[GitHub] [orc] dongjoon-hyun commented on a change in pull request #897: ORC-715: Add MapReduce test cases

[GitBox <gi...@apache.org>]

dongjoon-hyun commented on a change in pull request #897:
URL: https://github.com/apache/orc/pull/897#discussion_r702471067



##########
File path: java/mapreduce/src/test/org/apache/orc/mapreduce/TestMrUnit.java
##########
@@ -0,0 +1,253 @@
+/*
+ * 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.orc.mapreduce;
+
+import org.apache.hadoop.fs.FileStatus;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.StructColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch;
+import org.apache.hadoop.io.DataInputBuffer;
+import org.apache.hadoop.io.NullWritable;
+import org.apache.hadoop.io.RawComparator;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.JobConfigurable;
+import org.apache.hadoop.mapreduce.Job;
+import org.apache.hadoop.mapreduce.Mapper;
+import org.apache.hadoop.mapreduce.Reducer;
+import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
+import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
+import org.apache.orc.OrcConf;
+import org.apache.orc.OrcFile;
+import org.apache.orc.Reader;
+import org.apache.orc.RecordReader;
+import org.apache.orc.TypeDescription;
+import org.apache.orc.Writer;
+import org.apache.orc.mapred.OrcKey;
+import org.apache.orc.mapred.OrcStruct;
+import org.apache.orc.mapred.OrcValue;
+import org.junit.jupiter.api.Test;
+
+import java.io.File;
+import java.io.IOException;
+import java.nio.charset.StandardCharsets;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+public class TestMrUnit {
+
+  private static final File TEST_DIR = new File(
+      System.getProperty("test.build.data",
+          System.getProperty("java.io.tmpdir")), "TestMapReduce-mapreduce");
+  private static FileSystem FS;
+
+  private static final JobConf CONF = new JobConf();
+
+  private static final TypeDescription INPUT_SCHEMA = TypeDescription
+      .fromString("struct<one:struct<x:int,y:int>,two:struct<z:string>>");
+
+  private static final TypeDescription OUT_SCHEMA = TypeDescription
+      .fromString("struct<first:struct<x:int,y:int>,second:struct<z:string>>");
+
+  static {
+    OrcConf.MAPRED_SHUFFLE_KEY_SCHEMA.setString(CONF, "struct<x:int,y:int>");
+    OrcConf.MAPRED_SHUFFLE_VALUE_SCHEMA.setString(CONF, "struct<z:string>");
+    OrcConf.MAPRED_OUTPUT_SCHEMA.setString(CONF, OUT_SCHEMA.toString());
+    CONF.set("mapreduce.job.output.key.comparator.class", OrcKeyComparator.class.getName());

Review comment:
       Thank you for adding this. Could you add a comment referring ORC-964?




-- 
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: dev-unsubscribe@orc.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org