fluent-plugin-records-merger 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 5c802733686b3da60f4482bac6f209bbb8852f21a93c8adacf770c24e10cc8ab
+  data.tar.gz: 4c6157e2bc485d422e2debe7a988169682375af12a6e48df6a906ff361cafe77
+SHA512:
+  metadata.gz: 0d2078ded6a41d434291ae41468fa76784c09f64a57123148c96452a7f73cc6ccfcab53e7d7e0997df12aa7bce8812236a98dccf03a37a3e2992569ffa568a97
+  data.tar.gz: 3ce73da1351c592ee3a7f1cb6d7a3a8c2ae598aaee31337d251331f32ccd1233c21273a87bf954fb60068aaf7e6812b3a8c7e5c62704a510c20a9b6d951c7f4e

data/.gitignore

@@ -0,0 +1,3 @@
+.vscode/
+.idea
+pkg

data/Gemfile

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+source 'https://rubygems.org'
+
+gemspec

data/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   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.md

@@ -0,0 +1,43 @@
+# fluent-plugin-records-merger
+
+[Fluentd](https://fluentd.org/) output plugin to do something.
+
+TODO: write description for you plugin.
+
+## Installation
+
+### RubyGems
+
+```
+$ gem install fluent-plugin-records-merger
+```
+
+### Bundler
+
+Add following line to your Gemfile:
+
+```ruby
+gem "fluent-plugin-records-merger"
+```
+
+And then execute:
+
+```
+$ bundle
+```
+
+## Configuration
+
+You can generate configuration template:
+
+```
+$ fluent-plugin-config-format output records_merger
+```
+
+You can copy and paste generated documents here.
+
+## Copyright
+
+* Copyright(c) 2020- WallyNegima
+* License
+  * Apache License, Version 2.0

data/Rakefile

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+require 'bundler'
+Bundler::GemHelper.install_tasks
+
+require 'rake/testtask'
+
+Rake::TestTask.new(:test) do |t|
+  t.libs.push('lib', 'test')
+  t.test_files = FileList['test/**/test_*.rb']
+  t.verbose = true
+  t.warning = true
+end
+
+task default: [:test]

data/fluent-plugin-records-merger.gemspec

@@ -0,0 +1,29 @@
+# frozen_string_literal: true
+
+lib = File.expand_path('lib', __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+
+Gem::Specification.new do |spec|
+  spec.name    = 'fluent-plugin-records-merger'
+  spec.version = '0.1.0'
+  spec.authors = ['Nobuyuki Oishi', 'WallyNegima']
+  spec.email   = ['u.str.gm@gmail.com']
+
+  spec.summary       = 'this is fluentd plugin. some records merge and out.'
+  spec.description   = 'Parallels data is merged and out.'
+  spec.homepage      = "https://github.com/WallyNegima/fluent-plugin-records-merger"
+  spec.license       = 'Apache-2.0'
+
+  test_files, files  = `git ls-files -z`.split("\x0").partition do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.files         = files
+  spec.executables   = files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = test_files
+  spec.require_paths = ['lib']
+
+  spec.add_development_dependency 'bundler', '~> 1.14'
+  spec.add_development_dependency 'rake', '~> 12.0'
+  spec.add_development_dependency 'test-unit', '~> 3.0'
+  spec.add_runtime_dependency 'fluentd', ['>= 0.14.10', '< 2']
+end

data/lib/fluent/plugin/out_records_merger.rb

@@ -0,0 +1,461 @@
+# frozen_string_literal: true
+
+#
+# Copyright 2020- WallyNegima
+#
+# 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.
+
+require 'fluent/plugin/output'
+
+module Fluent
+  module Plugin
+    class RecordsMergerOutput < Fluent::Plugin::Output
+      Fluent::Plugin.register_output('records_merger', self)
+      helpers :event_emitter
+      PATTERN_MAX_NUM = 20
+
+      config_param :tag, :string, default: 'merged',
+                                  desc: 'Specify the output tag'
+      config_param :main_tag, :string,
+                   desc: 'Specify main_tag name'
+      config_param :sub_tag1, :string, # string: NAME REGEXP
+                   desc: 'Specify sub_tag name'
+      (2..PATTERN_MAX_NUM).each do |i|
+        config_param ('sub_tag' + i.to_s).to_sym, :string, default: nil, # NAME REGEXP
+                                                           desc: 'Specify sub_tag name'
+      end
+      config_param :auto_typecast, :bool, default: true, # false for lower version compatibility
+                                          desc: 'Automatically cast the field types.'
+      config_param :merge_timing, :enum, list: %i[before after simple], default: 'before',
+                                         desc: 'Choose merge timing before/after'
+      # ↓ これ、なんかエラー出てるっぽい。修正する。
+      config_param :tolerable_time_range, :integer, default: nil,
+                                                    desc: 'Specify tolerable time range for merging'
+      # 以下、未実装
+      config_param :force_emit, :bool, default: false,
+                                       desc: 'Specify to emit or not when exceeded the tolerable_time_range'
+
+      def configure(conf)
+        super
+        # p 'in configure()'
+        # p conf
+        # conf: {"@type"=>"records_merger", "tag"=>"merged1", "main_tag"=>"accesslog.1.main", "sub_tag1"=>"accesslog.1.sub1", "sub_tag2"=>"accesslog.1.sub2"}, []
+        @tag = conf['tag'] # これも，結局 ${tag} とかを有効にする関係で使わなくなりそう．
+        # set the tags set by the user
+        @main_tag = conf['main_tag']
+        @sub_tags = []
+        (1..PATTERN_MAX_NUM).each do |i|
+          next unless conf["sub_tag#{i}"]
+
+          @sub_tags.push(conf["sub_tag#{i}"])
+        end
+        if conf['merge_timing']
+          @merge_timing = conf['merge_timing']
+          p '@merge_timing is ' + @merge_timing.to_s
+        else
+          p 'Specify merge_timing before/after'
+        end
+
+        @tolerable_time_range = conf['tolerable_time_range'].to_i
+
+        @last_records = {} # main を流した後に削除する? (未実装)
+
+        p 'size of @sub_tags is ' + @sub_tags.size.to_s
+        @flags4merge = Array.new(@sub_tags.size + 1, 0)
+        # p @flags4merge # [0, 0,..., 0]
+
+        @force_emit = conf['force_emit']
+
+        # from out-record-reformer
+        map = {}
+        # load <record></record> directive
+        conf.elements.select { |element| element.name == 'record' }.each do |element|
+          element.each_pair do |k, v|
+            # p k
+            # p v
+            element.key?(k) # to suppress unread configuration warning
+            map[k] = parse_value(v)
+          end
+        end
+        # p 'print map below'
+        # p map
+
+        placeholder_expander_params = {
+          log: log,
+          auto_typecast: @auto_typecast
+        }
+        @placeholder_expander = PlaceholderExpander.new(placeholder_expander_params)
+        @map = @placeholder_expander.preprocess_map(map)
+        @tag = @placeholder_expander.preprocess_map(@tag)
+        @hostname = Socket.gethostname
+      end
+
+      def start
+        super
+      end
+
+      def shutdown
+        super
+      end
+
+      def process(tag, es)
+        # p 'in process(), merge_timing is '+@merge_timing.to_s
+        if @merge_timing == 'before'
+          # p 'merge timing is before'
+          if @main_tag == tag
+            # p 'main tag has come'
+            store_to_lastrecords(tag, es)
+            @flags4merge[0] = 1
+            # p 'store_to_lastrecords() seems to have no problems'
+            check_timegap if @tolerable_time_range > 0
+            # pp @flags4merge
+            if @flags4merge.all? { |flag| flag == 1 }
+              # pp 'Great! Now you can omit merged event!'
+              emit_new_event(es)
+            else
+              (0..@flags4merge.length - 1).each do |i|
+                @flags4merge[i] = 0
+              end
+            end
+          elsif @sub_tags.include?(tag)
+            store_to_lastrecords(tag, es)
+            @flags4merge[@sub_tags.index(tag) + 1] = 1
+            check_timegap if @tolerable_time_range > 0
+            # p @flags4merge
+          end
+        elsif @merge_timing == 'after'
+          # p 'merge timing is after'
+          if @main_tag == tag
+            store_to_lastrecords(tag, es)
+            @flags4merge[0] = 1
+            check_timegap if @tolerable_time_range > 0
+            # pp @flags4merge
+          elsif @sub_tags.include?(tag)
+            if @flags4merge[0] == 1
+              store_to_lastrecords(tag, es)
+              @flags4merge[@sub_tags.index(tag) + 1] = 1
+              check_timegap if @tolerable_time_range > 0
+              # p @flags4merge
+              if @flags4merge.all? { |flag| flag == 1 }
+                # pp 'Great! Now you can omit merged event!'
+                emit_new_event(es)
+              end
+            else
+              (0..@flags4merge.length - 1).each do |i|
+                @flags4merge[i] = 0
+              end
+              # p @flags4merge
+            end
+          else
+            p 'something else has come! check it!' + tag.to_s
+          end
+        elsif @merge_timing == 'simple'
+          # p 'merge timing is simple'
+          if @main_tag == tag
+            # p "main_tag_came"
+            store_to_lastrecords(tag, es)
+            # p 'after store_to_lastrecords()'
+            @flags4merge[0] = 1
+            check_timegap if @tolerable_time_range > 0
+            # pp @flags4merge
+            if @flags4merge.all? { |flag| flag == 1 }
+              # p 'before emit_new event()'
+              emit_new_event(es)
+              # p 'after emit_new event()'
+
+            end
+          elsif @sub_tags.include?(tag)
+            store_to_lastrecords(tag, es)
+            @flags4merge[@sub_tags.index(tag) + 1] = 1
+            # p @flags4merge
+            check_timegap if @tolerable_time_range > 0
+            emit_new_event(es) if @flags4merge.all? { |flag| flag == 1 }
+          else
+            p 'something else has come! check it!' + tag.to_s
+          end
+        end
+      rescue StandardError => e
+        log.warn "record_reformer: #{e.class} #{e.message} #{e.backtrace.first}"
+        log.debug "record_reformer: tag:#{@tag} map:#{@map} record:#{last_records} placeholder_values:#{placeholder_values}"
+      end
+
+      # そのまま持ってきてしまっているので，rewriteしたほうが良さそう?
+
+      private
+
+      def store_to_lastrecords(tag, es)
+        es.each do |time, record|
+          # p 'in store_to_lastrecords()'
+          # print 'time: '
+          # p time
+          # print 'record: '
+          # p record
+          record.store('time', time)
+          @last_records.store(tag, record)
+          # これで，last_recordsにはsub_tagの情報がそのまま入ってる．ちなみに，storeはkey, valueの形でハッシュに値を入れるために使う．
+          # ここはそのままでも問題なくて，mainが来たときにまとめて調整すれば良い．
+        end
+      end
+
+      def generate_placeholders
+        # here, tag can be used directly only because it is the main tag
+        main_tag_parts = @main_tag.split('.')
+        # p tag_parts
+        main_tag_prefix = tag_prefix(main_tag_parts)
+        # p tag_prefix
+        main_tag_suffix = tag_suffix(main_tag_parts)
+        # p tag_suffix
+
+        placeholder_values = {
+          'main' => @last_records[@main_tag],
+          'main_tag' => @main_tag,
+          'main_tags' => main_tag_parts,
+          'main_tag_parts' => main_tag_parts,
+          'main_tag_prefix' => main_tag_prefix,
+          'main_tag_suffix' => main_tag_suffix,
+          'hostname' => @hostname
+        }
+
+        # SubTagに関する内容を追加
+        (1..PATTERN_MAX_NUM).each do |i|
+          next unless @last_records.key?(@sub_tags[i - 1])
+
+          # p @sub_tags[i-1]
+          sub_tag_parts = @sub_tags[i - 1].split('.')
+          sub_tag_prefix = tag_prefix(sub_tag_parts)
+          sub_tag_suffix = tag_suffix(sub_tag_parts)
+          placeholder_values.merge!(
+            "sub#{i}" => @last_records[@sub_tags[i - 1]],
+            "sub#{i}_tag" => @sub_tags[i - 1],
+            "sub#{i}_tags" => sub_tag_parts,
+            "sub#{i}_tag_parts" => sub_tag_parts,
+            "sub#{i}_tag_prefix" => sub_tag_prefix,
+            "sub#{i}_tag_suffix" => sub_tag_suffix
+          )
+        end
+
+        placeholder_values
+      end
+
+      def emit_new_event(es)
+        # p "in emit_new_event"
+        es.each do |time, _record|
+          placeholder_values = generate_placeholders
+          message = @last_records
+          # print "message:"
+          # p @last_records
+          next if message.keys.empty?
+
+          new_tag, new_record = reform(@tag, @last_records, placeholder_values)
+          next unless new_tag
+
+          router.emit(new_tag, time, new_record)
+          # flagの初期化
+          (0..@flags4merge.length - 1).each do |i|
+            @flags4merge[i] = 0
+          end
+          # p @flags4merge
+          # router.emit(@tag, time, message)
+        end
+      end
+
+      def check_timegap
+        p @last_records.size
+        tag_time_hash = {}
+        if @last_records.size > 1
+          @last_records.each do |k, v|
+            # p k
+            # p v['time'].sec
+            # p v['time'].nsec # ナノセカンドでの比較は余裕があったら実装する
+            tag_time_hash.store(k, v['time'].sec)
+          end
+          # ここでtag_nameと一緒に保持しておきたい
+          latest = tag_time_hash.max { |a, b| a[1] <=> b[1] }
+          # p latest
+          oldest = tag_time_hash.min { |a, b| a[1] <=> b[1] }
+          # p oldest
+          # p @last_records
+
+          if latest[1] - oldest[1] > @tolerable_time_range
+            p oldest[0].to_s + ' is too old! so deleted'
+            @last_records.delete(oldest[0])
+            if oldest[0] == @main_tag
+              @flags4merge[0] = 0
+            else
+              @flags4merge[@sub_tags.index(oldest[0]) + 1] = 0
+            end
+          end
+        end
+      end
+
+      def parse_value(value_str)
+        if value_str.start_with?('{', '[')
+          JSON.parse(value_str)
+        else
+          value_str
+        end
+      rescue StandardError => e
+        log.warn "failed to parse #{value_str} as json. Assuming #{value_str} is a string", error_class: e.class, error: e.message
+        value_str # emit as string
+      end
+
+      def reform(tag, _record, placeholder_values)
+        # p 'in reform()'
+        # p 'tag: '
+        # pp tag
+        # p 'record'
+        # pp record
+        placeholders = @placeholder_expander.prepare_placeholders(placeholder_values)
+        # p 'placeholders'
+        # pp placeholders
+
+        new_tag = expand_placeholders(tag, placeholders) # 新しいtagを生成してる
+        # p 'new_tag'
+        # p new_tag
+
+        # 基本的に，全部ゼロから作るからここでdupする必要はない．
+        # new_record = @renew_record ? {} : record.dup # dupは新しいのを作ってコピーするやつ
+        # @keep_keys.each {|k| new_record[k] = record[k]} if @keep_keys and @renew_record
+
+        new_record = {}
+        # p '@map' # ここには，<record></record>で指定したものが入ってる．
+        # pp @map
+        new_record.merge!(expand_placeholders(@map, placeholders))
+        # p 'new_record'
+        # pp new_record
+
+        [new_tag, new_record]
+      end
+
+      def expand_placeholders(value, placeholders)
+        # p 'in expand_placeholders()'
+        # pp value
+        # pp placeholders
+        if value.is_a?(String)
+          new_value = @placeholder_expander.expand(value, placeholders)
+        elsif value.is_a?(Hash)
+          # ここが<record></record>を処理してる部分
+          new_value = {}
+          # ここで分割して，再帰的に実行している感じ．
+          value.each_pair do |k, v|
+            new_key = @placeholder_expander.expand(k, placeholders, true)
+            new_value[new_key] = expand_placeholders(v, placeholders)
+          end
+        elsif value.is_a?(Array)
+          # これはvalueがArrayで与えられてたら連結するために入ってる．
+          new_value = []
+          value.each_with_index do |v, i|
+            new_value[i] = expand_placeholders(v, placeholders)
+          end
+        else
+          new_value = value
+        end
+        new_value
+      end
+
+      def tag_prefix(tag_parts)
+        return [] if tag_parts.empty?
+
+        tag_prefix = [tag_parts.first]
+        1.upto(tag_parts.size - 1).each do |i|
+          tag_prefix[i] = "#{tag_prefix[i - 1]}.#{tag_parts[i]}"
+        end
+        tag_prefix
+      end
+
+      def tag_suffix(tag_parts)
+        return [] if tag_parts.empty?
+
+        rev_tag_parts = tag_parts.reverse
+        rev_tag_suffix = [rev_tag_parts.first]
+        1.upto(tag_parts.size - 1).each do |i|
+          rev_tag_suffix[i] = "#{rev_tag_parts[i]}.#{rev_tag_suffix[i - 1]}"
+        end
+        rev_tag_suffix.reverse!
+      end
+
+      # THIS CLASS MUST BE THREAD-SAFE
+      # これを入れることで，${tag}とか使えるようになる．
+      class PlaceholderExpander
+        attr_reader :placeholders, :log
+
+        def initialize(params)
+          @log = params[:log]
+          @auto_typecast = params[:auto_typecast]
+        end
+
+        def time_value(time)
+          Time.at(time).to_s
+        end
+
+        def preprocess_map(value, _force_stringify = false)
+          value
+        end
+
+        def prepare_placeholders(placeholder_values)
+          # p 'in prepare_placeholders()'
+          placeholders = {}
+
+          placeholder_values.each do |key, value|
+            # p key
+            if value.is_a?(Array) # tag_parts, etc
+              size = value.size
+              value.each_with_index do |v, idx|
+                placeholders.store("${#{key}[#{idx}]}", v)
+                placeholders.store("${#{key}[#{idx - size}]}", v) # support [-1]
+              end
+            elsif value.is_a?(Hash) # record, etc
+              value.each do |k, v|
+                unless placeholder_values.key?(k) # prevent overwriting the reserved keys such as tag
+                  placeholders.store("${#{k}}", v)
+                end
+                placeholders.store(%(${#{key}["#{k}"]}), v) # record["foo"]
+              end
+            else # string, interger, float, and others?
+              placeholders.store("${#{key}}", value)
+            end
+          end
+          # pp placeholders
+          # p 'end of prepare_placeholders()'
+          placeholders
+        end
+
+        # Expand string with placeholders
+        #
+        # @param [String] str
+        # @param [Boolean] force_stringify the value must be string, used for hash key
+        def expand(str, placeholders, force_stringify = false)
+          if @auto_typecast && !force_stringify
+            single_placeholder_matched = str.match(/\A(\${[^}]+}|__[A-Z_]+__)\z/)
+            if single_placeholder_matched
+              log_if_unknown_placeholder(Regexp.last_match(1), placeholders)
+              return placeholders[single_placeholder_matched[1]]
+            end
+          end
+          str.gsub(/(\${[^}]+}|__[A-Z_]+__)/) do
+            log_if_unknown_placeholder(Regexp.last_match(1), placeholders)
+            placeholders[Regexp.last_match(1)]
+          end
+        end
+
+        private
+
+        def log_if_unknown_placeholder(placeholder, placeholders)
+          unless placeholders.include?(placeholder)
+            log.warn "record_reformer: unknown placeholder `#{placeholder}` found"
+          end
+        end
+      end
+    end
+  end
+end

data/test/helper.rb

@@ -0,0 +1,10 @@
+# frozen_string_literal: true
+
+$LOAD_PATH.unshift(File.expand_path('..', __dir__))
+require 'test-unit'
+require 'fluent/test'
+require 'fluent/test/driver/output'
+require 'fluent/test/helpers'
+
+Test::Unit::TestCase.include(Fluent::Test::Helpers)
+Test::Unit::TestCase.extend(Fluent::Test::Helpers)

data/test/plugin/test_out_records_merger.rb

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+require 'helper'
+require 'fluent/plugin/out_records_merger.rb'
+
+class RecordsMergerOutputTest < Test::Unit::TestCase
+  setup do
+    Fluent::Test.setup
+  end
+
+  test 'failure' do
+    flunk
+  end
+
+  private
+
+  def create_driver(conf)
+    Fluent::Test::Driver::Output.new(Fluent::Plugin::RecordsMergerOutput).configure(conf)
+  end
+end

metadata

@@ -0,0 +1,117 @@
+--- !ruby/object:Gem::Specification
+name: fluent-plugin-records-merger
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Nobuyuki Oishi
+- WallyNegima
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2020-02-28 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.14'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.14'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '12.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '12.0'
+- !ruby/object:Gem::Dependency
+  name: test-unit
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: fluentd
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.14.10
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.14.10
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '2'
+description: Parallels data is merged and out.
+email:
+- u.str.gm@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- fluent-plugin-records-merger.gemspec
+- lib/fluent/plugin/out_records_merger.rb
+- test/helper.rb
+- test/plugin/test_out_records_merger.rb
+homepage: https://github.com/WallyNegima/fluent-plugin-records-merger
+licenses:
+- Apache-2.0
+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: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: this is fluentd plugin. some records merge and out.
+test_files:
+- test/helper.rb
+- test/plugin/test_out_records_merger.rb