spring-data-hadoop使用--maven配置详解

这几天一直在纠结spring-data-hadoop的JAR包，总是运行不成功，现在终于可以运行了，pom内容为：

<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>winksi.com.cn</groupId>
	<artifactId>hadoopTest</artifactId>
	<version>0.0.1-SNAPSHOT</version>

	<!-- 添加镜像依赖 ，在maven的官方库里是没有CDH相关包的，所以只能配置CDH的官网下载地址来下载jar包-->
	<repositories>
		<repository>
			<id>cloudera</id>
			<url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
		</repository>
		<repository>
			<id>spring-repo</id>
			<url>http://repo.springsource.org/libs-milestone</url>
		</repository>
	</repositories>
	<properties>
		<java.version>1.6</java.version>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
		<!-- Spring -->
		<spring-framework.version>3.2.3.RELEASE</spring-framework.version>
		<!-- Logging -->
		<logback.version>1.0.13</logback.version>
		<slf4j.version>1.7.5</slf4j.version>
		<!-- Test -->
		<junit.version>4.11</junit.version>
		<!-- hadoop -->
		<CDH.version>2.0.0-cdh4.5.0</CDH.version>
		<hadoop.core.version>2.0.0-mr1-cdh4.5.0</hadoop.core.version>
		<groovy.version>1.8.5</groovy.version>
	</properties>

	<dependencies>
		<!-- Spring and Transactions -->
		<dependency>
			<groupId>org.springframework</groupId>
			<artifactId>spring-context</artifactId>
			<version>${spring-framework.version}</version>
		</dependency>
		<dependency>
			<groupId>org.springframework</groupId>
			<artifactId>spring-tx</artifactId>
			<version>${spring-framework.version}</version>
		</dependency>
		<!-- Spring-jdbc -->
		<dependency>
			<groupId>org.springframework</groupId>
			<artifactId>spring-jdbc</artifactId>
			<version>${spring-framework.version}</version>
		</dependency>

		<!-- Logging with SLF4J & LogBack -->
		<dependency>
			<groupId>org.slf4j</groupId>
			<artifactId>slf4j-api</artifactId>
			<version>${slf4j.version}</version>
			<scope>compile</scope>
		</dependency>
		<dependency>
			<groupId>ch.qos.logback</groupId>
			<artifactId>logback-classic</artifactId>
			<version>${logback.version}</version>
			<scope>runtime</scope>
		</dependency>

		<!-- Test Artifacts -->
		<dependency>
			<groupId>org.springframework</groupId>
			<artifactId>spring-test</artifactId>
			<version>${spring-framework.version}</version>
			<scope>test</scope>
		</dependency>
		<dependency>
			<groupId>junit</groupId>
			<artifactId>junit</artifactId>
			<version>${junit.version}</version>
			<scope>test</scope>
		</dependency>
		<dependency>
			<groupId>com.alibaba</groupId>
			<artifactId>fastjson</artifactId>
			<version>1.1.37</version>
		</dependency>

		<span style="color:#FF0000;"><!-- hadoop -->
		<dependency>
			<groupId>org.springframework.data</groupId>
			<artifactId>spring-data-hadoop</artifactId>
			<version>1.0.2.RELEASE-cdh4</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-hdfs</artifactId>
			<version>${CDH.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-core</artifactId>
			<version>${hadoop.core.version}</version>
		</dependency>
		<dependency>
			<groupId>org.codehaus.groovy</groupId>
			<artifactId>groovy</artifactId>
			<version>${groovy.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-client</artifactId>
			<version>${CDH.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hive</groupId>
			<artifactId>hive-service</artifactId>
			<version>0.10.0-cdh4.5.0</version>
		</dependency>
		<dependency>
			<groupId>org.apache.hbase</groupId>
			<artifactId>hbase</artifactId>
			<version>0.94.6-cdh4.5.0</version>
		</dependency></span>
	</dependencies>
</project>

主要是红色部分的JAR包

spring配置文件为：

<?xml version="1.0" encoding="UTF-8"?>
<beans:beans xmlns="http://www.springframework.org/schema/hadoop"
	xmlns:beans="http://www.springframework.org/schema/beans"
	xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xmlns:context="http://www.springframework.org/schema/context"
	xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans.xsd
	  http://www.springframework.org/schema/context http://www.springframework.org/schema/context/spring-context.xsd
	  http://www.springframework.org/schema/hadoop http://www.springframework.org/schema/hadoop/spring-hadoop.xsd"
	  default-autowire="byName">
	<context:property-placeholder location="classpath:config.properties" />
	<configuration>
		fs.default.name=${hd.fs}
		mapred.job.tracker=${hd.mr}
	</configuration>

	<!-- This will throw a NPE at the end of running the app that should be ignored
	     
	     To avoid this, run against the stand-alone server, use the command line  
	     
	     hive -hiveconf fs.default.name=hdfs://localhost:9000 -hiveconf mapred.job.tracker=localhost:9001
	     
	     -->
	
	<hive-server port="${hive.port}" auto-startup="true"/>		     
	
	<hive-client-factory host="${hive.host}" port="${hive.port}"/>	
	
	<hive-template id="hiveTemplate"/>			

	
</beans:beans>

参数配置文件为：

hd.fs=hdfs://172.16.1.50:8020
hd.mr=172.16.1.50:8021
hd.zk.port=2181
hd.zk.host=172.16.1.50
hive.host=172.16.1.50
hive.port=10000

程序中调用方式：

        ApplicationContext ac = new ClassPathXmlApplicationContext("applicationContext.xml");
        HiveTemplate hiveTemplate = (HiveTemplate) ac.getBean("hiveTemplate");
        List list = hiveTemplate.query("show tables;");
        System.out.println(JSON.toJSONString(list));

调用成功