Aitozi commented on code in PR #21257: URL: https://github.com/apache/flink/pull/21257#discussion_r1023978296
########## flink-connectors/flink-connector-files/src/main/java/org/apache/flink/connector/file/table/batch/compact/BatchPartitionCommitter.java: ########## @@ -0,0 +1,141 @@ +/* + * 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.connector.file.table.batch.compact; + +import org.apache.flink.connector.file.table.FileSystemCommitter; +import org.apache.flink.connector.file.table.FileSystemFactory; +import org.apache.flink.connector.file.table.PartitionCommitPolicy; +import org.apache.flink.connector.file.table.PartitionCommitPolicyFactory; +import org.apache.flink.connector.file.table.TableMetaStoreFactory; +import org.apache.flink.connector.file.table.stream.compact.CompactMessages.CompactOutput; +import org.apache.flink.core.fs.Path; +import org.apache.flink.runtime.state.StateInitializationContext; +import org.apache.flink.streaming.api.operators.AbstractStreamOperator; +import org.apache.flink.streaming.api.operators.OneInputStreamOperator; +import org.apache.flink.streaming.runtime.streamrecord.StreamRecord; +import org.apache.flink.table.api.TableException; +import org.apache.flink.table.catalog.ObjectIdentifier; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Collections; +import java.util.HashMap; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; + +/** + * Committer operator for partition in batch mode. This is the single (non-parallel) task. It + * collects all the partition information including partition and written files send from upstream. + */ +public class BatchPartitionCommitter extends AbstractStreamOperator<Void> + implements OneInputStreamOperator<CompactOutput, Void> { + + private final FileSystemFactory fsFactory; + private final TableMetaStoreFactory msFactory; + private final PartitionCommitPolicyFactory partitionCommitPolicyFactory; + private final Path tmpPath; + private final boolean overwrite; + private final boolean isToLocal; + private final String[] partitionColumns; + private final LinkedHashMap<String, String> staticPartitions; + private final ObjectIdentifier identifier; + + private transient Map<String, List<Path>> partitionsFiles; + + public BatchPartitionCommitter( + FileSystemFactory fsFactory, + TableMetaStoreFactory msFactory, + boolean overwrite, + boolean isToLocal, + Path tmpPath, + String[] partitionColumns, + LinkedHashMap<String, String> staticPartitions, + ObjectIdentifier identifier, + PartitionCommitPolicyFactory partitionCommitPolicyFactory) { + this.fsFactory = fsFactory; + this.msFactory = msFactory; + this.partitionCommitPolicyFactory = partitionCommitPolicyFactory; + this.tmpPath = tmpPath; + this.identifier = identifier; + this.overwrite = overwrite; + this.isToLocal = isToLocal; + this.partitionColumns = partitionColumns; + this.staticPartitions = staticPartitions; + } + + @Override + public void initializeState(StateInitializationContext context) throws Exception { + super.initializeState(context); + partitionsFiles = new HashMap<>(); Review Comment: I think this should be put to `open()` -- 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: issues-unsubscr...@flink.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
