name: Download from GCS
inputs:
- {name: GCS path, type: URI}
outputs:
- {name: Data}
implementation:
    container:
        image: google/cloud-sdk
        command:
        - bash # Pattern comparison only works in Bash
        - -ex
        - -c
        - |
            if [ -n "${GOOGLE_APPLICATION_CREDENTIALS}" ]; then
                gcloud auth activate-service-account --key-file="${GOOGLE_APPLICATION_CREDENTIALS}"
            fi

            uri="$0"
            output_path="$1"

            # Checking whether the URI points to a single blob, a directory or a URI pattern
            # URI points to a blob when that URI does not end with slash and listing that URI only yields the same URI
            if [[ "$uri" != */ ]] && (gsutil ls "$uri" | grep --fixed-strings --line-regexp "$uri"); then
                mkdir -p "$(dirname "$output_path")"
                gsutil -m cp -r "$uri" "$output_path"
            else
                mkdir -p "$output_path" # When source path is a directory, gsutil requires the destination to also be a directory
                gsutil -m rsync -r "$uri" "$output_path" # gsutil cp has different path handling than Linux cp. It always puts the source directory (name) inside the destination directory. gsutil rsync does not have that problem.
            fi
        - inputValue: GCS path
        - outputPath: Data