fluent-plugin-datacounter 0.1.0

data/.gitignore

@@ -0,0 +1,11 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*
+# For TextMate, emacs, vim
+*.tmproj
+tmtags
+*~
+\#*
+.\#*
+*.swp

data/Gemfile

@@ -0,0 +1,4 @@
+source "http://rubygems.org"
+
+# Specify your gem's dependencies in fluent-plugin-datacounter.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,13 @@
+Copyright (c) 2012- TAGOMORI Satoshi
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

data/README.rdoc

@@ -0,0 +1,72 @@
+= fluent-plugin-datacounter
+
+== Component
+
+=== DataCounterOutput
+
+Count messages with data matches any of specified regexp patterns in specified attribute.
+
+- Counts per min/hour/day
+- Counts per second (average every min/hour/day)
+- Percentage of each pattern in total counts of messages
+
+DataCounterOutput emits messages contains results data, so you can output these message (with 'datacount' tag by default) to any outputs you want.
+
+    output ex1 (aggragates all inputs): {"pattern1_count":20, "pattern1_rate":0.333, "pattern1_percentage":25.0, "pattern2_count":40, "pattern2_rate":0.666, "pattern2_percentage":50.0, "unmatched_count":20, "unmatched_rate":0.333, "unmatched_percentage":25.0}
+    output ex2 (aggragates per tag): {"test_pattern1_count":10, "test_pattern1_rate":0.333, "test_pattern1_percentage":25.0, "test_pattern2_count":40, "test_pattern2_rate":0.666, "test_pattern2_percentage":50.0, "test_unmatched_count":20, "test_unmatched_rate":0.333, "test_unmatched_percentage":25.0}
+
+'input_tag_remove_prefix' option available if you want to remove tag prefix from output field names.
+
+== Configuration
+
+=== DataCounterOutput
+
+Count messages that have attribute 'referer' as 'google.com', 'yahoo.com' and 'facebook.com' from all messages matched, per minutes.
+
+    <match accesslog.**>
+      type datacounter
+      unit minute
+      aggregate all
+      count_key referer
+      # patternX: X(1-9)
+      pattern1 google google.com
+      pattern2 yahoo  yahoo.com
+      pattern3 facebook facebook.com
+      # but patterns above matches 'this-is-facebookXcom.xxxsite.com' ...
+    </match>
+
+Or, more exact match pattern, output per tags (default 'aggregate tag'), per hours.
+
+    <match accesslog.**>
+      type datacounter
+      unit hour
+      count_key referer
+      # patternX: X(1-9)
+      pattern1 google ^http://www\.google\.com/.*
+      pattern2 yahoo  ^http://www\.yahoo\.com/.*
+      pattern3 twitter ^https://twitter.com/.*
+    </match>
+
+HTTP status code patterns.
+
+    <match accesslog.**>
+      type datacounter
+      unit min
+      count_key status
+      # patternX: X(1-9)
+      pattern1 2xx ^2\d\d$
+      pattern2 3xx ^3\d\d$
+      pattern3 404 ^404$    # we want only 404 counts...
+      pattern4 4xx ^4\d\d$  # pattern4 doesn't matches messages matches pattern[123]
+      pattern5 5xx ^5\d\d$
+    </match>
+
+== TODO
+
+- consider what to do next
+- patches welcome!
+
+== Copyright
+
+Copyright:: Copyright (c) 2012- TAGOMORI Satoshi (tagomoris)
+License::   Apache License, Version 2.0

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/example.conf

@@ -0,0 +1,24 @@
+<source>
+  type forward
+</source>
+
+# out_sampling_filter strongly recommended
+<match test.**>
+  type sampling_filter
+  interval 2
+  remove_prefix test
+  add_prefix sampled
+</match>
+
+<match sampled.**>
+  type datacounter
+  tag result
+  aggregate all
+  count_key field
+  pattern1 ok ^OK
+  pattern2 ng ^NG
+</match>
+
+<match result>
+  type stdout
+</match>

data/fluent-plugin-datacounter.gemspec

@@ -0,0 +1,25 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+
+Gem::Specification.new do |s|
+  s.name        = "fluent-plugin-datacounter"
+  s.version     = "0.1.0"
+  s.authors     = ["TAGOMORI Satoshi"]
+  s.email       = ["tagomoris@gmail.com"]
+  s.homepage    = "https://github.com/tagomoris/fluent-plugin-datacounter"
+  s.summary     = %q{Output filter plugin to count messages that matches specified conditions}
+  s.description = %q{Output filter plugin to count messages that matches specified conditions}
+
+  s.rubyforge_project = "fluent-plugin-datacounter"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+
+  # specify any dependencies here; for example:
+  # s.add_development_dependency "rspec"
+  # s.add_runtime_dependency "rest-client"
+  s.add_development_dependency "fluentd"
+  s.add_runtime_dependency "fluentd"
+end

data/lib/fluent/plugin/out_datacounter.rb

@@ -0,0 +1,185 @@
+class Fluent::DataCounterOutput < Fluent::Output
+  Fluent::Plugin.register_output('datacounter', self)
+
+  config_param :unit, :string, :default => 'minute'
+  config_param :aggregate, :string, :default => 'tag'
+  config_param :tag, :string, :default => 'datacount'
+  config_param :input_tag_remove_prefix, :string, :default => nil
+  config_param :count_key, :string
+
+  # pattern0 reserved as unmatched counts
+  config_param :pattern1, :string # string: NAME REGEXP
+  (2..9).each do |i|
+    config_param ('pattern' + i.to_s).to_sym, :string, :default => nil # NAME REGEXP
+  end
+
+  attr_accessor :counts
+  attr_accessor :last_checked
+
+  def configure(conf)
+    super
+
+    @unit = case @unit
+            when 'minute' then :minute
+            when 'hour' then :hour
+            when 'day' then :day
+            else
+              raise Fluent::ConfigError, "flowcounter unit allows minute/hour/day"
+            end
+    @aggregate = case @aggregate
+                 when 'tag' then :tag
+                 when 'all' then :all
+                 else
+                   raise Fluent::ConfigError, "flowcounter aggregate allows tag/all"
+                 end
+
+    @patterns = [[0, 'unmatched', nil]]
+    pattern_names = ['unmatched']
+    (1..9).each do |i|
+      next unless conf["pattern#{i}"]
+      name,regexp = conf["pattern#{i}"].split(' ', 2)
+      @patterns.push([i, name, Regexp.new(regexp)])
+      pattern_names.push(name)
+    end
+    pattern_index_list = conf.keys.select{|s| s =~ /^pattern\d$/}.map{|v| (/^pattern(\d)$/.match(v))[1].to_i}
+    unless pattern_index_list.reduce(true){|v,i| v and @patterns[i]}
+      raise Fluent::ConfigError, "jump of pattern index found"
+    end
+    unless @patterns.length == pattern_names.uniq.length
+      raise Fluent::ConfigError, "duplicated pattern names"
+    end
+
+    if @input_tag_remove_prefix
+      @removed_prefix_string = @input_tag_remove_prefix + '.'
+      @removed_length = @removed_prefix_string.length
+    end
+
+    @counts = count_initialized
+  end
+
+  def start
+    super
+    @counts = count_initialized
+    start_watch
+  end
+
+  def shutdown
+    super
+    @watcher.terminate
+    @watcher.join
+  end
+
+  def count_initialized(keys=nil)
+    # counts['tag'][num] = count
+    if @aggregate == :all
+      {'all' => ([0] * @patterns.length)}
+    elsif keys
+      values = Array.new(keys.length) {|i|
+        Array.new(@patterns.length){|j| 0 }
+      }
+      Hash[[keys, values].transpose]
+    else
+      {}
+    end
+  end
+
+  def countups(tag, counts)
+    if @aggregate == :all
+      tag = 'all'
+    end
+    @counts[tag] ||= [0] * @patterns.length
+
+    counts.each_with_index do |count, i|
+      @counts[tag][i] += count
+    end
+  end
+
+  def stripped_tag(tag)
+    return tag unless @input_tag_remove_prefix
+    return tag[@removed_length..-1] if tag.start_with?(@removed_prefix_string) and tag.length > @removed_length
+    return tag[@removed_length..-1] if tag == @input_tag_remove_prefix
+    tag
+  end
+
+  def generate_output(counts, step)
+    output = {}
+    if @aggregate == :all
+      sum = counts['all'].inject(:+)
+      counts['all'].each_with_index do |count,i|
+        name = @patterns[i][1]
+        output[name + '_count'] = count
+        output[name + '_rate'] = ((count * 100.0) / (1.00 * step)).floor / 100.0
+        output[name + '_percentage'] = count * 100.0 / (1.00 * sum) if sum > 0
+      end
+      return output
+    end
+
+    counts.keys.each do |tag|
+      t = stripped_tag(tag)
+      sum = counts[tag].inject(:+)
+      counts[tag].each_with_index do |count,i|
+        name = @patterns[i][1]
+        output[t + '_' + name + '_count'] = count
+        output[t + '_' + name + '_rate'] = ((count * 100.0) / (1.00 * step)).floor / 100.0
+        output[t + '_' + name + '_percentage'] = count * 100.0 / (1.00 * sum) if sum > 0
+      end
+    end
+    output
+  end
+
+  def flush(step)
+    flushed,@counts = @counts,count_initialized(@counts.keys.dup)
+    generate_output(flushed, step)
+  end
+
+  def flush_emit(step)
+    Fluent::Engine.emit(@tag, Fluent::Engine.now, flush(step))
+  end
+
+  def start_watch
+    # for internal, or tests only
+    @watcher = Thread.new(&method(:watch))
+  end
+  
+  def watch
+    # instance variable, and public accessable, for test
+    @last_checked = Fluent::Engine.now
+    tick = case @unit
+           when :minute then 60
+           when :hour then 3600
+           when :day then 86400
+           else 
+             raise RuntimeError, "@unit must be one of minute/hour/day"
+           end
+    while true
+      sleep 0.5
+      if Fluent::Engine.now - @last_checked >= tick
+        now = Fluent::Engine.now
+        flush_emit(now - @last_checked)
+        @last_checked = now
+      end
+    end
+  end
+
+  def emit(tag, es, chain)
+    c = [0] * @patterns.length
+
+    es.each do |time,record|
+      value = record[@count_key]
+      next if value.nil?
+
+      value = value.to_s
+      matched = false
+      @patterns.each do |index, name, regexp|
+        next unless regexp and regexp.match(value)
+        c[index] += 1
+        matched = true
+        break
+      end
+      c[0] += 1 unless matched
+    end
+    countups(tag, c)
+
+    chain.next
+  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/out_datacounter'
+
+class Test::Unit::TestCase
+end

data/test/plugin/test_out_datacounter.rb

@@ -0,0 +1,205 @@
+require 'helper'
+
+class DataCounterOutputTest < Test::Unit::TestCase
+  def setup
+    Fluent::Test.setup
+  end
+
+  CONFIG = %[
+    unit minute
+    aggregate tag
+    input_tag_remove_prefix test
+    count_key target
+    pattern1 status2xx ^2\\d\\d$
+    pattern2 status3xx ^3\\d\\d$
+    pattern3 status4xx ^4\\d\\d$
+    pattern4 status5xx ^5\\d\\d$
+  ]
+
+  def create_driver(conf = CONFIG, tag='test.input')
+    Fluent::Test::OutputTestDriver.new(Fluent::DataCounterOutput, tag).configure(conf)
+  end
+
+  def test_configure
+    assert_raise(Fluent::ConfigError) {
+      d = create_driver('')
+    }
+    assert_raise(Fluent::ConfigError) {
+      d = create_driver %[
+        count_key field
+      ]
+    }
+    assert_raise(Fluent::ConfigError) {
+      d = create_driver %[
+        pattern1 hoge ^1\\d\\d$
+      ]
+    }
+    assert_raise(Fluent::ConfigError) {
+      d = create_driver %[
+        count_key field
+        pattern2 hoge ^1\\d\\d$
+      ]
+    }
+    assert_raise(Fluent::ConfigError) {
+      d = create_driver %[
+        count_key field
+        pattern1 hoge ^1\\d\\d$
+        pattern4 pos  ^4\\d\\d$
+      ]
+    }
+    assert_raise(Fluent::ConfigError) {
+      d = create_driver %[
+        count_key field
+        pattern1 hoge ^1\\d\\d$
+        pattern2 hoge ^4\\d\\d$
+      ]
+    }
+    d = create_driver %[
+      count_key field
+      pattern1 ok ^2\\d\\d$
+    ]
+    assert_equal :minute, d.instance.unit
+    assert_equal :tag, d.instance.aggregate
+    assert_equal 'datacount', d.instance.tag
+    assert_nil d.instance.input_tag_remove_prefix
+    assert_equal 'field', d.instance.count_key
+    assert_equal 'ok ^2\d\d$', d.instance.pattern1
+  end
+
+  def test_count_initialized
+    d = create_driver %[
+      aggregate all
+      count_key field
+      pattern1 hoge 1\d\d
+      pattern2 moge 2\d\d
+    ]
+    assert_equal [0,0,0], d.instance.counts['all']
+  end
+
+  def test_countups
+    d = create_driver
+    assert_nil d.instance.counts['test.input']
+
+    d.instance.countups('test.input', [0, 0, 0, 0, 0])
+    assert_equal [0,0,0,0,0], d.instance.counts['test.input']
+    d.instance.countups('test.input', [1, 1, 1, 0, 0])
+    assert_equal [1,1,1,0,0], d.instance.counts['test.input']
+    d.instance.countups('test.input', [0, 5, 1, 0, 0])
+    assert_equal [1,6,2,0,0], d.instance.counts['test.input']
+  end
+
+  def test_stripped_tag
+    d = create_driver
+    assert_equal 'input', d.instance.stripped_tag('test.input')
+    assert_equal 'test.input', d.instance.stripped_tag('test.test.input')
+    assert_equal 'input', d.instance.stripped_tag('input')
+  end
+
+  def test_generate_output
+    d = create_driver
+    r1 = d.instance.generate_output({'test.input' => [60,240,120,180,0], 'test.input2' => [0,600,0,0,0]}, 60)
+    assert_equal   60, r1['input_unmatched_count']
+    assert_equal  1.0, r1['input_unmatched_rate']
+    assert_equal 10.0, r1['input_unmatched_percentage']
+    assert_equal  240, r1['input_status2xx_count']
+    assert_equal  4.0, r1['input_status2xx_rate']
+    assert_equal 40.0, r1['input_status2xx_percentage']
+    assert_equal  120, r1['input_status3xx_count']
+    assert_equal  2.0, r1['input_status3xx_rate']
+    assert_equal 20.0, r1['input_status3xx_percentage']
+    assert_equal  180, r1['input_status4xx_count']
+    assert_equal  3.0, r1['input_status4xx_rate']
+    assert_equal 30.0, r1['input_status4xx_percentage']
+    assert_equal    0, r1['input_status5xx_count']
+    assert_equal  0.0, r1['input_status5xx_rate']
+    assert_equal  0.0, r1['input_status5xx_percentage']
+
+    assert_equal    0, r1['input2_unmatched_count']
+    assert_equal  0.0, r1['input2_unmatched_rate']
+    assert_equal  0.0, r1['input2_unmatched_percentage']
+    assert_equal  600, r1['input2_status2xx_count']
+    assert_equal 10.0, r1['input2_status2xx_rate']
+    assert_equal 100.0, r1['input2_status2xx_percentage']
+    assert_equal    0, r1['input2_status3xx_count']
+    assert_equal  0.0, r1['input2_status3xx_rate']
+    assert_equal  0.0, r1['input2_status3xx_percentage']
+    assert_equal    0, r1['input2_status4xx_count']
+    assert_equal  0.0, r1['input2_status4xx_rate']
+    assert_equal  0.0, r1['input2_status4xx_percentage']
+    assert_equal    0, r1['input2_status5xx_count']
+    assert_equal  0.0, r1['input2_status5xx_rate']
+    assert_equal  0.0, r1['input2_status5xx_percentage']
+
+    d = create_driver %[
+      aggregate all
+      count_key field
+      pattern1 hoge xxx\d\d
+    ]
+    r2 = d.instance.generate_output({'all' => [60,240]}, 60)
+    assert_equal   60, r2['unmatched_count']
+    assert_equal  1.0, r2['unmatched_rate']
+    assert_equal 20.0, r2['unmatched_percentage']
+    assert_equal  240, r2['hoge_count']
+    assert_equal  4.0, r2['hoge_rate']
+    assert_equal 80.0, r2['hoge_percentage']
+  end
+
+  def test_emit
+    d1 = create_driver(CONFIG, 'test.tag1')
+    d1.run do
+      60.times do
+        d1.emit({'target' => '200'})
+        d1.emit({'target' => '100'})
+        d1.emit({'target' => '200'})
+        d1.emit({'target' => '400'})
+      end
+    end
+    r1 = d1.instance.flush(60)
+    assert_equal 120, r1['tag1_status2xx_count']
+    assert_equal 2.0, r1['tag1_status2xx_rate']
+    assert_equal 50.0, r1['tag1_status2xx_percentage']
+
+    assert_equal 60, r1['tag1_status4xx_count']
+    assert_equal 1.0, r1['tag1_status4xx_rate']
+    assert_equal 25.0, r1['tag1_status4xx_percentage']
+    
+    assert_equal 60, r1['tag1_unmatched_count']
+    assert_equal 1.0, r1['tag1_unmatched_rate']
+    assert_equal 25.0, r1['tag1_unmatched_percentage']
+    
+    assert_equal 0, r1['tag1_status3xx_count']
+    assert_equal 0.0, r1['tag1_status3xx_rate']
+    assert_equal 0.0, r1['tag1_status3xx_percentage']
+    assert_equal 0, r1['tag1_status5xx_count']
+    assert_equal 0.0, r1['tag1_status5xx_rate']
+    assert_equal 0.0, r1['tag1_status5xx_percentage']
+
+    d2 = create_driver(%[
+      aggregate all
+      count_key target
+      pattern1 ok 2\\d\\d
+      pattern2 redirect 3\\d\\d
+    ], 'test.tag2')
+    d2.run do
+      60.times do
+        d2.emit({'target' => '200'})
+        d2.emit({'target' => '300 200'})
+      end
+    end
+    d2.instance.flush_emit(120)
+    emits = d2.emits
+    assert_equal 1, emits.length
+    data = emits[0]
+    assert_equal 'datacount', data[0] # tag
+    assert_equal 120, data[2]['ok_count']
+    assert_equal 1.0, data[2]['ok_rate']
+    assert_equal 100.0, data[2]['ok_percentage']
+    assert_equal 0, data[2]['redirect_count']
+    assert_equal 0.0, data[2]['redirect_rate']
+    assert_equal 0.0, data[2]['redirect_percentage']
+    assert_equal 0, data[2]['unmatched_count']
+    assert_equal 0.0, data[2]['unmatched_rate']
+    assert_equal 0.0, data[2]['unmatched_percentage']
+  end
+
+end

metadata

@@ -0,0 +1,79 @@
+--- !ruby/object:Gem::Specification
+name: fluent-plugin-datacounter
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+  prerelease: 
+platform: ruby
+authors:
+- TAGOMORI Satoshi
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-02-23 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: fluentd
+  requirement: &2153804860 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *2153804860
+- !ruby/object:Gem::Dependency
+  name: fluentd
+  requirement: &2153804420 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2153804420
+description: Output filter plugin to count messages that matches specified conditions
+email:
+- tagomoris@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.rdoc
+- Rakefile
+- example.conf
+- fluent-plugin-datacounter.gemspec
+- lib/fluent/plugin/out_datacounter.rb
+- test/helper.rb
+- test/plugin/test_out_datacounter.rb
+homepage: https://github.com/tagomoris/fluent-plugin-datacounter
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: fluent-plugin-datacounter
+rubygems_version: 1.8.6
+signing_key: 
+specification_version: 3
+summary: Output filter plugin to count messages that matches specified conditions
+test_files:
+- test/helper.rb
+- test/plugin/test_out_datacounter.rb