Java tutorial
/* * Cloud9: A MapReduce Library for Hadoop * * 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.IOException; import java.util.Iterator; import java.util.StringTokenizer; 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.Option; 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.FileStatus; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.WritableComparable; import org.apache.hadoop.io.WritableComparator; 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.util.Tool; import org.apache.hadoop.util.ToolRunner; import org.apache.log4j.Logger; import org.json.JSONObject; import tl.lin.data.pair.PairOfStringInt; import cern.colt.Arrays; /** * Simple word count demo. * * @author Shrawan Raina */ public class UserLocation extends Configured implements Tool { private static final Logger LOG = Logger.getLogger(UserLocation.class); // Mapper: emits (token, 1) for every word occurrence. private static class MapClass1 extends Mapper<LongWritable, Text, Text, IntWritable> { // Reuse objects to save overhead of object creation. private final static IntWritable ONE = new IntWritable(1); private final static Text WORD = new Text(); private static String wrd = new String(); @Override public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String line = ((Text) value).toString(); JSONObject obj = new JSONObject(line); JSONObject user = obj.getJSONObject("user"); //JSONObject rtStatus = obj.getJSONObject("retweeted_status"); //JSONObject rtUser = rtStatus.getJSONObject("user"); String user_location = user.getString("location"); //String rt_location = rtUser.getString("location"); //System.out.println("RT User: <<<<<<<" + rt_location); System.out.println("User: <<<<<<<" + user_location); if (user_location != "" || user_location != null) WORD.set(user_location); context.write(WORD, ONE); } } /* // Mapper with in-mapper combiner optimization. private static class MapWithInMapperCombiningClass1 extends Mapper<LongWritable, Text, Text, IntWritable> { @Override public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { } @Override public void cleanup(Context context) throws IOException, InterruptedException { } } // Combiner: sums partial PageRank contributions and passes node structure // along. private static class CombineClass1 extends Reducer<Text, IntWritable, Text, IntWritable> { @Override public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { } } */ // Reducer: sums up all the counts. private static class ReduceClass1 extends Reducer<Text, IntWritable, Text, IntWritable> { // Reuse objects. private final static IntWritable SUM = new IntWritable(); @Override public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { // Sum up values. Iterator<IntWritable> iter = values.iterator(); int sum = 0; while (iter.hasNext()) { sum += iter.next().get(); } SUM.set(sum); context.write(key, SUM); } } // Mapper: emits (token, 1) for every word occurrence. private static class MapClass2 extends Mapper<LongWritable, Text, PairOfStringInt, NullWritable> { // Reuse objects to save overhead of object creation. private static PairOfStringInt WORD = new PairOfStringInt(); private static final NullWritable VAL = NullWritable.get(); @Override public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String line = ((Text) value).toString(); String[] output = line.split("\t"); WORD.set(output[0], Integer.parseInt(output[1])); //System.out.println(WORD + "<<<<<" + output[1]); context.write(WORD, VAL); } } /* // Mapper with in-mapper combiner optimization. private static class MapWithInMapperCombiningClass2 extends Mapper<LongWritable, Text, Text, IntWritable> { @Override public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { } @Override public void cleanup(Context context) throws IOException, InterruptedException { } } // Combiner: sums partial PageRank contributions and passes node structure // along. private static class CombineClass2 extends Reducer<PairOfStringInt, IntWritable, Text, IntWritable> { @Override public void reduce(PairOfStringInt key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { } } */ // Reducer: sums up all the counts. private static class ReduceClass2 extends Reducer<PairOfStringInt, NullWritable, PairOfStringInt, NullWritable> { // Reuse objects. private final static Text WORD = new Text(); @Override public void reduce(PairOfStringInt key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException { // Sum up values. //WORD.set(key.getLeftElement()); context.write(key, NullWritable.get()); } } public static class CustomKeyComparator extends WritableComparator { public CustomKeyComparator() { super(PairOfStringInt.class, true); } private Integer int1; private Integer int2; @SuppressWarnings("rawtypes") @Override public int compare(WritableComparable w1, WritableComparable w2) { PairOfStringInt k1 = (PairOfStringInt) w1; PairOfStringInt k2 = (PairOfStringInt) w2; int1 = new Integer(k1.getRightElement()); int2 = new Integer(k2.getRightElement()); int result = -1 * int1.compareTo(int2); return result; } } public static class CustomGroupingComparator extends WritableComparator { protected CustomGroupingComparator() { super(PairOfStringInt.class, true); } @SuppressWarnings("rawtypes") @Override public int compare(WritableComparable w1, WritableComparable w2) { PairOfStringInt k1 = (PairOfStringInt) w1; PairOfStringInt k2 = (PairOfStringInt) w2; return k1.getLeftElement().compareTo(k2.getLeftElement()); } } public static class CustomKeyPartitioner extends Partitioner<PairOfStringInt, NullWritable> { @Override public int getPartition(PairOfStringInt key, NullWritable val, int numPartitions) { int hash = key.getLeftElement().hashCode(); int partition = hash % numPartitions; return partition; } } /** * Creates an instance of this tool. */ public UserLocation() { } private static final String INPUT = "input"; private static final String OUTPUT = "output"; private static final String NUM_REDUCERS = "numReducers"; private static final String COMBINER = "useCombiner"; private static final String INMAPPER_COMBINER = "useInMapperCombiner"; /** * 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)); options.addOption(new Option(COMBINER, "use combiner")); options.addOption(new Option(INMAPPER_COMBINER, "user in-mapper combiner")); 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; boolean useCombiner = cmdline.hasOption(COMBINER); boolean useInmapCombiner = cmdline.hasOption(INMAPPER_COMBINER); LOG.info("Tool: " + UserLocation.class.getSimpleName()); LOG.info(" - input path: " + inputPath); LOG.info(" - output path: " + outputPath); LOG.info(" - number of reducers: " + reduceTasks); LOG.info(" - use combiner: " + useCombiner); LOG.info(" - use in-mapper combiner: " + useInmapCombiner); runJob1(inputPath, outputPath, reduceTasks, useCombiner, useInmapCombiner); runJob2(outputPath, useCombiner, useInmapCombiner); return 0; } private void runJob1(String inputPath, String outputPath, int numNodes, boolean useCombiner, boolean useInMapperCombiner) throws Exception { Configuration conf = getConf(); Job job = Job.getInstance(conf); job.setJobName(UserLocation.class.getSimpleName()); job.setJarByClass(UserLocation.class); job.setNumReduceTasks(numNodes); FileInputFormat.setInputPaths(job, new Path(inputPath)); FileOutputFormat.setOutputPath(job, new Path(outputPath)); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setMapperClass(MapClass1.class); //job.setCombinerClass(ReduceClass.class); job.setReducerClass(ReduceClass1.class); // Delete the output directory if it exists already. Path outputDir = new Path(outputPath); FileSystem.get(conf).delete(outputDir, true); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); //return 0; } private void runJob2(String basePath, boolean useCombiner, boolean useInMapperCombiner) throws Exception { Configuration conf = getConf(); Job job = Job.getInstance(conf); job.setJobName(UserLocation.class.getSimpleName()); job.setJarByClass(UserLocation.class); // We need to actually count the number of part files to get the number // of partitions (because // the directory might contain _log). int numPartitions = 0; for (FileStatus s : FileSystem.get(getConf()).listStatus(new Path(basePath))) { if (s.getPath().getName().contains("part-")) numPartitions++; } job.setNumReduceTasks(numPartitions); FileInputFormat.setInputPaths(job, new Path(basePath)); String outputPath = basePath + "-out"; FileOutputFormat.setOutputPath(job, new Path(outputPath)); job.setMapOutputKeyClass(PairOfStringInt.class); job.setMapOutputValueClass(NullWritable.class); job.setOutputKeyClass(PairOfStringInt.class); job.setOutputValueClass(NullWritable.class); job.setMapperClass(MapClass2.class); //job.setCombinerClass(ReduceClass2.class); job.setReducerClass(ReduceClass2.class); //job.setPartitionerClass(CustomKeyPartitioner.class); job.setGroupingComparatorClass(CustomGroupingComparator.class); job.setSortComparatorClass(CustomKeyComparator.class); // Delete the output directory if it exists already. Path outputDir = new Path(outputPath); FileSystem.get(conf).delete(outputDir, true); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); LOG.info("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 UserLocation(), args); } }