This commit is contained in:
Grzegorz Michalski
2026-03-02 09:47:35 +01:00
commit 2c225d68ac
715 changed files with 130067 additions and 0 deletions

View File

@@ -0,0 +1,73 @@
from jinja2 import Environment, FileSystemLoader
import csv
environment = Environment(loader=FileSystemLoader("templates/"))
template_sq = environment.get_template("m_Template_sq.sql")
template_tgt = environment.get_template("m_Template_target.sql")
template_db = environment.get_template("db_Template.sql")
template_dag = environment.get_template("dag_Template.py")
csvFile = csv.reader(open("ods_mopdb_plain.txt", "r"))
header = next(csvFile) # skip header
for row in csvFile:
(schema, table) = row
# ou_tms,ACTIVITYLOGDUE,TMS,T_ACTIVITYLOGDUE,m_MOPDB_TMS_T_ACTIVITYLOGDUE_OU_TMS_ACTIVITYLOGDUE,w_ODS_TMS_ACTIVITYLOGDUE
target_table = f"T_{table}"
source_schema = f"OU_{schema}"
source_schema_lower = f"{source_schema}".lower()
source_table = table
mapping_name = f"m_MOPDB_{schema}_{target_table}_{source_schema}_{source_table}"
workflow_name = f"w_MOPDB_{schema}_{target_table}"
content = template_sq.render(
source_schema = source_schema_lower,
source_table = table,
target_schema = schema,
target_table = target_table,
mapping_name = mapping_name,
workflow_name = workflow_name
)
filename=f"source_qualifiers/{mapping_name}_SQ.sql"
with open(filename, mode="w", encoding="utf-8") as message:
message.write(content)
print(f"... wrote {filename}")
content = template_tgt.render(
source_schema = source_schema_lower,
source_table = table,
target_schema = schema,
target_table = target_table,
mapping_name = mapping_name,
workflow_name = workflow_name
)
filename=f"targets/{mapping_name}.sql"
with open(filename, mode="w", encoding="utf-8") as message:
message.write(content)
print(f"... wrote {filename}")
content = template_dag.render(
table = table
)
filename=f"dags/{workflow_name}.py"
with open(filename, mode="w", encoding="utf-8") as message:
message.write(content)
print(f"... wrote {filename}")
content = template_db.render(
table = table,
schema = schema
)
filename=f"db/{source_schema}_{source_table}.sql"
with open(filename, mode="w", encoding="utf-8") as message:
message.write(content)
print(f"... wrote {filename}")
filename=f"db/table_changes.sql"
with open(filename, mode="a", encoding="utf-8") as message:
message.write(f"{content}\n")
print(f"... wrote {filename}")

View File

@@ -0,0 +1,30 @@
SCHEMA,TABLE
TMS,ACMENTRYSTATELEDGERGROUP
TMS,ACTIVITYLOGDUE
TMS,ACTIVITY_LOG
TMS,BALANCE
TMS,BLACKOUT_LOG
TMS,BRANCH
TMS,CALENDAR
TMS,CASHFLOW
TMS,CLIENT
TMS,CUSTODYBALANCE
TMS,ECBINSTRUMENTBONDCASHFLOW
TMS,EFFECTIVEROLEPROFILE
TMS,FINMESSAGELOG
TMS,HISTORY_LOG
TMS,INSTRUMENTBONDCASHFLOW
TMS,INSTRUMENT_REPORT
TMS,MARKETINFO
TMS,PARAMETER
TMS,PORTFOLIOTREE
TMS,PRICES
TMS,PROPERTY
TMS,RECONCILIATION
TMS,ROLEPORTFOLIOPROFILE
TMS,RULES
TMS,SDM_ENTITY_STATE
TMS,SECURITYPOSITION
TMS,SETTLEMENTCASHFLOW
TMS,SETTLEMENTLOG
TMS,USERINFORMATION

View File

@@ -0,0 +1,95 @@
from airflow.decorators import dag
from airflow.operators.bash import BashOperator
from airflow.operators.python import PythonOperator
from airflow.utils.dates import days_ago
from airflow.utils.trigger_rule import TriggerRule
from cosmos import DbtTaskGroup, ProfileConfig, ProjectConfig, RenderConfig
# Define paths to your dbt files
dbt_root_path = "/home/dbt/DBT/mrds"
dbt_profiles_dir = "/home/dbt/.dbt/profiles.yml"
ODS_TABLE = "{{table}}"
DATABASE_NAME = "MOPDB"
DAG_NAME = f"w_{DATABASE_NAME}_TMS_T_{ODS_TABLE}_OU_TMS_{ODS_TABLE}"
MAPPING_NAME = f"m_{DATABASE_NAME}_TMS_T_{ODS_TABLE}_OU_TMS_{ODS_TABLE}"
# Define function for the retrieval of the current run_id
def retrieve_run_id(**kwargs):
# Retrieve the run_id from the Airflow context
run_id = kwargs['run_id']
# Store the run_id in XCom for future reference
ti = kwargs['ti']
ti.xcom_push(key='run_id', value=run_id)
return run_id
def check_dag_status(**kwargs):
for task_instance in kwargs['dag_run'].get_task_instances():
if task_instance.state == 'failed' and task_instance.task_id != kwargs['task_instance'].task_id:
raise Exception("Task {} failed. Failing this DAG run".format(task_instance.task_id))
# Define function for the check of the status of the previous tasks
def determine_workflow_status(**kwargs):
# Check the status of previous tasks
task_statuses = kwargs['ti'].xcom_pull(task_ids=['retrieve_run_id', 'control_external_run_start', 'mapping_mopdb'])
# If any task failed, set workflow_status to 'N', otherwise 'Y'
workflow_status = 'N' if any(status != 'success' for status in task_statuses) else 'Y'
return workflow_status
@dag(
dag_id=DAG_NAME,
schedule_interval=None,
start_date=days_ago(2),
catchup=False
)
def run_dag():
# Retrieve run_id
retrieve_run_id_task = PythonOperator(
task_id='retrieve_run_id',
python_callable=retrieve_run_id,
provide_context=True,
# pool='my_custom_pool', # Create pool in Airflow Web UI with one slot to ensure that only one dag can run it at a time.
)
# Run dbt macro control_external_run_start
control_external_run_start = BashOperator(
task_id='control_external_run_start',
bash_command=(
'cd /home/dbt/DBT/mrds && '
'dbt run-operation control_external_run_start --vars \'{"orchestration_run_id": "{% raw %}{{{% endraw %} task_instance.xcom_pull(task_ids="retrieve_run_id", key="run_id") {% raw %}}}{% endraw %}", "input_service_name": "' + DATABASE_NAME + '", "workflow_name": "' + DAG_NAME + '"}\' '
'--profiles-dir /home/dbt/.dbt/ --target dev'
)
)
# run dbt taskGroup with tag of the mapping name
dbtTaskGroup = DbtTaskGroup(
group_id=MAPPING_NAME,
project_config=ProjectConfig(
dbt_project_path = dbt_root_path),
profile_config=ProfileConfig(
profiles_yml_filepath = dbt_profiles_dir,
profile_name="mrds",
target_name="dev"),
render_config=RenderConfig(select=[f"tag:{MAPPING_NAME}"],),
operator_args={'vars': {'orchestration_run_id': '{% raw %}{{{% endraw %} task_instance.xcom_pull(task_ids="retrieve_run_id", key="run_id") {% raw %}}}{% endraw %}', "input_service_name": DATABASE_NAME, "workflow_name": DAG_NAME }}
)
control_external_run_end = BashOperator(
task_id='control_external_run_end',
bash_command=(
'cd /home/dbt/DBT/mrds && '
'dbt run-operation control_external_run_end --vars \'{"orchestration_run_id": "{% raw %}{{{% endraw %} task_instance.xcom_pull(task_ids="retrieve_run_id", key="run_id") {% raw %}}}{% endraw %}", "input_service_name": "' + DATABASE_NAME + '", "workflow_name": "' + DAG_NAME + '"}\' '
'--profiles-dir /home/dbt/.dbt/ --target dev'
),
trigger_rule=TriggerRule.ALL_DONE # Run regardless of previous task outcomes
)
dag_status = PythonOperator(
task_id='dag_status',
provide_context=True,
python_callable=check_dag_status,
trigger_rule=TriggerRule.ALL_DONE, # Ensures this task runs even if upstream fails
)
# Set task dependencies
retrieve_run_id_task >> control_external_run_start >> [dbtTaskGroup] >> control_external_run_end >> dag_status
globals()[DAG_NAME] = run_dag()

View File

@@ -0,0 +1,2 @@
ALTER TABLE OU_{{schema}}.{{table}} RENAME COLUMN A_ETL_LOAD_SET_FK TO A_WORKFLOW_HISTORY_KEY;
DROP TABLE {{schema}}.T_{{table}};

View File

@@ -0,0 +1,11 @@
{% raw %}{{{% endraw %}
config(
materialized="table",
tags=["{{mapping_name}}", "{{source_schema}}", "{{target_schema}}"],
alias="{{target_table}}_SQ",
schema="{{target_schema}}"
)
{% raw %}}}{% endraw %}
{% raw %}{{{% endraw %}
create_table_from_source("{{source_schema}}","{{source_table}}","{{workflow_name}}",get_main_task_name(model.name),['A_KEY','A_WORKFLOW_HISTORY_KEY'])
{% raw %}}}{% endraw %}

View File

@@ -0,0 +1,13 @@
{% raw %}-- depends_on: {{{% endraw %} ref('{{mapping_name}}_SQ') {% raw %}}} {% endraw %}
{% raw %}{{{% endraw %}
config(
tags=["{{mapping_name}}","MOPDB","{{target_schema}}"],
alias="{{target_table}}",
schema="{{target_schema}}",
materialized="incremental" ,
incremental_strategy="merge"
)
{% raw %}}}{% endraw %}
{% raw %}{{{% endraw %}
create_table_target('{{mapping_name}}_SQ')
{% raw %}}}{% endraw %}