datasets/cloud_datasets/pipelines/pdp_extract_tabular_metadata/pipeline.yaml

# Copyright 2022 Google LLC
#
# 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.

---
resources:
  - type: bigquery_table
    dataset_id: _cloud_datasets
    table_id: "tabular_datasets"
    description: "This table contains all the metadata for all the tabular datasets in the Cloud Datasets program"
    schema: |-
      [
        {
            "name": "extracted_at",
            "description": "The date and time when this row was extracted from BigQuery",
            "type": "TIMESTAMP"
        },
        {
            "name": "created_at",
            "description": "The date and time when the dataset was created",
            "type": "TIMESTAMP"
        },
        {
            "name": "modified_at",
            "description": "The date and time when the dataset was last modified",
            "type": "TIMESTAMP"
        },
        {
            "name": "project_id",
            "description": "The GCP project where the public dataset is stored",
            "type": "STRING"
        },
        {
            "name": "dataset_id",
            "description": "The BigQuery dataset ID",
            "type": "STRING"
        },
        {
            "name": "description",
            "description": "The dataset description",
            "type": "STRING"
        },
        {
            "name": "num_tables",
            "description": "Number of tables contained in this dataset",
            "type": "INTEGER"
        },
        {
            "name": "is_public",
            "description": "Whether or not the dataset is public to all users",
            "type": "BOOLEAN"
        }
      ]
  - type: bigquery_table
    dataset_id: _cloud_datasets
    table_id: "tables"
    description: "This table contains all the metadata for all the tables in the Cloud Datasets program"
    schema: |-
      [
        {
            "name": "extracted_at",
            "description": "The date and time when this row was extracted from BigQuery",
            "type": "TIMESTAMP"
        },
        {
            "name": "created_at",
            "description": "The date and time when the dataset was created",
            "type": "TIMESTAMP"
        },
        {
            "name": "modified_at",
            "description": "The date and time when the dataset was last modified",
            "type": "TIMESTAMP"
        },
        {
            "name": "project_id",
            "description": "The GCP project where the public dataset is stored",
            "type": "STRING"
        },
        {
            "name": "dataset_id",
            "description": "The BigQuery dataset ID",
            "type": "STRING"
        },
        {
            "name": "table_id",
            "description": "The BigQuery table ID",
            "type": "STRING"
        },
        {
            "name": "description",
            "description": "The dataset description",
            "type": "STRING"
        },
        {
            "name": "type",
            "description": "The type of the table",
            "type": "STRING"
        },
        {
            "name": "num_bytes",
            "description": "The number of bytes the table allocated on disk",
            "type": "INTEGER"
        },
        {
            "name": "num_rows",
            "description": "The number of rows in the table",
            "type": "INTEGER"
        },
        {
            "name": "num_columns",
            "description": "The number of columns in the table",
            "type": "INTEGER"
        },
        {
            "name": "described_columns",
            "description": "The number of columns in the table with a description",
            "type": "INTEGER"
        }
      ]
  - type: bigquery_table
    dataset_id: _cloud_datasets
    table_id: "tables_fields"
    description: "This table contains all the metadata for all the field in all the tables in the Cloud Datasets program"
    schema: |-
      [
        {
            "name": "extracted_at",
            "description": "The date and time when this row was extracted from BigQuery",
            "type": "TIMESTAMP"
        },
        {
            "name": "project_id",
            "description": "The GCP project where the public dataset is stored",
            "type": "STRING"
        },
        {
            "name": "dataset_id",
            "description": "The BigQuery dataset ID",
            "type": "STRING"
        },
        {
            "name": "table_id",
            "description": "The BigQuery table ID",
            "type": "STRING"
        },
        {
            "name": "name",
            "description": "The name of the field",
            "type": "STRING"
        },
        {
            "name": "description",
            "description": "The description for the field",
            "type": "STRING"
        },
        {
            "name": "field_type",
            "description": "The type of the field",
            "type": "STRING"
        },
        {
            "name": "mode",
            "description": "The mode of the field",
            "type": "STRING"
        },
        {
            "name": "precision",
            "description": "Precision for the NUMERIC field",
            "type": "INTEGER"
        },
        {
            "name": "scale",
            "description": "Scale for the NUMERIC field",
            "type": "INTEGER"
        },
        {
            "name": "max_length",
            "description": "Maximum length for the STRING or BYTES field",
            "type": "INTEGER"
        }
      ]

dag:
  airflow_version: 2
  initialize:
    dag_id: pdp_extract_tabular_metadata
    default_args:
      owner: "Google"
      depends_on_past: False
      start_date: '2022-08-20'
    max_active_runs: 1
    schedule_interval: "@daily"
    catchup: False
    default_view: graph

  tasks:
    - operator: "KubernetesPodOperator"
      description: "Extract the metadata for tabular datasets"
      args:
        task_id: "pdp_extract_tabular_metadata_task"
        name: "pdp_extract_tabular_metadata_task"
        namespace: "composer"
        service_account_name: "datasets"
        image_pull_policy: "Always"
        image: "{{ var.json.cloud_datasets.container_registry.pdp_extract_tabular_metadata_image }}"
        env_vars:
          SOURCE_PROJECTS_IDS: "{{ var.json.cloud_datasets.pdp_extract_tabular_metadata.source_projects_ids }}"
          TARGET_PROJECT_ID: "{{ var.value.gcp_project }}"
          TARGET_DATASET: "{{ var.json.cloud_datasets.pdp_extract_tabular_metadata.target_dataset }}"
          TABULAR_DATASET_TABLE_NAME: "{{ var.json.cloud_datasets.pdp_extract_tabular_metadata.tabular_dataset_table_name }}"
          TABLES_TABLE_NAME: "{{ var.json.cloud_datasets.pdp_extract_tabular_metadata.tables_table_name }}"
          TABLES_FIELDS_TABLE_NAME: "{{ var.json.cloud_datasets.pdp_extract_tabular_metadata.tables_fields_table_name }}"

        resources:
          request_memory: "128M"
          request_cpu: "200m"

  graph_paths:
    - "pdp_extract_tabular_metadata_task"