feat: initial commit for merica-pipeline delivery

This commit is contained in:
MERICA Admin
2026-10-08 19:33:15 +07:00
commit 42fedab752
46 changed files with 5484 additions and 0 deletions
+25
View File
@@ -0,0 +1,25 @@
name: 'dlh_transformation'
version: '1.0.0'
config-version: 2
profile: 'dlh_postgres'
model-paths: ["models"]
analysis-paths: ["analyses"]
test-paths: ["tests"]
seed-paths: ["seeds"]
macro-paths: ["macros"]
snapshot-paths: ["snapshots"]
clean-targets:
- "target"
- "dbt_packages"
models:
dlh_transformation:
silver:
+materialized: table
+schema: silver
gold:
+materialized: table
+schema: gold
+7
View File
@@ -0,0 +1,7 @@
{% macro generate_schema_name(custom_schema_name, node) -%}
{%- if custom_schema_name is none -%}
{{ target.schema }}
{%- else -%}
{{ custom_schema_name | trim }}
{%- endif -%}
{%- endmacro %}
+12
View File
@@ -0,0 +1,12 @@
-- dbt Gold Model: fct_spku_daily_mart
{{ config(materialized='table', schema='gold') }}
SELECT
stasiun_id,
nama_stasiun_clean,
AVG(ispu_value) AS avg_daily_ispu,
MAX(ispu_value) AS max_daily_ispu,
COUNT(*) AS total_readings,
CURRENT_DATE AS mart_date
FROM {{ ref('stg_spku_realtime') }}
GROUP BY stasiun_id, nama_stasiun_clean
@@ -0,0 +1,16 @@
{{ config(
materialized='table',
schema='gold'
) }}
SELECT
stasiun_id,
nama_stasiun,
CAST(recorded_at AS DATE) AS observation_date,
AVG(pm25_value) AS avg_pm25,
MAX(pm25_value) AS max_pm25,
AVG(pm10_value) AS avg_pm10,
MAX(pm10_value) AS max_pm10,
CURRENT_TIMESTAMP AS refreshed_at_gold
FROM {{ ref('silver_spku_sensor_clean') }}
GROUP BY 1, 2, 3
@@ -0,0 +1,13 @@
{{ config(
materialized='table',
schema='gold'
) }}
SELECT
CAST(issued_date AS DATE) AS permit_date,
permit_type,
permit_status,
COUNT(permit_id) AS total_permits,
CURRENT_TIMESTAMP AS refreshed_at_gold
FROM {{ ref('silver_environmental_permits_clean') }}
GROUP BY 1, 2, 3
@@ -0,0 +1,14 @@
{{ config(
materialized='table',
schema='gold'
) }}
SELECT
kecamatan,
tanggal_laporan,
COUNT(lokasi_tps) AS total_tps,
SUM(volume_sampah_m3) AS total_volume_sampah_m3,
AVG(volume_sampah_m3) AS avg_volume_per_tps_m3,
CURRENT_TIMESTAMP AS refreshed_at_gold
FROM {{ ref('silver_gws_waste_reports_clean') }}
GROUP BY 1, 2
@@ -0,0 +1,38 @@
{{ config(
materialized='incremental',
unique_key='permit_id',
schema='silver'
) }}
WITH cdc_raw AS (
SELECT
CAST(permit_id AS VARCHAR) AS permit_id,
TRIM(applicant_name) AS applicant_name,
LOWER(permit_type) AS permit_type,
CAST(status AS VARCHAR) AS permit_status,
CAST(issued_date AS TIMESTAMP) AS issued_date,
CAST(updated_at AS TIMESTAMP) AS updated_at,
_sling_op,
CAST(_sling_ts AS TIMESTAMP) AS _sling_ts,
ROW_NUMBER() OVER (
PARTITION BY permit_id
ORDER BY _sling_ts DESC
) AS row_num
FROM {{ source('bronze_lakehouse', 'environmental_permits_cdc') }}
{% if is_incremental() %}
WHERE _sling_ts > (SELECT MAX(_sling_ts) FROM {{ this }})
{% endif %}
)
SELECT
permit_id,
applicant_name,
permit_type,
permit_status,
issued_date,
updated_at,
_sling_ts,
CURRENT_TIMESTAMP AS ingested_at_silver
FROM cdc_raw
WHERE row_num = 1
AND _sling_op != 'D' -- Buang record yang di-DELETE
@@ -0,0 +1,22 @@
{{ config(
materialized='table',
schema='silver'
) }}
WITH raw_sheets AS (
SELECT
TRIM(CAST(lokasi_tps AS VARCHAR)) AS lokasi_tps,
TRIM(CAST(kecamatan AS VARCHAR)) AS kecamatan,
CAST(volume_sampah_m3 AS NUMERIC(10,2)) AS volume_sampah_m3,
CAST(tanggal_laporan AS DATE) AS tanggal_laporan
FROM {{ source('bronze_lakehouse', 'gws_waste_reports') }}
WHERE lokasi_tps IS NOT NULL AND lokasi_tps != ''
)
SELECT
lokasi_tps,
kecamatan,
volume_sampah_m3,
tanggal_laporan,
CURRENT_TIMESTAMP AS ingested_at_silver
FROM raw_sheets
@@ -0,0 +1,17 @@
{{ config(
materialized='table',
schema='silver'
) }}
WITH raw_json AS (
SELECT json_payload FROM {{ source('bronze_lakehouse', 'spku_api_raw') }}
)
SELECT
(json_payload->>'stasiun_id')::VARCHAR AS stasiun_id,
(json_payload->>'nama_stasiun')::VARCHAR AS nama_stasiun,
(json_payload->>'pm25')::NUMERIC(8,2) AS pm25_value,
(json_payload->>'pm10')::NUMERIC(8,2) AS pm10_value,
(json_payload->>'recorded_at')::TIMESTAMP AS recorded_at,
CURRENT_TIMESTAMP AS ingested_at_silver
FROM raw_json
+10
View File
@@ -0,0 +1,10 @@
-- dbt Silver Model: stg_spku_realtime
{{ config(materialized='table', schema='silver') }}
SELECT
stasiun_id,
LOWER(TRIM(nama_stasiun)) AS nama_stasiun_clean,
CAST(ispu_val AS FLOAT) AS ispu_value,
created_at
FROM {{ source('bronze', 'spku_api_raw') }}
WHERE ispu_val IS NOT NULL
+19
View File
@@ -0,0 +1,19 @@
version: 2
sources:
- name: bronze_lakehouse
schema: bronze_lakehouse
tables:
- name: environmental_permits_cdc
description: "Tabel landing Bronze staging untuk Change Data Capture (CDC) Perizinan Lingkungan"
- name: gws_waste_reports
description: "Tabel landing Bronze staging laporan penanganan sampah Google Workspace"
- name: spku_api_raw
description: "Tabel landing Bronze staging raw JSON payload sensor kualitas udara SPKU"
- name: bronze
schema: bronze_lakehouse
tables:
- name: environmental_permits_cdc
- name: gws_waste_reports
- name: spku_api_raw
+12
View File
@@ -0,0 +1,12 @@
dlh_postgres:
target: dev
outputs:
dev:
type: postgres
host: "{{ env_var('POSTGRES_HOST', 'postgres') }}"
port: 5432
user: "{{ env_var('POSTGRES_USER', 'dlh_user') }}"
pass: "{{ env_var('POSTGRES_PASSWORD', 'dlh_password') }}"
dbname: "{{ env_var('POSTGRES_DB', 'dlh_lakehouse') }}"
schema: public
threads: 4