szehon-ho commented on code in PR #7029: URL: https://github.com/apache/iceberg/pull/7029#discussion_r1147883549
########## spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/AbstractFileRewriteCoordinator.java: ########## @@ -0,0 +1,89 @@ +/* + * 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.iceberg.spark; + +import java.util.Map; +import java.util.Set; +import java.util.stream.Collectors; +import org.apache.iceberg.ContentFile; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableOperations; +import org.apache.iceberg.exceptions.ValidationException; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.util.Pair; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public abstract class AbstractFileRewriteCoordinator<F extends ContentFile<F>> { + + private static final Logger LOG = LoggerFactory.getLogger(FileRewriteCoordinator.class); + + private final Map<Pair<String, String>, Set<F>> resultMap = Maps.newConcurrentMap(); + + /** + * Called to persist the output of a rewrite action for a specific group. Since the write is done + * via a Spark Datasource, we have to propagate the result through this side-effect call. + * + * @param table table where the rewrite is occurring + * @param fileSetID the id used to identify the source set of files being rewritten + * @param newDataFiles the new files which have been written + */ + public void stageRewrite(Table table, String fileSetID, Set<F> newDataFiles) { + LOG.debug( + "Staging the output for {} - fileset {} with {} files", + table.name(), + fileSetID, + newDataFiles.size()); + Pair<String, String> id = toID(table, fileSetID); + resultMap.put(id, newDataFiles); + } + + public Set<F> fetchNewDataFiles(Table table, String fileSetID) { + Pair<String, String> id = toID(table, fileSetID); + Set<F> result = resultMap.get(id); + ValidationException.check( + result != null, "No results for rewrite of file set %s in table %s", fileSetID, table); + + return result; + } + + public void clearRewrite(Table table, String fileSetID) { Review Comment: Done -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
