Search in sources :

Example 61 with LongWritable

use of org.apache.hadoop.io.LongWritable in project camel by apache.

the class HdfsConsumerTest method testReadLong.

@Test
public void testReadLong() throws Exception {
    if (!canTest()) {
        return;
    }
    final Path file = new Path(new File("target/test/test-camel-long").getAbsolutePath());
    Configuration conf = new Configuration();
    SequenceFile.Writer writer = createWriter(conf, file, NullWritable.class, LongWritable.class);
    NullWritable keyWritable = NullWritable.get();
    LongWritable valueWritable = new LongWritable();
    long value = 31415926535L;
    valueWritable.set(value);
    writer.append(keyWritable, valueWritable);
    writer.sync();
    writer.close();
    MockEndpoint resultEndpoint = context.getEndpoint("mock:result", MockEndpoint.class);
    resultEndpoint.expectedMessageCount(1);
    context.addRoutes(new RouteBuilder() {

        public void configure() {
            from("hdfs2:localhost/" + file.toUri() + "?fileSystemType=LOCAL&fileType=SEQUENCE_FILE&initialDelay=0").to("mock:result");
        }
    });
    context.start();
    resultEndpoint.assertIsSatisfied();
}
Also used : Path(org.apache.hadoop.fs.Path) Configuration(org.apache.hadoop.conf.Configuration) SequenceFile(org.apache.hadoop.io.SequenceFile) RouteBuilder(org.apache.camel.builder.RouteBuilder) MockEndpoint(org.apache.camel.component.mock.MockEndpoint) LongWritable(org.apache.hadoop.io.LongWritable) ArrayFile(org.apache.hadoop.io.ArrayFile) SequenceFile(org.apache.hadoop.io.SequenceFile) File(java.io.File) NullWritable(org.apache.hadoop.io.NullWritable) Writer(org.apache.hadoop.io.SequenceFile.Writer) Test(org.junit.Test)

Example 62 with LongWritable

use of org.apache.hadoop.io.LongWritable in project camel by apache.

the class HdfsProducerTest method testWriteLong.

@Test
public void testWriteLong() throws Exception {
    if (!canTest()) {
        return;
    }
    long aLong = 1234567890;
    template.sendBody("direct:write_long", aLong);
    Configuration conf = new Configuration();
    Path file1 = new Path("file:///" + TEMP_DIR.toUri() + "/test-camel-long");
    FileSystem fs1 = FileSystem.get(file1.toUri(), conf);
    SequenceFile.Reader reader = new SequenceFile.Reader(fs1, file1, conf);
    Writable key = (Writable) ReflectionUtils.newInstance(reader.getKeyClass(), conf);
    Writable value = (Writable) ReflectionUtils.newInstance(reader.getValueClass(), conf);
    reader.next(key, value);
    long rLong = ((LongWritable) value).get();
    assertEquals(rLong, aLong);
    IOHelper.close(reader);
}
Also used : Path(org.apache.hadoop.fs.Path) Configuration(org.apache.hadoop.conf.Configuration) SequenceFile(org.apache.hadoop.io.SequenceFile) FileSystem(org.apache.hadoop.fs.FileSystem) Writable(org.apache.hadoop.io.Writable) DoubleWritable(org.apache.hadoop.io.DoubleWritable) LongWritable(org.apache.hadoop.io.LongWritable) ByteWritable(org.apache.hadoop.io.ByteWritable) IntWritable(org.apache.hadoop.io.IntWritable) BooleanWritable(org.apache.hadoop.io.BooleanWritable) FloatWritable(org.apache.hadoop.io.FloatWritable) LongWritable(org.apache.hadoop.io.LongWritable) Test(org.junit.Test)

Example 63 with LongWritable

use of org.apache.hadoop.io.LongWritable in project camel by apache.

the class HdfsProducerTest method testWriteLong.

@Test
public void testWriteLong() throws Exception {
    if (!canTest()) {
        return;
    }
    long aLong = 1234567890;
    template.sendBody("direct:write_long", aLong);
    Configuration conf = new Configuration();
    Path file1 = new Path("file:///" + TEMP_DIR.toUri() + "/test-camel-long");
    SequenceFile.Reader reader = new SequenceFile.Reader(conf, SequenceFile.Reader.file(file1));
    Writable key = (Writable) ReflectionUtils.newInstance(reader.getKeyClass(), conf);
    Writable value = (Writable) ReflectionUtils.newInstance(reader.getValueClass(), conf);
    reader.next(key, value);
    long rLong = ((LongWritable) value).get();
    assertEquals(rLong, aLong);
    IOHelper.close(reader);
}
Also used : Path(org.apache.hadoop.fs.Path) Configuration(org.apache.hadoop.conf.Configuration) SequenceFile(org.apache.hadoop.io.SequenceFile) Writable(org.apache.hadoop.io.Writable) DoubleWritable(org.apache.hadoop.io.DoubleWritable) LongWritable(org.apache.hadoop.io.LongWritable) ByteWritable(org.apache.hadoop.io.ByteWritable) IntWritable(org.apache.hadoop.io.IntWritable) BooleanWritable(org.apache.hadoop.io.BooleanWritable) FloatWritable(org.apache.hadoop.io.FloatWritable) LongWritable(org.apache.hadoop.io.LongWritable) Test(org.junit.Test)

Example 64 with LongWritable

use of org.apache.hadoop.io.LongWritable in project gatk by broadinstitute.

the class VariantsSparkSource method getParallelVariantContexts.

/**
     * Loads variants in parallel using Hadoop-BAM for vcfs and bcfs.
     * @param vcf file to load variants from.
     * @param intervals intervals of variants to include, or null if all should be included.
     * @return JavaRDD<VariantContext> of variants from all files.
     */
public JavaRDD<VariantContext> getParallelVariantContexts(final String vcf, final List<SimpleInterval> intervals) {
    Configuration conf = new Configuration();
    conf.setStrings("io.compression.codecs", BGZFEnhancedGzipCodec.class.getCanonicalName(), BGZFCodec.class.getCanonicalName());
    if (intervals != null && !intervals.isEmpty()) {
        VCFInputFormat.setIntervals(conf, intervals);
    }
    final JavaPairRDD<LongWritable, VariantContextWritable> rdd2 = ctx.newAPIHadoopFile(vcf, VCFInputFormat.class, LongWritable.class, VariantContextWritable.class, conf);
    return rdd2.map(v1 -> v1._2().get());
}
Also used : BGZFEnhancedGzipCodec(org.seqdoop.hadoop_bam.util.BGZFEnhancedGzipCodec) VariantContextWritable(org.seqdoop.hadoop_bam.VariantContextWritable) Configuration(org.apache.hadoop.conf.Configuration) BGZFCodec(org.seqdoop.hadoop_bam.util.BGZFCodec) LongWritable(org.apache.hadoop.io.LongWritable)

Example 65 with LongWritable

use of org.apache.hadoop.io.LongWritable in project incubator-systemml by apache.

the class MLContextConversionUtil method javaRDDStringCSVToMatrixObject.

/**
 * Convert a {@code JavaRDD<String>} in CSV format to a {@code MatrixObject}
 *
 * @param javaRDD
 *            the Java RDD of strings
 * @param matrixMetadata
 *            matrix metadata
 * @return the {@code JavaRDD<String>} converted to a {@code MatrixObject}
 */
public static MatrixObject javaRDDStringCSVToMatrixObject(JavaRDD<String> javaRDD, MatrixMetadata matrixMetadata) {
    JavaPairRDD<LongWritable, Text> javaPairRDD = javaRDD.mapToPair(new ConvertStringToLongTextPair());
    MatrixCharacteristics mc = (matrixMetadata != null) ? matrixMetadata.asMatrixCharacteristics() : new MatrixCharacteristics();
    MatrixObject matrixObject = new MatrixObject(ValueType.DOUBLE, OptimizerUtils.getUniqueTempFileName(), new MetaDataFormat(mc, OutputInfo.CSVOutputInfo, InputInfo.CSVInputInfo));
    JavaPairRDD<LongWritable, Text> javaPairRDD2 = javaPairRDD.mapToPair(new CopyTextInputFunction());
    matrixObject.setRDDHandle(new RDDObject(javaPairRDD2));
    return matrixObject;
}
Also used : MetaDataFormat(org.apache.sysml.runtime.matrix.MetaDataFormat) CopyTextInputFunction(org.apache.sysml.runtime.instructions.spark.functions.CopyTextInputFunction) MatrixObject(org.apache.sysml.runtime.controlprogram.caching.MatrixObject) ConvertStringToLongTextPair(org.apache.sysml.runtime.instructions.spark.functions.ConvertStringToLongTextPair) RDDObject(org.apache.sysml.runtime.instructions.spark.data.RDDObject) Text(org.apache.hadoop.io.Text) LongWritable(org.apache.hadoop.io.LongWritable) MatrixCharacteristics(org.apache.sysml.runtime.matrix.MatrixCharacteristics)

Aggregations

LongWritable (org.apache.hadoop.io.LongWritable)445 Text (org.apache.hadoop.io.Text)220 Test (org.junit.Test)171 IntWritable (org.apache.hadoop.io.IntWritable)102 Path (org.apache.hadoop.fs.Path)99 BytesWritable (org.apache.hadoop.io.BytesWritable)70 FloatWritable (org.apache.hadoop.io.FloatWritable)68 Configuration (org.apache.hadoop.conf.Configuration)62 DoubleWritable (org.apache.hadoop.hive.serde2.io.DoubleWritable)62 BooleanWritable (org.apache.hadoop.io.BooleanWritable)60 ArrayList (java.util.ArrayList)59 ObjectInspector (org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector)57 ShortWritable (org.apache.hadoop.hive.serde2.io.ShortWritable)53 IOException (java.io.IOException)49 ByteWritable (org.apache.hadoop.hive.serde2.io.ByteWritable)48 SequenceFile (org.apache.hadoop.io.SequenceFile)42 HiveDecimalWritable (org.apache.hadoop.hive.serde2.io.HiveDecimalWritable)40 FileSystem (org.apache.hadoop.fs.FileSystem)37 JobConf (org.apache.hadoop.mapred.JobConf)37 DeferredObject (org.apache.hadoop.hive.ql.udf.generic.GenericUDF.DeferredObject)35