六、HBase与MR整合

三种情况：

1. HDFS->MR->HBase
2. HBase->MR->HDFS
3. HBase->MR->HBase

###6.1 HDFS->MR->HBase

从HDFS读取数据，MR计算，结果存储于hbase

wordcount

从HDFS读取/usr/local/hello.txt，MR计算之后，将结果写到hbase的wordcount表中。

1、在hbase上添加表,hdfs上传源数据

xxxxxxxxxx
hbase(main):001:0> create 'wordcount', 'cf'
#Hdfs上输出准备
[root@node3 ~]# for i in `seq  100000`; do echo "hello bjsxt $i" >>hello.txt;done
[root@node3 ~]# hdfs dfs -mkdir /usr/local
[root@node3 ~]# hdfs dfs -put hello.txt /usr/local

2、修改pom.xml文件

xxxxxxxxxx
<properties>
  <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
  <maven.compiler.source>1.8</maven.compiler.source>
  <maven.compiler.target>1.8</maven.compiler.target>
  <hadoop.version>3.1.3</hadoop.version>
  <mapreduce.version>3.1.3</mapreduce.version>
  <hbase.version>2.0.5</hbase.version>
</properties>

<dependencies>
  <!--<dependency>
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase-server</artifactId>
    <version>2.0.5</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase-client</artifactId>
    <version>2.0.5</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-client</artifactId>
    <version>3.1.3</version>
  </dependency>-->
  <!--   hadoop-hdfs -->
  <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-common</artifactId>
    <version>${hadoop.version}</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-hdfs</artifactId>
    <version>${hadoop.version}</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-hdfs-client</artifactId>
    <version>${hadoop.version}</version>
  </dependency>
  <!--   hadoop-mapreduce -->
  <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-mapreduce-client-core</artifactId>
    <version>${mapreduce.version}</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
    <version>${mapreduce.version}</version>
    <scope>provided</scope>
  </dependency>
  <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-mapreduce-client-common</artifactId>
    <version>${mapreduce.version}</version>
  </dependency>
  <!--   hbase  -->
  <dependency>
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase-client</artifactId>
    <version>${hbase.version}</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase-common</artifactId>
    <version>${hbase.version}</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase</artifactId>
    <version>${hbase.version}</version>
    <type>pom</type>
  </dependency>
  <dependency>
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase-server</artifactId>
    <version>${hbase.version}</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase-mapreduce</artifactId>
    <version>${hbase.version}</version>
  </dependency>
    ......
</dependencies>

3、将hadoop-config下的四个hadoop配置文件拷贝到当前项目的resources目录下。