danny0405 commented on a change in pull request #3203: URL: https://github.com/apache/hudi/pull/3203#discussion_r728895613
########## File path: hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/RealtimeFileStatus.java ########## @@ -0,0 +1,90 @@ +/* + * 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.hudi.hadoop; + +import org.apache.hadoop.fs.FileStatus; +import org.apache.hadoop.fs.Path; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.List; + +public class RealtimeFileStatus extends FileStatus { Review comment: an -> a ########## File path: hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/utils/HoodieRealtimeInputFormatUtils.java ########## @@ -161,6 +162,51 @@ return rtSplits.toArray(new InputSplit[0]); } + // pick all incremental files and add them to rtSplits then filter out those files. + private static Map<Path, List<FileSplit>> filterOutIncrementalSplits( + List<FileSplit> fileSplitList, + List<InputSplit> rtSplits, + final Option<HoodieVirtualKeyInfo> finalHoodieVirtualKeyInfo) { + return fileSplitList.stream().filter(s -> { + // deal with incremental query. + try { + if (s instanceof BaseFileWithLogsSplit) { + BaseFileWithLogsSplit bs = (BaseFileWithLogsSplit)s; + if (bs.getBelongToIncrementalSplit()) { + rtSplits.add(new HoodieRealtimeFileSplit(bs, bs.getBasePath(), bs.getDeltaLogPaths(), bs.getMaxCommitTime(), finalHoodieVirtualKeyInfo)); + } + } else if (s instanceof RealtimeBootstrapBaseFileSplit) { + rtSplits.add(s); + } + } catch (IOException e) { + throw new HoodieIOException("Error creating hoodie real time split ", e); + } + // filter the snapshot split. + if (s instanceof RealtimeBootstrapBaseFileSplit) { + return false; + } else if ((s instanceof BaseFileWithLogsSplit) && ((BaseFileWithLogsSplit) s).getBelongToIncrementalSplit()) { Review comment: Yeah, we can actually abstract the handling of all kinds of splits into a separate method i guess. ########## File path: hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/PathWithBootstrapFileStatus.java ########## @@ -24,7 +24,7 @@ /** * Hacky Workaround !!! * With the base input format implementations in Hadoop/Hive, - * we need to encode additional information in Path to track matching external file. + * Encode additional information in Path to track matching external file. * Hence, this weird looking class which tracks an external file status Review comment: No need to change. -- 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]
