int MailMessage::parseHeaders(StringBuffer &rfcHeaders) {
ArrayList lines;
const StringBuffer *line;
StringBuffer strReceived;
bool receivedExtracted = false;
LOG.debug("parseHeaders START");
// Join header parts using \t or 8 blank
StringBuffer joinlinetab("\t");
rfcHeaders.replaceAll(joinlinetab, " ");
StringBuffer joinlinespaces(newline);
joinlinespaces+=" "; // 8 blanks
rfcHeaders.replaceAll(joinlinespaces, " ");
rfcHeaders.split(lines, newline);
// importance is set to "0" by default. Then there isn't anything modification
// in the header, at the end of the loop the importance will be set to "3", default normal
importance = "0";
for ( line=(StringBuffer *)lines.front();
line;
line=(StringBuffer *)lines.next() ) {
if( *line == "\r" )
break;
// The first empty line marks the end of the header section
if( line->empty() ){
break;
}
// Process the headers
if( line->ifind(TO) == 0 ){
to = MailMessage::decodeHeader(line->substr(TO_LEN));
}
else if( line->ifind(FROM) == 0 ) {
from = MailMessage::decodeHeader(line->substr(FROM_LEN));
}
else if( line->ifind(CC) == 0 ) {
cc = MailMessage::decodeHeader(line->substr(CC_LEN));
}
else if( line->ifind(BCC) == 0 ) {
bcc = MailMessage::decodeHeader(line->substr(BCC_LEN));
}
else if ( line->ifind(DATE) == 0 ) {
//subjectParsing = false;
if( date.parseRfc822(line->substr(DATE_LEN)) ) {
LOG.error("Error parsing date");
return 500;
}
}
else if( line->ifind(SUBJECT) == 0 ) {
subject = MailMessage::decodeHeader(line->substr(SUBJECT_LEN));
LOG.debug("SUBJECT: %s", subject.c_str());
}
else if( line->ifind(ENCODING) == 0 ) { // it is here for single part only
body.setEncoding(line->substr(ENCODING_LEN));
}
else if(line->ifind(MIMEVERS) == 0 ) {
mimeVersion = line->substr(MIMEVERS_LEN);
}
else if(line->ifind(MESSAGEID) == 0 ) {
messageId = line->substr(MESSAGEID_LEN);
}
else if(line->ifind(IMPORTANCE) == 0 ) {
StringBuffer data = line->substr(IMPORTANCE_LEN);
data.lowerCase();
importance = convertImportance(data);
}
else if(line->ifind(X_PRIORITY) == 0 ) {
if (importance == "0") {
StringBuffer data = line->substr(X_PRIORITY_LEN);
data.lowerCase();
importance = convertXPriority(data);
}
}
else if( line->ifind(MIMETYPE) == 0 ) {
StringBuffer sb = getTokenValue(line, MIMETYPE);
if (sb.length() > 0)
contentType = sb;
sb.reset();
sb = getTokenValue(line, "boundary=", false);
if (sb.length() > 0) {
boundary = sb;
} else {
body.setCharset(getTokenValue(line, CT_CHARSET));
}
/*
size_t len = line->find(";") - MIMETYPE_LEN ;
contentType = line->substr(MIMETYPE_LEN, len);
// Save boundary for multipart
size_t begin = line->ifind("boundary=");
size_t end = StringBuffer::npos;
if( begin != StringBuffer::npos ) {
begin += strlen("boundary=\"");
end = line->find("\"", begin) ;
boundary = line->substr( begin, end-begin );
}
else {
begin=line->ifind(CT_CHARSET);
if( begin != StringBuffer::npos ) {
begin += strlen(CT_CHARSET);
size_t end = begin;
size_t quote = line->find("\"", begin);
if (quote != StringBuffer::npos){
begin = quote + 1;
end = line->find("\"", begin) ;
}
else {
end = line->find(";", begin) ;
if (end == StringBuffer::npos) {
end = line->find(" ", begin);
}
}
body.setCharset( line->substr( begin, end-begin ) );
}
}
*/
}
else if(line->ifind(RECEIVED) == 0) {
if (!receivedExtracted) {
strReceived = line->substr(line->rfind(";") );
if (!strReceived.empty()) {
received.parseRfc822(strReceived.substr(2));
receivedExtracted = true;
}
/*
while (!strReceived.empty()) {
if (received.parseRfc822(strReceived.substr(2)) == 0) {
receivedExtracted = true;
break;
} else {
StringBuffer s(line->substr(line->rfind(strReceived.c_str())));
strReceived = line->substr(s.rfind(";"));
}
}
*/
}
}
else {
headers.add(*(StringBuffer *)line);
}
}
// If received was not found, copy send date
if( received == BasicTime() ){
received = date;
}
// if the importance is never set we put the importance to 3, normal
if (importance == "0") {
importance = "3";
}
LOG.debug("parseHeaders END");
// FIXME: should check for mandatory headers before return 0
return 0;
}
// Return true if the instance is empty (a valid MailMessage must have a valid date that is not
// the default 1/1/1970)
bool MailMessage::empty() {
return ( this->getDate() == BasicTime() );
}
/**
* Parse the date in RF 822 format
*
* Some examples:
* Date: Fri, 01 Aug 2003 14:04:55 +0800
* Date: Wed, 30 Jul 2003 13:24:21 -0700
* Date: 20 Jun 2003 15:42:12 -0500
*
* RFC822 date time
*
* date-time = [ day "," ] date time ; dd mm yy
* ; hh:mm:ss zzz
*
* day = "Mon" / "Tue" / "Wed" / "Thu"
* / "Fri" / "Sat" / "Sun"
*
* date = 1*2DIGIT month 2DIGIT ; day month year
* ; e.g. 20 Jun 82
*
* month = "Jan" / "Feb" / "Mar" / "Apr"
* / "May" / "Jun" / "Jul" / "Aug"
* / "Sep" / "Oct" / "Nov" / "Dec"
*
* time = hour zone ; ANSI and Military
*
* hour = 2DIGIT ":" 2DIGIT [":" 2DIGIT]
* ; 00:00:00 - 23:59:59
*
* zone = "UT" / "GMT" ; Universal Time
* ; North American : UT
* / "EST" / "EDT" ; Eastern: - 5/ - 4
* / "CST" / "CDT" ; Central: - 6/ - 5
* / "MST" / "MDT" ; Mountain: - 7/ - 6
* / "PST" / "PDT" ; Pacific: - 8/ - 7
* / 1ALPHA ; Military: Z = UT;
* ; A:-1; (J not used)
* ; M:-12; N:+1; Y:+12
* / ( ("+" / "-") 4DIGIT ) ; Local differential
* ; hours+min. (HHMM)
**/
int BasicTime::parseRfc822(const char *date)
{
int ret = 0;
if (!isADate(date)) {
return -1;
}
const char *days[] = {
"Sun", "Mon", "Tue", "Wed",
"Thu", "Fri", "Sat"
};
const char *months[] = {
"Jan", "Feb", "Mar", "Apr",
"May", "Jun", "Jul", "Aug",
"Sep", "Oct", "Nov", "Dec"
};
// In some cases the day of week may initially contain the day,dayofmonth,
// so its max length is 3+1+2
char dayOfWeek[7] = "---,";
char mon[4] = "---";
char time[10] = "00:00:00";
char timeZone[20] = "GMT";
// Wed Feb 01 14:40:45 Europe/Amsterdam 2006
// do we have day of week?
const char *pdate = strstr( date, "," );
if ( pdate == 0 ) {
ret=sscanf(date, "%d %s %d %s %s",
&day, mon, &year, time, timeZone);
}
else {
ret=sscanf(date, "%s %d %s %d %s %s",
dayOfWeek, &day, mon, &year, time, timeZone);
if (ret >= 1 && ret < 6) {
// it can be an error in the format: Mon,12 Feb 2007 09:00:01 +0100
// the comma is attached to the day
if (*(pdate + 1) != ' ') {
ret = sscanf(pdate + 1, "%d %s %d %s %s",
&day, mon, &year, time, timeZone);
}
}
// Convert day of week
for (int i = 0; i < 7; i++) {
if ( strncmp(days[i], dayOfWeek, 3) == 0 ) {
weekday = i;
break;
}
}
// Do not exit on error on weekday, treat it like if it was
// not present.
}
// Trap parsing error
if(ret == EOF || ret == 0){
return -1;
}
// Check validity
if (year > 3000 || day < 0 || day > 31){
*this = BasicTime();
return -1;
}
// Get month
int i;
for (i = 0; i < 12; i++) {
if ( strcmp(months[i], mon) == 0 ) {
month = i+1;
break;
}
}
// Trap parsing error
if (i==13) {
return -1;
}
// Year ---------------------------------
if (year <= 60) {
year += 2000;
} else if (year > 60 && year < 100) {
year += 1900;
}
// hh:mm:ss -------------------------
// do we have sec?
if (strlen(time) > 6 && time[5] == ':')
sscanf(time, "%d:%d:%d", &hour, &min, &sec);
else
sscanf(time, "%d:%d", &hour, &min);
// Timezone ---------------------------------
if ( strcmp(timeZone, "GMT") != 0 && strcmp(timeZone, "UT") != 0) {
// is this explicit time?
if ( timeZone[0] == '+' || timeZone[0]== '-' ) {
char wcH[4] = "+00";
char wcM[4] = "00";
// get hour
if ( strlen(timeZone) > 3) {
wcH[0] = timeZone[0];
wcH[1] = timeZone[1];
wcH[2] = timeZone[2];
wcH[3] = '\0';
}
// get min
if ( strlen(timeZone) >= 5) {
wcM[0] = timeZone[3];
wcM[1] = timeZone[4];
wcM[2] = '\0';
}
tzHour = atoi(wcH);
tzMin = atoi(wcM);
}
// otherwise it could be one string with the time
else if ( strcmp(timeZone, "EDT") == 0) {
tzHour = -4;
}
else if ( strcmp(timeZone, "EST") == 0
|| strcmp(timeZone, "CDT") == 0) {
tzHour = -5;
}
else if ( strcmp(timeZone, "CST") == 0
|| strcmp(timeZone, "MDT") == 0) {
tzHour = -6;
}
else if ( strcmp(timeZone, "MST") == 0
|| strcmp(timeZone, "PDT") == 0 ){
tzHour = -7;
}
else if ( strcmp(timeZone, "PST") == 0) {
tzHour = -8;
}
}
// clean up
return 0;
}
