# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

name: 'Preprocess Data using Spark - IBM Cloud'
description: |
  Preprocess data using IBM Cloud Spark Service
metadata:
  annotations: {platform: 'IBM Cloud Spark Service'}
inputs:
  - {name: bucket_name,       description: 'Required. Object storage bucket name'}
  - {name: data_url,          description: 'Required. URL of the data source'}
outputs:
  - {name: output,            description: 'Data Filename'}
implementation:
  container:
    image: docker.io/aipipeline/data_preprocess_spark:latest
    command: ['python']
    args: [
      -u, data_preprocess_spark.py,
      --bucket_name, {inputValue: bucket_name},
      --data_url, {inputValue: data_url},
      --output_filename_path, {outputPath: output}
    ]