yabola commented on code in PR #1023: URL: https://github.com/apache/parquet-mr/pull/1023#discussion_r1109441802
########## parquet-hadoop/src/main/java/org/apache/parquet/filter2/compat/PredicateEvaluation.java: ########## @@ -0,0 +1,105 @@ +/* + * 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.parquet.filter2.compat; + +import java.util.ArrayList; +import java.util.Arrays; +import java.util.List; + +import org.apache.parquet.filter2.predicate.FilterPredicate; +import org.apache.parquet.filter2.predicate.Operators; + +/** + * Used in Filters to mark whether we should DROP the block if data matches the condition. + * If we cannot decide whether the block matches, it will be always safe to return BLOCK_MIGHT_MATCH. + * We use Boolean Object here to distinguish the value type, please do not modify it. + */ +public class PredicateEvaluation { + /* The block might match, but we cannot decide yet, will check in the other filters. */ + public static final Boolean BLOCK_MIGHT_MATCH = new Boolean(false); + /* The block can match for sure. */ + public static final Boolean BLOCK_MUST_MATCH = new Boolean(false); + /* The block can't match for sure */ + public static final Boolean BLOCK_CANNOT_MATCH = new Boolean(true); + + public static Boolean evaluateAnd(Operators.And and, FilterPredicate.Visitor<Boolean> predicate) { + Boolean left = and.getLeft().accept(predicate); + if (left == BLOCK_CANNOT_MATCH) { + // seems unintuitive to put an || not an && here but we can + // drop a chunk of records if we know that either the left or + // the right predicate agrees that no matter what we don't + // need this chunk. + return BLOCK_CANNOT_MATCH; + } + Boolean right = and.getRight().accept(predicate); + if (right == BLOCK_CANNOT_MATCH) { + return BLOCK_CANNOT_MATCH; + } else if (left == BLOCK_MUST_MATCH && right == BLOCK_MUST_MATCH) { Review Comment: if left is `BLOCK_MUST_MATCH` , right is `BLOCK_MIGHT_MATCH` , left & right should be `BLOCK_MIGHT_MATCH`. Because in the next filter may right may be `BLOCK_CANNOT_MATCH ` and we should drop it. And I add new [UT](https://github.com/apache/parquet-mr/pull/1023/files#diff-8915e6fa23018e02c2e79a3f6cc5078a8882f8031022dbdde217fe9bf1d908afR143) In `StatisticsFilter` left might match (but can't match in DictionaryFilter), right must match -> return might match in StatisticsFilter, return can't match in DictionaryFilter -- 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: dev-unsubscr...@parquet.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
