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.shrawanraina; import java.io.ByteArrayOutputStream; import java.io.DataOutputStream; import java.io.IOException; import java.util.Arrays; import java.util.HashMap; import java.util.Iterator; 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.BytesWritable; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.VIntWritable; import org.apache.hadoop.io.WritableUtils; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Partitioner; 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.mapreduce.lib.output.MapFileOutputFormat; //import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; import org.apache.log4j.Logger; import tl.lin.data.fd.Object2IntFrequencyDistribution; import tl.lin.data.fd.Object2IntFrequencyDistributionEntry; import tl.lin.data.pair.PairOfObjectInt; import tl.lin.data.pair.PairOfStringInt; 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 Text WORD = new Text(); private static final Object2IntFrequencyDistribution<String> COUNTS = new Object2IntFrequencyDistributionEntry<String>(); private static final VIntWritable TF = new VIntWritable(); //private static HashMap<String, Integer> dfMap = new HashMap<String, Integer>(); @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) { WORD.set(e.getLeftElement()); TF.set(e.getRightElement()); context.write(new PairOfStringInt(WORD.toString(), (int) docno.get()), TF); /* if(!dfMap.containsKey(e.getLeftElement())) dfMap.put(e.getLeftElement(), 1); else{ dfMap.put(e.getLeftElement(), 1+dfMap.get(e.getLeftElement())); } */ } } /* @Override public void cleanup(Context context) throws IOException{ FileSystem fs = FileSystem.get(context.getConfiguration()); Path mapPath = new Path("./sidedata/dfMap.txt"); BufferedWriter bwMap = new BufferedWriter(new OutputStreamWriter(fs.create(mapPath))); for(Map.Entry<String, Integer> entry : dfMap.entrySet()){ bwMap.write(entry.getKey()+"<SPLIT>"+entry.getValue()); bwMap.write("\n"); } bwMap.close(); } */ } private static class MyReducer extends Reducer<PairOfStringInt, VIntWritable, Text, BytesWritable> { private static String prevKey; private static int prevDocNo; private static int df; private static int tf; private static int dgap; private final static ByteArrayOutputStream postings = new ByteArrayOutputStream(); private final static DataOutputStream stream = new DataOutputStream(postings); private final static Text KEY = new Text(); @Override public void setup(Context context) { prevKey = null; prevDocNo = 0; df = 0; tf = 0; dgap = 0; } @Override public void reduce(PairOfStringInt key, Iterable<VIntWritable> values, Context context) throws IOException, InterruptedException { String term = key.getLeftElement(); if (term.equals(prevKey) || prevKey == null) { prevKey = key.getLeftElement(); //Iterate through the values Iterator<VIntWritable> iter = values.iterator(); while (iter.hasNext()) { df++; tf = iter.next().get(); dgap = key.getRightElement() - prevDocNo; WritableUtils.writeVInt(stream, dgap); WritableUtils.writeVInt(stream, dgap); prevDocNo = key.getRightElement(); ; } } else { KEY.set(prevKey); stream.flush(); ByteArrayOutputStream dfpost = new ByteArrayOutputStream(); DataOutputStream dfstream = new DataOutputStream(dfpost); WritableUtils.writeVInt(dfstream, df); dfstream.write(postings.toByteArray()); dfstream.flush(); context.write(KEY, new BytesWritable(dfpost.toByteArray())); prevDocNo = 0; df = 0; prevKey = key.getLeftElement(); postings.reset(); Iterator<VIntWritable> iter = values.iterator(); while (iter.hasNext()) { df++; tf = iter.next().get(); dgap = key.getRightElement() - prevDocNo; WritableUtils.writeVInt(stream, dgap); WritableUtils.writeVInt(stream, tf); prevDocNo = key.getRightElement(); } } /* Iterator<VIntWritable> iter = values.iterator(); while(iter.hasNext()){ int tf = iter.next().get(); if(key.getLeftElement().equals(prevKey) || prevKey == null){ df++; prevKey = key.getLeftElement(); dgap = key.getRightElement() - prevDocNo; //System.out.println("1: "+key+" "+df+" "+tf+" "+dgap); WritableUtils.writeVInt(stream, dgap); WritableUtils.writeVInt(stream, tf); } else{ KEY.set(prevKey); stream.flush(); postings.flush(); ByteArrayOutputStream dfpost = new ByteArrayOutputStream(); DataOutputStream dfstream = new DataOutputStream(dfpost); WritableUtils.writeVInt(dfstream, df); dfstream.write(postings.toByteArray()); dfstream.flush(); context.write(KEY, new BytesWritable(dfpost.toByteArray())); //System.out.println("2: "+key+" "+df+" "+tf+" "+dgap); dgap = 0; df = 0; prevKey = key.getLeftElement(); postings.reset(); WritableUtils.writeVInt(stream, dgap); WritableUtils.writeVInt(stream, tf); } prevDocNo = key.getRightElement(); } */ } @Override public void cleanup(Context context) throws IOException, InterruptedException { KEY.set(prevKey); stream.flush(); ByteArrayOutputStream dfpost = new ByteArrayOutputStream(); DataOutputStream dfstream = new DataOutputStream(dfpost); WritableUtils.writeVInt(dfstream, df); dfstream.write(postings.toByteArray()); dfstream.flush(); context.write(KEY, new BytesWritable(dfpost.toByteArray())); postings.close(); stream.close(); } } protected static class MyPartitioner extends Partitioner<PairOfStringInt, IntWritable> { @Override public int getPartition(PairOfStringInt key, IntWritable 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(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); // Delete the output directory if it exists already. Path outputDir = new Path(outputPath); FileSystem.get(getConf()).delete(outputDir, true); /* // Delete side data directory if it exists already. Path sdDir = new Path("sidedata"); FileSystem.get(getConf()).delete(sdDir, 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); } }