-
-
Save MichalBryxi/5683991 to your computer and use it in GitHub Desktop.
Ever wanted to know why your grok patterns does not work? This might help a little.
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 'rubygems' | |
require 'pp' | |
# gem install jsl-grok | |
require 'grok-pure' | |
# Variable just to DRY it | |
BASE_PATH = '/home/michal/iw/puppet/modules/logstash/files' | |
# Set where are your grok patterns stored | |
PATTERN_GLOB = [ | |
"#{BASE_PATH}/grok_patterns/*", | |
"#{BASE_PATH}/grok.d/access_log" | |
] | |
# Text to match | |
TEXT = "lib01.intraworlds-resources.com | 80 | 178.199.249.47 | [31/May/2013:11:46:31 +0200] | GET /portal/application-v6.0//VERSION_72458/jquery-lib/prettyPhoto/js/jquery.prettyPhoto.js HTTP/1.1 | 200 | 6016 | https://www.bws-world.de/user/profile | Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:21.0) Gecko/20100101 Firefox/21.0 | 1817 | -" | |
# Try this match pattern out and see what shakes. | |
PATTERN = '%{IPORHOST:domain} \| %{NUMBER:port} \| %{IPORHOST:clientip} \| \[%{HTTPDATE:timestamp}\] \| %{WORD:verb} %{URIPATHPARAM:request} HTTP/%{NUMBER:httpversion} \| %{NUMBER:response} \| (?:%{NUMBER:bytes}|-) \| (?:%{URI:referrer}|-) \| %{DATA:agent} \| %{NUMBER:duration:int} \| (?:%{WORD:phpsessid}|-)' | |
# Set a new matcher | |
grok = Grok.new | |
# Load patterns | |
PATTERN_GLOB.each do |glob| | |
Dir.glob(glob).each do |file| | |
grok.add_patterns_from_file(file) | |
end | |
end | |
grok.compile(PATTERN) | |
match = grok.match(TEXT) | |
if match == false | |
puts "Pattern:\n%s\n\nDoes not match input:\n%s" % [PATTERN, TEXT] | |
else | |
pp match.captures | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment