Example usage for org.apache.hadoop.mapred JobConf setInputFormat

List of usage examples for org.apache.hadoop.mapred JobConf setInputFormat

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.mapred.*
  5. JobConf
  6. setInputFormat

Introduction

In this page you can find the example usage for org.apache.hadoop.mapred JobConf setInputFormat.

Prototype

public void setInputFormat(Class<? extends InputFormat> theClass)

Source Link

Document

Set the InputFormat implementation for the map-reduce job.

Usage

From source file:edu.umd.cloud9.collection.wikipedia.WikipediaForwardIndexBuilder.java

License:Apache License

@SuppressWarnings("static-access")
@Override//from   w w w .j  a  v a2 s .  c  o  m
public int run(String[] args) throws Exception {
    Options options = new Options();
    options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input").create(INPUT_OPTION));
    options.addOption(
            OptionBuilder.withArgName("path").hasArg().withDescription("index file").create(INDEX_FILE_OPTION));
    options.addOption(OptionBuilder
            .withArgName("en|sv|nl|de|fr|ru|it|es|vi|pl|ja|pt|zh|uk|ca|fa|no|fi|id|ar|sr|ko|hi|zh_yue|cs|tr")
            .hasArg().withDescription("two-letter or six-letter language code").create(LANGUAGE_OPTION));

    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_OPTION) || !cmdline.hasOption(INDEX_FILE_OPTION)) {
        HelpFormatter formatter = new HelpFormatter();
        formatter.printHelp(this.getClass().getName(), options);
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }

    Path inputPath = new Path(cmdline.getOptionValue(INPUT_OPTION));
    String indexFile = cmdline.getOptionValue(INDEX_FILE_OPTION);

    String tmpPath = "tmp-" + WikipediaForwardIndexBuilder.class.getSimpleName() + "-" + RANDOM.nextInt(10000);

    if (!inputPath.isAbsolute()) {
        System.err.println("Error: " + INPUT_OPTION + " must be an absolute path!");
        return -1;
    }

    String language = null;
    if (cmdline.hasOption(LANGUAGE_OPTION)) {
        language = cmdline.getOptionValue(LANGUAGE_OPTION);
        if (!(language.length() == 2 || language.length() == 6)) {
            System.err.println("Error: \"" + language + "\" unknown language!");
            return -1;
        }
    }

    JobConf conf = new JobConf(getConf(), WikipediaForwardIndexBuilder.class);
    FileSystem fs = FileSystem.get(conf);

    LOG.info("Tool name: " + this.getClass().getName());
    LOG.info(" - input path: " + inputPath);
    LOG.info(" - index file: " + indexFile);
    LOG.info(" - language: " + language);
    LOG.info("Note: This tool only works on block-compressed SequenceFiles!");

    conf.setJobName(String.format("BuildWikipediaForwardIndex[%s: %s, %s: %s, %s: %s]", INPUT_OPTION, inputPath,
            INDEX_FILE_OPTION, indexFile, LANGUAGE_OPTION, language));

    conf.setNumReduceTasks(1);

    FileInputFormat.setInputPaths(conf, inputPath);
    FileOutputFormat.setOutputPath(conf, new Path(tmpPath));
    FileOutputFormat.setCompressOutput(conf, false);

    if (language != null) {
        conf.set("wiki.language", language);
    }

    conf.setInputFormat(NoSplitSequenceFileInputFormat.class);
    conf.setOutputKeyClass(IntWritable.class);
    conf.setOutputValueClass(Text.class);

    conf.setMapRunnerClass(MyMapRunner.class);
    conf.setReducerClass(IdentityReducer.class);

    // Delete the output directory if it exists already.
    fs.delete(new Path(tmpPath), true);

    RunningJob job = JobClient.runJob(conf);

    Counters counters = job.getCounters();
    int blocks = (int) counters.getCounter(Blocks.Total);

    LOG.info("number of blocks: " + blocks);

    LOG.info("Writing index file...");
    LineReader reader = new LineReader(fs.open(new Path(tmpPath + "/part-00000")));
    FSDataOutputStream out = fs.create(new Path(indexFile), true);

    out.writeUTF(edu.umd.cloud9.collection.wikipedia.WikipediaForwardIndex.class.getCanonicalName());
    out.writeUTF(inputPath.toString());
    out.writeInt(blocks);

    int cnt = 0;
    Text line = new Text();
    while (reader.readLine(line) > 0) {
        String[] arr = line.toString().split("\\s+");

        int docno = Integer.parseInt(arr[0]);
        int offset = Integer.parseInt(arr[1]);
        short fileno = Short.parseShort(arr[2]);

        out.writeInt(docno);
        out.writeInt(offset);
        out.writeShort(fileno);

        cnt++;

        if (cnt % 100000 == 0) {
            LOG.info(cnt + " blocks written");
        }
    }

    reader.close();
    out.close();

    if (cnt != blocks) {
        throw new RuntimeException("Error: mismatch in block count!");
    }

    // Clean up.
    fs.delete(new Path(tmpPath), true);

    return 0;
}

From source file:edu.umd.cloud9.demo.DemoWordCountJSON.java

License:Apache License

/**
 * Runs this tool.//from w  ww  . j  ava2 s .c o  m
 */
public int run(String[] args) throws Exception {
    if (args.length != 4) {
        printUsage();
        return -1;
    }

    String inputPath = args[0];
    String outputPath = args[1];

    int numMapTasks = Integer.parseInt(args[2]);
    int numReduceTasks = Integer.parseInt(args[3]);

    sLogger.info("Tool: DemoWordCountJSON");
    sLogger.info(" - input path: " + inputPath);
    sLogger.info(" - output path: " + outputPath);
    sLogger.info(" - number of mappers: " + numMapTasks);
    sLogger.info(" - number of reducers: " + numReduceTasks);

    JobConf conf = new JobConf(DemoWordCountTuple1.class);
    conf.setJobName("DemoWordCountJSON");

    conf.setNumMapTasks(numMapTasks);
    conf.setNumReduceTasks(numReduceTasks);

    FileInputFormat.setInputPaths(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));
    FileOutputFormat.setCompressOutput(conf, false);

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputKeyClass(MyKey.class);
    conf.setOutputValueClass(IntWritable.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);

    conf.setMapperClass(MyMapper.class);
    conf.setCombinerClass(MyReducer.class);
    conf.setReducerClass(MyReducer.class);

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

    long startTime = System.currentTimeMillis();
    JobClient.runJob(conf);
    sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

    return 0;
}

From source file:edu.umd.cloud9.demo.DemoWordCountTuple1.java

License:Apache License

/**
 * Runs this tool.//from  w  ww .  j a  v  a  2s .  co m
 */
public int run(String[] args) throws Exception {
    if (args.length != 4) {
        printUsage();
        return -1;
    }

    String inputPath = args[0];
    String outputPath = args[1];

    int numMapTasks = Integer.parseInt(args[2]);
    int numReduceTasks = Integer.parseInt(args[3]);

    sLogger.info("Tool: DemoWordCountTuple1");
    sLogger.info(" - input path: " + inputPath);
    sLogger.info(" - output path: " + outputPath);
    sLogger.info(" - number of mappers: " + numMapTasks);
    sLogger.info(" - number of reducers: " + numReduceTasks);

    JobConf conf = new JobConf(DemoWordCountTuple1.class);
    conf.setJobName("DemoWordCountTuple1");

    conf.setNumMapTasks(numMapTasks);
    conf.setNumReduceTasks(numReduceTasks);

    FileInputFormat.setInputPaths(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));
    FileOutputFormat.setCompressOutput(conf, false);

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputKeyClass(Tuple.class);
    conf.setOutputValueClass(IntWritable.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);

    conf.setMapperClass(MyMapper.class);
    conf.setCombinerClass(MyReducer.class);
    conf.setReducerClass(MyReducer.class);

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

    long startTime = System.currentTimeMillis();
    JobClient.runJob(conf);
    sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

    return 0;
}

From source file:edu.umd.cloud9.demo.DemoWordCountTuple2.java

License:Apache License

/**
 * Runs this tool./*from w  w  w.  j av  a  2s .  c  o m*/
 */
public int run(String[] args) throws Exception {
    if (args.length != 4) {
        printUsage();
        return -1;
    }

    String inputPath = args[0];
    String outputPath = args[1];

    int numMapTasks = Integer.parseInt(args[2]);
    int numReduceTasks = Integer.parseInt(args[3]);

    sLogger.info("Tool: DemoWordCountTuple2");
    sLogger.info(" - input path: " + inputPath);
    sLogger.info(" - output path: " + outputPath);
    sLogger.info(" - number of mappers: " + numMapTasks);
    sLogger.info(" - number of reducers: " + numReduceTasks);

    JobConf conf = new JobConf(DemoWordCountTuple2.class);
    conf.setJobName("DemoWordCountTuple2");

    conf.setNumMapTasks(numMapTasks);
    conf.setNumReduceTasks(numReduceTasks);

    FileInputFormat.setInputPaths(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));
    FileOutputFormat.setCompressOutput(conf, false);

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputKeyClass(Tuple.class);
    conf.setOutputValueClass(IntWritable.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);

    conf.setMapperClass(MapClass.class);
    conf.setCombinerClass(ReduceClass.class);
    conf.setReducerClass(ReduceClass.class);

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

    long startTime = System.currentTimeMillis();
    JobClient.runJob(conf);
    sLogger.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");

    return 0;
}

From source file:edu.umd.cloud9.example.simple.DemoMapredNullInput.java

License:Apache License

/**
 * Runs the demo.//w  ww .  j  ava2 s.com
 */
public static void main(String[] args) throws IOException {
    JobConf conf = new JobConf(DemoMapredNullInput.class);
    conf.setJobName("DemoMapredNullInput");

    conf.setNumMapTasks(10);
    conf.setNumReduceTasks(0);

    conf.setInputFormat(NullInputFormat.class);
    conf.setOutputFormat(NullOutputFormat.class);
    conf.setMapperClass(MyMapper.class);

    JobClient.runJob(conf);
}

From source file:edu.umd.cloud9.example.simple.DemoNullInput.java

License:Apache License

/**
 * Runs the demo.//  w ww.  j av a2  s.  c  om
 */
public static void main(String[] args) throws IOException {
    JobConf conf = new JobConf(DemoNullInput.class);
    conf.setJobName("DemoNullInput");

    conf.setNumMapTasks(10);
    conf.setNumReduceTasks(0);

    conf.setInputFormat(NullInputFormat.class);
    conf.setOutputFormat(NullOutputFormat.class);
    conf.setMapperClass(MyMapper.class);

    JobClient.runJob(conf);
}

From source file:edu.umd.cloud9.io.benchmark.HadoopSortRandomPairsOfInts.java

License:Apache License

/**
 * Runs this benchmark.//from www.j  a  v  a2  s. c  o m
 */
public static void main(String[] args) throws IOException {
    String inputPath = "random-pairs.seq";
    String outputPath = "random-pairs.sorted";
    int numMapTasks = 1;
    int numReduceTasks = 1;

    JobConf conf = new JobConf(HadoopSortRandomPairsOfInts.class);
    conf.setJobName("SortRandomPairsOfInts");

    conf.setNumMapTasks(numMapTasks);
    conf.setNumReduceTasks(numReduceTasks);

    FileInputFormat.setInputPaths(conf, new Path(inputPath));
    FileOutputFormat.setOutputPath(conf, new Path(outputPath));
    FileOutputFormat.setCompressOutput(conf, false);

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputKeyClass(PairOfInts.class);
    conf.setOutputValueClass(IntWritable.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapperClass(IdentityMapper.class);
    conf.setCombinerClass(IdentityReducer.class);
    conf.setReducerClass(IdentityReducer.class);

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

    long startTime;
    double duration;

    startTime = System.currentTimeMillis();

    JobClient.runJob(conf);

    duration = (System.currentTimeMillis() - startTime) / 1000.0;
    System.out.println("Job took " + duration + " seconds");
}

From source file:edu.umd.cloud9.pagerank.BuildPageRankRecords.java

License:Apache License

/**
 * Runs this tool.//from www  .j a va  2s.c  o m
 */
public int run(String[] args) throws Exception {
    if (args.length != 3) {
        printUsage();
        return -1;
    }

    String inputPath = args[0];
    String outputPath = args[1];
    int n = Integer.parseInt(args[2]);

    sLogger.info("Tool name: BuildPageRankRecords");
    sLogger.info(" - inputDir: " + inputPath);
    sLogger.info(" - outputDir: " + outputPath);
    sLogger.info(" - numNodes: " + n);

    JobConf conf = new JobConf(BuildPageRankRecords.class);
    conf.setJobName("PackageLinkGraph");

    conf.setNumMapTasks(1);
    conf.setNumReduceTasks(0);

    conf.setInt("NodeCnt", n);
    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);

    TextInputFormat.addInputPath(conf, new Path(inputPath));
    SequenceFileOutputFormat.setOutputPath(conf, new Path(outputPath));

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);

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

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

    conf.setMapperClass(MyMapper.class);
    conf.setReducerClass(IdentityReducer.class);

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

    JobClient.runJob(conf);

    return 0;
}

From source file:edu.umd.cloud9.pagerank.FindMaxPageRankNodes.java

License:Apache License

/**
 * Runs this tool./*  www. j  a  va  2  s  . co m*/
 */
public int run(String[] args) throws Exception {
    if (args.length != 3) {
        printUsage();
        return -1;
    }

    String inputPath = args[0];
    String outputPath = args[1];
    int n = Integer.parseInt(args[2]);

    sLogger.info("Tool name: FindMaxPageRankNodes");
    sLogger.info(" - input: " + inputPath);
    sLogger.info(" - output: " + outputPath);
    sLogger.info(" - n: " + n);

    JobConf conf = new JobConf(FindMaxPageRankNodes.class);
    conf.setJobName("FindMaxPageRankNodes");

    conf.setNumMapTasks(1);
    conf.setNumReduceTasks(1);

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

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

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    conf.setMapOutputKeyClass(IntWritable.class);
    conf.setMapOutputValueClass(FloatWritable.class);

    conf.setOutputKeyClass(IntWritable.class);
    conf.setOutputValueClass(FloatWritable.class);

    conf.setMapperClass(MyMapper.class);
    conf.setReducerClass(MyReducer.class);

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

    JobClient.runJob(conf);

    return 0;
}

From source file:edu.umd.cloud9.pagerank.PartitionGraph.java

License:Apache License

public int run(String[] args) throws IOException {
    if (args.length != 5) {
        printUsage();/*from w ww .java 2  s.  c  o  m*/
        return -1;
    }

    String inPath = args[0];
    String outPath = args[1];
    int numParts = Integer.parseInt(args[2]);
    boolean useRange = Integer.parseInt(args[3]) != 0;
    int nodeCount = Integer.parseInt(args[4]);

    sLogger.info("Tool name: PartitionGraph");
    sLogger.info(" - inputDir: " + inPath);
    sLogger.info(" - outputDir: " + outPath);
    sLogger.info(" - numPartitions: " + numParts);
    sLogger.info(" - useRange?: " + useRange);
    sLogger.info(" - nodeCnt: " + nodeCount);

    JobConf conf = new JobConf(PartitionGraph.class);

    conf.setJobName("Partition Graph " + numParts);
    conf.setNumReduceTasks(numParts);

    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);
    conf.set("mapred.child.java.opts", "-Xmx2048m");
    conf.setInt("NodeCount", nodeCount);

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

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);

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

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

    conf.setMapperClass(MapClass.class);
    conf.setReducerClass(ReduceClass.class);

    conf.setSpeculativeExecution(false);

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

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

    JobClient.runJob(conf);

    return 0;
}