这篇文章将为大家详细讲解有关如何使用hadoop来提取文件中的指定内容,小编觉得挺实用的,因此分享给大家做个参考,希望大家阅读完这篇文章后可以有所收获。
把以下txt中含“baidu”字符串的链接输出到一个文件,否则输出到另外一个文件。
1.LogMapper.java
package com.whj.mapreduce.outputformat; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper; import java.io.IOException; public class LogMapper extends Mapper<LongWritable,Text,Text,NullWritable> { @Override protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { // 不做任何处理 context.write(value,NullWritable.get()); } }
2.LogReducer.java
package com.whj.mapreduce.outputformat; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer; import java.io.IOException; public class LogReducer extends Reducer<Text,NullWritable,Text,NullWritable> { @Override protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException { for (NullWritable value : values) { context.write(key,NullWritable.get()); } } }
3.LogOutputFormat.java
package com.whj.mapreduce.outputformat; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.RecordWriter; import org.apache.hadoop.mapreduce.TaskAttemptContext; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import java.io.IOException; public class LogOutputFormat extends FileOutputFormat<Text,NullWritable> { @Override public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException { LogRecordWriter lrw = new LogRecordWriter(job); return lrw; } }
4.LogRecordWriter.java
package com.whj.mapreduce.outputformat; import org.apache.hadoop.fs.FSDataOutputStream; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IOUtils; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.RecordWriter; import org.apache.hadoop.mapreduce.TaskAttemptContext; import java.io.IOException; public class LogRecordWriter extends RecordWriter<Text,NullWritable> { private FSDataOutputStream baiduOut;//ctrl+alt+f private FSDataOutputStream otherOut; public LogRecordWriter(TaskAttemptContext job) throws IOException { //创建两条流 FileSystem fs = FileSystem.get(job.getConfiguration()); baiduOut = fs.create(new Path("D:\\temp\\outputformat.log")); otherOut = fs.create(new Path("D:\\temp\\other.log")); } @Override public void write(Text key, NullWritable nullWritable) throws IOException, InterruptedException { // 具体写 String log = key.toString(); if(log.contains("baidu")){ baiduOut.writeBytes(log+"\n"); }else{ otherOut.writeBytes(log+"\n"); } } @Override public void close(TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException { //关流 IOUtils.closeStream(baiduOut); IOUtils.closeStream(otherOut); } }
5.LogDriver.java
package com.whj.mapreduce.outputformat; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import java.io.IOException; public class LogDriver { public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf); job.setJarByClass(LogDriver.class); job.setMapperClass(LogMapper.class); job.setReducerClass(LogReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(NullWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(NullWritable.class); //设置自定义的 outputformat job.setOutputFormatClass(LogOutputFormat.class); FileInputFormat.setInputPaths(job, new Path("D:\\input")); // 虽 然 我 们 自 定 义 了 outputformat , 但 是 因 为 我 们 的 outputformat 继承自fileoutputformat //而 fileoutputformat 要输出一个_SUCCESS 文件,所以在这还得指定一个输出目录 FileOutputFormat.setOutputPath(job, new Path("D:\\temp\\logoutput")); boolean b = job.waitForCompletion(true); System.exit(b ? 0 : 1); } }
关于“如何使用hadoop来提取文件中的指定内容”这篇文章就分享到这里了,希望以上内容可以对大家有一定的帮助,使各位可以学到更多知识,如果觉得文章不错,请把它分享出去让更多的人看到。
免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。