hadoop mapreduce实现数据去重
实现原理分析:
map函数数将输入的文本按照行读取, 并将Key--每一行的内容 输出 value--空。
reduce 会自动统计所有的key,我们让reduce输出key->输入的key value->空,这样就利用reduce自动合并相同的key的原理实现了数据去重。
源代码:
package com.duking.hadoop; import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; 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; import org.apache.hadoop.util.GenericOptionsParser; public class Dedup { // map将输入中的value复制到输出数据的key上,并直接输出 public static class Map extends Mapper<Object, Text, Text, Text> { private static Text line = new Text();// 每行数据 // 实现map函数 public void map(Object key, Text value, Context context) throws IOException, InterruptedException { line = value; context.write(line, new Text("")); } } // reduce将输入中的key复制到输出数据的key上,并直接输出 这是数据区重的思想 public static class Reduce extends Reducer<Text, Text, Text, Text> { // 实现reduce函数 public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException { context.write(key, new Text("")); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); // 这句话很关键 conf.set("mapred.job.tracker", "192.168.60.129:9000"); //指定带运行参数的目录为输入输出目录 String[] otherArgs = new GenericOptionsParser(conf, args) .getRemainingArgs(); /* 指定工程下的input2为文件输入目录 output2为文件输出目录 String[] ioArgs = new String[] { "input2", "output2" }; String[] otherArgs = new GenericOptionsParser(conf, ioArgs) .getRemainingArgs();*/ if (otherArgs.length != 2) { //判断路径参数是否为2个 System.err.println("Usage: Data Deduplication <in> <out>"); System.exit(2); } //set maprduce job name Job job = new Job(conf, "Data Deduplication"); job.setJarByClass(Dedup.class); // 设置Map、Combine和Reduce处理类 job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); // 设置输出类型 job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); // 设置输入和输出目录 FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }