11 @@ function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding) { /* -[ END MIME DECODING ]----------------------------------------------------------- */ /* This is here for debugging purposes. It will print out a list - * of all the entity IDs that are in the $message object. - */ +* of all the entity IDs that are in the $message object. +*/ function listEntities ($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[$i]); @@ -277,8 +279,8 @@ function getEntity ($message, $ent_id) { } /* translateText - * Extracted from strings.php 23/03/2002 - */ +* Extracted from strings.php 23/03/2002 +*/ function translateText(&$body, $wrap_at, $charset) { global $where, $what; /* from searching */ @@ -290,7 +292,7 @@ function translateText(&$body, $wrap_at, $charset) { for ($i=0; $i < count($body_ary); $i++) { $line = $body_ary[$i]; if (strlen($line) - 2 >= $wrap_at) { - sqWordWrap($line, $wrap_at); + sqWordWrap($line, $wrap_at, $charset); } $line = charset_decode($charset, $line); $line = str_replace("\t", ' ', $line); @@ -329,19 +331,20 @@ function translateText(&$body, $wrap_at, $charset) { $body = '
' . implode("\n", $body_ary) . '
'; } -/* This returns a parsed string called $body. That string can then - * be displayed as the actual message in the HTML. It contains - * everything needed, including HTML Tags, Attachments at the - * bottom, etc. - */ -function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $mailbox='INBOX') { +/** +* This returns a parsed string called $body. That string can then +* be displayed as the actual message in the HTML. It contains +* everything needed, including HTML Tags, Attachments at the +* bottom, etc. +* @param clean Do not output stuff that's irrelevant for the printable version. +*/ +function formatBody($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; + * primary message. To add more of them, just put them in the + * order that is their priority. + */ + global $startMessage, $languages, $squirrelmail_language, + $show_html_default, $sort, $has_unsafe_images, $passed_ent_id; if( !sqgetGlobalVar('view_unsafe_images', $view_unsafe_images, SQ_GET) ) { $view_unsafe_images = false; @@ -356,45 +359,55 @@ function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $ma $body = decodeBody($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 = $hookResults[1]; /* If there are other types that shouldn't be formatted, add - * them here. - */ + * them here. + */ if ($body_message->header->type1 == 'html') { if ($show_html_default <> 1) { $entity_conv = array(' ' => ' ', - '

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

' => "\n", - '
' => "\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')); } else { $body = magicHTML($body, $id, $message, $mailbox); } } else { translateText($body, $wrap_at, - $body_message->header->getParameter('charset')); + $body_message->header->getParameter('charset')); + } + + // if this is the clean display (i.e. printer friendly), stop here. + if ( $clean ) { + return $body; } - $link = 'read_body.php?passed_id=' . $id . '&ent_id='.$ent_num. + + $link = 'passed_id=' . $id . '&ent_id='.$ent_num. '&mailbox=' . $urlmailbox .'&sort=' . $sort . - '&startMessage=' . $startMessage . '&show_more=0'; + '&startMessage=' . $startMessage . '&show_more=0'; if (isset($passed_ent_id)) { $link .= '&passed_ent_id='.$passed_ent_id; } + $body .= '

' . _("Download this as a file") . ''; if ($view_unsafe_images) { $text = _("Hide Unsafe Images"); } else { @@ -405,16 +418,17 @@ function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $ma $text = ''; } } - $body .= '
'.$text. - '

' . "\n"; + if($text != '') { + $body .= ' | ' . $text . ''; + } + $body .= '

' . "\n"; } return $body; } function formatAttachments($message, $exclude_id, $mailbox, $id) { - global $where, $what, $startMessage, $color; - static $ShownHTML = 0; + global $where, $what, $startMessage, $color, $passed_ent_id; $att_ar = $message->getAttachments($exclude_id); @@ -430,10 +444,9 @@ function formatAttachments($message, $exclude_id, $mailbox, $id) { $type0 = strtolower($header->type0); $type1 = strtolower($header->type1); $name = ''; - $links['download link']['text'] = _("download"); + $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"; - $ImageURL = ''; if ($type0 =='message' && $type1 == 'rfc822') { $default_page = SM_PATH . 'src/read_body.php'; $rfc822_header = $att->rfc822_header; @@ -450,35 +463,7 @@ function formatAttachments($message, $exclude_id, $mailbox, $id) { $description = $from_name; } else { $default_page = SM_PATH . 'src/download.php'; - if (is_object($header->disposition)) { - $filename = $header->disposition->getProperty('filename'); - if (trim($filename) == '') { - $name = decodeHeader($header->disposition->getProperty('name')); - if (trim($name) == '') { - $name = $header->getParameter('name'); - if(trim($name) == '') { - if (trim( $header->id ) == '') { - $filename = 'untitled-[' . $ent . ']' ; - } else { - $filename = 'cid: ' . $header->id; - } - } else { - $filename = $name; - } - } else { - $filename = $name; - } - } - } else { - $filename = $header->getParameter('name'); - if (!trim($filename)) { - if (trim( $header->id ) == '') { - $filename = 'untitled-[' . $ent . ']' ; - } else { - $filename = 'cid: ' . $header->id; - } - } - } + $filename = $att->getFilename(); if ($header->description) { $description = decodeHeader($header->description); } else { @@ -493,35 +478,36 @@ function formatAttachments($message, $exclude_id, $mailbox, $id) { $passed_ent_id_link = ''; } $defaultlink = $default_page . "?startMessage=$startMessage" - . "&passed_id=$id&mailbox=$urlMailbox" - . '&ent_id='.$ent.$passed_ent_id_link; + . "&passed_id=$id&mailbox=$urlMailbox" + . '&ent_id='.$ent.$passed_ent_id_link; if ($where && $what) { - $defaultlink .= '&where='. urlencode($where).'&what='.urlencode($what); + $defaultlink .= '&where='. urlencode($where).'&what='.urlencode($what); } + /* This executes the attachment hook with a specific MIME-type. - * If that doesn't have results, it tries if there's a rule - * for a more generic type. - */ + * If that doesn't have results, it tries if there's a rule + * for a more generic type. + */ $hookresults = do_hook("attachment $type0/$type1", $links, - $startMessage, $id, $urlMailbox, $ent, $defaultlink, - $display_filename, $where, $what); + $startMessage, $id, $urlMailbox, $ent, $defaultlink, + $display_filename, $where, $what); if(count($hookresults[1]) <= 1) { $hookresults = do_hook("attachment $type0/*", $links, - $startMessage, $id, $urlMailbox, $ent, $defaultlink, - $display_filename, $where, $what); + $startMessage, $id, $urlMailbox, $ent, $defaultlink, + $display_filename, $where, $what); } $links = $hookresults[1]; $defaultlink = $hookresults[6]; - $attachments .= '' . - ''.decodeHeader($display_filename).' ' . - '' . show_readable_size($header->size) . - '  ' . - "[ $type0/$type1 ] " . - ''; + $attachments .= '' . + ''.decodeHeader($display_filename).' ' . + '' . show_readable_size($header->size) . + '  ' . + '[ '.htmlspecialchars($type0).'/'.htmlspecialchars($type1).' ] ' . + ''; $attachments .= '' . $description . ''; - $attachments .= ' '; + $attachments .= ' '; $skipspaces = 1; foreach ($links as $val) { @@ -533,7 +519,7 @@ function formatAttachments($message, $exclude_id, $mailbox, $id) { $attachments .= '' . $val['text'] . ''; } unset($links); - $attachments .= "\n"; + $attachments .= "\n"; } $attachmentadd = do_hook_function('attachments_bottom',$attachments); if ($attachmentadd != '') @@ -542,10 +528,30 @@ function formatAttachments($message, $exclude_id, $mailbox, $id) { } function sqimap_base64_decode(&$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 $sStringRem; } + /* This function decodes the body depending on the encoding type. */ function decodeBody($body, $encoding) { global $show_html_default; @@ -577,20 +583,28 @@ function decodeBody($body, $encoding) { return $body; } -/* - * This functions decode strings that is encoded according to - * RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text). - * Patched by Christian Schmidt 23/03/2002 - */ -function decodeHeader ($string, $utfencode=true,$htmlsave=true) { - global $languages, $squirrelmail_language; +/** +* 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,$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 $string; } @@ -610,35 +624,67 @@ function decodeHeader ($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],$replace); + if ($utfencode) { + if ($can_be_encoded) { + /* convert string to different charset, + * if functions asks for it (usually in compose) + */ + $ret .= charset_convert($res[2],$replace,$default_charset); + } else { + // convert string to html codes in order to display it + $ret .= charset_decode($res[2],$replace); + } + } else { + if ($htmlsave) { + $replace = htmlspecialchars($replace); + } + $ret.= $replace; + } break; case 'Q': $replace = str_replace('_', ' ', $res[4]); - $replace = preg_replace('/=([0-9a-f]{2})/ie', 'chr(hexdec("\1"))', + $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) { + if ($can_be_encoded) { + /* convert string to different charset, + * if functions asks for it (usually in compose) + */ + $replace = charset_convert($res[2], $replace,$default_charset); + } else { + // convert string to html codes in order to display it $replace = charset_decode($res[2], $replace); + } } else { if ($htmlsave) { $replace = htmlspecialchars($replace); @@ -652,13 +698,12 @@ function decodeHeader ($string, $utfencode=true,$htmlsave=true) { $chunk = $res[5]; $encoded = true; } -// } if (!$encoded) { if ($htmlsave) { - $ret .= ' '; + $ret .= ' '; } else { $ret .= ' '; - } + } } if (!$encoded && $htmlsave) { @@ -671,29 +716,31 @@ function decodeHeader ($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 as quoted-printable +* +* 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. +* +* @param string $string header string, that has to be encoded +* @return string quoted-printable encoded string +*/ function encodeHeader ($string) { global $default_charset, $languages, $squirrelmail_language; if (isset($languages[$squirrelmail_language]['XTRA_CODE']) && - function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) { - return $languages[$squirrelmail_language]['XTRA_CODE']('encodeheader', $string); - } - if (strtolower($default_charset) == 'iso-8859-1') { - $string = str_replace("\240",' ',$string); + function_exists($languages[$squirrelmail_language]['XTRA_CODE'] . '_encodeheader')) { + return call_user_func($languages[$squirrelmail_language]['XTRA_CODE'] . '_encodeheader', $string); } // Encode only if the string contains 8-bit characters or =? @@ -761,7 +808,7 @@ function encodeHeader ($string) { // 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); + $sToBeEncoded = array_pop($aLeadString); $iEncStart = $i - strlen($sToBeEncoded); $ret .= $sToBeEncoded; $cur_l += strlen($sToBeEncoded); @@ -818,7 +865,16 @@ function find_ent_id($id, $message) { if (strcasecmp($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; + } } } } @@ -834,22 +890,23 @@ function sq_check_save_extension($message) { /** - ** HTMLFILTER ROUTINES - */ +** HTMLFILTER ROUTINES +*/ /** - * This function is more or less a wrapper around stripslashes. Apparently - * Explorer is stupid enough to just remove the backslashes and then - * execute the content of the attribute as if nothing happened. - * Who does that? - * - * @param attvalue The value of the attribute - * @return attvalue The value of the attribute stripslashed. - */ +* This function is more or less a wrapper around stripslashes. Apparently +* Explorer is stupid enough to just remove the backslashes and then +* execute the content of the attribute as if nothing happened. +* Who does that? +* +* @param attvalue The value of the attribute +* @return attvalue The value of the attribute stripslashed. +*/ function sq_unbackslash($attvalue){ /** - * Remove any backslashes. See if there are any first. - */ + * Remove any backslashes. See if there are any first. + */ + if (strstr($attvalue, '\\') !== false){ $attvalue = stripslashes($attvalue); } @@ -857,13 +914,13 @@ function sq_unbackslash($attvalue){ } /** - * Kill any tabs, newlines, or carriage returns. Our friends the - * makers of the browser with 95% market value decided that it'd - * be funny to make "java[tab]script" be just as good as "javascript". - * - * @param attvalue The attribute value before extraneous spaces removed. - * @return attvalue The attribute value after extraneous spaces removed. - */ +* Kill any tabs, newlines, or carriage returns. Our friends the +* makers of the browser with 95% market value decided that it'd +* be funny to make "java[tab]script" be just as good as "javascript". +* +* @param attvalue The attribute value before extraneous spaces removed. +* @return attvalue The attribute value after extraneous spaces removed. +*/ function sq_unspace($attvalue){ if (strcspn($attvalue, "\t\r\n") != strlen($attvalue)){ $attvalue = str_replace(Array("\t", "\r", "\n"), Array('', '', ''), @@ -873,15 +930,15 @@ function sq_unspace($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 - * sq_sanitize internally. - * - * @param $tagname the name of the tag. - * @param $attary the array of attributes and their values - * @param $tagtype The type of the tag (see in comments). - * @return a string with the final tag representation. - */ +* This function returns the final tag out of the tag name, an array +* of attributes, and the type of the tag. This function is called by +* sq_sanitize internally. +* +* @param $tagname the name of the tag. +* @param $attary the array of attributes and their values +* @param $tagtype The type of the tag (see in comments). +* @return a string with the final tag representation. +*/ function sq_tagprint($tagname, $attary, $tagtype){ $me = 'sq_tagprint'; @@ -905,26 +962,26 @@ function sq_tagprint($tagname, $attary, $tagtype){ } /** - * A small helper function to use with array_walk. Modifies a by-ref - * value and makes it lowercase. - * - * @param $val a value passed by-ref. - * @return void since it modifies a by-ref value. - */ +* A small helper function to use with array_walk. Modifies a by-ref +* value and makes it lowercase. +* +* @param $val a value passed by-ref. +* @return void since it modifies a by-ref value. +*/ function sq_casenormalize(&$val){ $val = strtolower($val); } /** - * This function skips any whitespace from the current position within - * a string and to the next non-whitespace value. - * - * @param $body the string - * @param $offset the offset within the string where we should start - * looking for the next non-whitespace character. - * @return the location within the $body where the next - * non-whitespace char is located. - */ +* This function skips any whitespace from the current position within +* a string and to the next non-whitespace value. +* +* @param $body the string +* @param $offset the offset within the string where we should start +* looking for the next non-whitespace character. +* @return the location within the $body where the next +* non-whitespace char is located. +*/ function sq_skipspace($body, $offset){ $me = 'sq_skipspace'; preg_match('/^(\s*)/s', substr($body, $offset), $matches); @@ -936,16 +993,16 @@ function sq_skipspace($body, $offset){ } /** - * This function looks for the next character within a string. It's - * really just a glorified "strpos", except it catches if failures - * nicely. - * - * @param $body The string to look for needle in. - * @param $offset Start looking from this position. - * @param $needle The character/string to look for. - * @return location of the next occurance of the needle, or - * strlen($body) if needle wasn't found. - */ +* This function looks for the next character within a string. It's +* really just a glorified "strpos", except it catches if failures +* nicely. +* +* @param $body The string to look for needle in. +* @param $offset Start looking from this position. +* @param $needle The character/string to look for. +* @return location of the next occurance of the needle, or +* strlen($body) if needle wasn't found. +*/ function sq_findnxstr($body, $offset, $needle){ $me = 'sq_findnxstr'; $pos = strpos($body, $needle, $offset); @@ -956,18 +1013,18 @@ function sq_findnxstr($body, $offset, $needle){ } /** - * This function takes a PCRE-style regexp and tries to match it - * within the string. - * - * @param $body The string to look for needle in. - * @param $offset Start looking from here. - * @param $reg A PCRE-style regex to match. - * @return Returns a false if no matches found, or an array - * with the following members: - * - integer with the location of the match within $body - * - string with whatever content between offset and the match - * - string with whatever it is we matched - */ +* This function takes a PCRE-style regexp and tries to match it +* within the string. +* +* @param $body The string to look for needle in. +* @param $offset Start looking from here. +* @param $reg A PCRE-style regex to match. +* @return Returns a false if no matches found, or an array +* with the following members: +* - integer with the location of the match within $body +* - string with whatever content between offset and the match +* - string with whatever it is we matched +*/ function sq_findnxreg($body, $offset, $reg){ $me = 'sq_findnxreg'; $matches = Array(); @@ -984,19 +1041,19 @@ function sq_findnxreg($body, $offset, $reg){ } /** - * This function looks for the next tag. - * - * @param $body String where to look for the next tag. - * @param $offset Start looking from here. - * @return false if no more tags exist in the body, or - * an array with the following members: - * - string with the name of the tag - * - array with attributes and their values - * - integer with tag type (1, 2, or 3) - * - integer where the tag starts (starting "<") - * - integer where the tag ends (ending ">") - * first three members will be false, if the tag is invalid. - */ +* This function looks for the next tag. +* +* @param $body String where to look for the next tag. +* @param $offset Start looking from here. +* @return false if no more tags exist in the body, or +* an array with the following members: +* - string with the name of the tag +* - array with attributes and their values +* - integer with tag type (1, 2, or 3) +* - integer where the tag starts (starting "<") +* - integer where the tag ends (ending ">") +* first three members will be false, if the tag is invalid. +*/ function sq_getnxtag($body, $offset){ $me = 'sq_getnxtag'; if ($offset > strlen($body)){ @@ -1007,23 +1064,23 @@ function sq_getnxtag($body, $offset){ return false; } /** - * We are here: - * blah blah - * \---------^ - */ + * We are here: + * blah blah + * \---------^ + */ $pos = sq_skipspace($body, $lt+1); if ($pos >= strlen($body)){ return Array(false, false, false, $lt, strlen($body)); } /** - * There are 3 kinds of tags: - * 1. Opening tag, e.g.: - * - * 2. Closing tag, e.g.: - * - * 3. XHTML-style content-less tag, e.g.: - * - */ + * There are 3 kinds of tags: + * 1. Opening tag, e.g.: + * + * 2. Closing tag, e.g.: + * + * 3. XHTML-style content-less tag, e.g.: + * + */ $tagtype = false; switch (substr($body, $pos, 1)){ case '/': @@ -1032,8 +1089,8 @@ function sq_getnxtag($body, $offset){ break; case '!': /** - * A comment or an SGML declaration. - */ + * A comment or an SGML declaration. + */ if (substr($body, $pos+1, 2) == "--"){ $gt = strpos($body, "-->", $pos); if ($gt === false){ @@ -1049,18 +1106,17 @@ function sq_getnxtag($body, $offset){ break; default: /** - * Assume tagtype 1 for now. If it's type 3, we'll switch values - * later. - */ + * Assume tagtype 1 for now. If it's type 3, we'll switch values + * later. + */ $tagtype = 1; break; } - $tag_start = $pos; $tagname = ''; /** - * Look for next [\W-_], which will indicate the end of the tag name. - */ + * Look for next [\W-_], which will indicate the end of the tag name. + */ $regary = sq_findnxreg($body, $pos, "[^\w\-_]"); if ($regary == false){ return Array(false, false, false, $lt, strlen($body)); @@ -1069,20 +1125,20 @@ function sq_getnxtag($body, $offset){ $tagname = strtolower($tagname); /** - * $match can be either of these: - * '>' indicating the end of the tag entirely. - * '\s' indicating the end of the tag name. - * '/' indicating that this is type-3 xhtml tag. - * - * Whatever else we find there indicates an invalid tag. - */ + * $match can be either of these: + * '>' indicating the end of the tag entirely. + * '\s' indicating the end of the tag name. + * '/' indicating that this is type-3 xhtml tag. + * + * Whatever else we find there indicates an invalid tag. + */ switch ($match){ case '/': /** - * This is an xhtml-style tag with a closing / at the - * end, like so: . Check if it's followed - * by the closing bracket. If not, then this tag is invalid - */ + * This is an xhtml-style tag with a closing / at the + * end, like so: . Check if it's followed + * by the closing bracket. If not, then this tag is invalid + */ if (substr($body, $pos, 2) == "/>"){ $pos++; $tagtype = 3; @@ -1096,12 +1152,12 @@ function sq_getnxtag($body, $offset){ break; default: /** - * Check if it's whitespace - */ + * Check if it's whitespace + */ if (!preg_match('/\s/', $match)){ /** - * This is an invalid tag! Look for the next closing ">". - */ + * This is an invalid tag! Look for the next closing ">". + */ $gt = sq_findnxstr($body, $lt, ">"); return Array(false, false, false, $lt, $gt); } @@ -1109,33 +1165,32 @@ function sq_getnxtag($body, $offset){ } /** - * At this point we're here: - * - * \-------^ - * - * At this point we loop in order to find all attributes. - */ + * At this point we're here: + * + * \-------^ + * + * At this point we loop in order to find all attributes. + */ $attname = ''; - $atttype = false; $attary = Array(); while ($pos <= strlen($body)){ $pos = sq_skipspace($body, $pos); if ($pos == strlen($body)){ /** - * Non-closed tag. - */ + * Non-closed tag. + */ return Array(false, false, false, $lt, $pos); } /** - * See if we arrived at a ">" or "/>", which means that we reached - * the end of the tag. - */ + * See if we arrived at a ">" or "/>", which means that we reached + * the end of the tag. + */ $matches = Array(); if (preg_match("%^(\s*)(>|/>)%s", substr($body, $pos), $matches)) { /** - * Yep. So we did. - */ + * Yep. So we did. + */ $pos += strlen($matches{1}); if ($matches{2} == "/>"){ $tagtype = 3; @@ -1145,46 +1200,46 @@ function sq_getnxtag($body, $offset){ } /** - * There are several types of attributes, with optional - * [:space:] between members. - * Type 1: - * attrname[:space:]=[:space:]'CDATA' - * Type 2: - * attrname[:space:]=[:space:]"CDATA" - * Type 3: - * attr[:space:]=[:space:]CDATA - * Type 4: - * attrname - * - * We leave types 1 and 2 the same, type 3 we check for - * '"' and convert to """ if needed, then wrap in - * double quotes. Type 4 we convert into: - * attrname="yes". - */ + * There are several types of attributes, with optional + * [:space:] between members. + * Type 1: + * attrname[:space:]=[:space:]'CDATA' + * Type 2: + * attrname[:space:]=[:space:]"CDATA" + * Type 3: + * attr[:space:]=[:space:]CDATA + * Type 4: + * attrname + * + * We leave types 1 and 2 the same, type 3 we check for + * '"' and convert to """ if needed, then wrap in + * double quotes. Type 4 we convert into: + * attrname="yes". + */ $regary = sq_findnxreg($body, $pos, "[^:\w\-_]"); if ($regary == false){ /** - * Looks like body ended before the end of tag. - */ + * Looks like body ended before the end of tag. + */ return Array(false, false, false, $lt, strlen($body)); } list($pos, $attname, $match) = $regary; $attname = strtolower($attname); /** - * We arrived at the end of attribute name. Several things possible - * here: - * '>' means the end of the tag and this is attribute type 4 - * '/' if followed by '>' means the same thing as above - * '\s' means a lot of things -- look what it's followed by. - * anything else means the attribute is invalid. - */ + * We arrived at the end of attribute name. Several things possible + * here: + * '>' means the end of the tag and this is attribute type 4 + * '/' if followed by '>' means the same thing as above + * '\s' means a lot of things -- look what it's followed by. + * anything else means the attribute is invalid. + */ switch($match){ case '/': /** - * This is an xhtml-style tag with a closing / at the - * end, like so: . Check if it's followed - * by the closing bracket. If not, then this tag is invalid - */ + * This is an xhtml-style tag with a closing / at the + * end, like so: . Check if it's followed + * by the closing bracket. If not, then this tag is invalid + */ if (substr($body, $pos, 2) == "/>"){ $pos++; $tagtype = 3; @@ -1199,27 +1254,27 @@ function sq_getnxtag($body, $offset){ break; default: /** - * Skip whitespace and see what we arrive at. - */ + * Skip whitespace and see what we arrive at. + */ $pos = sq_skipspace($body, $pos); $char = substr($body, $pos, 1); /** - * Two things are valid here: - * '=' means this is attribute type 1 2 or 3. - * \w means this was attribute type 4. - * anything else we ignore and re-loop. End of tag and - * invalid stuff will be caught by our checks at the beginning - * of the loop. - */ + * Two things are valid here: + * '=' means this is attribute type 1 2 or 3. + * \w means this was attribute type 4. + * anything else we ignore and re-loop. End of tag and + * invalid stuff will be caught by our checks at the beginning + * of the loop. + */ if ($char == "="){ $pos++; $pos = sq_skipspace($body, $pos); /** - * Here are 3 possibilities: - * "'" attribute type 1 - * '"' attribute type 2 - * everything else is the content of tag type 3 - */ + * Here are 3 possibilities: + * "'" attribute type 1 + * '"' attribute type 2 + * everything else is the content of tag type 3 + */ $quot = substr($body, $pos, 1); if ($quot == "'"){ $regary = sq_findnxreg($body, $pos+1, "\'"); @@ -1239,28 +1294,28 @@ function sq_getnxtag($body, $offset){ $attary{$attname} = '"' . $attval . '"'; } else { /** - * These are hateful. Look for \s, or >. - */ + * These are hateful. Look for \s, or >. + */ $regary = sq_findnxreg($body, $pos, "[\s>]"); if ($regary == false){ return Array(false, false, false, $lt, strlen($body)); } list($pos, $attval, $match) = $regary; /** - * If it's ">" it will be caught at the top. - */ + * If it's ">" it will be caught at the top. + */ $attval = preg_replace("/\"/s", """, $attval); $attary{$attname} = '"' . $attval . '"'; } } else if (preg_match("|[\w/>]|", $char)) { /** - * That was attribute type 4. - */ + * That was attribute type 4. + */ $attary{$attname} = '"yes"'; } else { /** - * An illegal character. Find next '>' and return. - */ + * An illegal character. Find next '>' and return. + */ $gt = sq_findnxstr($body, $pos, ">"); return Array(false, false, false, $lt, $gt); } @@ -1268,53 +1323,54 @@ function sq_getnxtag($body, $offset){ } } /** - * The fact that we got here indicates that the tag end was never - * found. Return invalid tag indication so it gets stripped. - */ + * The fact that we got here indicates that the tag end was never + * found. Return invalid tag indication so it gets stripped. + */ return Array(false, false, false, $lt, strlen($body)); } /** - * This function checks attribute values for entity-encoded values - * and returns them translated into 8-bit strings so we can run - * checks on them. - * - * @param $attvalue A string to run entity check against. - * @return Translated value. - */ +* This function checks attribute values for entity-encoded values +* and returns them translated into 8-bit strings so we can run +* checks on them. +* +* @param $attvalue A string to run entity check against. +* @return Translated value. +*/ + function sq_deent($attvalue){ $me = 'sq_deent'; /** - * See if we have to run the checks first. All entities must start - * with "&". - */ - if (strpos($attvalue, "&") === false){ + * See if we have to run the checks first. All entities must start + * with "&". + */ + if (strpos($attvalue, '&') === false){ return $attvalue; } /** - * Check named entities first. - */ + * Check named entities first. + */ $trans = get_html_translation_table(HTML_ENTITIES); /** - * Leave " in, as it can mess us up. - */ + * Leave " in, as it can mess us up. + */ $trans = array_flip($trans); - unset($trans{"""}); + unset($trans{'"'}); while (list($ent, $val) = each($trans)){ - $attvalue = preg_replace("/$ent*(\W)/si", "$val\\1", $attvalue); + $attvalue = preg_replace('/' . $ent . '*/si', $val, $attvalue); } /** - * Now translate numbered entities from 1 to 255 if needed. - */ - if (strpos($attvalue, "#") !== false){ + * Now translate numbered entities from 1 to 255 if needed. + */ + if (strpos($attvalue, '#') !== false){ $omit = Array(34, 39); - for ($asc=1; $asc<256; $asc++){ + for ($asc = 256; $asc >= 0; $asc--){ if (!in_array($asc, $omit)){ $chr = chr($asc); - $attvalue = preg_replace("/\�*$asc;*(\D)/si", "$chr\\1", - $attvalue); - $attvalue = preg_replace("/\�*".dechex($asc).";*(\W)/si", - "$chr\\1", $attvalue); + $octrule = '/\�*' . $asc . ';*/si'; + $hexrule = '/\�*' . dechex($asc) . ';*/si'; + $attvalue = preg_replace($octrule, $chr, $attvalue); + $attvalue = preg_replace($hexrule, $chr, $attvalue); } } } @@ -1322,19 +1378,19 @@ function sq_deent($attvalue){ } /** - * This function runs various checks against the attributes. - * - * @param $tagname String with the name of the tag. - * @param $attary Array with all tag attributes. - * @param $rm_attnames See description for sq_sanitize - * @param $bad_attvals See description for sq_sanitize - * @param $add_attr_to_tag See description for sq_sanitize - * @param $message message object - * @param $id message id - * @return Array with modified attributes. - */ -function sq_fixatts($tagname, - $attary, +* This function runs various checks against the attributes. +* +* @param $tagname String with the name of the tag. +* @param $attary Array with all tag attributes. +* @param $rm_attnames See description for sq_sanitize +* @param $bad_attvals See description for sq_sanitize +* @param $add_attr_to_tag See description for sq_sanitize +* @param $message message object +* @param $id message id +* @return Array with modified attributes. +*/ +function sq_fixatts($tagname, + $attary, $rm_attnames, $bad_attvals, $add_attr_to_tag, @@ -1345,8 +1401,8 @@ function sq_fixatts($tagname, $me = 'sq_fixatts'; while (list($attname, $attvalue) = each($attary)){ /** - * See if this attribute should be removed. - */ + * See if this attribute should be removed. + */ foreach ($rm_attnames as $matchtag=>$matchattrs){ if (preg_match($matchtag, $tagname)){ foreach ($matchattrs as $matchattr){ @@ -1358,29 +1414,35 @@ function sq_fixatts($tagname, } } /** - * Remove any backslashes, entities, and extraneous whitespace. - */ + * Remove any backslashes, entities, and extraneous whitespace. + */ $attvalue = sq_unbackslash($attvalue); $attvalue = sq_deent($attvalue); $attvalue = sq_unspace($attvalue); /** - * Now let's run checks on the attvalues. - * I don't expect anyone to comprehend this. If you do, - * get in touch with me so I can drive to where you live and - * shake your hand personally. :) - */ + * Remove \r \n \t \0 " " "\\" + */ + $attvalue = str_replace(Array("\r", "\n", "\t", "\0", " ", "\\"), + Array('', '','','','',''), $attvalue); + + /** + * Now let's run checks on the attvalues. + * I don't expect anyone to comprehend this. If you do, + * get in touch with me so I can drive to where you live and + * shake your hand personally. :) + */ foreach ($bad_attvals as $matchtag=>$matchattrs){ if (preg_match($matchtag, $tagname)){ foreach ($matchattrs as $matchattr=>$valary){ if (preg_match($matchattr, $attname)){ /** - * There are two arrays in valary. - * First is matches. - * Second one is replacements - */ + * There are two arrays in valary. + * First is matches. + * Second one is replacements + */ list($valmatch, $valrepl) = $valary; - $newvalue = + $newvalue = preg_replace($valmatch, $valrepl, $attvalue); if ($newvalue != $attvalue){ $attary{$attname} = $newvalue; @@ -1389,16 +1451,38 @@ function sq_fixatts($tagname, } } } + + /** - * Turn cid: urls into http-friendly ones. + * 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, $mailbox); + } + } /** - * See if we need to append any attributes to this tag. - */ + * See if we need to append any attributes to this tag. + */ foreach ($add_attr_to_tag as $matchtag=>$addattary){ if (preg_match($matchtag, $tagname)){ $attary = array_merge($attary, $addattary); @@ -1408,15 +1492,16 @@ function sq_fixatts($tagname, } /** - * This function edits the style definition to make them friendly and - * usable in squirrelmail. - * - * @param $message the message object - * @param $id the message id - * @param $content a string with whatever is between - * @return a string with edited content. - */ -function sq_fixstyle($body, $pos, $message, $id){ +* This function edits the style definition to make them friendly and +* usable in SquirrelMail. +* +* @param $message the message object +* @param $id the message id +* @param $content a string with whatever is between +* @param $mailbox the message mailbox +* @return a string with edited content. +*/ +function sq_fixstyle($body, $pos, $message, $id, $mailbox){ global $view_unsafe_images; $me = 'sq_fixstyle'; $ret = sq_findnxreg($body, $pos, ''); @@ -1426,64 +1511,65 @@ function sq_fixstyle($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. - */ + * 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. - */ + * 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)){ + * 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); + $httpurl = sq_cid2http($message, $id, $cidurl, $mailbox); $content = preg_replace("|url\s*\(\s*$cidurl\s*\)|si", "url($httpurl)", $content); } /** - * Fix stupid css declarations which lead to vulnerabilities - * in IE. - */ + * Fix stupid css declarations which lead to vulnerabilities + * in IE. + */ $match = Array('/expression/i', - '/behaviou*r/i', - '/binding/i', - '/include-source/i'); + '/behaviou*r/i', + '/binding/i', + '/include-source/i'); $replace = Array('idiocy', 'idiocy', 'idiocy', 'idiocy'); $content = preg_replace($match, $replace, $content); return array($content, $newpos); } /** - * This function converts cid: url's into the ones that can be viewed in - * the browser. - * - * @param $message the message object - * @param $id the message id - * @param $cidurl the cid: url. - * @return a string with a http-friendly url - */ +* This function converts cid: url's into the ones that can be viewed in +* the browser. +* +* @param $message the message object +* @param $id the message id +* @param $cidurl the cid: url. +* @param $mailbox the message mailbox +* @return a string with a http-friendly url +*/ function sq_cid2http($message, $id, $cidurl, $mailbox){ /** - * Get rid of quotes. - */ + * Get rid of quotes. + */ $quotchar = substr($cidurl, 0, 1); if ($quotchar == '"' || $quotchar == "'"){ $cidurl = str_replace($quotchar, "", $cidurl); @@ -1493,30 +1579,55 @@ function sq_cid2http($message, $id, $cidurl, $mailbox){ $cidurl = substr(trim($cidurl), 4); $linkurl = find_ent_id($cidurl, $message); /* in case of non-save cid links $httpurl should be replaced by a sort of - unsave link image */ + 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; + } 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 = $quotechar . SM_PATH . 'images/blank.png'; } + return $httpurl; } /** - * 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 - * @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
- */ +* 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 +* @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, $mailbox, $message, $id){ $me = 'sq_body2div'; $divattary = Array('class' => "'bodyclass'"); - $bgcolor = '#ffffff'; $text = '#000000'; $has_bgc_stl = $has_txt_stl = false; $styledef = ''; @@ -1526,7 +1637,7 @@ function sq_body2div($attary, $mailbox, $message, $id){ $attvalue = str_replace($quotchar, "", $attvalue); switch ($attname){ case 'background': - $attvalue = sq_cid2http($message, $id, + $attvalue = sq_cid2http($message, $id, $attvalue, $mailbox); $styledef .= "background-image: url('$attvalue'); "; break; @@ -1553,69 +1664,69 @@ function sq_body2div($attary, $mailbox, $message, $id){ } /** - * This is the main function and the one you should actually be calling. - * There are several variables you should be aware of an which need - * special description. - * - * Since the description is quite lengthy, see it here: - * http://www.mricon.com/html/phpfilter.html - * - * @param $body the string with HTML you wish to filter - * @param $tag_list see description above - * @param $rm_tags_with_content see description above - * @param $self_closing_tags see description above - * @param $force_tag_closing see description above - * @param $rm_attnames see description above - * @param $bad_attvals see description above - * @param $add_attr_to_tag see description above - * @param $message message object - * @param $id message id - * @return sanitized html safe to show on your pages. - */ -function sq_sanitize($body, - $tag_list, - $rm_tags_with_content, - $self_closing_tags, - $force_tag_closing, - $rm_attnames, - $bad_attvals, - $add_attr_to_tag, - $message, - $id, - $mailbox - ){ +* This is the main function and the one you should actually be calling. +* There are several variables you should be aware of an which need +* special description. +* +* Since the description is quite lengthy, see it here: +* http://linux.duke.edu/projects/mini/htmlfilter/ +* +* @param $body the string with HTML you wish to filter +* @param $tag_list see description above +* @param $rm_tags_with_content see description above +* @param $self_closing_tags see description above +* @param $force_tag_closing see description above +* @param $rm_attnames see description above +* @param $bad_attvals see description above +* @param $add_attr_to_tag see description above +* @param $message message object +* @param $id message id +* @return sanitized html safe to show on your pages. +*/ +function sq_sanitize($body, + $tag_list, + $rm_tags_with_content, + $self_closing_tags, + $force_tag_closing, + $rm_attnames, + $bad_attvals, + $add_attr_to_tag, + $message, + $id, + $mailbox + ){ $me = 'sq_sanitize'; $rm_tags = array_shift($tag_list); /** - * Normalize rm_tags and rm_tags_with_content. - */ + * Normalize rm_tags and rm_tags_with_content. + */ @array_walk($tag_list, 'sq_casenormalize'); @array_walk($rm_tags_with_content, 'sq_casenormalize'); @array_walk($self_closing_tags, 'sq_casenormalize'); /** - * See if tag_list is of tags to remove or tags to allow. - * false means remove these tags - * true means allow these tags - */ + * See if tag_list is of tags to remove or tags to allow. + * false means remove these tags + * true means allow these tags + */ $curpos = 0; $open_tags = Array(); $trusted = "\n\n"; $skip_content = false; /** - * Take care of netscape's stupid javascript entities like - * &{alert('boo')}; - */ + * Take care of netscape's stupid javascript entities like + * &{alert('boo')}; + */ $body = preg_replace("/&(\{.*?\};)/si", "&\\1", $body); while (($curtag = sq_getnxtag($body, $curpos)) != FALSE){ list($tagname, $attary, $tagtype, $lt, $gt) = $curtag; $free_content = substr($body, $curpos, $lt-$curpos); /** - * Take care of