[PATCH 29 of 31] Autoindex: escape '?' in file names

[Maxim Dounin]

# HG changeset patch
# User Maxim Dounin <mdounin at mdounin.ru>
# Date 1297776703 -10800
# Node ID e6bfb619ca6875f2657c84eea714943217d397e6
# Parent  2643e3cdaa99a557294d5e93bb6dd5ee10bf5687
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 updated version of the patch originally posted at [1].  It introduces
generic NGX_ESCAPE_URI_COMPONENT which escapes everything but unreseved
characters as per RFC 3986.  This aproach 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

Reported by:	Konstantin Leonov

diff --git a/src/core/ngx_string.c b/src/core/ngx_string.c
--- a/src/core/ngx_string.c
+++ b/src/core/ngx_string.c
@@ -1380,6 +1380,26 @@ ngx_escape_uri(u_char *dst, u_char *src,
         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 */
+        0xffffffff  /* 1111 1111 1111 1111  1111 1111 1111 1111 */
+    };
+
                     /* " ", "#", """, "%", "'", %00-%1F, %7F-%FF */
 
     static uint32_t   html[] = {
@@ -1443,7 +1463,7 @@ ngx_escape_uri(u_char *dst, u_char *src,
                     /* 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
--- a/src/core/ngx_string.h
+++ b/src/core/ngx_string.h
@@ -185,12 +185,13 @@ size_t ngx_utf8_length(u_char *p, size_t
 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
--- a/src/http/modules/ngx_http_autoindex_module.c
+++ b/src/http/modules/ngx_http_autoindex_module.c
@@ -28,7 +28,6 @@ typedef struct {
     size_t         escape;
 
     unsigned       dir:1;
-    unsigned       colon:1;
 
     time_t         mtime;
     off_t          size;
@@ -338,7 +337,7 @@ ngx_http_autoindex_handler(ngx_http_requ
         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);
 
         if (utf8) {
             entry->utf_len = ngx_utf8_length(entry->name.data, entry->name.len);
@@ -346,8 +345,6 @@ ngx_http_autoindex_handler(ngx_http_requ
             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);
@@ -373,7 +370,7 @@ ngx_http_autoindex_handler(ngx_http_requ
             + 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
             + NGX_HTTP_AUTOINDEX_NAME_LEN + sizeof("&gt;") - 2
             + sizeof("</a>") - 1
             + sizeof(" 28-Sep-1970 12:00 ") - 1
@@ -406,14 +403,9 @@ ngx_http_autoindex_handler(ngx_http_requ
     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;