Last active
December 31, 2018 18:36
-
-
Save salrashid123/7377fc4d279ac2e002fcd9ed005a922b to your computer and use it in GitHub Desktop.
Google fluentd parser for nginx HttpRequest.proto logs (/opt/google-fluentd/embedded/lib/ruby/gems/2.4.0/gems/fluentd-1.2.5/lib/fluent/plugin/parser_nginx.rb)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'fluent/plugin/parser' | |
module Fluent | |
module Plugin | |
class NginxParser < Parser | |
Plugin.register_parser('nginx', self) | |
REGEXP = /^(?<host>[^ ]*) [^ ]* (?<user>[^ ]*) \[(?<time>[^\]]*)\] "(?<method>\S+)(?: +(?<path>(?:[^\"]|\\.)*?)(?: +\S*)?)?" (?<code>[^ ]*) (?<response_size>[^ ]*)(?: "(?<referer>(?:[^\"]|\\.)*)" "(?<agent>[^\"]*)"(?:\s+\"?(?<x_forwarded_for>[^\"]*)\"?)?) "(?<latency>[^\"]*)" "(?<http_x_cloud_trace_context>[^\"]*)"?$/ | |
TIME_FORMAT = "%d/%b/%Y:%H:%M:%S %z" | |
def initialize | |
super | |
@mutex = Mutex.new | |
end | |
def configure(conf) | |
super | |
@time_parser = time_parser_create(format: TIME_FORMAT) | |
end | |
def patterns | |
{'format' => REGEXP, 'time_format' => TIME_FORMAT} | |
end | |
def parse(text) | |
m = REGEXP.match(text) | |
unless m | |
yield nil, nil | |
return | |
end | |
host = m['host'] | |
host = (host == '-') ? nil : host | |
user = m['user'] | |
user = (user == '-') ? nil : user | |
time = m['time'] | |
time = @mutex.synchronize { @time_parser.parse(time) } | |
method = m['method'] | |
path = m['path'] | |
code = m['code'].to_i | |
code = nil if code == 0 | |
response_size = m['response_size'] | |
response_size = (response_size == '-') ? nil : response_size.to_i | |
referer = m['referer'] | |
referer = (referer == '-') ? nil : referer | |
agent = m['agent'] | |
agent = (agent == '-') ? nil : agent | |
x_forwarded_for = m['x_forwarded_for'] | |
x_forwarded_for = (x_forwarded_for == '-') ? nil : x_forwarded_for | |
latency = m['latency'] | |
latency = (latency == '-') ? nil : latency | |
http_x_cloud_trace_context = m['http_x_cloud_trace_context'] | |
#http_x_cloud_trace_context = (http_x_cloud_trace_context == '-') ? nil : http_x_cloud_trace_context | |
if http_x_cloud_trace_context == '-' | |
trace = '' | |
span_id = '' | |
else | |
trace = http_x_cloud_trace_context.split('/').first | |
span_id = http_x_cloud_trace_context.split('/').last | |
end | |
record = { | |
"host" => host, | |
"user" => user, | |
"method" => method, | |
"path" => path, | |
"code" => code, | |
"response_size" => response_size, | |
"referer" => referer, | |
"agent" => agent, | |
"x_forwarded_for" => x_forwarded_for, | |
"latency" => latency, | |
"http_x_cloud_trace_context" => trace, | |
"span_id" => span_id | |
} | |
record["time"] = m['time'] if @keep_time_key | |
yield time, record | |
end | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment