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.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.Configuration; import org.apache.hadoop.conf.Configured; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.hbase.HBaseConfiguration; import org.apache.hadoop.hbase.HColumnDescriptor; import org.apache.hadoop.hbase.HTableDescriptor; import org.apache.hadoop.hbase.TableName; import org.apache.hadoop.hbase.client.HBaseAdmin; import org.apache.hadoop.hbase.client.Put; import org.apache.hadoop.hbase.io.ImmutableBytesWritable; import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil; import org.apache.hadoop.hbase.mapreduce.TableReducer; import org.apache.hadoop.hbase.util.Bytes; import org.apache.hadoop.io.BytesWritable; 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.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; 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.PairOfInts; import tl.lin.data.pair.PairOfObjectInt; import tl.lin.data.pair.PairOfStringInt; public class BuildInvertedIndexHBaseCompressed extends Configured implements Tool { private static final Logger LOG = Logger.getLogger(BuildInvertedIndexHBaseCompressed.class); public static final String[] FAMILIES = { "p" }; public static final byte[] CF = FAMILIES[0].getBytes(); public static final byte[] COUNT = "count".getBytes(); 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(); @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())); } */ } } } 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, tf); 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(); } } } } public static class MyTableReducer extends TableReducer<PairOfStringInt, VIntWritable, ImmutableBytesWritable> { 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(); public void setup(Context context) { prevKey = null; prevDocNo = 0; df = 0; tf = 0; dgap = 0; } 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, tf); 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()) ); Put put = new Put(Bytes.toBytes(KEY.toString())); put.add(CF, COUNT, dfpost.toByteArray()); context.write(null, put); 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(); } } } 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())); Put put = new Put(Bytes.toBytes(KEY.toString())); put.add(CF, COUNT, dfpost.toByteArray()); context.write(null, put); postings.close(); stream.close(); } } private BuildInvertedIndexHBaseCompressed() { } 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 outputTable = cmdline.getOptionValue(OUTPUT); int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS)) : 1; // If the table doesn't already exist, create it. Configuration conf = getConf(); conf.addResource(new Path("/etc/hbase/conf/hbase-site.xml")); Configuration hbaseConfig = HBaseConfiguration.create(conf); HBaseAdmin admin = new HBaseAdmin(hbaseConfig); if (admin.tableExists(outputTable)) { LOG.info(String.format("Table '%s' exists: dropping table and recreating.", outputTable)); LOG.info(String.format("Disabling table '%s'", outputTable)); admin.disableTable(outputTable); LOG.info(String.format("Droppping table '%s'", outputTable)); admin.deleteTable(outputTable); } HTableDescriptor tableDesc = new HTableDescriptor(TableName.valueOf(outputTable)); for (int i = 0; i < FAMILIES.length; i++) { HColumnDescriptor hColumnDesc = new HColumnDescriptor(FAMILIES[i]); tableDesc.addFamily(hColumnDesc); } admin.createTable(tableDesc); LOG.info(String.format("Successfully created table '%s'", outputTable)); admin.close(); // Now we're ready to start running MapReduce. LOG.info("Tool: " + HBaseWordCount.class.getSimpleName()); LOG.info(" - input path: " + inputPath); LOG.info(" - output table: " + outputTable); LOG.info(" - number of reducers: " + reduceTasks); Job job = Job.getInstance(conf); job.setJobName(BuildInvertedIndexHBaseCompressed.class.getSimpleName()); job.setJarByClass(BuildInvertedIndexHBaseCompressed.class); job.setMapOutputKeyClass(PairOfStringInt.class); job.setMapOutputValueClass(VIntWritable.class); job.setMapperClass(MyMapper.class); job.setReducerClass(MyReducer.class); job.setNumReduceTasks(reduceTasks); // job.setOutputKeyClass(Text.class); // job.setOutputValueClass(PairOfWritables.class); FileInputFormat.setInputPaths(job, new Path(inputPath)); TableMapReduceUtil.initTableReducerJob(outputTable, MyTableReducer.class, job); // Delete the output directory if it exists already. Path outputDir = new Path(outputTable); 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 BuildInvertedIndexHBaseCompressed(), args); } }