Merging r4193, r4194:

Autoindex fixes:

*) Autoindex: escape '?' in file names.

   For files with '?' in their names autoindex generated links with '?' not
   escaped.  This resulted in effectively truncated links as '?' indicates
   query string start.

   This is an updated version of the patch originally posted at [1].  It
   introduces generic NGX_ESCAPE_URI_COMPONENT which escapes everything but
   unreserved characters as per RFC 3986.  This approach also renders unneeded
   special colon processing (as colon is percent-encoded now), it's dropped
   accordingly.

   [1] http://nginx.org/pipermail/nginx-devel/2010-February/000112.html

*) Autoindex: escape html in file names.

diff --git a/src/core/ngx_string.c b/src/core/ngx_string.c
index 75bc6578d4c4da53885f92b76443333dd9195080..8f29e9070054b6e2c3a7e1070c08d81ee6fcb89c 100644 (file)
--- a/src/core/ngx_string.c
+++ b/src/core/ngx_string.c
@@ -1374,6 +1374,26 @@ ngx_escape_uri(u_char *dst, u_char *src, size_t size, ngx_uint_t type)
                     /*  ~}| {zyx wvut srqp  onml kjih gfed cba` */
         0x80000000, /* 1000 0000 0000 0000  0000 0000 0000 0000 */
 
+        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 */
+    };
+
+                    /* not ALPHA, DIGIT, "-", ".", "_", "~" */
+
+    static uint32_t   uri_component[] = {
+        0xffffffff, /* 1111 1111 1111 1111  1111 1111 1111 1111 */
+
+                    /* ?>=< ;:98 7654 3210  /.-, +*)( '&%$ #"!  */
+        0xfc009fff, /* 1111 1100 0000 0000  1001 1111 1111 1111 */
+
+                    /* _^]\ [ZYX WVUT SRQP  ONML KJIH GFED CBA@ */
+        0x78000001, /* 0111 1000 0000 0000  0000 0000 0000 0001 */
+
+                    /*  ~}| {zyx wvut srqp  onml kjih gfed cba` */
+        0xb8000001, /* 1011 1000 0000 0000  0000 0000 0000 0001 */
+
         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 */
@@ -1443,7 +1463,7 @@ ngx_escape_uri(u_char *dst, u_char *src, size_t size, ngx_uint_t type)
                     /* mail_auth is the same as memcached */
 
     static uint32_t  *map[] =
-        { uri, args, html, refresh, memcached, memcached };
+        { uri, args, uri_component, html, refresh, memcached, memcached };
 
 
     escape = map[type];

diff --git a/src/core/ngx_string.h b/src/core/ngx_string.h
index 2030988d89f69c4ec0c8c6768639a3c5c415a56a..2b9c59a5e62d6c40660fed5c23aedb51933bb8b4 100644 (file)
--- a/src/core/ngx_string.h
+++ b/src/core/ngx_string.h
@@ -189,12 +189,13 @@ size_t ngx_utf8_length(u_char *p, size_t n);
 u_char *ngx_utf8_cpystrn(u_char *dst, u_char *src, size_t n, size_t len);
 
 
-#define NGX_ESCAPE_URI         0
-#define NGX_ESCAPE_ARGS        1
-#define NGX_ESCAPE_HTML        2
-#define NGX_ESCAPE_REFRESH     3
-#define NGX_ESCAPE_MEMCACHED   4
-#define NGX_ESCAPE_MAIL_AUTH   5
+#define NGX_ESCAPE_URI            0
+#define NGX_ESCAPE_ARGS           1
+#define NGX_ESCAPE_URI_COMPONENT  2
+#define NGX_ESCAPE_HTML           3
+#define NGX_ESCAPE_REFRESH        4
+#define NGX_ESCAPE_MEMCACHED      5
+#define NGX_ESCAPE_MAIL_AUTH      6
 
 #define NGX_UNESCAPE_URI       1
 #define NGX_UNESCAPE_REDIRECT  2

diff --git a/src/http/modules/ngx_http_autoindex_module.c b/src/http/modules/ngx_http_autoindex_module.c
index b6793180698055182a581a7c20dfdc3d373594e1..bd7388126ae137ae618a5effd71b76463ddbf690 100644 (file)
--- a/src/http/modules/ngx_http_autoindex_module.c
+++ b/src/http/modules/ngx_http_autoindex_module.c
@@ -26,9 +26,9 @@ typedef struct {
     ngx_str_t      name;
     size_t         utf_len;
     size_t         escape;
+    size_t         escape_html;
 
     unsigned       dir:1;
-    unsigned       colon:1;
 
     time_t         mtime;
     off_t          size;
@@ -138,7 +138,7 @@ ngx_http_autoindex_handler(ngx_http_request_t *r)
 {
     u_char                         *last, *filename, scale;
     off_t                           length;
-    size_t                          len, utf_len, allocated, root;
+    size_t                          len, char_len, escape_html, allocated, root;
     ngx_tm_t                        tm;
     ngx_err_t                       err;
     ngx_buf_t                      *b;
@@ -338,7 +338,10 @@ ngx_http_autoindex_handler(ngx_http_request_t *r)
         ngx_cpystrn(entry->name.data, ngx_de_name(&dir), len + 1);
 
         entry->escape = 2 * ngx_escape_uri(NULL, ngx_de_name(&dir), len,
-                                           NGX_ESCAPE_HTML);
+                                           NGX_ESCAPE_URI_COMPONENT);
+
+        entry->escape_html = ngx_escape_html(NULL, entry->name.data,
+                                             entry->name.len);
 
         if (utf8) {
             entry->utf_len = ngx_utf8_length(entry->name.data, entry->name.len);
@@ -346,8 +349,6 @@ ngx_http_autoindex_handler(ngx_http_request_t *r)
             entry->utf_len = len;
         }
 
-        entry->colon = (ngx_strchr(entry->name.data, ':') != NULL);
-
         entry->dir = ngx_de_is_dir(&dir);
         entry->mtime = ngx_de_mtime(&dir);
         entry->size = ngx_de_size(&dir);
@@ -358,10 +359,12 @@ ngx_http_autoindex_handler(ngx_http_request_t *r)
                       ngx_close_dir_n " \"%s\" failed", &path);
     }
 
+    escape_html = ngx_escape_html(NULL, r->uri.data, r->uri.len);
+
     len = sizeof(title) - 1
-          + r->uri.len
+          + r->uri.len + escape_html
           + sizeof(header) - 1
-          + r->uri.len
+          + r->uri.len + escape_html
           + sizeof("</h1>") - 1
           + sizeof("<hr><pre><a href=\"../\">../</a>" CRLF) - 1
           + sizeof("</pre><hr>") - 1
@@ -373,7 +376,8 @@ ngx_http_autoindex_handler(ngx_http_request_t *r)
             + entry[i].name.len + entry[i].escape
             + 1                                          /* 1 is for "/" */
             + sizeof("\">") - 1
-            + entry[i].name.len - entry[i].utf_len + entry[i].colon * 2
+            + entry[i].name.len - entry[i].utf_len
+            + entry[i].escape_html
             + NGX_HTTP_AUTOINDEX_NAME_LEN + sizeof("&gt;") - 2
             + sizeof("</a>") - 1
             + sizeof(" 28-Sep-1970 12:00 ") - 1
@@ -393,9 +397,18 @@ ngx_http_autoindex_handler(ngx_http_request_t *r)
     }
 
     b->last = ngx_cpymem(b->last, title, sizeof(title) - 1);
-    b->last = ngx_cpymem(b->last, r->uri.data, r->uri.len);
-    b->last = ngx_cpymem(b->last, header, sizeof(header) - 1);
-    b->last = ngx_cpymem(b->last, r->uri.data, r->uri.len);
+
+    if (escape_html) {
+        b->last = (u_char *) ngx_escape_html(b->last, r->uri.data, r->uri.len);
+        b->last = ngx_cpymem(b->last, header, sizeof(header) - 1);
+        b->last = (u_char *) ngx_escape_html(b->last, r->uri.data, r->uri.len);
+
+    } else {
+        b->last = ngx_cpymem(b->last, r->uri.data, r->uri.len);
+        b->last = ngx_cpymem(b->last, header, sizeof(header) - 1);
+        b->last = ngx_cpymem(b->last, r->uri.data, r->uri.len);
+    }
+
     b->last = ngx_cpymem(b->last, "</h1>", sizeof("</h1>") - 1);
 
     b->last = ngx_cpymem(b->last, "<hr><pre><a href=\"../\">../</a>" CRLF,
@@ -406,14 +419,9 @@ ngx_http_autoindex_handler(ngx_http_request_t *r)
     for (i = 0; i < entries.nelts; i++) {
         b->last = ngx_cpymem(b->last, "<a href=\"", sizeof("<a href=\"") - 1);
 
-        if (entry[i].colon) {
-            *b->last++ = '.';
-            *b->last++ = '/';
-        }
-
         if (entry[i].escape) {
             ngx_escape_uri(b->last, entry[i].name.data, entry[i].name.len,
-                           NGX_ESCAPE_HTML);
+                           NGX_ESCAPE_URI_COMPONENT);
 
             b->last += entry[i].name.len + entry[i].escape;
 
@@ -433,20 +441,41 @@ ngx_http_autoindex_handler(ngx_http_request_t *r)
 
         if (entry[i].name.len != len) {
             if (len > NGX_HTTP_AUTOINDEX_NAME_LEN) {
-                utf_len = NGX_HTTP_AUTOINDEX_NAME_LEN - 3 + 1;
+                char_len = NGX_HTTP_AUTOINDEX_NAME_LEN - 3 + 1;
 
             } else {
-                utf_len = NGX_HTTP_AUTOINDEX_NAME_LEN + 1;
+                char_len = NGX_HTTP_AUTOINDEX_NAME_LEN + 1;
             }
 
+            last = b->last;
             b->last = ngx_utf8_cpystrn(b->last, entry[i].name.data,
-                                       utf_len, entry[i].name.len + 1);
+                                       char_len, entry[i].name.len + 1);
+
+            if (entry[i].escape_html) {
+                b->last = (u_char *) ngx_escape_html(last, entry[i].name.data,
+                                                     b->last - last);
+            }
+
             last = b->last;
 
         } else {
-            b->last = ngx_cpystrn(b->last, entry[i].name.data,
-                                  NGX_HTTP_AUTOINDEX_NAME_LEN + 1);
-            last = b->last - 3;
+            if (entry[i].escape_html) {
+                if (len > NGX_HTTP_AUTOINDEX_NAME_LEN) {
+                    char_len = NGX_HTTP_AUTOINDEX_NAME_LEN - 3;
+
+                } else {
+                    char_len = len;
+                }
+
+                b->last = (u_char *) ngx_escape_html(b->last,
+                                                  entry[i].name.data, char_len);
+                last = b->last;
+
+            } else {
+                b->last = ngx_cpystrn(b->last, entry[i].name.data,
+                                      NGX_HTTP_AUTOINDEX_NAME_LEN + 1);
+                last = b->last - 3;
+            }
         }
 
         if (len > NGX_HTTP_AUTOINDEX_NAME_LEN) {