size_t multipart_parser_execute(multipart_parser *p,
const char *buf,
size_t len
)
{
size_t i = 0;
size_t mark = 0;
char c, cl;
int is_last = 0;
while ( i < len )
{
c = buf[i];
is_last = (i == (len - 1) );
switch ( p->state )
{
case s_start:
multipart_log("s_start");
p->index = 0;
p->state = s_start_boundary;
/* fallthrough */
case s_start_boundary:
multipart_log("s_start_boundary");
if ( p->index == p->boundary_length )
{
if ( c != CR )
{
return (i);
}
p->index++;
break;
}
else if ( p->index == (p->boundary_length + 1) )
{
if ( c != LF )
{
return (i);
}
p->index = 0;
NOTIFY_CB(part_data_begin);
p->state = s_header_field_start;
break;
}
if ( c != p->multipart_boundary[p->index] )
{
return (i);
}
p->index++;
break;
case s_header_field_start:
multipart_log("s_header_field_start");
mark = i;
p->state = s_header_field;
/* fallthrough */
case s_header_field:
multipart_log("s_header_field");
if ( c == CR )
{
p->state = s_headers_almost_done;
break;
}
if ( c == ':' )
{
EMIT_DATA_CB(header_field, buf + mark, i - mark);
p->state = s_header_value_start;
break;
}
cl = tolower(c);
if ( (c != '-') && ( (cl < 'a') || (cl > 'z') ) )
{
multipart_log("invalid character in header name");
return (i);
}
if ( is_last )
{
EMIT_DATA_CB(header_field, buf + mark, (i - mark) + 1);
}
break;
case s_headers_almost_done:
multipart_log("s_headers_almost_done");
if ( c != LF )
{
return (i);
}
p->state = s_part_data_start;
break;
case s_header_value_start:
multipart_log("s_header_value_start");
if ( c == ' ' )
{
break;
}
mark = i;
p->state = s_header_value;
/* fallthrough */
case s_header_value:
multipart_log("s_header_value");
if ( c == CR )
{
EMIT_DATA_CB(header_value, buf + mark, i - mark);
p->state = s_header_value_almost_done;
break;
}
if ( is_last )
{
EMIT_DATA_CB(header_value, buf + mark, (i - mark) + 1);
}
break;
case s_header_value_almost_done:
multipart_log("s_header_value_almost_done");
if ( c != LF )
{
return (i);
}
p->state = s_header_field_start;
break;
case s_part_data_start:
multipart_log("s_part_data_start");
NOTIFY_CB(headers_complete);
mark = i;
p->state = s_part_data;
/* fallthrough */
case s_part_data:
multipart_log("s_part_data");
if ( c == CR )
{
EMIT_DATA_CB(part_data, buf + mark, i - mark);
mark = i;
p->state = s_part_data_almost_boundary;
p->lookbehind[0] = CR;
break;
}
if ( is_last )
{
EMIT_DATA_CB(part_data, buf + mark, (i - mark) + 1);
}
break;
case s_part_data_almost_boundary:
multipart_log("s_part_data_almost_boundary");
if ( c == LF )
{
p->state = s_part_data_boundary;
p->lookbehind[1] = LF;
p->index = 0;
break;
}
EMIT_DATA_CB(part_data, p->lookbehind, 1);
p->state = s_part_data;
mark = i--;
break;
case s_part_data_boundary:
multipart_log("s_part_data_boundary");
if ( p->multipart_boundary[p->index] != c )
{
EMIT_DATA_CB(part_data, p->lookbehind, 2 + p->index);
p->state = s_part_data;
mark = i--;
break;
}
p->lookbehind[2 + p->index] = c;
if ( (++p->index) == p->boundary_length )
{
NOTIFY_CB(part_data_end);
p->state = s_part_data_almost_end;
}
break;
case s_part_data_almost_end:
multipart_log("s_part_data_almost_end");
if ( c == '-' )
{
p->state = s_part_data_final_hyphen;
break;
}
if ( c == CR )
{
p->state = s_part_data_end;
break;
}
return (i);
case s_part_data_final_hyphen:
multipart_log("s_part_data_final_hyphen");
if ( c == '-' )
{
NOTIFY_CB(body_end);
p->state = s_end;
break;
}
return (i);
case s_part_data_end:
multipart_log("s_part_data_end");
if ( c == LF )
{
p->state = s_header_field_start;
NOTIFY_CB(part_data_begin);
break;
}
return (i);
case s_end:
multipart_log("s_end: %02X", (int) c);
break;
default:
multipart_log("Multipart parser unrecoverable error");
return (0);
}
++i;
}
return (len);
}
size_t multipart_parser_c_execute(multipart_parser_c* p, const multipart_parser_c_settings* settings, const char *buf, size_t len) {
size_t i = 0;
size_t mark = 0;
char c, cl;
int is_last = 0;
while(i < len) {
c = buf[i];
is_last = (i == (len - 1));
switch (p->state) {
case s_start:
multipart_log("s_start");
p->index = 0;
NOTIFY_CB(message_begin);
p->state = s_start_boundary;
/* fallthrough */
case s_start_boundary:
multipart_log("s_start_boundary");
if (p->index == p->boundary_length) {
if (c != CR) {
return i;
}
p->index++;
break;
} else if (p->index == (p->boundary_length + 1)) {
if (c != LF) {
return i;
}
p->index = 0;
NOTIFY_CB(part_begin);
p->state = s_header_field_start;
break;
}
/* if starting boundaru doesn't match, assume we are reading the preamble */
if (c != p->multipart_boundary[p->index]) {
p->index = 0;
if (c == CR) { /* smallest preable is CR LF */
p->state = s_preamble_almost_boundary;
} else {
p->state = s_preamble;
}
break;
}
p->index++;
break;
case s_preamble:
if (c == CR) {
p->state = s_preamble_almost_boundary;
}
break;
case s_preamble_almost_boundary:
if(c == LF) {
p->state = s_start_boundary;
} else {
p->state = s_preamble;
}
break;
case s_header_field_start:
multipart_log("s_header_field_start");
mark = i;
p->state = s_header_field;
/* fallthrough */
case s_header_field:
multipart_log("s_header_field");
if (c == CR) {
p->state = s_headers_almost_done;
break;
}
if (c == ':') {
EMIT_DATA_CB(header_field, buf + mark, i - mark);
p->state = s_header_value_start;
break;
}
cl = tolower(c);
if ((c != '-') && (cl < 'a' || cl > 'z')) {
multipart_log("invalid character in header name");
return i;
}
if (is_last)
EMIT_DATA_CB(header_field, buf + mark, (i - mark) + 1);
break;
case s_headers_almost_done:
multipart_log("s_headers_almost_done");
if (c != LF) {
return i;
}
p->state = s_part_data_start;
break;
case s_header_value_start:
multipart_log("s_header_value_start");
if (c == ' ') {
break;
}
mark = i;
p->state = s_header_value;
/* fallthrough */
case s_header_value:
multipart_log("s_header_value");
if (c == CR) {
EMIT_DATA_CB(header_value, buf + mark, i - mark);
p->state = s_header_value_almost_done;
break;
}
if (is_last)
EMIT_DATA_CB(header_value, buf + mark, (i - mark) + 1);
break;
case s_header_value_almost_done:
multipart_log("s_header_value_almost_done");
if (c != LF) {
return i;
}
p->state = s_header_field_start;
break;
case s_part_data_start:
multipart_log("s_part_data_start");
NOTIFY_CB(headers_complete);
mark = i;
p->state = s_part_data;
/* fallthrough */
case s_part_data:
multipart_log("s_part_data");
if (c == CR) {
EMIT_DATA_CB(part_data, buf + mark, i - mark);
mark = i;
p->state = s_part_data_almost_boundary;
p->lookbehind[0] = CR;
break;
}
if (is_last)
EMIT_DATA_CB(part_data, buf + mark, (i - mark) + 1);
break;
case s_part_data_almost_boundary:
multipart_log("s_part_data_almost_boundary");
if (c == LF) {
p->state = s_part_data_boundary;
p->lookbehind[1] = LF;
p->index = 0;
break;
}
EMIT_DATA_CB(part_data, p->lookbehind, 1);
p->state = s_part_data;
mark = i --;
break;
case s_part_data_boundary:
multipart_log("s_part_data_boundary");
if (p->multipart_boundary[p->index] != c) {
EMIT_DATA_CB(part_data, p->lookbehind, 2 + p->index);
p->state = s_part_data;
mark = i --;
break;
}
p->lookbehind[2 + p->index] = c;
if ((++ p->index) == p->boundary_length) {
NOTIFY_CB(part_complete);
p->state = s_part_data_almost_end;
}
break;
case s_part_data_almost_end:
multipart_log("s_part_data_almost_end");
if (c == '-') {
p->state = s_part_data_final_hyphen;
break;
}
if (c == CR) {
p->state = s_part_complete;
break;
}
return i;
case s_part_data_final_hyphen:
multipart_log("s_part_data_final_hyphen");
if (c == '-') {
NOTIFY_CB(message_complete);
p->state = s_end;
break;
}
return i;
case s_part_complete:
multipart_log("s_part_complete");
if (c == LF) {
p->state = s_header_field_start;
NOTIFY_CB(part_begin);
break;
}
return i;
case s_end:
multipart_log("s_end: %02X", (int) c);
break;
default:
multipart_log("Multipart parser unrecoverable error");
return 0;
}
++ i;
}
return len;
}
size_t multipart_parser_execute(multipart_parser* p, const char *buf, size_t len) {
size_t i = 0;
size_t mark = 0;
char c, cl;
int is_last = 0;
while(i < len) {
c = buf[i];
is_last = (i == (len - 1));
switch (p->state) {
case s_start:
multipart_log("s_start");
p->index = 0;
p->state = s_start_boundary;
/* fallthrough */
case s_start_boundary:
multipart_log("s_start_boundary");
if (p->index == p->boundary_length) {
if (c != CR) {
return i;
}
p->index++;
break;
}
// encapsulation boundary→CRと来たので、LFがくる筈。
else if (p->index == (p->boundary_length + 1)) {
if (c != LF) {
return i;
}
p->index = 0;
NOTIFY_CB(part_data_begin);
p->state = s_header_field_start;
break;
}
// FIXME: http://www.w3.org/Protocols/rfc1341/7_2_Multipart.html の
// 7.2.1の引用：
// The Content-Type field for multipart entities requires one parameter,
// "boundary", which is used to specify the encapsulation boundary. The
// encapsulation boundary is defined as a line consisting entirely of
// two hyphen characters ("-", decimal code 45) followed by the boundary
// parameter value from the Content-Type header field.
//
// 「encapsulating boundary」と「boundary parameter value」は別物；なので、
// p->multipart_boundaryつまりは「boundary parameter value」との一致
// とは別に2つのハイフンとの一致を探さなければならない。
if (c != p->multipart_boundary[p->index]) {
return i;
}
p->index++;
break;
case s_header_field_start:
multipart_log("s_header_field_start");
mark = i;
p->state = s_header_field;
/* fallthrough */
case s_header_field:
multipart_log("s_header_field");
if (c == CR) {
p->state = s_headers_almost_done;
break;
}
if (c == '-') {
break;
}
if (c == ':') {
EMIT_DATA_CB(header_field, buf + mark, i - mark);
p->state = s_header_value_start;
break;
}
cl = tolower(c);
if (cl < 'a' || cl > 'z') {
multipart_log("invalid character in header name");
return i;
}
if (is_last)
EMIT_DATA_CB(header_field, buf + mark, (i - mark) + 1);
break;
case s_headers_almost_done:
multipart_log("s_headers_almost_done");
if (c != LF) {
return i;
}
p->state = s_part_data_start;
break;
case s_header_value_start:
multipart_log("s_header_value_start");
if (c == ' ') {
break;
}
mark = i;
p->state = s_header_value;
/* fallthrough */
case s_header_value:
multipart_log("s_header_value");
if (c == CR) {
EMIT_DATA_CB(header_value, buf + mark, i - mark);
p->state = s_header_value_almost_done;
}
if (is_last)
EMIT_DATA_CB(header_value, buf + mark, (i - mark) + 1);
break;
case s_header_value_almost_done:
multipart_log("s_header_value_almost_done");
if (c != LF) {
return i;
}
p->state = s_header_field_start;
break;
case s_part_data_start:
multipart_log("s_part_data_start");
NOTIFY_CB(headers_complete);
mark = i;
p->state = s_part_data;
/* fallthrough */
case s_part_data:
multipart_log("s_part_data");
if (c == CR) {
EMIT_DATA_CB(part_data, buf + mark, i - mark);
mark = i;
p->state = s_part_data_almost_boundary;
p->lookbehind[0] = CR;
break;
}
if (is_last)
EMIT_DATA_CB(part_data, buf + mark, (i - mark) + 1);
break;
case s_part_data_almost_boundary:
multipart_log("s_part_data_almost_boundary");
if (c == LF) {
p->state = s_part_data_boundary;
p->lookbehind[1] = LF;
p->index = 0;
break;
}
EMIT_DATA_CB(part_data, p->lookbehind, 1);
p->state = s_part_data;
mark = i --;
break;
case s_part_data_boundary:
multipart_log("s_part_data_boundary");
if (p->multipart_boundary[p->index] != c) {
EMIT_DATA_CB(part_data, p->lookbehind, 2 + p->index);
p->state = s_part_data;
mark = i --;
break;
}
p->lookbehind[2 + p->index] = c;
if ((++ p->index) == p->boundary_length) {
NOTIFY_CB(part_data_end);
p->state = s_part_data_almost_end;
}
break;
case s_part_data_almost_end:
multipart_log("s_part_data_almost_end");
if (c == '-') {
p->state = s_part_data_final_hyphen;
break;
}
if (c == CR) {
p->state = s_part_data_end;
break;
}
return i;
case s_part_data_final_hyphen:
multipart_log("s_part_data_final_hyphen");
if (c == '-') {
NOTIFY_CB(body_end);
p->state = s_end;
break;
}
return i;
case s_part_data_end:
multipart_log("s_part_data_end");
if (c == LF) {
p->state = s_header_field_start;
NOTIFY_CB(part_data_begin);
break;
}
return i;
case s_end:
multipart_log("s_end: %02X", (int) c);
break;
default:
multipart_log("Multipart parser unrecoverable error");
return 0;
}
++ i;
}
return len;
}
//Returns number of bytes parsed
size_t multipart_parser_execute(multipart_parser* p, const char *buf, size_t len) {
size_t i = 0;
size_t mark = 0;
char c;
int is_last = 0;
while(!is_last) {
c = buf[i];
is_last = (i == (len - 1));
switch (p->state) {
case s_start:
multipart_log("s_start");
p->index = 0;
p->state = s_start_boundary;
/* fallthrough */
case s_start_boundary:
multipart_log("s_start_boundary");
//Check to see if one past the end of the boundary
if (p->index == p->boundary_length) {
//If not properly terminated, then return immediately
if (c != CR) {
return i;
}
p->index++;
break;
} else if (p->index == (p->boundary_length + 1)) {
if (c != LF) {
return i;
}
p->index = 0;
NOTIFY_CB(part_data_begin);
p->state = s_header_field_start;
break;
}
if (c != p->multipart_boundary[p->index]) {
return i;
}
p->index++;
break;
case s_header_field_start:
multipart_log("s_header_field_start");
mark = i;
p->state = s_header_field;
/* fallthrough */
case s_header_field:
multipart_log("s_header_field");
if (c == CR) {
p->state = s_headers_almost_done;
break;
}
if (c == '-') {
if(is_last)
{
EMIT_DATA_CB(header_field,buf + mark, (i - mark) +1 );
}
break;
}
if (c == ':') {
EMIT_DATA_CB(header_field, buf + mark, i - mark);
p->state = s_header_value_start;
break;
}
if (not isalpha(c) ) {
multipart_log("invalid character in header name");
return i;
}
if (is_last)
{
EMIT_DATA_CB(header_field, buf + mark, (i - mark) + 1);
}
break;
case s_headers_almost_done:
multipart_log("s_headers_almost_done");
if (c != LF) {
return i;
}
p->state = s_part_data_start;
break;
case s_header_value_start:
multipart_log("s_header_value_start");
if (c == ' ') {
break;
}
mark = i;
p->state = s_header_value;
/* fallthrough */
case s_header_value:
multipart_log("s_header_value");
if (c == CR) {
EMIT_DATA_CB(header_value, buf + mark, i - mark);
p->state = s_header_value_almost_done;
}
if (is_last)
{
EMIT_DATA_CB(header_value, buf + mark, (i - mark) + 1);
}
break;
case s_header_value_almost_done:
multipart_log("s_header_value_almost_done");
if (c != LF) {
return i;
}
NOTIFY_CB(header_value_end);
p->state = s_header_field_start;
break;
case s_part_data_start:
multipart_log("s_part_data_start");
NOTIFY_CB(headers_complete);
mark = i;
p->state = s_part_data;
/* fallthrough */
case s_part_data:
multipart_log("s_part_data");
if (c == CR) {
EMIT_DATA_CB(part_data, buf + mark, i - mark);
mark = i;
p->state = s_part_data_almost_boundary;
p->lookbehind[0] = CR;
break;
}
if (is_last)
EMIT_DATA_CB(part_data, buf + mark, (i - mark) + 1);
break;
case s_part_data_almost_boundary:
multipart_log("s_part_data_almost_boundary");
if (c == LF) {
p->state = s_part_data_boundary;
p->lookbehind[1] = LF;
p->index = 0;
break;
}
EMIT_DATA_CB(part_data, p->lookbehind, 1);
p->state = s_part_data;
mark = i --;
break;
case s_part_data_boundary:
multipart_log("s_part_data_boundary");
if (p->multipart_boundary[p->index] != c) {
EMIT_DATA_CB(part_data, p->lookbehind, 2 + p->index);
p->state = s_part_data;
mark = i --;
break;
}
p->lookbehind[2 + p->index] = c;
if ((++ p->index) == p->boundary_length) {
NOTIFY_CB(part_data_end);
p->state = s_part_data_almost_end;
}
break;
case s_part_data_almost_end:
multipart_log("s_part_data_almost_end");
if (c == '-') {
p->state = s_part_data_final_hyphen;
break;
}
if (c == CR) {
p->state = s_part_data_end;
break;
}
return i;
case s_part_data_final_hyphen:
multipart_log("s_part_data_final_hyphen");
if (c == '-') {
NOTIFY_CB(body_end);
p->state = s_end;
break;
}
return i;
case s_part_data_end:
multipart_log("s_part_data_end");
if (c == LF) {
p->state = s_header_field_start;
NOTIFY_CB(part_data_begin);
break;
}
return i;
case s_end:
multipart_log("s_end: %02X", (int) c);
break;
default:
multipart_log("Multipart parser unrecoverable error");
return 0;
}
++ i;
}
return len;
}
