action.yml

name: Sync and cache an S3 bucket
author: Data Intuitive
description: >
  Sync an S3 bucket to a folder and create a cache.
inputs:
  s3_bucket:
    required: true
    description: 'Path to an S3 bucket.'
  dest_path:
    required: true
    description: 'Where to store the data.'
  cache_key_prefix:
    required: false
    description: A prefix for the cache hash key. Prefix is also used for restoring stale cache if no cache hit occurred for key.
    default: cachekey__
outputs:
  cache_key:
    description: Caching key.
    value: ${{ steps.cache_hash.outputs.cache_hash }}
runs:
  using: 'composite'
  steps:
    # create cache_hash key
    - name: Create hash key
      shell: bash
      id: cache_hash
      run: |
        hash=$(
          AWS_EC2_METADATA_DISABLED=true \
            aws s3 ls \
            ${{ inputs.s3_bucket }} \
            --recursive \
            --no-sign-request | \
            md5sum | \
            awk '{ print $1 }'
        )
        echo "cache_hash=${{ inputs.cache_key_prefix}}$hash" >> $GITHUB_OUTPUT
    
    # initialize cache
    - name: Cache resources
      uses: actions/cache@v4
      with:
        path: ${{ inputs.dest_path }}
        key: ${{ steps.cache_hash.outputs.cache_hash }}
        restore-keys: ${{ inputs.cache_key_prefix}}

    # sync if need be
    - name: Sync resources
      shell: bash
      run: |
        AWS_EC2_METADATA_DISABLED=true \
          aws s3 sync \
          ${{ inputs.s3_bucket }} \
          ${{ inputs.dest_path }} \
          --delete --no-sign-request
    - name: List resources
      shell: bash
      run: |
        tree ${{ inputs.dest_path }} -L 3