class PigOperator(BaseOperator):
"""
Executes pig script.
:param pig: the pig latin script to be executed. (templated)
:type pig: str
:param pig_cli_conn_id: reference to the Hive database
:type pig_cli_conn_id: str
:param pigparams_jinja_translate: when True, pig params-type templating
${var} gets translated into jinja-type templating {{ var }}. Note that
you may want to use this along with the
``DAG(user_defined_macros=myargs)`` parameter. View the DAG
object documentation for more details.
:type pigparams_jinja_translate: bool
:param pig_opts: pig options, such as: -x tez, -useHCatalog, ...
:type pig_opts: str
"""
template_fields: Sequence[str] = ('pig', )
template_ext: Sequence[str] = (
'.pig',
'.piglatin',
)
ui_color = '#f0e4ec'
def __init__(
self,
*,
pig: str,
pig_cli_conn_id: str = 'pig_cli_default',
pigparams_jinja_translate: bool = False,
pig_opts: Optional[str] = None,
**kwargs: Any,
) -> None:
super().__init__(**kwargs)
self.pigparams_jinja_translate = pigparams_jinja_translate
self.pig = pig
self.pig_cli_conn_id = pig_cli_conn_id
self.pig_opts = pig_opts
self.hook: Optional[PigCliHook] = None
def prepare_template(self):
if self.pigparams_jinja_translate:
self.pig = re.sub(r"(\$([a-zA-Z_][a-zA-Z0-9_]*))", r"{{ \g<2> }}",
self.pig)
def execute(self, context: 'Context'):
self.log.info('Executing: %s', self.pig)
self.hook = PigCliHook(pig_cli_conn_id=self.pig_cli_conn_id)
self.hook.run_cli(pig=self.pig, pig_opts=self.pig_opts)
def on_kill(self):
self.hook.kill()
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))
def execute(self, context):
self.log.info('Executing: %s', self.pig)
self.hook = PigCliHook(pig_cli_conn_id=self.pig_cli_conn_id)
self.hook.run_cli(pig=self.pig, pig_opts=self.pig_opts)
def get_hook(self):
return PigCliHook(pig_cli_conn_id=self.pig_cli_conn_id)