blob: be750edd08404db91c8193c645f785c9ae90f03b [file] [log] [blame] [raw]
/*
* Copyright (C) Igor Sysoev
* Copyright (C) Nginx, Inc.
*/
#include <ngx_config.h>
#include <ngx_core.h>
#include <ngx_http.h>
static uint32_t usual[] = {
0xffffdbfe, /* 1111 1111 1111 1111 1101 1011 1111 1110 */
/* ?>=< ;:98 7654 3210 /.-, +*)( '&%$ #"! */
0x7fff37d6, /* 0111 1111 1111 1111 0011 0111 1101 0110 */
/* _^]\ [ZYX WVUT SRQP ONML KJIH GFED CBA@ */
#if (NGX_WIN32)
0xefffffff, /* 1110 1111 1111 1111 1111 1111 1111 1111 */
#else
0xffffffff, /* 1111 1111 1111 1111 1111 1111 1111 1111 */
#endif
/* ~}| {zyx wvut srqp onml kjih gfed cba` */
0xffffffff, /* 1111 1111 1111 1111 1111 1111 1111 1111 */
0xffffffff, /* 1111 1111 1111 1111 1111 1111 1111 1111 */
0xffffffff, /* 1111 1111 1111 1111 1111 1111 1111 1111 */
0xffffffff, /* 1111 1111 1111 1111 1111 1111 1111 1111 */
0xffffffff /* 1111 1111 1111 1111 1111 1111 1111 1111 */
};
#if (NGX_HAVE_LITTLE_ENDIAN && NGX_HAVE_NONALIGNED)
#define ngx_str3_cmp(m, c0, c1, c2, c3) \
*(uint32_t *) m == ((c3 << 24) | (c2 << 16) | (c1 << 8) | c0)
#define ngx_str3Ocmp(m, c0, c1, c2, c3) \
*(uint32_t *) m == ((c3 << 24) | (c2 << 16) | (c1 << 8) | c0)
#define ngx_str4cmp(m, c0, c1, c2, c3) \
*(uint32_t *) m == ((c3 << 24) | (c2 << 16) | (c1 << 8) | c0)
#define ngx_str5cmp(m, c0, c1, c2, c3, c4) \
*(uint32_t *) m == ((c3 << 24) | (c2 << 16) | (c1 << 8) | c0) \
&& m[4] == c4
#define ngx_str6cmp(m, c0, c1, c2, c3, c4, c5) \
*(uint32_t *) m == ((c3 << 24) | (c2 << 16) | (c1 << 8) | c0) \
&& (((uint32_t *) m)[1] & 0xffff) == ((c5 << 8) | c4)
#define ngx_str7_cmp(m, c0, c1, c2, c3, c4, c5, c6, c7) \
*(uint32_t *) m == ((c3 << 24) | (c2 << 16) | (c1 << 8) | c0) \
&& ((uint32_t *) m)[1] == ((c7 << 24) | (c6 << 16) | (c5 << 8) | c4)
#define ngx_str8cmp(m, c0, c1, c2, c3, c4, c5, c6, c7) \
*(uint32_t *) m == ((c3 << 24) | (c2 << 16) | (c1 << 8) | c0) \
&& ((uint32_t *) m)[1] == ((c7 << 24) | (c6 << 16) | (c5 << 8) | c4)
#define ngx_str9cmp(m, c0, c1, c2, c3, c4, c5, c6, c7, c8) \
*(uint32_t *) m == ((c3 << 24) | (c2 << 16) | (c1 << 8) | c0) \
&& ((uint32_t *) m)[1] == ((c7 << 24) | (c6 << 16) | (c5 << 8) | c4) \
&& m[8] == c8
#else /* !(NGX_HAVE_LITTLE_ENDIAN && NGX_HAVE_NONALIGNED) */
#define ngx_str3_cmp(m, c0, c1, c2, c3) \
m[0] == c0 && m[1] == c1 && m[2] == c2
#define ngx_str3Ocmp(m, c0, c1, c2, c3) \
m[0] == c0 && m[2] == c2 && m[3] == c3
#define ngx_str4cmp(m, c0, c1, c2, c3) \
m[0] == c0 && m[1] == c1 && m[2] == c2 && m[3] == c3
#define ngx_str5cmp(m, c0, c1, c2, c3, c4) \
m[0] == c0 && m[1] == c1 && m[2] == c2 && m[3] == c3 && m[4] == c4
#define ngx_str6cmp(m, c0, c1, c2, c3, c4, c5) \
m[0] == c0 && m[1] == c1 && m[2] == c2 && m[3] == c3 \
&& m[4] == c4 && m[5] == c5
#define ngx_str7_cmp(m, c0, c1, c2, c3, c4, c5, c6, c7) \
m[0] == c0 && m[1] == c1 && m[2] == c2 && m[3] == c3 \
&& m[4] == c4 && m[5] == c5 && m[6] == c6
#define ngx_str8cmp(m, c0, c1, c2, c3, c4, c5, c6, c7) \
m[0] == c0 && m[1] == c1 && m[2] == c2 && m[3] == c3 \
&& m[4] == c4 && m[5] == c5 && m[6] == c6 && m[7] == c7
#define ngx_str9cmp(m, c0, c1, c2, c3, c4, c5, c6, c7, c8) \
m[0] == c0 && m[1] == c1 && m[2] == c2 && m[3] == c3 \
&& m[4] == c4 && m[5] == c5 && m[6] == c6 && m[7] == c7 && m[8] == c8
#endif
/* gcc, icc, msvc and others compile these switches as an jump table */
ngx_int_t
ngx_http_parse_request_line(ngx_http_request_t *r, ngx_buf_t *b)
{
u_char c, ch, *p, *m;
enum {
sw_start = 0,
sw_method,
sw_spaces_before_uri,
sw_schema,
sw_schema_slash,
sw_schema_slash_slash,
sw_host_start,
sw_host,
sw_host_end,
sw_host_ip_literal,
sw_port,
sw_host_http_09,
sw_after_slash_in_uri,
sw_check_uri,
sw_check_uri_http_09,
sw_uri,
sw_http_09,
sw_http_H,
sw_http_HT,
sw_http_HTT,
sw_http_HTTP,
sw_first_major_digit,
sw_major_digit,
sw_first_minor_digit,
sw_minor_digit,
sw_spaces_after_digit,
sw_almost_done
} state;
state = r->state;
for (p = b->pos; p < b->last; p++) {
ch = *p;
switch (state) {
/* HTTP methods: GET, HEAD, POST */
case sw_start:
r->request_start = p;
if (ch == CR || ch == LF) {
break;
}
if ((ch < 'A' || ch > 'Z') && ch != '_') {
return NGX_HTTP_PARSE_INVALID_METHOD;
}
state = sw_method;
break;
case sw_method:
if (ch == ' ') {
r->method_end = p - 1;
m = r->request_start;
switch (p - m) {
case 3:
if (ngx_str3_cmp(m, 'G', 'E', 'T', ' ')) {
r->method = NGX_HTTP_GET;
break;
}
if (ngx_str3_cmp(m, 'P', 'U', 'T', ' ')) {
r->method = NGX_HTTP_PUT;
break;
}
break;
case 4:
if (m[1] == 'O') {
if (ngx_str3Ocmp(m, 'P', 'O', 'S', 'T')) {
r->method = NGX_HTTP_POST;
break;
}
if (ngx_str3Ocmp(m, 'C', 'O', 'P', 'Y')) {
r->method = NGX_HTTP_COPY;
break;
}
if (ngx_str3Ocmp(m, 'M', 'O', 'V', 'E')) {
r->method = NGX_HTTP_MOVE;
break;
}
if (ngx_str3Ocmp(m, 'L', 'O', 'C', 'K')) {
r->method = NGX_HTTP_LOCK;
break;
}
} else {
if (ngx_str4cmp(m, 'H', 'E', 'A', 'D')) {
r->method = NGX_HTTP_HEAD;
break;
}
}
break;
case 5:
if (ngx_str5cmp(m, 'M', 'K', 'C', 'O', 'L')) {
r->method = NGX_HTTP_MKCOL;
}
if (ngx_str5cmp(m, 'P', 'A', 'T', 'C', 'H')) {
r->method = NGX_HTTP_PATCH;
}
if (ngx_str5cmp(m, 'T', 'R', 'A', 'C', 'E')) {
r->method = NGX_HTTP_TRACE;
}
break;
case 6:
if (ngx_str6cmp(m, 'D', 'E', 'L', 'E', 'T', 'E')) {
r->method = NGX_HTTP_DELETE;
break;
}
if (ngx_str6cmp(m, 'U', 'N', 'L', 'O', 'C', 'K')) {
r->method = NGX_HTTP_UNLOCK;
break;
}
break;
case 7:
if (ngx_str7_cmp(m, 'O', 'P', 'T', 'I', 'O', 'N', 'S', ' '))
{
r->method = NGX_HTTP_OPTIONS;
}
break;
case 8:
if (ngx_str8cmp(m, 'P', 'R', 'O', 'P', 'F', 'I', 'N', 'D'))
{
r->method = NGX_HTTP_PROPFIND;
}
break;
case 9:
if (ngx_str9cmp(m,
'P', 'R', 'O', 'P', 'P', 'A', 'T', 'C', 'H'))
{
r->method = NGX_HTTP_PROPPATCH;
}
break;
}
state = sw_spaces_before_uri;
break;
}
if ((ch < 'A' || ch > 'Z') && ch != '_') {
return NGX_HTTP_PARSE_INVALID_METHOD;
}
break;
/* space* before URI */
case sw_spaces_before_uri:
if (ch == '/') {
r->uri_start = p;
state = sw_after_slash_in_uri;
break;
}
c = (u_char) (ch | 0x20);
if (c >= 'a' && c <= 'z') {
r->schema_start = p;
state = sw_schema;
break;
}
switch (ch) {
case ' ':
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
case sw_schema:
c = (u_char) (ch | 0x20);
if (c >= 'a' && c <= 'z') {
break;
}
switch (ch) {
case ':':
r->schema_end = p;
state = sw_schema_slash;
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
case sw_schema_slash:
switch (ch) {
case '/':
state = sw_schema_slash_slash;
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
case sw_schema_slash_slash:
switch (ch) {
case '/':
state = sw_host_start;
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
case sw_host_start:
r->host_start = p;
if (ch == '[') {
state = sw_host_ip_literal;
break;
}
state = sw_host;
/* fall through */
case sw_host:
c = (u_char) (ch | 0x20);
if (c >= 'a' && c <= 'z') {
break;
}
if ((ch >= '0' && ch <= '9') || ch == '.' || ch == '-') {
break;
}
/* fall through */
case sw_host_end:
r->host_end = p;
switch (ch) {
case ':':
state = sw_port;
break;
case '/':
r->uri_start = p;
state = sw_after_slash_in_uri;
break;
case ' ':
/*
* use single "/" from request line to preserve pointers,
* if request line will be copied to large client buffer
*/
r->uri_start = r->schema_end + 1;
r->uri_end = r->schema_end + 2;
state = sw_host_http_09;
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
case sw_host_ip_literal:
if (ch >= '0' && ch <= '9') {
break;
}
c = (u_char) (ch | 0x20);
if (c >= 'a' && c <= 'z') {
break;
}
switch (ch) {
case ':':
break;
case ']':
state = sw_host_end;
break;
case '-':
case '.':
case '_':
case '~':
/* unreserved */
break;
case '!':
case '$':
case '&':
case '\'':
case '(':
case ')':
case '*':
case '+':
case ',':
case ';':
case '=':
/* sub-delims */
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
case sw_port:
if (ch >= '0' && ch <= '9') {
break;
}
switch (ch) {
case '/':
r->port_end = p;
r->uri_start = p;
state = sw_after_slash_in_uri;
break;
case ' ':
r->port_end = p;
/*
* use single "/" from request line to preserve pointers,
* if request line will be copied to large client buffer
*/
r->uri_start = r->schema_end + 1;
r->uri_end = r->schema_end + 2;
state = sw_host_http_09;
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
/* space+ after "http://host[:port] " */
case sw_host_http_09:
switch (ch) {
case ' ':
break;
case CR:
r->http_minor = 9;
state = sw_almost_done;
break;
case LF:
r->http_minor = 9;
goto done;
case 'H':
r->http_protocol.data = p;
state = sw_http_H;
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
/* check "/.", "//", "%", and "\" (Win32) in URI */
case sw_after_slash_in_uri:
if (usual[ch >> 5] & (1 << (ch & 0x1f))) {
state = sw_check_uri;
break;
}
switch (ch) {
case ' ':
r->uri_end = p;
state = sw_check_uri_http_09;
break;
case CR:
r->uri_end = p;
r->http_minor = 9;
state = sw_almost_done;
break;
case LF:
r->uri_end = p;
r->http_minor = 9;
goto done;
case '.':
r->complex_uri = 1;
state = sw_uri;
break;
case '%':
r->quoted_uri = 1;
state = sw_uri;
break;
case '/':
r->complex_uri = 1;
state = sw_uri;
break;
#if (NGX_WIN32)
case '\\':
r->complex_uri = 1;
state = sw_uri;
break;
#endif
case '?':
r->args_start = p + 1;
state = sw_uri;
break;
case '#':
r->complex_uri = 1;
state = sw_uri;
break;
case '+':
r->plus_in_uri = 1;
break;
case '\0':
return NGX_HTTP_PARSE_INVALID_REQUEST;
default:
state = sw_check_uri;
break;
}
break;
/* check "/", "%" and "\" (Win32) in URI */
case sw_check_uri:
if (usual[ch >> 5] & (1 << (ch & 0x1f))) {
break;
}
switch (ch) {
case '/':
#if (NGX_WIN32)
if (r->uri_ext == p) {
r->complex_uri = 1;
state = sw_uri;
break;
}
#endif
r->uri_ext = NULL;
state = sw_after_slash_in_uri;
break;
case '.':
r->uri_ext = p + 1;
break;
case ' ':
r->uri_end = p;
state = sw_check_uri_http_09;
break;
case CR:
r->uri_end = p;
r->http_minor = 9;
state = sw_almost_done;
break;
case LF:
r->uri_end = p;
r->http_minor = 9;
goto done;
#if (NGX_WIN32)
case '\\':
r->complex_uri = 1;
state = sw_after_slash_in_uri;
break;
#endif
case '%':
r->quoted_uri = 1;
state = sw_uri;
break;
case '?':
r->args_start = p + 1;
state = sw_uri;
break;
case '#':
r->complex_uri = 1;
state = sw_uri;
break;
case '+':
r->plus_in_uri = 1;
break;
case '\0':
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
/* space+ after URI */
case sw_check_uri_http_09:
switch (ch) {
case ' ':
break;
case CR:
r->http_minor = 9;
state = sw_almost_done;
break;
case LF:
r->http_minor = 9;
goto done;
case 'H':
r->http_protocol.data = p;
state = sw_http_H;
break;
default:
r->space_in_uri = 1;
state = sw_check_uri;
break;
}
break;
/* URI */
case sw_uri:
if (usual[ch >> 5] & (1 << (ch & 0x1f))) {
break;
}
switch (ch) {
case ' ':
r->uri_end = p;
state = sw_http_09;
break;
case CR:
r->uri_end = p;
r->http_minor = 9;
state = sw_almost_done;
break;
case LF:
r->uri_end = p;
r->http_minor = 9;
goto done;
case '#':
r->complex_uri = 1;
break;
case '\0':
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
/* space+ after URI */
case sw_http_09:
switch (ch) {
case ' ':
break;
case CR:
r->http_minor = 9;
state = sw_almost_done;
break;
case LF:
r->http_minor = 9;
goto done;
case 'H':
r->http_protocol.data = p;
state = sw_http_H;
break;
default:
r->space_in_uri = 1;
state = sw_uri;
break;
}
break;
case sw_http_H:
switch (ch) {
case 'T':
state = sw_http_HT;
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
case sw_http_HT:
switch (ch) {
case 'T':
state = sw_http_HTT;
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
case sw_http_HTT:
switch (ch) {
case 'P':
state = sw_http_HTTP;
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
case sw_http_HTTP:
switch (ch) {
case '/':
state = sw_first_major_digit;
break;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
/* first digit of major HTTP version */
case sw_first_major_digit:
if (ch < '1' || ch > '9') {
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
r->http_major = ch - '0';
state = sw_major_digit;
break;
/* major HTTP version or dot */
case sw_major_digit:
if (ch == '.') {
state = sw_first_minor_digit;
break;
}
if (ch < '0' || ch > '9') {
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
r->http_major = r->http_major * 10 + ch - '0';
break;
/* first digit of minor HTTP version */
case sw_first_minor_digit:
if (ch < '0' || ch > '9') {
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
r->http_minor = ch - '0';
state = sw_minor_digit;
break;
/* minor HTTP version or end of request line */
case sw_minor_digit:
if (ch == CR) {
state = sw_almost_done;
break;
}
if (ch == LF) {
goto done;
}
if (ch == ' ') {
state = sw_spaces_after_digit;
break;
}
if (ch < '0' || ch > '9') {
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
r->http_minor = r->http_minor * 10 + ch - '0';
break;
case sw_spaces_after_digit:
switch (ch) {
case ' ':
break;
case CR:
state = sw_almost_done;
break;
case LF:
goto done;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
break;
/* end of request line */
case sw_almost_done:
r->request_end = p - 1;
switch (ch) {
case LF:
goto done;
default:
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
}
}
b->pos = p;
r->state = state;
return NGX_AGAIN;
done:
b->pos = p + 1;
if (r->request_end == NULL) {
r->request_end = p;
}
r->http_version = r->http_major * 1000 + r->http_minor;
r->state = sw_start;
if (r->http_version == 9 && r->method != NGX_HTTP_GET) {
return NGX_HTTP_PARSE_INVALID_09_METHOD;
}
return NGX_OK;
}
ngx_int_t
ngx_http_parse_header_line(ngx_http_request_t *r, ngx_buf_t *b,
ngx_uint_t allow_underscores)
{
u_char c, ch, *p;
ngx_uint_t hash, i;
enum {
sw_start = 0,
sw_name,
sw_space_before_value,
sw_value,
sw_space_after_value,
sw_ignore_line,
sw_almost_done,
sw_header_almost_done
} state;
/* the last '\0' is not needed because string is zero terminated */
static u_char lowcase[] =
"\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"
"\0\0\0\0\0\0\0\0\0\0\0\0\0-\0\0" "0123456789\0\0\0\0\0\0"
"\0abcdefghijklmnopqrstuvwxyz\0\0\0\0\0"
"\0abcdefghijklmnopqrstuvwxyz\0\0\0\0\0"
"\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"
"\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"
"\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"
"\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0";
state = r->state;
hash = r->header_hash;
i = r->lowcase_index;
for (p = b->pos; p < b->last; p++) {
ch = *p;
switch (state) {
/* first char */
case sw_start:
r->header_name_start = p;
r->invalid_header = 0;
switch (ch) {
case CR:
r->header_end = p;
state = sw_header_almost_done;
break;
case LF:
r->header_end = p;
goto header_done;
default:
state = sw_name;
c = lowcase[ch];
if (c) {
hash = ngx_hash(0, c);
r->lowcase_header[0] = c;
i = 1;
break;
}
if (ch == '\0') {
return NGX_HTTP_PARSE_INVALID_HEADER;
}
r->invalid_header = 1;
break;
}
break;
/* header name */
case sw_name:
c = lowcase[ch];
if (c) {
hash = ngx_hash(hash, c);
r->lowcase_header[i++] = c;
i &= (NGX_HTTP_LC_HEADER_LEN - 1);
break;
}
if (ch == '_') {
if (allow_underscores) {
hash = ngx_hash(hash, ch);
r->lowcase_header[i++] = ch;
i &= (NGX_HTTP_LC_HEADER_LEN - 1);
} else {
r->invalid_header = 1;
}
break;
}
if (ch == ':') {
r->header_name_end = p;
state = sw_space_before_value;
break;
}
if (ch == CR) {
r->header_name_end = p;
r->header_start = p;
r->header_end = p;
state = sw_almost_done;
break;
}
if (ch == LF) {
r->header_name_end = p;
r->header_start = p;
r->header_end = p;
goto done;
}
/* IIS may send the duplicate "HTTP/1.1 ..." lines */
if (ch == '/'
&& r->upstream
&& p - r->header_name_start == 4
&& ngx_strncmp(r->header_name_start, "HTTP", 4) == 0)
{
state = sw_ignore_line;
break;
}
if (ch == '\0') {
return NGX_HTTP_PARSE_INVALID_HEADER;
}
r->invalid_header = 1;
break;
/* space* before header value */
case sw_space_before_value:
switch (ch) {
case ' ':
break;
case CR:
r->header_start = p;
r->header_end = p;
state = sw_almost_done;
break;
case LF:
r->header_start = p;
r->header_end = p;
goto done;
case '\0':
return NGX_HTTP_PARSE_INVALID_HEADER;
default:
r->header_start = p;
state = sw_value;
break;
}
break;
/* header value */
case sw_value:
switch (ch) {
case ' ':
r->header_end = p;
state = sw_space_after_value;
break;
case CR:
r->header_end = p;
state = sw_almost_done;
break;
case LF:
r->header_end = p;
goto done;
case '\0':
return NGX_HTTP_PARSE_INVALID_HEADER;
}
break;
/* space* before end of header line */
case sw_space_after_value:
switch (ch) {
case ' ':
break;
case CR:
state = sw_almost_done;
break;
case LF:
goto done;
case '\0':
return NGX_HTTP_PARSE_INVALID_HEADER;
default:
state = sw_value;
break;
}
break;
/* ignore header line */
case sw_ignore_line:
switch (ch) {
case LF:
state = sw_start;
break;
default:
break;
}
break;
/* end of header line */
case sw_almost_done:
switch (ch) {
case LF:
goto done;
case CR:
break;
default:
return NGX_HTTP_PARSE_INVALID_HEADER;
}
break;
/* end of header */
case sw_header_almost_done:
switch (ch) {
case LF:
goto header_done;
default:
return NGX_HTTP_PARSE_INVALID_HEADER;
}
}
}
b->pos = p;
r->state = state;
r->header_hash = hash;
r->lowcase_index = i;
return NGX_AGAIN;
done:
b->pos = p + 1;
r->state = sw_start;
r->header_hash = hash;
r->lowcase_index = i;
return NGX_OK;
header_done:
b->pos = p + 1;
r->state = sw_start;
return NGX_HTTP_PARSE_HEADER_DONE;
}
ngx_int_t
ngx_http_parse_complex_uri(ngx_http_request_t *r, ngx_uint_t merge_slashes)
{
u_char c, ch, decoded, *p, *u;
enum {
sw_usual = 0,
sw_slash,
sw_dot,
sw_dot_dot,
sw_quoted,
sw_quoted_second
} state, quoted_state;
#if (NGX_SUPPRESS_WARN)
decoded = '\0';
quoted_state = sw_usual;
#endif
state = sw_usual;
p = r->uri_start;
u = r->uri.data;
r->uri_ext = NULL;
r->args_start = NULL;
ch = *p++;
while (p <= r->uri_end) {
/*
* we use "ch = *p++" inside the cycle, but this operation is safe,
* because after the URI there is always at least one character:
* the line feed
*/
ngx_log_debug4(NGX_LOG_DEBUG_HTTP, r->connection->log, 0,
"s:%d in:'%Xd:%c', out:'%c'", state, ch, ch, *u);
switch (state) {
case sw_usual:
if (usual[ch >> 5] & (1 << (ch & 0x1f))) {
*u++ = ch;
ch = *p++;
break;
}
switch(ch) {
#if (NGX_WIN32)
case '\\':
if (u - 2 >= r->uri.data
&& *(u - 1) == '.' && *(u - 2) != '.')
{
u--;
}
r->uri_ext = NULL;
if (p == r->uri_start + r->uri.len) {
/*
* we omit the last "\" to cause redirect because
* the browsers do not treat "\" as "/" in relative URL path
*/
break;
}
state = sw_slash;
*u++ = '/';
break;
#endif
case '/':
#if (NGX_WIN32)
if (u - 2 >= r->uri.data
&& *(u - 1) == '.' && *(u - 2) != '.')
{
u--;
}
#endif
r->uri_ext = NULL;
state = sw_slash;
*u++ = ch;
break;
case '%':
quoted_state = state;
state = sw_quoted;
break;
case '?':
r->args_start = p;
goto args;
case '#':
goto done;
case '.':
r->uri_ext = u + 1;
*u++ = ch;
break;
case '+':
r->plus_in_uri = 1;
/* fall through */
default:
*u++ = ch;
break;
}
ch = *p++;
break;
case sw_slash:
if (usual[ch >> 5] & (1 << (ch & 0x1f))) {
state = sw_usual;
*u++ = ch;
ch = *p++;
break;
}
switch(ch) {
#if (NGX_WIN32)
case '\\':
break;
#endif
case '/':
if (!merge_slashes) {
*u++ = ch;
}
break;
case '.':
state = sw_dot;
*u++ = ch;
break;
case '%':
quoted_state = state;
state = sw_quoted;
break;
case '?':
r->args_start = p;
goto args;
case '#':
goto done;
case '+':
r->plus_in_uri = 1;
default:
state = sw_usual;
*u++ = ch;
break;
}
ch = *p++;
break;
case sw_dot:
if (usual[ch >> 5] & (1 << (ch & 0x1f))) {
state = sw_usual;
*u++ = ch;
ch = *p++;
break;
}
switch(ch) {
#if (NGX_WIN32)
case '\\':
#endif
case '/':
state = sw_slash;
u--;
break;
case '.':
state = sw_dot_dot;
*u++ = ch;
break;
case '%':
quoted_state = state;
state = sw_quoted;
break;
case '?':
r->args_start = p;
goto args;
case '#':
goto done;
case '+':
r->plus_in_uri = 1;
default:
state = sw_usual;
*u++ = ch;
break;
}
ch = *p++;
break;
case sw_dot_dot:
if (usual[ch >> 5] & (1 << (ch & 0x1f))) {
state = sw_usual;
*u++ = ch;
ch = *p++;
break;
}
switch(ch) {
#if (NGX_WIN32)
case '\\':
#endif
case '/':
state = sw_slash;
u -= 5;
for ( ;; ) {
if (u < r->uri.data) {
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
if (*u == '/') {
u++;
break;
}
u--;
}
break;
case '%':
quoted_state = state;
state = sw_quoted;
break;
case '?':
r->args_start = p;
goto args;
case '#':
goto done;
case '+':
r->plus_in_uri = 1;
default:
state = sw_usual;
*u++ = ch;
break;
}
ch = *p++;
break;
case sw_quoted:
r->quoted_uri = 1;
if (ch >= '0' && ch <= '9') {
decoded = (u_char) (ch - '0');
state = sw_quoted_second;
ch = *p++;
break;
}
c = (u_char) (ch | 0x20);
if (c >= 'a' && c <= 'f') {
decoded = (u_char) (c - 'a' + 10);
state = sw_quoted_second;
ch = *p++;
break;
}
return NGX_HTTP_PARSE_INVALID_REQUEST;
case sw_quoted_second:
if (ch >= '0' && ch <= '9') {
ch = (u_char) ((decoded << 4) + ch - '0');
if (ch == '%' || ch == '#') {
state = sw_usual;
*u++ = ch;
ch = *p++;
break;
} else if (ch == '\0') {
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
state = quoted_state;
break;
}
c = (u_char) (ch | 0x20);
if (c >= 'a' && c <= 'f') {
ch = (u_char) ((decoded << 4) + c - 'a' + 10);
if (ch == '?') {
state = sw_usual;
*u++ = ch;
ch = *p++;
break;
} else if (ch == '+') {
r->plus_in_uri = 1;
}
state = quoted_state;
break;
}
return NGX_HTTP_PARSE_INVALID_REQUEST;
}
}
done:
r->uri.len = u - r->uri.data;
if (r->uri_ext) {
r->exten.len = u - r->uri_ext;
r->exten.data = r->uri_ext;
}
r->uri_ext = NULL;
return NGX_OK;
args:
while (p < r->uri_end) {
if (*p++ != '#') {
continue;
}
r->args.len = p - 1 - r->args_start;
r->args.data = r->args_start;
r->args_start = NULL;
break;
}
r->uri.len = u - r->uri.data;
if (r->uri_ext) {
r->exten.len = u - r->uri_ext;
r->exten.data = r->uri_ext;
}
r->uri_ext = NULL;
return NGX_OK;
}
ngx_int_t
ngx_http_parse_status_line(ngx_http_request_t *r, ngx_buf_t *b,
ngx_http_status_t *status)
{
u_char ch;
u_char *p;
enum {
sw_start = 0,
sw_H,
sw_HT,
sw_HTT,
sw_HTTP,
sw_first_major_digit,
sw_major_digit,
sw_first_minor_digit,
sw_minor_digit,
sw_status,
sw_space_after_status,
sw_status_text,
sw_almost_done
} state;
state = r->state;
for (p = b->pos; p < b->last; p++) {
ch = *p;
switch (state) {
/* "HTTP/" */
case sw_start:
switch (ch) {
case 'H':
state = sw_H;
break;
default:
return NGX_ERROR;
}
break;
case sw_H:
switch (ch) {
case 'T':
state = sw_HT;
break;
default:
return NGX_ERROR;
}
break;
case sw_HT:
switch (ch) {
case 'T':
state = sw_HTT;
break;
default:
return NGX_ERROR;
}
break;
case sw_HTT:
switch (ch) {
case 'P':
state = sw_HTTP;
break;
default:
return NGX_ERROR;
}
break;
case sw_HTTP:
switch (ch) {
case '/':
state = sw_first_major_digit;
break;
default:
return NGX_ERROR;
}
break;
/* the first digit of major HTTP version */
case sw_first_major_digit:
if (ch < '1' || ch > '9') {
return NGX_ERROR;
}
r->http_major = ch - '0';
state = sw_major_digit;
break;
/* the major HTTP version or dot */
case sw_major_digit:
if (ch == '.') {
state = sw_first_minor_digit;
break;
}
if (ch < '0' || ch > '9') {
return NGX_ERROR;
}
r->http_major = r->http_major * 10 + ch - '0';
break;
/* the first digit of minor HTTP version */
case sw_first_minor_digit:
if (ch < '0' || ch > '9') {
return NGX_ERROR;
}
r->http_minor = ch - '0';
state = sw_minor_digit;
break;
/* the minor HTTP version or the end of the request line */
case sw_minor_digit:
if (ch == ' ') {
state = sw_status;
break;
}
if (ch < '0' || ch > '9') {
return NGX_ERROR;
}
r->http_minor = r->http_minor * 10 + ch - '0';
break;
/* HTTP status code */
case sw_status:
if (ch == ' ') {
break;
}
if (ch < '0' || ch > '9') {
return NGX_ERROR;
}
status->code = status->code * 10 + ch - '0';
if (++status->count == 3) {
state = sw_space_after_status;
status->start = p - 2;
}
break;
/* space or end of line */
case sw_space_after_status:
switch (ch) {
case ' ':
state = sw_status_text;
break;
case '.': /* IIS may send 403.1, 403.2, etc */
state = sw_status_text;
break;
case CR:
state = sw_almost_done;
break;
case LF:
goto done;
default:
return NGX_ERROR;
}
break;
/* any text until end of line */
case sw_status_text:
switch (ch) {
case CR:
state = sw_almost_done;
break;
case LF:
goto done;
}
break;
/* end of status line */
case sw_almost_done:
status->end = p - 1;
switch (ch) {
case LF:
goto done;
default:
return NGX_ERROR;
}
}
}
b->pos = p;
r->state = state;
return NGX_AGAIN;
done:
b->pos = p + 1;
if (status->end == NULL) {
status->end = p;
}
status->http_version = r->http_major * 1000 + r->http_minor;
r->state = sw_start;
return NGX_OK;
}
ngx_int_t
ngx_http_parse_unsafe_uri(ngx_http_request_t *r, ngx_str_t *uri,
ngx_str_t *args, ngx_uint_t *flags)
{
u_char ch, *p;
size_t len;
len = uri->len;
p = uri->data;
if (len == 0 || p[0] == '?') {
goto unsafe;
}
if (p[0] == '.' && len == 3 && p[1] == '.' && (ngx_path_separator(p[2]))) {
goto unsafe;
}
for ( /* void */ ; len; len--) {
ch = *p++;
if (usual[ch >> 5] & (1 << (ch & 0x1f))) {
continue;
}
if (ch == '?') {
args->len = len - 1;
args->data = p;
uri->len -= len;
return NGX_OK;
}
if (ch == '\0') {
goto unsafe;
}
if (ngx_path_separator(ch) && len > 2) {
/* detect "/../" */
if (p[0] == '.' && p[1] == '.' && ngx_path_separator(p[2])) {
goto unsafe;
}
}
}
return NGX_OK;
unsafe:
if (*flags & NGX_HTTP_LOG_UNSAFE) {
ngx_log_error(NGX_LOG_ERR, r->connection->log, 0,
"unsafe URI \"%V\" was detected", uri);
}
return NGX_ERROR;
}
ngx_int_t
ngx_http_parse_multi_header_lines(ngx_array_t *headers, ngx_str_t *name,
ngx_str_t *value)
{
ngx_uint_t i;
u_char *start, *last, *end, ch;
ngx_table_elt_t **h;
h = headers->elts;
for (i = 0; i < headers->nelts; i++) {
ngx_log_debug2(NGX_LOG_DEBUG_HTTP, headers->pool->log, 0,
"parse header: \"%V: %V\"", &h[i]->key, &h[i]->value);
if (name->len > h[i]->value.len) {
continue;
}
start = h[i]->value.data;
end = h[i]->value.data + h[i]->value.len;
while (start < end) {
if (ngx_strncasecmp(start, name->data, name->len) != 0) {
goto skip;
}
for (start += name->len; start < end && *start == ' '; start++) {
/* void */
}
if (value == NULL) {
if (start == end || *start == ',') {
return i;
}
goto skip;
}
if (start == end || *start++ != '=') {
/* the invalid header value */
goto skip;
}
while (start < end && *start == ' ') { start++; }
for (last = start; last < end && *last != ';'; last++) {
/* void */
}
value->len = last - start;
value->data = start;
return i;
skip:
while (start < end) {
ch = *start++;
if (ch == ';' || ch == ',') {
break;
}
}
while (start < end && *start == ' ') { start++; }
}
}
return NGX_DECLINED;
}
ngx_int_t
ngx_http_arg(ngx_http_request_t *r, u_char *name, size_t len, ngx_str_t *value)
{
u_char *p, *last;
if (r->args.len == 0) {
return NGX_DECLINED;
}
p = r->args.data;
last = p + r->args.len;
for ( /* void */ ; p < last; p++) {
/* we need '=' after name, so drop one char from last */
p = ngx_strlcasestrn(p, last - 1, name, len - 1);
if (p == NULL) {
return NGX_DECLINED;
}
if ((p == r->args.data || *(p - 1) == '&') && *(p + len) == '=') {
value->data = p + len + 1;
p = ngx_strlchr(p, last, '&');
if (p == NULL) {
p = r->args.data + r->args.len;
}
value->len = p - value->data;
return NGX_OK;
}
}
return NGX_DECLINED;
}
void
ngx_http_split_args(ngx_http_request_t *r, ngx_str_t *uri, ngx_str_t *args)
{
u_char *p, *last;
last = uri->data + uri->len;
p = ngx_strlchr(uri->data, last, '?');
if (p) {
uri->len = p - uri->data;
p++;
args->len = last - p;
args->data = p;
} else {
args->len = 0;
}
}