X-Git-Url: https://vcs.fsf.org/?p=squirrelmail.git;a=blobdiff_plain;f=functions%2Fmime.php;h=1175f26f4ba2eaee8aa3659463f8a6e9795857d5;hp=24e11590200449eec14dbe2840d0437525c915a3;hb=0f8a1ce94ff62c4a6022969cf2b3e8fb695282f4;hpb=bd9bbfefba8fa274260a37c965f7510bb6670599 diff --git a/functions/mime.php b/functions/mime.php index 24e11590..1175f26f 100644 --- a/functions/mime.php +++ b/functions/mime.php @@ -12,22 +12,6 @@ * $Id$ */ -/*****************************************************************/ -/*** THIS FILE NEEDS TO HAVE ITS FORMATTING FIXED!!! ***/ -/*** PLEASE DO SO AND REMOVE THIS COMMENT SECTION. ***/ -/*** + Base level indent should begin at left margin, as ***/ -/*** the require_once below. ***/ -/*** + All identation should consist of four space blocks ***/ -/*** + Tab characters are evil. ***/ -/*** + all comments should use "slash-star ... star-slash" ***/ -/*** style -- no pound characters, no slash-slash style ***/ -/*** + FLOW CONTROL STATEMENTS (if, while, etc) SHOULD ***/ -/*** ALWAYS USE { AND } CHARACTERS!!! ***/ -/*** + Please use ' instead of ", when possible. Note " ***/ -/*** should always be used in _( ) function calls. ***/ -/*** Thank you for your help making the SM code more readable. ***/ -/*****************************************************************/ - require_once('../functions/imap.php'); require_once('../functions/attachment_common.php'); @@ -44,1118 +28,1198 @@ class msg_header { // var $priority = ""; } - 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); - } +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; + } +} - $msg = mime_parse_structure ($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; - } +/* --------------------------------------------------------------------------------- */ +/* MIME DECODING */ +/* --------------------------------------------------------------------------------- */ - 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 = $id . '.0'; - } +/* This function gets the structure of a message and stores it in the "message" class. + * It will return this object for use with all relevant header information and + * fully parsed into the standard "message" object format. + */ +function mime_structure ($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 ); +} - 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 = $text; - break; - default: - if ($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']; - } - } +/* 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; +} - 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); - } - 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; - } - } - } - - // 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{$pos} == ')') { +/* Increments the element ID. An element id can look like any of + * the following: 1, 1.2, 4.3.2.4.1, etc. This function increments + * the last number of the element id, changing 1.2 to 1.3. + */ +function mime_increment_id ($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 = $text; + break; + default: + if ($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); + } + 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; + } + } +} + +/* + * 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{$pos} == '"') { + } elseif ($structure{$pos} == '"') { $pos++; - while( $structure{$pos} != '"' && - $pos < $j ) { - if (substr($structure, $pos, 2) == '\\"') + while ( $structure{$pos} != '"' && + $pos < $j ) { + if (substr($structure, $pos, 2) == '\\"') { $pos++; - elseif (substr($structure, $pos, 2) == '\\\\') + } elseif (substr($structure, $pos, 2) == '\\\\') { $pos++; + } $pos++; } - } elseif ( $structure{$pos} == '(' ) { + } elseif ( $structure{$pos} == '(' ) { $pos = mime_match_parenthesis ($pos, $structure); - } - } - echo "Error decoding mime structure. Report this as a bug!
\n"; - return( $pos ); - } - - function mime_fetch_body ($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); + } + } + echo _("Error decoding mime structure. Report this as a bug!") . '
'; + return( $pos ); +} + +function mime_fetch_body ($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; + $data = sqimap_run_command ($imap_stream, "FETCH $id BODY[$ent_id]", true, $response, $message); + $topline = array_shift($data); + while (! ereg('\\* [0-9]+ FETCH ', $topline) && $data) $topline = array_shift($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 ); + $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); + $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++; + $k = 0; + } elseif ( $k == 1 && !isnosep( $d{0} ) ) { + $base .= substr( $d, 1 ); } - if( $base <> '' ) - $ret = "" . $ret; + $k++; } - } else if (ereg('"([^"]*)"', $topline, $regs)) { - $ret = $regs[1]; + if ( $base <> '' ) + + $ret = "" . $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); } 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 '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!
\n" . - "Submit message
" . + $par .= "&startMessage=$startMessage&show_more=0"; + } + $par .= '&response='.urlencode($response).'&message='.urlencode($message). + '&topline='.urlencode($topline); + + echo '' . + _("Body retrieval error. The reason for this is most probably that the message is malformed. Please help us making future versions better by submitting this message to the developers knowledgebase!") . + "Submit message
" . + '' . _("Response:") . "$response
" . + _("Message:") . " $message
" . + _("FETCH line:") . " $topline
"; + + $data = sqimap_run_command ($imap_stream, "FETCH $passed_id BODY[]", true, $response, $message); + array_shift($data); + $wholemessage = implode('', $data); - "Response: $response
" . - "Message: $message
" . - "FETCH line: $topline
"; + $ret = "---------------\n$wholemessage"; - 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); + } + return( $ret ); +} - $ret = "---------------\n$wholemessage"; - - } - return( $ret ); +function mime_print_body_lines ($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; } + $sid = sqimap_session_id(); + // Don't kill the connection if the browser is over a dialup + // and it would take over 30 seconds to download it. - function mime_print_body_lines ($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, $encoding); - } + // donĀ“t call set_time_limit in safe mode. + if (!ini_get("safe_mode")) { + set_time_limit(0); + } + + fputs ($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); - $cnt++; + if (ereg("^".$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); + $cnt++; + } +} - /* -[ END MIME DECODING ]----------------------------------------------------------- */ +/* -[ END MIME DECODING ]----------------------------------------------------------- */ - /** This is the first function called. It decides if this is a multipart - message or if it should be handled as a single entity - **/ - function decodeMime ($imap_stream, &$header) { - global $username, $key, $imapServerAddress, $imapPort; - return mime_structure ($imap_stream, $header); - } - - // 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 "" . $message->header->entity_id . ' : ' . $message->header->type0 . '/' . $message->header->type1 . '
'; - for ($i = 0; $message->entities[$i]; $i++) { - $msg = listEntities($message->entities[$i], $ent_id); - if ($msg) - return $msg; - } - } - } - */ +/* This is the first function called. It decides if this is a multipart + message or if it should be handled as a single entity + */ +function decodeMime ($imap_stream, &$header) { + global $username, $key, $imapServerAddress, $imapPort; + return mime_structure ($imap_stream, $header); +} - // 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)) { +// 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 "" . $message->header->entity_id . ' : ' . $message->header->type0 . '/' . $message->header->type1 . '
'; + for ($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 $message; - } else { + } else { for ($i = 0; isset($message->entities[$i]); $i++) { - $msg = getEntity ($message->entities[$i], $ent_id); - if ($msg) - return $msg; + $msg = getEntity ($message->entities[$i], $ent_id); + if ($msg) { + return $msg; + } } - } - } - } + } + } +} - // 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; - } - - $i = 0; - while ($entity == 0 && isset($message->entities[$i]) ) { - $entity = findDisplayEntity($message->entities[$i], $textOnly); - $i++; - } +/* + * 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; + } + + $i = 0; + while ($entity == 0 && isset($message->entities[$i]) ) { + $entity = findDisplayEntity($message->entities[$i], $textOnly); + $i++; } - - return( $entity ); } + + return( $entity ); +} - // Shows the HTML version - function findDisplayEntityHTML ($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 $entity; - } - return 0; - } +/* Shows the HTML version */ +function findDisplayEntityHTML ($message) { - /** 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 ) { + 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 = strip_tags( $body ); translateText($body, $wrap_at, $body_message->header->charset); } else { $body = MagicHTML( $body, $id ); } - } else { + } else { translateText($body, $wrap_at, $body_message->header->charset); - } + } + + $body .= "
". _("Download this as a file") ."

"; + + /** Display the ATTACHMENTS: message if there's more than one part **/ + $body .= ""; + if (isset($message->entities[0])) { + $body .= formatAttachments ($message, $ent_num, $message->header->mailbox, $id); + } + $body .= ""; + } else { + $body = formatAttachments ($message, -1, $message->header->mailbox, $id); + } + return ($body); +} - $body .= "
". _("Download this as a file") ."

"; +/* + * 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; + + $body .= "\n" . + "
\n" . + _("Attachments") . ':' . + "
\n" . + "\n" . + formatAttachments ($message, $ent_id, $mailbox, $id) . + "
"; + + 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 (trim($filename) == '') { + if (trim($name) == '') { + if ( trim( $message->header->id ) == '' ) + $display_filename = 'untitled-[' . $message->header->entity_id . ']' ; + else + $display_filename = 'cid: ' . $message->header->id; + // $display_filename = 'untitled-[' . $message->header->entity_id . ']' ; + } else { + $display_filename = $name; + $filename = $name; + } + } else { + $display_filename = $filename; + } + + $urlMailbox = urlencode($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); + + $Links = $HookResults[1]; + $DefaultLink = $HookResults[6]; + + $body .= '  ' . + "$display_filename " . + '' . show_readable_size($message->header->size) . + '  ' . + "[ $type0/$type1 ] " . + ''; + if ($message->header->description) + $body .= '' . htmlspecialchars($message->header->description) . ''; + $body .= ' '; + + + $SkipSpaces = 1; + foreach ($Links as $Val) { + if ($SkipSpaces) { + $SkipSpaces = 0; + } else { + $body .= '  |  '; + } + $body .= '' . $Val['text'] . ''; + } - /** Display the ATTACHMENTS: message if there's more than one part **/ - $body .= ""; - if (isset($message->entities[0])) { - $body .= formatAttachments ($message, $ent_num, $message->header->mailbox, $id); - } - $body .= ""; - } else { - $body = formatAttachments ($message, -1, $message->header->mailbox, $id); - } - return ($body); - } - - // 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; - - $body .= "\n" . - "
\n" . - _("Attachments") . ':' . - "
\n" . - "\n" . - formatAttachments ($message, $ent_id, $mailbox, $id) . - "
"; - - return( $body ); - } + unset($Links); - 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 (trim($filename) == '') { - if (trim($name) == '') { - if( trim( $message->header->id ) == '' ) - $display_filename = 'untitled-[' . $message->header->entity_id . ']' ; - else - $display_filename = 'cid: ' . $message->header->id; - // $display_filename = 'untitled-[' . $message->header->entity_id . ']' ; - } else { - $display_filename = $name; - $filename = $name; - } - } else { - $display_filename = $filename; - } + $body .= "
\n"; + } + } else { + for ($i = 0; $i < count($message->entities); $i++) { + $body .= formatAttachments ($message->entities[$i], $ent_id, $mailbox, $id); + } + } + return( $body ); + } +} - $urlMailbox = urlencode($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); - - $Links = $HookResults[1]; - $DefaultLink = $HookResults[6]; - - $body .= '  ' . - "$display_filename " . - '' . show_readable_size($message->header->size) . - '  ' . - "[ $type0/$type1 ] " . - ''; - if ($message->header->description) - $body .= '' . htmlspecialchars($message->header->description) . ''; - $body .= ' '; - - - $SkipSpaces = 1; - foreach ($Links as $Val) { - if ($SkipSpaces) { - $SkipSpaces = 0; - } else { - $body .= '  |  '; - } - $body .= '' . $Val['text'] . ''; - } - unset($Links); +/** this function decodes the body depending on the encoding type. **/ +function decodeBody($body, $encoding) { + $body = str_replace("\r\n", "\n", $body); + $encoding = strtolower($encoding); - $body .= "\n"; - } - } else { - for ($i = 0; $i < count($message->entities); $i++) { - $body .= formatAttachments ($message->entities[$i], $ent_id, $mailbox, $id); - } - } - return( $body ); - } - } + global $show_html_default; + if ($encoding == 'quoted-printable') { + $body = quoted_printable_decode($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; + while (ereg("=\n", $body)) + $body = ereg_replace ("=\n", "", $body); - if ($encoding == 'quoted-printable') { - $body = quoted_printable_decode($body); - - - while (ereg("=\n", $body)) - $body = ereg_replace ("=\n", "", $body); - - } else if ($encoding == 'base64') { - $body = base64_decode($body); - } + } else if ($encoding == 'base64') { + $body = base64_decode($body); + } - // All other encodings are returned raw. - return $body; - } - - - // This functions decode strings that is encoded according to - // RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text). - function decodeHeader ($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); - } - $replace = quoted_printable_decode($replace); - } + // All other encodings are returned raw. + return $body; +} +/* + * This functions decode strings that is encoded according to + * RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text). + */ +function decodeHeader ($string, $utfencode=true) { + if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', + $string, $res)) { + if (ucfirst($res[2]) == 'B') { + $replace = base64_decode($res[3]); + } else { + $replace = str_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); + } + $replace = quoted_printable_decode($replace); + } + /* Only encode into entities by default. Some places + don't need the encoding, like the compose form. */ + if ($utfencode){ $replace = charset_decode ($res[1], $replace); + } - // Remove the name of the character set. - $string = eregi_replace ('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', - $replace, $string); - - // In case there should be more encoding in the string: recurse - return (decodeHeader($string)); - } else - 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; - - // 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) { + // Remove the name of the character set. + $string = eregi_replace ('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', + $replace, $string); + + // In case there should be more encoding in the string: recurse + return (decodeHeader($string)); + } else + 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; + + // 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 '?': + 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 ); +} - 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) - $textcolor = '#000000'; // Foreground style color (defaults to black) - $leftmargin = ''; // Left margin style - $title = ''; // HTML title if any - - $i = 0; - while( $i < $j ) { - if( $body{$i} == '<' ) { - $pos = $i + 1; - $tag = ''; - while ($body{$pos} == ' ' || $body{$pos} == "\t" || - $body{$pos} == "\n") - $pos ++; - while (strlen($tag) < 4 && $body{$pos} != ' ' && - $body{$pos} != "\t" && $body{$pos} != "\n") { - $tag .= $body{$pos}; - $pos ++; - } - 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 .= ""; - break; - // Substitute Title - case 'TITL': - $i += 5; - while( $body{$i} <> '>' && // - $i < $j ) - $i++; +*/ +function MagicHTML( $body, $id ) { + + global $message, $HTTP_SERVER_VARS, + $attachment_common_show_images; + + $attachment_common_show_images = + FALSE; // Don't display attached images in HTML mode + $j = strlen( $body ); // Legnth of the HTML + $ret = ''; // Returned string + $bgcolor = '#ffffff'; // Background style color (defaults to white) + $textcolor = '#000000'; // Foreground style color (defaults to black) + $leftmargin = ''; // Left margin style + $title = ''; // HTML title if any + + $i = 0; + while ( $i < $j ) { + if ( $body{$i} == '<' ) { + $pos = $i + 1; + $tag = ''; + while ($body{$pos} == ' ' || $body{$pos} == "\t" || + $body{$pos} == "\n") { + $pos ++; + } + while (strlen($tag) < 4 && $body{$pos} != ' ' && + $body{$pos} != "\t" && $body{$pos} != "\n") { + $tag .= $body{$pos}; + $pos ++; + } + 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 .= ""; + break; + // Substitute Title + case 'TITL': + $i += 5; + while ( $body{$i} <> '>' && // + $i < $j ) $i++; - $title = ''; - while( $body{$i} <> '<' && // + $i++; + $title = ''; + while ( $body{$i} <> '<' && // + $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} <> '>' && // + $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 ) { - $title .= $body{$i}; + // 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++; } - $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 ) + } else { + // Other style are mantained + $styleblk .= "$style "; + while ( $body{$i} <> '>' && + $body{$i} <> '<' && + $body{$i} <> '}' && + $i < $j ) { + $styleblk .= $body{$i}; $i++; - // $i++; - break; - case 'STYL': + } + $styleblk .= $body{$i}; + } + stripComments( $i, $j, $body ); + if ( $body{$i} <> '>' ) + $i++; + } + if ( $styleblk <> '' ) + $ret .= "