Example usage for org.apache.hadoop.mapreduce TaskAttemptContext setStatus

List of usage examples for org.apache.hadoop.mapreduce TaskAttemptContext setStatus

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce TaskAttemptContext setStatus.

Prototype

public void setStatus(String msg);

Source Link

Document

Set the current status of the task to the given string.

Usage

From source file:format.WikipediaPageInputFormat.java

License:Apache License

@Override
public RecordReader<LongWritable, WikipediaPage> createRecordReader(InputSplit split,
        TaskAttemptContext context) throws IOException, InterruptedException {
    context.setStatus(split.toString());
    return new WikipediaPageRecordReader(context.getConfiguration());
}

From source file:gov.llnl.ontology.text.hbase.XMLRecordReader.java

License:Open Source License

/**
 * Extract the {@link Path} for the file to be processed by this {@link
 * XMLRecordReader}./*from www  .  j av a  2 s  .  c  o m*/
 */
public void initialize(InputSplit isplit, TaskAttemptContext context) throws IOException, InterruptedException {
    Configuration config = context.getConfiguration();

    // Get the file stream for the xml file.
    FileSplit split = (FileSplit) isplit;
    Path file = split.getPath();
    FileSystem fs = file.getFileSystem(config);
    fsin = (useGzip) ? new GZIPInputStream(fs.open(split.getPath())) : fs.open(split.getPath());
    fsin = new BufferedInputStream(fsin);

    // Setup the limits of the xml file.
    start = split.getStart();
    end = start + split.getLength();
    pos = 0;

    // Get the xml document delmiters for this xml file.
    if (!config.get(DELIMITER_TAG).equals("")) {
        startTag = ("<" + config.get(DELIMITER_TAG)).getBytes();
        endTag = ("</" + config.get(DELIMITER_TAG) + ">").getBytes();
    } else {
        String fileNameBase = file.getName().replace(".xml", "");
        startTag = ("<" + fileNameBase).getBytes();
        endTag = ("</" + fileNameBase).getBytes();
    }
    context.setStatus(file.getName() + " " + pos + " " + end);
}

From source file:io.druid.indexer.JobHelper.java

License:Apache License

public static ProgressIndicator progressIndicatorForContext(final TaskAttemptContext context) {
    return new ProgressIndicator() {

        @Override/*from   w  ww. j a  va2  s  .  com*/
        public void progress() {
            context.progress();
        }

        @Override
        public void start() {
            context.progress();
            context.setStatus("STARTED");
        }

        @Override
        public void stop() {
            context.progress();
            context.setStatus("STOPPED");
        }

        @Override
        public void startSection(String section) {
            context.progress();
            context.setStatus(String.format("STARTED [%s]", section));
        }

        @Override
        public void progressSection(String section, String message) {
            log.info("Progress message for section [%s] : [%s]", section, message);
            context.progress();
            context.setStatus(String.format("PROGRESS [%s]", section));
        }

        @Override
        public void stopSection(String section) {
            context.progress();
            context.setStatus(String.format("STOPPED [%s]", section));
        }
    };
}

From source file:io.ssc.trackthetrackers.extraction.hadoop.io.ArcInputFormat.java

License:Open Source License

/**
 * Returns the <code>RecordReader</code> for reading the arc file.
 *
 *//*from  w  ww  .j  a v  a  2 s. co  m*/
public RecordReader<Text, ArcRecord> createRecordReader(InputSplit split, TaskAttemptContext context)
        throws IOException {
    context.setStatus(split.toString());
    return new ArcRecordReader();
}

From source file:ir.ac.ut.snl.mrcd.MyFileInputFormat.java

@Override
public RecordReader<Text, ShortestPathTuple> createRecordReader(InputSplit is, TaskAttemptContext tac)
        throws IOException, InterruptedException {
    tac.setStatus(is.toString());
    return new MyRecordReader(tac.getConfiguration(), (FileSplit) is);
}

From source file:org.apache.avro.mapreduce.lib.input.AvroInputFormat.java

License:Apache License

@Override
public RecordReader<AvroWrapper<T>, NullWritable> createRecordReader(InputSplit inputSplit,
        TaskAttemptContext context) throws IOException, InterruptedException {
    context.setStatus(inputSplit.toString());
    return new AvroRecordReader<T>(context.getConfiguration(), (FileSplit) inputSplit);
}

From source file:org.apache.crunch.types.avro.AvroInputFormat.java

License:Apache License

@Override
public RecordReader<AvroWrapper<T>, NullWritable> createRecordReader(InputSplit split,
        TaskAttemptContext context) throws IOException, InterruptedException {
    context.setStatus(split.toString());
    String jsonSchema = context.getConfiguration().get(AvroJob.INPUT_SCHEMA);
    Schema schema = new Schema.Parser().parse(jsonSchema);
    return new AvroRecordReader<T>(schema);
}

From source file:org.apache.giraph.utils.LoggerUtils.java

License:Apache License

/**
 * Set Hadoop status message./*from w  w w . j a v  a  2  s . c  o  m*/
 *
 * NOTE: In theory this function could get folded in to the callsites, but
 * the issue is that some Hadoop jars, e.g. 0.23 and 2.0.0, don't actually
 * throw IOException on setStatus while others do. This makes wrapping it in a
 * try/catch cause a compile error on those Hadoops. With this function every
 * caller sees a method that throws IOException. In case it doesn't actually,
 * there is no more compiler error because not throwing a decalred exception
 * is at best a warning.
 *
 * @param context Context to set the status with
 * @param message Message to set status with
 * @throws IOException If something goes wrong with setting status message
 */
private static void setStatus(TaskAttemptContext context, String message) throws IOException {
    context.setStatus(message);
}

From source file:org.apache.hcatalog.rcfile.RCFileMapReduceInputFormat.java

License:Apache License

@Override
public RecordReader<LongWritable, BytesRefArrayWritable> createRecordReader(InputSplit split,
        TaskAttemptContext context) throws IOException, InterruptedException {

    context.setStatus(split.toString());
    return new RCFileMapReduceRecordReader<LongWritable, BytesRefArrayWritable>();
}

From source file:org.apache.pig.builtin.AvroStorage.java

License:Apache License

/**
 * @see org.apache.pig.LoadFunc#getInputFormat()
 *///from   www  .  ja va 2s. com
@Override
public InputFormat<NullWritable, GenericData.Record> getInputFormat() throws IOException {

    return new org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigFileInputFormat<NullWritable, GenericData.Record>() {

        @Override
        public RecordReader<NullWritable, GenericData.Record> createRecordReader(final InputSplit is,
                final TaskAttemptContext tc) throws IOException, InterruptedException {
            Schema s = getInputAvroSchema();
            RecordReader<NullWritable, GenericData.Record> rr = null;
            if (s.getType() == Type.ARRAY) {
                rr = new AvroArrayReader(s);
            } else {
                rr = new AvroRecordReader(s);
            }
            rr.initialize(is, tc);
            tc.setStatus(is.toString());
            return rr;
        }
    };

}