fluent-plugin-s3-fork 0.4.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: afb81d1dd9426d54175ab62ac2e5d54301a80350
+  data.tar.gz: bf7cfd3bd1e1acfd5b2aaccfd5b1097f7e4e03b6
+SHA512:
+  metadata.gz: 0c6166ec2a11010b6cf7f473bfb308f9030195121b1594e99952a2bc4890f312eb9c147c661f596b566904ee58b6b937eeacfd588610c952e9166474cfb1febc
+  data.tar.gz: c322533b99d3b0bcca1d5a8f8b1acd1e9f90604209b0cb4dc48c3f5f493e0ea3478748a5ce8f5b53987e106da149f18b08efc9037c587f5527a5c42016bfae03

data/.travis.yml

@@ -0,0 +1,21 @@
+language: ruby
+
+rvm:
+  - 1.9.2
+  - 1.9.3
+  - 2.0.0
+  - 2.1
+  - rbx
+
+gemfile:
+ - Gemfile
+
+branches:
+  only:
+    - master
+
+script: bundle exec rake test
+
+matrix:
+  allow_failures:
+    - rvm: rbx

data/AUTHORS

@@ -0,0 +1,2 @@
+FURUHASHI Sadayuki <frsyuki _at_ gmail.com>
+MASAHIRO Nakagawa <repeatedly _at_ gmail.com>

data/ChangeLog

@@ -0,0 +1,122 @@
+Release 0.4.2 - 2014/10/22
+
+  * Update fluent-mixin-config-placeholders to v0.3.0
+
+
+Release 0.4.1 - 2014/10/16
+
+  * Add 's3_region' option to specify S3 region
+  * Restrict aws-sdk gem dependency version to use v1
+  * Fix infinite loop when same object path is generated
+
+
+Release 0.4.0 - 2014/06/06
+
+  * Add 'format' option to change one line format
+  * Update fluentd dependency to v0.10.49
+
+
+Release 0.3.7 - 2014/03/07
+
+  * Support lzma2 compression using 'xz' command
+    https://github.com/fluent/fluent-plugin-s3/pull/41
+  * Relax aws-sdk gem requirement
+    https://github.com/fluent/fluent-plugin-s3/pull/42
+
+
+Release 0.3.6 - 2014/02/05
+
+  * Support 'log_level' option
+
+
+Release 0.3.5 - 2013/12/05
+
+  * Add 'reduced_redundancy' option to store logs in reduced redundancy
+    https://github.com/fluent/fluent-plugin-s3/pull/33
+
+
+Release 0.3.4 - 2013/07/31
+
+  * Add dynamic path slicing by time formatted string
+    https://github.com/fluent/fluent-plugin-s3/pull/24
+
+
+Release 0.3.3 - 2013/06/18
+
+  * Fix require bug on case-sensitive environment
+
+
+Release 0.3.2 - 2013/06/18
+
+  * Support lzo mime-type
+    https://github.com/fluent/fluent-plugin-s3/pull/29
+  * Add proxy_uri option
+    https://github.com/fluent/fluent-plugin-s3/issues/25
+  * Add check_apikey_on_start option
+    https://github.com/fluent/fluent-plugin-s3/pull/28
+
+
+Release 0.3.1 - 2013/03/28
+
+  * Support json and text mime-types
+    https://github.com/fluent/fluent-plugin-s3/pull/20
+
+
+Release 0.3.0 - 2013/02/19
+
+  * Enable dynamic and configurable S3 object kyes
+    https://github.com/fluent/fluent-plugin-s3/pull/12
+  * Fix a lot of temporary files were left on /tmp when the plugin failed to write to S3
+    https://github.com/fluent/fluent-plugin-s3/pull/15
+  * Enable fluent-mixin-config-placeholders to support hostname, uuid and other parameters in configuration
+    https://github.com/fluent/fluent-plugin-s3/pull/19
+  * Update 'aws-sdk' version requirement to '~> 1.8.2'
+    https://github.com/fluent/fluent-plugin-s3/pull/21
+  * Create new S3 bucket if not exists
+    https://github.com/fluent/fluent-plugin-s3/pull/22
+  * Check the permission and bucket existence at start method, not write method.
+
+
+Release 0.2.6 - 2013/01/15
+
+  * Add use_ssl option
+
+
+Release 0.2.5 - 2012/12/06
+
+  * Add format_json and time/tag mixin options [#9]
+
+
+Release 0.2.4 - 2012/11/21
+
+  * Set content type when writing file to s3
+
+
+Release 0.2.3 - 2012/11/19
+
+  * Loosen 'aws-sdk' version requirement from "~> 1.1.3" to "~> 1.1"
+  * Support aws-sdk facility to load credentials from ENV vars or IAM Instance Profile by making the credentials non-mandatory
+  * Use Yajl instead of to_json not to raise exceptions when it got invalid bytes as UTF-8.
+
+
+Release 0.2.2 - 2011/12/15
+
+  * Add s3_endpoint option
+
+
+Release 0.2.1 - 2011/10/24
+
+  * Add sequential number to the file to avoid overwriting
+  * Use bundler instead of jeweler for packaging
+  * Updated README
+
+
+Release 0.2.0 - 2011/10/16
+
+  * Updated to fluentd-0.10.0
+
+
+Release 0.1.1 - 2011/09/27
+
+  * First release
+

data/Gemfile

@@ -0,0 +1,3 @@
+source "http://rubygems.org"
+
+gemspec

data/README.rdoc

@@ -0,0 +1,176 @@
+= Amazon S3 output plugin for {Fluentd}[http://github.com/fluent/fluentd]
+
+== Overview
+
+*s3* output plugin buffers event logs in local file and upload it to S3 periodically.
+
+This plugin splits files exactly by using the time of event logs (not the time when the logs are received). For example, a log '2011-01-02 message B' is reached, and then another log '2011-01-03 message B' is reached in this order, the former one is stored in "20110102.gz" file, and latter one in "20110103.gz" file.
+
+
+== Installation
+
+Simply use RubyGems:
+
+    gem install fluent-plugin-s3
+
+== Configuration
+
+    <match pattern>
+      type s3
+
+      aws_key_id YOUR_AWS_KEY_ID
+      aws_sec_key YOUR_AWS_SECRET/KEY
+      s3_bucket YOUR_S3_BUCKET_NAME
+      s3_endpoint s3-ap-northeast-1.amazonaws.com
+      s3_object_key_format %{path}%{time_slice}_%{index}.%{file_extension}
+      path logs/
+      buffer_path /var/log/fluent/s3
+
+      time_slice_format %Y%m%d-%H
+      time_slice_wait 10m
+      utc
+    </match>
+
+[aws_key_id] AWS access key id. This parameter is required when your agent is not running on EC2 instance with an IAM Role.
+
+[aws_sec_key] AWS secret key. This parameter is required when your agent is not running on EC2 instance with an IAM Role.
+
+[s3_bucket (required)] S3 bucket name.
+
+[s3_region] s3 region name. For example, US West (Oregon) Region is "us-west-2". The full list of regions are available here. > http://docs.aws.amazon.com/general/latest/gr/rande.html#s3_region. We recommend using `s3_region` instead of `s3_endpoint`.
+
+[s3_endpoint] s3 endpoint name. For example, US West (Oregon) Region is "s3-us-west-2.amazonaws.com". The full list of endpoints are available here. > http://docs.aws.amazon.com/general/latest/gr/rande.html#s3_region
+
+[s3_object_key_format] The format of S3 object keys. You can use several built-in variables:
+
+- %{path}
+- %{time_slice}
+- %{index}
+- %{file_extension}
+
+to decide keys dynamically.
+
+%{path} is exactly the value of *path* configured in the configuration file. E.g., "logs/" in the example configuration above.
+%{time_slice} is the time-slice in text that are formatted with *time_slice_format*.
+%{index} is the sequential number starts from 0, increments when multiple files are uploaded to S3 in the same time slice.
+%{file_extention} is always "gz" for now.
+
+The default format is "%{path}%{time_slice}_%{index}.%{file_extension}".
+
+For instance, using the example configuration above, actual object keys on S3 will be something like:
+
+    "logs/20130111-22_0.gz"
+    "logs/20130111-23_0.gz"
+    "logs/20130111-23_1.gz"
+    "logs/20130112-00_0.gz"
+
+With the configuration:
+
+    s3_object_key_format %{path}/events/ts=%{time_slice}/events_%{index}.%{file_extension}
+    path log
+    time_slice_format %Y%m%d-%H
+
+You get:
+
+    "log/events/ts=20130111-22/events_0.gz"
+    "log/events/ts=20130111-23/events_0.gz"
+    "log/events/ts=20130111-23/events_1.gz"
+    "log/events/ts=20130112-00/events_0.gz"
+
+The {fluent-mixin-config-placeholders}[https://github.com/tagomoris/fluent-mixin-config-placeholders] mixin is also incorporated, so additional variables such as %{hostname}, %{uuid}, etc. can be used in the s3_object_key_format. This could prove useful in preventing filename conflicts when writing from multiple servers.
+
+    s3_object_key_format %{path}/events/ts=%{time_slice}/events_%{index}-%{hostname}.%{file_extension}
+
+[store_as] archive format on S3. You can use serveral format:
+
+- gzip (default)
+- json
+- text
+- lzo (Need lzop command)
+
+[format] Change one line format in the S3 object. Supported formats are "out_file", "json", "ltsv" and "single_value".
+
+- out_file (default).
+
+    time\ttag\t{..json1..}
+    time\ttag\t{..json2..}
+    ...
+
+- json
+
+    {..json1..}
+    {..json2..}
+    ...
+
+At this format, "time" and "tag" are omitted.
+But you can set these information to the record by setting "include_tag_key" / "tag_key" and "include_time_key" / "time_key" option.
+If you set following configuration in S3 output:
+
+    format_json true
+    include_time_key true
+    time_key log_time # default is time
+
+then the record has log_time field.
+
+    {"log_time":"time string",...}
+
+- ltsv
+
+    key1:value1\tkey2:value2
+    key1:value1\tkey2:value2
+    ...
+
+"ltsv" format also accepts "include_xxx" related options. See "json" section.
+
+- single_value
+
+Use specified value instead of entire recode. If you get '{"message":"my log"}', then contents are
+
+    my log1
+    my log2
+    ...
+
+You can change key name by "message_key" option.
+
+[auto_create_bucket] Create S3 bucket if it does not exists. Default is true.
+
+[check_apikey_on_start] Check AWS key on start. Default is true.
+
+[proxy_uri] uri of proxy environment.
+
+[path] path prefix of the files on S3. Default is "" (no prefix).
+
+[buffer_path (required)] path prefix of the files to buffer logs.
+
+[time_slice_format] Format of the time used as the file name. Default is '%Y%m%d'. Use '%Y%m%d%H' to split files hourly.
+
+[time_slice_wait] The time to wait old logs. Default is 10 minutes. Specify larger value if old logs may reache.
+
+[utc] Use UTC instead of local time.
+
+== IAM Policy
+
+The following is an example for a minimal IAM policy needed to write to an s3 bucket (matches my-s3bucket/logs, my-s3bucket-test, etc.).
+
+    { "Statement": [
+     { "Effect":"Allow",
+       "Action":"s3:*",
+       "Resource":"arn:aws:s3:::my-s3bucket*"
+      } ]
+    }
+
+Note that the bucket must already exist and *auto_create_bucket* has no effect in this case.
+
+Refer to the {AWS documentation}[http://docs.aws.amazon.com/IAM/latest/UserGuide/ExampleIAMPolicies.html] for example policies.
+
+Using {IAM roles}[http://docs.aws.amazon.com/IAM/latest/UserGuide/WorkingWithRoles.html] with a properly configured IAM policy are preferred over embedding access keys on EC2 instances.
+
+== Website, license, et. al.
+
+Web site::  http://fluentd.org/
+Documents:: http://docs.fluentd.org/
+Source repository:: http://github.com/fluent
+Discussion:: http://groups.google.com/group/fluentd
+Author:: Sadayuki Furuhashi
+Copyright:: (c) 2011 FURUHASHI Sadayuki
+License:: Apache License, Version 2.0

data/Rakefile

@@ -0,0 +1,14 @@
+
+require 'bundler'
+Bundler::GemHelper.install_tasks
+
+require 'rake/testtask'
+
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.test_files = FileList['test/test_*.rb']
+  test.verbose = true
+end
+
+task :default => [:build]
+

data/VERSION

@@ -0,0 +1 @@
+0.4.2

data/fluent-plugin-s3.gemspec

@@ -0,0 +1,25 @@
+# encoding: utf-8
+$:.push File.expand_path('../lib', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.name        = "fluent-plugin-s3-fork"
+  gem.description = "Amazon S3 output plugin for Fluentd event collector"
+  gem.homepage    = "https://github.com/tomodian/fluent-plugin-s3"
+  gem.summary     = gem.description
+  gem.version     = File.read("VERSION").strip
+  gem.authors     = ["Hayato Tomoda"]
+  gem.email       = "tomodian@gmail.com"
+  gem.has_rdoc    = false
+  #gem.platform    = Gem::Platform::RUBY
+  gem.files       = `git ls-files`.split("\n")
+  gem.test_files  = `git ls-files -- {test,spec,features}/*`.split("\n")
+  gem.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  gem.require_paths = ['lib']
+
+  gem.add_dependency "fluentd", "~> 0.10.49"
+  gem.add_dependency "aws-sdk", "~> 1.38"
+  gem.add_dependency "yajl-ruby", "~> 1.0"
+  gem.add_dependency "fluent-mixin-config-placeholders", ">= 0.3.0"
+  gem.add_development_dependency "rake", ">= 0.9.2"
+  gem.add_development_dependency "flexmock", ">= 1.2.0"
+end

data/lib/fluent/plugin/out_s3.rb

@@ -0,0 +1,201 @@
+module Fluent
+  require 'fluent/mixin/config_placeholders'
+
+  class S3Output < Fluent::TimeSlicedOutput
+    Fluent::Plugin.register_output('s3', self)
+
+    unless method_defined?(:log)
+      define_method(:log) { $log }
+    end
+
+    def initialize
+      super
+      require 'aws-sdk'
+      require 'zlib'
+      require 'time'
+      require 'tempfile'
+      require 'open3'
+
+      @use_ssl = true
+    end
+
+    config_param :path, :string, :default => ""
+
+    config_param :aws_key_id, :string, :default => nil
+    config_param :aws_sec_key, :string, :default => nil
+    config_param :s3_bucket, :string
+    config_param :s3_region, :string, :default => nil
+    config_param :s3_endpoint, :string, :default => nil
+    config_param :s3_object_key_format, :string, :default => "%{path}%{time_slice}_%{index}.%{file_extension}"
+    config_param :store_as, :string, :default => "gzip"
+    config_param :command_parameter, :string, :default => nil
+    config_param :auto_create_bucket, :bool, :default => true
+    config_param :check_apikey_on_start, :bool, :default => true
+    config_param :proxy_uri, :string, :default => nil
+    config_param :reduced_redundancy, :bool, :default => false
+    config_param :format, :string, :default => 'out_file'
+
+    attr_reader :bucket
+
+    include Fluent::Mixin::ConfigPlaceholders
+
+    def placeholders
+      [:percent]
+    end
+
+    def configure(conf)
+      super
+
+      if use_ssl = conf['use_ssl']
+        if use_ssl.empty?
+          @use_ssl = true
+        else
+          @use_ssl = Config.bool_value(use_ssl)
+          if @use_ssl.nil?
+            raise ConfigError, "'true' or 'false' is required for use_ssl option on s3 output"
+          end
+        end
+      end
+
+      @ext, @mime_type = case @store_as
+                         when 'gzip'
+                           ['gz', 'application/x-gzip']
+                         when 'lzo'
+                           check_command('lzop', 'LZO')
+                           @command_parameter = '-qf1' if @command_parameter.nil?
+                           ['lzo', 'application/x-lzop']
+                         when 'lzma2'
+                           check_command('xz', 'LZMA2')
+                           @command_parameter = '-qf0' if @command_parameter.nil?
+                           ['xz', 'application/x-xz']
+                         when 'json'
+                           ['json', 'application/json']
+                         else
+                           ['txt', 'text/plain']
+                         end
+
+      if format_json = conf['format_json']
+        $log.warn "format_json is deprecated. Use 'format json' instead"
+        conf['format'] = 'json'
+      else
+        conf['format'] = @format
+      end
+      @formatter = TextFormatter.create(conf)
+
+      if @localtime
+        @path_slicer = Proc.new {|path|
+          Time.now.strftime(path)
+        }
+      else
+        @path_slicer = Proc.new {|path|
+          Time.now.utc.strftime(path)
+        }
+      end
+    end
+
+    def start
+      super
+      options = {}
+      if @aws_key_id && @aws_sec_key
+        options[:access_key_id] = @aws_key_id
+        options[:secret_access_key] = @aws_sec_key
+      end
+      options[:region] = @s3_region if @s3_region
+      options[:endpoint] = @s3_endpoint if @s3_endpoint
+      options[:proxy_uri] = @proxy_uri if @proxy_uri
+      options[:use_ssl] = @use_ssl
+
+      @s3 = AWS::S3.new(options)
+      @bucket = @s3.buckets[@s3_bucket]
+
+      check_apikeys if @check_apikey_on_start
+      ensure_bucket
+    end
+
+    def format(tag, time, record)
+      @formatter.format(tag, time, record)
+    end
+
+    def write(chunk)
+      i = 0
+      previous_path = nil
+
+      begin
+        path = @path_slicer.call(@path)
+        values_for_s3_object_key = {
+          "path" => path,
+          "time_slice" => chunk.key,
+          "file_extension" => @ext,
+          "index" => i
+        }
+        s3path = @s3_object_key_format.gsub(%r(%{[^}]+})) { |expr|
+          values_for_s3_object_key[expr[2...expr.size-1]]
+        }
+        if (i > 0) && (s3path == previous_path)
+          raise "duplicated path is generated. use %{index} in s3_object_key_format: path = #{s3path}"
+        end
+
+        i += 1
+        previous_path = s3path
+      end while @bucket.objects[s3path].exists?
+
+      tmp = Tempfile.new("s3-")
+      begin
+        if @store_as == "gzip"
+          w = Zlib::GzipWriter.new(tmp)
+          chunk.write_to(w)
+          w.close
+        elsif @store_as == "lzo"
+          w = Tempfile.new("chunk-tmp")
+          chunk.write_to(w)
+          w.close
+          tmp.close
+          # We don't check the return code because we can't recover lzop failure.
+          system "lzop #{@command_parameter} -o #{tmp.path} #{w.path}"
+        elsif @store_as == "lzma2"
+          w = Tempfile.new("chunk-xz-tmp")
+          chunk.write_to(w)
+          w.close
+          tmp.close
+          system "xz #{@command_parameter} -c #{w.path} > #{tmp.path}"
+        else
+          chunk.write_to(tmp)
+          tmp.close
+        end
+        @bucket.objects[s3path].write(Pathname.new(tmp.path), {:content_type => @mime_type,
+                                                               :reduced_redundancy => @reduced_redundancy})
+      ensure
+        tmp.close(true) rescue nil
+        w.close rescue nil
+        w.unlink rescue nil
+      end
+    end
+
+    private
+
+    def ensure_bucket
+      if !@bucket.exists?
+        if @auto_create_bucket
+          log.info "Creating bucket #{@s3_bucket} on #{@s3_endpoint}"
+          @s3.buckets.create(@s3_bucket)
+        else
+          raise "The specified bucket does not exist: bucket = #{@s3_bucket}"
+        end
+      end
+    end
+
+    def check_apikeys
+      @bucket.empty?
+    rescue
+      raise "aws_key_id or aws_sec_key is invalid. Please check your configuration"
+    end
+
+    def check_command(command, algo)
+      begin
+        Open3.capture3("#{command} -V")
+      rescue Errno::ENOENT
+        raise ConfigError, "'#{command}' utility must be in PATH for #{algo} compression"
+      end
+    end
+  end
+end

data/test/test_out_s3.rb

@@ -0,0 +1,322 @@
+require 'fluent/test'
+require 'fluent/plugin/out_s3'
+
+require 'flexmock/test_unit'
+require 'zlib'
+
+class S3OutputTest < Test::Unit::TestCase
+  def setup
+    require 'aws-sdk'
+    Fluent::Test.setup
+  end
+
+  CONFIG = %[
+    aws_key_id test_key_id
+    aws_sec_key test_sec_key
+    s3_bucket test_bucket
+    path log
+    utc
+    buffer_type memory
+  ]
+
+  def create_driver(conf = CONFIG)
+    Fluent::Test::BufferedOutputTestDriver.new(Fluent::S3Output) do
+      def write(chunk)
+        chunk.read
+      end
+
+      private
+
+      def ensure_bucket
+      end
+
+      def check_apikeys
+      end
+    end.configure(conf)
+  end
+
+  def test_configure
+    d = create_driver
+    assert_equal 'test_key_id', d.instance.aws_key_id
+    assert_equal 'test_sec_key', d.instance.aws_sec_key
+    assert_equal 'test_bucket', d.instance.s3_bucket
+    assert_equal 'log', d.instance.path
+    assert d.instance.instance_variable_get(:@use_ssl)
+    assert_equal 'gz', d.instance.instance_variable_get(:@ext)
+    assert_equal 'application/x-gzip', d.instance.instance_variable_get(:@mime_type)
+  end
+
+  def test_configure_with_mime_type_json
+    conf = CONFIG.clone
+    conf << "\nstore_as json\n"
+    d = create_driver(conf)
+    assert_equal 'json', d.instance.instance_variable_get(:@ext)
+    assert_equal 'application/json', d.instance.instance_variable_get(:@mime_type)
+  end
+
+  def test_configure_with_mime_type_text
+    conf = CONFIG.clone
+    conf << "\nstore_as text\n"
+    d = create_driver(conf)
+    assert_equal 'txt', d.instance.instance_variable_get(:@ext)
+    assert_equal 'text/plain', d.instance.instance_variable_get(:@mime_type)
+  end
+
+  def test_configure_with_mime_type_lzo
+    conf = CONFIG.clone
+    conf << "\nstore_as lzo\n"
+    d = create_driver(conf)
+    assert_equal 'lzo', d.instance.instance_variable_get(:@ext)
+    assert_equal 'application/x-lzop', d.instance.instance_variable_get(:@mime_type)
+  rescue => e
+    # TODO: replace code with disable lzop command
+    assert(e.is_a?(Fluent::ConfigError))
+  end
+
+  def test_path_slicing
+    config = CONFIG.clone.gsub(/path\slog/, "path log/%Y/%m/%d")
+    d = create_driver(config)
+    path_slicer = d.instance.instance_variable_get(:@path_slicer)
+    path = d.instance.instance_variable_get(:@path)
+    slice = path_slicer.call(path)
+    assert_equal slice, Time.now.utc.strftime("log/%Y/%m/%d")
+  end
+
+  def test_path_slicing_utc
+    config = CONFIG.clone.gsub(/path\slog/, "path log/%Y/%m/%d")
+    config << "\nutc\n"
+    d = create_driver(config)
+    path_slicer = d.instance.instance_variable_get(:@path_slicer)
+    path = d.instance.instance_variable_get(:@path)
+    slice = path_slicer.call(path)
+    assert_equal slice, Time.now.utc.strftime("log/%Y/%m/%d")
+  end
+
+  def test_format
+    d = create_driver
+
+    time = Time.parse("2011-01-02 13:14:15 UTC").to_i
+    d.emit({"a"=>1}, time)
+    d.emit({"a"=>2}, time)
+
+    d.expect_format %[2011-01-02T13:14:15Z\ttest\t{"a":1}\n]
+    d.expect_format %[2011-01-02T13:14:15Z\ttest\t{"a":2}\n]
+
+    d.run
+  end
+
+  def test_format_included_tag_and_time
+    config = [CONFIG, 'include_tag_key true', 'include_time_key true'].join("\n")
+    d = create_driver(config)
+
+    time = Time.parse("2011-01-02 13:14:15 UTC").to_i
+    d.emit({"a"=>1}, time)
+    d.emit({"a"=>2}, time)
+
+    d.expect_format %[2011-01-02T13:14:15Z\ttest\t{"a":1,"tag":"test","time":"2011-01-02T13:14:15Z"}\n]
+    d.expect_format %[2011-01-02T13:14:15Z\ttest\t{"a":2,"tag":"test","time":"2011-01-02T13:14:15Z"}\n]
+
+    d.run
+  end
+
+  def test_format_with_format_ltsv
+    config = [CONFIG, 'format ltsv'].join("\n")
+    d = create_driver(config)
+
+    time = Time.parse("2011-01-02 13:14:15 UTC").to_i
+    d.emit({"a"=>1, "b"=>1}, time)
+    d.emit({"a"=>2, "b"=>2}, time)
+
+    d.expect_format %[a:1\tb:1\n]
+    d.expect_format %[a:2\tb:2\n]
+
+    d.run
+  end
+
+  def test_format_with_format_json
+    config = [CONFIG, 'format json'].join("\n")
+    d = create_driver(config)
+
+    time = Time.parse("2011-01-02 13:14:15 UTC").to_i
+    d.emit({"a"=>1}, time)
+    d.emit({"a"=>2}, time)
+
+    d.expect_format %[{"a":1}\n]
+    d.expect_format %[{"a":2}\n]
+
+    d.run
+  end
+
+  def test_format_with_format_json_deprecated
+    config = [CONFIG, 'format_json true'].join("\n")
+    d = create_driver(config)
+
+    time = Time.parse("2011-01-02 13:14:15 UTC").to_i
+    d.emit({"a"=>1}, time)
+    d.emit({"a"=>2}, time)
+
+    d.expect_format %[{"a":1}\n]
+    d.expect_format %[{"a":2}\n]
+
+    d.run
+  end
+
+  def test_format_with_format_json_included_tag
+    config = [CONFIG, 'format_json true', 'include_tag_key true'].join("\n")
+    d = create_driver(config)
+
+    time = Time.parse("2011-01-02 13:14:15 UTC").to_i
+    d.emit({"a"=>1}, time)
+    d.emit({"a"=>2}, time)
+
+    d.expect_format %[{"a":1,"tag":"test"}\n]
+    d.expect_format %[{"a":2,"tag":"test"}\n]
+
+    d.run
+  end
+
+  def test_format_with_format_json_included_time
+    config = [CONFIG, 'format json', 'include_time_key true'].join("\n")
+    d = create_driver(config)
+
+    time = Time.parse("2011-01-02 13:14:15 UTC").to_i
+    d.emit({"a"=>1}, time)
+    d.emit({"a"=>2}, time)
+
+    d.expect_format %[{"a":1,"time":"2011-01-02T13:14:15Z"}\n]
+    d.expect_format %[{"a":2,"time":"2011-01-02T13:14:15Z"}\n]
+
+    d.run
+  end
+
+  def test_format_with_format_json_included_tag_and_time
+    config = [CONFIG, 'format json', 'include_tag_key true', 'include_time_key true'].join("\n")
+    d = create_driver(config)
+
+    time = Time.parse("2011-01-02 13:14:15 UTC").to_i
+    d.emit({"a"=>1}, time)
+    d.emit({"a"=>2}, time)
+
+    d.expect_format %[{"a":1,"tag":"test","time":"2011-01-02T13:14:15Z"}\n]
+    d.expect_format %[{"a":2,"tag":"test","time":"2011-01-02T13:14:15Z"}\n]
+
+    d.run
+  end
+
+  def test_chunk_to_write
+    d = create_driver
+
+    time = Time.parse("2011-01-02 13:14:15 UTC").to_i
+    d.emit({"a"=>1}, time)
+    d.emit({"a"=>2}, time)
+
+    # S3OutputTest#write returns chunk.read
+    data = d.run
+
+    assert_equal %[2011-01-02T13:14:15Z\ttest\t{"a":1}\n] +
+                 %[2011-01-02T13:14:15Z\ttest\t{"a":2}\n],
+                 data
+  end
+
+  CONFIG2 = %[
+    hostname testing.node.local
+    aws_key_id test_key_id
+    aws_sec_key test_sec_key
+    s3_bucket test_bucket
+    s3_object_key_format %{path}/events/ts=%{time_slice}/events_%{index}-%{hostname}.%{file_extension}
+    time_slice_format %Y%m%d-%H
+    path log
+    utc
+    buffer_type memory
+    auto_create_bucket false
+    log_level debug
+  ]
+
+  def create_time_sliced_driver(additional_conf = '')
+    d = Fluent::Test::TimeSlicedOutputTestDriver.new(Fluent::S3Output) do
+      private
+
+      def check_apikeys
+      end
+    end.configure([CONFIG2, additional_conf].join("\n"))
+    d
+  end
+
+  def test_write_with_custom_s3_object_key_format
+    # Assert content of event logs which are being sent to S3
+    s3obj = flexmock(AWS::S3::S3Object)
+    s3obj.should_receive(:exists?).with_any_args.and_return { false }
+    s3obj.should_receive(:write).with(
+      on { |pathname|
+        data = nil
+        # Event logs are compressed in GZip
+        pathname.open { |f|
+          gz = Zlib::GzipReader.new(f)
+          data = gz.read
+          gz.close
+        }
+        assert_equal %[2011-01-02T13:14:15Z\ttest\t{"a":1}\n] +
+                     %[2011-01-02T13:14:15Z\ttest\t{"a":2}\n],
+                     data
+
+        pathname.to_s.match(%r|s3-|)
+      },
+      {:content_type => "application/x-gzip", :reduced_redundancy => false})
+
+    # Assert the key of S3Object, which event logs are stored in
+    s3obj_col = flexmock(AWS::S3::ObjectCollection)
+    s3obj_col.should_receive(:[]).with(
+      on { |key|
+        key == "log/events/ts=20110102-13/events_0-testing.node.local.gz"
+      }).
+      and_return {
+        s3obj
+      }
+
+    # Partial mock the S3Bucket, not to make an actual connection to Amazon S3
+    s3bucket, _ = setup_mocks(true)
+    s3bucket.should_receive(:objects).with_any_args.and_return { s3obj_col }
+
+    # We must use TimeSlicedOutputTestDriver instead of BufferedOutputTestDriver,
+    # to make assertions on chunks' keys
+    d = create_time_sliced_driver
+
+    time = Time.parse("2011-01-02 13:14:15 UTC").to_i
+    d.emit({"a"=>1}, time)
+    d.emit({"a"=>2}, time)
+
+    # Finally, the instance of S3Output is initialized and then invoked
+    d.run
+  end
+
+  def setup_mocks(exists_return = false)
+    s3bucket = flexmock(AWS::S3::Bucket)
+    s3bucket.should_receive(:exists?).with_any_args.and_return { exists_return }
+    s3bucket_col = flexmock(AWS::S3::BucketCollection)
+    s3bucket_col.should_receive(:[]).with_any_args.and_return { s3bucket }
+    flexmock(AWS::S3).new_instances do |bucket|
+      bucket.should_receive(:buckets).with_any_args.and_return { s3bucket_col }
+    end
+
+    return s3bucket, s3bucket_col
+  end
+
+  def test_auto_create_bucket_false_with_non_existence_bucket
+    s3bucket, s3bucket_col = setup_mocks
+
+    d = create_time_sliced_driver('auto_create_bucket false')
+    assert_raise(RuntimeError, "The specified bucket does not exist: bucket = test_bucket") {
+      d.run
+    }
+  end
+
+  def test_auto_create_bucket_true_with_non_existence_bucket
+    s3bucket, s3bucket_col = setup_mocks
+    s3bucket_col.should_receive(:create).with_any_args.and_return { true }
+
+    d = create_time_sliced_driver('auto_create_bucket true')
+    assert_nothing_raised {
+      d.run
+    }
+  end
+end

metadata

@@ -0,0 +1,137 @@
+--- !ruby/object:Gem::Specification
+name: fluent-plugin-s3-fork
+version: !ruby/object:Gem::Version
+  version: 0.4.2
+platform: ruby
+authors:
+- Hayato Tomoda
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-10-29 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: fluentd
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.49
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.49
+- !ruby/object:Gem::Dependency
+  name: aws-sdk
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.38'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.38'
+- !ruby/object:Gem::Dependency
+  name: yajl-ruby
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: fluent-mixin-config-placeholders
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.0
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.2
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.2
+- !ruby/object:Gem::Dependency
+  name: flexmock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.2.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.2.0
+description: Amazon S3 output plugin for Fluentd event collector
+email: tomodian@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".travis.yml"
+- AUTHORS
+- ChangeLog
+- Gemfile
+- README.rdoc
+- Rakefile
+- VERSION
+- fluent-plugin-s3.gemspec
+- lib/fluent/plugin/out_s3.rb
+- test/test_out_s3.rb
+homepage: https://github.com/tomodian/fluent-plugin-s3
+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: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Amazon S3 output plugin for Fluentd event collector
+test_files:
+- test/test_out_s3.rb