package com.hbase;
import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.mapreduce.TableOutputFormat;
import org.apache.hadoop.hbase.util.Bytes;
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 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.input.TextInputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class WordCount extends Configured implements Tool {
public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
public void map(LongWritable key, Text value, Context context) {
String[] strs = value.toString().split(" ");
for(String str:strs) {
try {
context.write(new Text(str), new IntWritable(1));
} catch (IOException e) {
e.printStackTrace();
} catch (InterruptedException e) {
e.printStackTrace();
}
}
}
}
public static class Reduce extends Reducer<Text, IntWritable, NullWritable, Put> {
public void reduce(Text key, Iterable<IntWritable> values, Context context) {
int sum = 0;
Iterator<IntWritable> it = values.iterator();
while(it.hasNext()) {
sum = sum + it.next().get();
}
try {
//key作为rowkey
Put put = new Put(Bytes.toBytes(key.toString()));
//f1作为列族,c1作为列标识符,sum作为value
put.add(Bytes.toBytes("f1"), Bytes.toBytes("c1"), Bytes.toBytes(sum));
context.write(NullWritable.get(), put);
} catch (IOException e) {
e.printStackTrace();
} catch (InterruptedException e) {
e.printStackTrace();
}
}
}
public int run(String[] args) throws Exception {
Configuration conf = this.getConf();
String OUTPUT_TABLE = "hbase.mapred.outputtable";
conf.set(OUTPUT_TABLE, "wordcount");
//以下语句直接赋值会报错!!!在编译的时候就报错!!!
//conf.set(TableOutputFormat.OUTPUT_TABLE, "wordcount");
//在hbase创建表,列族为f1
HbaseApi.create("wordcount", "f1");
Job job = new Job(conf);
job.setJarByClass(WordCount.class);
job.setJobName(WordCount.class.getSimpleName());
String path = "hdfs://grid131:9000/stu.txt";
FileInputFormat.addInputPath(job, new Path(path));
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TableOutputFormat.class);
job.setMapperClass(Map.class);
//job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.waitForCompletion(true);
return job.isSuccessful()?0:1;
}
public static void main(String[] args) throws Exception {
int exit = ToolRunner.run(new WordCount(), args);
System.exit(exit);
}
}
转载于:https://my.oschina.net/sniperLi/blog/350469