MapReduce分区将结果输出到多个文件

首先自定义分区规则类

/**
	 * Partitioner
	 */
	public static class StepToolPartitioner extends Partitioner<Text, Text>{
		private static Map<String, Integer> accountMap = new HashMap<String, Integer>();
		static{
			accountMap.put("LATELY", 0);
			accountMap.put("TRUE", 0);
			accountMap.put("FALSE", 1);
		}
		
		@Override
		public int getPartition(Text key, Text value, int numPartitions) {
			String keyString[] = key.toString().split("\\|");
			Integer part = accountMap.get(keyString[1]);
			if(part==null){
				part=0;
			}
			return part;
		}
		
	}

在MapReduce Main方法中设置：

job.setPartitionerClass(StepToolPartitioner.class);

job.setNumReduceTasks(2);//根据上述return part有几个类型的reduce就要设置几个Task(accountMap中的value只有0或1，所以是2个)。

 

所需jar包：

commons-beanutils-1.8.0.jar

commons-cli-1.2.jar

commons-collections-3.2.2.jar

commons-configuration-1.6.jar

commons-httpclient-3.1.jar

commons-io-2.4.jar

commons-lang-2.6.jar

commons-logging-1.1.3.jar

ezmorph-1.0.6.jar

guava-11.0.2.jar

hadoop-auth-2.7.2.jar

hadoop-common-2.7.2.jar

hadoop-hdfs-2.7.2.jar

hadoop-mapreduce-client-core-2.7.2.jar

htrace-core-3.1.0-incubating.jar

httpclient-4.3.2.jar

httpcore-4.3.2.jar

json-lib-2.4-jdk15.jar

log4j-1.2.17.jar

ojdbc6.jar

protobuf-java-2.5.0.jar

servlet-api-2.5.jar

slf4j-api-1.7.10.jar