def execute(self, context=None): metastore = HiveMetastoreHook(metastore_conn_id=self.metastore_conn_id) table = metastore.get_table(table_name=self.table) field_types = {col.name: col.type for col in table.sd.cols} exprs = {('', 'count'): 'COUNT(*)'} for col, col_type in list(field_types.items()): d = {} if self.assignment_func: d = self.assignment_func(col, col_type) if d is None: d = self.get_default_exprs(col, col_type) else: d = self.get_default_exprs(col, col_type) exprs.update(d) exprs.update(self.extra_exprs) exprs = OrderedDict(exprs) exprs_str = ",\n ".join( [v + " AS " + k[0] + '__' + k[1] for k, v in exprs.items()]) where_clause = [ "{} = '{}'".format(k, v) for k, v in self.partition.items() ] where_clause = " AND\n ".join(where_clause) sql = "SELECT {exprs_str} FROM {table} WHERE {where_clause};".format( exprs_str=exprs_str, table=self.table, where_clause=where_clause) presto = PrestoHook(presto_conn_id=self.presto_conn_id) self.log.info('Executing SQL check: %s', sql) row = presto.get_first(hql=sql) self.log.info("Record: %s", row) if not row: raise AirflowException("The query returned None") part_json = json.dumps(self.partition, sort_keys=True) self.log.info("Deleting rows from previous runs if they exist") mysql = MySqlHook(self.mysql_conn_id) sql = """ SELECT 1 FROM hive_stats WHERE table_name='{table}' AND partition_repr='{part_json}' AND dttm='{dttm}' LIMIT 1; """.format(table=self.table, part_json=part_json, dttm=self.dttm) if mysql.get_records(sql): sql = """ DELETE FROM hive_stats WHERE table_name='{table}' AND partition_repr='{part_json}' AND dttm='{dttm}'; """.format(table=self.table, part_json=part_json, dttm=self.dttm) mysql.run(sql) self.log.info("Pivoting and loading cells into the Airflow db") rows = [(self.ds, self.dttm, self.table, part_json) + (r[0][0], r[0][1], r[1]) for r in zip(exprs, row)] mysql.insert_rows(table='hive_stats', rows=rows, target_fields=[ 'ds', 'dttm', 'table_name', 'partition_repr', 'col', 'metric', 'value', ])
def execute(self, context=None): metastore = HiveMetastoreHook(metastore_conn_id=self.metastore_conn_id) table = metastore.get_table(table_name=self.table) field_types = {col.name: col.type for col in table.sd.cols} exprs = { ('', 'count'): 'COUNT(*)' } for col, col_type in list(field_types.items()): d = {} if self.assignment_func: d = self.assignment_func(col, col_type) if d is None: d = self.get_default_exprs(col, col_type) else: d = self.get_default_exprs(col, col_type) exprs.update(d) exprs.update(self.extra_exprs) exprs = OrderedDict(exprs) exprs_str = ",\n ".join([ v + " AS " + k[0] + '__' + k[1] for k, v in exprs.items()]) where_clause = ["{} = '{}'".format(k, v) for k, v in self.partition.items()] where_clause = " AND\n ".join(where_clause) sql = "SELECT {exprs_str} FROM {table} WHERE {where_clause};".format( exprs_str=exprs_str, table=self.table, where_clause=where_clause) presto = PrestoHook(presto_conn_id=self.presto_conn_id) self.log.info('Executing SQL check: %s', sql) row = presto.get_first(hql=sql) self.log.info("Record: %s", row) if not row: raise AirflowException("The query returned None") part_json = json.dumps(self.partition, sort_keys=True) self.log.info("Deleting rows from previous runs if they exist") mysql = MySqlHook(self.mysql_conn_id) sql = """ SELECT 1 FROM hive_stats WHERE table_name='{table}' AND partition_repr='{part_json}' AND dttm='{dttm}' LIMIT 1; """.format(table=self.table, part_json=part_json, dttm=self.dttm) if mysql.get_records(sql): sql = """ DELETE FROM hive_stats WHERE table_name='{table}' AND partition_repr='{part_json}' AND dttm='{dttm}'; """.format(table=self.table, part_json=part_json, dttm=self.dttm) mysql.run(sql) self.log.info("Pivoting and loading cells into the Airflow db") rows = [(self.ds, self.dttm, self.table, part_json) + (r[0][0], r[0][1], r[1]) for r in zip(exprs, row)] mysql.insert_rows( table='hive_stats', rows=rows, target_fields=[ 'ds', 'dttm', 'table_name', 'partition_repr', 'col', 'metric', 'value', ] )