* Add CacheIgnoreQueryString directive to cache requests with a query string

even if no expiration time is specified. Futhermore the query string will not
  be used for key generation such that requests to the same URI path, but with
  different query strings are mapped to the same cache entity. Turning this
  setting to ON violates RFC 2616/13.9 and thus it is turned off by default.

PR: 41484
Submitted by: Fredrik Widlund <fredrik.widlund qbrick.com>
Reviewed by: rpluem


git-svn-id: https://svn.apache.org/repos/asf/httpd/httpd/trunk@504183 13f79535-47bb-0310-9956-ffa450edef68

CHANGES

@@ -2,6 +2,9 @@
 Changes with Apache 2.3.0
   [Remove entries to the current 2.0 and 2.2 section below, when backported]
 
+  *) mod_cache: Add CacheIgnoreQueryString directive.  PR 41484.
+     [Fredrik Widlund <fredrik.widlund qbrick.com>]
+
   *) mod_dbd: Introduce configuration groups to allow inheritance by virtual
      hosts of database configurations from the main server.  Determine the
      minimal set of distinct configurations and share connection pools

docs/manual/mod/mod_cache.xml

@@ -311,6 +311,31 @@ header.</description>
 <seealso><directive module="mod_cache">CacheStoreNoStore</directive></seealso>
 </directivesynopsis>
 
+<directivesynopsis>
+<name>CacheIgnoreQueryString</name>
+<description>Ignore query string when caching</description>
+<syntax>CacheIgnoreQueryString On|Off</syntax>
+<default>CacheIgnoreQueryString Off</default>
+<contextlist><context>server config</context><context>virtual host</context>
+</contextlist>
+
+<usage>
+    <p>Ordinarily, requests with query string parameters are cached separately
+    for each unique query string. This is according to RFC 2616/13.9 done only
+    if an expiration time is specified. The 
+    <directive>CacheIgnoreQueryString</directive> directive tells the cache to
+    cache requests even if no expiration time is specified, and to reply with 
+    a cached reply even if the query string differs. From a caching point of
+    view the request is treated as if having no query string when this 
+    directive is enabled.</p>
+
+    <example>
+      CacheIgnoreQueryString On
+    </example>
+
+</usage>
+</directivesynopsis>
+
 <directivesynopsis>
 <name>CacheLastModifiedFactor</name>
 <description>The factor used to compute an expiry date based on the

modules/cache/cache_storage.c

@@ -345,10 +345,18 @@ int cache_select(request_rec *r)
 apr_status_t cache_generate_key_default(request_rec *r, apr_pool_t* p,
                                         char**key)
 {
+    cache_server_conf *conf;
     char *port_str, *hn, *lcs;
     const char *hostname, *scheme;
     int i;
 
+    /*
+     * Get the module configuration. We need this for the CacheIgnoreQueryString
+     * option below.
+     */
+    conf = (cache_server_conf *) ap_get_module_config(r->server->module_config,
+                                                      &cache_module);
+
     /*
      * Use the canonical name to improve cache hit rate, but only if this is
      * not a proxy request or if this is a reverse proxy request.
@@ -439,9 +447,15 @@ apr_status_t cache_generate_key_default(request_rec *r, apr_pool_t* p,
         port_str = apr_psprintf(p, ":%u", ap_get_server_port(r));
     }
 
-    /* Key format is a URI */
-    *key = apr_pstrcat(p, scheme, "://", hostname, port_str,
-                       r->parsed_uri.path, "?", r->parsed_uri.query, NULL);
+    /* Key format is a URI, optionally without the query-string */
+    if (conf->ignorequerystring) {
+        *key = apr_pstrcat(p, scheme, "://", hostname, port_str,
+                           r->parsed_uri.path, "?", NULL);
+    }
+    else {
+        *key = apr_pstrcat(p, scheme, "://", hostname, port_str,
+                           r->parsed_uri.path, "?", r->parsed_uri.query, NULL);
+    }
 
     return APR_SUCCESS;
 }

modules/cache/mod_cache.c

@@ -452,7 +452,7 @@ static int cache_save_filter(ap_filter_t *f, apr_bucket_brigade *in)
         /* if a Expires header is in the past, don't cache it */
         reason = "Expires header already expired, not cacheable";
     }
-    else if (r->parsed_uri.query && exps == NULL) {
+    else if (!conf->ignorequerystring && r->parsed_uri.query && exps == NULL) {
         /* if query string present but no expiration time, don't cache it
          * (RFC 2616/13.9)
          */
@@ -920,6 +920,9 @@ static void * create_cache_config(apr_pool_t *p, server_rec *s)
     /* array of headers that should not be stored in cache */
     ps->ignore_headers = apr_array_make(p, 10, sizeof(char *));
     ps->ignore_headers_set = CACHE_IGNORE_HEADERS_UNSET;
+    /* flag indicating that query-string should be ignored when caching */
+    ps->ignorequerystring = 0;
+    ps->ignorequerystring_set = 0;
     return ps;
 }
 
@@ -966,6 +969,10 @@ static void * merge_cache_config(apr_pool_t *p, void *basev, void *overridesv)
         (overrides->ignore_headers_set == CACHE_IGNORE_HEADERS_UNSET)
         ? base->ignore_headers
         : overrides->ignore_headers;
+    ps->ignorequerystring =
+        (overrides->ignorequerystring_set == 0)
+        ? base->ignorequerystring
+        : overrides->ignorequerystring;
     return ps;
 }
 static const char *set_cache_ignore_no_last_mod(cmd_parms *parms, void *dummy,
@@ -1157,6 +1164,19 @@ static const char *set_cache_factor(cmd_parms *parms, void *dummy,
     return NULL;
 }
 
+static const char *set_cache_ignore_querystring(cmd_parms *parms, void *dummy,
+                                                int flag)
+{
+    cache_server_conf *conf;
+
+    conf =
+        (cache_server_conf *)ap_get_module_config(parms->server->module_config,
+                                                  &cache_module);
+    conf->ignorequerystring = flag;
+    conf->ignorequerystring_set = 1;
+    return NULL;
+}
+
 static int cache_post_config(apr_pool_t *p, apr_pool_t *plog,
                              apr_pool_t *ptemp, server_rec *s)
 {
@@ -1208,6 +1228,9 @@ static const command_rec cache_cmds[] =
     AP_INIT_ITERATE("CacheIgnoreHeaders", add_ignore_header, NULL, RSRC_CONF,
                     "A space separated list of headers that should not be "
                     "stored by the cache"),
+    AP_INIT_FLAG("CacheIgnoreQueryString", set_cache_ignore_querystring,
+                 NULL, RSRC_CONF,
+                 "Ignore query-string when caching"),
     AP_INIT_TAKE1("CacheLastModifiedFactor", set_cache_factor, NULL, RSRC_CONF,
                   "The factor used to estimate Expires date from "
                   "LastModified date"),

modules/cache/mod_cache.h

@@ -154,6 +154,9 @@ typedef struct {
     /* Minimum time to keep cached files in msecs */
     apr_time_t minex;
     int minex_set;
+    /** ignore query-string when caching */
+    int ignorequerystring;
+    int ignorequerystring_set;
 } cache_server_conf;
 
 /* cache info information */