Example usage for org.apache.hadoop.conf Configuration setInt

List of usage examples for org.apache.hadoop.conf Configuration setInt

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.conf.*
  5. Configuration
  6. setInt

Introduction

In this page you can find the example usage for org.apache.hadoop.conf Configuration setInt.

Prototype

public void setInt(String name, int value)

Source Link

Document

Set the value of the name property to an int.

Usage

From source file:edu.umd.cloud9.webgraph.driver.wt10g.GenericExtractLinks.java

License:Apache License

@Override
public int runTool() throws Exception {

    Configuration conf = getConf();
    Job job = new Job(conf);

    int numReducers = conf.getInt("Cloud9.Reducers", 200);

    String inputPath = conf.get("Cloud9.InputPath");
    String outputPath = conf.get("Cloud9.OutputPath");

    String mappingFile = conf.get("Cloud9.DocnoMappingFile");

    FileSystem fs = FileSystem.get(conf);
    if (!fs.exists(new Path(mappingFile))) {
        throw new RuntimeException("Error: Docno mapping data file " + mappingFile + " doesn't exist!");
    }//from  www .  j  a  v a 2  s.c  o m

    DistributedCache.addCacheFile(new Path(mappingFile).toUri(), job.getConfiguration());

    job.setJobName("ExtractLinks");
    conf.set("mapred.child.java.opts", "-Xmx2048m");
    conf.setInt("mapred.task.timeout", 60000000);

    job.setNumReduceTasks(numReducers);

    job.setMapperClass(GenericExtractLinks.Map.class);
    job.setCombinerClass(GenericExtractLinks.Reduce.class);
    job.setReducerClass(GenericExtractLinks.Reduce.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(ArrayListWritable.class);

    configer.applyJobConfig(job);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

    SequenceFileOutputFormat.setCompressOutput(job, true);
    SequenceFileOutputFormat.setOutputCompressionType(job, SequenceFile.CompressionType.BLOCK);

    recursivelyAddInputPaths(job, inputPath);

    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    LOG.info("ExtractLinks");
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - output path: " + outputPath);
    LOG.info(" - mapping file: " + mappingFile);
    LOG.info(" - include internal links? " + conf.getBoolean("Cloud9.IncludeInternalLinks", false));

    job.waitForCompletion(true);
    return 0;
}

From source file:edu.umd.cloud9.webgraph.TrecExtractLinks.java

License:Apache License

@Override
public int runTool() throws Exception {

    Configuration conf = getConf();
    conf.set("mapred.child.java.opts", "-Xmx3072m");
    conf.setInt("mapred.task.timeout", 60000000);
    Job job = new Job(conf);

    int numReducers = conf.getInt("Cloud9.Reducers", 200);

    String inputPath = conf.get("Cloud9.InputPath");
    String outputPath = conf.get("Cloud9.OutputPath");

    String mappingFile = conf.get("Cloud9.DocnoMappingFile");

    FileSystem fs = FileSystem.get(conf);
    if (!fs.exists(new Path(mappingFile))) {
        throw new RuntimeException("Error: Docno mapping data file " + mappingFile + " doesn't exist!");
    }//from www. ja v a  2 s .co m

    DistributedCache.addCacheFile(new Path(mappingFile).toUri(), job.getConfiguration());

    job.setJobName("ExtractLinks");
    job.setNumReduceTasks(numReducers);

    job.setJarByClass(TrecExtractLinks.class);
    job.setMapperClass(TrecExtractLinks.Map.class);
    job.setCombinerClass(TrecExtractLinks.Reduce.class);
    job.setReducerClass(TrecExtractLinks.Reduce.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(ArrayListWritable.class);

    configer.applyJobConfig(job);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

    SequenceFileOutputFormat.setCompressOutput(job, true);
    SequenceFileOutputFormat.setOutputCompressionType(job, SequenceFile.CompressionType.BLOCK);

    recursivelyAddInputPaths(job, inputPath);

    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    LOG.info("ExtractLinks");
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - output path: " + outputPath);
    LOG.info(" - mapping file: " + mappingFile);
    LOG.info(" - include internal links? " + conf.getBoolean("Cloud9.IncludeInternalLinks", false));

    job.waitForCompletion(true);
    return 0;
}

From source file:edu.umd.gorden2.BuildPersonalizedPageRankRecords.java

License:Apache License

/**
 * Runs this tool.//from  w  w w  .j av  a2 s  .  com
 */
@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 nodes").create(NUM_NODES));
    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(OUTPUT) || !cmdline.hasOption(NUM_NODES)) {
        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 n = Integer.parseInt(cmdline.getOptionValue(NUM_NODES));
    String m = cmdline.getOptionValue("sources");

    LOG.info("Tool name: " + BuildPersonalizedPageRankRecords.class.getSimpleName());
    LOG.info(" - inputDir: " + inputPath);
    LOG.info(" - outputDir: " + outputPath);
    LOG.info(" - numNodes: " + n);
    LOG.info(" - sources: " + m);

    Configuration conf = getConf();
    conf.setInt(NODE_CNT_FIELD, n);
    conf.setStrings("sources", m);
    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);

    Job job = Job.getInstance(conf);
    job.setJobName(BuildPersonalizedPageRankRecords.class.getSimpleName() + ":" + inputPath);
    job.setJarByClass(BuildPersonalizedPageRankRecords.class);

    job.setNumReduceTasks(0);

    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(PageRankNode.class);

    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(PageRankNode.class);

    job.setMapperClass(MyMapper.class);

    // Delete the output directory if it exists already.
    FileSystem.get(conf).delete(new Path(outputPath), true);

    job.waitForCompletion(true);

    return 0;
}

From source file:edu.umd.gorden2.ExtractTopPersonalizedPageRankNodes.java

License:Apache License

/**
 * Runs this tool./* w ww  .  j  a  v a  2 s .c  o  m*/
 */
@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;
}

From source file:edu.umd.gorden2.PartitionGraph.java

License:Apache License

/**
 * Runs this tool.// w  w  w.j av a2 s .c  o  m
 */
@SuppressWarnings({ "static-access" })
public int run(String[] args) throws Exception {
    Options options = new Options();

    options.addOption(new Option(RANGE, "use range partitioner"));

    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 nodes").create(NUM_NODES));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of partitions")
            .create(NUM_PARTITIONS));

    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) || !cmdline.hasOption(NUM_NODES)
            || !cmdline.hasOption(NUM_PARTITIONS)) {
        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 inPath = cmdline.getOptionValue(INPUT);
    String outPath = cmdline.getOptionValue(OUTPUT);
    int nodeCount = Integer.parseInt(cmdline.getOptionValue(NUM_NODES));
    int numParts = Integer.parseInt(cmdline.getOptionValue(NUM_PARTITIONS));
    boolean useRange = cmdline.hasOption(RANGE);

    LOG.info("Tool name: " + PartitionGraph.class.getSimpleName());
    LOG.info(" - input dir: " + inPath);
    LOG.info(" - output dir: " + outPath);
    LOG.info(" - num partitions: " + numParts);
    LOG.info(" - node cnt: " + nodeCount);
    LOG.info(" - use range partitioner: " + useRange);

    Configuration conf = getConf();
    conf.setInt("NodeCount", nodeCount);

    Job job = Job.getInstance(conf);
    job.setJobName(PartitionGraph.class.getSimpleName() + ":" + inPath);
    job.setJarByClass(PartitionGraph.class);

    job.setNumReduceTasks(numParts);

    FileInputFormat.setInputPaths(job, new Path(inPath));
    FileOutputFormat.setOutputPath(job, new Path(outPath));

    job.setInputFormatClass(NonSplitableSequenceFileInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(PageRankNode.class);

    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(PageRankNode.class);

    //if (useRange) {
    //job.setPartitionerClass(RangePartitioner.class);
    //}

    FileSystem.get(conf).delete(new Path(outPath), true);

    job.waitForCompletion(true);

    return 0;
}

From source file:edu.umd.honghongie.BuildPersonalizedPageRankRecords.java

License:Apache License

/**
 * Runs this tool./* w  w  w . j a  v  a  2  s. c  o  m*/
 */

@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 nodes").create(NUM_NODES));
    options.addOption(OptionBuilder.withArgName("node").hasArg()
            .withDescription("source node (i.e., destination of the random jump)").create(SOURCE));

    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) || !cmdline.hasOption(NUM_NODES)
            || !cmdline.hasOption(SOURCE)) {
        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 n = Integer.parseInt(cmdline.getOptionValue(NUM_NODES));
    String source = cmdline.getOptionValue(SOURCE); //get source information from cmdline

    LOG.info("Tool name: " + BuildPersonalizedPageRankRecords.class.getSimpleName());
    LOG.info(" - inputDir: " + inputPath);
    LOG.info(" - outputDir: " + outputPath);
    LOG.info(" - numNodes: " + n);
    LOG.info(" - source: " + source);

    Configuration conf = getConf();
    conf.setInt(NODE_CNT_FIELD, n);
    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);
    conf.set(SOURCE_NODES, source); //set source node and pass it to mapper setup

    Job job = Job.getInstance(conf);
    job.setJobName(BuildPersonalizedPageRankRecords.class.getSimpleName() + ":" + inputPath);
    job.setJarByClass(BuildPersonalizedPageRankRecords.class);

    job.setNumReduceTasks(0);

    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(PageRankNode.class);

    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(PageRankNode.class);

    job.setMapperClass(MyMapper.class);

    // Delete the output directory if it exists already.
    FileSystem.get(conf).delete(new Path(outputPath), true);

    job.waitForCompletion(true);

    return 0;
}

From source file:edu.umd.honghongie.ExtractTopPersonalizedPageRankNodes.java

License:Apache License

private void iterateSort(int i, int source, int n, String input, String output) throws Exception {

    Configuration conf = getConf();
    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);
    conf.setInt("n", n);
    conf.setInt("times", i);
    conf.setInt("source", source);

    Job job = Job.getInstance(conf);//from   w ww.  j  ava2 s .c  o  m
    job.setJobName(ExtractTopPersonalizedPageRankNodes.class.getName() + ":" + input);
    job.setJarByClass(ExtractTopPersonalizedPageRankNodes.class);

    job.setNumReduceTasks(1);

    FileInputFormat.addInputPath(job, new Path(input));
    FileOutputFormat.setOutputPath(job, new Path(output + Integer.toString(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(output + Integer.toString(i)), true);

    long startTime = System.currentTimeMillis();
    job.waitForCompletion(true);
    System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

}

From source file:edu.umd.honghongie.PartitionGraph.java

License:Apache License

/**
 * Runs this tool.//  w w w . j a v  a2s.  co  m
 */
@SuppressWarnings({ "static-access" })
public int run(String[] args) throws Exception {
    Options options = new Options();

    options.addOption(new Option(RANGE, "use range partitioner"));

    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 nodes").create(NUM_NODES));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of partitions")
            .create(NUM_PARTITIONS));

    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) || !cmdline.hasOption(NUM_NODES)
            || !cmdline.hasOption(NUM_PARTITIONS)) {
        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 inPath = cmdline.getOptionValue(INPUT);
    String outPath = cmdline.getOptionValue(OUTPUT);
    int nodeCount = Integer.parseInt(cmdline.getOptionValue(NUM_NODES));
    int numParts = Integer.parseInt(cmdline.getOptionValue(NUM_PARTITIONS));
    boolean useRange = cmdline.hasOption(RANGE);

    LOG.info("Tool name: " + PartitionGraph.class.getSimpleName());
    LOG.info(" - input dir: " + inPath);
    LOG.info(" - output dir: " + outPath);
    LOG.info(" - num partitions: " + numParts);
    LOG.info(" - node cnt: " + nodeCount);
    LOG.info(" - use range partitioner: " + useRange);

    Configuration conf = getConf();
    conf.setInt("NodeCount", nodeCount);

    Job job = Job.getInstance(conf);
    job.setJobName(PartitionGraph.class.getSimpleName() + ":" + inPath);
    job.setJarByClass(PartitionGraph.class);

    job.setNumReduceTasks(numParts);

    FileInputFormat.setInputPaths(job, new Path(inPath));
    FileOutputFormat.setOutputPath(job, new Path(outPath));

    job.setInputFormatClass(NonSplitableSequenceFileInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(PageRankNode.class);

    job.setOutputKeyClass(IntWritable.class);
    //  job.setOutputKeyClass(LongWritable.class);
    job.setOutputValueClass(PageRankNode.class);

    if (useRange) {
        job.setPartitionerClass(RangePartitioner.class);
    }

    FileSystem.get(conf).delete(new Path(outPath), true);

    job.waitForCompletion(true);

    return 0;
}

From source file:edu.umd.JBizz.BuildPersonalizedPageRankRecords.java

License:Apache License

/**
 * Runs this tool./*from   w  ww .j  a  va2  s . c o  m*/
 */
@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 nodes").create(NUM_NODES));
    options.addOption(OptionBuilder.withArgName("sources").hasArg().withDescription("Personalization Nodes")
            .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(OUTPUT) || !cmdline.hasOption(NUM_NODES)
            || !cmdline.hasOption(SOURCES)) {
        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 n = Integer.parseInt(cmdline.getOptionValue(NUM_NODES));
    String sources = cmdline.getOptionValue(SOURCES);

    String[] sourceList = sources.trim().split(",");
    int numSources = sourceList.length;

    int source = Integer.parseInt(sourceList[0]);

    int[] sourceNodes = new int[numSources];
    for (int i = 0; i < numSources; i++) {
        sourceNodes[i] = Integer.parseInt(sourceList[i]);
    }

    LOG.info("Tool name: " + BuildPersonalizedPageRankRecords.class.getSimpleName());
    LOG.info(" - inputDir: " + inputPath);
    LOG.info(" - outputDir: " + outputPath);
    LOG.info(" - numNodes: " + n);
    LOG.info("source list: " + sourceList);
    LOG.info("first source: " + source);

    Configuration conf = getConf();
    conf.setInt(NODE_CNT_FIELD, n);
    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);
    conf.setInt(SOURCE, source);
    conf.setInt(NUM_SOURCES, numSources);
    conf.set(SOURCE_NODES, sources);

    Job job = Job.getInstance(conf);
    job.setJobName(BuildPersonalizedPageRankRecords.class.getSimpleName() + ":" + inputPath);
    job.setJarByClass(BuildPersonalizedPageRankRecords.class);

    job.setNumReduceTasks(0);

    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(PageRankNode.class);

    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(PageRankNode.class);

    job.setMapperClass(MyMapper.class);

    // Delete the output directory if it exists already.
    FileSystem.get(conf).delete(new Path(outputPath), true);

    job.waitForCompletion(true);

    return 0;
}

From source file:edu.umd.JBizz.ExtractTopPersonalizedPageRankNodes.java

License:Apache License

/**
 * Runs this tool./*  ww w . ja  va  2  s.  c  om*/
 */
@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("top n").create(TOP));

    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) || !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 = cmdline.getOptionValue(OUTPUT);
    int n = Integer.parseInt(cmdline.getOptionValue(TOP));

    LOG.info("Tool name: " + ExtractTopPersonalizedPageRankNodes.class.getSimpleName());
    LOG.info(" - input: " + inputPath);
    LOG.info(" - output: " + outputPath);
    LOG.info(" - top: " + n);

    Configuration conf = getConf();
    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);
    conf.setInt("n", n);

    Job job = Job.getInstance(conf);
    job.setJobName(ExtractTopPersonalizedPageRankNodes.class.getName() + ":" + inputPath);
    job.setJarByClass(ExtractTopPersonalizedPageRankNodes.class);

    job.setNumReduceTasks(1);

    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    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), true);

    job.waitForCompletion(true);

    return 0;
}