Skip to content

Instantly share code, notes, and snippets.

View mesmacosta's full-sized avatar
🏠
Working from home

Marcelo Costa mesmacosta

🏠
Working from home
View GitHub Profile
from datetime import datetime, timedelta
from airflow.models import DAG
from airflow.operators.python import PythonOperator
from airflow.utils.session import provide_session
from alvin_integration.producers.airflow.pipeline.extractor import extract_dag_metadata
seven_days_ago = datetime.combine(
datetime.today() - timedelta(1), datetime.min.time()
"facets": {
"alvin": {
"connection_id": "google_cloud_default",
"execution": {
"alvin_package_version": "0.15.7",
"platform_id": "airflowprd",
"duration": 41.69428,
...
},
"job_id": "airflow_2141512512_fcf9812412412412412421412"
{
"eventType": "START",
"eventTime": "2020-12-09T23:37:31.081Z",
"run": {
"runId": "3b452093-782c-4ef2-9c0c-aafe2aa6f34d",
},
"job": {
"namespace": "my-scheduler-namespace",
"name": "myjob.mytask",
"facets": {...}
def execute(self, context: 'Context'):
# ... code suppresed for readability
if isinstance(self.sql, str):
job_id: Union[str, List[str]] = self.hook.run_query(
sql=self.sql,
destination_dataset_table=self.destination_dataset_table,
write_disposition=self.write_disposition,
allow_large_results=self.allow_large_results,
flatten_results=self.flatten_results,
udf_config=self.udf_config,
def execute(self, context: Any):
hook = BigQueryHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
impersonation_chain=self.impersonation_chain,
)
self.hook = hook
job_id = self._job_id(context)
@mesmacosta
mesmacosta / log.py
Created August 10, 2021 21:07
Python log Hack
handler = logging.StreamHandler()
# Set debug level for the client
es_logger.setLevel(logging.DEBUG)
es_logger.addHandler(handler)
es_logger.disabled = False
# Set trace logger
es_trace_logger = logging.getLogger('elasticsearch.trace')
es_trace_logger.setLevel(logging.DEBUG)
sql_objects:
- name: 'functions'
enabled: True
SELECT f.SCHEMA_NAME AS SCHEMA_NAME,
f.FUNCTION_NAME AS function_name,
f.INPUT_PARAMETER_COUNT AS input_parameter_count,
f.RETURN_VALUE_COUNT AS return_value_count,
f.DEFINITION AS definition,
f.IS_VALID AS is_valid,
f.OWNER_NAME AS owner_name,
f.CREATE_TIME AS create_time
FROM SYS.FUNCTIONS f
// ... Omitted to improve readability
{
"key": "functions",
"type": "function",
"name": "function_name",
"fields": [
{
"source": "schema_name",
"target": {
"field_name": "schema_name",
"model": "tag",
CREATE TABLE credit_tab_pii (Name varchar(20), CREDIT_CARD varchar(19))
WITH MASK (CREDIT_CARD USING credit_mask(credit_card));