fluent-plugin-bigquery-storage-write 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 95c405b96c77e504c30be911ef3821b2e4ff98ed817f142feb0eb927aa61b0f5
+  data.tar.gz: 779be744e6a644f6e257f86a9840f3ce65ddef0b88325ddd3bec4723f9985f34
+SHA512:
+  metadata.gz: 8299958843ee11bfaaa2c06c15362173fd0c942e85e6aaa36873ac985b7669f876bcb107a72ee0ebd313b273b5da34d9f93e7e50161668fdc6bdc1fd194f35ec
+  data.tar.gz: 8c0c2293d91382ae521c1572c57999256407f8754ee838ec81b1b1adacf65c927589db9b0af977f7f0a54b994c3842a1c0774e2a05b4c2d32af17c78fce0cfaf

data/.github/workflows/test.yml

@@ -0,0 +1,27 @@
+name: Test
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        ruby-version: ['2.7', '3.0', '3.1', '3.2']
+
+    steps:
+      - uses: actions/checkout@v2
+      - uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby-version }}
+      - name: Run tests
+        run: |
+          ruby -v
+          gem install bundler rake
+          bundle install --jobs 4 --retry 3
+          bundle exec rake test

data/.gitignore

@@ -0,0 +1,60 @@
+*.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?--*
+
+# Custom
+.idea/
+.vscode/

data/Gemfile

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

data/Gemfile.lock

@@ -0,0 +1,112 @@
+PATH
+  remote: .
+  specs:
+    fluent-plugin-bigquery-storage-write (0.1.0)
+      fluentd (>= 0.14.10, < 2)
+      google-cloud-bigquery-storage (>= 1.3.0)
+      googleauth (>= 1.5.2)
+      grpc (>= 1.55)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    addressable (2.8.4)
+      public_suffix (>= 2.0.2, < 6.0)
+    concurrent-ruby (1.2.2)
+    cool.io (1.7.1)
+    faraday (2.7.6)
+      faraday-net_http (>= 2.0, < 3.1)
+      ruby2_keywords (>= 0.0.4)
+    faraday-net_http (3.0.2)
+    faraday-retry (2.2.0)
+      faraday (~> 2.0)
+    fluentd (1.16.1)
+      bundler
+      cool.io (>= 1.4.5, < 2.0.0)
+      http_parser.rb (>= 0.5.1, < 0.9.0)
+      msgpack (>= 1.3.1, < 2.0.0)
+      serverengine (>= 2.3.2, < 3.0.0)
+      sigdump (~> 0.2.2)
+      strptime (>= 0.2.4, < 1.0.0)
+      tzinfo (>= 1.0, < 3.0)
+      tzinfo-data (~> 1.0)
+      webrick (~> 1.4)
+      yajl-ruby (~> 1.0)
+    gapic-common (0.19.1)
+      faraday (>= 1.9, < 3.a)
+      faraday-retry (>= 1.0, < 3.a)
+      google-protobuf (~> 3.14)
+      googleapis-common-protos (>= 1.3.12, < 2.a)
+      googleapis-common-protos-types (>= 1.3.1, < 2.a)
+      googleauth (~> 1.0)
+      grpc (~> 1.36)
+    google-cloud-bigquery-storage (1.3.0)
+      google-cloud-bigquery-storage-v1 (>= 0.8, < 2.a)
+      google-cloud-core (~> 1.6)
+    google-cloud-bigquery-storage-v1 (0.19.1)
+      gapic-common (>= 0.19.1, < 2.a)
+      google-cloud-errors (~> 1.0)
+    google-cloud-core (1.6.0)
+      google-cloud-env (~> 1.0)
+      google-cloud-errors (~> 1.0)
+    google-cloud-env (1.6.0)
+      faraday (>= 0.17.3, < 3.0)
+    google-cloud-errors (1.3.1)
+    google-protobuf (3.23.2-arm64-darwin)
+    googleapis-common-protos (1.4.0)
+      google-protobuf (~> 3.14)
+      googleapis-common-protos-types (~> 1.2)
+      grpc (~> 1.27)
+    googleapis-common-protos-types (1.6.0)
+      google-protobuf (~> 3.14)
+    googleauth (1.5.2)
+      faraday (>= 0.17.3, < 3.a)
+      jwt (>= 1.4, < 3.0)
+      memoist (~> 0.16)
+      multi_json (~> 1.11)
+      os (>= 0.9, < 2.0)
+      signet (>= 0.16, < 2.a)
+    grpc (1.55.0)
+      google-protobuf (~> 3.23)
+      googleapis-common-protos-types (~> 1.0)
+    grpc-tools (1.55.0)
+    http_parser.rb (0.8.0)
+    jwt (2.7.1)
+    memoist (0.16.2)
+    msgpack (1.7.1)
+    multi_json (1.15.0)
+    os (1.1.4)
+    power_assert (1.1.7)
+    public_suffix (5.0.1)
+    rake (13.0.1)
+    ruby2_keywords (0.0.5)
+    serverengine (2.3.2)
+      sigdump (~> 0.2.2)
+    sigdump (0.2.4)
+    signet (0.17.0)
+      addressable (~> 2.8)
+      faraday (>= 0.17.5, < 3.a)
+      jwt (>= 1.5, < 3.0)
+      multi_json (~> 1.10)
+    strptime (0.2.5)
+    test-unit (3.3.4)
+      power_assert
+    tzinfo (2.0.6)
+      concurrent-ruby (~> 1.0)
+    tzinfo-data (1.2023.3)
+      tzinfo (>= 1.0.0)
+    webrick (1.6.1)
+    yajl-ruby (1.4.3)
+
+PLATFORMS
+  arm64-darwin-22
+
+DEPENDENCIES
+  bundler
+  fluent-plugin-bigquery-storage-write!
+  grpc-tools (>= 1.55)
+  rake
+  test-unit
+
+BUNDLED WITH
+   2.4.13

data/LICENSE

@@ -0,0 +1,177 @@
+
+                                 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

data/README.md

@@ -0,0 +1,106 @@
+# fluent-plugin-bigquery-storage-write
+
+[Fluentd](https://fluentd.org/) output plugin to insert data into BigQuery through storage write api.
+
+## Overview
+
+Google Cloud Bigquery output plugin for [Fluentd](https://fluentd.org/).
+The main difference from [fluent-plugin-bigquery](https://github.com/fluent-plugins-nursery/fluent-plugin-bigquery) is that it uses BigQuery new API `Storage Write`.
+
+Advantages of using the Storage Write API are described [here](https://cloud.google.com/bigquery/docs/write-api#advantages).
+
+## Installation
+
+### RubyGems
+
+```sh
+gem install fluent-plugin-bigquery-storage-write
+```
+
+### Bundler
+
+Add following line to your Gemfile:
+
+```ruby
+gem "fluent-plugin-bigquery-storage-write"
+```
+
+And then execute:
+
+```sh
+bundle
+```
+
+## Configuration
+
+### bigquery_storage_write_insert
+
+| name                       | type   | required?      | default             | description                                                                                                  |
+|:---------------------------|:-------|:---------------|:--------------------|:-------------------------------------------------------------------------------------------------------------|
+| auth_method                | enum   | yes            | application_default | `json_key` or `compute_engine` or `application_default`                                                      |
+| json_key                   | string | yes (json_key) | nil                 | GCP JSON Key file path or JSON Key string                                                                    |
+| project                    | string | yes            | nil                 |                                                                                                              |
+| dataset                    | string | yes            | nil                 |                                                                                                              |
+| table                      | string | yes            | nil                 |                                                                                                              |
+| proto_schema_rb_path       | string | yes            | nil                 | Generated Protocol Buffers schema .rb file path.                                                             |
+| proto_message_class_name   | string | no             | nil                 | Class name of Protocol Buffers message. If not specified, table value that converted to pascal case is used. |
+
+### buffer section
+
+| name                        | type    | required? | default  | description                        |
+|:----------------------------|:--------|:----------|:---------|:-----------------------------------|
+| @type                       | string  | no        | memory   |                                    |
+| chunk_limit_size            | integer | no        | 1MB      |                                    |
+| total_limit_size            | integer | no        | 1GB      |                                    |
+| chunk_records_limit         | integer | no        | 500      |                                    |
+| flush_mode                  | enum    | no        | interval | default, lazy, interval, immediate |
+| flush_interval              | float   | no        | 1.0      |                                    |
+| flush_thread_interval       | float   | no        | 0.05     |                                    |
+| flush_thread_burst_interval | float   | no        | 0.05     |                                    |
+
+And, other params (defined by base class) are available
+
+see. https://github.com/fluent/fluentd/blob/master/lib/fluent/plugin/output.rb
+
+## Examples
+
+First, you have to generate Protocol Buffers compiled code to serialize data.
+Write code `.proto` and compile it using `protoc`.
+The sample code with BigQuery schema is located in the path below `proto/test_data.proto`.
+
+```sh
+bundle exec grpc_tools_ruby_protoc -I proto --ruby_out=proto proto/test_data.proto
+```
+
+Next, specify generated ruby code path to fluentd configuration file.
+
+```
+<match test>
+  @type bigquery_storage_write_insert
+
+  auth_method application_default
+
+  project sample-project
+  dataset test
+  table data
+
+  proto_schema_rb_path /your/generated/code/path/here/test_data_pb.rb
+  proto_message_class_name Data
+</match>
+```
+
+## Tips
+
+- Can I dynamically retrieve and use the BigQuery table schema?
+  - No, you have to use predefined schema generated from `protoc`.
+  - Also, you have to create BigQuery table before using this plugin.
+- Where is the type conversions between Protocol Buffers and BigQuery?
+  - https://cloud.google.com/bigquery/docs/write-api#data_type_conversions
+  - Note that some types, including google.protobuf.Timestamp, are not available due to [BigQuery limitation](https://github.com/googleapis/python-bigquery-storage/issues/257).
+
+## Copyright
+
+* Copyright(c) 2023 gumigumi4f
+* License
+  * Apache License, Version 2.0
+* This plugin includes some code from [fluent-plugin-bigquery](https://github.com/fluent-plugins-nursery/fluent-plugin-bigquery) for compatibility.

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/conf/fluentd.conf

@@ -0,0 +1,39 @@
+<source>
+  @type sample
+  sample {"bool_test":true,"float_test":1.2,"geography_test":"POINT(1 2)","integer_test":1,"json_test":"{\"test1\":1,\"test2\":2}","numeric_test":2,"string_test":"test","repeated_field_test":[1,2,3],"record_test":{"name":"foo","value":"bar"}}
+  tag test
+</source>
+
+<filter test>
+  @type record_transformer
+  enable_ruby
+  <record>
+    date_test ${time.to_i / (24 * 60 * 60) rescue nil}
+    datetime_test ${time.strftime('%Y-%m-%d %H:%M:%S') rescue nil}
+    time_test ${time.strftime('%H:%M:%S') rescue nil}
+    timestamp_test ${(time.to_f * 1_000_000).to_i rescue nil}
+  </record>
+</filter>
+
+<match test>
+  @type bigquery_storage_write_insert
+
+  auth_method application_default
+
+  project sample-project
+  dataset test
+  table data
+
+  proto_schema_rb_path proto/test_data_pb.rb
+  proto_message_class_name Data
+
+  <buffer>
+    @type memory
+
+    flush_at_shutdown           true
+    flush_mode                  interval
+    flush_interval              1
+    flush_thread_interval       1
+    flush_thread_burst_interval 1
+  </buffer>
+</match>

data/fluent-plugin-bigquery-storage-write.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-bigquery-storage-write"
+  spec.version = "0.1.0"
+  spec.authors = ["gumigumi4f"]
+  spec.email   = ["gumigumi4f@gmail.com"]
+
+  spec.summary       = %q{Fluentd output plugin to insert data into BigQuery through storage write api}
+  spec.description   = %q{Fluentd plugin to insert data into BigQuery}
+  spec.homepage      = "https://github.com/gumigumi4f/fluent-plugin-bigquery-storage-write"
+  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"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "test-unit"
+  spec.add_development_dependency "grpc-tools", ">= 1.55"
+  spec.add_runtime_dependency "fluentd", [">= 0.14.10", "< 2"]
+  spec.add_runtime_dependency "grpc", ">= 1.55"
+  spec.add_runtime_dependency "googleauth", ">= 1.5.2"
+  spec.add_runtime_dependency "google-cloud-bigquery-storage", ">= 1.3.0"
+end

data/lib/fluent/plugin/bigquery/storage/helper.rb

@@ -0,0 +1,25 @@
+module Fluent
+  module BigQuery
+    module Storage
+      module Helper
+        class << self
+          def snake_to_pascal(snake_case)
+            words = snake_case.split('_')
+            words.map(&:capitalize).join
+          end
+
+          def get_descriptor_data(file_path)
+            File.foreach(file_path) do |line|
+              if line.start_with?("descriptor_data = ")
+                data = line.chomp.gsub(/^descriptor_data = /, '')
+                return eval(data)
+              end
+            end
+
+            raise "No descriptor data found in file. path=#{file_path}"
+          end
+        end
+      end
+    end
+  end
+end

data/lib/fluent/plugin/bigquery/storage/writer.rb

@@ -0,0 +1,79 @@
+module Fluent
+  module BigQuery
+    module Storage
+      class Writer
+        def initialize(log, auth_method, project, dataset, table, proto_descriptor, **options)
+          @auth_method = auth_method
+          @scope = "https://www.googleapis.com/auth/bigquery"
+          @options = options
+          @log = log
+
+          @write_stream = "projects/#{project}/datasets/#{dataset}/tables/#{table}/streams/_default"
+          @write_schema = Google::Cloud::Bigquery::Storage::V1::ProtoSchema.new(
+            proto_descriptor: proto_descriptor
+          )
+        end
+
+        def client
+          @client ||= Google::Cloud::Bigquery::Storage::V1::BigQueryWrite::Client.new.tap do |cl|
+            cl.configure.credentials = get_auth
+          end
+        end
+
+        def insert(rows)
+          data = [
+            Google::Cloud::Bigquery::Storage::V1::AppendRowsRequest.new(
+              write_stream: @write_stream,
+              proto_rows: Google::Cloud::Bigquery::Storage::V1::AppendRowsRequest::ProtoData.new(
+                rows: Google::Cloud::Bigquery::Storage::V1::ProtoRows.new(
+                  serialized_rows: rows
+                ),
+                writer_schema: @write_schema
+              )
+            )
+          ]
+          client.append_rows(data).map do |e|
+            @log.trace(e)
+          end
+        end
+
+        private
+
+        def get_auth
+          case @auth_method
+          when :compute_engine
+            get_auth_from_compute_engine
+          when :json_key
+            get_auth_from_json_key
+          when :application_default
+            get_auth_from_application_default
+          else
+            raise ConfigError, "Unknown auth method: #{@auth_method}"
+          end
+        end
+
+        def get_auth_from_compute_engine
+          Google::Auth::GCECredentials.new
+        end
+
+        def get_auth_from_json_key
+          json_key = @options[:json_key]
+
+          begin
+            JSON.parse(json_key)
+            key = StringIO.new(json_key)
+            Google::Auth::ServiceAccountCredentials.make_creds(json_key_io: key, scope: @scope)
+          rescue JSON::ParserError
+            File.open(json_key) do |f|
+              Google::Auth::ServiceAccountCredentials.make_creds(json_key_io: f, scope: @scope)
+            end
+          end
+        end
+
+        def get_auth_from_application_default
+          Google::Auth.get_application_default([@scope])
+        end
+      end
+    end
+  end
+end

data/lib/fluent/plugin/out_bigquery_storage_write_insert.rb

@@ -0,0 +1,109 @@
+require "fluent/plugin/output"
+
+require "fluent/plugin/bigquery/storage/writer"
+require "fluent/plugin/bigquery/storage/helper"
+
+require 'google/protobuf'
+require "google/cloud/bigquery/storage/v1"
+require 'googleauth'
+
+module Fluent
+  module Plugin
+    class BigQueryStorageWriteInsertOutput < Fluent::Plugin::Output
+      Fluent::Plugin.register_output("bigquery_storage_write_insert", self)
+
+      helpers :inject
+
+      config_param :auth_method, :enum, list: [:compute_engine, :json_key, :application_default], default: :application_default
+      config_param :json_key, default: nil, secret: true
+
+      config_param :project, :string
+      config_param :dataset, :string
+      config_param :table, :string
+
+      config_param :proto_schema_rb_path, :string
+      config_param :proto_message_class_name, :string, default: nil
+
+      config_section :buffer do
+        config_set_default :@type, "memory"
+        config_set_default :flush_mode, :interval
+        config_set_default :flush_interval, 1
+        config_set_default :flush_thread_interval, 0.05
+        config_set_default :flush_thread_burst_interval, 0.05
+        config_set_default :chunk_limit_size, 1 * 1024 ** 2 # 1MB
+        config_set_default :total_limit_size, 1 * 1024 ** 3 # 1GB
+        config_set_default :chunk_limit_records, 500
+      end
+
+      def configure(conf)
+        super
+
+        case @auth_method
+        when :compute_engine
+          # Do nothing
+        when :json_key
+          unless @json_key
+            raise Fluent::ConfigError, "'json_key' must be specified if auth_method == 'json_key'"
+          end
+        when :application_default
+          # Do nothing
+        else
+          raise Fluent::ConfigError, "unrecognized 'auth_method': #{@auth_method}"
+        end
+      end
+
+      def start
+        super
+
+        message_cls_name = @proto_message_class_name
+        if message_cls_name.nil?
+          message_cls_name = Fluent::BigQuery::Storage::Helper.snake_to_pascal(@table)
+        end
+
+        descriptor_data = Fluent::BigQuery::Storage::Helper.get_descriptor_data(@proto_schema_rb_path)
+
+        Google::Protobuf::DescriptorPool.generated_pool.add_serialized_file(descriptor_data)
+        parsed = Google::Protobuf::FileDescriptorProto.decode(descriptor_data)
+        @descriptor_proto = parsed.message_type.find { |msg| msg.name == message_cls_name }
+        if @descriptor_proto.nil?
+          raise "No descriptor proto found. class_name=#{message_cls_name}"
+        end
+        @klass = Google::Protobuf::DescriptorPool.generated_pool.lookup(message_cls_name).msgclass
+
+        @writer = Fluent::BigQuery::Storage::Writer.new(@log, @auth_method, @project, @dataset, @table, @descriptor_proto,
+                                                        json_key: @json_key)
+      rescue => e
+        log.error("initialize error")
+        raise Fluent::UnrecoverableError, e
+      end
+
+      def format(tag, time, record)
+        if record.nil?
+          log.warn("nil record detected. corrupted chunks? tag=#{tag}, time=#{time}")
+          return
+        end
+
+        record = inject_values_to_record(tag, time, record)
+        record.to_json + "\n"
+      rescue
+        log.error("format error", record: record)
+        raise
+      end
+
+      def write(chunk)
+        rows = chunk.open do |io|
+          io.map do |line|
+            val = @klass.decode_json(line, ignore_unknown_fields: true)
+            @klass.encode(val)
+          end
+        end
+
+        @writer.insert(rows)
+      end
+
+      def multi_workers_ready?
+        true
+      end
+    end
+  end
+end

data/proto/test_data.proto

@@ -0,0 +1,105 @@
+syntax = "proto2";
+
+message Data {
+  message Record {
+    optional string name = 1;
+    optional string value = 2;
+  }
+
+  optional bool bool_test = 1;
+  optional int32 date_test = 2;
+  optional string datetime_test = 3;
+  optional double float_test = 4;
+  optional string geography_test = 5;
+  optional int64 integer_test = 6;
+  optional string json_test = 7;
+  optional int64 numeric_test = 8;
+  optional string string_test = 9;
+  optional string time_test = 10;
+  optional int64 timestamp_test = 11;
+  repeated int64 repeated_field_test = 12;
+  optional Record record_test = 13;
+}
+
+// Below is the schema on BigQuery
+/*
+[
+    {
+        "name": "bool_test",
+        "type": "BOOLEAN",
+        "mode": "NULLABLE"
+    },
+    {
+        "name": "date_test",
+        "type": "DATE",
+        "mode": "NULLABLE"
+    },
+    {
+        "name": "datetime_test",
+        "type": "DATETIME",
+        "mode": "NULLABLE"
+    },
+    {
+        "name": "float_test",
+        "type": "FLOAT",
+        "mode": "NULLABLE"
+    },
+    {
+        "name": "geography_test",
+        "type": "GEOGRAPHY",
+        "mode": "NULLABLE"
+    },
+    {
+        "name": "integer_test",
+        "type": "INTEGER",
+        "mode": "NULLABLE"
+    },
+    {
+        "name": "json_test",
+        "type": "JSON",
+        "mode": "NULLABLE"
+    },
+    {
+        "name": "numeric_test",
+        "type": "NUMERIC",
+        "mode": "NULLABLE"
+    },
+    {
+        "name": "string_test",
+        "type": "STRING",
+        "mode": "NULLABLE"
+    },
+    {
+        "name": "time_test",
+        "type": "TIME",
+        "mode": "NULLABLE"
+    },
+    {
+        "name": "timestamp_test",
+        "type": "TIMESTAMP",
+        "mode": "NULLABLE"
+    },
+    {
+        "name": "repeated_field_test",
+        "type": "INTEGER",
+        "mode": "REPEATED"
+    },
+    {
+        "name": "record_test",
+        "type": "RECORD",
+        "mode": "NULLABLE",
+        "fields": [
+            {
+                "name": "name",
+                "type": "STRING",
+                "mode": "NULLABLE"
+            },
+            {
+                "name": "value",
+                "type": "STRING",
+                "mode": "NULLABLE"
+            }
+        ]
+    }
+]
+*/

data/proto/test_data_pb.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# source: test_data.proto
+
+require 'google/protobuf'
+
+
+descriptor_data = "\n\x0ftest_data.proto\"\xd5\x02\n\x04\x44\x61ta\x12\x11\n\tbool_test\x18\x01 \x01(\x08\x12\x11\n\tdate_test\x18\x02 \x01(\x05\x12\x15\n\rdatetime_test\x18\x03 \x01(\t\x12\x12\n\nfloat_test\x18\x04 \x01(\x01\x12\x16\n\x0egeography_test\x18\x05 \x01(\t\x12\x14\n\x0cinteger_test\x18\x06 \x01(\x03\x12\x11\n\tjson_test\x18\x07 \x01(\t\x12\x14\n\x0cnumeric_test\x18\x08 \x01(\x03\x12\x13\n\x0bstring_test\x18\t \x01(\t\x12\x11\n\ttime_test\x18\n \x01(\t\x12\x16\n\x0etimestamp_test\x18\x0b \x01(\x03\x12\x1b\n\x13repeated_field_test\x18\x0c \x03(\x03\x12!\n\x0brecord_test\x18\r \x01(\x0b\x32\x0c.Data.Record\x1a%\n\x06Record\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\t"
+
+pool = Google::Protobuf::DescriptorPool.generated_pool
+
+begin
+  pool.add_serialized_file(descriptor_data)
+rescue TypeError => e
+  # Compatibility code: will be removed in the next major version.
+  require 'google/protobuf/descriptor_pb'
+  parsed = Google::Protobuf::FileDescriptorProto.decode(descriptor_data)
+  parsed.clear_dependency
+  serialized = parsed.class.encode(parsed)
+  file = pool.add_serialized_file(serialized)
+  warn "Warning: Protobuf detected an import path issue while loading generated file #{__FILE__}"
+  imports = [
+  ]
+  imports.each do |type_name, expected_filename|
+    import_file = pool.lookup(type_name).file_descriptor
+    if import_file.name != expected_filename
+      warn "- #{file.name} imports #{expected_filename}, but that import was loaded as #{import_file.name}"
+    end
+  end
+  warn "Each proto file must use a consistent fully-qualified name."
+  warn "This will become an error in the next major version."
+end
+
+Data = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("Data").msgclass
+Data::Record = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("Data.Record").msgclass

data/test/helper.rb

@@ -0,0 +1,7 @@
+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_bigquery_storage_write_insert.rb

@@ -0,0 +1,51 @@
+require "helper"
+require "fluent/plugin/out_bigquery_storage_write_insert.rb"
+
+class BigQueryStorageWriteInsertOutputTest < Test::Unit::TestCase
+  CONFIG = %[
+    @type bigquery_storage_write_insert
+
+    auth_method application_default
+
+    project sample-project
+    dataset test
+    table data
+
+    proto_schema_rb_path /path/to/schema_rb
+    proto_message_class_name Test
+  ]
+
+  setup do
+    Fluent::Test.setup
+  end
+
+  sub_test_case 'configure' do
+    test 'all params are configured' do
+      d = create_driver(%[
+        auth_method json_key
+        json_key test
+
+        project sample-project
+        dataset test
+        table data
+
+        proto_schema_rb_path /path/to/schema_rb
+        proto_message_class_name Test
+      ])
+
+      assert_equal(:json_key, d.instance.auth_method)
+      assert_equal('test', d.instance.json_key)
+      assert_equal('sample-project', d.instance.project)
+      assert_equal('test', d.instance.dataset)
+      assert_equal('data', d.instance.table)
+      assert_equal('/path/to/schema_rb', d.instance.proto_schema_rb_path)
+      assert_equal('Test', d.instance.proto_message_class_name)
+    end
+  end
+
+  private
+
+  def create_driver(conf = CONFIG)
+    Fluent::Test::Driver::Output.new(Fluent::Plugin::BigQueryStorageWriteInsertOutput).configure(conf)
+  end
+end

metadata

@@ -0,0 +1,180 @@
+--- !ruby/object:Gem::Specification
+name: fluent-plugin-bigquery-storage-write
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- gumigumi4f
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2023-06-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: test-unit
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: grpc-tools
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.55'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.55'
+- !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: grpc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.55'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '1.55'
+- !ruby/object:Gem::Dependency
+  name: googleauth
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.5.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.5.2
+- !ruby/object:Gem::Dependency
+  name: google-cloud-bigquery-storage
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.3.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.3.0
+description: Fluentd plugin to insert data into BigQuery
+email:
+- gumigumi4f@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".github/workflows/test.yml"
+- ".gitignore"
+- Gemfile
+- Gemfile.lock
+- LICENSE
+- README.md
+- Rakefile
+- conf/fluentd.conf
+- fluent-plugin-bigquery-storage-write.gemspec
+- lib/fluent/plugin/bigquery/storage/helper.rb
+- lib/fluent/plugin/bigquery/storage/writer.rb
+- lib/fluent/plugin/out_bigquery_storage_write_insert.rb
+- proto/test_data.proto
+- proto/test_data_pb.rb
+- test/helper.rb
+- test/plugin/test_out_bigquery_storage_write_insert.rb
+homepage: https://github.com/gumigumi4f/fluent-plugin-bigquery-storage-write
+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: 3.1.6
+signing_key: 
+specification_version: 4
+summary: Fluentd output plugin to insert data into BigQuery through storage write
+  api
+test_files:
+- test/helper.rb
+- test/plugin/test_out_bigquery_storage_write_insert.rb