dataset: datasource/database/schema/platform_automation variables: CONTRACT_NAME: default: "datahem_platform_automation" DOMAIN_SQUAD: default: "Data Engineering Team" ORIGIN_SERVICE_REPO: default: "https://github.com/mathem/origin-service" BUSINESS_DESCRIPTION: default: "Handles data lifecycle automation and transformation for real-time data ingestion and processing." SCHEMA_VERSION: default: "1.0" checks: - schema: allow_extra_columns: false allow_other_column_order: false - row_count: threshold: must_be_greater_than: 0 - freshness: column: processed_at threshold: unit: hour must_be_less_than: 12 columns: - name: contract_name data_type: string checks: - missing: - duplicate: - invalid: name: "Contract Name length guardrail" valid_min_length: 1 valid_max_length: 128 - name: domain_squad data_type: string checks: - missing: - invalid: name: "Domain Squad name guardrail" valid_min_length: 1 valid_max_length: 64 - name: origin_service_repo data_type: string checks: - missing: - invalid: name: "Origin Service Repo URL" valid_min_length: 5 valid_max_length: 255 - name: business_description data_type: string checks: - missing: - invalid: name: "Business Description length guardrail" valid_min_length: 10 valid_max_length: 255 - name: schema_version data_type: string checks: - missing: - invalid: name: "Schema Version format" valid_format: name: Version pattern regex: '^[0-9]+\.[0-9]+$' - name: source_type data_type: string checks: - missing: - invalid: name: "Valid Source Type" valid_values: - cdc - event - file - api_pull - db_query - name: source_ref data_type: string checks: - missing: - invalid: name: "Source Reference length guardrail" valid_min_length: 1 valid_max_length: 128 - name: ingest_mode data_type: string checks: - missing: - invalid: name: "Valid Ingest Mode" valid_values: - streaming - microbatch - name: bq_project_layer data_type: string checks: - missing: - invalid: name: "Valid BQ Project Layer" valid_values: - bronze - silver - gold - experimental - name: bq_dataset data_type: string checks: - missing: - invalid: name: "BQ Dataset name guardrail" valid_min_length: 1 valid_max_length: 64 - name: bq_table data_type: string checks: - missing: - invalid: name: "BQ Table name guardrail" valid_min_length: 1 valid_max_length: 128