说,我们接受两个输入文件:
file1 content: a b c d
file2 content: b c d e
我希望TokenizerMapper.class
在
ab ac ad ae bd bc bd be cb cc cd ce db dc dd de
一个词与另一个词对齐
我将file1内容存储到一个数组中,将file2内容存储到另一个数组中
并运行循环来创建它。
问题是如何使用MultipleInputs
将两个文件内容组合在同一个类中?
自爆代码有MultipleIputs
:
public class WordCount {
public static class TokenizerMapper
extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
public static class IntSumReducer
extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values,
Context context
) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
//FileInputFormat.addInputPath(job, new Path(args[0]));
MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, TokenizerMapper.class);
MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, TokenizerMapper.class);
FileOutputFormat.setOutputPath(job, new Path(args[2]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}