mashr/templates/mashrTemplates/rand_config.yml

Simple data pipeline framework for GCP's BigQuery

# Template for random input. Change the required fields.
mashr:
  service_account_email: ''
  # the keyfile must be in current working directory
  json_keyfile: ''
  table_id:     ''
  dataset_id:   ''
  project_id:   ''
  # name the integration for bucket, instance and function name.
  # integration_name must match regex (?:[a-z](?:[-a-z0-9]{0,61}[a-z0-9])?)
  integration_name: ''
  # you can set the command that runs embulk here.
  # embulk_config.yml is the required name of the config file generated for embulk:
  embulk_run_command: 'embulk run embulk_config.yml' # 'embulk run embulk_config.yml -c embulk_diff.yml'
  embulk_gems:
    - embulk-input-random
embulk: # read about embulk here: https://github.com/embulk/embulk
  exec:
    min_output_tasks: 1
  in:
    type: random
    rows: 10
    threads: 1
    schema:
      myid: primary_key
      name: string
      score: integer