From 90d654c46c6a66cb996f4c7a89293ea477bb6dc8 Mon Sep 17 00:00:00 2001
From: Matt Palmer <mpalmer@hezmatt.org>
Date: Wed, 28 Jun 2017 14:34:41 +1000
Subject: [PATCH] Include HTTP Host header in nginx logs

This is crucial in multisite installations, because otherwise the nginx logs
are fairly useless, however it can also be quite handy to know what
hostnames are being sent to your site.  The variable is quoted, because it
is untrusted input (it is taken directly from the HTTP request), but nginx
helpfully escapes the quoting character automagically, so we don't have to
worry about that.

For now, the log analysis plugin *recognises* the new log format
(and continues to recognise the previous format, for backwards
compatibility), but doesn't do anything with the new log entry field.  This
means your multisite performance plugin data is still broken, but it's no
worse than it was before.
---
 config/nginx.sample.conf                                      | 2 +-
 .../discourse-nginx-performance-report/lib/log_analyzer.rb    | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/config/nginx.sample.conf b/config/nginx.sample.conf
index 5c26da3428d..d1ff7d8cbb6 100644
--- a/config/nginx.sample.conf
+++ b/config/nginx.sample.conf
@@ -25,7 +25,7 @@ map $http_x_forwarded_proto $thescheme {
   https https;
 }
 
-log_format log_discourse '[$time_local] $remote_addr "$request" "$http_user_agent" "$sent_http_x_discourse_route" $status $bytes_sent "$http_referer" $upstream_response_time $request_time "$sent_http_x_discourse_username"';
+log_format log_discourse '[$time_local] "$http_host" $remote_addr "$request" "$http_user_agent" "$sent_http_x_discourse_route" $status $bytes_sent "$http_referer" $upstream_response_time $request_time "$sent_http_x_discourse_username"';
 
 server {
 
diff --git a/plugins/discourse-nginx-performance-report/lib/log_analyzer.rb b/plugins/discourse-nginx-performance-report/lib/log_analyzer.rb
index de23062c43b..79cac5163ad 100644
--- a/plugins/discourse-nginx-performance-report/lib/log_analyzer.rb
+++ b/plugins/discourse-nginx-performance-report/lib/log_analyzer.rb
@@ -3,12 +3,12 @@ class LogAnalyzer
   class LineParser
 
 
-    # log_format log_discourse '[$time_local] $remote_addr "$request" "$http_user_agent" "$sent_http_x_discourse_route" $status $bytes_sent "$http_referer" $upstream_response_time $request_time "$sent_http_x_discourse_username"';
+    # log_format log_discourse '[$time_local] "$http_host" $remote_addr "$request" "$http_user_agent" "$sent_http_x_discourse_route" $status $bytes_sent "$http_referer" $upstream_response_time $request_time "$sent_http_x_discourse_username"';
 
     attr_accessor :time, :ip_address, :url, :route, :user_agent, :rails_duration, :total_duration,
                   :username, :status, :bytes_sent, :referer
 
-    PATTERN = /\[(.*)\] (\S+) \"(.*)\" \"(.*)\" \"(.*)\" ([0-9]+) ([0-9]+) \"(.*)\" ([0-9.]+) ([0-9.]+) "(.*)"/
+    PATTERN = /\[(.*)\](?: ".*")? (\S+) \"(.*)\" \"(.*)\" \"(.*)\" ([0-9]+) ([0-9]+) \"(.*)\" ([0-9.]+) ([0-9.]+) "(.*)"/
 
     TIME_FORMAT = "%d/%b/%Y:%H:%M:%S %Z"