Examples with SimpleFileIOOutputProperties org.talend.components.simplefileio.output.SimpleFileIOOutputProperties used on opensource projects

Example 16 with SimpleFileIOOutputProperties

use of org.talend.components.simplefileio.output.SimpleFileIOOutputProperties in project components by Talend.

the class SimpleFileIORoundTripRuntimeTest method testAvro.

/**
 * Basic Avro test.
 */
@Test
public void testAvro() throws IOException {
    // The file that we will be creating.
    RecordSet rs = getSimpleTestData(0);
    String fileSpec = mini.getLocalFsNewFolder() + "output/";
    // Configure the components.
    SimpleFileIOOutputProperties outputProps = createOutputComponentProperties();
    outputProps.getDatasetProperties().format.setValue(SimpleFileIOFormat.AVRO);
    outputProps.getDatasetProperties().path.setValue(fileSpec);
    SimpleFileIOInputProperties inputProps = createInputComponentProperties();
    inputProps.setDatasetProperties(outputProps.getDatasetProperties());
    List<IndexedRecord> actual = runRoundTripPipelines(beam, rs.getAllData(), outputProps, inputProps);
    // Generate the set of expected records. By default, CSV turns all columns into String and loses the original
    // column name.
    List<IndexedRecord> expected = rs.getAllData();
    assertThat(actual, containsInAnyOrder(expected.toArray()));
// Verify that the file on the filesystem was correctly written.
// TODO(rskraba): verify independently
// mini.assertReadFile(
// mini.getLocalFs(),
// fileSpec,
// rewriteRecordsAsCsvLines(expected, inputProps.getDatasetProperties().recordDelimiter.getValue(),
// inputProps.getDatasetProperties().fieldDelimiter.getValue()));
}

Example 17 with SimpleFileIOOutputProperties

use of org.talend.components.simplefileio.output.SimpleFileIOOutputProperties in project components by Talend.

the class SimpleFileIORoundTripRuntimeTest method testBasicDefaults.

/**
 * Basic unit test using all default values (except for the path) on an in-memory DFS cluster.
 */
@Test
public void testBasicDefaults() throws IOException {
    // The file that we will be creating.
    RecordSet rs = getSimpleTestData(0);
    String fileSpec = mini.getLocalFsNewFolder() + "output/";
    // Configure the components.
    SimpleFileIOOutputProperties outputProps = createOutputComponentProperties();
    outputProps.getDatasetProperties().path.setValue(fileSpec);
    SimpleFileIOInputProperties inputProps = createInputComponentProperties();
    inputProps.setDatasetProperties(outputProps.getDatasetProperties());
    List<IndexedRecord> actual = runRoundTripPipelines(beam, rs.getAllData(), outputProps, inputProps);
    // Generate the set of expected records. By default, CSV turns all columns into String and loses the original
    // column name.
    List<IndexedRecord> expected = rewriteRecordsWithCsvSchema(rs.getAllData());
    assertThat(expected, containsInAnyOrder(actual.toArray()));
    // Verify that the file on the filesystem was correctly written.
    mini.assertReadFile(mini.getLocalFs(), fileSpec, rewriteRecordsAsCsvLines(expected, inputProps.getDatasetProperties().getRecordDelimiter(), inputProps.getDatasetProperties().getFieldDelimiter()));
}

Example 18 with SimpleFileIOOutputProperties

use of org.talend.components.simplefileio.output.SimpleFileIOOutputProperties in project components by Talend.

the class SparkSimpleFileIOOutputRuntimeTestIT method testBasicDefaults.

/**
 * Basic unit test using all default values (except for the path) on an in-memory DFS cluster.
 */
@Category(ValidatesRunner.class)
@Ignore("BEAM-1206")
@Test
public void testBasicDefaults() throws IOException {
    FileSystem fs = FileSystem.get(spark.createHadoopConfiguration());
    String fileSpec = fs.getUri().resolve(new Path(tmp.getRoot().toString(), "basic").toUri()).toString();
    // Configure the component.
    SimpleFileIOOutputProperties props = SimpleFileIOOutputRuntimeTest.createOutputComponentProperties();
    props.getDatasetProperties().path.setValue(fileSpec);
    props.getDatasetProperties().format.setValue(SimpleFileIOFormat.AVRO);
    // Create the runtime.
    SimpleFileIOOutputRuntime runtime = new SimpleFileIOOutputRuntime();
    runtime.initialize(null, props);
    // Use the runtime in a Spark pipeline to test.
    final Pipeline p = spark.createPipeline();
    PCollection<IndexedRecord> input = // 
    p.apply(// 
    Create.of(// 
    ConvertToIndexedRecord.convertToAvro(new String[] { "1", "one" }), // 
    ConvertToIndexedRecord.convertToAvro(new String[] { "2", "two" })));
    input.apply(runtime);
    // And run the test.
    p.run().waitUntilFinish();
    // Check the expected values.
    MiniDfsResource.assertReadFile(fs, fileSpec, "1;one", "2;two");
}

Example 19 with SimpleFileIOOutputProperties

use of org.talend.components.simplefileio.output.SimpleFileIOOutputProperties in project components by Talend.

the class SimpleFileIOOutputRuntimeTest method testTryToOverwrite.

/**
 * Basic unit test using all default values (except for the path) on an in-memory DFS cluster.
 */
@Test
public void testTryToOverwrite() throws IOException, URISyntaxException {
    Path parent = new Path(mini.newFolder().toString());
    Path dst = new Path(parent, "output");
    String fileSpec = mini.getLocalFs().getUri().resolve(dst.toUri()).toString();
    // Write something to the file before trying to run.
    try (OutputStream out = mini.getLocalFs().create(new Path(dst, "part-00000"))) {
        out.write(0);
    }
    // Now try using the component.
    try {
        // Configure the component.
        SimpleFileIOOutputProperties props = SimpleFileIOOutputRuntimeTest.createOutputComponentProperties();
        props.getDatasetProperties().path.setValue(fileSpec);
        props.overwrite.setValue(true);
        // Create the runtime.
        SimpleFileIOOutputRuntime runtime = new SimpleFileIOOutputRuntime();
        runtime.initialize(null, props);
        // Use the runtime in a direct pipeline to test.
        final Pipeline p = beam.createPipeline();
        PCollection<IndexedRecord> input = // 
        p.apply(// 
        Create.of(// 
        ConvertToIndexedRecord.convertToAvro(new String[] { "1", "one" }), // 
        ConvertToIndexedRecord.convertToAvro(new String[] { "2", "two" })));
        input.apply(runtime);
        // And run the test.
        runtime.runAtDriver(null);
        p.run().waitUntilFinish();
    } catch (Pipeline.PipelineExecutionException e) {
        if (e.getCause() instanceof TalendRuntimeException)
            throw (TalendRuntimeException) e.getCause();
        throw e;
    }
    // Check the expected values, which should be overwritten.
    mini.assertReadFile(mini.getLocalFs(), fileSpec, "1;one", "2;two");
}

Example 20 with SimpleFileIOOutputProperties

use of org.talend.components.simplefileio.output.SimpleFileIOOutputProperties in project components by Talend.

the class SimpleFileIOOutputRuntimeTest method testBasicDefaults.

/**
 * Basic unit test using all default values (except for the path) on an in-memory DFS cluster.
 */
@Test
public void testBasicDefaults() throws IOException, URISyntaxException {
    String fileSpec = mini.getLocalFs().getUri().resolve(new Path(mini.newFolder().toString(), "output.csv").toUri()).toString();
    // Configure the component.
    SimpleFileIOOutputProperties props = createOutputComponentProperties();
    props.getDatasetProperties().path.setValue(fileSpec);
    // Create the runtime.
    SimpleFileIOOutputRuntime runtime = new SimpleFileIOOutputRuntime();
    runtime.initialize(null, props);
    // Use the runtime in a direct pipeline to test.
    final Pipeline p = beam.createPipeline();
    PCollection<IndexedRecord> input = // 
    p.apply(// 
    Create.of(// 
    ConvertToIndexedRecord.convertToAvro(new String[] { "1", "one" }), // 
    ConvertToIndexedRecord.convertToAvro(new String[] { "2", "two" })));
    input.apply(runtime);
    // And run the test.
    p.run().waitUntilFinish();
    // Check the expected values.
    mini.assertReadFile(mini.getLocalFs(), fileSpec, "1;one", "2;two");
}