# HG changeset patch
# User Valentin Bartenev <vbart@nginx.com>
# Date 1322471733 0
# Node ID e7db97bfac25a98fa727514225ad13871364d614
# Parent  0a8e51a1648411ca67a2be2b7bb2818ffbc324b5
Added support for IP-literal in the Host header and request line (ticket #1).

Additional parsing logic added to correctly handle RFC 3986 compliant IPv6 and
IPvFuture characters enclosed in square brackets.

The host validation was completely rewritten. The behavior for non IP literals
was changed in a more proper and safer way:

 - Host part is now delimited either by the first colon or by the end of string
   if there's no colon. Previously the last colon was used as delimiter which
   allowed substitution of a port number in the $host variable.
   (e.g. Host: 127.0.0.1:9000:80)

 - Fixed stripping of the ending dot in the Host header when the host was also
   followed by a port number.
   (e.g. Host: nginx.com.:80)

 - Fixed upper case characters detection. Previously it was broken which led to
   wasting memory and CPU.

diff --git a/src/http/ngx_http_parse.c b/src/http/ngx_http_parse.c
--- a/src/http/ngx_http_parse.c
+++ b/src/http/ngx_http_parse.c
@@ -110,7 +110,10 @@ ngx_http_parse_request_line(ngx_http_req
         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,
@@ -323,14 +326,26 @@ ngx_http_parse_request_line(ngx_http_req
         case sw_schema_slash_slash:
             switch (ch) {
             case '/':
-                r->host_start = p + 1;
-                state = sw_host;
+                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);
@@ -342,6 +357,10 @@ ngx_http_parse_request_line(ngx_http_req
                 break;
             }
 
+            /* fall through */
+
+        case sw_host_end:
+
             r->host_end = p;
 
             switch (ch) {
@@ -366,6 +385,47 @@ ngx_http_parse_request_line(ngx_http_req
             }
             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;
diff --git a/src/http/ngx_http_request.c b/src/http/ngx_http_request.c
--- a/src/http/ngx_http_request.c
+++ b/src/http/ngx_http_request.c
@@ -1674,56 +1674,85 @@ static ssize_t
 ngx_http_validate_host(ngx_http_request_t *r, u_char **host, size_t len,
     ngx_uint_t alloc)
 {
-    u_char      *h, ch;
-    size_t       i, last;
-    ngx_uint_t   dot;
-
-    last = len;
+    u_char  *h, ch;
+    size_t   i, dot_pos, host_len;
+
+    enum {
+        sw_usual = 0,
+        sw_literal,
+        sw_rest
+    } state;
+
+    dot_pos = len;
+    host_len = len;
+
     h = *host;
-    dot = 0;
+
+    state = sw_usual;
 
     for (i = 0; i < len; i++) {
         ch = h[i];
 
-        if (ch == '.') {
-            if (dot) {
+        switch (ch) {
+
+        case '.':
+            if (dot_pos == i - 1) {
                 return 0;
             }
-
-            dot = 1;
-            continue;
-        }
-
-        dot = 0;
-
-        if (ch == ':') {
-            last = i;
-            continue;
-        }
-
-        if (ngx_path_separator(ch) || ch == '\0') {
+            dot_pos = i;
+            break;
+
+        case ':':
+            if (state == sw_usual) {
+                host_len = i;
+                state = sw_rest;
+            }
+            break;
+
+        case '[':
+            if (i == 0) {
+                state = sw_literal;
+            }
+            break;
+
+        case ']':
+            if (state == sw_literal) {
+                host_len = i + 1;
+                state = sw_rest;
+            }
+            break;
+
+        case '\0':
             return 0;
-        }
-
-        if (ch >= 'A' || ch < 'Z') {
-            alloc = 1;
+
+        default:
+
+            if (ngx_path_separator(ch)) {
+                return 0;
+            }
+
+            if (ch >= 'A' && ch <= 'Z') {
+                alloc = 1;
+            }
+
+            break;
         }
     }
 
-    if (dot) {
-        last--;
+    if (dot_pos == host_len - 1) {
+        host_len--;
     }
 
     if (alloc) {
-        *host = ngx_pnalloc(r->pool, last) ;
+        *host = ngx_pnalloc(r->pool, host_len);
         if (*host == NULL) {
             return -1;
         }
 
-        ngx_strlow(*host, h, last);
+        ngx_strlow(*host, h, host_len);
     }
 
-    return last;
+    return host_len;
 }