import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.util.HashSet;
import java.util.Set;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.filecache.DistributedCache;
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.output.FileOutputFormat;
import org.apache.hadoop.util.StringUtils;
public class WordCountV20 {
public static class Map extends
Mapper<LongWritable, Text, Text, IntWritable> {
static enum Counters {
INPUT_WORDS
}
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
private boolean caseSensitive = true;
private Set<String> patternsToSkip = new HashSet<String>();
private void parseSkipFile(Path patternsFile) {
try {
BufferedReader fis = new BufferedReader(new FileReader(
patternsFile.toString()));
String pattern = null;
while ((pattern = fis.readLine()) != null) {
patternsToSkip.add(pattern);
}
} catch (IOException ioe) {
System.err
.println("Caught exception while parsing the cached file '"
+ patternsFile
+ "' : "
+ StringUtils.stringifyException(ioe));
}
}
@Override
public void setup(Context context) {
Configuration conf = context.getConfiguration();
caseSensitive = conf.getBoolean("wordcount.case.sensitive", true);
if (conf.getBoolean("wordcount.skip.patterns", false)) {
Path[] patternsFiles = new Path[0];
try {
patternsFiles = DistributedCache.getLocalCacheFiles(conf);
} catch (IOException ioe) {
System.err
.println("Caught exception while getting cached files: "
+ StringUtils.stringifyException(ioe));
}
for (Path patternsFile : patternsFiles) {
parseSkipFile(patternsFile);
}
}
}
@Override
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = (caseSensitive) ? value.toString() : value.toString()
.toLowerCase();
for (String pattern : patternsToSkip) {
line = line.replaceAll(pattern, "");
}
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
context.write(word, one);
}
}
}
public static class Reduce extends
Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result = new 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();
}
result.set(sum);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
String[] argv = { "/home/nchc/input", "/home/nchc/output-wc2", "-c", "-skip",
"/home/nchc/patterns/patterns.txt" };
args = argv;
Configuration conf = new Configuration();
conf.set("mapred.job.tracker", "local"); // for single
conf.set("fs.default.name", "file:///"); // for single
if (args.length < 2) {
System.err
.println("Usage: hadoop jar WordCount.jar <input> <output> [-c] [-skip <path>]");
System.exit(2);
}
for (int i = 0; i < args.length; ++i) {
if ("-skip".equals(args[i])) {
DistributedCache
.addCacheFile(new Path(args[++i]).toUri(), conf);
conf.setBoolean("wordcount.skip.patterns", true);
}
if ("-c".equals(args[i])){
conf.setBoolean("wordcount.case.sensitive", false);
}
}
CheckAndDelete.checkAndDelete(args[1], conf);
Job job = new Job(conf, "Word Count");
job.setJarByClass(WordCountV20.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}