Example usage for org.apache.hadoop.mapreduce Job setOutputKeyClass

List of usage examples for org.apache.hadoop.mapreduce Job setOutputKeyClass

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.mapreduce.*
  5. Job
  6. setOutputKeyClass

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce Job setOutputKeyClass.

Prototype

public void setOutputKeyClass(Class<?> theClass) throws IllegalStateException

Source Link

Document

Set the key class for the job output data.

Usage

From source file:com.ifeng.vdn.iparea.parser.IPAreaLocalDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    Job job = Job.getInstance(getConf());

    job.setJarByClass(getClass());//from w ww  . jav  a  2  s.  co  m

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(IPAreaMapper.class);
    job.setReducerClass(IPAreaReducer.class);

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

    return job.waitForCompletion(true) ? 0 : 1;

}

From source file:com.ifeng.vdn.loggroup.mapper.VideologGroupDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getSimpleName());
        ToolRunner.printGenericCommandUsage(System.err);
        return -1;
    }//from   w  w w.j  a v a 2 s . c o m

    Job job = Job.getInstance(super.getConf());

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(VideoLogGroupMapper.class);
    job.setReducerClass(VideologGroupReducer.class);
    job.setCombinerClass(VideologGroupReducer.class);

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

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.ifeng.vdn.logparser.mapper.VideoLogDriver.java

License:Apache License

@Override
public int run(String[] paths) throws Exception {
    Job job = Job.getInstance(super.getConf());
    job.setJarByClass(getClass());//w w  w. j ava 2 s  .c om

    FileInputFormat.addInputPath(job, new Path(paths[0]));
    FileOutputFormat.setOutputPath(job, new Path(paths[1]));

    job.setMapperClass(VideoLogMapper.class);
    job.setReducerClass(VideoLogReducer.class);
    job.setCombinerClass(VideoLogReducer.class);

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

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.ifeng.vdn.parser.VideoLogParseDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    Job job = Job.getInstance(getConf());

    job.setJarByClass(getClass());/*w  ww.  j  a v a 2s .c om*/

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(VideoLogParseMapper.class);
    job.setReducerClass(VideoLogParseReducer.class);
    job.setCombinerClass(VideoLogParseReducer.class);

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

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.ifeng.vdn.parser.VideoLogParseLocalDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    Job job = Job.getInstance(getConf());

    job.setJarByClass(getClass());//  w ww  .  jav a  2  s  .c o  m

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(VideoLogParseMapper.class);
    job.setReducerClass(VideoLogParseReducer.class);
    job.setCombinerClass(VideoLogParseReducer.class);

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

    return job.waitForCompletion(true) ? 0 : 1;

}

From source file:com.ifeng.vdn.videolog.sort.SortGroupResultPreprocessor.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getSimpleName());
        ToolRunner.printGenericCommandUsage(System.err);
        return -1;
    }/*  www. j a v a2  s.  c  o m*/

    Job job = Job.getInstance(getConf());
    job.setMapperClass(SortGroupResultMapper.class);
    job.setNumReduceTasks(0);

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

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    // Sort data by total number:
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.iflytek.spider.crawl.CrawlDb.java

License:Apache License

public static Job createJob(Configuration config, Path crawlDb) throws IOException {
    Path newCrawlDb = new Path(crawlDb, Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));

    Job job = AvroJob.getAvroJob(config);
    job.setJobName("crawldb " + crawlDb);

    Path current = new Path(crawlDb, CURRENT_NAME);
    if (FileSystem.get(config).exists(current)) {
        FileInputFormat.addInputPath(job, current);
    }/*from  w  ww.  java2s  .  c o  m*/
    job.setInputFormatClass(AvroPairInputFormat.class);

    job.setMapperClass(CrawlDbFilter.class);
    job.setReducerClass(CrawlDbReducer.class);

    FileOutputFormat.setOutputPath(job, newCrawlDb);
    job.setOutputFormatClass(AvroMapOutputFormat.class);
    job.setOutputKeyClass(String.class);
    job.setOutputValueClass(CrawlDatum.class);

    return job;
}

From source file:com.iflytek.spider.crawl.GeneratorSmart.java

License:Apache License

/**
 * Generate fetchlists in one or more segments. Whether to filter URLs or not
 * is read from the crawl.generate.filter property in the configuration files.
 * If the property is not found, the URLs are filtered. Same for the
 * normalisation./*from w w w . j av  a  2 s  .  co  m*/
 * 
 * @param dbDir
 *          Crawl database directory
 * @param segments
 *          Segments directory
 * @param numLists
 *          Number of reduce tasks
 * @param curTime
 *          Current time in milliseconds
 * 
 * @return Path to generated segment or null if no entries were selected
 * 
 * @throws IOException
 *           When an I/O error occurs
 * @throws ClassNotFoundException
 * @throws InterruptedException
 */
public Path[] generate(Path dbDir, Path segments, int numLists, long curTime, boolean force)
        throws IOException, InterruptedException, ClassNotFoundException {
    //getConf().set("mapred.temp.dir", "d:/tmp");
    Path tempDir = new Path(
            getConf().get("mapred.temp.dir", ".") + "/generate-temp-" + System.currentTimeMillis());

    Path lock = new Path(dbDir, CrawlDb.LOCK_NAME);
    FileSystem fs = FileSystem.get(getConf());
    LockUtil.createLockFile(fs, lock, force);

    LOG.info("Generator: Selecting best-scoring urls due for fetch.");
    LOG.info("Generator: starting");

    Job job = AvroJob.getAvroJob(getConf());
    if (numLists == -1) { // for politeness make
        numLists = job.getNumReduceTasks(); // a partition per fetch task
    }
    if ("local".equals(job.getConfiguration().get("mapred.job.tracker")) && numLists != 1) {
        // override
        LOG.info("Generator: jobtracker is 'local', generating exactly one partition.");
        numLists = 1;
    }
    LOG.info("Generator: with " + numLists + " partition.");
    job.getConfiguration().setLong(GENERATOR_CUR_TIME, curTime);
    // record real generation time
    long generateTime = System.currentTimeMillis();
    job.getConfiguration().setLong(Spider.GENERATE_TIME_KEY, generateTime);

    FileInputFormat.addInputPath(job, new Path(dbDir, CrawlDb.CURRENT_NAME));
    job.setInputFormatClass(AvroPairInputFormat.class);

    job.setMapperClass(SelectorMapper.class);
    job.setReducerClass(SelectorReducer.class);

    FileOutputFormat.setOutputPath(job, tempDir);
    //job.setOutputFormatClass(AvroPairOutputFormat.class);
    job.setOutputFormatClass(GeneratorOutputFormat.class);
    job.setOutputKeyClass(Float.class);
    job.setOutputValueClass(SelectorEntry.class);
    // AvroMultipleOutputs.addNamedOutput(job, "seq",
    // AvroPairOutputFormat.class, Float.class, SelectorEntry.class);
    try {
        job.waitForCompletion(true);
    } catch (IOException e) {
        e.printStackTrace();
        return null;
    }

    // read the subdirectories generated in the temp
    // output and turn them into segments
    List<Path> generatedSegments = new ArrayList<Path>();

    FileStatus[] status = fs.listStatus(tempDir);
    try {
        for (FileStatus stat : status) {
            Path subfetchlist = stat.getPath();
            if (!subfetchlist.getName().startsWith("fetchlist-"))
                continue;
            // start a new partition job for this segment
            Path newSeg = partitionSegment(fs, segments, subfetchlist, numLists);

            fs.createNewFile(new Path(newSeg, "generatored"));
            generatedSegments.add(newSeg);
        }
    } catch (Exception e) {
        LOG.warn("Generator: exception while partitioning segments, exiting ...");
        fs.delete(tempDir, true);
        return null;
    }

    if (generatedSegments.size() == 0) {
        LOG.warn("Generator: 0 records selected for fetching, exiting ...");
        LockUtil.removeLockFile(fs, lock);
        fs.delete(tempDir, true);
        return null;
    }

    if (getConf().getBoolean(GENERATE_UPDATE_CRAWLDB, false)) {
        // update the db from tempDir
        Path tempDir2 = new Path(
                getConf().get("mapred.temp.dir", ".") + "/generate-temp-" + System.currentTimeMillis());

        job = AvroJob.getAvroJob(getConf());
        job.setJobName("generate: updatedb " + dbDir);
        job.getConfiguration().setLong(Spider.GENERATE_TIME_KEY, generateTime);
        for (Path segmpaths : generatedSegments) {
            Path subGenDir = new Path(segmpaths, CrawlDatum.GENERATE_DIR_NAME);
            FileInputFormat.addInputPath(job, subGenDir);
        }
        FileInputFormat.addInputPath(job, new Path(dbDir, CrawlDb.CURRENT_NAME));
        job.setInputFormatClass(AvroPairInputFormat.class);
        job.setMapperClass(CrawlDbUpdateMapper.class);
        // job.setReducerClass(CrawlDbUpdater.class);
        job.setOutputFormatClass(AvroMapOutputFormat.class);
        job.setOutputKeyClass(String.class);
        job.setOutputValueClass(CrawlDatum.class);
        FileOutputFormat.setOutputPath(job, tempDir2);
        try {
            job.waitForCompletion(true);
            CrawlDb.install(job, dbDir);
        } catch (IOException e) {
            LockUtil.removeLockFile(fs, lock);
            fs.delete(tempDir, true);
            fs.delete(tempDir2, true);
            throw e;
        }
        fs.delete(tempDir2, true);
    }

    LockUtil.removeLockFile(fs, lock);
    fs.delete(tempDir, true);

    if (LOG.isInfoEnabled()) {
        LOG.info("Generator: done.");
    }
    Path[] patharray = new Path[generatedSegments.size()];
    return generatedSegments.toArray(patharray);
}

From source file:com.iflytek.spider.crawl.GeneratorSmart.java

License:Apache License

private Path partitionSegment(FileSystem fs, Path segmentsDir, Path inputDir, int numLists)
        throws IOException, InterruptedException, ClassNotFoundException {
    // invert again, partition by host/domain/IP, sort by url hash
    if (LOG.isInfoEnabled()) {
        LOG.info("Generator: Partitioning selected urls for politeness:" + inputDir);
    }//from w  w w.  ja va2 s .  c  om
    Path segment = new Path(segmentsDir, generateSegmentName());
    Path output = new Path(segment, CrawlDatum.GENERATE_DIR_NAME);

    LOG.info("Generator: segment: " + segment + " with " + numLists + " Fetchers");

    Job job = AvroJob.getAvroJob(getConf());
    job.setJobName("generate: partition " + segment);
    job.getConfiguration().setInt("partition.url.seed", new Random().nextInt());

    FileInputFormat.addInputPath(job, inputDir);
    job.setInputFormatClass(AvroPairInputFormat.class);

    job.setMapperClass(SelectorInverseMapper.class);
    job.setPartitionerClass(AveragePartition.class);
    job.setMapOutputKeyClass(String.class);
    job.setMapOutputValueClass(SelectorEntry.class);
    job.setReducerClass(PartitionReducer.class);
    job.setNumReduceTasks(numLists);

    FileOutputFormat.setOutputPath(job, output);
    job.setOutputFormatClass(AvroPairOutputFormat.class);
    job.setOutputKeyClass(String.class);
    job.setOutputValueClass(CrawlDatum.class);

    job.waitForCompletion(true);
    return segment;
}

From source file:com.iflytek.spider.parse.ParseSegment.java

License:Apache License

public void parse(Path segment) throws IOException, InterruptedException, ClassNotFoundException {

    if (LOG.isInfoEnabled()) {
        LOG.info("Parse: starting");
        LOG.info("Parse: segment: " + segment);
    }//from  ww w  .j  a v  a  2s. c om

    Job job = AvroJob.getAvroJob(getConf());
    job.setJobName("parse " + segment);

    FileInputFormat.addInputPath(job, new Path(segment, Content.DIR_NAME));
    job.getConfiguration().set(Spider.SEGMENT_NAME_KEY, segment.getName());

    job.setInputFormatClass(AvroPairInputFormat.class);
    job.setMapperClass(ParseMapper.class);

    FileOutputFormat.setOutputPath(job, segment);
    job.setOutputFormatClass(ParseOutputFormat.class);
    job.setOutputKeyClass(String.class);
    job.setOutputValueClass(UnionData.class);

    job.waitForCompletion(true);
    if (LOG.isInfoEnabled()) {
        LOG.info("Parse: done");
    }
}