fluent-plugin-cloudfront-log-v0.14-fix 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: bddf4c6de34233ea0fc327a2620d1739598e041d
+  data.tar.gz: 53f6abff048836b78e187046a5a3647bcf64d155
+SHA512:
+  metadata.gz: fd657fc1db7d5c378f54ea1fd4c4c42be6d114864360749a1d8cd448e9479d7c6db64a1e3626d6329dca4a0a2774ead543be4db7e96b74cddbee4c072c35ee8a
+  data.tar.gz: fc97ec882180002c0756b9a4cc559769205d6a68d565226bfd1382a612e90a65a79380b7b470d51c7bf5f15adcb8ba9a395d891897a0519a57c27163c7504f3c

data/.gitignore

@@ -0,0 +1,42 @@
+# Created by https://www.gitignore.io/api/ruby
+
+### Ruby ###
+.bin
+*.gems
+*.gem
+*.rbc
+/.config
+/coverage/
+/InstalledFiles
+/pkg/
+/spec/reports/
+/spec/examples.txt
+/test/tmp/
+/test/version_tmp/
+/tmp/
+
+## Specific to RubyMotion:
+.dat*
+.repl_history
+build/
+
+## Documentation cache and generated files:
+/.yardoc/
+/_yardoc/
+/doc/
+/rdoc/
+
+## Environment normalization:
+/.bundle/
+/vendor/bundle
+/lib/bundler/man/
+
+# for a library or gem, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+Gemfile.lock
+.ruby-version
+.ruby-gemset
+
+# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
+.rvmrc
+

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in fluent-plugin-cloudfront-log-v0.14-fix.gemspec
+gemspec

data/README.md

@@ -0,0 +1,94 @@
+# Fluent::Plugin::Cloudfront::Log
+This plugin will connect to the S3 bucket that you store your cloudfront logs in. Once the plugin processes them and ships them to FluentD, it moves them to another location(either another bucket or sub directory).
+
+This is a fork of https://github.com/kubihie/fluent-plugin-cloudfront-log with a
+fix with regards to fluentd v0.14 error. This is a temporary gem that I would
+publish until PR https://github.com/kubihie/fluent-plugin-cloudfront-log/pull/9
+is merged.
+
+## Example config
+```
+<source>
+@type       cloudfront_log
+log_bucket  cloudfront-logs
+log_prefix  production
+region      us-east-1
+interval    300
+aws_key_id  xxxxxx
+aws_sec_key xxxxxx
+tag         reverb.cloudfront
+verbose     true
+</source>
+```
+
+## Configuration options
+
+#### log_bucket
+This option tells the plugin where to look for the cloudfront logs
+
+#### log_prefix
+For example if your logs are stored in a folder called "production" under the "cloudfront-logs" bucket, your logs would be stored in cloudfront like "cloudfront-logs/production/log.gz".
+In this case, you'd want to use the prefix "production".
+
+#### moved_log_bucket
+Here you can specify where you'd like the log files to be moved after processing. If left blank this defaults to a folder called `_moved` under the bucket configured for `@log_bucket`.
+
+#### moved_log_prefix
+This specifices what the log files will be named once they're processed. This defaults to `_moved`.
+
+#### region
+The region where your cloudfront logs are stored.
+
+#### interval
+This is the rate in seconds at which we check the bucket for updated logs. This defaults to 300.
+#### aws_sec_id
+The ID of your AWS keypair. Note: Since this plugin uses aws-sdk under the hood you can leave these two aws fields blank if you have an IAM role applied to your FluentD instance.
+
+#### aws_sec_key
+The secret key portion of your AWS keypair
+
+#### tag
+This is a FluentD builtin.
+
+#### thread_num
+The number of threads to create to concurrently process the S3 objects. Defaults to 4.
+
+#### s3_get_max
+Control the size of the S3 fetched list on each iteration. Default to 200.
+
+#### delimiter
+You shouldn't have to specify delimiter at all but this option is provided and passed to the S3 client in the event that you have a weird delimiter in your log file names. Defaults to `nil`.
+
+#### verbose
+Turn this on if you'd like to see verbose information about the plugin and how it's processing your files.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'fluent-plugin-cloudfront-log-v0.14-fix'
+```
+
+And then execute:
+
+$ bundle
+
+Or install it yourself as:
+
+$ gem install 'fluent-plugin-cloudfront-log-v0.14-fix'
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/packetloop/fluent-plugin-cloudfront-log-v0.14-fix.
+
+## Credits
+
+kubihie
+

data/Rakefile

@@ -0,0 +1,11 @@
+require "bundler/gem_tasks"
+
+require "rake/testtask"
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+
+task :default => :test

data/fluent-plugin-cloudfront-log-v0.14-fix.gemspec

@@ -0,0 +1,25 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+
+Gem::Specification.new do |spec|
+  spec.name          = "fluent-plugin-cloudfront-log-v0.14-fix"
+  spec.version       = "0.0.1"
+  spec.authors       = ["lenfree"]
+  spec.email         = ["lenfree.yeung@gmail.com"]
+
+  spec.summary       = %q{AWS CloudFront log input plugin with temporary fix for v0.14. Credit to kubihie.}
+  spec.description   = %q{AWS CloudFront log input plugin for fluentd. This repo is temporary until PR to upstream is addressed.}
+  spec.homepage      = "https://github.com/packetloop/fluent-plugin-cloudfront-log-v0.14-fix"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "fluentd", "~> 0"
+  spec.add_dependency "aws-sdk", "~> 2.1"
+  spec.add_development_dependency "bundler"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency 'test-unit', "~> 2"
+end

data/lib/fluent/plugin/in_cloudfront_log.rb

@@ -0,0 +1,192 @@
+require  'fluent/input'
+
+class Fluent::Cloudfront_LogInput < Fluent::Input
+  Fluent::Plugin.register_input('cloudfront_log', self)
+
+  config_param :aws_key_id,        :string,  :default => nil, :secret => true
+  config_param :aws_sec_key,       :string,  :default => nil, :secret => true
+  config_param :log_bucket,        :string
+  config_param :log_prefix,        :string
+  config_param :moved_log_bucket,  :string,  :default => @log_bucket
+  config_param :moved_log_prefix,  :string,  :default => '_moved'
+  config_param :region,            :string
+  config_param :tag,               :string,  :default => 'cloudfront.access'
+  config_param :interval,          :integer, :default => 300
+  config_param :delimiter,         :string,  :default => nil
+  config_param :verbose,           :string,  :default => false
+  config_param :thread_num,        :integer, :default => 4
+  config_param :s3_get_max,        :integer, :default => 200
+
+  def initialize
+    super
+    require 'logger'
+    require 'aws-sdk'
+    require 'zlib'
+    require 'time'
+    require 'uri'
+  end
+
+  def configure(conf)
+    super
+
+    raise Fluent::ConfigError.new unless @log_bucket
+    raise Fluent::ConfigError.new unless @region
+    raise Fluent::ConfigError.new unless @log_prefix
+
+    @moved_log_bucket = @log_bucket unless @moved_log_bucket
+    @moved_log_prefix = @log_prefix + '_moved' unless @moved_log_prefix
+
+    if @verbose
+      log.info("@log_bucket: #{@log_bucket}")
+      log.info("@moved_log_bucket: #{@moved_log_bucket}")
+      log.info("@log_prefix: #{@log_prefix}")
+      log.info("@moved_log_prefix: #{@moved_log_prefix}")
+      log.info("@thread_num: #{@thread_num}")
+    end
+  end
+
+  def start
+    super
+    log.info("Cloudfront verbose logging enabled") if @verbose
+    client
+
+    @loop = Coolio::Loop.new
+    timer = TimerWatcher.new(@interval, true, log, &method(:input))
+
+    @loop.attach(timer)
+    @thread = Thread.new(&method(:run))
+  end
+
+  def shutdown
+    @loop.stop
+    @thread.join
+  end
+
+  def run
+    @loop.run
+  end
+
+  def client
+    begin
+      options = {:region => @region}
+      if @aws_key_id and @aws_sec_key
+        options[:access_key_id] = @aws_key_id
+        options[:secret_access_key] = @aws_sec_key
+      end
+      @client = Aws::S3::Client.new(options)
+    rescue => e
+      log.warn("S3 client error. #{e.message}")
+    end
+  end
+
+  def parse_header(line)
+    case line
+    when /^#Version:.+/i then
+      @version = line.sub(/^#Version:/i, '').strip
+    when /^#Fields:.+/i then
+      @fields = line.sub(/^#Fields:/i, '').strip.split("\s")
+    end
+  end
+
+  def purge(filename)
+    # Key is the name of the object without the bucket prefix, e.g: asdf/asdf.jpg
+    source_object_key       = [@log_prefix, filename].join('/')
+
+    # Full path includes bucket name in addition to object key, e.g: bucket/asdf/asdf.jpg
+    source_object_full_path = [@log_bucket, source_object_key].join('/')
+
+    dest_object_key         = [@moved_log_prefix, filename].join('/')
+    dest_object_full_path   = [@moved_log_bucket, dest_object_key].join('/')
+
+    log.info("Copying object: #{source_object_full_path} to #{dest_object_full_path}") if @verbose
+
+    begin
+      client.copy_object(:bucket => @moved_log_bucket, :copy_source => source_object_full_path, :key => dest_object_key)
+    rescue => e
+      log.warn("S3 Copy client error. #{e.message}")
+      return
+    end
+
+
+    log.info("Deleting object: #{source_object_key} from #{@log_bucket}") if @verbose
+    begin
+      client.delete_object(:bucket => @log_bucket, :key => source_object_key)
+    rescue => e
+      log.warn("S3 Delete client error. #{e.message}")
+      return
+    end
+  end
+
+
+  def process_content(content)
+    filename = content.key.sub(/^#{@log_prefix}\//, "")
+    log.info("CloudFront Currently processing: #{filename}") if @verbose
+    return if filename[-1] == '/'  #skip directory/
+    return unless filename[-2, 2] == 'gz'  #skip without gz file
+
+    begin
+      access_log_gz = client.get_object(:bucket => @log_bucket, :key => content.key).body
+      access_log = Zlib::GzipReader.new(access_log_gz).read
+    rescue => e
+      log.warn("S3 GET client error. #{e.message}")
+      return
+    end
+
+    access_log.split("\n").each do |line|
+      if line[0.1] == '#'
+        parse_header(line)
+        next
+      end
+      line = URI.unescape(line)  #hoge%2520fuga -> hoge%20fuga
+      line = URI.unescape(line)  #hoge%20fuga   -> hoge fuga
+      line = line.split("\t")
+      record = Hash[@fields.collect.zip(line)]
+      timestamp = Time.parse("#{record['date']}T#{record['time']}+00:00").to_i
+      router.emit(@tag, timestamp, record)
+    end
+    purge(filename)
+  end
+
+  def input
+    log.info("CloudFront Begining input going to list S3")
+    begin
+      s3_list = client.list_objects(:bucket => @log_bucket, :prefix => @log_prefix , :delimiter => @delimiter, :max_keys => @s3_get_max)
+    rescue => e
+      log.warn("S3 GET list error. #{e.message}")
+      return
+    end
+    log.info("Finished S3 get list")
+    queue = Queue.new
+    threads = []
+    log.debug("S3 List size: #{s3_list.contents.length}")
+    s3_list.contents.each do |content|
+      queue << content
+    end
+    # BEGINS THREADS
+    @thread_num.times do
+      threads << Thread.new do
+        until queue.empty?
+          work_unit = queue.pop(true) rescue nil
+          if work_unit
+            process_content(work_unit)
+          end
+        end
+       end
+     end
+     log.debug("CloudFront Waiting for Threads to finish...")
+     threads.each { |t| t.join }
+     log.debug("CloudFront Finished")
+  end
+
+  class TimerWatcher < Coolio::TimerWatcher
+    def initialize(interval, repeat, log, &callback)
+      @callback = callback
+      @log = log
+      super(interval, repeat)
+    end
+
+    def on_timer
+      @callback.call
+    end
+  end
+end

data/test/helper.rb

@@ -0,0 +1,28 @@
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'test/unit'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'fluent/test'
+unless ENV.has_key?('VERBOSE')
+  nulllogger = Object.new
+  nulllogger.instance_eval {|obj|
+    def method_missing(method, *args)
+      # pass
+    end
+  }
+  $log = nulllogger
+end
+
+require 'fluent/plugin/in_cloudfront_log'
+
+class Test::Unit::TestCase
+end

data/test/plugin/test_in_cloudfrontlog.rb

@@ -0,0 +1,66 @@
+require_relative '../helper'
+require 'fluent/test'
+
+class Cloudfront_LogInputTest < Test::Unit::TestCase
+  def setup
+    Fluent::Test.setup
+  end
+
+  DEFAULT_CONFIG = {
+    :aws_key_id        => 'AKIAZZZZZZZZZZZZZZZZ',
+    :aws_sec_key       => '1234567890qwertyuiopasdfghjklzxcvbnm',
+    :log_bucket        => 'bucket-name',
+    :log_prefix        => 'a/b/c',
+    :moved_log_bucket  => 'bucket-name-moved',
+    :moved_log_prefix  => 'a/b/c_moved',
+    :region            => 'ap-northeast-1',
+    :tag               => 'cloudfront',
+    :interval          => '500',
+    :delimiter         => nil,
+    :verbose           => true,
+  }
+
+  def parse_config(conf = {})
+    ''.tap{|s| conf.each { |k, v| s << "#{k} #{v}\n" } }
+  end
+
+  def create_driver(conf = DEFAULT_CONFIG)
+    Fluent::Test::InputTestDriver.new(Fluent::Cloudfront_LogInput).configure(parse_config conf)
+  end
+
+  def test_configure
+    assert_nothing_raised { driver = create_driver }
+
+    exception = assert_raise(Fluent::ConfigError) {
+      conf = DEFAULT_CONFIG.clone
+      conf.delete(:log_bucket)
+      driver = create_driver(conf)
+    }
+    assert_equal("'log_bucket' parameter is required", exception.message)
+
+    exception = assert_raise(Fluent::ConfigError) {
+      conf = DEFAULT_CONFIG.clone
+      conf.delete(:region)
+      driver = create_driver(conf)
+    }
+    assert_equal("'region' parameter is required", exception.message)
+
+    exception = assert_raise(Fluent::ConfigError) {
+      conf = DEFAULT_CONFIG.clone
+      conf.delete(:log_prefix)
+      driver = create_driver(conf)
+    }
+    assert_equal("'log_prefix' parameter is required", exception.message)
+
+    conf = DEFAULT_CONFIG.clone
+    conf.delete(:moved_log_bucket)
+    driver = create_driver(conf)
+    assert_equal(driver.instance.log_bucket, driver.instance.moved_log_bucket)
+
+    conf = DEFAULT_CONFIG.clone
+    conf.delete(:moved_log_prefix)
+    driver = create_driver(conf)
+    assert_equal('_moved', driver.instance.moved_log_prefix)
+  end
+
+end

metadata

@@ -0,0 +1,124 @@
+--- !ruby/object:Gem::Specification
+name: fluent-plugin-cloudfront-log-v0.14-fix
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- lenfree
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2018-01-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: fluentd
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: aws-sdk
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: test-unit
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2'
+description: AWS CloudFront log input plugin for fluentd. This repo is temporary until
+  PR to upstream is addressed.
+email:
+- lenfree.yeung@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- README.md
+- Rakefile
+- fluent-plugin-cloudfront-log-v0.14-fix.gemspec
+- lib/fluent/plugin/in_cloudfront_log.rb
+- test/helper.rb
+- test/plugin/test_in_cloudfrontlog.rb
+homepage: https://github.com/packetloop/fluent-plugin-cloudfront-log-v0.14-fix
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.11
+signing_key: 
+specification_version: 4
+summary: AWS CloudFront log input plugin with temporary fix for v0.14. Credit to kubihie.
+test_files:
+- test/helper.rb
+- test/plugin/test_in_cloudfrontlog.rb