ngx_http_parse.c

Nginx是一个高性能的HTTP和反向代理服务器

            case '#':
                r->complex_uri = 1;
                state = sw_uri;
                break;
            case '+':
                r->plus_in_uri = 1;
                break;
            case '\0':
                r->zero_in_uri = 1;
                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':
                r->zero_in_uri = 1;
                break;
            }
            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:
                return NGX_HTTP_PARSE_INVALID_REQUEST;
            }
            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)
{
    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->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;
                r->header_name_start = p;

                c = lowcase[ch];

                if (c) {
                    hash = ngx_hash(0, c);
                    r->lowcase_header[0] = c;
                    i = 1;
                    break;
                }

                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 == ':') {
                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;
            }

            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;
            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;
            }
            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;
            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,
#if (NGX_WIN32)
        sw_dot_dot_dot,
#endif
        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 charcter:
         * 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) {