summaryrefslogtreecommitdiffstats
path: root/sandbox/ctrezzo/src/org/apache/hadoop
diff options
context:
space:
mode:
authorjsdelfino <jsdelfino@13f79535-47bb-0310-9956-ffa450edef68>2008-07-15 17:36:41 +0000
committerjsdelfino <jsdelfino@13f79535-47bb-0310-9956-ffa450edef68>2008-07-15 17:36:41 +0000
commit787e4871904a8b6d31c1c9050eb7ca6058daa555 (patch)
tree19732e078c8398b4f755d6e0a1fd9beb2639dc0d /sandbox/ctrezzo/src/org/apache/hadoop
parent20777692c2aea486ad8a568f61fa423213acedf1 (diff)
Applied patch from JIRA TUSCANY-2471.
git-svn-id: http://svn.us.apache.org/repos/asf/tuscany@676988 13f79535-47bb-0310-9956-ffa450edef68
Diffstat (limited to '')
-rw-r--r--sandbox/ctrezzo/src/org/apache/hadoop/myExamples/WordCount.java157
1 files changed, 157 insertions, 0 deletions
diff --git a/sandbox/ctrezzo/src/org/apache/hadoop/myExamples/WordCount.java b/sandbox/ctrezzo/src/org/apache/hadoop/myExamples/WordCount.java
new file mode 100644
index 0000000000..54b43905af
--- /dev/null
+++ b/sandbox/ctrezzo/src/org/apache/hadoop/myExamples/WordCount.java
@@ -0,0 +1,157 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hadoop.myExamples;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Iterator;
+import java.util.List;
+import java.util.StringTokenizer;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
+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.mapred.JobClient;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.Reducer;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.util.Tool;
+import org.apache.hadoop.util.ToolRunner;
+
+/**
+ * This is an example Hadoop Map/Reduce application.
+ * It reads the text input files, breaks each line into words
+ * and counts them. The output is a locally sorted list of words and the
+ * count of how often they occurred.
+ *
+ * To run: bin/hadoop jar build/hadoop-examples.jar wordcount
+ * [-m <i>maps</i>] [-r <i>reduces</i>] <i>in-dir</i> <i>out-dir</i>
+ */
+public class WordCount extends Configured implements Tool {
+
+ /**
+ * Counts the words in each line.
+ * For each line of input, break the line into words and emit them as
+ * (<b>word</b>, <b>1</b>).
+ */
+ public static class MapClass extends MapReduceBase
+ implements Mapper<LongWritable, Text, Text, IntWritable> {
+
+ private final static IntWritable one = new IntWritable(1);
+ private Text word = new Text();
+
+ public void map(LongWritable key, Text value,
+ OutputCollector<Text, IntWritable> output,
+ Reporter reporter) throws IOException {
+ String line = value.toString();
+ StringTokenizer itr = new StringTokenizer(line);
+ while (itr.hasMoreTokens()) {
+ word.set(itr.nextToken());
+ output.collect(word, one);
+ }
+ }
+ }
+
+ /**
+ * A reducer class that just emits the sum of the input values.
+ */
+ public static class Reduce extends MapReduceBase
+ implements Reducer<Text, IntWritable, Text, IntWritable> {
+
+ public void reduce(Text key, Iterator<IntWritable> values,
+ OutputCollector<Text, IntWritable> output,
+ Reporter reporter) throws IOException {
+ int sum = 0;
+ while (values.hasNext()) {
+ sum += values.next().get();
+ }
+ output.collect(key, new IntWritable(sum));
+ }
+ }
+
+ static int printUsage() {
+ System.out.println("wordcount [-m <maps>] [-r <reduces>] <input> <output>");
+ ToolRunner.printGenericCommandUsage(System.out);
+ return -1;
+ }
+
+ /**
+ * The main driver for word count map/reduce program.
+ * Invoke this method to submit the map/reduce job.
+ * @throws IOException When there is communication problems with the
+ * job tracker.
+ */
+ public int run(String[] args) throws Exception {
+ JobConf conf = new JobConf(getConf(), WordCount.class);
+ conf.setJobName("wordcount");
+
+ // the keys are words (strings)
+ conf.setOutputKeyClass(Text.class);
+ // the values are counts (ints)
+ conf.setOutputValueClass(IntWritable.class);
+
+ conf.setMapperClass(MapClass.class);
+ conf.setCombinerClass(Reduce.class);
+ conf.setReducerClass(Reduce.class);
+
+ List<String> other_args = new ArrayList<String>();
+ for(int i=0; i < args.length; ++i) {
+ try {
+ if ("-m".equals(args[i])) {
+ conf.setNumMapTasks(Integer.parseInt(args[++i]));
+ } else if ("-r".equals(args[i])) {
+ conf.setNumReduceTasks(Integer.parseInt(args[++i]));
+ } else {
+ other_args.add(args[i]);
+ }
+ } catch (NumberFormatException except) {
+ System.out.println("ERROR: Integer expected instead of " + args[i]);
+ return printUsage();
+ } catch (ArrayIndexOutOfBoundsException except) {
+ System.out.println("ERROR: Required parameter missing from " +
+ args[i-1]);
+ return printUsage();
+ }
+ }
+ // Make sure there are exactly 2 parameters left.
+ if (other_args.size() != 2) {
+ System.out.println("ERROR: Wrong number of parameters: " +
+ other_args.size() + " instead of 2.");
+ return printUsage();
+ }
+ conf.setInputPath(new Path(other_args.get(0)));
+ conf.setOutputPath(new Path(other_args.get(1)));
+
+ JobClient.runJob(conf);
+ return 0;
+ }
+
+
+ public static void main(String[] args) throws Exception {
+ int res = ToolRunner.run(new Configuration(), new WordCount(), args);
+ System.exit(res);
+ }
+
+}