feat(pipeline): deploy e2e_cems_industrial_emissions_flow from MERICA Canvas UI

This commit is contained in:
2026-10-19 04:04:02 +07:00
parent 13835055b1
commit ab5ba1d7a7
4 changed files with 97 additions and 81 deletions
+42 -34
View File
@@ -8,7 +8,7 @@ governance:
tier: Tier.Tier1
certification: Certification.Gold
tasks:
- task_id: node-1975
- task_id: node-6716
type: source_db
label: Extract Master Emission Sources
enabled: true
@@ -19,12 +19,12 @@ tasks:
table: public.ref_emission_sources
table_name: public.ref_emission_sources
target_type: minio_s3
- task_id: node-3042
- task_id: node-7780
type: duckdb_transform
label: DuckDB Master to Bronze Iceberg
enabled: true
dependencies:
- node-1975
- node-6716
config:
layer: silver
source_parquet_path: s3://dlh-bronze/staging/ref_emission_sources/*.parquet
@@ -47,7 +47,7 @@ tasks:
region_zone, license_status, created_at FROM read_parquet('s3://dlh-bronze/staging/ref_emission_sources/*.parquet')
QUALIFY ROW_NUMBER() OVER (PARTITION BY source_id ORDER BY created_at DESC)
= 1
- task_id: node-4059
- task_id: node-8779
type: source_db
label: Extract Raw CEMS Telemetry
enabled: true
@@ -58,12 +58,12 @@ tasks:
table: public.raw_cems_telemetry_logs
table_name: public.raw_cems_telemetry_logs
target_type: minio_s3
- task_id: node-5075
- task_id: node-9796
type: ge_quality
label: GE Telemetry Staging Check
enabled: true
dependencies:
- node-4059
- node-8779
config:
ge_scope_level: all
ge_table_name: staging_cems_telemetry
@@ -75,43 +75,45 @@ tasks:
ge_col_table: stasiun_spku
ge_target_column: stasiun_id
ge_column_test_type: not_null
sql_assertion: ''
sql: ''
sql_assertion: SELECT count(*) FROM silver.table WHERE status NOT IN ('APPROVED',
'IN_REVIEW', 'REJECTED')
sql: SELECT count(*) FROM silver.table WHERE status NOT IN ('APPROVED', 'IN_REVIEW',
'REJECTED')
expected: 0
error_message: Unexpected rows detected in table
suite: bronze
fail: Stop DAG
- task_id: node-6110
- task_id: node-0811
type: duckdb_transform
label: DuckDB Telemetry to Bronze Iceberg
enabled: true
dependencies:
- node-5075
- node-9796
config:
layer: silver
source_parquet_path: s3://dlh-bronze/staging/raw_cems_telemetry/*.parquet
source_path: s3://dlh-bronze/staging/raw_cems_telemetry/*.parquet
source_parquet_path: s3://dlh-bronze/staging/raw_cems_telemetry_logs/*.parquet
source_path: s3://dlh-bronze/staging/raw_cems_telemetry_logs/*.parquet
target_table: bronze_cems_telemetry_logs
table_name: bronze_cems_telemetry_logs
primary_keys: log_id
query: SELECT log_id, source_id, telemetry_timestamp, so2_mg_nm3, nox_mg_nm3,
pm_dust_mg_nm3, co_mg_nm3, flue_gas_flow_m3_s, flue_temp_celsius, sensor_status,
created_at FROM read_parquet('s3://dlh-bronze/staging/raw_cems_telemetry/*.parquet')
created_at FROM read_parquet('s3://dlh-bronze/staging/raw_cems_telemetry_logs/*.parquet')
QUALIFY ROW_NUMBER() OVER (PARTITION BY log_id ORDER BY created_at DESC) = 1
sql_query: SELECT log_id, source_id, telemetry_timestamp, so2_mg_nm3, nox_mg_nm3,
pm_dust_mg_nm3, co_mg_nm3, flue_gas_flow_m3_s, flue_temp_celsius, sensor_status,
created_at FROM read_parquet('s3://dlh-bronze/staging/raw_cems_telemetry/*.parquet')
created_at FROM read_parquet('s3://dlh-bronze/staging/raw_cems_telemetry_logs/*.parquet')
QUALIFY ROW_NUMBER() OVER (PARTITION BY log_id ORDER BY created_at DESC) = 1
transformation_sql: SELECT log_id, source_id, telemetry_timestamp, so2_mg_nm3,
nox_mg_nm3, pm_dust_mg_nm3, co_mg_nm3, flue_gas_flow_m3_s, flue_temp_celsius,
sensor_status, created_at FROM read_parquet('s3://dlh-bronze/staging/raw_cems_telemetry/*.parquet')
sensor_status, created_at FROM read_parquet('s3://dlh-bronze/staging/raw_cems_telemetry_logs/*.parquet')
QUALIFY ROW_NUMBER() OVER (PARTITION BY log_id ORDER BY created_at DESC) = 1
- task_id: node-7127
- task_id: node-1818
type: ge_quality
label: GE Telemetry Bronze Quality
enabled: true
dependencies:
- node-6110
- node-0811
config:
ge_scope_level: all
ge_table_name: bronze_cems_telemetry_logs
@@ -123,19 +125,21 @@ tasks:
ge_col_table: stasiun_spku
ge_target_column: stasiun_id
ge_column_test_type: not_null
sql_assertion: ''
sql: ''
sql_assertion: SELECT count(*) FROM silver.table WHERE status NOT IN ('APPROVED',
'IN_REVIEW', 'REJECTED')
sql: SELECT count(*) FROM silver.table WHERE status NOT IN ('APPROVED', 'IN_REVIEW',
'REJECTED')
expected: 0
error_message: Unexpected rows detected in table
suite: bronze
fail: Stop DAG
- task_id: node-8143
- task_id: node-2864
type: dbt_transform
label: dbt Silver CEMS Enriched
enabled: true
dependencies:
- node-3042
- node-7127
- node-7780
- node-1818
config:
dbt_layer: silver
dbt_model: silver_cems_emission_enriched
@@ -170,12 +174,12 @@ tasks:
\ t.sensor_status\nFROM {{ ref('bronze_cems_telemetry_logs') }} t\nJOIN {{\
\ ref('bronze_ref_emission_sources') }} s\n ON t.source_id = s.source_id\n\
WHERE t.sensor_status = 'VALID'"
- task_id: node-9175
- task_id: node-3898
type: ge_quality
label: GE Silver Compliance Quality Gate
enabled: true
dependencies:
- node-8143
- node-2864
config:
ge_scope_level: all
ge_table_name: silver_cems_emission_enriched
@@ -187,18 +191,20 @@ tasks:
ge_col_table: stasiun_spku
ge_target_column: stasiun_id
ge_column_test_type: not_null
sql_assertion: ''
sql: ''
sql_assertion: SELECT count(*) FROM silver.table WHERE status NOT IN ('APPROVED',
'IN_REVIEW', 'REJECTED')
sql: SELECT count(*) FROM silver.table WHERE status NOT IN ('APPROVED', 'IN_REVIEW',
'REJECTED')
expected: 0
error_message: Unexpected rows detected in table
suite: bronze
fail: Stop DAG
- task_id: node-0193
- task_id: node-5020
type: dbt_transform
label: dbt Gold Industrial Compliance Mart
enabled: true
dependencies:
- node-9175
- node-3898
config:
dbt_layer: gold
dbt_model: gold_industry_emission_compliance_mart
@@ -231,12 +237,12 @@ tasks:
\ CURRENT_TIMESTAMP AS mart_refreshed_at\nFROM {{ ref('silver_cems_emission_enriched')\
\ }}\nGROUP BY region_zone, industry_sector\nORDER BY total_violations_count\
\ DESC, total_so2_emission_ton DESC"
- task_id: node-1241
- task_id: node-6105
type: ge_quality
label: GE Gold Compliance Mart Gate
enabled: true
dependencies:
- node-0193
- node-5020
config:
ge_scope_level: all
ge_table_name: gold_industry_emission_compliance_mart
@@ -248,18 +254,20 @@ tasks:
ge_col_table: stasiun_spku
ge_target_column: stasiun_id
ge_column_test_type: not_null
sql_assertion: ''
sql: ''
sql_assertion: SELECT count(*) FROM silver.table WHERE status NOT IN ('APPROVED',
'IN_REVIEW', 'REJECTED')
sql: SELECT count(*) FROM silver.table WHERE status NOT IN ('APPROVED', 'IN_REVIEW',
'REJECTED')
expected: 0
error_message: Unexpected rows detected in table
suite: bronze
fail: Stop DAG
- task_id: node-2409
- task_id: node-7152
type: sitomat_callback
label: SITOMAT Governance Callback
enabled: true
dependencies:
- node-1241
- node-6105
config:
layer: gold
artifact_ref: lakehouse.gold.gold_industry_emission_compliance_mart