Java tutorial
/* * Cloud9: A Hadoop toolkit for working with big data * * Licensed 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 edu.umd.JBizz; import java.io.IOException; import java.util.Arrays; import java.util.Collections; import java.util.Iterator; import java.io.ByteArrayOutputStream; import java.io.ObjectOutputStream; import java.io.DataOutputStream; import org.apache.commons.cli.CommandLine; import org.apache.commons.cli.CommandLineParser; import org.apache.commons.cli.GnuParser; import org.apache.commons.cli.HelpFormatter; import org.apache.commons.cli.OptionBuilder; import org.apache.commons.cli.Options; import org.apache.commons.cli.ParseException; import org.apache.hadoop.conf.Configured; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.VIntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.BytesWritable; import org.apache.hadoop.io.WritableUtils; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.Partitioner; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.MapFileOutputFormat; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; import org.apache.log4j.Logger; import tl.lin.data.array.ArrayListWritable; import tl.lin.data.fd.Object2IntFrequencyDistribution; import tl.lin.data.fd.Object2IntFrequencyDistributionEntry; import tl.lin.data.pair.PairOfInts; import tl.lin.data.pair.PairOfStringInt; import tl.lin.data.pair.PairOfObjectInt; import tl.lin.data.pair.PairOfWritables; public class BuildInvertedIndexCompressed extends Configured implements Tool { private static final Logger LOG = Logger.getLogger(BuildInvertedIndexCompressed.class); private static class MyMapper extends Mapper<LongWritable, Text, PairOfStringInt, VIntWritable> { private static final PairOfStringInt COMPKEY = new PairOfStringInt(); private static final Object2IntFrequencyDistribution<String> COUNTS = new Object2IntFrequencyDistributionEntry<String>(); @Override public void map(LongWritable docno, Text doc, Context context) throws IOException, InterruptedException { String text = doc.toString(); COUNTS.clear(); String[] terms = text.split("\\s+"); // First build a histogram of the terms. for (String term : terms) { if (term == null || term.length() == 0) { continue; } COUNTS.increment(term); } // Emit postings. for (PairOfObjectInt<String> e : COUNTS) { COMPKEY.set(e.getLeftElement(), (int) docno.get()); context.write(COMPKEY, new VIntWritable(e.getRightElement())); } } } private static class MyReducer extends Reducer<PairOfStringInt, VIntWritable, Text, BytesWritable> { private final static ArrayListWritable<PairOfInts> POSTINGS = new ArrayListWritable<PairOfInts>(); private final static Text PREV = new Text(); @Override public void reduce(PairOfStringInt key, Iterable<VIntWritable> values, Context context) throws IOException, InterruptedException { Iterator<VIntWritable> iter = values.iterator(); if (PREV.getLength() == 0 || PREV.toString() == null) { PREV.set(key.getLeftElement()); } if (key.getLeftElement().equals(PREV.toString())) { while (iter.hasNext()) { POSTINGS.add(new PairOfInts(key.getRightElement(), iter.next().get())); } PREV.set(key.getLeftElement()); } else { ByteArrayOutputStream baos = new ByteArrayOutputStream(); DataOutputStream oos = new DataOutputStream(baos); for (PairOfInts poi : POSTINGS) { WritableUtils.writeVInt(oos, poi.getLeftElement()); WritableUtils.writeVInt(oos, poi.getRightElement()); } byte[] posterino = baos.toByteArray(); BytesWritable out = new BytesWritable(posterino); Text keyOut = new Text(); keyOut.set(PREV); context.write(keyOut, out); oos.close(); POSTINGS.clear(); PREV.set(key.getLeftElement()); while (iter.hasNext()) { POSTINGS.add(new PairOfInts(key.getRightElement(), iter.next().get())); } } } } public static class MyPartitioner extends Partitioner<PairOfStringInt, VIntWritable> { @Override public int getPartition(PairOfStringInt key, VIntWritable value, int numReduceTasks) { return (key.getLeftElement().hashCode() & Integer.MAX_VALUE) % numReduceTasks; } } private BuildInvertedIndexCompressed() { } private static final String INPUT = "input"; private static final String OUTPUT = "output"; private static final String NUM_REDUCERS = "numReducers"; /** * Runs this tool. */ @SuppressWarnings({ "static-access" }) public int run(String[] args) throws Exception { Options options = new Options(); options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT)); options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("output path").create(OUTPUT)); options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of reducers") .create(NUM_REDUCERS)); CommandLine cmdline; CommandLineParser parser = new GnuParser(); try { cmdline = parser.parse(options, args); } catch (ParseException exp) { System.err.println("Error parsing command line: " + exp.getMessage()); return -1; } if (!cmdline.hasOption(INPUT) || !cmdline.hasOption(OUTPUT)) { System.out.println("args: " + Arrays.toString(args)); HelpFormatter formatter = new HelpFormatter(); formatter.setWidth(120); formatter.printHelp(this.getClass().getName(), options); ToolRunner.printGenericCommandUsage(System.out); return -1; } String inputPath = cmdline.getOptionValue(INPUT); String outputPath = cmdline.getOptionValue(OUTPUT); int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS)) : 1; LOG.info("Tool name: " + BuildInvertedIndexCompressed.class.getSimpleName()); LOG.info(" - input path: " + inputPath); LOG.info(" - output path: " + outputPath); LOG.info(" - num reducers: " + reduceTasks); Job job = Job.getInstance(getConf()); job.setJobName(BuildInvertedIndexCompressed.class.getSimpleName()); job.setJarByClass(BuildInvertedIndexCompressed.class); job.setNumReduceTasks(reduceTasks); FileInputFormat.setInputPaths(job, new Path(inputPath)); FileOutputFormat.setOutputPath(job, new Path(outputPath)); //job.setMapOutputKeyClass(Text.class); //job.setMapOutputValueClass(PairOfInts.class); job.setMapOutputKeyClass(PairOfStringInt.class); job.setMapOutputValueClass(VIntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(BytesWritable.class); job.setOutputFormatClass(MapFileOutputFormat.class); job.setMapperClass(MyMapper.class); job.setReducerClass(MyReducer.class); job.setPartitionerClass(MyPartitioner.class); // Delete the output directory if it exists already. Path outputDir = new Path(outputPath); FileSystem.get(getConf()).delete(outputDir, true); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; } /** * Dispatches command-line arguments to the tool via the {@code ToolRunner}. */ public static void main(String[] args) throws Exception { ToolRunner.run(new BuildInvertedIndexCompressed(), args); } }