Hbase第五章 MapReduce操作HBase

容易遇到的坑：

　　当用mapReducer操作HBase时，运行jar包的过程中如果遇到 java.lang.NoClassDefFoundError 类似的错误时，一般是由于hadoop环境没有hbase相关的jar包，这时候需要修改hadoop_env.sh文件，在最后面添加一行:

HADOOP_CLASSPATH=/home/hadoop/apps/hbase/lib/*

实例演示：

　　pom.xml

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>cn.itcast.hbase</groupId>
    <artifactId>hbase</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <dependencies>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-client -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.4</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hbase/hbase-client -->
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>0.99.2</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hbase/hbase-server -->
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>1.4.0</version>
        </dependency>
    </dependencies>
</project>

　　HbaseWordCount.java

package cn.itcast.bigdata.mapreduce;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Mutation;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;

public class HbaseWordCount {
    private final static String tableName = "word";// 表名1
    private final static String colf = "content";// 列族
    private final static String col = "info";// 列
    private final static String tableName2 = "stat";// 表名2
    private final static IntWritable one = new IntWritable(1);
    private final static Text word = new Text();
    private static Configuration config;
    private static Connection connection;

    static class MyMapper extends TableMapper<Text, IntWritable> {

        @Override
        protected void map(ImmutableBytesWritable key, Result value,
                Mapper<ImmutableBytesWritable, Result, Text, IntWritable>.Context context)
                throws IOException, InterruptedException {
            // 获取一行数据中的colf：col
            // 表里面只有一个列族，所以我就直接获取每一行的值
            String words = Bytes.toString(value.getValue(Bytes.toBytes(colf), Bytes.toBytes(col)));
            // 按空格分割
            String itr[] = words.toString().split(" ");
            for (int i = 0; i < itr.length; i++) {
                word.set(itr[i]);
                context.write(word, one);
            }

        }

    }

    static class MyReducer extends TableReducer<Text, IntWritable, ImmutableBytesWritable> {
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values,
                Reducer<Text, IntWritable, ImmutableBytesWritable, Mutation>.Context context)
                throws IOException, InterruptedException {

            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            Put put = new Put(Bytes.toBytes(key.toString()));
            put.add(Bytes.toBytes(colf), Bytes.toBytes(col), Bytes.toBytes(String.valueOf(sum)));
            context.write(new ImmutableBytesWritable(Bytes.toBytes(key.toString())), put);
        }

    }

    // 初始化配置
    private static void init() throws IOException {
        config = HBaseConfiguration.create();
        // 配置zookeeper
        config.set("hbase.zookeeper.quorum", "hadoop2,hadoop3,hadoop4");
        config.set("hbase.zookeeper.property.clientPort", "2181");
        connection = ConnectionFactory.createConnection(config);
        CreateTable();
    }

    // 初始化hbase表
    private static void CreateTable() throws IOException {

        Admin admin = connection.getAdmin();
        // 删除表
        if (admin.tableExists(TableName.valueOf(tableName)) || admin.tableExists(TableName.valueOf(tableName2))) {
            System.out.println("table is already exists!");
            admin.disableTable(TableName.valueOf(tableName));
            admin.deleteTable(TableName.valueOf(tableName));
            admin.disableTable(TableName.valueOf(tableName2));
            admin.deleteTable(TableName.valueOf(tableName2));

        }
        // 创建表
        HTableDescriptor desc = new HTableDescriptor(TableName.valueOf(tableName));
        HColumnDescriptor family = new HColumnDescriptor(colf);
        desc.addFamily(family);
        admin.createTable(desc);

        HTableDescriptor desc2 = new HTableDescriptor(TableName.valueOf(tableName2));
        HColumnDescriptor family2 = new HColumnDescriptor(colf);
        desc2.addFamily(family2);
        admin.createTable(desc2);
        // 插入数据
        Table table = connection.getTable(TableName.valueOf(tableName));

        table.setAutoFlushTo(false);
        table.setWriteBufferSize(5);
        List<Put> lp = new ArrayList<Put>();
        Put p1 = new Put(Bytes.toBytes("1"));
        p1.add(colf.getBytes(), col.getBytes(), ("The Apache Hadoop software library is a framework").getBytes());
        lp.add(p1);

        Put p2 = new Put(Bytes.toBytes("2"));
        p2.add(colf.getBytes(), col.getBytes(),
                ("The common utilities that support the other Hadoop modules").getBytes());
        lp.add(p2);

        Put p3 = new Put(Bytes.toBytes("3"));
        p3.add(colf.getBytes(), col.getBytes(), ("Hadoop by reading the documentation").getBytes());
        lp.add(p3);

        Put p4 = new Put(Bytes.toBytes("4"));
        p4.add(colf.getBytes(), col.getBytes(), ("Hadoop from the release page").getBytes());
        lp.add(p4);

        Put p5 = new Put(Bytes.toBytes("5"));
        p5.add(colf.getBytes(), col.getBytes(), ("Hadoop on the mailing list").getBytes());
        lp.add(p5);

        table.put(lp);
        table.flushCommits();
        lp.clear();
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        init();
        Job job = Job.getInstance(config);
        job.setJarByClass(HbaseWordCount.class);
        Scan scan = new Scan();
        scan.addColumn(Bytes.toBytes(colf), Bytes.toBytes(col));
        //创建读取hbase数据的mapper，指定表名，scan，mapper类，输出的key和value
        TableMapReduceUtil.initTableMapperJob(tableName, scan, MyMapper.class, Text.class, IntWritable.class, job);
        // 创建写入hbase的reducer，指定表名、reducer类、job
        TableMapReduceUtil.initTableReducerJob(tableName2, MyReducer.class, job);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

实例代码流程说明：

　　1、在init()中首先会初始化Hbase的相关配置，主要配置zookeeper集群地址，zookeeper的端口号。

　　2、创建hbase word和 stat表，并向word表中添加数据。

　　3、然后执行mapreduce程序，从word表中读取数据，经过处理好，保存进stat表。注意执行mapreduce代码的时候，必须先创建好word表和stat表。