rabbit-slide-abetomo-apache-arrow-meetup-in-tokyo-2025-spring 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 512ebe3a058cf615117be3f7e2f651d72febb5b1d8cfdbd46e1b6753280d4457
+  data.tar.gz: feb12fb97436878f41c07cabc0aee4916bf78237f0326f4bb37890371637d081
+SHA512:
+  metadata.gz: f1b4116c585c49437cb250c2e998553f01324030be4a4474d195e3fc6a78e033aed1c9360d0e7b4a152da7c712c36f2762ff6281a8f0fac2cd8358922d9bab6a
+  data.tar.gz: 9410083634d8318dca1d80698a34a6e0859e3f7dfe8616284089a176800b72c7dbceb1c3d9e370c5e3095e40dffc763ab65a47f4e72329459cb8495ae9a754b3

data/.rabbit

@@ -0,0 +1,2 @@
+--size 800,600
+groonga-and-apache-arrow.md

data/README.md

@@ -0,0 +1,24 @@
+# Groonga and Apache Arrow
+
+https://red-data-tools.connpass.com/event/349680/
+
+## For author
+
+### Show
+
+    rake
+
+### Publish
+
+    rake publish
+
+## For viewers
+
+### Install
+
+    gem install rabbit-slide-abetomo-apache-arrow-meetup-in-tokyo-2025-spring
+
+### Show
+
+    rabbit rabbit-slide-abetomo-apache-arrow-meetup-in-tokyo-2025-spring.gem
+

data/Rakefile

@@ -0,0 +1,17 @@
+require "rabbit/task/slide"
+
+# Edit ./config.yaml to customize meta data
+
+spec = nil
+Rabbit::Task::Slide.new do |task|
+  spec = task.spec
+  # spec.files += Dir.glob("doc/**/*.*")
+  # spec.files -= Dir.glob("private/**/*.*")
+  # spec.add_runtime_dependency("rabbit-theme-YOUR-THEME")
+end
+
+desc "Tag #{spec.version}"
+task :tag do
+  sh("git", "tag", "-a", spec.version.to_s, "-m", "Publish #{spec.version}")
+  sh("git", "push", "--tags")
+end

data/config.yaml

@@ -0,0 +1,23 @@
+---
+id: apache-arrow-meetup-in-tokyo-2025-spring
+base_name: groonga-and-apache-arrow
+tags: []
+presentation_date: 
+presentation_start_time: 
+presentation_end_time: 
+version: 1.0.0
+licenses: []
+slideshare_id: 
+speaker_deck_id: 
+vimeo_id: 
+youtube_id: 
+width: 800
+height: 600
+source_code_uri: 
+author:
+  markup_language: :markdown
+  name: Abe Tomoaki
+  email: abe@clear-code.com
+  rubygems_user: abetomo
+  slideshare_user: 
+  speaker_deck_user: 

data/groonga-and-apache-arrow.md

@@ -0,0 +1,104 @@
+# Groonga and Apache Arrow
+
+author
+:   Abe Tomoaki
+
+institution
+:   ClearCode Inc.
+
+theme
+:   clear-code
+
+# GroongaはApache Arrowフォーマットで入出力できるよ！
+
+# Groongaとは？
+
+* オープンソースのカラムストア機能付き全文検索エンジン
+* 即時更新
+* 参照ロックフリー
+* 集計もできる
+
+# 例で紹介Groonga: 検索
+
+```js
+// SQLで書くとこういう感じ
+// select _key, introduction
+// from Users
+// where introduction &@ 'engine'
+query = new URLSearchParams({
+  table: 'Users',
+  output_columns: '_key,introduction',
+  match_columns: 'introduction',
+  query: 'engine', // 「engine」で全文検索
+  // output_type: 'apache-arrow', このパラメータを付与するとApache Arrowフォーマットになる
+  command_version: 3
+});
+response = await fetch(`http://localhost:10041/d/select?${query}`);
+(await response.json()).body.drilldowns.department.records
+// [
+//   [ "Groonga", "Groonga is an open-source fulltext search engine and column store." ],
+//   [ "Mroonga", "A MySQL pluggable storage engine based on Groonga." ]
+// ]
+```
+
+# 例で紹介Groonga: 集計
+
+```js
+// SQLで書くとこういう感じ
+// select department, avg(age)
+// from Users
+// group by department
+
+// drilldownというので集計できる
+query = new URLSearchParams({
+  table: 'Users',
+  output_columns: '_id',
+  drilldown: 'department',
+  drilldown_calc_types: 'AVG',
+  drilldown_calc_target: 'age',
+  drilldown_output_columns: '_key,_avg',
+  command_version: 3
+});
+response = await fetch(`http://localhost:10041/d/select?${query}`);
+(await response.json()).body.drilldowns.department.records
+// [
+//   [ "A", 37 ],
+//   [ "B", 15.5 ]
+// ]
+```
+
+# 事例紹介
+
+# 活用事例1: Groonga delta
+
+* MySQL/MariaDBのデータをリアルタイムでGroongaに同期するツール
+* 差分情報をApache Parquet形式で保存
+  * Groongaへの取り込みを高速に行える
+
+# Groonga delta補足
+
+* MySQL/MariaDBのbinlog（差分情報）を一度ストレージに書き出す
+  * これにより途中で失敗してもやり直しがしやすい
+  * この書き出すフォーマットがApache Parquet形式
+
+# 活用事例2: ログ収集製品
+
+* 某ログ収集製品でGroongaが利用されている
+* データのやり取りにApache Arrowフォーマットを使うことで高速化できた
+
+# まとめ
+
+* GroongaはApache Arrowフォーマットで入出力できるよ！
+* Groongaは全文検索も集計もできるよ！
+
+# 宣伝
+
+何かとApache Parquet形式でデータを保存する時代なので、Groongaでデータ分析の前処理とかしてみるといいよ！
+
+# 参考
+
+* Groonga
+  * https://groonga.org/
+* Groonga delta
+  * https://github.com/groonga/groonga-delta
+  * https://www.clear-code.com/blog/2022/5/20/groonga-delta.html

metadata

@@ -0,0 +1,62 @@
+--- !ruby/object:Gem::Specification
+name: rabbit-slide-abetomo-apache-arrow-meetup-in-tokyo-2025-spring
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Abe Tomoaki
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2025-04-11 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rabbit
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.0.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.0.2
+description: https://red-data-tools.connpass.com/event/349680/
+email:
+- abe@clear-code.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rabbit"
+- README.md
+- Rakefile
+- config.yaml
+- groonga-and-apache-arrow.md
+- pdf/apache-arrow-meetup-in-tokyo-2025-spring-groonga-and-apache-arrow.pdf
+homepage: https://slide.rabbit-shocker.org/authors/abetomo/apache-arrow-meetup-in-tokyo-2025-spring/
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.5
+signing_key: 
+specification_version: 4
+summary: Groonga and Apache Arrow
+test_files: []