/branches/GSoC-config/squirrelmail/functions/mime.php

Large files files are truncated, but you can click here to view the full file

<?php

/**
 * mime.php
 *
 * This contains the functions necessary to detect and decode MIME
 * messages.
 *
 * @copyright &copy; 1999-2007 The SquirrelMail Project Team
 * @license http://opensource.org/licenses/gpl-license.php GNU Public License
 * @version $Id: mime.php 12450 2007-06-08 20:14:37Z kink $
 * @package squirrelmail
 */

/**
 * 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                                                              */
/* -------------------------------------------------------------------------- */

/**
 * 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. */
    $read = trim(substr ($bodystructure, strpos(strtolower($bodystructure), 'bodystructure') + 13));
    $read = trim(substr ($read, 0, -1));
    $i = 0;
    $msg = Message::parseStructure($read,$i);

    if (!is_object($msg)) {
        global $color, $mailbox;
        displayPageHeader( $color, $mailbox );
        $errormessage  = _("SquirrelMail could not decode the bodystructure of the message");
        $errormessage .= '<br />'._("The bodystructure provided by your IMAP server:").'<br /><br />';
        $errormessage .= '<pre>' . htmlspecialchars($read) . '</pre>';
        plain_error_message( $errormessage );
        echo '</body></html>';
        exit;
    }
    if (count($flags)) {
        foreach ($flags as $flag) {
//FIXME: please document why it is we have to check the first char of the flag but we then go ahead and do a full string comparison anyway.  Is this a speed enhancement?  If not, let's keep it simple and just compare the full string and forget the switch block.
            $char = strtoupper($flag{1});
            switch ($char) {
                case 'S':
                    if (strtolower($flag) == '\\seen') {
                        $msg->is_seen = true;
                    }
                    break;
                case 'A':
                    if (strtolower($flag) == '\\answered') {
                        $msg->is_answered = true;
                    }
                    break;
                case 'D':
                    if (strtolower($flag) == '\\deleted') {
                        $msg->is_deleted = true;
                    }
                    break;
                case 'F':
                    if (strtolower($flag) == '\\flagged') {
                        $msg->is_flagged = true;
                    }
                    break;
                case 'M':
                    if (strtolower($flag) == '$mdnsent') {
                        $msg->is_mdnsent = true;
                    }
                    break;
                default:
                    break;
            }
        }
    }
    //    listEntities($msg);
    return $msg;
}



/* This starts the parsing of a particular structure.  It is called recursively,
 * so it can be passed different structures.  It returns an object of type
 * $message.
 * First, it checks to see if it is a multipart message.  If it is, then it
 * handles that as it sees is necessary.  If it is just a regular entity,
 * then it parses it and adds the necessary header information (by calling out
 * to mime_get_elements()
 */

function mime_fetch_body($imap_stream, $id, $ent_id=1, $fetch_size=0) {
    /* Do a bit of error correction.  If we couldn't find the entity id, just guess
     * that it is the first one.  That is usually the case anyway.
     */

    if (!$ent_id) {
        $cmd = "FETCH $id BODY[]";
    } else {
        $cmd = "FETCH $id BODY[$ent_id]";
    }

    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)) ;

    $wholemessage = implode('', $data);
    if (ereg('\\{([^\\}]*)\\}', $topline, $regs)) {
        $ret = substr($wholemessage, 0, $regs[1]);
        /* There is some information in the content info header that could be important
         * in order to parse html messages. Let's get them here.
         */
//        if ($ret{0} == '<') {
//            $data = sqimap_run_command ($imap_stream, "FETCH $id BODY[$ent_id.MIME]", true, $response, $message, TRUE);
//        }
    } else if (ereg('"([^"]*)"', $topline, $regs)) {
        $ret = $regs[1];
    } else {
        global $where, $what, $mailbox, $passed_id, $startMessage;
        $par = 'mailbox=' . urlencode($mailbox) . '&amp;passed_id=' . $passed_id;
        if (isset($where) && isset($what)) {
            $par .= '&amp;where=' . urlencode($where) . '&amp;what=' . urlencode($what);
        } else {
            $par .= '&amp;startMessage=' . $startMessage . '&amp;show_more=0';
        }
        $par .= '&amp;response=' . urlencode($response) .
            '&amp;message='  . urlencode($message)  .
            '&amp;topline='  . urlencode($topline);

        echo '<tt><br />' .
            '<table width="80%"><tr>' .
            '<tr><td colspan="2">' .
            _("Body retrieval error. The reason for this is most probably that the message is malformed.") .
            '</td></tr>' .
            '<tr><td><b>' . _("Command:") . "</td><td>$cmd</td></tr>" .
            '<tr><td><b>' . _("Response:") . "</td><td>$response</td></tr>" .
            '<tr><td><b>' . _("Message:") . "</td><td>$message</td></tr>" .
            '<tr><td><b>' . _("FETCH line:") . "</td><td>$topline</td></tr>" .
            "</table><br /></tt></font><hr />";

        $data = sqimap_run_command ($imap_stream, "FETCH $passed_id BODY[]", true, $response, $message, TRUE);
        array_shift($data);
        $wholemessage = implode('', $data);

        $ret = $wholemessage;
    }
    return $ret;
}

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.
     */

    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 */
    if (strtolower($encoding) == 'base64') {
        if (!$ent_id) {
            $query = "FETCH $id BODY[]";
        } else {
            $query = "FETCH $id BODY[$ent_id]";
        }
        sqimap_run_command($imap_stream,$query,true,$response,$message,TRUE,'sqimap_base64_decode',$rStream,true);
    } else {
        $body = mime_fetch_body ($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
       means we also should provide $results from sqimap_fread (by ref) to
       te function and set $no_return to false. The $filter function for
       quoted printable should handle unsetting of $results.
     */
    /*
       TODO 2: find out how we write to the output stream php://stdout. fwrite
       doesn't work because 'php://stdout isn't a stream.
     */

    return;
}

/* -[ END MIME DECODING ]----------------------------------------------------------- */

/* This is here for debugging purposes.  It will print out a list
 * of all the entity IDs that are in the $message object.
 */
function listEntities ($message) {
    if ($message) {
        echo "<tt>" . $message->entity_id . ' : ' . $message->type0 . '/' . $message->type1 . ' parent = '. $message->parent->entity_id. '<br />';
        for ($i = 0; isset($message->entities[$i]); $i++) {
            echo "$i : ";
            $msg = listEntities($message->entities[$i]);

            if ($msg) {
                echo "return: ";
                return $msg;
            }
        }
    }
}

function getPriorityStr($priority) {
    $priority_level = substr($priority,0,1);

    switch($priority_level) {
        /* Check for a higher then normal priority. */
        case '1':
        case '2':
            $priority_string = _("High");
            break;

        /* Check for a lower then normal priority. */
        case '4':
        case '5':
            $priority_string = _("Low");
            break;

        /* Check for a normal priority. */
        case '3':
        default:
            $priority_level = '3';
            $priority_string = _("Normal");
            break;

    }
    return $priority_string;
}

/* returns a $message object for a particular entity id */
function getEntity ($message, $ent_id) {
    return $message->getEntity($ent_id);
}

/* translateText
 * Extracted from strings.php 23/03/2002
 */

function translateText(&$body, $wrap_at, $charset) {
    global $where, $what;   /* from searching */
    global $color;          /* color theme */

    // require_once(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, $charset);
        }
        $line = charset_decode($charset, $line);
        $line = str_replace("\t", '        ', $line);

        parseUrl ($line);

        $quotes = 0;
        $pos = 0;
        $j = strlen($line);

        while ($pos < $j) {
            if ($line[$pos] == ' ') {
                $pos++;
            } else if (strpos($line, '&gt;', $pos) === $pos) {
                $pos += 4;
                $quotes++;
            } else {
                break;
            }
        }

        if ($quotes % 2) {
            $line = '<span class="quote1">' . $line . '</span>';
        } elseif ($quotes) {
            $line = '<span class="quote2">' . $line . '</span>';
        }

        $body_ary[$i] = $line;
    }
    $body = '<pre>' . implode("\n", $body_ary) . '</pre>';
}

/**
 * This returns a parsed string called $body. That string can then
 * be displayed as the actual message in the HTML. It contains
 * everything needed, including HTML Tags, Attachments at the
 * bottom, etc.
 *
 * 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', $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, $languages, $squirrelmail_language,
           $show_html_default, $sort, $has_unsafe_images, $passed_ent_id,
           $use_iframe, $iframe_height, $download_and_unsafe_link,
           $download_href, $unsafe_image_toggle_href, $unsafe_image_toggle_text,
           $oTemplate;

    $nbsp = $oTemplate->fetch('non_breaking_space.tpl');

    // 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;
    }

    $body = '';
    $urlmailbox = urlencode($mailbox);
    $body_message = getEntity($message, $ent_num);
    if (($body_message->header->type0 == 'text') ||
            ($body_message->header->type0 == 'rfc822')) {
        $body = mime_fetch_body ($imap_stream, $id, $ent_num);
        $body = decodeBody($body, $body_message->header->encoding);

        if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
                function_exists($languages[$squirrelmail_language]['XTRA_CODE'] . '_decode')) {
            if (mb_detect_encoding($body) != 'ASCII') {
                $body = call_user_func($languages[$squirrelmail_language]['XTRA_CODE'] . '_decode',$body);
            }
        }

        /* As of 1.5.2, $body is passed (and modified) by reference */
        do_hook('message_body', $body);

        /* If there are other types that shouldn't be formatted, add
         * them here.
         */

        if ($body_message->header->type1 == 'html') {
            if ($show_html_default <> 1) {
                $entity_conv = array('&nbsp;' => ' ',
                                     '<p>'    => "\n",
                                     '<P>'    => "\n",
                                     '<br>'   => "\n",
                                     '<BR>'   => "\n",
                                     '<br />' => "\n",
                                     '<BR />' => "\n",
                                     '&gt;'   => '>',
                                     '&lt;'   => '<');
                $body = strtr($body, $entity_conv);
                $body = strip_tags($body);
                $body = trim($body);
                translateText($body, $wrap_at,
                        $body_message->header->getParameter('charset'));
            } elseif ($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
                    . '&amp;passed_id=' . $id
                    . '&amp;ent_id=' . $ent_num
                    . '&amp;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
                /**
                 * convert character set. charset_decode does not remove html special chars
                 * applied by magicHTML functions and does not sanitize them second time if
                 * fourth argument is true.
                 */
                $charset = $body_message->header->getParameter('charset');
                if (!empty($charset)) {
                    $body = charset_decode($charset,$body,false,true);
                }
                $body = magicHTML($body, $id, $message, $mailbox);
            }
        } else {
            translateText($body, $wrap_at,
                    $body_message->header->getParameter('charset'));
        }

        // if this is the clean display (i.e. printer friendly), stop here.
        if ( $clean ) {
            return $body;
        }

        $download_and_unsafe_link = '';

        $link = 'passed_id=' . $id . '&amp;ent_id='.$ent_num.
            '&amp;mailbox=' . $urlmailbox .'&amp;sort=' . $sort .
            '&amp;startMessage=' . $startMessage . '&amp;show_more=0';
        if (isset($passed_ent_id)) {
            $link .= '&amp;passed_ent_id='.$passed_ent_id;
        }
        $download_href = SM_PATH . 'src/download.php?absolute_dl=true&amp;' . $link;
        $download_and_unsafe_link .= "$nbsp|$nbsp" 
            . create_hyperlink($download_href, _("Download this as a file"));
        if ($view_unsafe_images) {
            $text = _("Hide Unsafe Images");
        } else {
            if (isset($has_unsafe_images) && $has_unsafe_images) {
                $link .= '&amp;view_unsafe_images=1';
                $text = _("View Unsafe Images");
            } else {
                $text = '';
            }
        }
        if($text != '') {
            $unsafe_image_toggle_href = SM_PATH . 'src/read_body.php?'.$link;
            $unsafe_image_toggle_text = $text;
            $download_and_unsafe_link .= "$nbsp|$nbsp"
                . create_hyperlink($unsafe_image_toggle_href, $text);
        }
    }
    return $body;
}

/**
 * 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);
    $urlMailbox = urlencode($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 = array();
        $links['download link']['text'] = _("Download");
        $links['download link']['href'] = $base_uri .
            "src/download.php?absolute_dl=true&amp;passed_id=$id&amp;mailbox=$urlMailbox&amp;ent_id=$ent";

        if ($type0 =='message' && $type1 == 'rfc822') {
            $default_page = $base_uri  . 'src/read_body.php';
            $rfc822_header = $att->rfc822_header;
            $filename = $rfc822_header->subject;
            if (trim( $filename ) == '') {
                $filename = 'untitled-[' . $ent . ']' ;
            }
            $from_o = $rfc822_header->from;
            if (is_object($from_o)) {
                $from_name = decodeHeader($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");
            }
            $description = _("From").': '.$from_name;
        } else {
            $default_page = $base_uri  . 'src/download.php';
            $filename = $att->getFilename();
            if ($header->description) {
                $description = decodeHeader($header->description);
            } else {
                $description = '';
            }
        }

        $display_filename = $filename;
        if (isset($passed_ent_id)) {
            $passed_ent_id_link = '&amp;passed_ent_id='.$passed_ent_id;
        } else {
            $passed_ent_id_link = '';
        }
        $defaultlink = $default_page . "?startMessage=$startMessage"
            . "&amp;passed_id=$id&amp;mailbox=$urlMailbox"
            . '&amp;ent_id='.$ent.$passed_ent_id_link;
        if ($where && $what) {
            $defaultlink .= '&amp;where='. urlencode($where).'&amp;what='.urlencode($what);
        }
        // IE does make use of mime content sniffing. Forcing a download
        // prohibit execution of XSS inside an application/octet-stream attachment
        if ($type0 == 'application' && $type1 == 'octet-stream') {
            $defaultlink .= '&amp;absolute_dl=true';
        }

        /* This executes the attachment hook with a specific MIME-type.
         * If that doesn't have results, it tries if there's a rule
         * for a more generic type. Finally, a hook for ALL attachment
         * types is run as well.
         */
        /* The API for this hook has changed as of 1.5.2 so that all plugin
           arguments are passed in an array instead of each their own plugin
           argument, and arguments are passed by reference, so instead of
           returning any changes, changes should simply be made to the original
           arguments themselves. */
        do_hook("attachment $type0/$type1", $temp=array(&$links,
                &$startMessage, &$id, &$urlMailbox, &$ent, &$defaultlink,
                &$display_filename, &$where, &$what));
        if(count($links) <= 1) {
            /* The API for this hook has changed as of 1.5.2 so that all plugin
               arguments are passed in an array instead of each their own plugin
               argument, and arguments are passed by reference, so instead of
               returning any changes, changes should simply be made to the original
               arguments themselves. */
            do_hook("attachment $type0/*", $temp=array(&$links,
                    &$startMessage, &$id, &$urlMailbox, &$ent, &$defaultlink,
                    &$display_filename, &$where, &$what));
        }
        /* The API for this hook has changed as of 1.5.2 so that all plugin
           arguments are passed in an array instead of each their own plugin
           argument, and arguments are passed by reference, so instead of
           returning any changes, changes should simply be made to the original
           arguments themselves. */
        do_hook("attachment */*", $temp=array(&$links,
                &$startMessage, &$id, &$urlMailbox, &$ent, &$defaultlink, 
                &$display_filename, &$where, &$what));

        $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 $val) {
            if ($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);
    }

    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) {

    // 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;
}

/**
 * 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) {

    $body = str_replace("\r\n", "\n", $body);
    $encoding = strtolower($encoding);

    $encoding_handler = do_hook('decode_body', $encoding);


    // plugins get first shot at decoding the body
    //
    if (!empty($encoding_handler) && function_exists($encoding_handler)) {
        $body = $encoding_handler('decode', $body);

    } 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);
    } elseif ($encoding == 'base64') {
        $body = base64_decode($body);
    }

    // All other encodings are returned raw.
    return $body;
}

/**
 * Decodes headers
 *
 * This function decodes strings that are encoded according to
 * RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text).
 * Patched by Christian Schmidt <christian@ostenfeld.dk>  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'] . '_decodeheader')) {
        $string = call_user_func($languages[$squirrelmail_language]['XTRA_CODE'] . '_decodeheader', $string);
        // Do we need to return at this point?
        // return $string;
    }
    $i = 0;
    $iLastMatch = -2;
    $encoded = true;

    $aString = explode(' ',$string);
    $ret = '';
    foreach ($aString as $chunk) {
        if ($encoded && $chunk === '') {
            continue;
        } elseif ($chunk === '') {
            $ret .= ' ';
            continue;
        }
        $encoded = false;
        /* if encoded words are not separated by a linear-space-white we still catch them */
        $j = $i-1;

        while ($match = preg_match('/^(.*)=\?([^?]*)\?(Q|B)\?([^?]*)\?=(.*)$/Ui',$chunk,$res)) {
            /* if the last chunk isn't an encoded string then put back the space, otherwise don't */
            if ($iLastMatch !== $j) {
                if ($htmlsave) {
                    $ret .= '&#32;';
                } else {
                    $ret .= ' ';
                }
            }
            $iLastMatch = $i;
            $j = $i;
            if ($htmlsave) {
                $ret .= htmlspecialchars($res[1]);
            } else {
                $ret .= $res[1];
            }
            $encoding = ucfirst($res[3]);

            /* decide about valid decoding */
            if ($decide && is_conversion_safe($res[2])) {
                $utfencode=true;
                $can_be_encoded=true;
            } else {
                $can_be_encoded=false;
            }
            switch ($encoding)
            {
                case 'B':
                    $replace = base64_decode($res[4]);
                    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;
                    }
                    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 .= '&#32;';
            } else {
                $ret .= ' ';
            }
        }

        if (!$encoded && $htmlsave) {
            $ret .= htmlspecialchars($chunk);
        } else {
            $ret .= $chunk;
        }
        ++$i;
    }
    /* remove the first added space */
    if ($ret) {
        if ($htmlsave) {
            $ret = substr($ret,5);
        } else {
            $ret = substr($ret,1);
        }
    }

    return $ret;
}

/**
 * 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'] . '_encodeheader')) {
        return  call_user_func($languages[$squirrelmail_language]['XTRA_CODE'] . '_encodeheader', $string);
    }

    // Use B encoding for multibyte charsets
    $mb_charsets = array('utf-8','big5','gb2313','euc-kr');
    if (in_array($default_charset,$mb_charsets) &&
        in_array($default_charset,sq_mb_list_encodings()) &&
        sq_is8bit($string)) {
        return encodeHeaderBase64($string,$default_charset);
    } elseif (in_array($default_charset,$mb_charsets) &&
              sq_is8bit($string) &&
              ! in_array($default_charset,sq_mb_list_encodings())) {
        // Add E_USER_NOTICE error here (can cause 'Cannot add header information' warning in compose.php)
        // trigger_error('encodeHeader: Multibyte character set unsupported by mbstring extension.',E_USER_NOTICE);
    }

    // Encode only if the string contains 8-bit characters or =?
    $j = strlen($string);
    $max_l = 75 - strlen($default_charset) - 7;
    $aRet = array();
    $ret = '';
    $iEncStart = $enc_init = false;
    $cur_l = $iOffset = 0;
    for($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) {
                        $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset);
                        $aRet[] = "=?$default_charset?Q?$ret?=";
                        $iOffset = $i;
                        $cur_l = 0;
                        $ret = '';
                        $iEncStart = false;
                    } else {
                        $ret .= '_';
                    }
                }
                break;
            default:
                $k = ord($string{$i});
                if ($k > 126) {
                    if ($iEncStart === false) {
                        // 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;
        }
    }

    if ($enc_init) {
        if ($iEncStart !== false) {
            $aRet[] = substr($string,$iOffset,$iEncStart-$iOffset);
            $aRet[] = "=?$default_charset?Q?$ret?=";
        } else {
            $aRet[] = substr($string,$iOffset);
        }
        $string = implode('',$aRet);
    }
    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); $i++) {
        if ($message->entities[$i]->header->type0 == 'multipart')  {
            $ret = find_ent_id($id, $message->entities[$i]);
        } else {
            if (strcasecmp($message->entities[$i]->header->id, $id) == 0) {
//                if (sq_check_save_extension($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;
                }
            }
        }
    }
    return $ret;
}

function sq_check_save_extension($message) {
    $filename = $message->getFilename();
    $ext = substr($filename, strrpos($filename,'.')+1);
    $save_extensions = array('jpg','jpeg','gif','png','bmp');
    return in_array($ext, $save_extensions);
}


/**
 ** 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;
    // before deent, translate the dangerous unicode characters and ... to safe values
    // otherwise the regular expressions do not match.



    do {
        $m = false;
        $m = $m || sq_deent($attvalue, '/\&#0*(\d+);*/s');
        $m = $m || sq_deent($attvalue, '/\&#x0*((\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);
    }
}

/**
 * Translate all dangerous Unicode or Shift_JIS characters which are accepted by
 * IE as regular characters.
 *
 * @param  attvalue  The attribute value before dangerous characters are translated.
 * @return attvalue  Nothing, modifies a reference value.
 * @author Marc Groot Koerkamp.
 */
function sq_fixIE_idiocy(&$attvalue) {
    // remove NUL
    $attvalue = str_replace("\0", "", $attvalue);
    // remove comments
    $attvalue = preg_replace("/(\/\*.*?\*\/)/","",$attvalue);

    // IE has the evil habit of accepting every possible value for the attribute expression.
    // The table below contains characters which are parsed by IE if they are used in the "expression"
    // attribute value.
    $aDangerousCharsReplacementTable = array(
                        array('&#x029F;', '&#0671;' ,/* L UNICODE IPA Extension */
                              '&#x0280;', '&#0640;' ,/* R UNICODE IPA Extension */
                              '&#x0274;', '&#0628;' ,/* N UNICODE IPA Extension */
                              '&#xFF25;', '&#65317;' ,/* Unicode FULLWIDTH LATIN CAPITAL LETTER E */
                              '&#xFF45;', '&#65349;' ,/* Unicode FULLWIDTH LATIN SMALL LETTER E */
                              '&#xFF38;', '&#65336;',/* Unicode FULLWIDTH LATIN CAPITAL LETTER X */
                              '&#xFF58;', '&#65368;',/* Unicode FULLWIDTH LATIN SMALL LETTER X */
                              '&#xFF30;', '&#65328;',/* Unicode FULLWIDTH LATIN CAPITAL LETTER P */
                              '&#xFF50;', '&#65360;',/* Unicode FULLWIDTH LATIN SMALL LETTER P */
                              '&#xFF32;', '&#65330;',/* Unicode FULLWIDTH LATIN CAPITAL LETTER R */
                              '&#xFF52;', '&#65362;',/* Unicode FULLWIDTH LATIN SMALL LETTER R */
                              '&#xFF33;', '&#65331;',/* Unicode FULLWIDTH LATIN CAPITAL LETTER S */
                              '&#xFF53;', '&#65363;',/* Unicode FULLWIDTH LATIN SMALL LETTER S */
                              '&#xFF29;', '&#65321;',/* Unicode FULLWIDTH LATIN CAPITAL LETTER I */
                              '&#xFF49;', '&#65353;',/* Unicode FULLWIDTH LATIN SMALL LETTER I */
                              '&#xFF2F;', '&#65327;',/* Unicode FULLWIDTH LATIN CAPITAL LETTER O */
                              '&#xFF4F;', '&#65359;',/* Unicode FULLWIDTH LATIN SMALL LETTER O */
                              '&#xFF2E;', '&#65326;',/* Unicode FULLWIDTH LATIN CAPITAL LETTER N */
                              '&#xFF4E;', '&#65358;',/* Unicode FULLWIDTH LATIN SMALL LETTER N */
                              '&#xFF2C;', '&#65324;',/* Unicode FULLWIDTH LATIN CAPITAL LETTER L */
                              '&#xFF4C;', '&#65356;',/* Unicode FULLWIDTH LATIN SMALL LETTER L */
                              '&#xFF35;', '&#65333;',/* Unicode FULLWIDTH LATIN CAPITAL LETTER U */
                              '&#xFF55;', '&#65365;',/* Unicode FULLWIDTH LATIN SMALL LETTER U */
                              '&#x207F;', '&#8319;' ,/* Unicode SUPERSCRIPT LATIN SMALL LETTER N */
                              "\xEF\xBC\xA5", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER E */   // in unicode this is some Chinese char range
                              "\xEF\xBD\x85", /* Shift JIS FULLWIDTH LATIN SMALL LETTER E */
                              "\xEF\xBC\xB8", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER X */
                              "\xEF\xBD\x98", /* Shift JIS FULLWIDTH LATIN SMALL LETTER X */
                              "\xEF\xBC\xB0", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER P */
                              "\xEF\xBD\x90", /* Shift JIS FULLWIDTH LATIN SMALL LETTER P */
                              "\xEF\xBC\xB2", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER R */
                              "\xEF\xBD\x92", /* Shift JIS FULLWIDTH LATIN SMALL LETTER R */
                              "\xEF\xBC\xB3", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER S */
                              "\xEF\xBD\x93", /* Shift JIS FULLWIDTH LATIN SMALL LETTER S */
                              "\xEF\xBC\xA9", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER I */
                              "\xEF\xBD\x89", /* Shift JIS FULLWIDTH LATIN SMALL LETTER I */
                              "\xEF\xBC\xAF", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER O */
                              "\xEF\xBD\x8F", /* Shift JIS FULLWIDTH LATIN SMALL LETTER O */
                              "\xEF\xBC\xAE", /* Shift JIS FULLWIDTH LATIN CAPITAL LETTER N */
                              "\xEF\xBD\x8E", /* Shift JIS FULLWIDTH LATIN SMALL LETTER N */
                              "\xEF\xBC\xAC", /* Shift JIS FULLWIDTH L…

Large files files are truncated, but you can click here to view the full file