From 02474e438504d76616ffd9b307388038ebdc80a7 Mon Sep 17 00:00:00 2001 From: stekkel Date: Mon, 7 Feb 2005 18:06:17 +0000 Subject: [PATCH] Fixed: filenames in case of forwarding a message. Cleanup: Make use of getFilename method from the Message class and remove this code from mime.php git-svn-id: https://svn.code.sf.net/p/squirrelmail/code/trunk/squirrelmail@8805 7612ce4b-ef26-0410-bec9-ea0150e637f0 --- class/mime/Message.class.php | 44 +- functions/mime.php | 1300 +++++++++++++++++----------------- 2 files changed, 671 insertions(+), 673 deletions(-) diff --git a/class/mime/Message.class.php b/class/mime/Message.class.php index 47013c1d..e55fccde 100644 --- a/class/mime/Message.class.php +++ b/class/mime/Message.class.php @@ -48,15 +48,41 @@ class Message { } function getFilename() { - $filename = $this->header->getParameter('filename'); - if (!$filename) { - $filename = $this->header->getParameter('name'); - } - - if (!$filename) { - $filename = 'untitled-'.$this->entity_id; - } - return $filename; + $filename = ''; + $header = $this->header; + if (is_object($header->disposition)) { + $filename = $header->disposition->getProperty('filename'); + if (trim($filename) == '') { + $name = decodeHeader($header->disposition->getProperty('name')); + if (!trim($name)) { + $name = $header->getParameter('name'); + if(!trim($name)) { + if (!trim( $header->id )) { + $filename = 'untitled-[' . $this->entity_id . ']' ; + } else { + $filename = 'cid: ' . $header->id; + } + } else { + $filename = $name; + } + } else { + $filename = $name; + } + } + } else { + $filename = $header->getParameter('filename'); + if (!trim($filename)) { + $filename = $header->getParameter('name'); + if (!trim($filename)) { + if (!trim( $header->id )) { + $filename = 'untitled-[' . $this->entity_id . ']' ; + } else { + $filename = 'cid: ' . $header->id; + } + } + } + } + return $filename; } diff --git a/functions/mime.php b/functions/mime.php index 890dcb9a..ea49c4d8 100644 --- a/functions/mime.php +++ b/functions/mime.php @@ -1,17 +1,17 @@
' . - '' . - '' . - '" . - '" . - '" . - '" . - "
' . - _("Body retrieval error. The reason for this is most probably that the message is malformed.") . - '
' . _("Command:") . "$cmd
' . _("Response:") . "$response
' . _("Message:") . "$message
' . _("FETCH line:") . "$topline

"; + '' . + '' . + '" . + '" . + '" . + '" . + "
' . + _("Body retrieval error. The reason for this is most probably that the message is malformed.") . + '
' . _("Command:") . "$cmd
' . _("Response:") . "$response
' . _("Message:") . "$message
' . _("FETCH line:") . "$topline

"; $data = sqimap_run_command ($imap_stream, "FETCH $passed_id BODY[]", true, $response, $message, TRUE); array_shift($data); @@ -160,40 +160,40 @@ function mime_fetch_body($imap_stream, $id, $ent_id=1, $fetch_size=0) { function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding) { /* Don't kill the connection if the browser is over a dialup - * and it would take over 30 seconds to download it. - * Don't call set_time_limit in safe mode. - */ + * and it would take over 30 seconds to download it. + * Don't call set_time_limit in safe mode. + */ if (!ini_get('safe_mode')) { set_time_limit(0); } /* in case of base64 encoded attachments, do not buffer them. - Instead, echo the decoded attachment directly to screen */ + Instead, echo the decoded attachment directly to screen */ if (strtolower($encoding) == 'base64') { if (!$ent_id) { - $query = "FETCH $id BODY[]"; + $query = "FETCH $id BODY[]"; } else { - $query = "FETCH $id BODY[$ent_id]"; + $query = "FETCH $id BODY[$ent_id]"; } sqimap_run_command($imap_stream,$query,true,$response,$message,TRUE,'sqimap_base64_decode','php://stdout',true); } else { - $body = mime_fetch_body ($imap_stream, $id, $ent_id); - echo decodeBody($body, $encoding); + $body = mime_fetch_body ($imap_stream, $id, $ent_id); + echo decodeBody($body, $encoding); } /* - TODO, use the same method for quoted printable. - However, I assume that quoted printable attachments aren't that large - so the performancegain / memory usage drop will be minimal. - If we decide to add that then we need to adapt sqimap_fread because - we need to split te result on \n and fread doesn't stop at \n. That - means we also should provide $results from sqimap_fread (by ref) to - te function and set $no_return to false. The $filter function for - quoted printable should handle unsetting of $results. + TODO, use the same method for quoted printable. + However, I assume that quoted printable attachments aren't that large + so the performancegain / memory usage drop will be minimal. + If we decide to add that then we need to adapt sqimap_fread because + we need to split te result on \n and fread doesn't stop at \n. That + means we also should provide $results from sqimap_fread (by ref) to + te function and set $no_return to false. The $filter function for + quoted printable should handle unsetting of $results. */ /* - TODO 2: find out how we write to the output stream php://stdout. fwrite - doesn't work because 'php://stdout isn't a stream. + TODO 2: find out how we write to the output stream php://stdout. fwrite + doesn't work because 'php://stdout isn't a stream. */ return; @@ -214,7 +214,7 @@ function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding) { return; } else { echo decodeBody($read1, $encoding) . - decodeBody($read, $encoding); + decodeBody($read, $encoding); } } else if ($cnt) { echo decodeBody($read, $encoding); @@ -229,8 +229,8 @@ function mime_print_body_lines ($imap_stream, $id, $ent_id=1, $encoding) { /* -[ END MIME DECODING ]----------------------------------------------------------- */ /* This is here for debugging purposes. It will print out a list - * of all the entity IDs that are in the $message object. - */ +* of all the entity IDs that are in the $message object. +*/ function listEntities ($message) { if ($message) { echo "" . $message->entity_id . ' : ' . $message->type0 . '/' . $message->type1 . ' parent = '. $message->parent->entity_id. '
'; @@ -279,8 +279,8 @@ function getEntity ($message, $ent_id) { } /* translateText - * Extracted from strings.php 23/03/2002 - */ +* Extracted from strings.php 23/03/2002 +*/ function translateText(&$body, $wrap_at, $charset) { global $where, $what; /* from searching */ @@ -332,19 +332,19 @@ function translateText(&$body, $wrap_at, $charset) { } /** - * This returns a parsed string called $body. That string can then - * be displayed as the actual message in the HTML. It contains - * everything needed, including HTML Tags, Attachments at the - * bottom, etc. - * @param clean Do not output stuff that's irrelevant for the printable version. - */ +* This returns a parsed string called $body. That string can then +* be displayed as the actual message in the HTML. It contains +* everything needed, including HTML Tags, Attachments at the +* bottom, etc. +* @param clean Do not output stuff that's irrelevant for the printable version. +*/ function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $mailbox='INBOX', $clean=FALSE) { /* This if statement checks for the entity to show as the - * primary message. To add more of them, just put them in the - * order that is their priority. - */ + * 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; + $show_html_default, $sort, $has_unsafe_images, $passed_ent_id; if( !sqgetGlobalVar('view_unsafe_images', $view_unsafe_images, SQ_GET) ) { $view_unsafe_images = false; @@ -368,31 +368,31 @@ function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $ma $body = $hookResults[1]; /* If there are other types that shouldn't be formatted, add - * them here. - */ + * them here. + */ if ($body_message->header->type1 == 'html') { if ($show_html_default <> 1) { $entity_conv = array(' ' => ' ', - '

' => "\n", - '

' => "\n", - '
' => "\n", - '
' => "\n", - '
' => "\n", - '
' => "\n", - '>' => '>', - '<' => '<'); + '

' => "\n", + '

' => "\n", + '
' => "\n", + '
' => "\n", + '
' => "\n", + '
' => "\n", + '>' => '>', + '<' => '<'); $body = strtr($body, $entity_conv); $body = strip_tags($body); $body = trim($body); translateText($body, $wrap_at, - $body_message->header->getParameter('charset')); + $body_message->header->getParameter('charset')); } else { $body = magicHTML($body, $id, $message, $mailbox); } } else { translateText($body, $wrap_at, - $body_message->header->getParameter('charset')); + $body_message->header->getParameter('charset')); } // if this is the clean display (i.e. printer friendly), stop here. @@ -407,7 +407,7 @@ function formatBody($imap_stream, $message, $color, $wrap_at, $ent_num, $id, $ma $link .= '&passed_ent_id='.$passed_ent_id; } $body .= '

' . _("Download this as a file") . ''; + $link . '">' . _("Download this as a file") . ''; if ($view_unsafe_images) { $text = _("Hide Unsafe Images"); } else { @@ -463,35 +463,7 @@ function formatAttachments($message, $exclude_id, $mailbox, $id) { $description = $from_name; } else { $default_page = SM_PATH . 'src/download.php'; - if (is_object($header->disposition)) { - $filename = $header->disposition->getProperty('filename'); - if (trim($filename) == '') { - $name = decodeHeader($header->disposition->getProperty('name')); - if (trim($name) == '') { - $name = $header->getParameter('name'); - if(trim($name) == '') { - if (trim( $header->id ) == '') { - $filename = 'untitled-[' . $ent . ']' ; - } else { - $filename = 'cid: ' . $header->id; - } - } else { - $filename = $name; - } - } else { - $filename = $name; - } - } - } else { - $filename = $header->getParameter('name'); - if (!trim($filename)) { - if (trim( $header->id ) == '') { - $filename = 'untitled-[' . $ent . ']' ; - } else { - $filename = 'cid: ' . $header->id; - } - } - } + $filename = $att->getFilename(); if ($header->description) { $description = decodeHeader($header->description); } else { @@ -506,23 +478,23 @@ function formatAttachments($message, $exclude_id, $mailbox, $id) { $passed_ent_id_link = ''; } $defaultlink = $default_page . "?startMessage=$startMessage" - . "&passed_id=$id&mailbox=$urlMailbox" - . '&ent_id='.$ent.$passed_ent_id_link; + . "&passed_id=$id&mailbox=$urlMailbox" + . '&ent_id='.$ent.$passed_ent_id_link; if ($where && $what) { - $defaultlink .= '&where='. urlencode($where).'&what='.urlencode($what); + $defaultlink .= '&where='. urlencode($where).'&what='.urlencode($what); } /* This executes the attachment hook with a specific MIME-type. - * If that doesn't have results, it tries if there's a rule - * for a more generic type. - */ + * If that doesn't have results, it tries if there's a rule + * for a more generic type. + */ $hookresults = do_hook("attachment $type0/$type1", $links, - $startMessage, $id, $urlMailbox, $ent, $defaultlink, - $display_filename, $where, $what); + $startMessage, $id, $urlMailbox, $ent, $defaultlink, + $display_filename, $where, $what); if(count($hookresults[1]) <= 1) { $hookresults = do_hook("attachment $type0/*", $links, - $startMessage, $id, $urlMailbox, $ent, $defaultlink, - $display_filename, $where, $what); + $startMessage, $id, $urlMailbox, $ent, $defaultlink, + $display_filename, $where, $what); } $links = $hookresults[1]; @@ -612,18 +584,18 @@ function decodeBody($body, $encoding) { } /** - * Decodes headers - * - * This functions decode strings that is encoded according to - * RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text). - * Patched by Christian Schmidt 23/03/2002 - * - * @param string $string header string that has to be made readable - * @param boolean $utfencode change message in order to be readable on user's charset. defaults to true - * @param boolean $htmlsave preserve spaces and sanitize html special characters. defaults to true - * @param boolean $decide decide if string can be utfencoded. defaults to false - * @return string decoded header string - */ +* Decodes headers +* +* This functions decode strings that is encoded according to +* RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text). +* Patched by Christian Schmidt 23/03/2002 +* +* @param string $string header string that has to be made readable +* @param boolean $utfencode change message in order to be readable on user's charset. defaults to true +* @param boolean $htmlsave preserve spaces and sanitize html special characters. defaults to true +* @param boolean $decide decide if string can be utfencoded. defaults to false +* @return string decoded header string +*/ function decodeHeader ($string, $utfencode=true,$htmlsave=true,$decide=false) { global $languages, $squirrelmail_language,$default_charset; if (is_array($string)) { @@ -673,10 +645,10 @@ function decodeHeader ($string, $utfencode=true,$htmlsave=true,$decide=false) { /* decide about valid decoding */ if ($decide && is_conversion_safe($res[2])) { - $utfencode=true; - $can_be_encoded=true; + $utfencode=true; + $can_be_encoded=true; } else { - $can_be_encoded=false; + $can_be_encoded=false; } switch ($encoding) { @@ -685,8 +657,8 @@ function decodeHeader ($string, $utfencode=true,$htmlsave=true,$decide=false) { if ($utfencode) { if ($can_be_encoded) { /* convert string to different charset, - * if functions asks for it (usually in compose) - */ + * if functions asks for it (usually in compose) + */ $ret .= charset_convert($res[2],$replace,$default_charset); } else { // convert string to html codes in order to display it @@ -704,15 +676,15 @@ function decodeHeader ($string, $utfencode=true,$htmlsave=true,$decide=false) { $replace = preg_replace('/=([0-9a-f]{2})/ie', 'chr(hexdec("\1"))', $replace); if ($utfencode) { - if ($can_be_encoded) { + if ($can_be_encoded) { /* convert string to different charset, - * if functions asks for it (usually in compose) - */ + * if functions asks for it (usually in compose) + */ $replace = charset_convert($res[2], $replace,$default_charset); - } else { + } else { // convert string to html codes in order to display it $replace = charset_decode($res[2], $replace); - } + } } else { if ($htmlsave) { $replace = htmlspecialchars($replace); @@ -754,15 +726,15 @@ function decodeHeader ($string, $utfencode=true,$htmlsave=true,$decide=false) { } /** - * Encodes header as quoted-printable - * - * Encode a string according to RFC 1522 for use in headers if it - * contains 8-bit characters or anything that looks like it should - * be encoded. - * - * @param string $string header string, that has to be encoded - * @return string quoted-printable encoded string - */ +* Encodes header as quoted-printable +* +* Encode a string according to RFC 1522 for use in headers if it +* contains 8-bit characters or anything that looks like it should +* be encoded. +* +* @param string $string header string, that has to be encoded +* @return string quoted-printable encoded string +*/ function encodeHeader ($string) { global $default_charset, $languages, $squirrelmail_language; @@ -909,22 +881,22 @@ function sq_check_save_extension($message) { /** - ** HTMLFILTER ROUTINES - */ +** HTMLFILTER ROUTINES +*/ /** - * This function is more or less a wrapper around stripslashes. Apparently - * Explorer is stupid enough to just remove the backslashes and then - * execute the content of the attribute as if nothing happened. - * Who does that? - * - * @param attvalue The value of the attribute - * @return attvalue The value of the attribute stripslashed. - */ +* This function is more or less a wrapper around stripslashes. Apparently +* Explorer is stupid enough to just remove the backslashes and then +* execute the content of the attribute as if nothing happened. +* Who does that? +* +* @param attvalue The value of the attribute +* @return attvalue The value of the attribute stripslashed. +*/ function sq_unbackslash($attvalue){ /** - * Remove any backslashes. See if there are any first. - */ + * Remove any backslashes. See if there are any first. + */ if (strstr($attvalue, '\\') !== false){ $attvalue = stripslashes($attvalue); @@ -933,13 +905,13 @@ function sq_unbackslash($attvalue){ } /** - * Kill any tabs, newlines, or carriage returns. Our friends the - * makers of the browser with 95% market value decided that it'd - * be funny to make "java[tab]script" be just as good as "javascript". - * - * @param attvalue The attribute value before extraneous spaces removed. - * @return attvalue The attribute value after extraneous spaces removed. - */ +* Kill any tabs, newlines, or carriage returns. Our friends the +* makers of the browser with 95% market value decided that it'd +* be funny to make "java[tab]script" be just as good as "javascript". +* +* @param attvalue The attribute value before extraneous spaces removed. +* @return attvalue The attribute value after extraneous spaces removed. +*/ function sq_unspace($attvalue){ if (strcspn($attvalue, "\t\r\n") != strlen($attvalue)){ $attvalue = str_replace(Array("\t", "\r", "\n"), Array('', '', ''), @@ -949,15 +921,15 @@ function sq_unspace($attvalue){ } /** - * This function returns the final tag out of the tag name, an array - * of attributes, and the type of the tag. This function is called by - * sq_sanitize internally. - * - * @param $tagname the name of the tag. - * @param $attary the array of attributes and their values - * @param $tagtype The type of the tag (see in comments). - * @return a string with the final tag representation. - */ +* This function returns the final tag out of the tag name, an array +* of attributes, and the type of the tag. This function is called by +* sq_sanitize internally. +* +* @param $tagname the name of the tag. +* @param $attary the array of attributes and their values +* @param $tagtype The type of the tag (see in comments). +* @return a string with the final tag representation. +*/ function sq_tagprint($tagname, $attary, $tagtype){ $me = 'sq_tagprint'; @@ -981,26 +953,26 @@ function sq_tagprint($tagname, $attary, $tagtype){ } /** - * A small helper function to use with array_walk. Modifies a by-ref - * value and makes it lowercase. - * - * @param $val a value passed by-ref. - * @return void since it modifies a by-ref value. - */ +* A small helper function to use with array_walk. Modifies a by-ref +* value and makes it lowercase. +* +* @param $val a value passed by-ref. +* @return void since it modifies a by-ref value. +*/ function sq_casenormalize(&$val){ $val = strtolower($val); } /** - * This function skips any whitespace from the current position within - * a string and to the next non-whitespace value. - * - * @param $body the string - * @param $offset the offset within the string where we should start - * looking for the next non-whitespace character. - * @return the location within the $body where the next - * non-whitespace char is located. - */ +* This function skips any whitespace from the current position within +* a string and to the next non-whitespace value. +* +* @param $body the string +* @param $offset the offset within the string where we should start +* looking for the next non-whitespace character. +* @return the location within the $body where the next +* non-whitespace char is located. +*/ function sq_skipspace($body, $offset){ $me = 'sq_skipspace'; preg_match('/^(\s*)/s', substr($body, $offset), $matches); @@ -1012,16 +984,16 @@ function sq_skipspace($body, $offset){ } /** - * This function looks for the next character within a string. It's - * really just a glorified "strpos", except it catches if failures - * nicely. - * - * @param $body The string to look for needle in. - * @param $offset Start looking from this position. - * @param $needle The character/string to look for. - * @return location of the next occurance of the needle, or - * strlen($body) if needle wasn't found. - */ +* This function looks for the next character within a string. It's +* really just a glorified "strpos", except it catches if failures +* nicely. +* +* @param $body The string to look for needle in. +* @param $offset Start looking from this position. +* @param $needle The character/string to look for. +* @return location of the next occurance of the needle, or +* strlen($body) if needle wasn't found. +*/ function sq_findnxstr($body, $offset, $needle){ $me = 'sq_findnxstr'; $pos = strpos($body, $needle, $offset); @@ -1032,18 +1004,18 @@ function sq_findnxstr($body, $offset, $needle){ } /** - * This function takes a PCRE-style regexp and tries to match it - * within the string. - * - * @param $body The string to look for needle in. - * @param $offset Start looking from here. - * @param $reg A PCRE-style regex to match. - * @return Returns a false if no matches found, or an array - * with the following members: - * - integer with the location of the match within $body - * - string with whatever content between offset and the match - * - string with whatever it is we matched - */ +* This function takes a PCRE-style regexp and tries to match it +* within the string. +* +* @param $body The string to look for needle in. +* @param $offset Start looking from here. +* @param $reg A PCRE-style regex to match. +* @return Returns a false if no matches found, or an array +* with the following members: +* - integer with the location of the match within $body +* - string with whatever content between offset and the match +* - string with whatever it is we matched +*/ function sq_findnxreg($body, $offset, $reg){ $me = 'sq_findnxreg'; $matches = Array(); @@ -1060,19 +1032,19 @@ function sq_findnxreg($body, $offset, $reg){ } /** - * This function looks for the next tag. - * - * @param $body String where to look for the next tag. - * @param $offset Start looking from here. - * @return false if no more tags exist in the body, or - * an array with the following members: - * - string with the name of the tag - * - array with attributes and their values - * - integer with tag type (1, 2, or 3) - * - integer where the tag starts (starting "<") - * - integer where the tag ends (ending ">") - * first three members will be false, if the tag is invalid. - */ +* This function looks for the next tag. +* +* @param $body String where to look for the next tag. +* @param $offset Start looking from here. +* @return false if no more tags exist in the body, or +* an array with the following members: +* - string with the name of the tag +* - array with attributes and their values +* - integer with tag type (1, 2, or 3) +* - integer where the tag starts (starting "<") +* - integer where the tag ends (ending ">") +* first three members will be false, if the tag is invalid. +*/ function sq_getnxtag($body, $offset){ $me = 'sq_getnxtag'; if ($offset > strlen($body)){ @@ -1083,23 +1055,23 @@ function sq_getnxtag($body, $offset){ return false; } /** - * We are here: - * blah blah - * \---------^ - */ + * We are here: + * blah blah + * \---------^ + */ $pos = sq_skipspace($body, $lt+1); if ($pos >= strlen($body)){ return Array(false, false, false, $lt, strlen($body)); } /** - * There are 3 kinds of tags: - * 1. Opening tag, e.g.: - * - * 2. Closing tag, e.g.: - * - * 3. XHTML-style content-less tag, e.g.: - * - */ + * There are 3 kinds of tags: + * 1. Opening tag, e.g.: + * + * 2. Closing tag, e.g.: + * + * 3. XHTML-style content-less tag, e.g.: + * + */ $tagtype = false; switch (substr($body, $pos, 1)){ case '/': @@ -1108,8 +1080,8 @@ function sq_getnxtag($body, $offset){ break; case '!': /** - * A comment or an SGML declaration. - */ + * A comment or an SGML declaration. + */ if (substr($body, $pos+1, 2) == "--"){ $gt = strpos($body, "-->", $pos); if ($gt === false){ @@ -1125,17 +1097,17 @@ function sq_getnxtag($body, $offset){ break; default: /** - * Assume tagtype 1 for now. If it's type 3, we'll switch values - * later. - */ + * Assume tagtype 1 for now. If it's type 3, we'll switch values + * later. + */ $tagtype = 1; break; } $tagname = ''; /** - * Look for next [\W-_], which will indicate the end of the tag name. - */ + * Look for next [\W-_], which will indicate the end of the tag name. + */ $regary = sq_findnxreg($body, $pos, "[^\w\-_]"); if ($regary == false){ return Array(false, false, false, $lt, strlen($body)); @@ -1144,20 +1116,20 @@ function sq_getnxtag($body, $offset){ $tagname = strtolower($tagname); /** - * $match can be either of these: - * '>' indicating the end of the tag entirely. - * '\s' indicating the end of the tag name. - * '/' indicating that this is type-3 xhtml tag. - * - * Whatever else we find there indicates an invalid tag. - */ + * $match can be either of these: + * '>' indicating the end of the tag entirely. + * '\s' indicating the end of the tag name. + * '/' indicating that this is type-3 xhtml tag. + * + * Whatever else we find there indicates an invalid tag. + */ switch ($match){ case '/': /** - * This is an xhtml-style tag with a closing / at the - * end, like so: . Check if it's followed - * by the closing bracket. If not, then this tag is invalid - */ + * This is an xhtml-style tag with a closing / at the + * end, like so: . Check if it's followed + * by the closing bracket. If not, then this tag is invalid + */ if (substr($body, $pos, 2) == "/>"){ $pos++; $tagtype = 3; @@ -1171,12 +1143,12 @@ function sq_getnxtag($body, $offset){ break; default: /** - * Check if it's whitespace - */ + * Check if it's whitespace + */ if (!preg_match('/\s/', $match)){ /** - * This is an invalid tag! Look for the next closing ">". - */ + * This is an invalid tag! Look for the next closing ">". + */ $gt = sq_findnxstr($body, $lt, ">"); return Array(false, false, false, $lt, $gt); } @@ -1184,12 +1156,12 @@ function sq_getnxtag($body, $offset){ } /** - * At this point we're here: - * - * \-------^ - * - * At this point we loop in order to find all attributes. - */ + * At this point we're here: + * + * \-------^ + * + * At this point we loop in order to find all attributes. + */ $attname = ''; $attary = Array(); @@ -1197,19 +1169,19 @@ function sq_getnxtag($body, $offset){ $pos = sq_skipspace($body, $pos); if ($pos == strlen($body)){ /** - * Non-closed tag. - */ + * Non-closed tag. + */ return Array(false, false, false, $lt, $pos); } /** - * See if we arrived at a ">" or "/>", which means that we reached - * the end of the tag. - */ + * See if we arrived at a ">" or "/>", which means that we reached + * the end of the tag. + */ $matches = Array(); if (preg_match("%^(\s*)(>|/>)%s", substr($body, $pos), $matches)) { /** - * Yep. So we did. - */ + * Yep. So we did. + */ $pos += strlen($matches{1}); if ($matches{2} == "/>"){ $tagtype = 3; @@ -1219,46 +1191,46 @@ function sq_getnxtag($body, $offset){ } /** - * There are several types of attributes, with optional - * [:space:] between members. - * Type 1: - * attrname[:space:]=[:space:]'CDATA' - * Type 2: - * attrname[:space:]=[:space:]"CDATA" - * Type 3: - * attr[:space:]=[:space:]CDATA - * Type 4: - * attrname - * - * We leave types 1 and 2 the same, type 3 we check for - * '"' and convert to """ if needed, then wrap in - * double quotes. Type 4 we convert into: - * attrname="yes". - */ + * There are several types of attributes, with optional + * [:space:] between members. + * Type 1: + * attrname[:space:]=[:space:]'CDATA' + * Type 2: + * attrname[:space:]=[:space:]"CDATA" + * Type 3: + * attr[:space:]=[:space:]CDATA + * Type 4: + * attrname + * + * We leave types 1 and 2 the same, type 3 we check for + * '"' and convert to """ if needed, then wrap in + * double quotes. Type 4 we convert into: + * attrname="yes". + */ $regary = sq_findnxreg($body, $pos, "[^:\w\-_]"); if ($regary == false){ /** - * Looks like body ended before the end of tag. - */ + * Looks like body ended before the end of tag. + */ return Array(false, false, false, $lt, strlen($body)); } list($pos, $attname, $match) = $regary; $attname = strtolower($attname); /** - * We arrived at the end of attribute name. Several things possible - * here: - * '>' means the end of the tag and this is attribute type 4 - * '/' if followed by '>' means the same thing as above - * '\s' means a lot of things -- look what it's followed by. - * anything else means the attribute is invalid. - */ + * We arrived at the end of attribute name. Several things possible + * here: + * '>' means the end of the tag and this is attribute type 4 + * '/' if followed by '>' means the same thing as above + * '\s' means a lot of things -- look what it's followed by. + * anything else means the attribute is invalid. + */ switch($match){ case '/': /** - * This is an xhtml-style tag with a closing / at the - * end, like so: . Check if it's followed - * by the closing bracket. If not, then this tag is invalid - */ + * This is an xhtml-style tag with a closing / at the + * end, like so: . Check if it's followed + * by the closing bracket. If not, then this tag is invalid + */ if (substr($body, $pos, 2) == "/>"){ $pos++; $tagtype = 3; @@ -1273,27 +1245,27 @@ function sq_getnxtag($body, $offset){ break; default: /** - * Skip whitespace and see what we arrive at. - */ + * Skip whitespace and see what we arrive at. + */ $pos = sq_skipspace($body, $pos); $char = substr($body, $pos, 1); /** - * Two things are valid here: - * '=' means this is attribute type 1 2 or 3. - * \w means this was attribute type 4. - * anything else we ignore and re-loop. End of tag and - * invalid stuff will be caught by our checks at the beginning - * of the loop. - */ + * Two things are valid here: + * '=' means this is attribute type 1 2 or 3. + * \w means this was attribute type 4. + * anything else we ignore and re-loop. End of tag and + * invalid stuff will be caught by our checks at the beginning + * of the loop. + */ if ($char == "="){ $pos++; $pos = sq_skipspace($body, $pos); /** - * Here are 3 possibilities: - * "'" attribute type 1 - * '"' attribute type 2 - * everything else is the content of tag type 3 - */ + * Here are 3 possibilities: + * "'" attribute type 1 + * '"' attribute type 2 + * everything else is the content of tag type 3 + */ $quot = substr($body, $pos, 1); if ($quot == "'"){ $regary = sq_findnxreg($body, $pos+1, "\'"); @@ -1313,28 +1285,28 @@ function sq_getnxtag($body, $offset){ $attary{$attname} = '"' . $attval . '"'; } else { /** - * These are hateful. Look for \s, or >. - */ + * These are hateful. Look for \s, or >. + */ $regary = sq_findnxreg($body, $pos, "[\s>]"); if ($regary == false){ return Array(false, false, false, $lt, strlen($body)); } list($pos, $attval, $match) = $regary; /** - * If it's ">" it will be caught at the top. - */ + * If it's ">" it will be caught at the top. + */ $attval = preg_replace("/\"/s", """, $attval); $attary{$attname} = '"' . $attval . '"'; } } else if (preg_match("|[\w/>]|", $char)) { /** - * That was attribute type 4. - */ + * That was attribute type 4. + */ $attary{$attname} = '"yes"'; } else { /** - * An illegal character. Find next '>' and return. - */ + * An illegal character. Find next '>' and return. + */ $gt = sq_findnxstr($body, $pos, ">"); return Array(false, false, false, $lt, $gt); } @@ -1342,45 +1314,45 @@ function sq_getnxtag($body, $offset){ } } /** - * The fact that we got here indicates that the tag end was never - * found. Return invalid tag indication so it gets stripped. - */ + * The fact that we got here indicates that the tag end was never + * found. Return invalid tag indication so it gets stripped. + */ return Array(false, false, false, $lt, strlen($body)); } /** - * This function checks attribute values for entity-encoded values - * and returns them translated into 8-bit strings so we can run - * checks on them. - * - * @param $attvalue A string to run entity check against. - * @return Translated value. - */ +* This function checks attribute values for entity-encoded values +* and returns them translated into 8-bit strings so we can run +* checks on them. +* +* @param $attvalue A string to run entity check against. +* @return Translated value. +*/ function sq_deent($attvalue){ $me = 'sq_deent'; /** - * See if we have to run the checks first. All entities must start - * with "&". - */ + * See if we have to run the checks first. All entities must start + * with "&". + */ if (strpos($attvalue, '&') === false){ return $attvalue; } /** - * Check named entities first. - */ + * Check named entities first. + */ $trans = get_html_translation_table(HTML_ENTITIES); /** - * Leave " in, as it can mess us up. - */ + * Leave " in, as it can mess us up. + */ $trans = array_flip($trans); unset($trans{'"'}); while (list($ent, $val) = each($trans)){ $attvalue = preg_replace('/' . $ent . '*/si', $val, $attvalue); } /** - * Now translate numbered entities from 1 to 255 if needed. - */ + * Now translate numbered entities from 1 to 255 if needed. + */ if (strpos($attvalue, '#') !== false){ $omit = Array(34, 39); for ($asc = 256; $asc >= 0; $asc--){ @@ -1397,17 +1369,17 @@ function sq_deent($attvalue){ } /** - * This function runs various checks against the attributes. - * - * @param $tagname String with the name of the tag. - * @param $attary Array with all tag attributes. - * @param $rm_attnames See description for sq_sanitize - * @param $bad_attvals See description for sq_sanitize - * @param $add_attr_to_tag See description for sq_sanitize - * @param $message message object - * @param $id message id - * @return Array with modified attributes. - */ +* 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, $rm_attnames, @@ -1420,8 +1392,8 @@ function sq_fixatts($tagname, $me = 'sq_fixatts'; while (list($attname, $attvalue) = each($attary)){ /** - * See if this attribute should be removed. - */ + * See if this attribute should be removed. + */ foreach ($rm_attnames as $matchtag=>$matchattrs){ if (preg_match($matchtag, $tagname)){ foreach ($matchattrs as $matchattr){ @@ -1433,33 +1405,33 @@ function sq_fixatts($tagname, } } /** - * Remove any backslashes, entities, and extraneous whitespace. - */ + * Remove any backslashes, entities, and extraneous whitespace. + */ $attvalue = sq_unbackslash($attvalue); $attvalue = sq_deent($attvalue); $attvalue = sq_unspace($attvalue); /** - * Remove \r \n \t \0 " " "\\" - */ + * Remove \r \n \t \0 " " "\\" + */ $attvalue = str_replace(Array("\r", "\n", "\t", "\0", " ", "\\"), Array('', '','','','',''), $attvalue); /** - * Now let's run checks on the attvalues. - * I don't expect anyone to comprehend this. If you do, - * get in touch with me so I can drive to where you live and - * shake your hand personally. :) - */ + * Now let's run checks on the attvalues. + * I don't expect anyone to comprehend this. If you do, + * get in touch with me so I can drive to where you live and + * shake your hand personally. :) + */ foreach ($bad_attvals as $matchtag=>$matchattrs){ if (preg_match($matchtag, $tagname)){ foreach ($matchattrs as $matchattr=>$valary){ if (preg_match($matchattr, $attname)){ /** - * There are two arrays in valary. - * First is matches. - * Second one is replacements - */ + * There are two arrays in valary. + * First is matches. + * Second one is replacements + */ list($valmatch, $valrepl) = $valary; $newvalue = preg_replace($valmatch, $valrepl, $attvalue); @@ -1471,15 +1443,15 @@ function sq_fixatts($tagname, } } /** - * Turn cid: urls into http-friendly ones. - */ + * Turn cid: urls into http-friendly ones. + */ if (preg_match("/^[\'\"]\s*cid:/si", $attvalue)){ $attary{$attname} = sq_cid2http($message, $id, $attvalue, $mailbox); } } /** - * See if we need to append any attributes to this tag. - */ + * See if we need to append any attributes to this tag. + */ foreach ($add_attr_to_tag as $matchtag=>$addattary){ if (preg_match($matchtag, $tagname)){ $attary = array_merge($attary, $addattary); @@ -1489,15 +1461,15 @@ function sq_fixatts($tagname, } /** - * This function edits the style definition to make them friendly and - * usable in SquirrelMail. - * - * @param $message the message object - * @param $id the message id - * @param $content a string with whatever is between - * @param $mailbox the message mailbox - * @return a string with edited content. - */ +* This function edits the style definition to make them friendly and +* usable in SquirrelMail. +* +* @param $message the message object +* @param $id the message id +* @param $content a string with whatever is between +* @param $mailbox the message mailbox +* @return a string with edited content. +*/ function sq_fixstyle($body, $pos, $message, $id, $mailbox){ global $view_unsafe_images; $me = 'sq_fixstyle'; @@ -1508,32 +1480,32 @@ function sq_fixstyle($body, $pos, $message, $id, $mailbox){ $newpos = $ret[0] + strlen($ret[2]); $content = $ret[1]; /** - * First look for general BODY style declaration, which would be - * like so: - * body {background: blah-blah} - * and change it to .bodyclass so we can just assign it to a
- */ + * First look for general BODY style declaration, which would be + * like so: + * body {background: blah-blah} + * and change it to .bodyclass so we can just assign it to a
+ */ $content = preg_replace("|body(\s*\{.*?\})|si", ".bodyclass\\1", $content); $secremoveimg = '../images/' . _("sec_remove_eng.png"); /** - * Fix url('blah') declarations. - */ + * Fix url('blah') declarations. + */ $content = preg_replace("|url\s*\(\s*([\'\"])\s*\S+script\s*:.*?([\'\"])\s*\)|si", "url(\\1$secremoveimg\\2)", $content); /** - * Fix url('https*://.*) declarations but only if $view_unsafe_images - * is false. - */ + * Fix url('https*://.*) declarations but only if $view_unsafe_images + * is false. + */ if (!$view_unsafe_images){ $content = preg_replace("|url\s*\(\s*([\'\"])\s*https*:.*?([\'\"])\s*\)|si", "url(\\1$secremoveimg\\2)", $content); } /** - * Fix urls that refer to cid: - */ + * Fix urls that refer to cid: + */ while (preg_match("|url\s*\(\s*([\'\"]\s*cid:.*?[\'\"])\s*\)|si", - $content, $matches)){ + $content, $matches)){ $cidurl = $matches{1}; $httpurl = sq_cid2http($message, $id, $cidurl, $mailbox); $content = preg_replace("|url\s*\(\s*$cidurl\s*\)|si", @@ -1541,32 +1513,32 @@ function sq_fixstyle($body, $pos, $message, $id, $mailbox){ } /** - * Fix stupid css declarations which lead to vulnerabilities - * in IE. - */ + * Fix stupid css declarations which lead to vulnerabilities + * in IE. + */ $match = Array('/expression/i', - '/behaviou*r/i', - '/binding/i', - '/include-source/i'); + '/behaviou*r/i', + '/binding/i', + '/include-source/i'); $replace = Array('idiocy', 'idiocy', 'idiocy', 'idiocy'); $content = preg_replace($match, $replace, $content); return array($content, $newpos); } /** - * This function converts cid: url's into the ones that can be viewed in - * the browser. - * - * @param $message the message object - * @param $id the message id - * @param $cidurl the cid: url. - * @param $mailbox the message mailbox - * @return a string with a http-friendly url - */ +* This function converts cid: url's into the ones that can be viewed in +* the browser. +* +* @param $message the message object +* @param $id the message id +* @param $cidurl the cid: url. +* @param $mailbox the message mailbox +* @return a string with a http-friendly url +*/ function sq_cid2http($message, $id, $cidurl, $mailbox){ /** - * Get rid of quotes. - */ + * Get rid of quotes. + */ $quotchar = substr($cidurl, 0, 1); if ($quotchar == '"' || $quotchar == "'"){ $cidurl = str_replace($quotchar, "", $cidurl); @@ -1576,26 +1548,26 @@ function sq_cid2http($message, $id, $cidurl, $mailbox){ $cidurl = substr(trim($cidurl), 4); $linkurl = find_ent_id($cidurl, $message); /* in case of non-save cid links $httpurl should be replaced by a sort of - unsave link image */ + unsave link image */ $httpurl = ''; if ($linkurl) { $httpurl = $quotchar . SM_PATH . 'src/download.php?absolute_dl=true&' . - "passed_id=$id&mailbox=" . urlencode($mailbox) . - '&ent_id=' . $linkurl . $quotchar; + "passed_id=$id&mailbox=" . urlencode($mailbox) . + '&ent_id=' . $linkurl . $quotchar; } return $httpurl; } /** - * This function changes the tag into a
tag since we - * can't really have a body-within-body. - * - * @param $attary an array of attributes and values of - * @param $mailbox mailbox we're currently reading (for cid2http) - * @param $message current message (for cid2http) - * @param $id current message id (for cid2http) - * @return a modified array of attributes to be set for
- */ +* This function changes the tag into a
tag since we +* can't really have a body-within-body. +* +* @param $attary an array of attributes and values of +* @param $mailbox mailbox we're currently reading (for cid2http) +* @param $message current message (for cid2http) +* @param $id current message id (for cid2http) +* @return a modified array of attributes to be set for
+*/ function sq_body2div($attary, $mailbox, $message, $id){ $me = 'sq_body2div'; $divattary = Array('class' => "'bodyclass'"); @@ -1635,66 +1607,66 @@ function sq_body2div($attary, $mailbox, $message, $id){ } /** - * This is the main function and the one you should actually be calling. - * There are several variables you should be aware of an which need - * special description. - * - * Since the description is quite lengthy, see it here: - * http://linux.duke.edu/projects/mini/htmlfilter/ - * - * @param $body the string with HTML you wish to filter - * @param $tag_list see description above - * @param $rm_tags_with_content see description above - * @param $self_closing_tags see description above - * @param $force_tag_closing see description above - * @param $rm_attnames see description above - * @param $bad_attvals see description above - * @param $add_attr_to_tag see description above - * @param $message message object - * @param $id message id - * @return sanitized html safe to show on your pages. - */ +* This is the main function and the one you should actually be calling. +* There are several variables you should be aware of an which need +* special description. +* +* Since the description is quite lengthy, see it here: +* http://linux.duke.edu/projects/mini/htmlfilter/ +* +* @param $body the string with HTML you wish to filter +* @param $tag_list see description above +* @param $rm_tags_with_content see description above +* @param $self_closing_tags see description above +* @param $force_tag_closing see description above +* @param $rm_attnames see description above +* @param $bad_attvals see description above +* @param $add_attr_to_tag see description above +* @param $message message object +* @param $id message id +* @return sanitized html safe to show on your pages. +*/ function sq_sanitize($body, - $tag_list, - $rm_tags_with_content, - $self_closing_tags, - $force_tag_closing, - $rm_attnames, - $bad_attvals, - $add_attr_to_tag, - $message, - $id, - $mailbox - ){ + $tag_list, + $rm_tags_with_content, + $self_closing_tags, + $force_tag_closing, + $rm_attnames, + $bad_attvals, + $add_attr_to_tag, + $message, + $id, + $mailbox + ){ $me = 'sq_sanitize'; $rm_tags = array_shift($tag_list); /** - * Normalize rm_tags and rm_tags_with_content. - */ + * Normalize rm_tags and rm_tags_with_content. + */ @array_walk($tag_list, 'sq_casenormalize'); @array_walk($rm_tags_with_content, 'sq_casenormalize'); @array_walk($self_closing_tags, 'sq_casenormalize'); /** - * See if tag_list is of tags to remove or tags to allow. - * false means remove these tags - * true means allow these tags - */ + * See if tag_list is of tags to remove or tags to allow. + * false means remove these tags + * true means allow these tags + */ $curpos = 0; $open_tags = Array(); $trusted = "\n\n"; $skip_content = false; /** - * Take care of netscape's stupid javascript entities like - * &{alert('boo')}; - */ + * Take care of netscape's stupid javascript entities like + * &{alert('boo')}; + */ $body = preg_replace("/&(\{.*?\};)/si", "&\\1", $body); while (($curtag = sq_getnxtag($body, $curpos)) != FALSE){ list($tagname, $attary, $tagtype, $lt, $gt) = $curtag; $free_content = substr($body, $curpos, $lt-$curpos); /** - * Take care of