blob: 211df4d66e535dbc9bb311ad2887b400b403a3e7 [file] [log] [blame]
/*
* 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.pig.test.pigmix.mapreduce;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.Properties;
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.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
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.mapred.TextInputFormat;
import org.apache.hadoop.mapred.jobcontrol.Job;
import org.apache.hadoop.mapred.jobcontrol.JobControl;
public class L1 {
public static class ReadPageViews extends MapReduceBase
implements Mapper<LongWritable, Text, Text, IntWritable> {
public void map(
LongWritable k,
Text val,
OutputCollector<Text, IntWritable> oc,
Reporter reporter) throws IOException {
// Split the line
List<Text> fields = Library.splitLine(val, '');
if (fields.size() != 9) return;
int cnt = 0;
if (fields.get(1).toString() == "1") {
Text throwAway = Library.mapLookup(fields.get(7), new Text("a"));
cnt++;
} else {
List<Text> le = Library.splitLine(fields.get(8), '');
for (Text e : le) {
Text throwAway = Library.mapLookup(e, new Text("b"));
cnt++;
}
}
oc.collect(fields.get(0), new IntWritable(cnt));
}
}
public static class Group extends MapReduceBase
implements Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(
Text key,
Iterator<IntWritable> iter,
OutputCollector<Text, IntWritable> oc,
Reporter reporter) throws IOException {
int cnt = 0;
while (iter.hasNext()) {
cnt += iter.next().get();
}
oc.collect(key, new IntWritable(cnt));
reporter.setStatus("OK");
}
}
public static void main(String[] args) throws IOException {
if (args.length!=3) {
System.out.println("Parameters: inputDir outputDir parallel");
System.exit(1);
}
String inputDir = args[0];
String outputDir = args[1];
String parallel = args[2];
JobConf lp = new JobConf(L1.class);
lp.setJobName("L1 Load Page Views");
lp.setInputFormat(TextInputFormat.class);
lp.setOutputKeyClass(Text.class);
lp.setOutputValueClass(IntWritable.class);
lp.setMapperClass(ReadPageViews.class);
lp.setCombinerClass(Group.class);
lp.setReducerClass(Group.class);
Properties props = System.getProperties();
for (Map.Entry<Object,Object> entry : props.entrySet()) {
lp.set((String)entry.getKey(), (String)entry.getValue());
}
FileInputFormat.addInputPath(lp, new Path(inputDir + "/page_views"));
FileOutputFormat.setOutputPath(lp, new Path(outputDir + "/L1out"));
lp.setNumReduceTasks(Integer.parseInt(parallel));
Job group = new Job(lp);
JobControl jc = new JobControl("L1 join");
jc.addJob(group);
new Thread(jc).start();
int i = 0;
while(!jc.allFinished()){
ArrayList<Job> failures = jc.getFailedJobs();
if (failures != null && failures.size() > 0) {
for (Job failure : failures) {
System.err.println(failure.getMessage());
}
break;
}
try {
Thread.sleep(5000);
} catch (InterruptedException e) {}
if (i % 10000 == 0) {
System.out.println("Running jobs");
ArrayList<Job> running = jc.getRunningJobs();
if (running != null && running.size() > 0) {
for (Job r : running) {
System.out.println(r.getJobName());
}
}
System.out.println("Ready jobs");
ArrayList<Job> ready = jc.getReadyJobs();
if (ready != null && ready.size() > 0) {
for (Job r : ready) {
System.out.println(r.getJobName());
}
}
System.out.println("Waiting jobs");
ArrayList<Job> waiting = jc.getWaitingJobs();
if (waiting != null && waiting.size() > 0) {
for (Job r : ready) {
System.out.println(r.getJobName());
}
}
System.out.println("Successful jobs");
ArrayList<Job> success = jc.getSuccessfulJobs();
if (success != null && success.size() > 0) {
for (Job r : ready) {
System.out.println(r.getJobName());
}
}
}
i++;
}
ArrayList<Job> failures = jc.getFailedJobs();
if (failures != null && failures.size() > 0) {
for (Job failure : failures) {
System.err.println(failure.getMessage());
}
}
jc.stop();
}
}