protocol.c

Apache HTTP Server 是一个功能强大的灵活的与HTTP/1.1相兼容的web服务器.这里给出的是Apache HTTP服务器的源码。

                    tmp = last_char;
                }

                next_size = n - bytes_handled;

                    rv = ap_rgetline_core(&tmp, next_size,
                                          &next_len, r, 0, bb);

                if (rv != APR_SUCCESS) {
                    return rv;
                }

                if (do_alloc && next_len > 0) {
                    char *new_buffer;
                    apr_size_t new_size = bytes_handled + next_len + 1;

                    /* we need to alloc an extra byte for a null */
                    new_buffer = apr_palloc(r->pool, new_size);

                    /* Copy what we already had. */
                    memcpy(new_buffer, *s, bytes_handled);

                    /* copy the new line, including the trailing null */
                    memcpy(new_buffer + bytes_handled, tmp, next_len + 1);
                    *s = new_buffer;
                }

                    bytes_handled += next_len;
            }
            }
            else { /* next character is not tab or space */
                break;
            }
        }
    }

    *read = bytes_handled;
    return APR_SUCCESS;
}

#if APR_CHARSET_EBCDIC
AP_DECLARE(apr_status_t) ap_rgetline(char **s, apr_size_t n,
                                     apr_size_t *read, request_rec *r,
                                     int fold, apr_bucket_brigade *bb)
{
    /* on ASCII boxes, ap_rgetline is a macro which simply invokes
     * ap_rgetline_core with the same parms
     *
     * on EBCDIC boxes, each complete http protocol input line needs to be
     * translated into the code page used by the compiler.  Since
     * ap_rgetline_core uses recursion, we do the translation in a wrapper
     * function to insure that each input character gets translated only once.
     */
    apr_status_t rv;

    rv = ap_rgetline_core(s, n, read, r, fold, bb);
    if (rv == APR_SUCCESS) {
        ap_xlate_proto_from_ascii(*s, *read);
    }
    return rv;
}
#endif

AP_DECLARE(int) ap_getline(char *s, int n, request_rec *r, int fold)
{
    char *tmp_s = s;
    apr_status_t rv;
    apr_size_t len;
    apr_bucket_brigade *tmp_bb;

    tmp_bb = apr_brigade_create(r->pool, r->connection->bucket_alloc);
    rv = ap_rgetline(&tmp_s, n, &len, r, fold, tmp_bb);
    apr_brigade_destroy(tmp_bb);

    /* Map the out-of-space condition to the old API. */
    if (rv == APR_ENOSPC) {
        return n;
    }

    /* Anything else is just bad. */
    if (rv != APR_SUCCESS) {
        return -1;
    }

    return (int)len;
}

/* parse_uri: break apart the uri
 * Side Effects:
 * - sets r->args to rest after '?' (or NULL if no '?')
 * - sets r->uri to request uri (without r->args part)
 * - sets r->hostname (if not set already) from request (scheme://host:port)
 */
AP_CORE_DECLARE(void) ap_parse_uri(request_rec *r, const char *uri)
{
    int status = HTTP_OK;

    r->unparsed_uri = apr_pstrdup(r->pool, uri);

    if (r->method_number == M_CONNECT) {
        status = apr_uri_parse_hostinfo(r->pool, uri, &r->parsed_uri);
    }
    else {
        /* Simple syntax Errors in URLs are trapped by
         * parse_uri_components().
         */
        status = apr_uri_parse(r->pool, uri, &r->parsed_uri);
    }

    if (status == APR_SUCCESS) {
        /* if it has a scheme we may need to do absoluteURI vhost stuff */
        if (r->parsed_uri.scheme
            && !strcasecmp(r->parsed_uri.scheme, ap_http_method(r))) {
            r->hostname = r->parsed_uri.hostname;
        }
        else if (r->method_number == M_CONNECT) {
            r->hostname = r->parsed_uri.hostname;
        }

        r->args = r->parsed_uri.query;
        r->uri = r->parsed_uri.path ? r->parsed_uri.path
                 : apr_pstrdup(r->pool, "/");

#if defined(OS2) || defined(WIN32)
        /* Handle path translations for OS/2 and plug security hole.
         * This will prevent "http://www.wherever.com/..\..\/" from
         * returning a directory for the root drive.
         */
        {
            char *x;

            for (x = r->uri; (x = strchr(x, '\\')) != NULL; )
                *x = '/';
        }
#endif /* OS2 || WIN32 */
    }
    else {
        r->args = NULL;
        r->hostname = NULL;
        r->status = HTTP_BAD_REQUEST;             /* set error status */
        r->uri = apr_pstrdup(r->pool, uri);
    }
}

static int read_request_line(request_rec *r, apr_bucket_brigade *bb)
{
    const char *ll;
    const char *uri;
    const char *pro;

#if 0
    conn_rec *conn = r->connection;
#endif
    int major = 1, minor = 0;   /* Assume HTTP/1.0 if non-"HTTP" protocol */
    char http[5];
    apr_size_t len;
    int num_blank_lines = 0;
    int max_blank_lines = r->server->limit_req_fields;

    if (max_blank_lines <= 0) {
        max_blank_lines = DEFAULT_LIMIT_REQUEST_FIELDS;
    }

    /* Read past empty lines until we get a real request line,
     * a read error, the connection closes (EOF), or we timeout.
     *
     * We skip empty lines because browsers have to tack a CRLF on to the end
     * of POSTs to support old CERN webservers.  But note that we may not
     * have flushed any previous response completely to the client yet.
     * We delay the flush as long as possible so that we can improve
     * performance for clients that are pipelining requests.  If a request
     * is pipelined then we won't block during the (implicit) read() below.
     * If the requests aren't pipelined, then the client is still waiting
     * for the final buffer flush from us, and we will block in the implicit
     * read().  B_SAFEREAD ensures that the BUFF layer flushes if it will
     * have to block during a read.
     */

    do {
        apr_status_t rv;

        /* insure ap_rgetline allocates memory each time thru the loop
         * if there are empty lines
         */
        r->the_request = NULL;
        rv = ap_rgetline(&(r->the_request), (apr_size_t)(r->server->limit_req_line + 2),
                         &len, r, 0, bb);

        if (rv != APR_SUCCESS) {
            r->request_time = apr_time_now();

            /* ap_rgetline returns APR_ENOSPC if it fills up the
             * buffer before finding the end-of-line.  This is only going to
             * happen if it exceeds the configured limit for a request-line.
             */
            if (rv == APR_ENOSPC) {
                r->status    = HTTP_REQUEST_URI_TOO_LARGE;
                r->proto_num = HTTP_VERSION(1,0);
                r->protocol  = apr_pstrdup(r->pool, "HTTP/1.0");
            }

            return 0;
        }
    } while ((len <= 0) && (++num_blank_lines < max_blank_lines));

    /* we've probably got something to do, ignore graceful restart requests */

    r->request_time = apr_time_now();
    ll = r->the_request;
    r->method = ap_getword_white(r->pool, &ll);

#if 0
/* XXX If we want to keep track of the Method, the protocol module should do
 * it.  That support isn't in the scoreboard yet.  Hopefully next week
 * sometime.   rbb */
    ap_update_connection_status(AP_CHILD_THREAD_FROM_ID(conn->id), "Method",
                                r->method);
#endif

    uri = ap_getword_white(r->pool, &ll);

    /* Provide quick information about the request method as soon as known */

    r->method_number = ap_method_number_of(r->method);
    if (r->method_number == M_GET && r->method[0] == 'H') {
        r->header_only = 1;
    }

    ap_parse_uri(r, uri);

    if (ll[0]) {
        r->assbackwards = 0;
        pro = ll;
        len = strlen(ll);
    } else {
        r->assbackwards = 1;
        pro = "HTTP/0.9";
        len = 8;
    }
    r->protocol = apr_pstrmemdup(r->pool, pro, len);

    /* XXX ap_update_connection_status(conn->id, "Protocol", r->protocol); */

    /* Avoid sscanf in the common case */
    if (len == 8
        && pro[0] == 'H' && pro[1] == 'T' && pro[2] == 'T' && pro[3] == 'P'
        && pro[4] == '/' && apr_isdigit(pro[5]) && pro[6] == '.'
        && apr_isdigit(pro[7])) {
        r->proto_num = HTTP_VERSION(pro[5] - '0', pro[7] - '0');
    }
    else if (3 == sscanf(r->protocol, "%4s/%u.%u", http, &major, &minor)
             && (strcasecmp("http", http) == 0)
             && (minor < HTTP_VERSION(1, 0)) ) /* don't allow HTTP/0.1000 */
        r->proto_num = HTTP_VERSION(major, minor);
    else
        r->proto_num = HTTP_VERSION(1, 0);

    return 1;
}

AP_DECLARE(void) ap_get_mime_headers_core(request_rec *r, apr_bucket_brigade *bb)
{
    char *last_field = NULL;
    apr_size_t last_len = 0;
    apr_size_t alloc_len = 0;
    char *field;
    char *value;
    apr_size_t len;
    int fields_read = 0;
    char *tmp_field;

    /*
     * Read header lines until we get the empty separator line, a read error,
     * the connection closes (EOF), reach the server limit, or we timeout.
     */
    while(1) {
        apr_status_t rv;
        int folded = 0;

        field = NULL;
        rv = ap_rgetline(&field, r->server->limit_req_fieldsize + 2,
                         &len, r, 0, bb);

        /* ap_rgetline returns APR_ENOSPC if it fills up the buffer before
         * finding the end-of-line.  This is only going to happen if it
         * exceeds the configured limit for a field size.
         */
        if (rv == APR_ENOSPC && field) {
            r->status = HTTP_BAD_REQUEST;
            /* insure ap_escape_html will terminate correctly */
            field[len - 1] = '\0';
            apr_table_setn(r->notes, "error-notes",
                           apr_pstrcat(r->pool,
                                       "Size of a request header field "
                                       "exceeds server limit.<br />\n"
                                       "<pre>\n",
                                       ap_escape_html(r->pool, field),
                                       "</pre>\n", NULL));
            return;
        }

        if (rv != APR_SUCCESS) {
            r->status = HTTP_BAD_REQUEST;
            return;
        }

        if (last_field != NULL) {
            if ((len > 0) && ((*field == '\t') || *field == ' ')) {
                /* This line is a continuation of the preceding line(s),
                 * so append it to the line that we've set aside.
                 * Note: this uses a power-of-two allocator to avoid
                 * doing O(n) allocs and using O(n^2) space for
                 * continuations that span many many lines.
                 */
                apr_size_t fold_len = last_len + len + 1; /* trailing null */

                if ((fold_len - 1) > r->server->limit_req_fieldsize) {
                    r->status = HTTP_BAD_REQUEST;
                    /* report what we have accumulated so far before the
                     * overflow (last_field) as the field with the problem
                     */
                    apr_table_setn(r->notes, "error-notes",
                                   apr_pstrcat(r->pool,
                                               "Size of a request header field " 
                                               "after folding "
                                               "exceeds server limit.<br />\n"
                                               "<pre>\n",
                                               ap_escape_html(r->pool, last_field),
                                               "</pre>\n", NULL));
                    return;
                }

                if (fold_len > alloc_len) {
                    char *fold_buf;
                    alloc_len += alloc_len;
                    if (fold_len > alloc_len) {
                        alloc_len = fold_len;
                    }
                    fold_buf = (char *)apr_palloc(r->pool, alloc_len);
                    memcpy(fold_buf, last_field, last_len);
                    last_field = fold_buf;
                }
                memcpy(last_field + last_len, field, len +1); /* +1 for nul */
                last_len += len;
                folded = 1;
            }
            else /* not a continuation line */ {

                if (r->server->limit_req_fields
                    && (++fields_read > r->server->limit_req_fields)) {
                    r->status = HTTP_BAD_REQUEST;
                    apr_table_setn(r->notes, "error-notes",
                                   "The number of request header fields "
                                   "exceeds this server's limit.");
                    return;
                }

                if (!(value = strchr(last_field, ':'))) { /* Find ':' or    */
                    r->status = HTTP_BAD_REQUEST;      /* abort bad request */
                    apr_table_setn(r->notes, "error-notes",
                                   apr_pstrcat(r->pool,
                                               "Request header field is "
                                               "missing ':' separator.<br />\n"
                                               "<pre>\n",
                                               ap_escape_html(r->pool,
                                                              last_field),
                                               "</pre>\n", NULL));
                    return;
                }
                
                tmp_field = value - 1; /* last character of field-name */

                *value++ = '\0'; /* NUL-terminate at colon */

                while (*value == ' ' || *value == '\t') {
                    ++value;            /* Skip to start of value   */
                }

                /* Strip LWS after field-name: */
                while (tmp_field > last_field 
                       && (*tmp_field == ' ' || *tmp_field == '\t')) {
                    *tmp_field-- = '\0';
                }
                
                /* Strip LWS after field-value: */