def execute(self, context: dict) -> Any:
hook = AzureDataLakeHook(
azure_data_lake_conn_id=self.azure_data_lake_conn_id)
return hook.remove(path=self.path,
recursive=self.recursive,
ignore_not_found=self.ignore_not_found)
def execute(self, context: dict) -> list:
hook = AzureDataLakeHook(azure_data_lake_conn_id=self.azure_data_lake_conn_id)
self.log.info('Getting list of ADLS files in path: %s', self.path)
return hook.list(path=self.path)
def test_list_walk(self, mock_lib, mock_fs):
from airflow.providers.microsoft.azure.hooks.azure_data_lake import AzureDataLakeHook
hook = AzureDataLakeHook(azure_data_lake_conn_id='adl_test_key')
hook.list('file_path/some_folder/')
mock_fs.return_value.walk.assert_called_once_with(
'file_path/some_folder/')
def test_remove(self, mock_lib, mock_fs):
from airflow.providers.microsoft.azure.hooks.azure_data_lake import AzureDataLakeHook
hook = AzureDataLakeHook(azure_data_lake_conn_id='adl_test_key')
hook.remove('filepath', True)
mock_fs.return_value.remove.assert_called_once_with('filepath',
recursive=True)
def test_conn(self, mock_lib):
from airflow.providers.microsoft.azure.hooks.azure_data_lake import AzureDataLakeHook
from azure.datalake.store import core
hook = AzureDataLakeHook(azure_data_lake_conn_id='adl_test_key')
self.assertIsNone(hook._conn)
self.assertEqual(hook.conn_id, 'adl_test_key')
self.assertIsInstance(hook.get_conn(), core.AzureDLFileSystem)
assert mock_lib.auth.called
def test_download_file(self, mock_lib, mock_downloader):
from airflow.providers.microsoft.azure.hooks.azure_data_lake import AzureDataLakeHook
hook = AzureDataLakeHook(azure_data_lake_conn_id='adl_test_key')
hook.download_file(local_path='test_adl_hook.py',
remote_path='/test_adl_hook.py',
nthreads=64, overwrite=True,
buffersize=4194304, blocksize=4194304)
mock_downloader.assert_called_once_with(hook.get_conn(),
lpath='test_adl_hook.py',
rpath='/test_adl_hook.py',
nthreads=64, overwrite=True,
buffersize=4194304, blocksize=4194304)
def execute(self, context: dict) -> None:
oracle_hook = OracleHook(oracle_conn_id=self.oracle_conn_id)
azure_data_lake_hook = AzureDataLakeHook(azure_data_lake_conn_id=self.azure_data_lake_conn_id)
self.log.info("Dumping Oracle query results to local file")
conn = oracle_hook.get_conn()
cursor = conn.cursor() # type: ignore[attr-defined]
cursor.execute(self.sql, self.sql_params)
with TemporaryDirectory(prefix='airflow_oracle_to_azure_op_') as temp:
self._write_temp_file(cursor, os.path.join(temp, self.filename))
self.log.info("Uploading local file to Azure Data Lake")
azure_data_lake_hook.upload_file(
os.path.join(temp, self.filename), os.path.join(self.azure_data_lake_path, self.filename)
)
cursor.close()
conn.close() # type: ignore[attr-defined]
def execute(self, context: dict) -> None:
if '**' in self.local_path:
raise AirflowException(
"Recursive glob patterns using `**` are not supported")
if not self.extra_upload_options:
self.extra_upload_options = {}
hook = AzureDataLakeHook(
azure_data_lake_conn_id=self.azure_data_lake_conn_id)
self.log.info('Uploading %s to %s', self.local_path, self.remote_path)
return hook.upload_file(
local_path=self.local_path,
remote_path=self.remote_path,
nthreads=self.nthreads,
overwrite=self.overwrite,
buffersize=self.buffersize,
blocksize=self.blocksize,
**self.extra_upload_options,
)
def execute(self, context):
# use the super to list all files in an Azure Data Lake path
files = super().execute(context)
g_hook = GCSHook(
gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
impersonation_chain=self.google_impersonation_chain,
)
if not self.replace:
# if we are not replacing -> list all files in the ADLS path
# and only keep those files which are present in
# ADLS and not in Google Cloud Storage
bucket_name, prefix = _parse_gcs_url(self.dest_gcs)
existing_files = g_hook.list(bucket_name=bucket_name,
prefix=prefix)
files = set(files) - set(existing_files)
if files:
hook = AzureDataLakeHook(
azure_data_lake_conn_id=self.azure_data_lake_conn_id)
for obj in files:
with NamedTemporaryFile(mode='wb', delete=True) as f:
hook.download_file(local_path=f.name, remote_path=obj)
f.flush()
dest_gcs_bucket, dest_gcs_prefix = _parse_gcs_url(
self.dest_gcs)
dest_path = os.path.join(dest_gcs_prefix, obj)
self.log.info("Saving file to %s", dest_path)
g_hook.upload(bucket_name=dest_gcs_bucket,
object_name=dest_path,
filename=f.name,
gzip=self.gzip)
self.log.info("All done, uploaded %d files to GCS", len(files))
else:
self.log.info("In sync, no files needed to be uploaded to GCS")
return files
def test_check_for_blob(self, mock_lib, mock_filesystem):
from airflow.providers.microsoft.azure.hooks.azure_data_lake import AzureDataLakeHook
hook = AzureDataLakeHook(azure_data_lake_conn_id='adl_test_key')
hook.check_for_file('file_path')
mock_filesystem.glob.called
def get_hook(self):
if self.conn_type == 'mysql':
from airflow.providers.mysql.hooks.mysql import MySqlHook
return MySqlHook(mysql_conn_id=self.conn_id)
elif self.conn_type == 'google_cloud_platform':
from airflow.gcp.hooks.bigquery import BigQueryHook
return BigQueryHook(bigquery_conn_id=self.conn_id)
elif self.conn_type == 'postgres':
from airflow.providers.postgres.hooks.postgres import PostgresHook
return PostgresHook(postgres_conn_id=self.conn_id)
elif self.conn_type == 'pig_cli':
from airflow.providers.apache.pig.hooks.pig import PigCliHook
return PigCliHook(pig_cli_conn_id=self.conn_id)
elif self.conn_type == 'hive_cli':
from airflow.providers.apache.hive.hooks.hive import HiveCliHook
return HiveCliHook(hive_cli_conn_id=self.conn_id)
elif self.conn_type == 'presto':
from airflow.providers.presto.hooks.presto import PrestoHook
return PrestoHook(presto_conn_id=self.conn_id)
elif self.conn_type == 'hiveserver2':
from airflow.providers.apache.hive.hooks.hive import HiveServer2Hook
return HiveServer2Hook(hiveserver2_conn_id=self.conn_id)
elif self.conn_type == 'sqlite':
from airflow.providers.sqlite.hooks.sqlite import SqliteHook
return SqliteHook(sqlite_conn_id=self.conn_id)
elif self.conn_type == 'jdbc':
from airflow.providers.jdbc.hooks.jdbc import JdbcHook
return JdbcHook(jdbc_conn_id=self.conn_id)
elif self.conn_type == 'mssql':
from airflow.providers.microsoft.mssql.hooks.mssql import MsSqlHook
return MsSqlHook(mssql_conn_id=self.conn_id)
elif self.conn_type == 'odbc':
from airflow.providers.odbc.hooks.odbc import OdbcHook
return OdbcHook(odbc_conn_id=self.conn_id)
elif self.conn_type == 'oracle':
from airflow.providers.oracle.hooks.oracle import OracleHook
return OracleHook(oracle_conn_id=self.conn_id)
elif self.conn_type == 'vertica':
from airflow.providers.vertica.hooks.vertica import VerticaHook
return VerticaHook(vertica_conn_id=self.conn_id)
elif self.conn_type == 'cloudant':
from airflow.providers.cloudant.hooks.cloudant import CloudantHook
return CloudantHook(cloudant_conn_id=self.conn_id)
elif self.conn_type == 'jira':
from airflow.providers.jira.hooks.jira import JiraHook
return JiraHook(jira_conn_id=self.conn_id)
elif self.conn_type == 'redis':
from airflow.providers.redis.hooks.redis import RedisHook
return RedisHook(redis_conn_id=self.conn_id)
elif self.conn_type == 'wasb':
from airflow.providers.microsoft.azure.hooks.wasb import WasbHook
return WasbHook(wasb_conn_id=self.conn_id)
elif self.conn_type == 'docker':
from airflow.providers.docker.hooks.docker import DockerHook
return DockerHook(docker_conn_id=self.conn_id)
elif self.conn_type == 'azure_data_lake':
from airflow.providers.microsoft.azure.hooks.azure_data_lake import AzureDataLakeHook
return AzureDataLakeHook(azure_data_lake_conn_id=self.conn_id)
elif self.conn_type == 'azure_cosmos':
from airflow.providers.microsoft.azure.hooks.azure_cosmos import AzureCosmosDBHook
return AzureCosmosDBHook(azure_cosmos_conn_id=self.conn_id)
elif self.conn_type == 'cassandra':
from airflow.providers.apache.cassandra.hooks.cassandra import CassandraHook
return CassandraHook(cassandra_conn_id=self.conn_id)
elif self.conn_type == 'mongo':
from airflow.providers.mongo.hooks.mongo import MongoHook
return MongoHook(conn_id=self.conn_id)
elif self.conn_type == 'gcpcloudsql':
from airflow.gcp.hooks.cloud_sql import CloudSQLDatabaseHook
return CloudSQLDatabaseHook(gcp_cloudsql_conn_id=self.conn_id)
elif self.conn_type == 'grpc':
from airflow.providers.grpc.hooks.grpc import GrpcHook
return GrpcHook(grpc_conn_id=self.conn_id)
raise AirflowException("Unknown hook type {}".format(self.conn_type))
