---
# see https://docs.datahub.com/docs/generated/ingestion/sources/bigquery for complete documentation
source:
  type: "bigquery"
  config:
    ## Coordinates
    project_id: project-id-1234567
    ## Credentials
    ## If GOOGLE_APPLICATION_CREDENTIALS environment variable is not set you can specify credentials here
    #credential:
    #  project_id: project-id-1234567
    #  private_key_id: "d0121d0000882411234e11166c6aaa23ed5d74e0"
    #  private_key: "-----BEGIN PRIVATE KEY-----\nMIIyourkey\n-----END PRIVATE KEY-----\n"
    #  client_email: "test@suppproject-id-1234567.iam.gserviceaccount.com"
    #  client_id: "123456678890"
    #include_tables: true
    #include_views: true
    #include_table_lineage: true
    #extract_policy_tags_from_catalog: true
    #start_time: 2021-12-15T20:08:23.091Z
    #end_time: 2023-12-15T20:08:23.091Z
    #profiling:
    #  enabled: true
    #  turn_off_expensive_profiling_metrics: false
    #  query_combiner_enabled: true
    #  max_number_of_fields_to_profile: 8
    #  profile_table_level_only: false
    #  include_field_null_count: true
    #  include_field_min_value: true
    #  include_field_max_value: true
    #  include_field_mean_value: true
    #  include_field_median_value: true
    #  include_field_stddev_value: false
    #  include_field_quantiles: false
    #  include_field_distinct_value_frequencies: false
    #  include_field_histogram: false
    #  include_field_sample_values: false
    #profile_pattern:
    #  allow:
    #  - "schema.table.column"
    #  deny:
    #  - "*.*.*"
    #storage_project_id: project-id-1234567
    ## Lineage with GCS Source
    # include_column_lineage_with_gcs: true/false
    # gcs_lineage_config:
    #   path_specs:
    #     - include: "gs://my-bucket/foo/tests/bar.avro"
    #     - include: "gs://my-bucket/foo/tests/*.*"
    #     - include: "gs://my-bucket/foo/tests/{table}/*.avro"
    #     - include: "gs://my-bucket/foo/tests/{table}/*/*.avro"
    #     - include: "gs://my-bucket/foo/tests/{table}/*.*"
    #     - include: "gs://my-bucket/{dept}/tests/{table}/*.avro"
    #     - include: "gs://my-bucket/{dept}/tests/{table}/{partition_key[0]}={partition[0]}/{partition_key[1]}={partition[1]}/*.avro"
    #     - include: "gs://my-bucket/{dept}/tests/{table}/{partition[0]}/{partition[1]}/{partition[2]}/*.avro"
    #     - include: "gs://my-bucket/{dept}/tests/{table}/{partition[0]}/{partition[1]}/{partition[2]}/*.*"
    #     - include: "gs://my-bucket/*/{table}/{partition[0]}/{partition[1]}/{partition[2]}/*.*"
    #     - include: "gs://my-bucket/*/*/{table}/{partition[0]}/{partition[1]}/{partition[2]}/*.*"
    # strip_urls: false


## see https://docs.datahub.com/docs/metadata-ingestion/sink_docs/datahub for complete documentation
sink:
  type: "datahub-rest"
  config:
    server: "http://localhost:8080"