The following reply was made to PR mod_log-any/3449; it has been noted by GNATS.
From: "Rainer Scherg," <[EMAIL PROTECTED]>
To: "'[EMAIL PROTECTED]'" <[EMAIL PROTECTED]>
Cc: "'[EMAIL PROTECTED]'" <[EMAIL PROTECTED]>
Subject: mod_log-any/3449: RefererIgnore in CustomLog
Date: Thu, 26 Nov 1998 15:39:03 +0100
Hi! As requested by Ken, here comes the diff-file...
The enhancements are roughly tested (running on our intranet
since yesterday - 'til now it's working fine).
Work done:
- AgentLog fn (compatability with mod_log_agent)
- RefererLog fn (compatability with mod_log_referer)
- RefererIgnore str str ... ( - " - , slightly behavior)
- RefererReplace str repl (new function at no add. cost)
- Predefined log format ELF (please have a look on def.!)
Still to be done:
- Doc (HTML)
>> diff -u mod_log_config.c.cvs-tree mod_log_config.new.c
Please send feedback if question or problem.
=== Rainer
=== snip =======
--- mod_log_config.c.cvs-tree Thu Nov 26 14:34:11 1998
+++ mod_log_config.c Thu Nov 26 14:32:40 1998
@@ -75,6 +75,27 @@
* CookieLog fn For backwards compatability with old Cookie
* logging module - now deprecated.
*
+ *--- Added 1998-11-24:
+ * RefererLog fn For backwards compat. with old log_referer
module
+ * RefererIgnore string1 string2 ...
+ * Avoid logging of referer information,
+ * if string is found in referer.
+ * (same as RefererReplace string - )
+ * Remark: RefererLog logs "-" instead of nothing!!
+ * RefererReplace string repl
+ * Replace referer information with repl, if
+ * string is found in referer.
+ * AgentLog fn For backwards compat. with log_agent module
+ *
+ *
+ * RefererReplace could be used to abstract referer information
+ * from e.g. a specific host, if a detailed URL information isn't
+ * needed. E.g. mark referer information of your own server as "Local":
+ * RefererReplace www.mydomain.com "Local"
+ * RefererReplace www.mypartner.de "Linked_From_My_Partner"
+ * This could minimize the size of logfiles and abstract information
+ * for e.g. statistic tools.
+ *---
* There can be any number of TransferLog and CustomLog
* commands. Each request will be logged to _ALL_ the
* named files, in the appropriate format.
@@ -106,7 +127,7 @@
* CustomLog logs/referer "%{referer}i -> %U"
* CustomLog logs/agent "%{user-agent}i"
*
- * Except: no RefererIgnore functionality
+ * Except:
* logs '-' if no Referer or User-Agent instead of nothing
*
* But using this method allows much easier modification of the
@@ -163,9 +184,31 @@
* server. If it doesn't have its own TransferLog, it writes to the
* same descriptor (meaning the same process for "| ...").
*
- * --- rst */
+ * --- rst
+ *
+ * 1998-11-24 [EMAIL PROTECTED]
+ * - merge mod_log_referer/mod_log_agent -> mod_log_config.c
+ * - AgentLog directive (for backwards compat.)
+ * - RefererLog directive (for backwards compat.)
+ * - RefererIgnore directive
+ * - RefererReplace directive (new)
+ * - Add predefined format nickname ELF
+ * ToDo: Bind RefererIgnore/Replace to format nickname
+ * (necessary?)
+ */
+
#define DEFAULT_LOG_FORMAT "%h %l %u %t \"%r\" %>s %b"
+/* $$$ see: http://www.netstore.de/Supply/http-analyze/manual/index.html
+ $$$ abrevations of logfilenames used by some statistic tools...
+ $$$ Standard predefined names makes life easy for non-expierienced
users
+*/
+#define COMBINED_LOG_FORMAT "%h %l %u %t \"%r\" %s %b \"%{Referer}i\"
\"%{User-agent}i\""
+#define EXTENDED_LOG_FORMAT "%h %l %u %t \"%r\" %s %b \"%{User-agent}i\"
\"%{Referer}i\""
+#define REFERER_LOG_FORMAT "%{referer}i -> %U"
+#define AGENT_LOG_FORMAT "%{user-agent}i"
+#define COOKIE_LOG_FORMAT "%{Cookie}n \"%r\" %t"
+
#include "httpd.h"
#include "http_config.h"
@@ -173,8 +216,16 @@
#include "http_log.h"
#include <limits.h>
+
module MODULE_VAR_EXPORT config_log_module;
+
+static const char *check_referer_replace(const char *referer,
+ array_header *referer_replace_list, request_rec *orig);
+
+
+
+
static int xfer_flags = (O_WRONLY | O_APPEND | O_CREAT);
#if defined(OS2) || defined(WIN32)
/* OS/2 dosen't support users and groups */
@@ -213,14 +264,24 @@
* which might be empty.
*/
+
+typedef struct {
+ char *str; /* search for str */
+ char *repl; /* replace with */
+} replace_entry;
+
typedef struct {
char *default_format_string;
array_header *default_format;
array_header *config_logs;
array_header *server_config_logs;
table *formats;
+ array_header *referer_replace_list;
} multi_log_state;
+
+
+
/*
* config_log_state holds the status of a single log file. fname might
* be NULL, which means this module does no logging for this
@@ -234,6 +295,7 @@
char *fname;
char *format_string;
array_header *format;
+ array_header *referer_replace_list;
int log_fd;
#ifdef BUFFERED_LOGS
int outcnt;
@@ -256,6 +318,7 @@
array_header *conditions;
} log_format_item;
+
static char *format_integer(pool *p, int i)
{
return ap_psprintf(p, "%d", i);
@@ -364,6 +427,7 @@
{
return ap_table_get(r->notes, a);
}
+
static const char *log_env_var(request_rec *r, char *a)
{
return ap_table_get(r->subprocess_env, a);
@@ -637,7 +701,7 @@
*/
static const char *process_item(request_rec *r, request_rec *orig,
- log_format_item *item)
+ log_format_item *item, config_log_state *cls)
{
const char *cp;
@@ -664,6 +728,17 @@
/* We do. Do it... */
cp = (*item->func) (item->want_orig ? orig : r, item->arg);
+
+ /* Referer handling
+ * - RefererReplace
+ */
+
+ if (cp && (*item->func == log_header_in)
+ && item->arg && !strcasecmp (item->arg,"referer")) {
+
+ cp = check_referer_replace (cp,cls->referer_replace_list,orig);
+ }
+
return cp ? cp : "-";
}
@@ -708,7 +783,7 @@
}
for (i = 0; i < format->nelts; ++i) {
- strs[i] = process_item(r, orig, &items[i]);
+ strs[i] = process_item(r, orig, &items[i], cls);
}
for (i = 0; i < format->nelts; ++i) {
@@ -785,11 +860,13 @@
multi_log_state *mls = (multi_log_state *) ap_palloc(p,
sizeof(multi_log_state));
mls->config_logs = ap_make_array(p, 1, sizeof(config_log_state));
+ mls->referer_replace_list = ap_make_array(p, 4,
sizeof(replace_entry));
mls->default_format_string = NULL;
mls->default_format = NULL;
mls->server_config_logs = NULL;
mls->formats = ap_make_table(p, 4);
ap_table_setn(mls->formats, "CLF", DEFAULT_LOG_FORMAT);
+ ap_table_setn(mls->formats, "ELF", EXTENDED_LOG_FORMAT);
return mls;
}
@@ -812,6 +889,10 @@
}
add->formats = ap_overlay_tables(p, base->formats, add->formats);
+ /* $$$ Something to Do for RefererReplace?
+ $$$ Inherit from master server?
+ */
+
return add;
}
@@ -861,7 +942,7 @@
cls->format = parse_log_string(cmd->pool, fmt, &err_string);
}
cls->log_fd = -1;
-
+ cls->referer_replace_list = mls->referer_replace_list;
return err_string;
}
@@ -872,9 +953,85 @@
static const char *set_cookie_log(cmd_parms *cmd, void *dummy, char *fn)
{
- return add_custom_log(cmd, dummy, fn, "%{Cookie}n \"%r\" %t");
+ return add_custom_log(cmd, dummy, fn, COOKIE_LOG_FORMAT);
}
+
+/* Backward compatibility (mod_log_referer.c, mod_log_agent.c)
+ * - RefererLog file
+ * Log referer information "uri -> document" to file
+ * - RefererIgnore host [host] ...
+ * Exclude RefererInfo from Log
+ * - RefererReplace string replacestring
+ * Replace RefererInfo
+ * - AgentLog file
+ */
+
+static const char *set_referer_log(cmd_parms *cmd, void *dummy, char *fn)
+{
+ return add_custom_log(cmd, dummy, fn, REFERER_LOG_FORMAT);
+}
+
+
+static const char *set_agent_log(cmd_parms *cmd, void *dummy, char *fn)
+{
+ return add_custom_log(cmd, dummy, fn, AGENT_LOG_FORMAT);
+}
+
+
+
+static const char *add_referer_replace(cmd_parms *cmd, void *dummy, char
*str,
+ char *repl)
+{
+ replace_entry *new_re;
+ multi_log_state *mls =
ap_get_module_config(cmd->server->module_config,
+ &config_log_module);
+
+ /* RefererReplace string replacestring */
+
+ if (str && repl) {
+ ap_str_tolower(str);
+ new_re = ap_push_array(mls->referer_replace_list);
+
+ new_re->str = str;
+ new_re->repl = repl;
+ }
+ return NULL;
+}
+
+
+static const char *add_referer_ignore(cmd_parms *parms, void *dummy, char
*arg)
+{
+ return add_referer_replace (parms,dummy,arg,"-");
+}
+
+
+/*
+ * Check if referer information should be replaced with repl-string.
+ */
+
+static const char *check_referer_replace(const char *referer,
+ array_header *r_list, request_rec *orig)
+
+{
+ replace_entry *r_entry,*rp;
+ char *referertest;
+ int i;
+
+
+ referertest = ap_pstrdup(orig->pool, referer);
+ ap_str_tolower(referertest);
+
+ r_entry = (replace_entry *) r_list->elts;
+ for (i=0; i < r_list->nelts; i++) {
+ rp = &r_entry[i];
+ if (strstr(referertest, rp->str)) return (const char *)rp->repl;
+ }
+
+ return referer;
+}
+
+
static const command_rec config_log_cmds[] =
{
{"CustomLog", add_custom_log, NULL, RSRC_CONF, TAKE2,
@@ -885,8 +1042,17 @@
"a log format string (see docs) and an optional format name"},
{"CookieLog", set_cookie_log, NULL, RSRC_CONF, TAKE1,
"the filename of the cookie log"},
+ {"RefererLog", set_referer_log, NULL, RSRC_CONF, TAKE1,
+ "the filename of the referer log"},
+ {"RefererIgnore", add_referer_ignore, NULL, RSRC_CONF, ITERATE,
+ "referer hostnames to ignore"},
+ {"RefererReplace", add_referer_replace, NULL, RSRC_CONF, TAKE2,
+ "referer hostnames to ignore"},
+ {"AgentLog", set_agent_log, NULL, RSRC_CONF, TAKE1,
+ "the filename of the agent log"},
{NULL}
};
+
static config_log_state *open_config_log(server_rec *s, pool *p,
config_log_state *cls,
