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

Introduction

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

Prototype

public void setOutputKeyClass(Class<?> theClass)

Source Link

Document

Set the key class for the job output data.

Usage

From source file:com.ibm.jaql.io.hadoop.CompositeOutputAdapter.java

License:Apache License

private void set(JobConf conf) throws Exception {
    // TODO: Should this call be passed to outputs?
    conf.setOutputFormat(this.getClass());
    conf.setOutputCommitter(CompositeCommitter.class);
    conf.setOutputKeyClass(JsonHolderDefault.class);
    conf.setOutputValueClass(JsonHolderDefault.class);
    HadoopSerializationDefault.register(conf);

    // We do not support speculative execution at this time.
    conf.setSpeculativeExecution(false);

    // write out the input adapter args array
    ConfUtil.writeConfArray(conf, ConfSetter.CONFOUTOPTIONS_NAME, descriptors);
}

From source file:com.ibm.jaql.io.hadoop.FileOutputConfigurator.java

License:Apache License

protected void registerSerializers(JobConf conf) {
    conf.setOutputKeyClass(JsonHolderDefault.class);
    conf.setOutputValueClass(JsonHolderDefault.class);
    HadoopSerializationDefault.register(conf);
}

From source file:com.ibm.jaql.io.hadoop.TempFileOutputConfigurator.java

License:Apache License

@Override
protected void registerSerializers(JobConf conf) {
    conf.setOutputKeyClass(JsonHolderTempKey.class);
    conf.setOutputValueClass(JsonHolderTempValue.class);
    HadoopSerializationTemp.register(conf);
}

From source file:com.ibm.jaql.io.hadoop.TextFileOutputConfigurator.java

License:Apache License

@Override
protected void registerSerializers(JobConf conf) {
    conf.setMapOutputKeyClass(JsonHolderDefault.class);
    conf.setMapOutputValueClass(JsonHolderDefault.class);
    conf.setOutputKeyClass(NullWritable.class);
    conf.setOutputValueClass(Text.class);
}

From source file:com.ibm.jaql.io.hbase.TableOutputConfigurator.java

License:Apache License

public void setParallel(JobConf conf) throws Exception {
    conf.set(TableOutputFormat.OUTPUT_TABLE, location);
    conf.setOutputKeyClass(JsonHolderDefault.class);
    conf.setOutputValueClass(JsonHolderDefault.class);
    HadoopSerializationDefault.register(conf);
    conf.setOutputKeyComparatorClass(DefaultJsonComparator.class);
}

From source file:com.impetus.code.examples.hadoop.mapred.wordcount.WordCount.java

License:Apache License

public static void main(String[] args) throws Exception {
    JobConf conf = new JobConf(WordCount.class);
    conf.setJobName("wordcount");

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

    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);

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

    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));

    JobClient.runJob(conf);//from w w w  .  j  a  v  a2  s. com

}

From source file:com.intel.hadoop.graphbuilder.idnormalize.mapreduce.HashIdMR.java

License:Open Source License

/**
 * @param inputpath/*from   w  w  w . j a  v a2 s . co  m*/
 *          the path to a unique vertex list. Each line is parsed into (vid,
 *          data) using {@code vidparser} and {@code vdataparser}.
 * @param outputpath
 *          the path of output directory.
 * @throws IOException
 */
public void run(String inputpath, String outputpath) throws IOException {
    JobConf conf = new JobConf(HashIdMR.class);

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

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

    conf.setMapperClass(HashIdMapper.class);
    conf.setReducerClass(HashIdReducer.class);

    conf.setInputFormat(NLineInputFormat.class);
    conf.setOutputFormat(MultiDirOutputFormat.class);

    conf.setInt("mapred.line.input.format.linespermap", linespermap);
    conf.set("GraphParser", graphparser.getClass().getName());
    conf.set("VidParser", vidparser.getClass().getName());
    conf.set("VdataParser", vdataparser.getClass().getName());

    FileInputFormat.setInputPaths(conf, new Path(inputpath));
    FileOutputFormat.setOutputPath(conf, new Path(outputpath));

    LOG.info("====== Job: Create integer Id maps for vertices ==========");
    LOG.info("Input = " + inputpath);
    LOG.info("Output = " + outputpath);
    LOG.debug("Lines per map = 6000000");
    LOG.debug("GraphParser = " + graphparser.getClass().getName());
    LOG.debug("VidParser = " + vidparser.getClass().getName());
    LOG.debug("VdataParser = " + vdataparser.getClass().getName());
    LOG.info("==========================================================");
    JobClient.runJob(conf);
    LOG.info("=======================Done =====================\n");
}

From source file:com.intel.hadoop.graphbuilder.idnormalize.mapreduce.SortDictMR.java

License:Open Source License

/**
 * @param inputpath/* ww  w.  ja v a 2 s . c  om*/
 *          the path to a rawId to newId dictionary.
 * @param outputpath
 *          the path of output directory.
 * @throws IOException
 */
public void run(String inputpath, String outputpath) throws IOException {

    JobConf conf = new JobConf(SortDictMR.class);

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

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

    conf.setMapperClass(SortDictMapper.class);
    conf.setReducerClass(SortDictReducer.class);

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

    conf.setBoolean("hashRawVid", hashRawVid);
    conf.setInt("numChunks", numChunks);
    conf.set("VidParser", vidparser.getClass().getName());

    String outprefix = "vidhashmap";
    for (int i = 0; i < numChunks; i++) {
        MultipleOutputs.addNamedOutput(conf, outprefix + i, TextOutputFormat.class, Text.class, Text.class);
    }

    FileInputFormat.setInputPaths(conf, new Path(inputpath));
    FileOutputFormat.setOutputPath(conf, new Path(outputpath));

    LOG.info("========== Job: Partition the map of rawid -> id ===========");
    LOG.info("Input = " + inputpath);
    LOG.info("Output = " + outputpath);
    LOG.info("======================================================");
    if (hashRawVid)
        LOG.info("Partition on rawId.");
    else
        LOG.info("Partition on newId");
    LOG.debug("numChunks = " + numChunks);
    LOG.debug("VidParser = " + vidparser.getClass().getName());
    JobClient.runJob(conf);
    LOG.info("======================= Done ==========================\n");
}

From source file:com.intel.hadoop.graphbuilder.idnormalize.mapreduce.SortEdgeMR.java

License:Open Source License

public void run(String inputpath, String outputpath) throws IOException {

    JobConf conf = new JobConf(SortEdgeMR.class);

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

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

    conf.setMapperClass(SortEdgeMapper.class);
    conf.setReducerClass(SortEdgeReducer.class);

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

    conf.setInt("numChunks", numChunks);
    conf.set("GraphParser", graphparser.getClass().getName());
    conf.set("VidParser", vidparser.getClass().getName());
    conf.set("EdataParser", edataparser.getClass().getName());

    FileInputFormat.setInputPaths(conf, new Path(inputpath));
    FileOutputFormat.setOutputPath(conf, new Path(outputpath));

    LOG.info("==== Job: Partition the input edges by hash(sourceid) =========");
    LOG.info("Input = " + inputpath);
    LOG.info("Output = " + outputpath);
    LOG.debug("numChunks = " + numChunks);
    LOG.debug("GraphParser = " + graphparser.getClass().getName());
    LOG.debug("VidParser = " + vidparser.getClass().getName());
    LOG.debug("EdataParser = " + edataparser.getClass().getName());
    LOG.info("===============================================================");

    JobClient.runJob(conf);//from   ww w. j a v a 2  s  . c o  m
    LOG.info("=================== Done ====================================\n");
}

From source file:com.intel.hadoop.graphbuilder.idnormalize.mapreduce.TransEdgeMR.java

License:Open Source License

/**
 * @param inputpath//from   w  w  w.  j a  va 2s .com
 *          path of the partitioned edge list
 * @param outputpath
 *          path of the output directory
 * @throws IOException
 */
public void run(String inputpath, String outputpath) throws IOException {

    JobConf conf = new JobConf(TransEdgeMR.class);

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

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

    conf.setMapperClass(TransEdgeMapper.class);
    conf.setReducerClass(TransEdgeReducer.class);

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

    conf.setInt("numChunks", numChunks);
    conf.set("GraphParser", graphparser.getClass().getName());
    conf.set("VidParser", vidparser.getClass().getName());
    conf.set("EdataParser", edataparser.getClass().getName());

    conf.set("dictionaryPath", dictionaryPath);

    FileInputFormat.setInputPaths(conf, new Path(inputpath));
    FileOutputFormat.setOutputPath(conf, new Path(outputpath));

    LOG.info("============= Job: Normalize Ids in Edges ====================");
    LOG.info("Input = " + inputpath);
    LOG.info("Output = " + outputpath);
    LOG.info("Dictionary = " + dictionaryPath);
    LOG.debug("numChunks = " + numChunks);
    LOG.debug("GraphParser = " + graphparser.getClass().getName());
    LOG.debug("VidParser = " + vidparser.getClass().getName());
    LOG.debug("EdataParser = " + edataparser.getClass().getName());
    LOG.info("===============================================================");

    JobClient.runJob(conf);

    LOG.info("========================= Done ===============================");
}