Example usage for org.apache.hadoop.util StringUtils arrayToString

Introduction

In this page you can find the example usage for org.apache.hadoop.util StringUtils arrayToString.

Prototype

public static String arrayToString(String[] strs) 

Source Link

Document

Given an array of strings, return a comma-separated list of its elements.

Usage

From source file:org.apache.hcatalog.templeton.tool.TempletonUtils.java

License:Apache License

public static String hadoopFsListAsString(String files, Configuration conf, String user)
        throws URISyntaxException, FileNotFoundException, IOException, InterruptedException {
    if (files == null || conf == null) {
        return null;
    }//  w  ww  . ja  v  a2  s .  c om
    return StringUtils.arrayToString(hadoopFsListAsArray(files, conf, user));
}

---

From source file:org.apache.jena.hadoop.rdf.stats.jobs.JobFactory.java

License:Apache License

/**
 * Gets a job for computing node counts on RDF triple inputs
 * //www. j av  a 2 s  .  c o  m
 * @param config
 *            Configuration
 * @param inputPaths
 *            Input paths
 * @param outputPath
 *            Output path
 * @return Job
 * @throws IOException
 */
public static Job getTripleNodeCountJob(Configuration config, String[] inputPaths, String outputPath)
        throws IOException {
    Job job = Job.getInstance(config);
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Triples Node Usage Count");

    // Map/Reduce classes
    job.setMapperClass(TripleNodeCountMapper.class);
    job.setMapOutputKeyClass(NodeWritable.class);
    job.setMapOutputValueClass(LongWritable.class);
    job.setReducerClass(NodeCountReducer.class);

    // Input and Output
    job.setInputFormatClass(TriplesInputFormat.class);
    job.setOutputFormatClass(NTriplesNodeOutputFormat.class);
    FileInputFormat.setInputPaths(job, StringUtils.arrayToString(inputPaths));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job;
}

---

From source file:org.apache.jena.hadoop.rdf.stats.jobs.JobFactory.java

License:Apache License

/**
 * Gets a job for computing node counts on RDF quad inputs
 * /* ww  w  .jav  a 2  s.com*/
 * @param config
 *            Configuration
 * @param inputPaths
 *            Input paths
 * @param outputPath
 *            Output path
 * @return Job
 * @throws IOException
 */
public static Job getQuadNodeCountJob(Configuration config, String[] inputPaths, String outputPath)
        throws IOException {
    Job job = Job.getInstance(config);
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Quads Node Usage Count");

    // Map/Reduce classes
    job.setMapperClass(QuadNodeCountMapper.class);
    job.setMapOutputKeyClass(NodeWritable.class);
    job.setMapOutputValueClass(LongWritable.class);
    job.setReducerClass(NodeCountReducer.class);

    // Input and Output
    job.setInputFormatClass(QuadsInputFormat.class);
    job.setOutputFormatClass(NTriplesNodeOutputFormat.class);
    FileInputFormat.setInputPaths(job, StringUtils.arrayToString(inputPaths));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job;
}

---

From source file:org.apache.jena.hadoop.rdf.stats.jobs.JobFactory.java

License:Apache License

/**
 * Gets a job for computing node counts on RDF triple and/or quad inputs
 * /*  w  w  w  .  java  2 s  .  co  m*/
 * @param config
 *            Configuration
 * @param inputPaths
 *            Input paths
 * @param outputPath
 *            Output path
 * @return Job
 * @throws IOException
 */
public static Job getNodeCountJob(Configuration config, String[] inputPaths, String outputPath)
        throws IOException {
    Job job = Job.getInstance(config);
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Node Usage Count");

    // Map/Reduce classes
    job.setMapperClass(QuadNodeCountMapper.class);
    job.setMapOutputKeyClass(NodeWritable.class);
    job.setMapOutputValueClass(LongWritable.class);
    job.setReducerClass(NodeCountReducer.class);

    // Input and Output
    job.setInputFormatClass(TriplesOrQuadsInputFormat.class);
    job.setOutputFormatClass(NTriplesNodeOutputFormat.class);
    FileInputFormat.setInputPaths(job, StringUtils.arrayToString(inputPaths));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job;
}

---

From source file:org.apache.jena.hadoop.rdf.stats.jobs.JobFactory.java

License:Apache License

public static Job getTripleGraphSizesJob(Configuration config, String[] inputPaths, String outputPath)
        throws IOException {
    Job job = Job.getInstance(config);//from  w ww  .ja  v a2  s.  c  o m
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Triples Graph Sizes");

    // Map/Reduce classes
    ChainMapper.addMapper(job, TriplesToQuadsConstantGraphMapper.class, LongWritable.class,
            TripleWritable.class, LongWritable.class, QuadWritable.class, config);
    ChainMapper.addMapper(job, QuadGraphCountMapper.class, LongWritable.class, QuadWritable.class,
            NodeWritable.class, LongWritable.class, config);
    job.setMapOutputKeyClass(NodeWritable.class);
    job.setMapOutputValueClass(LongWritable.class);
    job.setReducerClass(NodeCountReducer.class);

    // Input and Output
    job.setInputFormatClass(TriplesInputFormat.class);
    job.setOutputFormatClass(NTriplesNodeOutputFormat.class);
    FileInputFormat.setInputPaths(job, StringUtils.arrayToString(inputPaths));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job;
}

---

From source file:org.apache.jena.hadoop.rdf.stats.jobs.JobFactory.java

License:Apache License

public static Job getQuadGraphSizesJob(Configuration config, String[] inputPaths, String outputPath)
        throws IOException {
    Job job = Job.getInstance(config);/* ww  w. j a v a2  s. c o  m*/
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Quads Graph Sizes");

    // Map/Reduce classes
    job.setMapperClass(QuadGraphCountMapper.class);
    job.setMapOutputKeyClass(NodeWritable.class);
    job.setMapOutputValueClass(LongWritable.class);
    job.setReducerClass(NodeCountReducer.class);

    // Input and Output
    job.setInputFormatClass(QuadsInputFormat.class);
    job.setOutputFormatClass(NTriplesNodeOutputFormat.class);
    FileInputFormat.setInputPaths(job, StringUtils.arrayToString(inputPaths));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job;
}

---

From source file:org.apache.jena.hadoop.rdf.stats.jobs.JobFactory.java

License:Apache License

public static Job getGraphSizesJob(Configuration config, String[] inputPaths, String outputPath)
        throws IOException {
    Job job = Job.getInstance(config);/*from  w w  w. jav a  2  s  .c om*/
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Graph Sizes");

    // Map/Reduce classes
    job.setMapperClass(QuadGraphCountMapper.class);
    job.setMapOutputKeyClass(NodeWritable.class);
    job.setMapOutputValueClass(LongWritable.class);
    job.setReducerClass(NodeCountReducer.class);

    // Input and Output
    job.setInputFormatClass(TriplesOrQuadsInputFormat.class);
    job.setOutputFormatClass(NTriplesNodeOutputFormat.class);
    FileInputFormat.setInputPaths(job, StringUtils.arrayToString(inputPaths));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    return job;
}

---

From source file:org.apache.jena.hadoop.rdf.stats.jobs.JobFactory.java

License:Apache License

/**
 * Gets a sequence of jobs that can be used to compute characteristic sets
 * for RDF triples/*  w  ww.  j  a va  2  s .c om*/
 * 
 * @param config
 *            Configuration
 * @param inputPaths
 *            Input paths
 * @param intermediateOutputPath
 *            Intermediate output path
 * @param outputPath
 *            Final output path
 * @return Sequence of jobs
 * @throws IOException
 */
public static Job[] getTripleCharacteristicSetJobs(Configuration config, String[] inputPaths,
        String intermediateOutputPath, String outputPath) throws IOException {
    Job[] jobs = new Job[2];

    Job job = Job.getInstance(config);
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Triples Characteristic Set (Generation)");

    // Map/Reduce classes
    job.setMapperClass(TripleGroupBySubjectMapper.class);
    job.setMapOutputKeyClass(NodeWritable.class);
    job.setMapOutputValueClass(TripleWritable.class);
    job.setReducerClass(TripleCharacteristicSetGeneratingReducer.class);
    job.setOutputKeyClass(CharacteristicSetWritable.class);
    job.setOutputValueClass(NullWritable.class);

    // Input and Output
    job.setInputFormatClass(TriplesInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    FileInputFormat.setInputPaths(job, StringUtils.arrayToString(inputPaths));
    FileOutputFormat.setOutputPath(job, new Path(intermediateOutputPath));
    SequenceFileOutputFormat.setCompressOutput(job, true);
    FileOutputFormat.setOutputCompressorClass(job, BZip2Codec.class);
    SequenceFileOutputFormat.setOutputCompressionType(job, CompressionType.BLOCK);

    jobs[0] = job;

    job = Job.getInstance(config);
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Triples Characteristic Set (Reduction)");

    // Map/Reduce classes
    job.setMapperClass(KeyMapper.class);
    job.setMapOutputKeyClass(CharacteristicSetWritable.class);
    job.setMapOutputValueClass(CharacteristicSetWritable.class);
    job.setReducerClass(CharacteristicSetReducer.class);
    job.setOutputKeyClass(CharacteristicSetWritable.class);
    job.setOutputValueClass(CharacteristicSetWritable.class);

    // Input and Output
    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    FileInputFormat.setInputPaths(job, intermediateOutputPath);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    jobs[1] = job;
    return jobs;
}

---

From source file:org.apache.jena.hadoop.rdf.stats.jobs.JobFactory.java

License:Apache License

/**
 * Gets a sequence of jobs that can be used to compute characteristic sets
 * for RDF quads/*from  ww w. jav a  2 s .  c  o  m*/
 * 
 * @param config
 *            Configuration
 * @param inputPaths
 *            Input paths
 * @param intermediateOutputPath
 *            Intermediate output path
 * @param outputPath
 *            Final output path
 * @return Sequence of jobs
 * @throws IOException
 */
public static Job[] getQuadCharacteristicSetJobs(Configuration config, String[] inputPaths,
        String intermediateOutputPath, String outputPath) throws IOException {
    Job[] jobs = new Job[2];

    Job job = Job.getInstance(config);
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Quads Characteristic Set (Generation)");

    // Map/Reduce classes
    job.setMapperClass(QuadGroupBySubjectMapper.class);
    job.setMapOutputKeyClass(NodeWritable.class);
    job.setMapOutputValueClass(QuadWritable.class);
    job.setReducerClass(QuadCharacteristicSetGeneratingReducer.class);
    job.setOutputKeyClass(CharacteristicSetWritable.class);
    job.setOutputValueClass(NullWritable.class);

    // Input and Output
    job.setInputFormatClass(QuadsInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    FileInputFormat.setInputPaths(job, StringUtils.arrayToString(inputPaths));
    FileOutputFormat.setOutputPath(job, new Path(intermediateOutputPath));
    SequenceFileOutputFormat.setCompressOutput(job, true);
    FileOutputFormat.setOutputCompressorClass(job, BZip2Codec.class);
    SequenceFileOutputFormat.setOutputCompressionType(job, CompressionType.BLOCK);

    jobs[0] = job;

    job = Job.getInstance(config);
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Quads Characteristic Set (Reduction)");

    // Map/Reduce classes
    job.setMapperClass(KeyMapper.class);
    job.setMapOutputKeyClass(CharacteristicSetWritable.class);
    job.setMapOutputValueClass(CharacteristicSetWritable.class);
    job.setReducerClass(CharacteristicSetReducer.class);
    job.setOutputKeyClass(CharacteristicSetWritable.class);
    job.setOutputValueClass(CharacteristicSetWritable.class);

    // Input and Output
    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    FileInputFormat.setInputPaths(job, intermediateOutputPath);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    jobs[1] = job;
    return jobs;
}

---

From source file:org.apache.jena.hadoop.rdf.stats.jobs.JobFactory.java

License:Apache License

/**
 * Gets a sequence of jobs that can be used to compute characteristic sets
 * for RDF triple and/or quad inputs//w  ww.j  a  va 2 s  .co m
 * 
 * @param config
 *            Configuration
 * @param inputPaths
 *            Input paths
 * @param intermediateOutputPath
 *            Intermediate output path
 * @param outputPath
 *            Final output path
 * @return Sequence of jobs
 * @throws IOException
 */
public static Job[] getCharacteristicSetJobs(Configuration config, String[] inputPaths,
        String intermediateOutputPath, String outputPath) throws IOException {
    Job[] jobs = new Job[2];

    Job job = Job.getInstance(config);
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Characteristic Set (Generation)");

    // Map/Reduce classes
    job.setMapperClass(QuadGroupBySubjectMapper.class);
    job.setMapOutputKeyClass(NodeWritable.class);
    job.setMapOutputValueClass(QuadWritable.class);
    job.setReducerClass(QuadCharacteristicSetGeneratingReducer.class);
    job.setOutputKeyClass(CharacteristicSetWritable.class);
    job.setOutputValueClass(NullWritable.class);

    // Input and Output
    job.setInputFormatClass(TriplesOrQuadsInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    FileInputFormat.setInputPaths(job, StringUtils.arrayToString(inputPaths));
    FileOutputFormat.setOutputPath(job, new Path(intermediateOutputPath));
    SequenceFileOutputFormat.setCompressOutput(job, true);
    FileOutputFormat.setOutputCompressorClass(job, BZip2Codec.class);
    SequenceFileOutputFormat.setOutputCompressionType(job, CompressionType.BLOCK);

    jobs[0] = job;

    job = Job.getInstance(config);
    job.setJarByClass(JobFactory.class);
    job.setJobName("RDF Characteristic Set (Reduction)");

    // Map/Reduce classes
    job.setMapperClass(KeyMapper.class);
    job.setMapOutputKeyClass(CharacteristicSetWritable.class);
    job.setMapOutputValueClass(CharacteristicSetWritable.class);
    job.setReducerClass(CharacteristicSetReducer.class);
    job.setOutputKeyClass(CharacteristicSetWritable.class);
    job.setOutputValueClass(CharacteristicSetWritable.class);

    // Input and Output
    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    FileInputFormat.setInputPaths(job, intermediateOutputPath);
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    jobs[1] = job;
    return jobs;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• »