Examples with SerializableSplit org.apache.beam.sdk.io.hadoop.format.HadoopFormatIO.SerializableSplit used on opensource projects

Example 6 with SerializableSplit

use of org.apache.beam.sdk.io.hadoop.format.HadoopFormatIO.SerializableSplit in project beam by apache.

the class HadoopFormatIOReadTest method testReadDisplayData.

/**
 * This test validates functionality of {@link
 * HadoopInputFormatBoundedSource#populateDisplayData(DisplayData.Builder)}
 * populateDisplayData(DisplayData.Builder)}.
 */
@Test
public void testReadDisplayData() {
    HadoopInputFormatBoundedSource<Text, Employee> boundedSource = new HadoopInputFormatBoundedSource<>(serConf, WritableCoder.of(Text.class), AvroCoder.of(Employee.class), // No key translation required.
    null, // No value translation required.
    null, new SerializableSplit(), false, false);
    DisplayData displayData = DisplayData.from(boundedSource);
    assertThat(displayData, hasDisplayItem("mapreduce.job.inputformat.class", serConf.get().get("mapreduce.job.inputformat.class")));
    assertThat(displayData, hasDisplayItem("key.class", serConf.get().get("key.class")));
    assertThat(displayData, hasDisplayItem("value.class", serConf.get().get("value.class")));
}

Example 7 with SerializableSplit

use of org.apache.beam.sdk.io.hadoop.format.HadoopFormatIO.SerializableSplit in project beam by apache.

the class HadoopFormatIOReadTest method testReadIfCreateRecordReaderFails.

/**
 * This test validates behavior of {@link HadoopInputFormatBoundedSource} if RecordReader object
 * creation fails.
 */
@Test
public void testReadIfCreateRecordReaderFails() throws Exception {
    thrown.expect(Exception.class);
    thrown.expectMessage("Exception in creating RecordReader");
    InputFormat<Text, Employee> mockInputFormat = Mockito.mock(EmployeeInputFormat.class);
    Mockito.when(mockInputFormat.createRecordReader(Mockito.any(InputSplit.class), Mockito.any(TaskAttemptContext.class))).thenThrow(new IOException("Exception in creating RecordReader"));
    HadoopInputFormatBoundedSource<Text, Employee> boundedSource = new HadoopInputFormatBoundedSource<>(serConf, WritableCoder.of(Text.class), AvroCoder.of(Employee.class), // No key translation required.
    null, // No value translation required.
    null, new SerializableSplit(), false, false);
    boundedSource.setInputFormatObj(mockInputFormat);
    SourceTestUtils.readFromSource(boundedSource, p.getOptions());
}

Example 8 with SerializableSplit

use of org.apache.beam.sdk.io.hadoop.format.HadoopFormatIO.SerializableSplit in project beam by apache.

the class HadoopFormatIOReadTest method testGetFractionConsumedForBadProgressValue.

/**
 * This test validates the method getFractionConsumed()- when a bad progress value is returned by
 * the inputformat.
 */
@Test
public void testGetFractionConsumedForBadProgressValue() throws Exception {
    InputFormat<Text, Employee> mockInputFormat = Mockito.mock(EmployeeInputFormat.class);
    EmployeeRecordReader mockReader = Mockito.mock(EmployeeRecordReader.class);
    Mockito.when(mockInputFormat.createRecordReader(Mockito.any(), Mockito.any())).thenReturn(mockReader);
    Mockito.when(mockReader.nextKeyValue()).thenReturn(true);
    // Set to a bad value , not in range of 0 to 1
    Mockito.when(mockReader.getProgress()).thenReturn(2.0F);
    InputSplit mockInputSplit = Mockito.mock(NewObjectsEmployeeInputSplit.class);
    HadoopInputFormatBoundedSource<Text, Employee> boundedSource = new HadoopInputFormatBoundedSource<>(serConf, WritableCoder.of(Text.class), AvroCoder.of(Employee.class), // No key translation required.
    null, // No value translation required.
    null, new SerializableSplit(mockInputSplit), false, false);
    boundedSource.setInputFormatObj(mockInputFormat);
    BoundedReader<KV<Text, Employee>> reader = boundedSource.createReader(p.getOptions());
    assertEquals(Double.valueOf(0), reader.getFractionConsumed());
    boolean start = reader.start();
    assertTrue(start);
    if (start) {
        boolean advance = reader.advance();
        assertEquals(null, reader.getFractionConsumed());
        assertTrue(advance);
        if (advance) {
            advance = reader.advance();
            assertEquals(null, reader.getFractionConsumed());
        }
    }
    // Validate if getFractionConsumed() returns null after few number of reads as getProgress
    // returns invalid value '2' which is not in the range of 0 to 1.
    assertEquals(null, reader.getFractionConsumed());
    reader.close();
}

Example 9 with SerializableSplit

use of org.apache.beam.sdk.io.hadoop.format.HadoopFormatIO.SerializableSplit in project beam by apache.

the class HadoopFormatIOReadTest method testReadWithNullCreateRecordReader.

/**
 * This test validates behavior of HadoopInputFormatSource if {@link
 * InputFormat#createRecordReader(InputSplit, TaskAttemptContext)} createRecordReader(InputSplit,
 * TaskAttemptContext)} of InputFormat returns null.
 */
@Test
public void testReadWithNullCreateRecordReader() throws Exception {
    InputFormat<Text, Employee> mockInputFormat = Mockito.mock(EmployeeInputFormat.class);
    thrown.expect(IOException.class);
    thrown.expectMessage(String.format("Null RecordReader object returned by %s", mockInputFormat.getClass()));
    Mockito.when(mockInputFormat.createRecordReader(Mockito.any(InputSplit.class), Mockito.any(TaskAttemptContext.class))).thenReturn(null);
    HadoopInputFormatBoundedSource<Text, Employee> boundedSource = new HadoopInputFormatBoundedSource<>(serConf, WritableCoder.of(Text.class), AvroCoder.of(Employee.class), // No key translation required.
    null, // No value translation required.
    null, new SerializableSplit(), false, false);
    boundedSource.setInputFormatObj(mockInputFormat);
    SourceTestUtils.readFromSource(boundedSource, p.getOptions());
}

Example 10 with SerializableSplit

use of org.apache.beam.sdk.io.hadoop.format.HadoopFormatIO.SerializableSplit in project beam by apache.

the class HadoopFormatIOReadTest method testReadersStartWhenZeroRecords.

/**
 * This test validates behavior of {@link
 * HadoopInputFormatBoundedSource.HadoopInputFormatReader#start() start()} method if InputFormat's
 * {@link InputFormat#getSplits(JobContext)} getSplits(JobContext)} returns InputSplitList having
 * zero records.
 */
@Test
public void testReadersStartWhenZeroRecords() throws Exception {
    InputFormat mockInputFormat = Mockito.mock(EmployeeInputFormat.class);
    EmployeeRecordReader mockReader = Mockito.mock(EmployeeRecordReader.class);
    Mockito.when(mockInputFormat.createRecordReader(Mockito.any(), Mockito.any())).thenReturn(mockReader);
    Mockito.when(mockReader.nextKeyValue()).thenReturn(false);
    InputSplit mockInputSplit = Mockito.mock(NewObjectsEmployeeInputSplit.class);
    HadoopInputFormatBoundedSource<Text, Employee> boundedSource = new HadoopInputFormatBoundedSource<>(serConf, WritableCoder.of(Text.class), AvroCoder.of(Employee.class), // No key translation required.
    null, // No value translation required.
    null, new SerializableSplit(mockInputSplit), false, false);
    boundedSource.setInputFormatObj(mockInputFormat);
    BoundedReader<KV<Text, Employee>> reader = boundedSource.createReader(p.getOptions());
    assertFalse(reader.start());
    assertEquals(Double.valueOf(1), reader.getFractionConsumed());
    reader.close();
}