uranusjr commented on code in PR #31398: URL: https://github.com/apache/airflow/pull/31398#discussion_r1246184997
########## airflow/providers/openlineage/utils/sql.py: ########## @@ -0,0 +1,195 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +from __future__ import annotations + +import logging +from collections import defaultdict +from contextlib import closing +from enum import IntEnum +from typing import TYPE_CHECKING, Dict, List, Optional + +from attrs import define +from sqlalchemy import Column, MetaData, Table, and_, union_all + +from openlineage.client.facet import SchemaDatasetFacet, SchemaField +from openlineage.client.run import Dataset + +if TYPE_CHECKING: + from sqlalchemy.engine import Engine + from sqlalchemy.sql import ClauseElement + + from airflow.hooks.base import BaseHook + + +logger = logging.getLogger(__name__) + + +class ColumnIndex(IntEnum): + """Enumerates the indices of columns in information schema view.""" + + SCHEMA = 0 + TABLE_NAME = 1 + COLUMN_NAME = 2 + ORDINAL_POSITION = 3 + # Use 'udt_name' which is the underlying type of column + UDT_NAME = 4 + # Database is optional as 5th column + DATABASE = 5 + + +TablesHierarchy = Dict[Optional[str], Dict[Optional[str], List[str]]] + + +@define +class TableSchema: + """Temporary object used to construct OpenLineage Dataset.""" + + table: str + schema: str | None + database: str | None + fields: list[SchemaField] + + def to_dataset(self, namespace: str, database: str | None = None) -> Dataset: + # Prefix the table name with database and schema name using + # the format: {database_name}.{table_schema}.{table_name}. + name = ".".join( + [ + x + for x in [self.database if self.database else database, self.schema, self.table] + if x is not None + ] + ) + + return Dataset( + namespace=namespace, + name=name, + facets={"schema": SchemaDatasetFacet(fields=self.fields)} if len(self.fields) is not None else {}, Review Comment: The `len()` part can never be None and thus the `else` part can never execute. Is there a typo here? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
