<?php
- /** mime.php
- **
- ** This contains the functions necessary to detect and decode MIME
- ** messages.
- **
- ** $Id$
- **/
-
- if (defined('mime_php'))
- return;
- define('mime_php', true);
-
- require_once('../functions/imap.php');
-
- /** Setting up the objects that have the structure for the message **/
-
- class msg_header {
- /** msg_header contains generic variables for values that **/
- /** could be in a header. **/
-
- var $type0 = '', $type1 = '', $boundary = '', $charset = '';
- var $encoding = '', $size = 0, $to = array(), $from = '', $date = '';
- var $cc = array(), $bcc = array(), $reply_to = '', $subject = '';
- var $id = 0, $mailbox = '', $description = '', $filename = '';
- var $entity_id = 0, $message_id = 0, $name = '';
- }
-
- class message {
- /** message is the object that contains messages. It is a recursive
- object in that through the $entities variable, it can contain
- more objects of type message. See documentation in mime.txt for
- a better description of how this works.
- **/
- var $header = '';
- var $entities = array();
-
- function addEntity ($msg) {
- $this->entities[] = $msg;
- }
- }
-
- /* --------------------------------------------------------------------------------- */
- /* MIME DECODING */
- /* --------------------------------------------------------------------------------- */
-
- // This function gets the structure of a message and stores it in the "message" class.
- // It will return this object for use with all relevant header information and
- // fully parsed into the standard "message" object format.
- function mime_structure ($imap_stream, $header) {
-
- sqimap_messages_flag ($imap_stream, $header->id, $header->id, 'Seen');
- $ssid = sqimap_session_id();
- $lsid = strlen( $ssid );
- $id = $header->id;
- fputs ($imap_stream, "$ssid FETCH $id BODYSTRUCTURE\r\n");
- //
- // This should use sqimap_read_data instead of reading it itself
- //
- $read = fgets ($imap_stream, 10000);
- $bodystructure = '';
- while( substr($read, 0, $lsid) <> $ssid &&
- !feof( $imap_stream ) ) {
- $bodystructure .= $read;
- $read = fgets ($imap_stream, 10000);
- }
- $read = $bodystructure;
-
- // isolate the body structure and remove beginning and end parenthesis
- $read = trim(substr ($read, strpos(strtolower($read), 'bodystructure') + 13));
- $read = trim(substr ($read, 0, -1));
- $end = mime_match_parenthesis(0, $read);
- while ($end == strlen($read)-1) {
- $read = trim(substr ($read, 0, -1));
- $read = trim(substr ($read, 1));
- $end = mime_match_parenthesis(0, $read);
- }
-
- $msg = mime_parse_structure ($read, 0);
- $msg->header = $header;
- 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
- // $message.
- // First, it checks to see if it is a multipart message. If it is, then it
- // handles that as it sees is necessary. If it is just a regular entity,
- // then it parses it and adds the necessary header information (by calling out
- // to mime_get_elements()
- function mime_parse_structure ($structure, $ent_id) {
-
- $msg = new message();
- if ($structure{0} == '(') {
- $ent_id = mime_new_element_level($ent_id);
- $start = $end = -1;
- do {
- $start = $end+1;
- $end = mime_match_parenthesis ($start, $structure);
-
- $element = substr($structure, $start+1, ($end - $start)-1);
- $ent_id = mime_increment_id ($ent_id);
- $newmsg = mime_parse_structure ($element, $ent_id);
- $msg->addEntity ($newmsg);
- } while ($structure{$end+1} == '(');
- } else {
- // parse the elements
- $msg = mime_get_element ($structure, $msg, $ent_id);
- }
- return $msg;
- }
-
- // Increments the element ID. An element id can look like any of
- // the following: 1, 1.2, 4.3.2.4.1, etc. This function increments
- // the last number of the element id, changing 1.2 to 1.3.
- function mime_increment_id ($id) {
-
- if (strpos($id, ".")) {
- $first = substr($id, 0, strrpos($id, "."));
- $last = substr($id, strrpos($id, ".")+1);
- $last++;
- $new = $first . "." .$last;
- } else {
- $new = $id + 1;
- }
-
- return $new;
- }
-
- // See comment for mime_increment_id().
- // This adds another level on to the entity_id changing 1.3 to 1.3.0
- // NOTE: 1.3.0 is not a valid element ID. It MUST be incremented
- // before it can be used. I left it this way so as not to have
- // to make a special case if it is the first entity_id. It
- // always increments it, and that works fine.
- function mime_new_element_level ($id) {
-
- if (!$id) {
- $id = 0;
- } else {
- $id = $id . '.0';
- }
-
- return( $id );
- }
- function mime_get_element (&$structure, $msg, $ent_id) {
-
- $elem_num = 1;
- $msg->header = new msg_header();
- $msg->header->entity_id = $ent_id;
- $properties = array();
-
- while (strlen($structure) > 0) {
- $structure = trim($structure);
- $char = $structure{0};
-
- if (strtolower(substr($structure, 0, 3)) == 'nil') {
- $text = '';
- $structure = substr($structure, 3);
- } else if ($char == '"') {
- // loop through until we find the matching quote, and return that as a string
- $pos = 1;
- $text = '';
- while ( ($char = $structure{$pos} ) <> '"' && $pos < strlen($structure)) {
- $text .= $char;
- $pos++;
- }
- $structure = substr($structure, strlen($text) + 2);
- } else if ($char == '(') {
- // comment me
- $end = mime_match_parenthesis (0, $structure);
- $sub = substr($structure, 1, $end-1);
- $properties = mime_get_props($properties, $sub);
- $structure = substr($structure, strlen($sub) + 2);
- } else {
- // loop through until we find a space or an end parenthesis
- $pos = 0;
- $char = $structure{$pos};
- $text = '';
- while ($char != ' ' && $char != ')' && $pos < strlen($structure)) {
- $text .= $char;
- $pos++;
- $char = $structure{$pos};
- }
- $structure = substr($structure, strlen($text));
- }
-
- // This is where all the text parts get put into the header
- switch ($elem_num) {
- case 1:
- $msg->header->type0 = strtolower($text);
- break;
- case 2:
- $msg->header->type1 = strtolower($text);
- break;
- case 4: // Id
- // Invisimail enclose images with <>
- $msg->header->id = str_replace( '<', '', str_replace( '>', '', $text ) );
- break;
- case 5:
- $msg->header->description = $text;
- break;
- case 6:
- $msg->header->encoding = strtolower($text);
- break;
- case 7:
- $msg->header->size = $text;
- break;
+/**
+ * mime.php
+ *
+ * Copyright (c) 1999-2002 The SquirrelMail Project Team
+ * Licensed under the GNU GPL. For full terms see the file COPYING.
+ *
+ * This contains the functions necessary to detect and decode MIME
+ * messages.
+ *
+ * $Id$
+ */
+
+require_once('../functions/imap.php');
+require_once('../functions/attachment_common.php');
+
+/* --------------------------------------------------------------------------------- */
+/* MIME DECODING */
+/* --------------------------------------------------------------------------------- */
+
+/* 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));
+ $msg = &new message();
+ $read = trim(substr ($read, 0, -1));
+ $res = $msg->parseStructure($read);
+ $msg = $res[0];
+ $msg->setEnt('0');
+ if (count($flags)) {
+ foreach ($flags as $flag) {
+ $char = strtoupper($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') {
+ $msg->is_mdnsent = true;
+ }
+ break;
default:
- if ($msg->header->type0 == 'text' && $elem_num == 8) {
- // This is a plain text message, so lets get the number of lines
- // that it contains.
- $msg->header->num_lines = $text;
-
- } else if ($msg->header->type0 == 'message' && $msg->header->type1 == 'rfc822' && $elem_num == 8) {
- // This is an encapsulated message, so lets start all over again and
- // parse this message adding it on to the existing one.
- $structure = trim($structure);
- if ( $structure{0} == '(' ) {
- $e = mime_match_parenthesis (0, $structure);
- $structure = substr($structure, 0, $e);
- $structure = substr($structure, 1);
- $m = mime_parse_structure($structure, $msg->header->entity_id);
-
- // the following conditional is there to correct a bug that wasn't
- // incrementing the entity IDs correctly because of the special case
- // that message/rfc822 is. This fixes it fine.
- if (substr($structure, 1, 1) != '(')
- $m->header->entity_id = mime_increment_id(mime_new_element_level($ent_id));
-
- // Now we'll go through and reformat the results.
- if ($m->entities) {
- for ($i=0; $i < count($m->entities); $i++) {
- $msg->addEntity($m->entities[$i]);
- }
- } else {
- $msg->addEntity($m);
- }
- $structure = "";
- }
- }
- break;
- }
- $elem_num++;
- $text = "";
- }
- // loop through the additional properties and put those in the various headers
- if ($msg->header->type0 != 'message') {
- for ($i=0; $i < count($properties); $i++) {
- $msg->header->{$properties[$i]['name']} = $properties[$i]['value'];
- }
- }
-
- return $msg;
- }
-
- // I did most of the MIME stuff yesterday (June 20, 2000), but I couldn't
- // figure out how to do this part, so I decided to go to bed. I woke up
- // in the morning and had a flash of insight. I went to the white-board
- // and scribbled it out, then spent a bit programming it, and this is the
- // result. Nothing complicated, but I think my brain was fried yesterday.
- // Funny how that happens some times.
- //
- // This gets properties in a nested parenthesisized list. For example,
- // this would get passed something like: ("attachment" ("filename" "luke.tar.gz"))
- // This returns an array called $props with all paired up properties.
- // It ignores the "attachment" for now, maybe that should change later
- // down the road. In this case, what is returned is:
- // $props[0]["name"] = "filename";
- // $props[0]["value"] = "luke.tar.gz";
- function mime_get_props ($props, $structure) {
-
- while (strlen($structure) > 0) {
- $structure = trim($structure);
- $char = $structure{0};
-
- if ($char == '"') {
- $pos = 1;
- $tmp = '';
- while ( ( $char = $structure{$pos} ) != '"' &&
- $pos < strlen($structure)) {
- $tmp .= $char;
- $pos++;
- }
- $structure = trim(substr($structure, strlen($tmp) + 2));
- $char = $structure{0};
-
- if ($char == '"') {
- $pos = 1;
- $value = '';
- while ( ( $char = $structure{$pos} ) != '"' &&
- $pos < strlen($structure) ) {
- $value .= $char;
- $pos++;
- }
- $structure = trim(substr($structure, strlen($tmp) + 2));
-
- $k = count($props);
- $props[$k]['name'] = strtolower($tmp);
- $props[$k]['value'] = $value;
- } else if ($char == '(') {
- $end = mime_match_parenthesis (0, $structure);
- $sub = substr($structure, 1, $end-1);
- if (! isset($props))
- $props = array();
- $props = mime_get_props($props, $sub);
- $structure = substr($structure, strlen($sub) + 2);
+ break;
}
- return $props;
- } else if ($char == '(') {
- $end = mime_match_parenthesis (0, $structure);
- $sub = substr($structure, 1, $end-1);
- $props = mime_get_props($props, $sub);
- $structure = substr($structure, strlen($sub) + 2);
- return $props;
- } else {
- return $props;
- }
- }
- }
+ }
+ }
+ // listEntities($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) {
+ global $uid_support;
+ /*
+ * do a bit of error correction. If we couldn't find the entity id, just guess
+ * that it is the first one. That is usually the case anyway.
+ */
+ if (!$ent_id) {
+ $ent_id = 1;
+ }
+ $cmd = "FETCH $id BODY[$ent_id]";
+
+ $data = sqimap_run_command ($imap_stream, $cmd, true, $response, $message, $uid_support);
+ 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, $uid_support);
+ }
+ } else if (ereg('"([^"]*)"', $topline, $regs)) {
+ $ret = $regs[1];
+ } else {
+ global $where, $what, $mailbox, $passed_id, $startMessage;
+ $par = 'mailbox=' . urlencode($mailbox) . "&passed_id=$passed_id";
+ if (isset($where) && isset($what)) {
+ $par .= '&where='. urlencode($where) . "&what=" . urlencode($what);
+ } else {
+ $par .= "&startMessage=$startMessage&show_more=0";
+ }
+ $par .= '&response=' . urlencode($response) .
+ '&message=' . urlencode($message).
+ '&topline=' . urlencode($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. Please help us making future versions better by submitting this message to the developers knowledgebase!") .
+ " <A HREF=\"../src/retrievalerror.php?$par\"><br>" .
+ _("Submit message") . '</A><BR> ' .
+ '</td></tr>' .
+ '<td><b>' . _("Command:") . "</td><td>$cmd</td></tr>" .
+ '<td><b>' . _("Response:") . "</td><td>$response</td></tr>" .
+ '<td><b>' . _("Message:") . "</td><td>$message</td></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, $uid_support);
+ array_shift($data);
+ $wholemessage = implode('', $data);
- // Matches parenthesis. It will return the position of the matching
- // parenthesis in $structure. For instance, if $structure was:
- // ("text" "plain" ("val1name", "1") nil ... )
- // x x
- // then this would return 42 to match up those two.
- function mime_match_parenthesis ($pos, $structure) {
-
- $j = strlen( $structure );
-
- // ignore all extra characters
- // If inside of a string, skip string -- Boundary IDs and other
- // things can have ) in them.
- if( $structure{$pos} != '(' )
- return( $j );
-
- while( $pos < $j ) {
- $pos++;
- if ($structure{$pos} == ')') {
- return $pos;
- } elseif ($structure{$pos} == '"') {
- $pos++;
- while( $structure{$pos} != '"' &&
- $pos < $j ) {
- if (substr($structure, $pos, 2) == '\\"')
- $pos++;
- elseif (substr($structure, $pos, 2) == '\\\\')
- $pos++;
- $pos++;
- }
- } elseif ( $structure{$pos} == '(' ) {
- $pos = mime_match_parenthesis ($pos, $structure);
- }
- }
- echo "Error decoding mime structure. Report this as a bug!<br>\n";
- return( $pos );
- }
+ $ret = $wholemessage;
+ }
+ return( $ret );
+}
+
+function mime_print_body_lines ($imap_stream, $id, $ent_id, $encoding) {
+ global $uid_support;
+ // do a bit of error correction. If we couldn't find the entity id, just guess
+ // that it is the first one. That is usually the case anyway.
+ if (!$ent_id) {
+ $ent_id = 1;
+ }
+ $sid = sqimap_session_id($uid_support);
+ // Don't kill the connection if the browser is over a dialup
+ // and it would take over 30 seconds to download it.
- function mime_fetch_body ($imap_stream, $id, $ent_id ) {
- // do a bit of error correction. If we couldn't find the entity id, just guess
- // that it is the first one. That is usually the case anyway.
- if (!$ent_id)
- $ent_id = 1;
- $sid = sqimap_session_id();
- fputs ($imap_stream, "$sid FETCH $id BODY[$ent_id]\r\n");
- $data = sqimap_read_data ($imap_stream, $sid, true, $response, $message);
- $topline = array_shift($data);
- while (! ereg('\\* [0-9]+ FETCH ', $topline) && $data)
- $topline = array_shift($data);
- $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( $ret{0} == '<' ) {
- fputs ($imap_stream, "$sid FETCH $id BODY[$ent_id.MIME]\r\n");
- $data = sqimap_read_data ($imap_stream, $sid, true, $response, $message);
- $base = '';
- $k = 10;
- foreach( $data as $d ) {
- if( substr( $d, 0, 13 ) == 'Content-Base:' ) {
- $j = strlen( $d );
- $i = 13;
- $base = '';
- while( $i < $j &&
- ( !isNoSep( $d{$i} ) || $d{$i} == '"' ) )
- $i++;
- while( $i < $j ) {
- if( isNoSep( $d{$i} ) )
- $base .= $d{$i};
- $i++;
- }
- $k = 0;
- } elseif( $k == 1 && !isnosep( $d{0} ) ) {
- $base .= substr( $d, 1 );
- }
- $k++;
- }
- if( $base <> '' )
- $ret = "<base href=\"$base\">" . $ret;
- }
- } else if (ereg('"([^"]*)"', $topline, $regs)) {
- $ret = $regs[1];
- } else {
- global $where, $what, $mailbox, $passed_id, $startMessage;
- $par = "mailbox=".urlencode($mailbox)."&passed_id=$passed_id";
- if (isset($where) && isset($what)) {
- $par .= "&where=".urlencode($where)."&what=".urlencode($what);
+ // don´t call set_time_limit in safe mode.
+ if (!ini_get("safe_mode")) {
+ set_time_limit(0);
+ }
+ if ($uid_support) {
+ $sid_s = substr($sid,0,strpos($sid, ' '));
+ } else {
+ $sid_s = $sid;
+ }
+
+ $body = mime_fetch_body ($imap_stream, $id, $ent_id);
+ echo decodeBody($body, $encoding);
+ return;
+/*
+ fputs ($imap_stream, "$sid FETCH $id BODY[$ent_id]\r\n");
+ $cnt = 0;
+ $continue = true;
+ $read = fgets ($imap_stream,8192);
+
+
+ // This could be bad -- if the section has sqimap_session_id() . ' OK'
+ // or similar, it will kill the download.
+ while (!ereg("^".$sid_s." (OK|BAD|NO)(.*)$", $read, $regs)) {
+ if (trim($read) == ')==') {
+ $read1 = $read;
+ $read = fgets ($imap_stream,4096);
+ if (ereg("^".$sid." (OK|BAD|NO)(.*)$", $read, $regs)) {
+ return;
} else {
- $par .= "&startMessage=$startMessage&show_more=0";
+ echo decodeBody($read1, $encoding) .
+ decodeBody($read, $encoding);
}
- $par .= '&response='.urlencode($response).'&message='.urlencode($message).
- '&topline='.urlencode($topline);
-
- echo '<b><font color=$color[2]>Body retrieval error. The reason for this is most probably that<BR> ' .
- 'the message is malformed. Please help us making future versions<BR> ' .
- "better by submitting this message to the developers knowledgebase!<BR>\n" .
- "<A HREF=\"../src/retrievalerror.php?$par\">Submit message</A><BR>" .
+ } else if ($cnt) {
+ echo decodeBody($read, $encoding);
+ }
+ $read = fgets ($imap_stream,4096);
+ $cnt++;
+// break;
+ }
+*/
+}
- "<tt>Response: $response<BR>" .
- "Message: $message<BR>" .
- "FETCH line: $topline<BR></tt></font></b>";
+/* -[ END MIME DECODING ]----------------------------------------------------------- */
- fputs ($imap_stream, "$sid FETCH $passed_id BODY[]\r\n");
- $data = sqimap_read_data ($imap_stream, $sid, true, $response, $message);
- array_shift($data);
- $wholemessage = implode('', $data);
+// This is here for debugging purposese. It will print out a list
+// of all the entity IDs that are in the $message object.
- $ret = "---------------\n$wholemessage";
+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]);
- }
- return( $ret );
+ if ($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';
+ $priority_string = _("Normal");
+ break;
- function mime_print_body_lines ($imap_stream, $id, $ent_id, $encoding) {
- // do a bit of error correction. If we couldn't find the entity id, just guess
- // that it is the first one. That is usually the case anyway.
- if (!$ent_id) $ent_id = 1;
- $sid = sqimap_session_id();
- // Don't kill the connection if the browser is over a dialup
- // and it would take over 30 seconds to download it.
- set_time_limit(0);
-
- fputs ($imap_stream, "$sid FETCH $id BODY[$ent_id]\r\n");
- $cnt = 0;
- $continue = true;
- $read = fgets ($imap_stream,4096);
- // This could be bad -- if the section has sqimap_session_id() . ' OK'
- // or similar, it will kill the download.
- while (!ereg("^".$sid." (OK|BAD|NO)(.*)$", $read, $regs)) {
- if (trim($read) == ')==') {
- $read1 = $read;
- $read = fgets ($imap_stream,4096);
- if (ereg("^".$sid." (OK|BAD|NO)(.*)$", $read, $regs)) {
- return;
- } else {
- echo decodeBody($read1, $encoding) .
- decodeBody($read, $encoding);
- }
- } else if ($cnt) {
- echo decodeBody($read, $encoding);
- }
- $read = fgets ($imap_stream,4096);
- $cnt++;
- }
}
+ 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('../functions/url_parser.php');
+
+ $body_ary = explode("\n", $body);
+ $PriorQuotes = 0;
+ for ($i=0; $i < count($body_ary); $i++) {
+ $line = $body_ary[$i];
+ if (strlen($line) - 2 >= $wrap_at) {
+ sqWordWrap($line, $wrap_at);
+ }
+ $line = charset_decode($charset, $line);
+ $line = str_replace("\t", ' ', $line);
- /* -[ END MIME DECODING ]----------------------------------------------------------- */
-
-
+ parseUrl ($line);
- /** This is the first function called. It decides if this is a multipart
- message or if it should be handled as a single entity
- **/
- function decodeMime ($imap_stream, &$header) {
- global $username, $key, $imapServerAddress, $imapPort;
- return mime_structure ($imap_stream, $header);
- }
+ $Quotes = 0;
+ $pos = 0;
+ $j = strlen( $line );
- // This is here for debugging purposese. It will print out a list
- // of all the entity IDs that are in the $message object.
- /*
- function listEntities ($message) {
- if ($message) {
- if ($message->header->entity_id)
- echo "<tt>" . $message->header->entity_id . ' : ' . $message->header->type0 . '/' . $message->header->type1 . '<br>';
- for ($i = 0; $message->entities[$i]; $i++) {
- $msg = listEntities($message->entities[$i], $ent_id);
- if ($msg)
- return $msg;
- }
- }
- }
- */
-
- // returns a $message object for a particular entity id
- function getEntity ($message, $ent_id) {
- if ($message) {
- if ($message->header->entity_id == $ent_id && strlen($ent_id) == strlen($message->header->entity_id)) {
- return $message;
- } else {
- for ($i = 0; isset($message->entities[$i]); $i++) {
- $msg = getEntity ($message->entities[$i], $ent_id);
- if ($msg)
- return $msg;
+ while ( $pos < $j ) {
+ if ($line[$pos] == ' ') {
+ $pos ++;
+ } else if (strpos($line, '>', $pos) === $pos) {
+ $pos += 4;
+ $Quotes ++;
+ } else {
+ break;
}
- }
- }
- }
-
- // figures out what entity to display and returns the $message object
- // for that entity.
- function findDisplayEntity ($message, $textOnly = 1) {
- global $show_html_default;
-
- $entity = 0;
+ }
- if ($message) {
- if ( $message->header->type0 == 'multipart' &&
- ( $message->header->type1 == 'alternative' ||
- $message->header->type1 == 'related' ) &&
- $show_html_default && ! $textOnly ) {
- $entity = findDisplayEntityHTML($message);
- }
-
- // Show text/plain or text/html -- the first one we find.
- if ( $entity == 0 &&
- $message->header->type0 == 'text' &&
- ( $message->header->type1 == 'plain' ||
- $message->header->type1 == 'html' ) &&
- isset($message->header->entity_id) ) {
- $entity = $message->header->entity_id;
+ if ($Quotes > 1) {
+ if (! isset($color[14])) {
+ $color[14] = '#FF0000';
}
-
- $i = 0;
- while ($entity == 0 && isset($message->entities[$i]) ) {
- $entity = findDisplayEntity($message->entities[$i], $textOnly);
- $i++;
+ $line = '<FONT COLOR="' . $color[14] . '">' . $line . '</FONT>';
+ } elseif ($Quotes) {
+ if (! isset($color[13])) {
+ $color[13] = '#800000';
}
+ $line = '<FONT COLOR="' . $color[13] . '">' . $line . '</FONT>';
}
-
- return( $entity );
+
+ $body_ary[$i] = $line;
}
-
- // Shows the HTML version
- function findDisplayEntityHTML ($message) {
- if ($message->header->type0 == 'text' &&
- $message->header->type1 == 'html' &&
- isset($message->header->entity_id))
- return $message->header->entity_id;
- for ($i = 0; isset($message->entities[$i]); $i ++) {
- $entity = findDisplayEntityHTML($message->entities[$i]);
- if ($entity != 0)
- return $entity;
- }
- return 0;
- }
-
- /** 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) {
- // 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;
-
- $id = $message->header->id;
- $urlmailbox = urlencode($message->header->mailbox);
-
- // Get the right entity and redefine message to be this entity
- // Pass the 0 to mean that we want the 'best' viewable one
- $ent_num = findDisplayEntity ($message, 0);
- $body_message = getEntity($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);
- $hookResults = do_hook("message_body", $body);
- $body = $hookResults[1];
-
- // If there are other types that shouldn't be formatted, add
- // them here
- if ($body_message->header->type1 == 'html') {
- if( $show_html_default <> 1 ) {
+ $body = '<pre>' . implode("\n", $body_ary) . '</pre>';
+}
+
+
+/* This returns a parsed string called $body. That string can then
+be displayed as the actual message in the HTML. It contains
+everything needed, including HTML Tags, Attachments at the
+bottom, etc.
+*/
+function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $mailbox='INBOX') {
+ // 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, $has_unsafe_images, $view_unsafe_images, $sort;
+
+ $has_unsafe_images= 0;
+ $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);
+ $hookResults = do_hook("message_body", $body);
+ $body = $hookResults[1];
+
+ // If there are other types that shouldn't be formatted, add
+ // them here
+
+ if ($body_message->header->type1 == 'html') {
+ if ( $show_html_default <> 1 ) {
+ $entity_conv = array(' ' => ' ',
+ '>' => '>',
+ '<' => '<');
$body = strip_tags( $body );
- translateText($body, $wrap_at, $body_message->header->charset);
+ $body = strtr($body, $entity_conv);
+ $body = trim($body);
+ translateText($body, $wrap_at,
+ $body_message->header->getParameter('charset'));
} else {
- $body = MagicHTML( $body, $id );
+ $body = magicHTML( $body, $id, $message, $mailbox );
}
- } else {
- translateText($body, $wrap_at, $body_message->header->charset);
- }
-
- $body .= "<SMALL><CENTER><A HREF=\"../src/download.php?absolute_dl=true&passed_id=$id&passed_ent_id=$ent_num&mailbox=$urlmailbox&showHeaders=1\">". _("Download this as a file") ."</A></CENTER><BR></SMALL>";
-
- /** Display the ATTACHMENTS: message if there's more than one part **/
- $body .= "</TD></TR></TABLE>";
- if (isset($message->entities[0])) {
- $body .= formatAttachments ($message, $ent_num, $message->header->mailbox, $id);
- }
- $body .= "</TD></TR></TABLE>";
- } else {
- $body = formatAttachments ($message, -1, $message->header->mailbox, $id);
- }
- return( $body );
- }
+ } else {
+ translateText($body, $wrap_at,
+ $body_message->header->getParameter('charset'));
+ }
- // A recursive function that returns a list of attachments with links
- // to where to download these attachments
- function formatAttachments ($message, $ent_id, $mailbox, $id) {
- global $where, $what;
- global $startMessage, $color;
- static $ShownHTML = 0;
-
- $body = "";
- if ($ShownHTML == 0) {
- $ShownHTML = 1;
-
- $body .= "<TABLE WIDTH=100% CELLSPACING=0 CELLPADDING=2 BORDER=0 BGCOLOR=\"$color[0]\"><TR>\n" .
- "<TH ALIGN=\"left\" BGCOLOR=\"$color[9]\"><B>\n" .
- _("Attachments") . ':' .
- "</B></TH></TR><TR><TD>\n" .
- "<TABLE CELLSPACING=0 CELLPADDING=1 BORDER=0>\n" .
- formatAttachments ($message, $ent_id, $mailbox, $id) .
- "</TABLE></TD></TR></TABLE>";
-
- return( $body );
- }
-
- if ($message) {
- if (!$message->entities) {
- $type0 = strtolower($message->header->type0);
- $type1 = strtolower($message->header->type1);
- $name = decodeHeader($message->header->name);
-
- if ($message->header->entity_id != $ent_id) {
- $filename = decodeHeader($message->header->filename);
+ if ($has_unsafe_images) {
+ if ($view_unsafe_images) {
+ $body .= "<CENTER><SMALL><A HREF=\"read_body.php?passed_id=$id&passed_ent_id=".$message->entity_id."&mailbox=$urlmailbox&sort=$sort&startMessage=$startMessage&show_more=0\">". _("Hide Unsafe Images") ."</A></SMALL></CENTER><BR>\n";
+ } else {
+ $body .= "<CENTER><SMALL><A HREF=\"read_body.php?passed_id=$id&passed_ent_id=".$message->entity_id."&mailbox=$urlmailbox&sort=$sort&startMessage=$startMessage&show_more=0&view_unsafe_images=1\">". _("View Unsafe Images") ."</A></SMALL></CENTER><BR>\n";
+ }
+ }
+ }
+ return ($body);
+}
+
+
+function formatAttachments($message, $exclude_id, $mailbox, $id) {
+ global $where, $what, $startMessage, $color;
+ static $ShownHTML = 0;
+
+ $att_ar = $message->getAttachments($exclude_id);
+
+ if (!count($att_ar)) return '';
+
+ $attachments = '';
+
+ $urlMailbox = urlencode($mailbox);
+
+ foreach ($att_ar as $att) {
+ $ent = urldecode($att->entity_id);
+ $header = $att->header;
+ $type0 = strtolower($header->type0);
+ $type1 = strtolower($header->type1);
+ $name = '';
+ $Links['download link']['text'] = _("download");
+ $Links['download link']['href'] =
+ "../src/download.php?absolute_dl=true&passed_id=$id&mailbox=$urlMailbox&ent_id=$ent";
+ $ImageURL = '';
+ if ($type0 =='message' && $type1 == 'rfc822') {
+ $default_page = '../src/read_body.php';
+ $rfc822_header = $att->rfc822_header;
+ $filename = decodeHeader($rfc822_header->subject);
+
+ $from_o = $rfc822_header->from;
+ if (is_object($from_o)) {
+ $from_name = $from_o->getAddress(false);
+ } else {
+ $from_name = _("Unknown sender");
+ }
+ $from_name = decodeHeader(htmlspecialchars($from_name));
+ $description = $from_name;
+ } else {
+ $default_page = '../src/download.php';
+ if (is_object($header->disposition)) {
+ $filename = decodeHeader($header->disposition->getProperty('filename'));
if (trim($filename) == '') {
+ $name = decodeHeader($header->disposition->getProperty('name'));
if (trim($name) == '') {
- if( trim( $message->header->id ) == '' )
- $display_filename = 'untitled-[' . $message->header->entity_id . ']' ;
+ if ( trim( $header->id ) == '' )
+ $filename = 'untitled-[' . $ent . ']' ;
else
- $display_filename = 'cid: ' . $message->header->id;
- // $display_filename = 'untitled-[' . $message->header->entity_id . ']' ;
+ $filename = 'cid: ' . $header->id;
} else {
- $display_filename = $name;
$filename = $name;
}
- } else {
- $display_filename = $filename;
}
+ } else {
+ if ( trim( $header->id ) == '' )
+ $filename = 'untitled-[' . $ent . ']' ;
+ else
+ $filename = 'cid: ' . $header->id;
+ }
+
+ if ($header->description) {
+ $description = htmlspecialchars($header->description);
+ } else {
+ $description = '';
+ }
+ }
- $urlMailbox = urlencode($mailbox);
- $ent = urlencode($message->header->entity_id);
-
- $DefaultLink =
- "../src/download.php?startMessage=$startMessage&passed_id=$id&mailbox=$urlMailbox&passed_ent_id=$ent";
- if ($where && $what)
- $DefaultLink .= '&where=' . urlencode($where) . '&what=' . urlencode($what);
- $Links['download link']['text'] = _("download");
- $Links['download link']['href'] =
- "../src/download.php?absolute_dl=true&passed_id=$id&mailbox=$urlMailbox&passed_ent_id=$ent";
- $ImageURL = '';
-
- $HookResults = do_hook("attachment $type0/$type1", $Links,
- $startMessage, $id, $urlMailbox, $ent, $DefaultLink,
- $display_filename, $where, $what);
+ $display_filename = $filename;
+ if (isset($passed_ent_id)) {
+ $passed_ent_id_link = '&passed_ent_id='.$passed_ent_id;
+ } else {
+ $passed_ent_id_link = '';
+ }
+ $DefaultLink = $default_page . "?startMessage=$startMessage"
+ . "&passed_id=$id&mailbox=$urlMailbox"
+ . '&ent_id='.$ent.$passed_ent_id_link;
+ if ($where && $what) {
+ $DefaultLink = '&where='. urlencode($where).'&what='.urlencode($what);
+ }
+ /* this executes the attachment hook with a specific MIME-type.
+ * if that doens'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, $what);
+ if(count($HookResults[1]) <= 1) {
+ $HookResults = do_hook("attachment $type0/*", $Links,
+ $startMessage, $id, $urlMailbox, $ent, $DefaultLink,
+ $display_filename, $where, $what);
+ }
- $Links = $HookResults[1];
- $DefaultLink = $HookResults[6];
+ $Links = $HookResults[1];
+ $DefaultLink = $HookResults[6];
- $body .= '<TR><TD> </TD><TD>' .
+ $attachments .= '<TR><TD>' .
"<A HREF=\"$DefaultLink\">$display_filename</A> </TD>" .
- '<TD><SMALL><b>' . show_readable_size($message->header->size) .
+ '<TD><SMALL><b>' . show_readable_size($header->size) .
'</b> </small></TD>' .
"<TD><SMALL>[ $type0/$type1 ] </SMALL></TD>" .
'<TD><SMALL>';
- if ($message->header->description)
- $body .= '<b>' . htmlspecialchars($message->header->description) . '</b>';
- $body .= '</SMALL></TD><TD><SMALL> ';
-
-
- $SkipSpaces = 1;
- foreach ($Links as $Val) {
- if ($SkipSpaces) {
- $SkipSpaces = 0;
- } else {
- $body .= ' | ';
- }
- $body .= '<a href="' . $Val['href'] . '">' . $Val['text'] . '</a>';
- }
+ $attachments .= '<b>' . $description . '</b>';
+ $attachments .= '</SMALL></TD><TD><SMALL> ';
- unset($Links);
-
- $body .= "</SMALL></TD></TR>\n";
- }
- } else {
- for ($i = 0; $i < count($message->entities); $i++) {
- $body .= formatAttachments ($message->entities[$i], $ent_id, $mailbox, $id);
+ $SkipSpaces = 1;
+ foreach ($Links as $Val) {
+ if ($SkipSpaces) {
+ $SkipSpaces = 0;
+ } else {
+ $attachments .= ' | ';
}
- }
- return( $body );
- }
- }
-
-
- /** this function decodes the body depending on the encoding type. **/
- function decodeBody($body, $encoding) {
- $body = str_replace("\r\n", "\n", $body);
- $encoding = strtolower($encoding);
-
- global $show_html_default;
-
- if ($encoding == 'quoted-printable') {
- $body = quoted_printable_decode($body);
-
-
- /*
- Following code has been comented as I see no reason for it.
- If there is any please tell me a mingo@rotedic.com
-
- while (ereg("=\n", $body))
- $body = ereg_replace ("=\n", "", $body);
- */
- } else if ($encoding == 'base64') {
- $body = base64_decode($body);
- }
-
- // All other encodings are returned raw.
- return $body;
- }
+ $attachments .= '<a href="' . $Val['href'] . '">' . $Val['text'] . '</a>';
+ }
+ unset($Links);
+ $attachments .= "</TD></TR>\n";
+ }
+ return $attachments;
+}
+/** this function decodes the body depending on the encoding type. **/
+function decodeBody($body, $encoding) {
+ global $languages, $squirrelmail_language;
- // This functions decode strings that is encoded according to
- // RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text).
- function decodeHeader ($string) {
- if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=',
- $string, $res)) {
- if (ucfirst($res[2]) == "B") {
- $replace = base64_decode($res[3]);
- } else {
- $replace = ereg_replace("_", " ", $res[3]);
- // Convert lowercase Quoted Printable to uppercase for
- // quoted_printable_decode to understand it.
- while (ereg("(=(([0-9][abcdef])|([abcdef][0-9])|([abcdef][abcdef])))", $replace, $res)) {
- $replace = str_replace($res[1], strtoupper($res[1]), $replace);
+ $body = str_replace("\r\n", "\n", $body);
+ $encoding = strtolower($encoding);
+
+ global $show_html_default;
+
+ if ($encoding == 'quoted-printable' ||
+ $encoding == 'quoted_printable') {
+ $body = quoted_printable_decode($body);
+
+ while (ereg("=\n", $body)) {
+ $body = ereg_replace ("=\n", '', $body);
}
- $replace = quoted_printable_decode($replace);
- }
+
+ } else if ($encoding == 'base64') {
+ $body = base64_decode($body);
+ }
+
+ if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
+ function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) {
+ $body = $languages[$squirrelmail_language]['XTRA_CODE']('decode', $body);
+ }
+
+ // All other encodings are returned raw.
+ return( $body );
+}
+
+/*
+ * This functions decode strings that is encoded according to
+ * RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text).
+ * Patched by Christian Schmidt <christian@ostenfeld.dk> 23/03/2002
+ */
+function decodeHeader ($string, $utfencode=true) {
+ global $languages, $squirrelmail_language;
+ if (is_array($string)) {
+ $string = implode("\n", $string);
+ }
- $replace = charset_decode ($res[1], $replace);
+ if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
+ function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) {
+ $string = $languages[$squirrelmail_language]['XTRA_CODE']('decodeheader', $string);
+ }
- // Remove the name of the character set.
- $string = eregi_replace ('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=',
- $replace, $string);
+ $i = 0;
+ while (preg_match('/^(.{' . $i . '})(.*)=\?([^?]*)\?(Q|B)\?([^?]*)\?=/Ui',
+ $string, $res)) {
+ $prefix = $res[1];
+ // Ignore white-space between consecutive encoded-words
+ if (strspn($res[2], " \t") != strlen($res[2])) {
+ $prefix .= $res[2];
+ }
- // In case there should be more encoding in the string: recurse
- return (decodeHeader($string));
- } else
- return ($string);
- }
+ if (ucfirst($res[4]) == 'B') {
+ $replace = base64_decode($res[5]);
+ } else {
+ $replace = str_replace('_', ' ', $res[5]);
+ $replace = preg_replace('/=([0-9a-f]{2})/ie', 'chr(hexdec("\1"))',
+ $replace);
+ /* Only encode into entities by default. Some places
+ don't need the encoding, like the compose form. */
+ if ($utfencode) {
+ $replace = charset_decode($res[3], $replace);
+ }
+ }
+ $string = $prefix . $replace . substr($string, strlen($res[0]));
+ $i = strlen($prefix) + strlen($replace);
+ }
+ return( $string );
+}
+
+/*
+ * Encode a string according to RFC 1522 for use in headers if it
+ * contains 8-bit characters or anything that looks like it should
+ * be encoded.
+ */
+function encodeHeader ($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', $string);
+ }
- // Encode a string according to RFC 1522 for use in headers if it
- // contains 8-bit characters or anything that looks like it should
- // be encoded.
- function encodeHeader ($string) {
- global $default_charset;
-
- // Encode only if the string contains 8-bit characters or =?
- $j = strlen( $string );
- $l = FALSE; // Must be encoded ?
- $ret = '';
- for( $i=0; $i < $j; ++$i) {
+ // Encode only if the string contains 8-bit characters or =?
+ $j = strlen( $string );
+ $l = strstr($string, '=?'); // Must be encoded ?
+ $ret = '';
+ for( $i=0; $i < $j; ++$i) {
switch( $string{$i} ) {
case '=':
$ret .= '=3D';
break;
- case '?':
- $l = TRUE;
+ case '?':
$ret .= '=3F';
break;
- case '_':
+ case '_':
$ret .= '=5F';
break;
- case ' ':
+ case ' ':
$ret .= '_';
break;
- default:
+ default:
$k = ord( $string{$i} );
- if( $k > 126 ) {
+ if ( $k > 126 ) {
$ret .= sprintf("=%02X", $k);
$l = TRUE;
} else
$ret .= $string{$i};
}
- }
+ }
- if( $l )
+ if ( $l ) {
$string = "=?$default_charset?Q?$ret?=";
+ }
- return( $string );
- }
-
- /*
- Strips dangerous tags from html messages.
- */
-
- function MagicHTML( $body, $id ) {
-
- global $message, $PHP_SELF, $HTTP_SERVER_VARS;
-
- $j = strlen( $body ); // Legnth of the HTML
- $ret = ''; // Returned string
- $bgcolor = '#ffffff'; // Background style color (defaults to white)
- $leftmargin = ''; // Left margin style
- $title = ''; // HTML title if any
-
- $i = 0;
- while( $i < $j ) {
- if( $body{$i} == '<' ) {
- $tag = $body{$i+1}.$body{$i+2}.$body{$i+3}.$body{$i+4};
- switch( strtoupper( $tag ) ) {
- // Strips the entire tag and contents
- case 'APPL':
- case 'EMBB':
- case 'FRAM':
- case 'SCRI':
- case 'OBJE':
- $etg = '/' . $tag;
- while( $body{$i+1}.$body{$i+2}.$body{$i+3}.$body{$i+4}.$body{$i+5} <> $etg &&
- $i < $j ) $i++;
- while( $i < $j && $body{++$i} <> '>' );
- // $ret .= "<!-- $tag removed -->";
- break;
- // Substitute Title
- case 'TITL':
- $i += 5;
- while( $body{$i} <> '>' && // </title>
- $i < $j )
- $i++;
- $i++;
- $title = '';
- while( $body{$i} <> '<' && // </title>
- $i < $j ) {
- $title .= $body{$i};
- $i++;
- }
- $i += 7;
- break;
- // Destroy these tags
- case 'HTML':
- case 'HEAD':
- case '/HTM':
- case '/HEA':
- case '!DOC':
- case 'META':
- case 'DIV ':
- case '/DIV':
- case '!-- ':
- $i += 4;
- while( $body{$i} <> '>' &&
- $i < $j )
- $i++;
- // $i++;
- break;
- case 'STYL':
- $i += 5;
- while( $body{$i} <> '>' && // </title>
- $i < $j )
- $i++;
- $i++;
- // We parse the style to look for interesting stuff
- $styleblk = '';
- while( $body{$i} <> '>' &&
- $i < $j ) {
- // First we get the name of the style
- $style = '';
- while( $body{$i} <> '>' &&
- $body{$i} <> '<' &&
- $body{$i} <> '{' &&
- $i < $j ) {
- if( isnoSep( $body{$i} ) )
- $style .= $body{$i};
- $i++;
- }
- stripComments( $i, $j, $body );
- $style = strtoupper( trim( $style ) );
- if( $style == 'BODY' ) {
- // Next we look into the definitions of the body style
- while( $body{$i} <> '>' &&
- $body{$i} <> '}' &&
- $i < $j ) {
- // We look for the background color if any.
- if( substr( $body, $i, 17 ) == 'BACKGROUND-COLOR:' ) {
- $i += 17;
- $bgcolor = getStyleData( $i, $j, $body );
- } elseif ( substr( $body, $i, 12 ) == 'MARGIN-LEFT:' ) {
- $i += 12;
- $leftmargin = getStyleData( $i, $j, $body );
- }
- $i++;
- }
- } else {
- // Other style are mantained
- $styleblk .= "$style ";
- while( $body{$i} <> '>' &&
- $body{$i} <> '<' &&
- $body{$i} <> '}' &&
- $i < $j ) {
- $styleblk .= $body{$i};
- $i++;
- }
- $styleblk .= $body{$i};
- }
- stripComments( $i, $j, $body );
- if( $body{$i} <> '>' )
- $i++;
- }
- if( $styleblk <> '' )
- $ret .= "<style>$styleblk";
- break;
- case 'BODY':
- if( $title <> '' )
- $ret .= '<b>' . _("Title:") . " </b>$title<br>\n";
- $ret .= "<TABLE";
- $i += 5;
- if (! isset($base))
- $base = '';
- $ret .= stripEvent( $i, $j, $body, $id, $base );
- //if( $bgcolor <> '' )
- $ret .= " bgcolor=$bgcolor";
- $ret .= ' width=100%><tr>';
- if( $leftmargin <> '' )
- $ret .= "<td width=$leftmargin> </td>";
- $ret .= '<td>';
- break;
- case 'BASE':
- $i += 5;
- $base = '';
- while( !isNoSep( $body{$i} ) &&
- $i < $j )
- $i++;
- if( strcasecmp( substr( $base, 0, 4 ), 'href' ) ) {
- $i += 5;
- while( !isNoSep( $body{$i} ) &&
- $i < $j )
- $i++;
- while( $body{$i} <> '>' &&
- $i < $j ) {
- if( $body{$i} <> '"' )
- $base .= $body{$i};
- $i++;
- }
- // Debuging $ret .= "<!-- base == $base -->";
- if( strcasecmp( substr( $base, 0, 4 ), 'file' ) <> 0 )
- $ret .= "\n<BASE HREF=\"$base\">\n";
- }
- break;
- case '/BOD':
- $ret .= '</td></tr></TABLE>';
- $i += 6;
- break;
- default:
- // Following tags can contain some event handler, lets search it
- stripComments( $i, $j, $body );
- if (! isset($base))
- $base = '';
- $ret .= stripEvent( $i, $j, $body, $id, $base ) . '>';
- // $ret .= "<!-- $tag detected -->";
- }
- } else {
- $ret .= $body{$i};
+ return( $string );
+}
+
+/* This function trys to locate the entity_id of a specific mime element */
+
+function find_ent_id( $id, $message ) {
+ $ret = '';
+ for ($i=0; $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 )
+ $ret = $message->entities[$i]->entity_id;
+ }
+ }
+ return( $ret );
+}
+
+/**
+ ** HTMLFILTER ROUTINES
+ */
+
+/**
+ * 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){
+
+ $me = 'sq_tagprint';
+
+ if ($tagtype == 2){
+ $fulltag = '</' . $tagname . '>';
+ } else {
+ $fulltag = '<' . $tagname;
+ if (is_array($attary) && sizeof($attary)){
+ $atts = Array();
+ while (list($attname, $attvalue) = each($attary)){
+ array_push($atts, "$attname=$attvalue");
}
- $i++;
+ $fulltag .= ' ' . join(" ", $atts);
+ }
+ if ($tagtype == 3){
+ $fulltag .= ' /';
+ }
+ $fulltag .= '>';
+ }
+ return $fulltag;
+}
+
+/**
+ * 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 $body where the next
+ * non-whitespace char is located.
+ */
+function sq_skipspace($body, $offset){
+ $me = 'sq_skipspace';
+ preg_match("/^(\s*)/s", substr($body, $offset), $matches);
+ if (sizeof($matches{1})){
+ $count = strlen($matches{1});
+ $offset += $count;
+ }
+ return $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.
+ */
+function sq_findnxstr($body, $offset, $needle){
+ $me = 'sq_findnxstr';
+ $pos = strpos($body, $needle, $offset);
+ if ($pos === FALSE){
+ $pos = strlen($body);
+ }
+ return $pos;
+}
+
+/**
+ * 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();
+ $retarr = Array();
+ preg_match("%^(.*?)($reg)%s", substr($body, $offset), $matches);
+ if (!$matches{0}){
+ $retarr = false;
+ } else {
+ $retarr{0} = $offset + strlen($matches{1});
+ $retarr{1} = $matches{1};
+ $retarr{2} = $matches{2};
+ }
+ return $retarr;
+}
+
+/**
+ * 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)){
+ return false;
+ }
+ $lt = sq_findnxstr($body, $offset, "<");
+ if ($lt == strlen($body)){
+ return false;
+ }
+ /**
+ * We are here:
+ * blah blah <tag attribute="value">
+ * \---------^
+ */
+ $pos = sq_skipspace($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.:
+ * <a href="blah">
+ * 2. Closing tag, e.g.:
+ * </a>
+ * 3. XHTML-style content-less tag, e.g.:
+ * <img src="blah"/>
+ */
+ $tagtype = false;
+ switch (substr($body, $pos, 1)){
+ case '/':
+ $tagtype = 2;
+ $pos++;
+ break;
+ case '!':
+ /**
+ * A comment or an SGML declaration.
+ */
+ if (substr($body, $pos+1, 2) == "--"){
+ $gt = strpos($body, "-->", $pos);
+ if ($gt === false){
+ $gt = strlen($body);
+ } else {
+ $gt += 2;
+ }
+ return Array(false, false, false, $lt, $gt);
+ } else {
+ $gt = sq_findnxstr($body, $pos, ">");
+ return Array(false, false, false, $lt, $gt);
}
+ break;
+ default:
+ /**
+ * Assume tagtype 1 for now. If it's type 3, we'll switch values
+ * later.
+ */
+ $tagtype = 1;
+ break;
+ }
- return( "\n\n<!-- HTML Output ahead -->\n" .
- $ret .
- "\n<!-- END of HTML Output --><base href=\"".
- $HTTP_SERVER_VARS["SERVER_NAME"] . substr( $PHP_SELF, 0, strlen( $PHP_SELF ) - 13 ) .
- "\">\n\n" );
- }
+ $tag_start = $pos;
+ $tagname = '';
+ /**
+ * 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));
+ }
+ list($pos, $tagname, $match) = $regary;
+ $tagname = strtolower($tagname);
+
+ /**
+ * $match can be either of these:
+ * '>' indicating the end of the tag entirely.
+ * '\s' indicating the end of the tag name.
+ * '/' indicating that this is type-3 xhtml tag.
+ *
+ * Whatever else we find there indicates an invalid tag.
+ */
+ switch ($match){
+ case '/':
+ /**
+ * This is an xhtml-style tag with a closing / at the
+ * end, like so: <img src="blah"/>. Check if it's followed
+ * by the closing bracket. If not, then this tag is invalid
+ */
+ if (substr($body, $pos, 2) == "/>"){
+ $pos++;
+ $tagtype = 3;
+ } else {
+ $gt = sq_findnxstr($body, $pos, ">");
+ $retary = Array(false, false, false, $lt, $gt);
+ return $retary;
+ }
+ case '>':
+ return Array($tagname, false, $tagtype, $lt, $pos);
+ break;
+ default:
+ /**
+ * Check if it's whitespace
+ */
+ if (preg_match("/\s/", $match)){
+ } else {
+ /**
+ * This is an invalid tag! Look for the next closing ">".
+ */
+ $gt = sq_findnxstr($body, $offset, ">");
+ return Array(false, false, false, $lt, $gt);
+ }
+ }
+
+ /**
+ * At this point we're here:
+ * <tagname attribute='blah'>
+ * \-------^
+ *
+ * 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.
+ */
+ return Array(false, false, false, $lt, $pos);
+ }
+ /**
+ * 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.
+ */
+ $pos += strlen($matches{1});
+ if ($matches{2} == "/>"){
+ $tagtype = 3;
+ $pos++;
+ }
+ return Array($tagname, $attary, $tagtype, $lt, $pos);
+ }
- function isNoSep( $char ) {
+ /**
+ * 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.
+ */
+ 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.
+ */
+ switch($match){
+ case '/':
+ /**
+ * This is an xhtml-style tag with a closing / at the
+ * end, like so: <img src="blah"/>. Check if it's followed
+ * by the closing bracket. If not, then this tag is invalid
+ */
+ if (substr($body, $pos, 2) == "/>"){
+ $pos++;
+ $tagtype = 3;
+ } else {
+ $gt = sq_findnxstr($body, $pos, ">");
+ $retary = Array(false, false, false, $lt, $gt);
+ return $retary;
+ }
+ case '>':
+ $attary{$attname} = '"yes"';
+ return Array($tagname, $attary, $tagtype, $lt, $pos);
+ break;
+ default:
+ /**
+ * Skip whitespace and see what we arrive at.
+ */
+ $pos = sq_skipspace($body, $pos);
+ $char = substr($body, $pos, 1);
+ /**
+ * Two things are valid here:
+ * '=' means this is attribute type 1 2 or 3.
+ * \w means this was attribute type 4.
+ * anything else we ignore and re-loop. End of tag and
+ * invalid stuff will be caught by our checks at the beginning
+ * of the loop.
+ */
+ if ($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
+ */
+ $quot = substr($body, $pos, 1);
+ if ($quot == "'"){
+ $regary = sq_findnxreg($body, $pos+1, "\'");
+ if ($regary == false){
+ return Array(false, false, false, $lt, strlen($body));
+ }
+ list($pos, $attval, $match) = $regary;
+ $pos++;
+ $attary{$attname} = "'" . $attval . "'";
+ } else if ($quot == '"'){
+ $regary = sq_findnxreg($body, $pos+1, '\"');
+ if ($regary == false){
+ return Array(false, false, false, $lt, strlen($body));
+ }
+ list($pos, $attval, $match) = $regary;
+ $pos++;
+ $attary{$attname} = '"' . $attval . '"';
+ } else {
+ /**
+ * 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.
+ */
+ $attval = preg_replace("/\"/s", """, $attval);
+ $attary{$attname} = '"' . $attval . '"';
+ }
+ } else if (preg_match("|[\w/>]|", $char)) {
+ /**
+ * That was attribute type 4.
+ */
+ $attary{$attname} = '"yes"';
+ } else {
+ /**
+ * An illegal character. Find next '>' and return.
+ */
+ $gt = sq_findnxstr($body, $pos, ">");
+ return Array(false, false, false, $lt, $gt);
+ }
+ }
+ }
+ /**
+ * 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 $attvalue A string to run entity check against.
+ * @return Translated value.
+ */
+function sq_deent($attvalue){
+ $me = 'sq_deent';
+ /**
+ * See if we have to run the checks first. All entities must start
+ * with "&".
+ */
+ if (strpos($attvalue, "&") === false){
+ return $attvalue;
+ }
+ /**
+ * Check named entities first.
+ */
+ $trans = get_html_translation_table(HTML_ENTITIES);
+ /**
+ * Leave " in, as it can mess us up.
+ */
+ $trans = array_flip($trans);
+ unset($trans{"""});
+ while (list($ent, $val) = each($trans)){
+ $attvalue = preg_replace("/$ent*(\W)/si", "$val\\1", $attvalue);
+ }
+ /**
+ * Now translate numbered entities from 1 to 255 if needed.
+ */
+ if (strpos($attvalue, "#") !== false){
+ $omit = Array(34, 39);
+ for ($asc=1; $asc<256; $asc++){
+ if (!in_array($asc, $omit)){
+ $chr = chr($asc);
+ $attvalue = preg_replace("/\�*$asc;*(\D)/si", "$chr\\1",
+ $attvalue);
+ $attvalue = preg_replace("/\�*".dechex($asc).";*(\W)/si",
+ "$chr\\1", $attvalue);
+ }
+ }
+ }
+ return $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,
+ $rm_attnames,
+ $bad_attvals,
+ $add_attr_to_tag,
+ $message,
+ $id,
+ $mailbox
+ ){
+ $me = 'sq_fixatts';
+ while (list($attname, $attvalue) = each($attary)){
+ /**
+ * See if this attribute should be removed.
+ */
+ foreach ($rm_attnames as $matchtag=>$matchattrs){
+ if (preg_match($matchtag, $tagname)){
+ foreach ($matchattrs as $matchattr){
+ if (preg_match($matchattr, $attname)){
+ unset($attary{$attname});
+ continue;
+ }
+ }
+ }
+ }
+ /**
+ * Remove any entities.
+ */
+ $attvalue = sq_deent($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, $attname)){
+ /**
+ * There are two arrays in valary.
+ * First is matches.
+ * Second one is replacements
+ */
+ list($valmatch, $valrepl) = $valary;
+ $newvalue =
+ preg_replace($valmatch, $valrepl, $attvalue);
+ if ($newvalue != $attvalue){
+ $attary{$attname} = $newvalue;
+ }
+ }
+ }
+ }
+ }
+ /**
+ * Turn cid: urls into http-friendly ones.
+ */
+ if (preg_match("/^[\'\"]\s*cid:/si", $attvalue)){
+ $attary{$attname} = sq_cid2http($message, $id, $attvalue, $mailbox);
+ }
+ }
+ /**
+ * See if we need to append any attributes to this tag.
+ */
+ foreach ($add_attr_to_tag as $matchtag=>$addattary){
+ if (preg_match($matchtag, $tagname)){
+ $attary = array_merge($attary, $addattary);
+ }
+ }
+ return $attary;
+}
+
+/**
+ * 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 $content a string with whatever is between <style> and </style>
+ * @return a string with edited content.
+ */
+function sq_fixstyle($message, $id, $content){
+ global $view_unsafe_images;
+ $me = 'sq_fixstyle';
+ /**
+ * 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 <div>
+ */
+ $content = preg_replace("|body(\s*\{.*?\})|si", ".bodyclass\\1", $content);
+ $secremoveimg = "../images/" . _("sec_remove_eng.png");
+ /**
+ * Fix url('blah') declarations.
+ */
+ $content = preg_replace("|url\(([\'\"])\s*\S+script\s*:.*?([\'\"])\)|si",
+ "url(\\1$secremoveimg\\2)", $content);
+ /**
+ * Fix url('https*://.*) declarations but only if $view_unsafe_images
+ * is false.
+ */
+ if (!$view_unsafe_images){
+ $content = preg_replace("|url\(([\'\"])\s*https*:.*?([\'\"])\)|si",
+ "url(\\1$secremoveimg\\2)", $content);
+ }
+
+ /**
+ * Fix urls that refer to cid:
+ */
+ while (preg_match("|url\(([\'\"]\s*cid:.*?[\'\"])\)|si", $content,
+ $matches)){
+ $cidurl = $matches{1};
+ $httpurl = sq_cid2http($message, $id, $cidurl);
+ $content = preg_replace("|url\($cidurl\)|si",
+ "url($httpurl)", $content);
+ }
- switch( $char ) {
- case ' ':
- case "\n":
- case "\t":
- case "\r":
- case '>':
- case '"':
- return( FALSE );
+ /**
+ * Fix stupid css declarations which lead to vulnerabilities
+ * in IE.
+ */
+ $match = Array('/expression/si',
+ '/behaviou*r/si',
+ '/binding/si');
+ $replace = Array('idiocy', 'idiocy', 'idiocy');
+ $content = preg_replace($match, $replace, $content);
+ return $content;
+}
+
+/**
+ * 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 $cidurl the cid: url.
+ * @return a string with a http-friendly url
+ */
+function sq_cid2http($message, $id, $cidurl, $mailbox){
+ /**
+ * Get rid of quotes.
+ */
+ $quotchar = substr($cidurl, 0, 1);
+ $cidurl = str_replace($quotchar, "", $cidurl);
+ $cidurl = substr(trim($cidurl), 4);
+ $httpurl = $quotchar . "../src/download.php?absolute_dl=true&" .
+ "passed_id=$id&mailbox=" . urlencode($mailbox) .
+ "&ent_id=" . find_ent_id($cidurl, $message) . $quotchar;
+ return $httpurl;
+}
+
+/**
+ * This function changes the <body> tag into a <div> tag since we
+ * can't really have a body-within-body.
+ *
+ * @param $attary an array of attributes and values of <body>
+ * @return a modified array of attributes to be set for <div>
+ */
+function sq_body2div($attary){
+ $me = 'sq_body2div';
+ $divattary = Array( 'class' => "'bodyclass'" );
+ $bgcolor = '#ffffff';
+ $text = '#000000';
+ $styledef = '';
+ if (is_array($attary) && sizeof($attary) > 0){
+ foreach ($attary as $attname=>$attvalue){
+ $quotchar = substr($attvalue, 0, 1);
+ $attvalue = str_replace($quotchar, "", $attvalue);
+ switch ($attname){
+ case 'background':
+ $styledef .= "background-image: url('$attvalue'); ";
break;
- default:
- return( TRUE );
+ case 'bgcolor':
+ $styledef .= "background-color: $attvalue; ";
+ break;
+ case 'text':
+ $styledef .= "color: $attvalue; ";
+ }
}
-
- }
-
- /*
- The following function is usefull to remove extra data that can cause
- html not to display properly. Especialy with MS stuff.
- */
-
- function stripComments( &$i, $j, &$body ) {
-
- while( $body{$i}.$body{$i+1}.$body{$i+2}.$body{$i+3} == '<!--' &&
- $i < $j ) {
- $i += 5;
- while( $body{$i-2}.$body{$i-1}.$body{$i} <> '-->' &&
- $i < $j )
- $i++;
- $i++;
+ if (strlen($styledef) > 0){
+ $divattary{"style"} = "\"$styledef\"";
}
-
- return;
-
- }
-
- /* Gets the style data of a specific style */
-
- function getStyleData( &$i, $j, &$body ) {
-
- // We skip spaces
- while( $body{$i} <> '>' && !isNoSep( $body{$i} ) &&
- $i < $j ) {
- $i++;
+ }
+ return $divattary;
+}
+
+/**
+ * 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
+ ){
+ $me = 'sq_sanitize';
+ /**
+ * Normalize rm_tags and rm_tags_with_content.
+ */
+ @array_walk($rm_tags, '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
+ */
+ $rm_tags = array_shift($tag_list);
+ $curpos = 0;
+ $open_tags = Array();
+ $trusted = "<!-- begin sanitized html -->\n";
+ $skip_content = false;
+ /**
+ * 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 <style>
+ */
+ if ($tagname == "style" && $tagtype == 2){
+ /**
+ * This is a closing </style>. Edit the
+ * content before we apply it.
+ */
+ $free_content = sq_fixstyle($message, $id, $free_content);
}
- // And get the color
- $ret = '';
- while( isNoSep( $body{$i} ) &&
- $i < $j ) {
- $ret .= $body{$i};
- $i++;
+ if ($skip_content == false){
+ $trusted .= $free_content;
+ } else {
}
-
- return( $ret );
- }
-
- /*
- Private function for strip_dangerous_tag. Look for event based coded and "remove" it
- change on with no (onload -> noload)
- */
-
- function stripEvent( &$i, $j, &$body, $id, $base ) {
-
- global $message;
-
- $ret = '';
-
- while( $body{$i} <> '>' &&
- $i < $j ) {
- $etg = strtolower($body{$i}.$body{$i+1}.$body{$i+2});
- switch( $etg ) {
- case '../':
- // Retrolinks are not allowed without a base because they mess with SM security
- if( $base == '' ) {
- $i += 2;
+ if ($tagname != FALSE){
+ if ($tagtype == 2){
+ if ($skip_content == $tagname){
+ /**
+ * Got to the end of tag we needed to remove.
+ */
+ $tagname = false;
+ $skip_content = false;
+ } else {
+ if ($skip_content == false){
+ if ($tagname == "body"){
+ $tagname = "div";
} else {
- $ret .= '.';
- }
- break;
- case 'cid':
- // Internal link
- $k = $i-1;
- if( $body{$i+3} == ':') {
- $i +=4;
- $name = '';
- while( isNoSep( $body{$i} ) &&
- $i < $j )
- $name .= $body{$i++};
- if( $name <> '' ) {
- $ret .= "../src/download.php?absolute_dl=true&passed_id=$id&mailbox=" .
- urlencode( $message->header->mailbox ) .
- "&passed_ent_id=" . find_ent_id( $name, $message );
- if( $body{$k} == '"' )
- $ret .= '" ';
- else
- $ret .= ' ';
+ if (isset($open_tags{$tagname}) &&
+ $open_tags{$tagname} > 0){
+ $open_tags{$tagname}--;
+ } else {
+ $tagname = false;
+ }
}
- if( $body{$i} == '>' )
- $i -= 1;
+ } else {
}
- break;
- case ' on':
- case "\non":
- case "\ron":
- case "\ton":
- $ret .= ' no';
- $i += 2;
- break;
- case 'pt:':
- if( strcasecmp( $body{$i-4}.$body{$i-3}.$body{$i-2}.$body{$i-1}.$body{$i}.$body{$i+1}.$body{$i+2}, 'script:') == 0 ) {
- $ret .= '_no/';
+ }
+ } else {
+ /**
+ * $rm_tags_with_content
+ */
+ if ($skip_content == false){
+ /**
+ * See if this is a self-closing type and change
+ * tagtype appropriately.
+ */
+ if ($tagtype == 1
+ && in_array($tagname, $self_closing_tags)){
+ $tagtype=3;
+ }
+ /**
+ * See if we should skip this tag and any content
+ * inside it.
+ */
+ if ($tagtype == 1 &&
+ in_array($tagname, $rm_tags_with_content)){
+ $skip_content = $tagname;
} else {
- $ret .= $etg;
+ if (($rm_tags == false
+ && in_array($tagname, $tag_list)) ||
+ ($rm_tags == true &&
+ !in_array($tagname, $tag_list))){
+ $tagname = false;
+ } else {
+ if ($tagtype == 1){
+ if (isset($open_tags{$tagname})){
+ $open_tags{$tagname}++;
+ } else {
+ $open_tags{$tagname}=1;
+ }
+ }
+ /**
+ * This is where we run other checks.
+ */
+ if (is_array($attary) && sizeof($attary) > 0){
+ $attary = sq_fixatts($tagname,
+ $attary,
+ $rm_attnames,
+ $bad_attvals,
+ $add_attr_to_tag,
+ $message,
+ $id,
+ $mailbox
+ );
+ }
+ /**
+ * Convert body into div.
+ */
+ if ($tagname == "body"){
+ $tagname = "div";
+ $attary = sq_body2div($attary, $message, $id);
+ }
+ }
}
- $i += 2;
- break;
- default:
- $ret .= $body{$i};
+ } else {
+ }
}
- $i++;
+ if ($tagname != false && $skip_content == false){
+ $trusted .= sq_tagprint($tagname, $attary, $tagtype);
+ }
+ } else {
}
- return( $ret );
+ $curpos = $gt+1;
}
-
-
- /* This function trys to locate the entity_id of a specific mime element */
-
- function find_ent_id( $id, $message ) {
-
- $ret = '';
- for ($i=0; $ret == '' && $i < count($message->entities); $i++) {
-
- if( $message->entities[$i]->header->entity_id == '' ) {
- $ret = find_ent_id( $id, $message->entities[$i] );
- } else {
- if( strcasecmp( $message->entities[$i]->header->id, $id ) == 0 )
- $ret = $message->entities[$i]->header->entity_id;
+ $trusted .= substr($body, $curpos, strlen($body)-$curpos);
+ if ($force_tag_closing == true){
+ foreach ($open_tags as $tagname=>$opentimes){
+ while ($opentimes > 0){
+ $trusted .= '</' . $tagname . '>';
+ $opentimes--;
}
-
}
-
- return( $ret );
-
+ $trusted .= "\n";
+ }
+ $trusted .= "<!-- end sanitized html -->\n";
+ return $trusted;
+}
+
+/**
+ * This is a wrapper function to call html sanitizing routines.
+ *
+ * @param $body the body of the message
+ * @param $id the id of the message
+ * @return a string with html safe to display in the browser.
+ */
+function magicHTML($body, $id, $message, $mailbox = 'INBOX'){
+ global $attachment_common_show_images, $view_unsafe_images,
+ $has_unsafe_images;
+ /**
+ * Don't display attached images in HTML mode.
+ */
+ $attachment_common_show_images = false;
+ $tag_list = Array(
+ false,
+ "object",
+ "meta",
+ "html",
+ "head",
+ "base",
+ "link"
+ );
+
+ $rm_tags_with_content = Array(
+ "script",
+ "applet",
+ "embed",
+ "title"
+ );
+
+ $self_closing_tags = Array(
+ "img",
+ "br",
+ "hr",
+ "input"
+ );
+
+ $force_tag_closing = false;
+
+ $rm_attnames = Array(
+ "/.*/" =>
+ Array(
+ "/target/si",
+ "/^on.*/si",
+ "/^dynsrc/si",
+ "/^data.*/si"
+ )
+ );
+
+ $secremoveimg = "../images/" . _("sec_remove_eng.png");
+ $bad_attvals = Array(
+ "/.*/" =>
+ Array(
+ "/^src|background/i" =>
+ Array(
+ Array(
+ "|^([\'\"])\s*\.\./.*([\'\"])|si",
+ "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si",
+ "/^([\'\"])\s*mocha\s*:*.*([\'\"])/si",
+ "/^([\'\"])\s*about\s*:.*([\'\"])/si"
+ ),
+ Array(
+ "\\1$secremoveimg\\2",
+ "\\1$secremoveimg\\2",
+ "\\1$secremoveimg\\2",
+ "\\1$secremoveimg\\2"
+ )
+ ),
+ "/^href|action/i" =>
+ Array(
+ Array(
+ "|^([\'\"])\s*\.\./.*([\'\"])|si",
+ "/^([\'\"])\s*\S+script\s*:.*([\'\"])/si",
+ "/^([\'\"])\s*mocha\s*:*.*([\'\"])/si",
+ "/^([\'\"])\s*about\s*:.*([\'\"])/si"
+ ),
+ Array(
+ "\\1#\\2",
+ "\\1#\\2",
+ "\\1#\\2",
+ "\\1#\\2"
+ )
+ ),
+ "/^style/si" =>
+ Array(
+ Array(
+ "/expression/si",
+ "/binding/si",
+ "/behaviou*r/si",
+ "|url\(([\'\"])\s*\.\./.*([\'\"])\)|si",
+ "/url\(([\'\"])\s*\S+script\s*:.*([\'\"])\)/si",
+ "/url\(([\'\"])\s*mocha\s*:.*([\'\"])\)/si",
+ "/url\(([\'\"])\s*about\s*:.*([\'\"])\)/si"
+ ),
+ Array(
+ "idiocy",
+ "idiocy",
+ "idiocy",
+ "url(\\1#\\2)",
+ "url(\\1#\\2)",
+ "url(\\1#\\2)",
+ "url(\\1#\\2)"
+ )
+ )
+ )
+ );
+ if (!$view_unsafe_images){
+ /**
+ * Remove any references to http/https if view_unsafe_images set
+ * to false.
+ */
+ array_push($bad_attvals{'/.*/'}{'/^src|background/i'}[0],
+ '/^([\'\"])\s*https*:.*([\'\"])/si');
+ array_push($bad_attvals{'/.*/'}{'/^src|background/i'}[1],
+ "\\1$secremoveimg\\2");
+ array_push($bad_attvals{'/.*/'}{'/^style/si'}[0],
+ '/url\(([\'\"])\s*https*:.*([\'\"])\)/si');
+ array_push($bad_attvals{'/.*/'}{'/^style/si'}[1],
+ "url(\\1$secremoveimg\\2)");
}
-?>
+
+ $add_attr_to_tag = Array(
+ "/^a$/si" => Array('target'=>'"_new"')
+ );
+ $trusted = sq_sanitize($body,
+ $tag_list,
+ $rm_tags_with_content,
+ $self_closing_tags,
+ $force_tag_closing,
+ $rm_attnames,
+ $bad_attvals,
+ $add_attr_to_tag,
+ $message,
+ $id,
+ $mailbox
+ );
+ if (preg_match("|$secremoveimg|si", $trusted)){
+ $has_unsafe_images = true;
+ }
+ return $trusted;
+}
+
+?>
\ No newline at end of file
projects / squirrelmail.git / blobdiff