Hadoop 写SequenceFile文件 源代码

package com.tdxx.hadoop.sequencefile;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.SequenceFile.Writer;

public class SequenceFileStudy{

	/**
	 * 写入到sequence file
	 * 
	 * @param filePath
	 * @param conf
	 * @param datas
	 */
	public static void write2SequenceFile(String filePath, Configuration conf,
			LongWritable key,LongWritable val) {
		FileSystem fs = null;
		Writer writer = null;
		Path path = null;
		//LongWritable idKey = new LongWritable(0);

		try {
			fs = FileSystem.get(conf);
			path = new Path(filePath);
			writer = SequenceFile.createWriter(fs, conf, path,
					LongWritable.class, LongWritable.class);
			writer.append(key, val);
			
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} finally {
			IOUtils.closeStream(writer);
		}
	}

	private static Configuration getDefaultConf() {
		Configuration conf = new Configuration();
		conf.set("mapred.job.tracker", "local");
		conf.set("fs.default.name", "file:///");
		return conf;
	}

	/**
	 * @param args
	 */
	public static void main(String[] args) {
		String filePath = "data/longValue.sequence"; // 文件路径
		
		// 生成数据
		for (int i = 1; i <= 20; i++) {
			// 写入到sequence file
			LongWritable key = new LongWritable(i);
			LongWritable value = new LongWritable(i+1);
			write2SequenceFile(filePath, getDefaultConf(), key,value);
		}
	}

}


posted @ 2013-07-03 20:54  爱生活,爱编程  阅读(258)  评论(0编辑  收藏  举报