Commit efdea1c5 authored by cloudera_vm's avatar cloudera_vm
Browse files

clearing files for Qa

parent 1e3b38e5
package SetSimilarityJoins;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Arrays;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class Qa extends Configured implements Tool {
public static void main(String[] args) throws Exception {
System.out.println(Arrays.toString(args));
int res = ToolRunner.run(new Configuration(), new Qa(), args);
System.exit(res);
}
@Override
public int run(String[] args) throws Exception {
System.out.println(Arrays.toString(args));
Job job = new Job(getConf(), "Qa_ALL_PAIRS");
job.setJarByClass(Qa.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
Path outputFilePath = new Path(args[1]);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, outputFilePath);
FileSystem fs = FileSystem.newInstance(getConf());
if (fs.exists(outputFilePath)) {
fs.delete(outputFilePath, true);
}
job.waitForCompletion(true);
return 0;
}
public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable ONE = new IntWritable(1);
private Text word = new Text();
String stopwords_file = "/home/cloudera/workspace/bpa/Assign2/stopwords/stopwords";
String stopwords = new String(Files.readAllBytes(Paths.get(stopwords_file)));
public Map() throws IOException{
System.out.println(stopwords);
}
@Override
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
for (String token: value.toString().replaceAll("[^A-Za-z0-9 ]", " ").split("\\s+")) {
if (!stopwords.contains(token)) {
word.set(token);
context.write(word, ONE);
}
}
}
}
public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
@Override
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));
}
}
}
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment