https://www.mediawiki.org/wiki/Special:Code/MediaWiki/115056
Revision: 115056
Author: faidon
Date: 2012-04-25 22:47:23 +0000 (Wed, 25 Apr 2012)
Log Message:
-----------
Update tree with what's in the apt repository
debian/changelog was missing the latest changes (even though the changes
themselves were commited) and debian/patches/udplog.diff was horribly outdated
with regards to what was in modules. Bring the tree back to a sane state.
Modified Paths:
--------------
trunk/debs/nginx/debian/changelog
trunk/debs/nginx/debian/patches/udplog.diff
Modified: trunk/debs/nginx/debian/changelog
===================================================================
--- trunk/debs/nginx/debian/changelog 2012-04-25 19:37:34 UTC (rev 115055)
+++ trunk/debs/nginx/debian/changelog 2012-04-25 22:47:23 UTC (rev 115056)
@@ -1,3 +1,16 @@
+nginx (0.7.65-4wmf1) lucid-wikimedia; urgency=low
+
+ * Applying fix for overly long user agents
+
+ -- Ryan Lane <[email protected]> Mon, 23 Jan 2012 02:09:43 +0000
+
+nginx (0.7.65-3wmf1) lucid-wikimedia; urgency=low
+
+ * Applying patches for escaping user agents in udplog module. Patches by
+ abemusic.
+
+ -- Ryan Lane <[email protected]> Thu, 21 Jan 2012 05:39:14 +0000
+
nginx (0.7.65-2wmf1) lucid-wikimedia; urgency=low
* Adding udplog module
Modified: trunk/debs/nginx/debian/patches/udplog.diff
===================================================================
--- trunk/debs/nginx/debian/patches/udplog.diff 2012-04-25 19:37:34 UTC (rev
115055)
+++ trunk/debs/nginx/debian/patches/udplog.diff 2012-04-25 22:47:23 UTC (rev
115056)
@@ -1,7 +1,8 @@
--- /dev/null
+++ b/modules/nginx-udplog/LICENCE
-@@ -0,0 +1,24 @@
+@@ -0,0 +1,25 @@
+* Copyright (c) 2010, Valery Kholodkov
++* Copyright (c) 2011, Ryan Lane
+* All rights reserved.
+*
+* Redistribution and use in source and binary forms, with or without
@@ -62,7 +63,7 @@
+
--- /dev/null
+++ b/modules/nginx-udplog/README
-@@ -0,0 +1,10 @@
+@@ -0,0 +1,37 @@
+
+Documentation for this module could be found under following URLs:
+
@@ -73,6 +74,33 @@
+ * Russian:
+
+ http://www.grid.net.ru/nginx/udplog.ru.html
++
++---------------------------------------------------------------------
++
++Test client usage:
++
++ usage: python test_client.py [-h] [-w W] [-l L] url
++
++ positional arguments:
++ url URL of the nginx web server to send requests to
++
++ optional arguments:
++ -h, --help show this help message and exit
++ -n N Number of random user agent strings to send (default=10)
++ -w W Seconds to wait between requests (default=0.25)
++ -l L Length of garbage user agent strings (default=50)
++
++
++ Note that this is mainly for testing that the User-Agent strings are
++ being properly encoded so before running this you'll need to configure
++ nginx to make use of the "access_updlog" command and add the new
++ variable $udplog_escaped-user_agent in your "log_format".
++
++ Once configured, the access logs will then be written to the defined
++ host via UDP. To see these you can listen on the port with socat and
++ write the data to stdout:
++
++ socat UDP-LISTEN:<port> STDOUT
--- /dev/null
+++ b/modules/nginx-udplog/config
@@ -0,0 +1,3 @@
@@ -81,7 +109,7 @@
+NGX_ADDON_SRCS="$NGX_ADDON_SRCS $ngx_addon_dir/ngx_http_udplog_module.c"
--- /dev/null
+++ b/modules/nginx-udplog/ngx_http_udplog_module.c
-@@ -0,0 +1,608 @@
+@@ -0,0 +1,682 @@
+
+/*
+ * Copyright (C) 2010 Valery Kholodkov
@@ -169,12 +197,20 @@
+ ngx_http_variable_value_t *v, uintptr_t data);
+static ngx_int_t ngx_http_udplog_sequence_variable(ngx_http_request_t *r,
+ ngx_http_variable_value_t *v, uintptr_t data);
++static ngx_int_t
ngx_http_udplog_escaped_user_agent_variable(ngx_http_request_t *r,
++ ngx_http_variable_value_t *v, uintptr_t data);
++static ngx_int_t
ngx_http_udplog_escaped_content_type_variable(ngx_http_request_t *r,
++ ngx_http_variable_value_t *v, uintptr_t data);
+
+static ngx_http_variable_t ngx_http_udplog_variables[] = {
+ { ngx_string("udplog_time"), NULL, ngx_http_udplog_time_variable, 0,
+ NGX_HTTP_VAR_NOCACHEABLE|NGX_HTTP_VAR_NOHASH, 0 },
+ { ngx_string("udplog_sequence"), NULL,
ngx_http_udplog_sequence_variable, 0,
+ NGX_HTTP_VAR_NOCACHEABLE|NGX_HTTP_VAR_NOHASH, 0 },
++ { ngx_string("udplog_escaped_user_agent"), NULL,
ngx_http_udplog_escaped_user_agent_variable, 0,
++ NGX_HTTP_VAR_NOCACHEABLE|NGX_HTTP_VAR_NOHASH, 0 },
++ { ngx_string("udplog_escaped_content_type"), NULL,
ngx_http_udplog_escaped_content_type_variable, 0,
++ NGX_HTTP_VAR_NOCACHEABLE|NGX_HTTP_VAR_NOHASH, 0 },
+
+ { ngx_null_string, NULL, NULL, 0, 0, 0 }
+};
@@ -288,6 +324,72 @@
+}
+
+static ngx_int_t
++ngx_http_udplog_escaped_user_agent_variable(ngx_http_request_t *r,
++ ngx_http_variable_value_t *v, uintptr_t data)
++{
++ u_char *ua;
++ uintptr_t escape;
++ size_t l;
++
++ // Check that the user agent string was processed. NULL seems
++ // to occur when the user agent string is very large (~8K)
++ if(r->headers_in.user_agent == NULL) {
++ return NGX_ERROR;
++ }
++
++ ua = r->headers_in.user_agent->value.data;
++ l = r->headers_in.user_agent->value.len;
++ escape = 2 * ngx_escape_uri(NULL, ua, l, NGX_ESCAPE_URI);
++
++ v->data = ngx_pnalloc(r->pool, l + escape);
++ if (v->data == NULL) {
++ return NGX_ERROR;
++ }
++
++ ngx_escape_uri(v->data, ua, l, NGX_ESCAPE_URI);
++
++ v->len = l + escape;
++ v->valid = 1;
++ v->no_cacheable = 0;
++ v->not_found = 0;
++
++ return NGX_OK;
++
++}
++
++static ngx_int_t
++ngx_http_udplog_escaped_content_type_variable(ngx_http_request_t *r,
++ ngx_http_variable_value_t *v, uintptr_t data)
++{
++ u_char *ct;
++ uintptr_t escape;
++ size_t l;
++
++ // Check that the content type string was processed.
++ if(r->headers_in.content_type == NULL) {
++ return NGX_ERROR;
++ }
++
++ ct = r->headers_in.content_type->value.data;
++ l = r->headers_in.content_type->value.len;
++ escape = 2 * ngx_escape_uri(NULL, ct, l, NGX_ESCAPE_URI);
++
++ v->data = ngx_pnalloc(r->pool, l + escape);
++ if (v->data == NULL) {
++ return NGX_ERROR;
++ }
++
++ ngx_escape_uri(v->data, ct, l, NGX_ESCAPE_URI);
++
++ v->len = l + escape;
++ v->valid = 1;
++ v->no_cacheable = 0;
++ v->not_found = 0;
++
++ return NGX_OK;
++}
++
++static ngx_int_t
+ngx_http_udplog_add_variables(ngx_conf_t *cf)
+{
+ ngx_http_variable_t *var, *v;
@@ -690,3 +792,70 @@
+
+ return NGX_OK;
+}
+--- /dev/null
++++ b/modules/nginx-udplog/test_client.py
+@@ -0,0 +1,64 @@
++##
++# See the README for usage
++##
++
++import argparse
++import urllib2
++import random
++import time
++
++USER_AGENTS = (
++ 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.6)
Gecko/20070725 Firefox/2.0.0.6',
++ 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)',
++ 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322;
.NET CLR 2.0.50727; .NET CLR 3.0.04506.30)',
++ 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; .NET CLR 1.1.4322)',
++ 'Mozilla/4.0 (compatible; MSIE 5.0; Windows NT 5.1; .NET CLR 1.1.4322)',
++ 'Opera/9.20 (Windows NT 6.0; U; en)',
++ 'Opera/9.00 (Windows NT 5.1; U; en)',
++ 'Mozilla/4.0 (compatible; MSIE 6.0; MSIE 5.5; Windows NT 5.1) Opera 7.02
[en]',
++ 'Googlebot-Image/1.0 ( http://www.googlebot.com/bot.html)',
++ 'msnbot-Products/1.0 (+http://search.msn.com/msnbot.htm)',
++
++ # really long user agent
++ 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322;
.NET CLR 2.0.50727; .NET CLR 3.0.04506.30)'*10,
++)
++
++def rand_ustring(n):
++ "Create n-char string of unicode"
++ return u"".join(unichr(random.randint(0x66d, 0x1000)) for i in xrange(n))
++
++if __name__ == "__main__":
++ parser = argparse.ArgumentParser()
++ parser.add_argument("url",
++ type=str,
++ help="URL of the nginx web server to send requests
to")
++ parser.add_argument("-n",
++ type=int,
++ help="Number of random user agent strings to send
(default=10)",
++ default=10)
++ parser.add_argument("-w",
++ type=float,
++ help="Seconds to wait between requests
(default=0.25)",
++ default=0.25)
++ parser.add_argument("-l",
++ type=int,
++ help="Length of garbage user agent strings
(default=50)",
++ default=50)
++ args = parser.parse_args()
++
++ # Send good user agents
++ for user_agent in USER_AGENTS:
++ req = urllib2.Request(args.url, headers={
++ "User-Agent": user_agent
++ })
++ urllib2.urlopen(req)
++ time.sleep(args.w)
++
++ # Send random unicode user agents
++ for i in xrange(args.n):
++ garbage = rand_ustring(args.l)
++ req = urllib2.Request(args.url, headers={
++ "User-Agent": garbage.encode('utf-8')
++ })
++ urllib2.urlopen(req)
++ time.sleep(args.w)
_______________________________________________
MediaWiki-CVS mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-cvs
