Files
merica-pipelines/configs/ingestion_gws_waste_reports.yaml
T

37 lines
880 B
YAML
Raw Normal View History

pipeline_id: ingestion_gws_waste_reports
description: "Google Workspace Spreadsheet Extractor for Waste Reports -> Pandas Cleansing -> Trino Iceberg Target -> dbt Gold Mart"
schedule: "0 4 * * *"
owner: de_team_dlh
tags:
- dlh
- gws
- waste
mode: medallion
bronze:
source_type: gws
connection_id: conn_gws_service_account
spreadsheet_id: "1OSRugXZvfjoY9M0yySKT-F3L4LTZXa40J0knU3_4Hik"
sheet_range: "Sheet1!A1:Z1000"
target:
bucket: dlh-bronze
format: csv
silver:
engine: pyiceberg
quality_check:
expectation_suite: waste_gws_suite
transformation:
engine: pyiceberg
source_parquet_path: s3://dlh-bronze/waste_reports.parquet
target_table: dlh_lakehouse.silver.waste_reports
write_mode: overwrite
select_models: stg_waste_reports
gold:
engine: dbt
transformation:
engine: dbt
select_models: fct_waste_daily_mart