connector/read/SupportsPushDownFilters.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.sources.Filter;
0022
0023 /**
0024  * A mix-in interface for {@link ScanBuilder}. Data sources can implement this interface to
0025  * push down filters to the data source and reduce the size of the data to be read.
0026  *
0027  * @since 3.0.0
0028  */
0029 @Evolving
0030 public interface SupportsPushDownFilters extends ScanBuilder {
0031
0032   /**
0033    * Pushes down filters, and returns filters that need to be evaluated after scanning.
0034    * <p>
0035    * Rows should be returned from the data source if and only if all of the filters match. That is,
0036    * filters must be interpreted as ANDed together.
0037    */
0038   Filter[] pushFilters(Filter[] filters);
0039
0040   /**
0041    * Returns the filters that are pushed to the data source via {@link #pushFilters(Filter[])}.
0042    *
0043    * There are 3 kinds of filters:
0044    *  1. pushable filters which don't need to be evaluated again after scanning.
0045    *  2. pushable filters which still need to be evaluated after scanning, e.g. parquet
0046    *     row group filter.
0047    *  3. non-pushable filters.
0048    * Both case 1 and 2 should be considered as pushed filters and should be returned by this method.
0049    *
0050    * It's possible that there is no filters in the query and {@link #pushFilters(Filter[])}
0051    * is never called, empty array should be returned for this case.
0052    */
0053   Filter[] pushedFilters();
0054 }