flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] [flink] wuchong commented on a change in pull request #8109: [FLINK-12017][table-planner-blink] Support translation from Rank/Deduplicate to StreamTransformation
Date Fri, 12 Apr 2019 15:20:24 GMT
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_r274952010
 
 

 ##########
 File path: flink-table/flink-table-runtime-blink/src/main/java/org/apache/flink/table/runtime/deduplicate/DeduplicateFunction.java
 ##########
 @@ -0,0 +1,99 @@
+/*
+ * 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.deduplicate;
+
+import org.apache.flink.api.common.state.ValueState;
+import org.apache.flink.api.common.state.ValueStateDescriptor;
+import org.apache.flink.configuration.Configuration;
+import org.apache.flink.table.dataformat.BaseRow;
+import org.apache.flink.table.generated.GeneratedRecordEqualiser;
+import org.apache.flink.table.generated.RecordEqualiser;
+import org.apache.flink.table.runtime.functions.KeyedProcessFunctionWithCleanupState;
+import org.apache.flink.table.typeutils.BaseRowTypeInfo;
+import org.apache.flink.util.Collector;
+
+import static org.apache.flink.table.runtime.deduplicate.DeduplicateFunctionHelper.processFirstRow;
+import static org.apache.flink.table.runtime.deduplicate.DeduplicateFunctionHelper.processLastRow;
+
+/**
+ * This function is used to deduplicate on keys and keeps only first row or last row.
+ */
+public class DeduplicateFunction
+		extends KeyedProcessFunctionWithCleanupState<BaseRow, BaseRow, BaseRow> {
+
+	private static final long serialVersionUID = 4950071982706870944L;
+
+	private final BaseRowTypeInfo rowTypeInfo;
+	private final boolean generateRetraction;
+	private final boolean keepLastRow;
+	private ValueState<BaseRow> pkRow;
+	private GeneratedRecordEqualiser generatedEqualiser;
+	private transient RecordEqualiser equaliser;
+
+	public DeduplicateFunction(long minRetentionTime, long maxRetentionTime, BaseRowTypeInfo
rowTypeInfo,
+			boolean generateRetraction, boolean keepLastRow, GeneratedRecordEqualiser generatedEqualiser)
{
+		super(minRetentionTime, maxRetentionTime);
+		this.rowTypeInfo = rowTypeInfo;
+		this.generateRetraction = generateRetraction;
+		this.keepLastRow = keepLastRow;
+		this.generatedEqualiser = generatedEqualiser;
+	}
+
+	@Override
+	public void open(Configuration configure) throws Exception {
+		super.open(configure);
+		String stateName = keepLastRow ? "DeduplicateFunctionCleanupTime" : "DeduplicateFunctionCleanupTime";
+		initCleanupTimeState(stateName);
+		ValueStateDescriptor rowStateDesc = new ValueStateDescriptor("rowState", rowTypeInfo);
 
 Review comment:
   Yes. I think we should only store the PK in state here. 
   
   If we only store PK, the ideal state schema should be `ValueState<Boolean>`, but
this can't share the same state with LastRow mode. Maybe we need to separate the implementation
for firstRow and lastRow.

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

Mime
View raw message