wombatu-kun commented on code in PR #18375: URL: https://github.com/apache/hudi/pull/18375#discussion_r3036741339
########## hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/realtime/HoodieLanceRealtimeInputFormat.java: ########## @@ -0,0 +1,100 @@ +/* + * 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.realtime; + +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.ValidationUtils; +import org.apache.hudi.hadoop.HoodieLanceInputFormat; +import org.apache.hudi.hadoop.UseFileSplitsFromInputFormat; +import org.apache.hudi.hadoop.UseRecordReaderFromInputFormat; +import org.apache.hudi.hadoop.utils.HoodieInputFormatUtils; +import org.apache.hudi.hadoop.utils.HoodieRealtimeInputFormatUtils; + +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hive.serde2.ColumnProjectionUtils; +import org.apache.hadoop.io.ArrayWritable; +import org.apache.hadoop.io.NullWritable; +import org.apache.hadoop.mapred.InputSplit; +import org.apache.hadoop.mapred.JobConf; +import org.apache.hadoop.mapred.RecordReader; +import org.apache.hadoop.mapred.Reporter; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; + +/** + * HoodieRealtimeInputFormat for HUDI datasets which store data in Lance base file format. + */ +@UseRecordReaderFromInputFormat +@UseFileSplitsFromInputFormat +public class HoodieLanceRealtimeInputFormat extends HoodieMergeOnReadTableInputFormat { + + private static final Logger LOG = LoggerFactory.getLogger(HoodieLanceRealtimeInputFormat.class); + + // NOTE: We're only using {@code HoodieLanceInputFormat} to compose {@code RecordReader} + private final HoodieLanceInputFormat lanceInputFormat = new HoodieLanceInputFormat(); + + @Override + public RecordReader<NullWritable, ArrayWritable> getRecordReader(final InputSplit split, final JobConf jobConf, + final Reporter reporter) throws IOException { + // Hive on Spark invokes multiple getRecordReaders from different threads in the same spark task (and hence the + // same JVM) unlike Hive on MR. Due to this, accesses to JobConf, which is shared across all threads, is at the + // risk of experiencing race conditions. Hence, we synchronize on the JobConf object here. There is negligible + // latency incurred here due to the synchronization since get record reader is called once per spilt before the + // actual heavy lifting of reading the parquet files happen. + if (jobConf.get(HoodieInputFormatUtils.HOODIE_READ_COLUMNS_PROP) == null) { Review Comment: fixed -- 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]
