fluent-plugin-s3-arrow 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 8d4d40af870606fbd11cf131fa371e29e45013281f7b23deae6e30b4f260ecf4
+  data.tar.gz: dc911408cac26e521a32eb50a56e544d18b1f36e2ea83b20fbf7d08c357b7a3e
+SHA512:
+  metadata.gz: 26a33661cab8c5d524d160c727eab8da58c43973ea708d8e1aad45eade08a220612a1620404f9647628d9e6e81cb94e8ccb2a08a59019317d1a582e5254831fc
+  data.tar.gz: c24341e83a739023ab2bfc9b151ab9d1d6cedbba1f25bce63ae1455c426d724e20807cbed89a6663d18840f96196b266446772946176a0a5fdd7d4629f31b028

data/.github/workflows/bench.yml

@@ -0,0 +1,20 @@
+name: "bench"
+on:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: 'build with docker'
+      run: |
+        docker build -t fluent-plugin-s3-arrow .
+    - name: 'bench'
+      id: 'bench'
+      run: |
+        docker run fluent-plugin-s3-arrow /bin/bash -c "benchmark-driver benchmark/compress.yml"
+    - name: 'bench memory'
+      id: 'bench_mem'
+      run: |
+        docker run fluent-plugin-s3-arrow /bin/bash -c "benchmark-driver benchmark/compress.yml --runner memory"

data/.github/workflows/test.yml

@@ -0,0 +1,13 @@
+name: "test"
+on:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: 'Test with docker'
+      run: |
+        docker build -t fluent-plugin-s3-arrow .
+        docker run fluent-plugin-s3-arrow /bin/bash -c "bundle exec rake test"

data/.gitignore

@@ -0,0 +1,56 @@
+*.gem
+*.rbc
+/.config
+/coverage/
+/InstalledFiles
+/pkg/
+/spec/reports/
+/spec/examples.txt
+/test/tmp/
+/test/version_tmp/
+/tmp/
+
+# Used by dotenv library to load environment variables.
+# .env
+
+# Ignore Byebug command history file.
+.byebug_history
+
+## Specific to RubyMotion:
+.dat*
+.repl_history
+build/
+*.bridgesupport
+build-iPhoneOS/
+build-iPhoneSimulator/
+
+## Specific to RubyMotion (use of CocoaPods):
+#
+# We recommend against adding the Pods directory to your .gitignore. However
+# you should judge for yourself, the pros and cons are mentioned at:
+# https://guides.cocoapods.org/using/using-cocoapods.html#should-i-check-the-pods-directory-into-source-control
+#
+# vendor/Pods/
+
+## 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
+
+# Used by RuboCop. Remote config files pulled in from inherit_from directive.
+# .rubocop-https?--*

data/Dockerfile

@@ -0,0 +1,22 @@
+FROM ruby:2.7-buster
+
+RUN apt update && \
+    apt install -y -V ca-certificates lsb-release wget time gzip && \
+    wget https://apache.bintray.com/arrow/$(lsb_release --id --short | tr 'A-Z' 'a-z')/apache-arrow-archive-keyring-latest-$(lsb_release --codename --short).deb && \
+    apt install -y -V ./apache-arrow-archive-keyring-latest-$(lsb_release --codename --short).deb
+
+RUN apt update && \
+    apt install -y -V libparquet-glib-dev
+
+RUN cd /var/tmp/ && \
+    curl -L -O https://github.com/reproio/columnify/releases/download/v0.1.0/columnify_0.1.0_Linux_x86_64.tar.gz && \
+    tar xvfz columnify_0.1.0_Linux_x86_64.tar.gz && \
+    chmod +x columnify && \
+    mv columnify /usr/local/bin/ && \
+    rm -rf /var/tmp/* && \
+    which columnify
+
+RUN mkdir /app
+WORKDIR /app
+COPY . /app
+RUN apt update && bundle install

data/Gemfile

@@ -0,0 +1,3 @@
+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 +1,60 @@
+# fluent-plugin-s3-arrow
+
+Extends the [fluent-plugin-s3](https://github.com/fluent/fluent-plugin-s3) (de)compression algorithm to enable red-arrow compression.
+
+## Installation
+
+### Requirements
+
+- Apache Arrow GLib and Apache Parquet GLib
+  - See Apache [Arrow install document](https://arrow.apache.org/install/) for details.
+- [red-arrow](https://github.com/apache/arrow/tree/master/ruby/red-arrow)
+- [red-parquet](https://github.com/apache/arrow/tree/master/ruby/red-parquet)
+
+### RubyGems
+
+```
+$ gem install fluent-plugin-s3-arrow
+```
+
+### Bundler
+
+Add following line to your Gemfile:
+
+```ruby
+gem "fluent-plugin-s3-arrow"
+```
+
+And then execute:
+
+```
+$ bundle
+```
+
+## Configuration
+
+Example of fluent-plugin-s3 configuration.
+
+```
+<match pattern>
+  @type s3
+
+  # fluent-plugin-s3 configurations ...
+
+  <format>
+    @type json # This plugin currently supports only json formatter.
+  </format>
+
+  store_as arrow
+  <arrow>
+    schema [
+      {"name": "test_string", "type": "string"},
+      {"name": "test_uint64", "type": "uint64"}
+    ]
+  </arrow>
+</match>
+```
+
+## License
+
+Apache License, Version 2.0

data/Rakefile

@@ -0,0 +1,13 @@
+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/benchmark/compress.yml

@@ -0,0 +1,23 @@
+prelude: |-
+  $LOAD_PATH.unshift(File.expand_path("benchmark"))
+  require 'prelude'
+  require 's3_compressor_parquet'
+
+  gzip = create_compressor GZIP_CONFIG
+  arrow = create_compressor ARROW_CONFIG
+  columnify = create_compressor COLUMNIFY_CONFIG
+  chunk = create_chunk
+  
+benchmark:
+  gzip: |-
+    Tempfile.create do |tmp|
+      gzip.compress(chunk, tmp)
+    end
+  arrow: |-
+    Tempfile.create do |tmp|
+      arrow.compress(chunk, tmp)
+    end
+  columnify: |-
+    Tempfile.create do |tmp|
+      columnify.compress(chunk, tmp)
+    end

data/benchmark/prelude.rb

@@ -0,0 +1,59 @@
+$LOAD_PATH.unshift(File.expand_path("lib"))
+require "fluent/test"
+require "fluent/test/driver/output"
+require "fluent/test/helpers"
+require "fluent/plugin/out_s3"
+require "fluent/plugin/s3_compressor_arrow"
+require "json"
+require "faker"
+
+GZIP_CONFIG = %[
+  s3_bucket test_bucket
+  store_as gzip
+]
+
+ARROW_CONFIG = %[
+  s3_bucket test_bucket
+  store_as arrow
+  <arrow>
+    format parquet
+    compression gzip
+    schema [
+      {"name": "test_string",  "type": "string"},
+      {"name": "test_uint64",  "type": "uint64"},
+      {"name": "test_boolean", "type": "boolean"}
+    ]
+  </arrow>
+]
+
+COLUMNIFY_CONFIG = %[
+  s3_bucket test_bucket
+  store_as parquet
+  <compress>
+    schema_type bigquery
+    schema_file benchmark/schema.bq.json
+    record_type jsonl
+    parquet_compression_codec gzip
+  </compress>
+]
+
+def create_compressor(conf = CONFIG)
+  Fluent::Test::Driver::Output.new(Fluent::Plugin::S3Output) do
+  end.configure(conf).instance.instance_variable_get(:@compressor)
+end
+
+state = ENV.fetch("FAKER_RANDOM_SEED", 17).to_i
+Faker::Config.random = Random.new(state)
+
+def create_chunk
+    chunk = Fluent::Plugin::Buffer::MemoryChunk.new(Object.new)
+    while chunk.bytesize < 8388608 do 
+      data = {
+          "test_string"  => Faker::Name.name,
+          "test_uint64"  => Faker::Number.number(digits: 11).to_i,
+          "test_boolean" => Faker::Boolean.boolean
+      }
+      chunk.append([data.to_json + "\n"])
+    end
+    return chunk
+end

data/benchmark/s3_compressor_parquet.rb

@@ -0,0 +1,83 @@
+require "open3"
+
+module Fluent::Plugin
+  class S3Output
+    class ParquetCompressor < Compressor
+      S3Output.register_compressor("parquet", self)
+
+      config_section :compress, multi: false do
+        desc "parquet compression codec"
+        config_param :parquet_compression_codec, :enum, list: [:uncompressed, :snappy, :gzip, :lzo, :brotli, :lz4, :zstd], default: :snappy
+        desc "parquet file page size"
+        config_param :parquet_page_size, :size, default: 8192
+        desc "parquet file row group size"
+        config_param :parquet_row_group_size, :size, default: 128 * 1024 * 1024
+        desc "record data format type"
+        config_param :record_type, :enum, list: [:avro, :csv, :jsonl, :msgpack, :tsv, :json], default: :msgpack
+        desc "schema type"
+        config_param :schema_type, :enum, list: [:avro, :bigquery], default: :avro
+        desc "path to schema file"
+        config_param :schema_file, :string
+      end
+
+      def configure(conf)
+        super
+        check_command("columnify", "-h")
+
+        if [:lzo, :brotli, :lz4].include?@compress.parquet_compression_codec
+          raise Fluent::ConfigError, "unsupported compression codec: #{@compress.parquet_compression_codec}"
+        end
+
+        @parquet_compression_codec = @compress.parquet_compression_codec.to_s.upcase
+        if @compress.record_type == :json
+          @record_type = :jsonl
+        else
+          @record_type = @compress.record_type
+        end
+      end
+
+      def ext
+        "parquet".freeze
+      end
+
+      def content_type
+        "application/octet-stream".freeze
+      end
+
+      def compress(chunk, tmp)
+        chunk_is_file = @buffer_type == "file"
+        path = if chunk_is_file
+                 chunk.path
+               else
+                 w = Tempfile.new("chunk-parquet-tmp")
+                 w.binmode
+                 chunk.write_to(w)
+                 w.close
+                 w.path
+               end
+        stdout, stderr, status = columnify(path, tmp.path)
+        unless status.success?
+          raise "failed to execute columnify command. stdout=#{stdout} stderr=#{stderr} status=#{status.inspect}"
+        end
+      ensure
+        unless chunk_is_file
+          w.close(true) rescue nil
+        end
+      end
+
+      private
+
+      def columnify(src_path, dst_path)
+        Open3.capture3("columnify",
+                       "-parquetCompressionCodec", @parquet_compression_codec,
+                       "-parquetPageSize", @compress.parquet_page_size.to_s,
+                       "-parquetRowGroupSize", @compress.parquet_row_group_size.to_s,
+                       "-recordType", @record_type.to_s,
+                       "-schemaType", @compress.schema_type.to_s,
+                       "-schemaFile", @compress.schema_file,
+                       "-output", dst_path,
+                       src_path)
+      end
+    end
+  end
+end

data/benchmark/schema.bq.json

@@ -0,0 +1,17 @@
+[
+    {
+        "name": "test_string",
+        "type": "STRING",
+        "mode": "REQUIRED"
+    },
+    {
+        "name": "test_uint64",
+        "type": "INTEGER",
+        "mode": "REQUIRED"
+    },
+    {
+        "name": "test_boolean",
+        "type": "BOOLEAN",
+        "mode": "REQUIRED"
+    }
+]

data/fluent-plugin-s3-arrow.gemspec

@@ -0,0 +1,31 @@
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+
+Gem::Specification.new do |spec|
+  spec.name    = "fluent-plugin-s3-arrow"
+  spec.version = "0.1.0"
+  spec.authors = ["kanga333"]
+  spec.email   = ["e411z7t40w@gmail.com"]
+
+  spec.summary       = %q{Extends the fluent-plugin-s3 (de)compression algorithm to enable red-arrow compression.}
+  spec.description   = %q{Extends the fluent-plugin-s3 (de)compression algorithm to enable red-arrow compression.}
+  spec.homepage      = "https://github.com/red-data-tools/fluent-plugin-s3-arrow"
+  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 "benchmark-driver"
+  spec.add_development_dependency "faker"
+  spec.add_development_dependency "rake", "~> 12.0"
+  spec.add_development_dependency "test-unit", "~> 3.0"
+  spec.add_runtime_dependency "fluentd", [">= 0.14.10", "< 2"]
+  spec.add_runtime_dependency "fluent-plugin-s3", ">= 1.0"
+  spec.add_runtime_dependency "red-arrow", ">= 1.0"
+  spec.add_runtime_dependency "red-parquet", ">= 1.0"
+end

data/lib/fluent/plugin/s3_compressor_arrow.rb

@@ -0,0 +1,56 @@
+require 'arrow'
+require 'parquet'
+
+module Fluent::Plugin
+  class S3Output
+    class ArrowCompressor < Compressor
+      S3Output.register_compressor('arrow', self)
+
+      INVALID＿COMBINATIONS = {
+        :arrow => [:snappy],
+        :feather => [:gzip, :snappy],
+      }
+
+      config_section :arrow, multi: false do
+        config_param :schema, :array
+        config_param :format, :enum, list: [:arrow, :feather, :parquet], default: :arrow
+        SUPPORTED_COMPRESSION = [:gzip, :snappy, :zstd]
+        config_param :compression, :enum, list: SUPPORTED_COMPRESSION, default: nil
+        config_param :chunk_size, :integer, default: 1024
+      end
+
+      def configure(conf)
+        super
+
+        if INVALID＿COMBINATIONS[@arrow.format]&.include? @arrow.compression
+          raise Fluent::ConfigError, "#{@arrow.format} unsupported with #{@arrow.format}"
+        end
+
+        @schema = Arrow::Schema.new(@arrow.schema)
+        @options = Arrow::JSONReadOptions.new
+        @options.schema = @schema
+        @options.unexpected_field_behavior = :ignore
+      end
+
+      def ext
+        @arrow.format.freeze
+      end
+
+      def content_type
+        'application/x-apache-arrow-file'.freeze
+      end
+
+      def compress(chunk, tmp)
+        buffer = Arrow::Buffer.new(chunk.read)
+        stream = Arrow::BufferInputStream.new(buffer)
+        table = Arrow::JSONReader.new(stream, @options)
+
+        table.read.save(tmp,
+          format: @arrow.format,
+          chunk_size: @arrow.chunk_size,
+          compression: @arrow.compression,
+        )
+      end
+    end
+  end
+end

data/test/helper.rb

@@ -0,0 +1,8 @@
+$LOAD_PATH.unshift(File.expand_path("../../", __FILE__))
+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_s3_compressor_arrow.rb

@@ -0,0 +1,132 @@
+require "helper"
+require 'json'
+require "fluent/plugin/out_s3"
+require "fluent/plugin/s3_compressor_arrow"
+require "fluent/plugin/output"
+
+class S3OutputTest < Test::Unit::TestCase
+    def setup
+      Fluent::Test.setup
+    end
+  
+    S3_CONFIG = {"s3_bucket" => "test", "store_as" => "arrow"}
+    SCHEMA = [
+      {"name": "test_string", "type": "string"},
+      {"name": "test_uint64", "type": "uint64"},
+    ]
+    CONFIG = config_element("ROOT", "", S3_CONFIG, [config_element("arrow", "", {"schema" => SCHEMA})])
+
+    def test_configure
+      d = create_driver
+      c = d.instance.instance_variable_get(:@compressor)
+      assert_equal :arrow, c.ext
+      assert_equal 'application/x-apache-arrow-file', c.content_type
+      assert c.instance_variable_get(:@schema).is_a?(Arrow::Schema)
+      assert_equal 1024, c.instance_variable_get(:@arrow).chunk_size
+    end
+
+    data(
+      'arrow_snappy':   ['arrow', 'snappy'],
+      'feather_gzip':   ['feather', 'gzip'],
+      'feather_snappy': ['feather', 'snappy'],
+    )
+    def test_invalid_configure
+      format, compression = data
+      arrow_config = config_element("arrow", "", { "schema" => SCHEMA,
+        "format" => format,
+        "compression" => compression,
+      })
+      config = config_element("ROOT", "", S3_CONFIG, [arrow_config])
+      assert_raise Fluent::ConfigError do
+        create_driver(config)
+      end
+    end
+
+    def test_compress
+      d = create_driver
+      c = d.instance.instance_variable_get(:@compressor)
+
+      chunk = Fluent::Plugin::Buffer::MemoryChunk.new(Object.new)
+      d1 = {"test_string" => 'record1', "test_uint64" => 1}
+      d2 = {"test_string" => 'record2', "test_uint64" => 2, "unexpected_field" => false}
+      expected_d2 = d2.dup
+      expected_d2.delete "unexpected_field"
+      chunk.append([d1.to_json + "\n", d2.to_json + "\n"])
+      
+      Tempfile.create do |tmp|
+        c.compress(chunk, tmp)
+        Arrow::MemoryMappedInputStream.open(tmp.path) do |input|
+          reader = Arrow::RecordBatchFileReader.new(input)
+          reader.each do |record_batch|
+            assert_equal([d1, expected_d2], record_batch.collect(&:to_h))
+          end
+        end
+      end
+    end
+
+    data(gzip: "gzip", zstd: "zstd")
+    def test_compress_with_compression
+      arrow_config = config_element("arrow", "", { "schema" => SCHEMA,
+        "compression" => data,
+      })
+      config = config_element("ROOT", "", S3_CONFIG, [arrow_config])
+
+      d = create_driver(conf=config)
+      c = d.instance.instance_variable_get(:@compressor)
+
+      chunk = Fluent::Plugin::Buffer::MemoryChunk.new(Object.new)
+      d1 = {"test_string" => 'record1', "test_uint64" => 1}
+      d2 = {"test_string" => 'record2', "test_uint64" => 2}
+      chunk.append([d1.to_json + "\n", d2.to_json + "\n"])
+      codec = Arrow::Codec.new(data.to_sym)
+      
+      Tempfile.create do |tmp|
+        c.compress(chunk, tmp)
+        raw_input = Arrow::MemoryMappedInputStream.open(tmp.path)
+        Arrow::CompressedInputStream.new(codec,raw_input) do |input|
+          reader = Arrow::RecordBatchFileReader.new(input)
+          reader.each do |record_batch|
+            assert_equal([d1, d2], record_batch.collect(&:to_h))
+          end
+        end
+      end
+    end
+
+    data(
+      'parquet_gzip':   ['parquet', 'gzip'],
+      'parquet_snappy': ['parquet', 'snappy'],
+      'parquet_zstd':   ['parquet', 'zstd'],
+      'feather_zstd':   ['feather', 'zstd'],
+    )
+    def test_compress_with_format
+      format, compression = data
+      arrow_config = config_element("arrow", "", { "schema" => SCHEMA,
+        "format" => format,
+        "compression" => compression,
+      })
+      config = config_element("ROOT", "", S3_CONFIG, [arrow_config])
+
+      d = create_driver(conf=config)
+      c = d.instance.instance_variable_get(:@compressor)
+
+      chunk = Fluent::Plugin::Buffer::MemoryChunk.new(Object.new)
+      d1 = {"test_string" => 'record1', "test_uint64" => 1}
+      d2 = {"test_string" => 'record2', "test_uint64" => 2}
+      chunk.append([d1.to_json + "\n", d2.to_json + "\n"])
+      
+      Tempfile.create do |tmp|
+        c.compress(chunk, tmp)
+        table = Arrow::Table.load(tmp.path, format: format.to_sym, compress: compression.to_sym)
+        table.each_record_batch do |record_batch|
+          assert_equal([d1, d2], record_batch.collect(&:to_h))
+        end
+      end
+    end
+
+    private
+
+    def create_driver(conf = CONFIG)
+      Fluent::Test::Driver::Output.new(Fluent::Plugin::S3Output) do
+      end.configure(conf)
+    end
+end

metadata

@@ -0,0 +1,181 @@
+--- !ruby/object:Gem::Specification
+name: fluent-plugin-s3-arrow
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- kanga333
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2020-09-30 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: benchmark-driver
+  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: faker
+  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: '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'
+- !ruby/object:Gem::Dependency
+  name: fluent-plugin-s3
+  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: red-arrow
+  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: red-parquet
+  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'
+description: Extends the fluent-plugin-s3 (de)compression algorithm to enable red-arrow
+  compression.
+email:
+- e411z7t40w@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".github/workflows/bench.yml"
+- ".github/workflows/test.yml"
+- ".gitignore"
+- Dockerfile
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- benchmark/compress.yml
+- benchmark/prelude.rb
+- benchmark/s3_compressor_parquet.rb
+- benchmark/schema.bq.json
+- fluent-plugin-s3-arrow.gemspec
+- lib/fluent/plugin/s3_compressor_arrow.rb
+- test/helper.rb
+- test/plugin/test_s3_compressor_arrow.rb
+homepage: https://github.com/red-data-tools/fluent-plugin-s3-arrow
+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: Extends the fluent-plugin-s3 (de)compression algorithm to enable red-arrow
+  compression.
+test_files:
+- test/helper.rb
+- test/plugin/test_s3_compressor_arrow.rb