wuchong commented on a change in pull request #8109: [FLINK-12017][table-planner-blink] Support translation from Rank/Deduplicate to StreamTransformation URL: https://github.com/apache/flink/pull/8109#discussion_r275106594
########## File path: flink-table/flink-table-runtime-blink/src/main/java/org/apache/flink/table/runtime/rank/RetractRankFunction.java ########## @@ -0,0 +1,250 @@ +/* + * 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.flink.table.runtime.rank; + +import org.apache.flink.api.common.state.MapState; +import org.apache.flink.api.common.state.MapStateDescriptor; +import org.apache.flink.api.common.state.ValueState; +import org.apache.flink.api.common.state.ValueStateDescriptor; +import org.apache.flink.api.common.typeinfo.BasicTypeInfo; +import org.apache.flink.api.java.typeutils.ListTypeInfo; +import org.apache.flink.configuration.Configuration; +import org.apache.flink.table.dataformat.BaseRow; +import org.apache.flink.table.dataformat.util.BaseRowUtil; +import org.apache.flink.table.generated.GeneratedRecordComparator; +import org.apache.flink.table.generated.GeneratedRecordEqualiser; +import org.apache.flink.table.runtime.keyselector.BaseRowKeySelector; +import org.apache.flink.table.typeutils.BaseRowTypeInfo; +import org.apache.flink.table.typeutils.SortedMapTypeInfo; +import org.apache.flink.util.Collector; + +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.util.ArrayList; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.SortedMap; +import java.util.TreeMap; + +/** + * RetractRankFunction's input stream could contain append record, update record, delete record. + */ +public class RetractRankFunction extends AbstractRankFunction { + + private static final long serialVersionUID = 1365312180599454479L; + + private static final Logger LOG = LoggerFactory.getLogger(RetractRankFunction.class); + + // Message to indicate the state is cleared because of ttl restriction. The message could be used to output to log. + private static final String STATE_CLEARED_WARN_MSG = "The state is cleared because of state ttl. " + + "This will result in incorrect result. You can increase the state ttl to avoid this."; + + private final BaseRowTypeInfo sortKeyType; + + // flag to skip records with non-exist error instead to fail, true by default. + private final boolean lenient = true; + + // a map state stores mapping from sort key to records list + private transient MapState<BaseRow, List<BaseRow>> dataState; + + // a sorted map stores mapping from sort key to records count + private transient ValueState<SortedMap<BaseRow, Long>> treeMap; + + public RetractRankFunction(long minRetentionTime, long maxRetentionTime, BaseRowTypeInfo inputRowType, + GeneratedRecordComparator generatedRecordComparator, BaseRowKeySelector sortKeySelector, + RankType rankType, RankRange rankRange, GeneratedRecordEqualiser generatedEqualiser, + boolean generateRetraction, boolean outputRankNumber) { + super(minRetentionTime, maxRetentionTime, inputRowType, generatedRecordComparator, sortKeySelector, rankType, + rankRange, generatedEqualiser, generateRetraction, outputRankNumber); + this.sortKeyType = sortKeySelector.getProducedType(); + } + + @Override + public void open(Configuration parameters) throws Exception { + super.open(parameters); + ListTypeInfo<BaseRow> valueTypeInfo = new ListTypeInfo<>(inputRowType); + MapStateDescriptor<BaseRow, List<BaseRow>> mapStateDescriptor = new MapStateDescriptor( + "data-state", sortKeyType, valueTypeInfo); + dataState = getRuntimeContext().getMapState(mapStateDescriptor); + + ValueStateDescriptor<SortedMap<BaseRow, Long>> valueStateDescriptor = new ValueStateDescriptor( Review comment: ```suggestion ValueStateDescriptor<SortedMap<BaseRow, Long>> valueStateDescriptor = new ValueStateDescriptor<>( ``` ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
