Created
August 10, 2015 10:35
-
-
Save wappy100/c8fed09a220f59146c80 to your computer and use it in GitHub Desktop.
accesslog parse sample
This file contains hidden or 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
| #!/usr/bin/env ruby | |
| require 'net/http' | |
| require 'uri' | |
| require 'json' | |
| require 'date' | |
| require 'find' | |
| require 'erb' | |
| require 'em-synchrony' | |
| require 'em-synchrony/em-http' | |
| require 'em-synchrony/fiber_iterator' | |
| module ApacheLog | |
| class Entry | |
| def initialize(args) | |
| @ip_address = args[:ip_address] | |
| @identity_check = args[:identity_check] | |
| @user = args[:user] | |
| @datetime = args[:datetime] | |
| @request = args[:request] | |
| @status = args[:status] | |
| @size = args[:size] | |
| @referer = args[:referer] | |
| @user_agent = args[:user_agent] | |
| @cookie = args[:cookie] | |
| end | |
| attr_reader :ip_address, | |
| :identity_check, | |
| :user, | |
| :datetime, | |
| :request, | |
| :status, | |
| :size, | |
| :referer, | |
| :user_agent, | |
| :cookie | |
| def self.parse(line) | |
| match = line.match(log_pattern) | |
| raise "parse error\n at line: <#{line}> \n" if match.nil? | |
| captures = match.captures | |
| self.new({ | |
| :ip_address => captures[0], | |
| :identity_check => captures[1], | |
| :user => captures[2], | |
| :datetime => parse_datetime(captures[3]), | |
| :request => parse_request(captures[4]), | |
| :status => captures[5], | |
| :size => captures[6], | |
| :referer => captures[7], | |
| :user_agent => captures[8], | |
| :cookie => captures[9], | |
| }) | |
| end | |
| # private class methods | |
| def self.log_pattern | |
| / | |
| ^ | |
| (\S+) # ip_address | |
| \s+ | |
| (\S+) # identity_check | |
| \s+ | |
| (\S+) # user | |
| \s+ | |
| \[ (.*?) \] # date | |
| \s+ | |
| " (.*?) " # request | |
| \s+ | |
| (\S+) # status | |
| \s+ | |
| (\S+) # size | |
| \s+ | |
| " (.*?) " # referer | |
| \s+ | |
| " (.*?) " # user_agent | |
| \s+ | |
| " (.*?) " # cookie | |
| $ | |
| /x | |
| end | |
| def self.parse_datetime(str) | |
| DateTime.strptime( str, '%d/%b/%Y:%T %z') | |
| end | |
| def self.parse_request(str) | |
| method, path, protocol = str.split | |
| { | |
| :method => method, | |
| :path => path, | |
| :protocol => protocol | |
| } | |
| end | |
| private_class_method :log_pattern, :parse_datetime, :parse_request | |
| end | |
| end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment