embulk-output-bigquery 0.6.9 → 0.7.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c07225701eda6aae9b1785a0204f22a7c19dcc6af5df3bb9186ff32029ca4a89
-  data.tar.gz: d611f3d7b023f49c9d35febe3bdb2caaab73feeeb7903cb22d432f9c0799b6fc
+  metadata.gz: 4fba97c5f4a2935df80c4c4efb7f389c9818f221773c856b5f490f8e3e65c172
+  data.tar.gz: e6949d104a822c586dc65180aff030af3da963a535a9e2ca3a9ac5b93f706527
 SHA512:
-  metadata.gz: 99f64826852010f0f3473f70016d38fb0640d70e5ee713861e633834cb41d4b8f606214272a8a11c0612b6fadaa8905f581e226b952fac3eb06908a050dfa090
-  data.tar.gz: d6d3e7a11b7406710afa6fccca129809011465597d664be4d2b5cb55886711fa7751e43be1c91bee2d013a042402d6aa5f451096fc166e3f0cecb392ab4d13d3
+  metadata.gz: 695c2c596d172eed178ddf34e12b985c7179cff73924d316641e77e4ee52465bb79d94d7e7c1141a7831859fe44d15cfd28b6f7aa0b409ce0d57626ac83abea9
+  data.tar.gz: c48f7b6ce8df9141f2c716ffec0d0786fc5aa87cad034fffeb6df5055236cb5dff651f41f17580a6041b769cfd9198be36656909b87e1c844a694faef42616fa

data/.github/workflows/check.yml

@@ -0,0 +1,42 @@
+name: Check
+on: [ pull_request, push ]
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    # push: always run.
+    # pull_request: run only when the PR is submitted from a forked repository, not within this repository.
+    if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name != github.repository
+    strategy:
+      matrix:
+        jruby_version:
+        - 9.3.10.0
+        - 9.4.2.0
+      fail-fast: false
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up OpenJDK 8
+      uses: actions/setup-java@v4
+      with:
+        java-version: 8
+        distribution: "temurin"
+    - uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: 'jruby-${{ matrix.jruby_version }}'
+        bundler-cache: true
+    - name: show ruby version
+      run: ruby -v
+    - name: bundle install
+      run: bundle install
+    #
+    # This step avoids the following error in the JRuby 9.4 test.
+    #
+    # Gem::LoadError: You have already activated rake 13.0.6,
+    # but your Gemfile requires rake 13.1.0. Prepending
+    # `bundle exec` to your command may solve this.
+    #
+    - name: install rake 13.1.0
+      run: gem install rake -v 13.1.0
+    - name: install embulk.jar
+      run: "curl -L -o embulk.jar https://github.com/embulk/embulk/releases/download/v0.10.49/embulk-0.10.49.jar"
+    - name: rake test
+      run: bundle exec env RUBYOPT="-r ./embulk.jar" rake test

data/.github/workflows/publish.yml

@@ -0,0 +1,41 @@
+name: Publish
+on:
+  push:
+    tags:
+      - "v0.*"
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: maven-central-and-ruby-gems
+    strategy:
+      fail-fast: true
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: 3.3.0
+    # get tag variable using {{ github.ref_name }}
+    #
+    # References:
+    # * https://docs.github.com/en/actions/learn-github-actions/contexts#github-context
+    # * https://docs.github.com/en/actions/learn-github-actions/variables#default-environment-variables
+    - name: extract gem version from tag
+      id: vars
+      run: echo version=${{ github.ref_name }} | sed -e 's/v0/0/' >> $GITHUB_OUTPUT
+    #
+    # From gem push documents.
+    #
+    # The push command will use ~/.gem/credentials to authenticate to a server,
+    # but you can use the RubyGems environment variable GEM_HOST_API_KEY
+    # to set the api key to authenticate.
+    #
+    # https://guides.rubygems.org/command-reference/#gem-push
+    #
+    - name: Publish
+      run: |
+        rake build
+        gem push pkg/${EMBULK_PLUGIN_NAME}-${{ steps.vars.outputs.version }}.gem
+      env:
+        EMBULK_PLUGIN_NAME: embulk-output-bigquery
+        GEM_HOST_API_KEY: "${{secrets.RUBYGEMS_API_KEY}}"

data/CHANGELOG.md

@@ -1,3 +1,12 @@
+## 0.7.1 - 2024-03-4
+* [enhancement] Support description of columns and tables (Thanks to @kyoshidajp and @fagai ) #142
+* [maintenance] Add missing GitHub Actions environment setting. #160
+* [maintenance] Replace google-api-client with specific Google APIs (Thanks to @Nozomuts) #161
+* [maintenance] Update GitHub Actions use checkout@v4 and setup-java@v4 #162
+
+## 0.7.0 - 2024-02-1
+* [enhancement] Add support Embulk 0.11.x
+
 ## 0.6.9 - 2023-03-16
 * [enhancement] Add SSLException to retry job (thanks to @mzumi)
 

data/Gemfile

@@ -1,8 +1,7 @@
 source 'https://rubygems.org/'
 
 gemspec
-gem 'embulk', '< 0.10'
-gem 'liquid', '= 4.0.0' # the version included in embulk.jar
+gem 'embulk', '= 0.10.49'
 gem 'embulk-parser-none'
 gem 'embulk-parser-jsonl'
 gem 'pry-nav'

data/README.md

@@ -1,7 +1,5 @@
 # embulk-output-bigquery
 
-[![Build Status](https://secure.travis-ci.org/embulk/embulk-output-bigquery.png?branch=master)](http://travis-ci.org/embulk/embulk-output-bigquery)
-
 [Embulk](https://github.com/embulk/embulk/) output plugin to load/insert data into [Google BigQuery](https://cloud.google.com/bigquery/) using [direct insert](https://cloud.google.com/bigquery/loading-data-into-bigquery#loaddatapostrequest)
 
 ## Overview
@@ -14,6 +12,13 @@ https://developers.google.com/bigquery/loading-data-into-bigquery
 * **Cleanup supported**: no
 * **Dynamic table creating**: yes
 
+### Supported Embulk
+
+| gem version      | Embulk version     |
+|------------------|--------------------|
+| 0.7.0 and higher | v0.11.0 and higher |
+| 0.6.9 and lower  | v0.9.X and lower   |
+
 ### NOT IMPLEMENTED
 * insert data over streaming inserts
   * for continuous real-time insertions
@@ -55,6 +60,7 @@ OAuth flow for installed applications.
 |  gcs_bucket                          | string      | optional   | nil                      | See [GCS Bucket](#gcs-bucket) |
 |  auto_create_gcs_bucket              | boolean     | optional   | false                    | See [GCS Bucket](#gcs-bucket) |
 |  progress_log_interval               | float       | optional   | nil (Disabled)           | Progress log interval. The progress log is disabled by nil (default). NOTE: This option may be removed in a future because a filter plugin can achieve the same goal |
+|  description                         | string      | optional   | nil                      | description of table |
 
 Client or request options
 
@@ -324,6 +330,7 @@ Column options are used to aid guessing BigQuery schema, or to define conversion
     - json:      `STRING`,  `RECORD` (default: `STRING`)
   - **mode**: BigQuery mode such as `NULLABLE`, `REQUIRED`, and `REPEATED` (string, default: `NULLABLE`)
   - **fields**: Describes the nested schema fields if the type property is set to RECORD. Please note that this is **required** for `RECORD` column.
+  - **description**: description (string, default is `None`).
   - **timestamp_format**: timestamp format to convert into/from `timestamp` (string, default is `default_timestamp_format`)
   - **timezone**: timezone to convert into/from `timestamp`, `date` (string, default is `default_timezone`).
 - **default_timestamp_format**: default timestamp format for column_options (string, default is "%Y-%m-%d %H:%M:%S.%6N")

data/embulk-output-bigquery.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |spec|
   spec.name          = "embulk-output-bigquery"
-  spec.version       = "0.6.9"
+  spec.version       = "0.7.1"
   spec.authors       = ["Satoshi Akama", "Naotoshi Seo"]
   spec.summary       = "Google BigQuery output plugin for Embulk"
   spec.description   = "Embulk plugin that insert records to Google BigQuery."
@@ -14,18 +14,14 @@ Gem::Specification.new do |spec|
   spec.test_files    = spec.files.grep(%r{^(test|spec)/})
   spec.require_paths = ["lib"]
 
-  # TODO
-  # signet 0.12.0 and google-api-client 0.33.0 require >= Ruby 2.4.
-  # Embulk 0.9 use JRuby 9.1.X.Y and it's compatible with Ruby 2.3.
-  # So, force install signet < 0.12 and google-api-client < 0.33.0
-  # Also, representable version >= 3.1.0 requires Ruby version >= 2.4
-  spec.add_dependency 'signet', '~> 0.7', '< 0.12.0'
-  spec.add_dependency 'google-api-client','< 0.33.0'
+  # the latest version
+  spec.add_dependency 'google-apis-storage_v1'
+  spec.add_dependency 'google-apis-bigquery_v2'
   spec.add_dependency 'time_with_zone'
-  spec.add_dependency "representable", ['~> 3.0.0', '< 3.1']
-  # faraday 1.1.0 require >= Ruby 2.4.
-  # googleauth 0.9.0 requires faraday ~> 0.12
-  spec.add_dependency "faraday", '~> 0.12'
+  spec.add_dependency 'thwait'
+  # activesupport require Ruby >= 2.7.0
+  # jruby-9.3.0.0 is MRI 2.6 compatible
+  spec.add_dependency 'activesupport', "< 7.0"
 
   spec.add_development_dependency 'bundler', ['>= 1.10.6']
   spec.add_development_dependency 'rake', ['>= 10.0']

data/lib/embulk/output/bigquery/bigquery_client.rb

@@ -121,7 +121,7 @@ module Embulk
               opts = {}
 
               Embulk.logger.debug { "embulk-output-bigquery: insert_job(#{@project}, #{body}, #{opts})" }
-              response = with_network_retry { client.insert_job(@project, body, opts) }
+              response = with_network_retry { client.insert_job(@project, body, **opts) }
               unless @task['is_skip_job_result_check']
                 response = wait_load('Load', response)
               end
@@ -222,7 +222,7 @@ module Embulk
                 # },
               }
               Embulk.logger.debug { "embulk-output-bigquery: insert_job(#{@project}, #{body}, #{opts})" }
-              response = with_network_retry { client.insert_job(@project, body, opts) }
+              response = with_network_retry { client.insert_job(@project, body, **opts) }
               if @task['is_skip_job_result_check']
                 response
               else
@@ -278,7 +278,7 @@ module Embulk
 
               opts = {}
               Embulk.logger.debug { "embulk-output-bigquery: insert_job(#{@project}, #{body}, #{opts})" }
-              response = with_network_retry { client.insert_job(@project, body, opts) }
+              response = with_network_retry { client.insert_job(@project, body, **opts) }
               wait_load('Copy', response)
             rescue Google::Apis::ServerError, Google::Apis::ClientError, Google::Apis::AuthorizationError => e
               response = {status_code: e.status_code, message: e.message, error_class: e.class}
@@ -372,7 +372,7 @@ module Embulk
             end
             opts = {}
             Embulk.logger.debug { "embulk-output-bigquery: insert_dataset(#{@project}, #{dataset}, #{@location_for_log}, #{body}, #{opts})" }
-            with_network_retry { client.insert_dataset(@project, body, opts) }
+            with_network_retry { client.insert_dataset(@project, body, **opts) }
           rescue Google::Apis::ServerError, Google::Apis::ClientError, Google::Apis::AuthorizationError => e
             if e.status_code == 409 && /Already Exists:/ =~ e.message
               # ignore 'Already Exists' error
@@ -420,6 +420,7 @@ module Embulk
               table_reference: {
                 table_id: table,
               },
+              description: @task['description'],
               schema: {
                 fields: fields,
               }
@@ -447,7 +448,7 @@ module Embulk
 
             opts = {}
             Embulk.logger.debug { "embulk-output-bigquery: insert_table(#{@project}, #{dataset}, #{@location_for_log}, #{body}, #{opts})" }
-            with_network_retry { client.insert_table(@project, dataset, body, opts) }
+            with_network_retry { client.insert_table(@project, dataset, body, **opts) }
           rescue Google::Apis::ServerError, Google::Apis::ClientError, Google::Apis::AuthorizationError => e
             if e.status_code == 409 && /Already Exists:/ =~ e.message
               # ignore 'Already Exists' error

data/lib/embulk/output/bigquery/helper.rb

@@ -46,10 +46,11 @@ module Embulk
             embulk_type   = column[:type]
             column_option = column_options_map[column_name] || {}
             {}.tap do |field|
-              field[:name]   = column_name
-              field[:type]   = (column_option['type'] || bq_type_from_embulk_type(embulk_type)).upcase
-              field[:mode]   = column_option['mode'] if column_option['mode']
-              field[:fields] = deep_symbolize_keys(column_option['fields']) if column_option['fields']
+              field[:name]        = column_name
+              field[:type]        = (column_option['type'] || bq_type_from_embulk_type(embulk_type)).upcase
+              field[:mode]        = column_option['mode'] if column_option['mode']
+              field[:fields]      = deep_symbolize_keys(column_option['fields']) if column_option['fields']
+              field[:description] = column_option['description'] if column_option['description']
             end
           end
         end

data/lib/embulk/output/bigquery.rb

@@ -63,6 +63,8 @@ module Embulk
           'payload_column'                 => config.param('payload_column',                 :string,  :default => nil),
           'payload_column_index'           => config.param('payload_column_index',           :integer, :default => nil),
 
+          'description'                    => config.param('description',                    :string,  :default => nil),
+
           'open_timeout_sec'               => config.param('open_timeout_sec',               :integer, :default => nil),
           'timeout_sec'                    => config.param('timeout_sec',                    :integer, :default => nil), # google-api-ruby-client < v0.11.0
           'send_timeout_sec'               => config.param('send_timeout_sec',               :integer, :default => nil), # google-api-ruby-client >= v0.11.0

data/test/helper.rb

@@ -4,14 +4,14 @@ require 'bundler/setup'
 require 'test/unit'
 require 'test/unit/rr'
 
+# Embulk 0.10.x introduced new bootstrap mechanism.
+# https://github.com/embulk/embulk/blob/641f35fec064cca7b1a7314d634a4b64ef8637f1/embulk-ruby/test/vanilla/run-test.rb#L8-L13
+static_initializer = Java::org.embulk.EmbulkDependencyClassLoader.staticInitializer().useSelfContainedJarFiles()
+static_initializer.java_send :initialize
+
+require 'embulk/java/bootstrap'
 require 'embulk'
-begin
-  # Embulk ~> 0.8.x
-  Embulk.setup
-rescue NotImplementedError, NoMethodError, NameError
-  # Embulk ~> 0.9.x
-  require 'embulk/java/bootstrap'
-end
+
 Embulk.logger = Embulk::Logger.new('/dev/null')
 
 APP_ROOT = File.expand_path('../', __dir__)

data/test/test_helper.rb

@@ -68,7 +68,7 @@ module Embulk
           ])
           task = {
             'column_options' => [
-              {'name' => 'boolean',   'type' => 'STRING', 'mode' => 'REQUIRED'},
+              {'name' => 'boolean',   'type' => 'STRING', 'mode' => 'REQUIRED', 'description' => 'hoge'},
               {'name' => 'long',      'type' => 'STRING'},
               {'name' => 'double',    'type' => 'STRING'},
               {'name' => 'string',    'type' => 'INTEGER'},
@@ -81,7 +81,7 @@ module Embulk
             ],
           }
           expected = [
-            {name: 'boolean',   type: 'STRING', mode: 'REQUIRED'},
+            {name: 'boolean', type: 'STRING', mode: 'REQUIRED', description: 'hoge'},
             {name: 'long',      type: 'STRING'},
             {name: 'double',    type: 'STRING'},
             {name: 'string',    type: 'INTEGER'},

data/test/test_transaction.rb

@@ -109,7 +109,7 @@ module Embulk
           task = Bigquery.configure(config, schema, processor_count)
           any_instance_of(BigqueryClient) do |obj|
             mock(obj).get_dataset(config['dataset'])
-            mock(obj).create_table_if_not_exists(config['temp_table'])
+            mock(obj).create_table_if_not_exists(config['temp_table'], options: {"expiration_time"=>nil})
             mock(obj).create_table_if_not_exists(config['table'])
             mock(obj).copy(config['temp_table'], config['table'], write_disposition: 'WRITE_TRUNCATE')
             mock(obj).delete_table(config['temp_table'])
@@ -122,7 +122,7 @@ module Embulk
           task = Bigquery.configure(config, schema, processor_count)
           any_instance_of(BigqueryClient) do |obj|
             mock(obj).get_dataset(config['dataset'])
-            mock(obj).create_table_if_not_exists(config['temp_table'])
+            mock(obj).create_table_if_not_exists(config['temp_table'], options: {"expiration_time"=>nil})
             mock(obj).create_table_if_not_exists(config['table'])
             mock(obj).copy(config['temp_table'], config['table'], write_disposition: 'WRITE_TRUNCATE')
             mock(obj).delete_table(config['temp_table'])
@@ -138,7 +138,7 @@ module Embulk
           any_instance_of(BigqueryClient) do |obj|
             mock(obj).get_dataset(config['dataset'])
             mock(obj).get_dataset(config['dataset_old'])
-            mock(obj).create_table_if_not_exists(config['temp_table'])
+            mock(obj).create_table_if_not_exists(config['temp_table'], options: {"expiration_time"=>nil})
             mock(obj).create_table_if_not_exists(config['table'])
             mock(obj).create_table_if_not_exists(config['table_old'], dataset: config['dataset_old'])
 
@@ -158,7 +158,7 @@ module Embulk
             mock(obj).create_dataset(config['dataset'])
             mock(obj).create_dataset(config['dataset_old'], reference: config['dataset'])
             mock(obj).create_table_if_not_exists(config['table'])
-            mock(obj).create_table_if_not_exists(config['temp_table'])
+            mock(obj).create_table_if_not_exists(config['temp_table'], options: {"expiration_time"=>nil})
             mock(obj).create_table_if_not_exists(config['table_old'], dataset: config['dataset_old'])
 
             mock(obj).get_table_or_partition(config['table'])
@@ -176,7 +176,7 @@ module Embulk
           any_instance_of(BigqueryClient) do |obj|
             mock(obj).get_dataset(config['dataset'])
             mock(obj).get_dataset(config['dataset_old'])
-            mock(obj).create_table_if_not_exists(config['temp_table'])
+            mock(obj).create_table_if_not_exists(config['temp_table'], options: {"expiration_time"=>nil})
             mock(obj).create_table_if_not_exists(config['table'])
             mock(obj).create_table_if_not_exists(config['table_old'], dataset: config['dataset_old'])
 
@@ -196,7 +196,7 @@ module Embulk
           task = Bigquery.configure(config, schema, processor_count)
           any_instance_of(BigqueryClient) do |obj|
             mock(obj).get_dataset(config['dataset'])
-            mock(obj).create_table_if_not_exists(config['temp_table'])
+            mock(obj).create_table_if_not_exists(config['temp_table'], options: {"expiration_time"=>nil})
             mock(obj).create_table_if_not_exists(config['table'])
             mock(obj).copy(config['temp_table'], config['table'], write_disposition: 'WRITE_APPEND')
             mock(obj).delete_table(config['temp_table'])
@@ -209,7 +209,7 @@ module Embulk
           task = Bigquery.configure(config, schema, processor_count)
           any_instance_of(BigqueryClient) do |obj|
             mock(obj).get_dataset(config['dataset'])
-            mock(obj).create_table_if_not_exists(config['temp_table'])
+            mock(obj).create_table_if_not_exists(config['temp_table'], options: {"expiration_time"=>nil})
             mock(obj).create_table_if_not_exists(config['table'])
             mock(obj).copy(config['temp_table'], config['table'], write_disposition: 'WRITE_APPEND')
             mock(obj).delete_table(config['temp_table'])

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: embulk-output-bigquery
 version: !ruby/object:Gem::Version
-  version: 0.6.9
+  version: 0.7.1
 platform: ruby
 authors:
 - Satoshi Akama
@@ -9,42 +9,36 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-03-17 00:00:00.000000000 Z
+date: 2024-03-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: signet
+  name: google-apis-storage_v1
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.7'
-    - - "<"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.12.0
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.7'
-    - - "<"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.12.0
+        version: '0'
 - !ruby/object:Gem::Dependency
-  name: google-api-client
+  name: google-apis-bigquery_v2
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "<"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.33.0
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "<"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.33.0
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: time_with_zone
   requirement: !ruby/object:Gem::Requirement
@@ -60,39 +54,33 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: representable
+  name: thwait
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 3.0.0
-    - - "<"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.1'
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 3.0.0
-    - - "<"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.1'
+        version: '0'
 - !ruby/object:Gem::Dependency
-  name: faraday
+  name: activesupport
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - "<"
       - !ruby/object:Gem::Version
-        version: '0.12'
+        version: '7.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - "<"
       - !ruby/object:Gem::Version
-        version: '0.12'
+        version: '7.0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -129,6 +117,8 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/check.yml"
+- ".github/workflows/publish.yml"
 - ".gitignore"
 - ".travis.yml"
 - CHANGELOG.md
@@ -172,7 +162,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
+rubygems_version: 3.5.3
 signing_key: 
 specification_version: 4
 summary: Google BigQuery output plugin for Embulk