huaxingao commented on a change in pull request #33754: URL: https://github.com/apache/spark/pull/33754#discussion_r690892887
########## File path: sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/index/Index.java ########## @@ -0,0 +1,79 @@ +/* + * 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. + */ + +package org.apache.spark.sql.connector.catalog.index; + +import java.util.Collections; +import java.util.Map; + +import org.apache.spark.annotation.Evolving; +import org.apache.spark.sql.connector.catalog.Identifier; +import org.apache.spark.sql.connector.expressions.FieldReference; + +/** + * An Index in a table + * + * @since 3.3.0 + */ +@Evolving +public class Index { + private String indexName; + private String indexType; + private Identifier table; + private FieldReference[] columns; + private Map<String, String> properties = Collections.emptyMap(); + + public Index( + String indexName, + String indexType, Review comment: The example index types are `BLOOM_FILTER_INDEX`, `Z_ORDERING_INDEX`, `BTREE_INDEX`. I actually started with enum and changed to String. It's more convenient to have index type outside of `properties`. in majority of the data sources, the create index syntax is `CREATE [index_type] INDEX index_name ON [TABLE] table_name (column_name [ , . . . ])[OPTIONS indexPropertyList]` @cloud-fan Shall we use enum instead of String for index type? Even though the catalog implementation is responsible for recognizing and taking care of user-specified index type, we still need to add these specific index types in `SqlBase`? We probably want to use enum to let users know what index types are supported? ########## File path: sql/catalyst/src/main/java/org/apache/spark/sql/connector/catalog/index/SupportsIndex.java ########## @@ -0,0 +1,137 @@ +/* + * 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. + */ + +package org.apache.spark.sql.connector.catalog.index; + +import java.util.Map; +import java.util.Properties; + +import org.apache.spark.annotation.Evolving; +import org.apache.spark.sql.catalyst.analysis.IndexAlreadyExistsException; +import org.apache.spark.sql.catalyst.analysis.NoSuchIndexException; +import org.apache.spark.sql.catalyst.analysis.NoSuchTableException; +import org.apache.spark.sql.connector.catalog.CatalogPlugin; +import org.apache.spark.sql.connector.catalog.Identifier; +import org.apache.spark.sql.connector.expressions.FieldReference; + +/** + * Catalog methods for working with index + * + * @since 3.3.0 + */ +@Evolving +public interface SupportsIndex extends CatalogPlugin { + + /** + * Creates an index. + * + * @param indexName the name of the index to be created + * @param indexType the IndexType of the index to be created + * @param table the table on which index to be created + * @param columns the columns on which index to be created + * @param properties the properties of the index to be created + * @throws IndexAlreadyExistsException If the index already exists (optional) + * @throws UnsupportedOperationException If create index is not a supported operation + */ + void createIndex(String indexName, Review comment: This is up to the data source implementation. I think it makes more sense at file level (each data file has an index file). -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
