Files
merica-pipelines/configs/ingestion_db_environmental_permits_cdc.yaml
T

38 lines
901 B
YAML

pipeline_id: ingestion_db_environmental_permits_cdc
description: "CDC Ingestion for Environmental Permits (Perizinan Lingkungan) Postgres DB -> Bronze -> dbt Silver -> dbt Gold"
schedule: "0 */2 * * *"
owner: de_team_dlh
tags:
- dlh
- cdc
- permits
mode: medallion
bronze:
source_type: database
connection_id: conn_postgres_source_db
table_name: public.environmental_permits
target:
bucket: dlh-bronze
format: parquet
silver:
engine: duckdb
quality_check:
expectation_suite: permits_bronze_suite
transformation:
engine: duckdb
source_parquet_path: s3://dlh-bronze/environmental_permits.parquet
target_table: dlh_lakehouse.silver.environmental_permits
primary_keys:
- id
- updated_at
select_models: silver_environmental_permits_clean
gold:
engine: dbt
transformation:
engine: dbt
select_models: gold_permits_summary_daily