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.gorden2; import java.io.*; import java.util.Arrays; import java.util.Iterator; import java.net.*; import java.text.DecimalFormat; import java.text.NumberFormat; 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.FileStatus; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.FloatWritable; import org.apache.hadoop.io.IntWritable; 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.mapreduce.lib.input.SequenceFileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; 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.pair.PairOfObjectFloat; import tl.lin.data.queue.TopScoredObjects; public class ExtractTopPersonalizedPageRankNodes extends Configured implements Tool { private static final Logger LOG = Logger.getLogger(ExtractTopPersonalizedPageRankNodes.class); private static class MyMapper extends Mapper<IntWritable, PageRankNode, IntWritable, FloatWritable> { private TopScoredObjects<Integer> queue; int index; @Override public void setup(Context context) throws IOException { int k = context.getConfiguration().getInt("n", 100); queue = new TopScoredObjects<Integer>(k); index = context.getConfiguration().getInt("index", -1); } @Override public void map(IntWritable nid, PageRankNode node, Context context) throws IOException, InterruptedException { queue.add(node.getNodeId(), node.getPageRank().get(index)); } @Override public void cleanup(Context context) throws IOException, InterruptedException { IntWritable key = new IntWritable(); FloatWritable value = new FloatWritable(); for (PairOfObjectFloat<Integer> pair : queue.extractAll()) { key.set(pair.getLeftElement()); value.set(pair.getRightElement()); context.write(key, value); } } } private static class MyReducer extends Reducer<IntWritable, FloatWritable, IntWritable, FloatWritable> { private static TopScoredObjects<Integer> queue; @Override public void setup(Context context) throws IOException { int k = context.getConfiguration().getInt("n", 100); queue = new TopScoredObjects<Integer>(k); } @Override public void reduce(IntWritable nid, Iterable<FloatWritable> iterable, Context context) throws IOException { Iterator<FloatWritable> iter = iterable.iterator(); queue.add(nid.get(), iter.next().get()); // Shouldn't happen. Throw an exception. if (iter.hasNext()) { throw new RuntimeException(); } } @Override public void cleanup(Context context) throws IOException, InterruptedException { IntWritable key = new IntWritable(); FloatWritable value = new FloatWritable(); for (PairOfObjectFloat<Integer> pair : queue.extractAll()) { key.set(pair.getLeftElement()); float v = (float) StrictMath.exp(pair.getRightElement()); NumberFormat formatter = new DecimalFormat("0.00000"); v = Float.parseFloat(formatter.format(v)); LOG.info("-float" + v); value.set(v); context.write(key, value); } } } public ExtractTopPersonalizedPageRankNodes() { } private static final String INPUT = "input"; private static final String OUTPUT = "output"; private static final String TOP = "top"; /** * 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("num").hasArg().withDescription("top n").create(TOP)); options.addOption( OptionBuilder.withArgName("sources").hasArg().withDescription("sources").create("sources")); 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(TOP)) { 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 = "result"; int n = Integer.parseInt(cmdline.getOptionValue(TOP)); String m = cmdline.getOptionValue("sources"); LOG.info("Tool name: " + ExtractTopPersonalizedPageRankNodes.class.getSimpleName()); LOG.info(" - input: " + inputPath); LOG.info(" - output: " + outputPath); LOG.info(" - top: " + n); LOG.info(" - sources: " + m); Configuration conf = getConf(); conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024); conf.setInt("n", n); String[] mm = m.split(","); for (int i = 0; i < mm.length; i++) { Job job = Job.getInstance(conf); job.setJobName(ExtractTopPersonalizedPageRankNodes.class.getName() + ":" + inputPath + "#" + i); job.setJarByClass(ExtractTopPersonalizedPageRankNodes.class); job.getConfiguration().setInt("index", i); job.setNumReduceTasks(1); FileInputFormat.addInputPath(job, new Path(inputPath)); FileOutputFormat.setOutputPath(job, new Path(outputPath + "/" + i)); job.setInputFormatClass(SequenceFileInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(FloatWritable.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(FloatWritable.class); job.setMapperClass(MyMapper.class); job.setReducerClass(MyReducer.class); // Delete the output directory if it exists already. FileSystem.get(conf).delete(new Path(outputPath + "/" + i), true); job.waitForCompletion(true); } for (int i = 0; i < mm.length; i++) { String outm = outputPath + "/" + i + "/part-r-00000"; FileSystem fs = FileSystem.get(getConf()); for (FileStatus f : fs.listStatus(new Path(outm))) { BufferedReader d = new BufferedReader(new InputStreamReader(fs.open(f.getPath()))); String line = "Source: " + mm[i]; System.out.println(line); while (true) { line = d.readLine(); if (line == null) break; System.out.println(line); } } } return 0; } /** * Dispatches command-line arguments to the tool via the {@code ToolRunner}. */ public static void main(String[] args) throws Exception { int res = ToolRunner.run(new ExtractTopPersonalizedPageRankNodes(), args); System.exit(res); } }