зеркало из https://github.com/mozilla/jydoop.git
86 строки
2.8 KiB
Java
86 строки
2.8 KiB
Java
|
package org.apache.hadoop.examples;
|
||
|
|
||
|
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.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;
|
||
|
import org.python.core.PyObject;
|
||
|
import org.python.util.PythonInterpreter;
|
||
|
|
||
|
public class WordCount {
|
||
|
private static PythonInterpreter py = null;
|
||
|
|
||
|
public static void Python(String methodName, Object arg1, Object arg2, Object arg3, Object arg4) {
|
||
|
if (py == null) {
|
||
|
py = new PythonInterpreter();
|
||
|
py.exec("import CallJava");
|
||
|
}
|
||
|
py.set("a1", arg1);
|
||
|
if (arg2 == null)
|
||
|
py.exec("CallJava." + methodName + "(a1)");
|
||
|
else {
|
||
|
py.set("a2", arg2);
|
||
|
py.set("a3", arg3);
|
||
|
py.set("a4", arg4);
|
||
|
py.exec("CallJava." + methodName + "(a1, a2, a3, a4)");
|
||
|
}
|
||
|
}
|
||
|
|
||
|
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 {
|
||
|
Python("map", value, one, word, context);
|
||
|
|
||
|
}
|
||
|
}
|
||
|
|
||
|
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();
|
||
|
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
|
||
|
if (otherArgs.length != 2) {
|
||
|
System.err.println("Usage: wordcount <in> <out>");
|
||
|
System.exit(2);
|
||
|
}
|
||
|
Job job = new Job(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(otherArgs[0]));
|
||
|
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
|
||
|
System.exit(job.waitForCompletion(true) ? 0 : 1);
|
||
|
}
|
||
|
}
|