Generate TPC-H Dataset #17

	---
	name: Generate TPC-H Dataset

	on:
	workflow_dispatch:
	inputs:
	scale-factor:
	description: 'TPC-H Scale Factor (e.g., 0.01, 0.1, 1.0)'
	required: true
	default: '0.01'
	type: string
	bucket-name:
	description: 'S3 Bucket Name'
	required: true
	default: 'xtdb-play-datasets'
	type: string

	env:
	AWS_REGION: eu-west-1

	jobs:
	generate-dataset:
	runs-on: ubuntu-latest
	if: github.repository == 'xtdb/play'
	permissions:
	contents: read
	steps:
	- name: Checkout repository
	uses: actions/checkout@v4

	- name: Configure AWS credentials
	uses: aws-actions/configure-aws-credentials@v1
	with:
	aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
	aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
	aws-region: ${{ env.AWS_REGION }}

	- name: Prepare java
	uses: actions/setup-java@v4.2.1
	with:
	distribution: 'temurin'
	java-version: '21'

	- name: Setup Clojure
	uses: DeLaGuardo/setup-clojure@12.5
	with:
	cli: 1.11.3.1463

	- name: Cache clojure dependencies
	uses: actions/cache@v3
	with:
	path: \|
	~/.m2/repository
	~/.gitlibs
	~/.deps.clj
	key: cljdeps-tpch-${{ hashFiles('deps.edn') }}
	restore-keys: cljdeps-

	- name: Generate TPC-H Dataset
	run: \|
	echo "Generating TPC-H dataset with scale factor ${{ inputs.scale-factor }}"
	clojure -M:generate-tpch ${{ inputs.bucket-name }} ${{ inputs.scale-factor }} ${{ env.AWS_REGION }}

	- name: Verify upload
	run: \|
	echo "Verifying dataset was uploaded to S3..."
	aws s3 ls s3://${{ inputs.bucket-name }}/tpch-sf${{ inputs.scale-factor }}/ --recursive --human-readable --summarize

Provide feedback