AWS RDS Postgres (via Collector method) - v3.0.0

GRANT USAGE ON SCHEMA pg_catalog TO <kada user>;
GRANT SELECT ON ALL TABLES IN SCHEMA pg_catalog TO <kada user>;

pip install kada_collectors_extractors_<version>-none-any.whl

pip install kada_collectors_lib-<version>-none-any.whl

{
    "host": "",
    "server": "",
    "username": "",
    "password": "",
    "databases": [],
    "port": 5432,
    "output_path": "/tmp/output",
    "mask": true,
    "compress": true,
    "meta_only": true
}

import os
import argparse
from kada_collectors.extractors.utils import load_config, get_hwm, publish_hwm, get_generic_logger
from kada_collectors.extractors.postgres import Extractor

get_generic_logger('root') # Set to use the root logger, you can change the context accordingly or define your own logger

_type = 'postgres'
dirname = os.path.dirname(__file__)
filename = os.path.join(dirname, 'kada_{}_extractor_config.json'.format(_type))

parser = argparse.ArgumentParser(description='KADA Postgres Extractor.')
parser.add_argument('--config', '-c', dest='config', default=filename, help='Location of the configuration json, default is the config json in the same directory as the script.')
parser.add_argument('--name', '-n', dest='name', default=_type, help='Name of the collector instance.')
args = parser.parse_args()

start_hwm, end_hwm = get_hwm(args.name)

ext = Extractor(**load_config(args.config))
ext.test_connection()

disable_roles_sql = """SELECT DISTINCT 'USER' AS "OBJECT_TYPE", '' AS "OBJECT_ID", '' AS "USER", '' AS "ROLE" where 1 = 2"""
ext.overwrite_sql('ROLES_SQL', disable_roles_sql)

ext.run(**{"start_hwm": start_hwm, "end_hwm": end_hwm})

publish_hwm(_type, end_hwm)

from kada_collectors.extractors.snowflake import Extractor

kwargs = {my args} # However you choose to construct your args
hwm_kwrgs = {"start_hwm": "end_hwm": } # The hwm values

ext = Extractor(**kwargs)
ext.run(**hwm_kwrgs)

class Extractor(username: str = None, password: str = None, host: str = None, \
    server: str = None, databases: list = [], port: int = 5432, \
    output_path: str = './output', mask: bool = False, compress: bool = False, \
    meta_only: bool = False) -> None

# built-in
import os

# Installed
from airflow.operators.python_operator import PythonOperator
from airflow.models.dag import DAG
from airflow.operators.dummy import DummyOperator
from airflow.utils.dates import days_ago
from airflow.utils.task_group import TaskGroup

from plugins.utils.azure_blob_storage import AzureBlobStorage

from kada_collectors.extractors.utils import load_config, get_hwm, publish_hwm, get_generic_logger
from kada_collectors.extractors.tableau import Extractor

# To be configed by the customer.
# Note variables may change if using a different object store.
KADA_SAS_TOKEN = os.getenv("KADA_SAS_TOKEN")
KADA_CONTAINER = ""
KADA_STORAGE_ACCOUNT = ""
KADA_LANDING_PATH = "lz/tableau/landing"
KADA_EXTRACTOR_CONFIG = {
    "server_address": "http://tabserver",
    "username": "user",
    "password": "password",
    "sites": [],
    "db_host": "tabserver",
    "db_username": "repo_user",
    "db_password": "repo_password",
    "db_port": 8060,
    "db_name": "workgroup",
    "meta_only": False,
    "retries": 5,
    "dry_run": False,
    "output_path": "/set/to/output/path",
    "mask": True,
    "mapping": {}
}

# To be implemented by the customer. 
# Upload to your landing zone storage.
def upload():
  output = KADA_EXTRACTOR_CONFIG['output_path']
  for filename in os.listdir(output):
      if filename.endswith('.csv'):
        file_to_upload_path = os.path.join(output, filename)

        AzureBlobStorage.upload_file_sas_token(
            client=KADA_SAS_TOKEN,
            storage_account=KADA_STORAGE_ACCOUNT,
            container=KADA_CONTAINER, 
            blob=f'{KADA_LANDING_PATH}/{filename}', 
            local_path=file_to_upload_path
        )

with DAG(dag_id="taskgroup_example", start_date=days_ago(1)) as dag:
  
    # To be implemented by the customer.
    # Retrieve the timestamp from the prior run
    start_hwm = 'YYYY-MM-DD HH:mm:SS'
    end_hwm = 'YYYY-MM-DD HH:mm:SS' # timestamp now
    
    ext = Extractor(**KADA_EXTRACTOR_CONFIG)
    
    start = DummyOperator(task_id="start")

    with TaskGroup("taskgroup_1", tooltip="extract tableau and upload") as extract_upload:
        task_1 = PythonOperator(
            task_id="extract_tableau",
            python_callable=ext.run, 
            op_kwargs={"start_hwm": start_hwm, "end_hwm": end_hwm},
            provide_context=True,
        )
        
        task_2 = PythonOperator(
            task_id="upload_extracts",
            python_callable=upload, 
            op_kwargs={},
            provide_context=True,
        )

        # To be implemented by the customer. 
        # Timestamp needs to be saved for next run
        task_3 = DummyOperator(task_id='save_hwm') 

    end = DummyOperator(task_id='end')

    start >> extract_upload >> end