Files
merica-pipelines/metadata/e2e_modernized_ingestion_flow.json

387 lines
12 KiB
JSON

{
"id": "e2e_modernized_ingestion_flow",
"description": "Dynamic Data Lakehouse Pipeline via DLH Studio",
"schedule": "0 */1 * * *",
"owner_id": "local-admin",
"owner_name": "Administrator Lokal (Break-Glass)",
"nodes": [
{
"id": "node-5630",
"type": "customNode",
"position": {
"x": 80,
"y": 80
},
"data": {
"label": "Source Database (Environmental Permits)",
"type": "source_db",
"subtitle": "Postgres / MySQL / Oracle",
"isSource": true,
"configured": true,
"config": {
"conn": "Postgres",
"conn_id": "conn_postgres_source_db",
"table": "public.environmental_permits",
"table_name": "public.environmental_permits",
"target_type": "minio_s3",
"watermark_column": "updated_at",
"ingestion_mode": "incremental_watermark"
}
},
"width": 96,
"height": 96,
"selected": false,
"dragging": false
},
{
"id": "node-6855",
"type": "customNode",
"position": {
"x": 270,
"y": 80
},
"data": {
"label": "Source GWS (Waste Reports)",
"type": "source_gws",
"subtitle": "Sheets & Drive PDF",
"isSource": true,
"configured": true,
"config": {
"url": "gws_sheet_1OSRugXZvfjoY9M0yySKT_sampah_2026",
"spreadsheet_id": "gws_sheet_1OSRugXZvfjoY9M0yySKT_sampah_2026",
"sheet_range": "Sheet1",
"sheet_name": "Sheet1",
"folder_id": "1OSRugXZvfjoY9M0yySKT",
"drive_folder_id": "1OSRugXZvfjoY9M0yySKT",
"selected_filename": "Laporan_Sampah_Kabupaten_2026.xlsx",
"header_row": 2
}
},
"width": 96,
"height": 96,
"selected": false,
"dragging": false
},
{
"id": "node-8156",
"type": "customNode",
"position": {
"x": 460,
"y": 80
},
"data": {
"label": "Source REST API dlt (Sensor SPKU)",
"type": "source_api_dlt",
"subtitle": "Auto Un-nesting & Pagination",
"isSource": true,
"configured": true,
"config": {
"endpoint_url": "https://api.spku.dlh.id/v1/telemetry",
"http_method": "GET",
"auth_type": "none",
"auth_token": "",
"pagination_strategy": "page_number",
"page_param": "page",
"limit_param": "limit",
"page_size": 100,
"cursor_column": "measured_at",
"lookback_hours": 3,
"unnest_mode": "auto_flatten",
"landing_bucket": "dlh-landing",
"landing_prefix": "api/spku_hourly/",
"bronze_table": "bronze_spku_telemetry",
"url": "https://api.spku.dlh.id/v1/telemetry"
}
},
"width": 96,
"height": 96,
"selected": false,
"dragging": false
},
{
"id": "node-9404",
"type": "customNode",
"position": {
"x": 650,
"y": 80
},
"data": {
"label": "DuckDB Bronze Ingestion & Dedup",
"type": "duckdb_transform",
"subtitle": "In-process SQL (<512MB)",
"configured": true,
"config": {
"layer": "silver",
"source_parquet_path": "s3://dlh-bronze/staging/environmental_permits/*.parquet",
"source_path": "s3://dlh-bronze/staging/environmental_permits/*.parquet",
"target_table": "bronze_environmental_permits",
"table_name": "bronze_environmental_permits",
"primary_keys": "permit_id",
"query": "SELECT permit_id, permit_number, company_name, activity_type AS permit_type, status, issued_date, updated_at FROM read_parquet('s3://dlh-bronze/staging/environmental_permits/*.parquet') QUALIFY ROW_NUMBER() OVER (PARTITION BY permit_id ORDER BY updated_at DESC) = 1",
"sql_query": "SELECT permit_id, permit_number, company_name, activity_type AS permit_type, status, issued_date, updated_at FROM read_parquet('s3://dlh-bronze/staging/environmental_permits/*.parquet') QUALIFY ROW_NUMBER() OVER (PARTITION BY permit_id ORDER BY updated_at DESC) = 1",
"transformation_sql": "SELECT permit_id, permit_number, company_name, activity_type AS permit_type, status, issued_date, updated_at FROM read_parquet('s3://dlh-bronze/staging/environmental_permits/*.parquet') QUALIFY ROW_NUMBER() OVER (PARTITION BY permit_id ORDER BY updated_at DESC) = 1"
}
},
"width": 96,
"height": 96,
"selected": false,
"dragging": false
},
{
"id": "node-0708",
"type": "customNode",
"position": {
"x": 840,
"y": 80
},
"data": {
"label": "dbt Silver Cleansed Permits Enriched",
"type": "dbt_transform",
"subtitle": "dbt-postgres",
"configured": true,
"config": {
"dbt_layer": "silver",
"dbt_model": "silver_permits_enriched",
"sel": "silver_permits_enriched",
"tgt": "postgres",
"trino_catalog": "iceberg",
"sql_query_preview": "-- dbt Silver Cleansed Environmental Permits\nSELECT \n permit_id,\n permit_number,\n company_name,\n permit_type,\n status,\n issued_date,\n updated_at,\n CURRENT_TIMESTAMP AS dbt_validated_at\nFROM {{ ref('bronze_environmental_permits') }}\nWHERE status != 'REVISED'",
"query": "-- dbt Silver Cleansed Environmental Permits\nSELECT \n permit_id,\n permit_number,\n company_name,\n permit_type,\n status,\n issued_date,\n updated_at,\n CURRENT_TIMESTAMP AS dbt_validated_at\nFROM {{ ref('bronze_environmental_permits') }}\nWHERE status != 'REVISED'",
"test_configs": {
"unique_columns": [
"permit_id",
"permit_number"
],
"not_null_columns": [
"permit_id",
"status",
"updated_at"
],
"accepted_values": {},
"enforce_contract": true
},
"unique_columns": [
"permit_id",
"permit_number"
],
"not_null_columns": [
"permit_id",
"status",
"updated_at"
],
"enforce_contract": true,
"use_cosmos": true,
"transformation_engine": "cosmos"
}
},
"width": 96,
"height": 96,
"selected": false,
"dragging": false
},
{
"id": "node-2234",
"type": "customNode",
"position": {
"x": 1030,
"y": 80
},
"data": {
"label": "GE Silver Compliance Quality Gate",
"type": "ge_quality",
"subtitle": "Great Expectations",
"configured": true,
"config": {
"ge_scope_level": "table",
"ge_table_name": "silver_permits_enriched",
"test_table_row_count": true,
"test_table_schema_match": true,
"test_table_table_not_empty": true,
"table_min_rows": 1,
"table_max_rows": 1000000,
"ge_col_table": "stasiun_spku",
"ge_target_column": "stasiun_id",
"ge_column_test_type": "not_null",
"sql_assertion": "",
"sql": "",
"expected": 0,
"error_message": "Unexpected rows detected in table",
"suite": "bronze",
"fail": "Stop DAG"
}
},
"width": 96,
"height": 96,
"selected": false,
"dragging": false
},
{
"id": "node-3694",
"type": "customNode",
"position": {
"x": 1220,
"y": 80
},
"data": {
"label": "dbt Gold Regulatory Compliance Mart",
"type": "dbt_transform",
"subtitle": "dbt-postgres",
"configured": true,
"config": {
"dbt_layer": "gold",
"dbt_model": "gold_compliance_summary_mart",
"sel": "gold_compliance_summary_mart",
"tgt": "postgres",
"trino_catalog": "iceberg",
"sql_query_preview": "-- dbt Gold Regulatory Compliance Mart\nSELECT \n permit_type,\n status,\n COUNT(permit_id) AS total_permits,\n COUNT(DISTINCT company_name) AS unique_companies,\n CURRENT_TIMESTAMP AS mart_refreshed_at\nFROM {{ ref('silver_permits_enriched') }}\nGROUP BY permit_type, status",
"query": "-- dbt Gold Regulatory Compliance Mart\nSELECT \n permit_type,\n status,\n COUNT(permit_id) AS total_permits,\n COUNT(DISTINCT company_name) AS unique_companies,\n CURRENT_TIMESTAMP AS mart_refreshed_at\nFROM {{ ref('silver_permits_enriched') }}\nGROUP BY permit_type, status",
"test_configs": {
"unique_columns": [],
"not_null_columns": [
"permit_type",
"status"
],
"accepted_values": {},
"enforce_contract": false
},
"unique_columns": [],
"not_null_columns": [
"permit_type",
"status"
],
"use_cosmos": true,
"transformation_engine": "cosmos"
}
},
"width": 96,
"height": 96,
"selected": false,
"dragging": false
},
{
"id": "node-4977",
"type": "customNode",
"position": {
"x": 1410,
"y": 80
},
"data": {
"label": "SITOMAT Governance Callback",
"type": "sitomat_callback",
"subtitle": "Status callback",
"configured": true,
"config": {
"layer": "gold",
"artifact_ref": "lakehouse.gold.gold_compliance_summary_mart",
"checksum": "sha256-verified-modernized-ingestion",
"sitomat_base_url": "http://localhost:3000",
"openmetadata_fqn": "dlh_airflow_service.pipeline.task",
"ge_status": "PASSED",
"url": "/sitomat/callback",
"stage": "bronze"
}
},
"width": 96,
"height": 96,
"selected": true,
"dragging": false
}
],
"edges": [
{
"source": "node-5630",
"sourceHandle": null,
"target": "node-9404",
"targetHandle": null,
"type": "removableEdge",
"style": {
"stroke": "var(--muted)",
"strokeWidth": 2
},
"data": {},
"id": "reactflow__edge-node-5630-node-9404"
},
{
"source": "node-6855",
"sourceHandle": null,
"target": "node-9404",
"targetHandle": null,
"type": "removableEdge",
"style": {
"stroke": "var(--muted)",
"strokeWidth": 2
},
"data": {},
"id": "reactflow__edge-node-6855-node-9404"
},
{
"source": "node-8156",
"sourceHandle": null,
"target": "node-9404",
"targetHandle": null,
"type": "removableEdge",
"style": {
"stroke": "var(--muted)",
"strokeWidth": 2
},
"data": {},
"id": "reactflow__edge-node-8156-node-9404"
},
{
"source": "node-9404",
"sourceHandle": null,
"target": "node-0708",
"targetHandle": null,
"type": "removableEdge",
"style": {
"stroke": "var(--muted)",
"strokeWidth": 2
},
"data": {},
"id": "reactflow__edge-node-9404-node-0708"
},
{
"source": "node-0708",
"sourceHandle": null,
"target": "node-2234",
"targetHandle": null,
"type": "removableEdge",
"style": {
"stroke": "var(--muted)",
"strokeWidth": 2
},
"data": {},
"id": "reactflow__edge-node-0708-node-2234"
},
{
"source": "node-2234",
"sourceHandle": null,
"target": "node-3694",
"targetHandle": null,
"type": "removableEdge",
"style": {
"stroke": "var(--muted)",
"strokeWidth": 2
},
"data": {},
"id": "reactflow__edge-node-2234-node-3694"
},
{
"source": "node-3694",
"sourceHandle": null,
"target": "node-4977",
"targetHandle": null,
"type": "removableEdge",
"style": {
"stroke": "var(--muted)",
"strokeWidth": 2
},
"data": {},
"id": "reactflow__edge-node-3694-node-4977"
}
],
"notes": [],
"is_draft": false,
"status": "deployed",
"updated_at": "2026-10-21T08:59:34.908289Z"
}