commit e9b1adeafd88347375a5a129ca43b4fb7ff90031
author Maxim Dounin <mdounin@mdounin.ru> Thu Dec 10 20:09:30 2020 +0300
committer Maxim Dounin <mdounin@mdounin.ru> Thu Dec 10 20:09:30 2020 +0300
tree 75d159374284c79ce9c1343f21279b0f701385f7
parent cfde753736c18c2579249466829be1f7dd94b0c3

Fixed parsing of absolute URIs with empty path (ticket #2079).

When the request line contains request-target in the absolute-URI form,
it can contain path-empty instead of a single slash (see RFC 7230, RFC 3986).
Previously, the ngx_http_parse_request_line() function only accepted empty
path when there was no query string.

With this change, non-empty query is also correctly handled.  That is,
request line "GET http://example.com?foo HTTP/1.1" is accepted and results
in $uri "/" and $args "foo".

Note that $request_uri remains "?foo", similarly to how spaces in URIs
are handled.  Providing "/?foo", similarly to how "/" is provided for
"GET http://example.com HTTP/1.1", requires allocation.

src/http/ngx_http_parse.c

diff --git a/src/http/ngx_http_parse.c b/src/http/ngx_http_parse.c
index cfc42f9..20ad89a 100644
--- a/src/http/ngx_http_parse.c
+++ b/src/http/ngx_http_parse.c
@@ -380,6 +380,12 @@
                 r->uri_start = p;
                 state = sw_after_slash_in_uri;
                 break;
+            case '?':
+                r->uri_start = p;
+                r->args_start = p + 1;
+                r->empty_path_in_uri = 1;
+                state = sw_uri;
+                break;
             case ' ':
                 /*
                  * use single "/" from request line to preserve pointers,
@@ -446,6 +452,13 @@
                 r->uri_start = p;
                 state = sw_after_slash_in_uri;
                 break;
+            case '?':
+                r->port_end = p;
+                r->uri_start = p;
+                r->args_start = p + 1;
+                r->empty_path_in_uri = 1;
+                state = sw_uri;
+                break;
             case ' ':
                 r->port_end = p;
                 /*
@@ -1287,6 +1300,10 @@
     r->uri_ext = NULL;
     r->args_start = NULL;
 
+    if (r->empty_path_in_uri) {
+        *u++ = '/';
+    }
+
     ch = *p++;
 
     while (p <= r->uri_end) {

src/http/ngx_http_request.c

diff --git a/src/http/ngx_http_request.c b/src/http/ngx_http_request.c
index e954c7c..73ab204 100644
--- a/src/http/ngx_http_request.c
+++ b/src/http/ngx_http_request.c
@@ -1224,7 +1224,11 @@
         r->uri.len = r->uri_end - r->uri_start;
     }
 
-    if (r->complex_uri || r->quoted_uri) {
+    if (r->complex_uri || r->quoted_uri || r->empty_path_in_uri) {
+
+        if (r->empty_path_in_uri) {
+            r->uri.len++;
+        }
 
         r->uri.data = ngx_pnalloc(r->pool, r->uri.len + 1);
         if (r->uri.data == NULL) {
@@ -1250,7 +1254,7 @@
     r->unparsed_uri.len = r->uri_end - r->uri_start;
     r->unparsed_uri.data = r->uri_start;
 
-    r->valid_unparsed_uri = r->space_in_uri ? 0 : 1;
+    r->valid_unparsed_uri = (r->space_in_uri || r->empty_path_in_uri) ? 0 : 1;
 
     if (r->uri_ext) {
         if (r->args_start) {

src/http/ngx_http_request.h

diff --git a/src/http/ngx_http_request.h b/src/http/ngx_http_request.h
index 70c2d42..6dfb4a4 100644
--- a/src/http/ngx_http_request.h
+++ b/src/http/ngx_http_request.h
@@ -470,6 +470,9 @@
     /* URI with " " */
     unsigned                          space_in_uri:1;
 
+    /* URI with empty path */
+    unsigned                          empty_path_in_uri:1;
+
     unsigned                          invalid_header:1;
 
     unsigned                          add_uri_to_alias:1;