1、Hive支持
创建表时指定orc格式即可：
create table tmp.orc_test(id bigint, name string, age int) stored as orc TBLPROPERTIES('orc.compress'='SNAPPY')
压缩格式有"SNAPPY"和 "ZLIB"两种，需要哪种格式指定即可。
2、SPARK支持
Spark读：
df = spark.read.orc("/tmp/test/orc_data") # 读出来的数据是一个dataframe
Spark写：
df.write.format("orc").save("/tmp/test/orc_data2")
3、Hadoop Streaming支持
3.1、读orc文件，输出text
hadoop jar /usr/local/hadoop-2.7.0//share/hadoop/tools/lib/hadoop-streaming-2.7.0.jar \
-libjars /usr/local/hive-1.2.0/lib/hive-exec-1.2.0-SNAPSHOT.jar \
-mapper /bin/cat -reducer /bin/cat \
-input /tmp/test/orc_test1 \
-output /tmp/test/orc_streaming_test3 \
-inputformat org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
返回的数据：
null {"name":"123","age":"456"}
null {"name":"456","age":"789"}
3.2、读orc文件，写orc文件：
hadoop jar /usr/local/hadoop-2.7.0//share/hadoop/tools/lib/hadoop-streaming-2.7.0.jar \
-libjars orc_maprd_test.jar \
-D orc.mapred.output.schema="struct" \
-input /tmp/test/orc_streaming_test \
-output /tmp/test/orc_streaming_test2 \
-inputformat org.apache.orc.mapred.OrcInputFormat \
-outputformat org.apache.orc.mapred.OrcOutputFormat \
-mapper is.orc.MyMapper -reducer is.orc.MyReducer
pom.xml
org.apache.orc
orc-mapreduce
1.1.0
org.apache.hadoop
hadoop-mapreduce-client-core
2.7.0
mapper:
package is.orc;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
import org.apache.orc.mapred.OrcStruct;
import java.io.IOException;
import java.util.Random;
class MyMapper implements Mapper {
Random random = new Random();
public void close() { }
public void map(NullWritable nullWritable, OrcStruct orcStruct, OutputCollector outputCollector, Reporter reporter) throws IOException {
StringBuffer str = new StringBuffer();
str.append(orcStruct.getFieldValue(0).toString() + "\t");
str.append(orcStruct.getFieldValue(1).toString() + "\t");
str.append(orcStruct.getFieldValue(2).toString() + "\t");
str.append(orcStruct.getFieldValue(3).toString() );
//不知道为什么Mapper的OutputKey只能用LongWritable,用随机数生成一个key，防止读orc文件后单reduce的情况
LongWritable key = new LongWritable(random.nextInt(5));
outputCollector.collect(key, new Text(str.toString()));
}
public void configure(JobConf jobConf) {
jobConf.setMapOutputKeyClass(Writable.class);
jobConf.setMapOutputValueClass(Text.class);
}
}
Reducer:
package is.orc;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.orc.TypeDescription;
import org.apache.orc.mapred.OrcStruct;
import java.io.IOException;
import java.util.Iterator;
class MyReducer implements Reducer {
//要创建的ORC文件中的字段类型
private TypeDescription schema = TypeDescription.fromString(
"struct"
);
private OrcStruct pair = (OrcStruct)OrcStruct.createValue(schema);
public void reduce(LongWritable text, Iterator iterator, OutputCollector outputCollector, Reporter reporter) throws IOException {
while (iterator.hasNext()) {
String[] lineSplit = iterator.next().toString().split("\t");
pair.setFieldValue("name",new Text(lineSplit[0]));
pair.setFieldValue("sex",new Text(lineSplit[1]));
pair.setFieldValue("age",new Text(lineSplit[2]));
pair.setFieldValue("id",new Text(lineSplit[3]));
break;
}
outputCollector.collect(NullWritable.get(),pair);
}
public void close() throws IOException {
}
public void configure(JobConf jobConf) {
}
}
4、MapReduce支持
读orc的mapper：
package is.orc;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.orc.mapred.OrcStruct;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class OrcFileReadMapper extends Mapper {
private Text outputKey = new Text();
@Override
protected void map(NullWritable key, OrcStruct value, Context context) throws IOException, InterruptedException {
StringBuffer sb= new StringBuffer();
if (value.getFieldValue(0) == null){
sb.append("-1\t");
}else{
sb.append(value.getFieldValue(0).toString() + "\t"); //通过下标索引获取数据
}
sb.append(value.getFieldValue(1).toString()+ "\t");
sb.append(value.getFieldValue(2).toString()+ "\t");
sb.append(value.getFieldValue(3).toString()); //也可以通过字段名获取数据
outputKey = new Text(sb.toString());
context.write(outputKey, NullWritable.get());
}
}
写orc的reduer：
package is.orc;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import java.io.IOException;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.orc.TypeDescription;
import org.apache.orc.mapred.OrcStruct;
import java.io.IOException;
public class OrcFileWriteReducer extends Reducer {
//要创建的ORC文件中的字段类型
private TypeDescription schema = TypeDescription.fromString(
"struct"
);
private OrcStruct pair = (OrcStruct)OrcStruct.createValue(schema);
@Override
protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
String line = key.toString();
String[] lineSplit = line.trim().split("\t");
pair.setFieldValue("id",new Text(lineSplit[0]));
pair.setFieldValue("name",new Text(lineSplit[1]));
pair.setFieldValue("sex",new Text(lineSplit[2]));
pair.setFieldValue("age",new Text(lineSplit[3]));
context.write(NullWritable.get(),pair);
}
}
job配置：
package is.orc;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.orc.mapred.OrcStruct;
import org.apache.orc.mapreduce.OrcInputFormat;
import org.apache.orc.mapreduce.OrcOutputFormat;
import java.io.IOException;
/**
* @author lyf
* @since 2018/06/16
*/
public class OrcFileWriteJob extends Configured implements Tool {
public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = getConf();
conf.set("orc.mapred.output.schema","struct");
String input = "/dws/dd_read_d_v2/dt=20180809/000000_0";
String output = "/tmp/test/test_mr_orc";
Job job = Job.getInstance(conf);
job.setJarByClass(OrcFileWriteJob.class);
job.setMapperClass(OrcFileReadMapper.class);
job.setReducerClass(OrcFileWriteReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(NullWritable.class);
job.setOutputKeyClass(NullWritable.class);
job.setOutputValueClass(OrcStruct.class);
job.setInputFormatClass(OrcInputFormat.class);
job.setOutputFormatClass(OrcOutputFormat.class);
FileInputFormat.addInputPath(job,new Path(input));
FileOutputFormat.setOutputPath(job,new Path(output));
boolean rt = job.waitForCompletion(true);
return rt?0:1;
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
int retnum = ToolRunner.run(conf,new OrcFileWriteJob(),args);
}
}