本篇博客介绍使用Hadoop实现单词统计(来源:慕课网学习),下面是具体步骤:
1.创建目录
hadoop fs -mkdir input
hadoop fs -mkdir word_count_class
2.复制博客末尾的代码到Java文件,命名WordCount.java,并运行如下命令编译java文件
javac -classpath /opt/hadoop-1.2.1/hadoop-core-1.2.1.jar:/opt/hadoop-1.2.1/lib/commons-cli-1.2.jar -d 编译后地址(自己制定,e.g.:wordcount_class) 编译后的文件名(自己指定,e.g.:WordCount)
3.打包指令
jar -cvf 打包后文件名.jar(自己指定) *.class
4.在当前目录的子目录input目录下创建两个输入文件(input1,input2),里面加入需要统计的单词,用空格隔开(e.g.:word hadoop …),并输入文件提交输入文件给hadoop
hadoop fs -put 文件路径 提交后的路径
hadoop fs -put input/* input_wordcount/
5.提交jar给hadoop执行
hadoop jar jar包路径 执行的主函数名(主类名,main方法所在类名) 输入目录名 输出目录名
hadoop jar word_count_class/wordcount.jar WordCount input_wordcount output_wordcount
6.运行结果文件存在output_wordcount中,运行如下命令即可查看
hadoop fs -ls ouput_wordcount
7、查看output_wordcount目录下part-…文件即为统计结果
hadoop fs -cat ouput_wordcount/part-..
下面是代码:
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class WordCount {
public static class WordCountMap extends
Mapper<LongWritable, Text, Text, IntWritable> {
private final IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer token = new StringTokenizer(line);
while (token.hasMoreTokens()) {
word.set(token.nextToken());
context.write(word, one);
}
}
}
public static class WordCountReduce extends
Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterable<IntWritable> values,
Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
context.write(key, new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = new Job(conf);
job.setJarByClass(WordCount.class);
job.setJobName("wordcount");
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(WordCountMap.class);
job.setReducerClass(WordCountReduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.waitForCompletion(true);
}
}
欢迎关注我的公众号:
编程技术与生活(ID:hw_cchang)