cloud_frond request log analyser for IP frequency

cloud_front.rb

class CloudFront < RequestLogAnalyzer::FileFormat::Base
  extend RequestLogAnalyzer::FileFormat::CommonRegularExpressions

  line_definition :access do |line|
    line.header = true
    line.footer = true

    line.regexp = /^(#{timestamp('%Y-%m-%d	%H:%M:%S')})\s(\w+)\s(\d+)\s(#{ip_address})\s(\w+)\s(\S+)\s(\S+)\s(\d+)\s(\S+)\s(\S+)\s(\S+)\s(\S+)\s(\w+)\s(\S+)\s(\S+)\s(\w+)\s(\d+)\s(\S+)\s(#{ip_address}|-)\s+(\S+)\s(\S+)\s(\w+)\s(\S+)/

    line.capture(:timestamp).as(:timestamp)
    line.capture(:edge_location)
    line.capture(:bytes_sent).as(:traffic, unit: :byte)
    line.capture(:remote_ip)
  end

  report do |analyze|

    analyze.frequency category: :remote_ip, title: 'Most active clients'
  end

  class Request < RequestLogAnalyzer::Request
    # Do not use DateTime.parse, but parse the timestamp ourselves to return a integer
    # to speed up parsing.
    def convert_timestamp(value, _definition)
      "#{value[0, 4]}#{value[5, 2]}#{value[8, 2]}#{value[11, 2]}#{value[14, 2]}#{value[17, 2]}".to_i
    end
  end
end