Hive ORC數據格式的MapReduce讀寫

1，mr代碼如下

package com.test.hadoop;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
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.TypeDescription;
import org.apache.orc.mapred.OrcStruct;
import org.apache.orc.mapreduce.OrcInputFormat;
import org.apache.orc.mapreduce.OrcOutputFormat;

public class ORCSample {

	public static class ORCMapper extends
			Mapper<NullWritable, OrcStruct, Text, Text> {
		public void map(NullWritable key, OrcStruct value, Context output)
				throws IOException, InterruptedException {
			output.write((Text) value.getFieldValue(1),
					(Text) value.getFieldValue(2));
		}
	}

	public static class ORCReducer extends
			Reducer<Text, Text, NullWritable, OrcStruct> {
		private TypeDescription schema = TypeDescription
				.fromString("struct<name:string,mobile:string>");
		private OrcStruct pair = (OrcStruct) OrcStruct.createValue(schema);

		private final NullWritable nw = NullWritable.get();

		public void reduce(Text key, Iterable<Text> values, Context output)
				throws IOException, InterruptedException {
			for (Text val : values) {
				pair.setFieldValue(0, key);
				pair.setFieldValue(1, val);
				output.write(nw, pair);
			}
		}
	}

	public static void main(String args[]) throws Exception {

		Configuration conf = new Configuration();
		conf.set("orc.mapred.output.schema","struct<name:string,mobile:string>");
		Job job = Job.getInstance(conf, "ORC Test");
		job.setJarByClass(ORCSample.class);
		job.setMapperClass(ORCMapper.class);
		job.setReducerClass(ORCReducer.class);
		job.setInputFormatClass(OrcInputFormat.class);
		job.setOutputFormatClass(OrcOutputFormat.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		job.setOutputKeyClass(NullWritable.class);
		job.setOutputValueClass(OrcStruct.class);
		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}
}

2，pom.xml中添加依賴（基於hadoop2.7.1）

<dependencies>
  <dependency>
    <groupId>org.apache.orc</groupId>
    <artifactId>orc-mapreduce</artifactId>
    <version>1.1.0</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-mapreduce-client-core</artifactId>
    <version>2.7.1</version>
  </dependency>
</dependencies>

3，創建表，在 t_test_orc中添加3行數據。

CREATE  TABLE `t_test_orc`(
  `siteid` string, 
  `name` string, 
  `mobile` string)
 stored as orc

CREATE TABLE `t_test_orc_new`(
  `name` string, 
  `mobile` string)
ROW FORMAT SERDE 
  'org.apache.hadoop.hive.ql.io.orc.OrcSerde' 
STORED AS INPUTFORMAT 
  'org.apache.hadoop.hive.ql.io.orc.OrcInputFormat' 
OUTPUTFORMAT 
  'org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat'
LOCATION
  'hdfs://namenode:9000/user/testorc3'

4，打包運行

hadoop jar MRTest-1.0-jar-with-dependencies.jar com.test.hadoop.ORCSample /hive/warehouse/mytest.db/t_test_orc /user/testorc3

5，完成後可以用hive --orcfiledump -d 查看執行結果

並且進入hive 查詢orc格式的 t_test_orc_new表也可以看到數據

更多信息可以參考https://orc.apache.org/