eskabetxe commented on code in PR #209: URL: https://github.com/apache/flink-connector-jdbc/pull/209#discussion_r3785469134
########## flink-connector-jdbc-core/src/main/java/org/apache/flink/connector/jdbc/core/datastream/source/enumerator/splitter/snapshot/TableSplitterEnumerator.java: ########## @@ -0,0 +1,212 @@ +/* + * 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.jdbc.core.datastream.source.enumerator.splitter.snapshot; + +import org.apache.flink.annotation.PublicEvolving; +import org.apache.flink.connector.jdbc.core.datastream.source.enumerator.splitter.SplitterEnumerator; +import org.apache.flink.connector.jdbc.core.datastream.source.enumerator.splitter.snapshot.domain.TableBounds; +import org.apache.flink.connector.jdbc.core.datastream.source.enumerator.splitter.snapshot.domain.TableColumn; +import org.apache.flink.connector.jdbc.core.datastream.source.enumerator.splitter.snapshot.domain.TableId; +import org.apache.flink.connector.jdbc.core.datastream.source.split.CheckpointedOffset; +import org.apache.flink.connector.jdbc.core.datastream.source.split.JdbcSourceSplit; +import org.apache.flink.connector.jdbc.datasource.connections.JdbcConnectionProvider; + +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.Serializable; +import java.util.ArrayList; +import java.util.Comparator; +import java.util.LinkedHashSet; +import java.util.List; +import java.util.Objects; +import java.util.Optional; +import java.util.Set; +import java.util.stream.Collectors; + +/** + * An implementation of {@link SplitterEnumerator} that splits a table into multiple splits based on + * the primary key column and a specified chunk size. + */ +@PublicEvolving +public class TableSplitterEnumerator extends AsyncSnapshotSplitterEnumerator<TableBounds> { + private final Logger log = LoggerFactory.getLogger(TableSplitterEnumerator.class); + + private final TableId tableId; + private final Set<String> columnNames; + private final int chunkSize; + + private TableColumn tablePrimaryKey; + private final Set<String> lineageQueries; + + private TableBounds tableMinMax; + private Object currentLowerBound; + private boolean boundsInitialized; + + protected TableSplitterEnumerator(TableId tableId, Set<String> columnNames, int chunkSize) { Review Comment: The overloaded constructor won't compile: Set<String> and Set<TableColumn> erase to the same (TableId, Set, int) signature. But we are calling two times per table not partitioned, I will say the cost is marginal.. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
