log_analysis 0.1.4

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "log_analysis"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/log_analysis.rb

@@ -0,0 +1,52 @@
+require 'log_analysis/version'
+require 'log_analysis/preprocess'
+require 'log_analysis/user_identification'
+require 'log_analysis/session_identification'
+require 'log_analysis/transformation'
+require 'log_analysis/rule_generation'
+require 'time'
+
+class LogAnalysis
+  class Error < StandardError; end
+  # Your code goes here...
+
+  attr_reader :path, :type, :cleaned_data
+
+  def initialize(path, type = nil)
+    @path         = path
+    @type         = type
+    @cleaned_data = PreProcess.input(path, type) do |record|
+      if block_given?
+        yield(record) ? record : nil
+      else
+        record
+      end
+    end
+  end
+
+  def identified_user
+    UserIdentification.execute(@cleaned_data)
+  end
+
+  def identified_session
+    SessionIdentification.execute(@cleaned_data)
+  end
+
+  def transformation
+    Transformation.execute(identified_session)
+  end
+
+  def rule_generation(conf = 0.5, sup = 60)
+    result = RuleGeneration.execute(transformation, conf, sup)
+    move_data
+    result
+  end
+
+  def move_data
+    return unless File.directory?('/home/app/data/waazabag/')
+
+    system('mv', "transform_data_#{Time.now.strftime('%Y%m%d')}.txt", '/home/app/data/waazabag/')
+    system('mv', "output_#{Time.now.strftime('%Y%m%d')}.txt", '/home/app/data/waazabag/')
+    system('mv', "map_uri_#{Time.now.strftime('%Y%m%d')}.txt", '/home/app/data/waazabag/')
+  end
+end

data/lib/log_analysis/model/record.rb

@@ -0,0 +1,84 @@
+require 'ipaddr'
+require 'useragent'
+require 'log_analysis/model/user_identity'
+require 'active_support/core_ext/numeric/time'
+
+class Record
+  attr_accessor :time,
+                :host,
+                :status,
+                :size,
+                :request_length,
+                :req,
+                :method,
+                :uri,
+                :referer,
+                :ua,
+                :reqtime,
+                :runtime,
+                :apptime,
+                :cache,
+                :vhost,
+                :user,
+                :forwardedfor,
+                :forwardedproto
+
+  attr_reader   :params
+
+  DATA_TYPE = %w[.txt .json .js .css .jpg .jpeg .gif .woff2 .ico .png .bmp .mp3 .wav .avi .mpeg .vmw .mpg .map .pdf .doc .svg .otf].freeze
+  REGEX_BOT = /facebookexternalhit|Mediapartners-Google|AWS|-|Crawler|spider|Detection/.freeze
+
+  def initialize(params)
+    @params = params
+    record_params.keys.each { |key| instance_variable_set("@#{key}", record_params[key]) }
+  end
+
+  def status_200?
+    status == 200
+  end
+
+  def method_get?
+    method == 'GET'
+  end
+
+  def uri_without_data
+    return false if uri.nil? || uri.end_with?(*DATA_TYPE)
+
+    true
+  end
+
+  def robot?
+    ua.bot? || ua.to_s.match?(REGEX_BOT)
+  end
+
+  private
+
+  def record_params
+    {}.tap do |p|
+      p['time']           = Time.parse(@params['time'].split.first.sub(/:/, ' ')) || nil
+      p['host']           = IPAddr.new(@params['host'])
+      p['status']         = @params['status'].to_i || 0
+      p['size']           = @params['size'].to_i || 0
+      p['request_length'] = @params['request_length'].to_i || 0
+      p['req']            = validate_string(@params['req'])
+      p['method']         = validate_string(@params['method'])
+      p['uri']            = validate_string(@params['uri'])
+      p['referer']        = validate_string(@params['referer'])
+      p['ua']             = UserAgent.parse(@params['ua'])
+      p['reqtime']        = @params['reqtime'].to_f
+      p['runtime']        = @params['runtime'].to_f
+      p['apptime']        = @params['apptime'].to_f
+      p['cache']          = validate_string(@params['cache'])
+      p['vhost']          = validate_string(@params['vhost'])
+      p['user']           = @params['user'] || nil
+      p['forwardedfor']   = validate_string(@params['forwardedfor'])
+      p['forwardedproto'] = validate_string(@params['forwardedproto'])
+    end
+  rescue IPAddr::InvalidAddressError => e
+    puts e
+  end
+
+  def validate_string(value)
+    value == '-' ? nil : value
+  end
+end

data/lib/log_analysis/model/session_identity.rb

@@ -0,0 +1,8 @@
+class SessionIdentity
+  attr_accessor :user, :records
+
+  def initialize(params)
+    @user    = params[:user]
+    @records = params[:records]
+  end
+end

data/lib/log_analysis/model/user_identity.rb

@@ -0,0 +1,13 @@
+require 'active_support/core_ext/module/delegation'
+require 'useragent'
+
+class UserIdentity
+  attr_accessor :host, :user_agent
+
+  delegate :browser, :version, :os, :platform, :mobile?, :application, :localization, to: :user_agent
+
+  def initialize(params)
+    @host       = params[:host]
+    @user_agent = params[:user_agent]
+  end
+end

data/lib/log_analysis/preprocess.rb

@@ -0,0 +1,72 @@
+require 'log_analysis/model/record'
+require 'log_analysis/model/user_identity'
+require 'json'
+
+module PreProcess
+  class Error < StandardError; end
+  # Your code goes here...
+
+  REGEX_KEYS   = /(time:| host:| status:| size:| request_length:| req:| method:| uri:| referer:| ua:| reqtime:| runtime:| apptime:| cache:| vhost:| server:| user:| forwardedfor:| forwardedproto:)/.freeze
+  REGEX_NGINX  = /\A^(?<host>\S*) (?<identity>\S*) (?<user>\S*) \[(?<time>[^\]]*)\] "(?<method>\S+)(?: +(?<path>[^\"]*?)(?:\s+\S*)?)?" (?<code>\S*) (?<size>\S*)(?: "(?<referer>[^\"]*)" "(?<agent>[^\"]*)"(?:\s+(?<http_x_forwarded_for>\S+))?)?$/.freeze
+  REGEX_APACHE = %r{(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}) - (.{0})- \[([^\]]+?)\] "(GET|POST|PUT|DELETE) ([^\s]+?) (HTTP\/1\.1)" (\d+) (\d+) "-" "(.*)"}.freeze
+
+  CONVERT_RECORD = { 'nginx' => 'convert_nginx_logs', 'apache' => 'convert_apache_logs', 'default' => 'to_records' }.freeze
+
+  def self.input(file_path, type)
+    @users    = []
+    text_file = File.readlines(file_path)
+
+    text_file.each_with_object([]).with_index do |(line, arr), i|
+      preprocessed_log = type.nil? ? line.gsub(/[\t]/i, ' ').chomp! : line
+      record_params    = send(CONVERT_RECORD[type.nil? ? 'nginx' : type], preprocessed_log)
+      record           = Record.new(record_params) if record_params && preprocessed_log
+      record           = yield(record) if block_given? && record
+
+      arr.push(record) if record && record.status_200? && record.method_get? && record.uri_without_data && !record.robot?
+
+      system('clear')
+      puts "#{((i.to_f / text_file.size) * 100).round}/100"
+    end
+  end
+
+  def self.to_record(log)
+    o = log.gsub!('\t', ' ')
+    o = log.split(REGEX_KEYS)
+    o = o.map(&:strip)
+    o.delete('')
+    o.each_slice(2).to_a.each_with_object({}) { |pair, log_obj| log_obj.merge!(to_json(pair)) }
+  end
+
+  def self.convert_nginx_logs(log)
+    o = log.split(REGEX_NGINX)
+
+    return false if o.size <= 1
+    o.delete('')
+
+    {}.tap do |p|
+      p['host']      = o[0]
+      p['user']      = o[2]
+      p['time']      = o[3]
+      p['method']    = o[4]
+      p['uri']       = o[5]
+      p['status']    = o[6]
+      p['size']      = o[7]
+      p['referer']   = o[8]
+      p['ua']        = o[9]
+      p['forwarded'] = o[10]
+      p['user']      = save_user(o)
+    end
+  end
+
+  def self.to_json(pair)
+    { pair.first.delete(':') => pair.last }
+  end
+
+  def self.save_user(log)
+    user = @users.find { |i| i.host == log[0] && i.user_agent.to_s == log[9] }
+    return user unless user.nil?
+
+    @users.push(UserIdentity.new(host: IPAddr.new(log[0]), user_agent: UserAgent.parse(log[9])))
+    @users.last
+  end
+end

data/lib/log_analysis/rule_generation.rb

@@ -0,0 +1,59 @@
+require 'time'
+require 'log_analysis/version'
+
+module RuleGeneration
+  JAR_FILE_PATH       = File.join(File.dirname(__FILE__), './files/spmf.jar')
+  TRANSFORM_DATA_PATH = "transform_data_#{Time.now.strftime('%Y%m%d')}.txt".freeze
+  RULE_FILE_PATH      = "output_#{Time.now.strftime('%Y%m%d')}.txt".freeze
+  MAP_URI_FILE_PATH   = "map_uri_#{Time.now.strftime('%Y%m%d')}.txt".freeze
+
+  class Error < StandardError; end
+  # Your code goes here...
+
+  def self.execute(transform_data, min_conf, min_sup)
+    File.open(TRANSFORM_DATA_PATH, 'w+') { |f| transform_data.keys.each { |e| f.puts(transform_data[e].map { |i| i.is_a?(Array) ? i.join(' ') : i }.join(' -1 ').concat(' -1 -2')) } }
+    system("java -jar #{JAR_FILE_PATH} run SPADE #{TRANSFORM_DATA_PATH} #{RULE_FILE_PATH} #{min_sup}%")
+    result = rule_gen(get_seq(File.read(RULE_FILE_PATH)), min_conf)
+    map_uri = File.read(MAP_URI_FILE_PATH).split(' ')
+
+    result.map do |rule|
+      seq, sub, rea = rule
+      [seq.map { |i| map_uri[i.to_i] }, sub.map { |i| map_uri[i.to_i] }, rea]
+    end
+  end
+
+  def self.rule_gen(seqs, min_conf)
+    seqs.each_with_object([]) { |seq, arr| seqs.each { |sub| arr.push([seq[0], sub[0], seq[1] / sub[1]]) if sub[0] != seq[0] && sub_seq?(sub[0], seq[0]) && seq[1] / sub[1] >= min_conf } }
+  end
+
+  def self.sub_seq?(first, second)
+    ptr = 0
+    first.each do |sub|
+      return false if ptr >= second.size
+
+      (ptr..second.size - 1).each do |n|
+        if sub?(second[n], sub)
+          ptr = n + 1
+          break
+        end
+        return false if ptr == second.size - 1
+      end
+    end
+    true
+  end
+
+  def self.sub?(str, sub)
+    mark_sub = 0
+    sub.split(' ').each { |char| mark_sub += 1 if str.include?(char) }
+
+    mark_sub == sub.split(' ').size
+  end
+
+  def self.get_seq(seq_str)
+    seq = seq_str.split("\n")
+    seq.each_with_object([]) do |s, arr|
+      split_seq = s.split('-1')
+      arr.push([split_seq[0..-2], split_seq[-1][-1].to_f])
+    end
+  end
+end

data/lib/log_analysis/session_identification.rb

@@ -0,0 +1,29 @@
+require 'active_support/core_ext/numeric/time'
+require 'log_analysis/model/session_identity'
+
+module SessionIdentification
+  MINUTE_THRESHOLD = 10
+
+  class Error < StandardError; end
+  # Your code goes here...
+
+  def self.execute(cleaned_data)
+    cleaned_data.each_with_object([]) do |record, arr|
+      isession = arr.rindex { |s| s.user == record.user }
+      isession.present? && validate_time_session(arr[isession].records.last.time, record.time) ? arr[isession].records << record : arr << SessionIdentity.new(session_identity_params(record))
+    end
+  end
+
+  private
+
+  def self.session_identity_params(record)
+    {}.tap do |p|
+      p[:user]    = record.user
+      p[:records] = [record]
+    end
+  end
+
+  def self.validate_time_session(last_session_record_time, time)
+    (time - last_session_record_time) / 60 < MINUTE_THRESHOLD
+  end
+end

data/lib/log_analysis/transformation.rb

@@ -0,0 +1,26 @@
+require 'log_analysis/model/session_identity'
+require 'log_analysis/model/user_identity'
+require 'log_analysis/version'
+
+module Transformation
+  MAP_URI_FILE_PATH = "map_uri_#{Time.now.strftime('%Y%m%d')}.txt".freeze
+
+  class Error < StandardError; end
+  # Your code goes here...
+
+  def self.execute(identified_session)
+    map_uri = []
+    transform = identified_session.each_with_object({}) do |v, hash|
+      uries = v.records.map(&:uri)
+      uries.each { |i| map_uri.push(i) unless map_uri.include?(i) }
+      if hash.key?(v.user.host.to_s)
+        uries.size == 1 ? hash[v.user.host.to_s] += v.records.map { |i| map_uri.index(i.uri) } : hash[v.user.host.to_s].push(v.records.map { |i| map_uri.index(i.uri) })
+      else
+        hash.merge!(v.user.host.to_s => v.records.map { |i| map_uri.index(i.uri) })
+      end
+    end
+
+    File.open(MAP_URI_FILE_PATH, 'w+') { |f| f.write(map_uri.join(' ')) }
+    transform
+  end
+end

data/lib/log_analysis/user_identification.rb

@@ -0,0 +1,11 @@
+require 'ipaddr'
+require 'log_analysis/model/user_identity'
+
+module UserIdentification
+  class Error < StandardError; end
+  # Your code goes here...
+
+  def self.execute(cleaned_data)
+    cleaned_data.map(&:user).uniq
+  end
+end

data/lib/log_analysis/version.rb

@@ -0,0 +1,3 @@
+class LogAnalysis
+  VERSION   = '0.1.4'
+end

data/log_analysis.gemspec

@@ -0,0 +1,31 @@
+require_relative 'lib/log_analysis/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "log_analysis"
+  spec.version       = LogAnalysis::VERSION
+  spec.authors       = ["Michael Tran"]
+  spec.email         = ["mictran205@gmail.com"]
+
+  spec.summary       = 'Log Analysis for thesis Huflit'
+  spec.description   = 'Preprocess step of web mining'
+  spec.homepage      = 'https://github.com/michaelt0520/log_analysis_thesis'
+  spec.license       = "MIT"
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
+
+  # spec.metadata["allowed_push_host"] = "TODO: Set to 'http://mygemserver.com'"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = "https://github.com/michaelt0520/log_analysis_thesis"
+
+  spec.add_dependency "useragent", "~> 0.16.10"
+  spec.add_dependency "activesupport", "~> 6.0.3.1"
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+end

metadata

@@ -0,0 +1,96 @@
+--- !ruby/object:Gem::Specification
+name: log_analysis
+version: !ruby/object:Gem::Version
+  version: 0.1.4
+platform: ruby
+authors:
+- Michael Tran
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2020-07-14 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: useragent
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.16.10
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.16.10
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 6.0.3.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 6.0.3.1
+description: Preprocess step of web mining
+email:
+- mictran205@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".ruby-version"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- Rakefile
+- access.log
+- bin/console
+- bin/setup
+- lib/log_analysis.rb
+- lib/log_analysis/files/spmf.jar
+- lib/log_analysis/model/record.rb
+- lib/log_analysis/model/session_identity.rb
+- lib/log_analysis/model/user_identity.rb
+- lib/log_analysis/preprocess.rb
+- lib/log_analysis/rule_generation.rb
+- lib/log_analysis/session_identification.rb
+- lib/log_analysis/transformation.rb
+- lib/log_analysis/user_identification.rb
+- lib/log_analysis/version.rb
+- log_analysis.gemspec
+homepage: https://github.com/michaelt0520/log_analysis_thesis
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/michaelt0520/log_analysis_thesis
+  source_code_uri: https://github.com/michaelt0520/log_analysis_thesis
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.3.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.1.2
+signing_key:
+specification_version: 4
+summary: Log Analysis for thesis Huflit
+test_files: []