connector/read/SupportsPushDownRequiredColumns.java

0001 /*
0002  * Licensed to the Apache Software Foundation (ASF) under one or more
0003  * contributor license agreements.  See the NOTICE file distributed with
0004  * this work for additional information regarding copyright ownership.
0005  * The ASF licenses this file to You under the Apache License, Version 2.0
0006  * (the "License"); you may not use this file except in compliance with
0007  * the License.  You may obtain a copy of the License at
0008  *
0009  *    http://www.apache.org/licenses/LICENSE-2.0
0010  *
0011  * Unless required by applicable law or agreed to in writing, software
0012  * distributed under the License is distributed on an "AS IS" BASIS,
0013  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014  * See the License for the specific language governing permissions and
0015  * limitations under the License.
0016  */
0017
0018 package org.apache.spark.sql.connector.read;
0019
0020 import org.apache.spark.annotation.Evolving;
0021 import org.apache.spark.sql.types.StructType;
0022
0023 /**
0024  * A mix-in interface for {@link ScanBuilder}. Data sources can implement this
0025  * interface to push down required columns to the data source and only read these columns during
0026  * scan to reduce the size of the data to be read.
0027  *
0028  * @since 3.0.0
0029  */
0030 @Evolving
0031 public interface SupportsPushDownRequiredColumns extends ScanBuilder {
0032
0033   /**
0034    * Applies column pruning w.r.t. the given requiredSchema.
0035    *
0036    * Implementation should try its best to prune the unnecessary columns or nested fields, but it's
0037    * also OK to do the pruning partially, e.g., a data source may not be able to prune nested
0038    * fields, and only prune top-level columns.
0039    *
0040    * Note that, {@link Scan#readSchema()} implementation should take care of the column
0041    * pruning applied here.
0042    */
0043   void pruneColumns(StructType requiredSchema);
0044 }