SourabhBadhya commented on code in PR #3801: URL: https://github.com/apache/hive/pull/3801#discussion_r1064290065
########## ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/OrcFileMerger.java: ########## @@ -0,0 +1,114 @@ +/* + * 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.hadoop.hive.ql.txn.compactor; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; +import org.apache.hadoop.hive.ql.io.orc.CompressionKind; +import org.apache.hadoop.hive.ql.io.orc.OrcFile; +import org.apache.hadoop.hive.ql.io.orc.Reader; +import org.apache.hadoop.hive.ql.io.orc.RecordReader; +import org.apache.hadoop.hive.ql.io.orc.Writer; +import org.apache.hadoop.fs.Path; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.util.List; + +/** + * Class to support fast merging of ORC files. + */ +public class OrcFileMerger { + + private final Configuration conf; + private static final Logger LOG = LoggerFactory.getLogger(OrcFileMerger.class); + + public OrcFileMerger(Configuration conf) { + this.conf = conf; + } + + /** + * Merge orc files into a single file + * @param files list of orc file paths to be merged + * @param outPath the path of output orc file + * @throws IOException error happened during file operations + */ + public void mergeFiles(List<Reader> readers, Path outPath) throws IOException { + Writer writer = null; + try { + for (Reader reader : readers) { + if (writer == null) { + writer = setupWriter(reader, outPath); + } + VectorizedRowBatch batch = reader.getSchema().createRowBatchV2(); + RecordReader rows = reader.rows(); + while (rows.nextBatch(batch)) { + if (batch != null) { + writer.addRowBatch(batch); + } + } + rows.close(); + } + } finally { + if (writer != null) { + writer.close(); + } + } Review Comment: If we create a writer irrespective of number of readers in try with resources block then a writer will always be created and this may create a empty file (if readers are not present). ########## ql/src/java/org/apache/hadoop/hive/ql/txn/compactor/OrcFileMerger.java: ########## @@ -0,0 +1,114 @@ +/* + * 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.hadoop.hive.ql.txn.compactor; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; +import org.apache.hadoop.hive.ql.io.orc.CompressionKind; +import org.apache.hadoop.hive.ql.io.orc.OrcFile; +import org.apache.hadoop.hive.ql.io.orc.Reader; +import org.apache.hadoop.hive.ql.io.orc.RecordReader; +import org.apache.hadoop.hive.ql.io.orc.Writer; +import org.apache.hadoop.fs.Path; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.IOException; +import java.util.List; + +/** + * Class to support fast merging of ORC files. + */ +public class OrcFileMerger { + + private final Configuration conf; + private static final Logger LOG = LoggerFactory.getLogger(OrcFileMerger.class); + + public OrcFileMerger(Configuration conf) { + this.conf = conf; + } + + /** + * Merge orc files into a single file + * @param files list of orc file paths to be merged + * @param outPath the path of output orc file + * @throws IOException error happened during file operations + */ + public void mergeFiles(List<Reader> readers, Path outPath) throws IOException { + Writer writer = null; + try { + for (Reader reader : readers) { + if (writer == null) { + writer = setupWriter(reader, outPath); + } + VectorizedRowBatch batch = reader.getSchema().createRowBatchV2(); + RecordReader rows = reader.rows(); + while (rows.nextBatch(batch)) { + if (batch != null) { + writer.addRowBatch(batch); + } + } + rows.close(); + } + } finally { + if (writer != null) { + writer.close(); + } + } Review Comment: If we create a writer irrespective of number of readers in try with resources block then a writer will always be created and this may create an empty file (if readers are not present). -- 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: gitbox-unsubscr...@hive.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
