重庆分公司,新征程启航
为企业提供网站建设、域名注册、服务器等服务
这篇文章主要为大家展示了“Hadoop中如何自定义Map端输出Key”,内容简而易懂,条理清晰,希望能够帮助大家解决疑惑,下面让小编带领大家一起研究并学习一下“Hadoop中如何自定义Map端输出Key”这篇文章吧。
你所需要的网站建设服务,我们均能行业靠前的水平为你提供.标准是产品质量的保证,主要从事成都网站设计、做网站、企业网站建设、手机网站制作、网页设计、品牌网站制作、网页制作、做网站、建网站。创新互联拥有实力坚强的技术研发团队及素养的视觉设计专才。
package sort; import java.io.DataInput; import java.io.DataOutput; import java.io.IOException; import java.net.URI; import java.net.URISyntaxException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.RawComparator; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.WritableComparable; import org.apache.hadoop.io.WritableComparator; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; /** * 自定义排序 * 初始结果: * 3 3 * 3 2 * 3 1 * 2 2 * 2 1 * 1 1 * 输出结果: 1 1 2 1 2 2 3 1 3 2 3 3 * @author Xr * */ public class SortApp { public static final String INPUT_PATH = "hdfs://hadoop:9000/data"; public static final String OUTPUT_PATH = "hdfs://hadoop:9000/datas"; public static void main(String[] args)throws Exception{ Configuration conf = new Configuration(); existsFile(conf); Job job = new Job(conf, SortApp.class.getName()); FileInputFormat.setInputPaths(job, INPUT_PATH); job.setMapperClass(MyMapper.class); //自定义输出Key job.setMapOutputKeyClass(NewKey.class); job.setMapOutputValueClass(LongWritable.class); job.setReducerClass(MyReducer.class); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(LongWritable.class); FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH)); job.waitForCompletion(true); } private static void existsFile(Configuration conf) throws IOException, URISyntaxException { FileSystem fs = FileSystem.get(new URI(OUTPUT_PATH),conf); if(fs.exists(new Path(OUTPUT_PATH))){ fs.delete(new Path(OUTPUT_PATH),true); } } } class MyMapper extends Mapper{ @Override protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String string = value.toString(); String[] split = string.split("\t"); NewKey k2 = new NewKey(); k2.set(Long.parseLong(split[0]),Long.parseLong(split[1])); context.write(k2, new LongWritable(Long.parseLong(split[1]))); } } class MyReducer extends Reducer { @Override protected void reduce(NewKey key2, Iterable values,Context context) throws IOException, InterruptedException { long max = Long.MIN_VALUE; for(LongWritable v2 : values){ long l = v2.get(); if(l>max){ max = l; } } context.write(new LongWritable(key2.first),new LongWritable(max)); } } class NewKey implements WritableComparable { long first; long second; @Override public void write(DataOutput out) throws IOException { out.writeLong(this.first); out.writeLong(this.second); } public void set(long parseLong, long parseLong2) { this.first = parseLong; this.second = parseLong2; } @Override public void readFields(DataInput in) throws IOException { this.first = in.readLong(); this.second = in.readLong(); } @Override public int compareTo(NewKey o) { if(this.first==o.first){ if(this.second < o.second){ return -1; }else if(this.second == o.second){ return 0; }else{ return 1; } }else{ if(this.first < o.first){ return -1; }else{ return 1; } } } } Name:Xr Date:2014-03-04 21:31
以上是“Hadoop中如何自定义Map端输出Key”这篇文章的所有内容,感谢各位的阅读!相信大家都有了一定的了解,希望分享的内容对大家有所帮助,如果还想学习更多知识,欢迎关注创新互联行业资讯频道!