How to use

readGenericRecords

method

in

org.apache.beam.sdk.io.AvroIO

public static void runAvroToCsv(SampleOptions options)
  throws IOException, IllegalArgumentException {
 FileSystems.setDefaultPipelineOptions(options);
 // Get Avro Schema
 String schemaJson = getSchema(options.getAvroSchema());
 Schema schema = new Schema.Parser().parse(schemaJson);
 // Check schema field types before starting the Dataflow job
 checkFieldTypes(schema);
 // Create the Pipeline object with the options we defined above.
 Pipeline pipeline = Pipeline.create(options);
 // Convert Avro To CSV
 pipeline.apply("Read Avro files",
   AvroIO.readGenericRecords(schemaJson).from(options.getInputFile()))
   .apply("Convert Avro to CSV formatted data",
     ParDo.of(new ConvertAvroToCsv(schemaJson, options.getCsvDelimiter())))
   .apply("Write CSV formatted data", TextIO.write().to(options.getOutput())
     .withSuffix(".csv"));
 // Run the pipeline.
 pipeline.run().waitUntilFinish();
}

/**
 * Reads Avro file(s) containing records of the specified schema. The schema is specified as a
 * JSON-encoded string.
 */
public static Read<GenericRecord> readGenericRecords(String schema) {
 return readGenericRecords(new Schema.Parser().parse(schema));
}

@Test
@Category(NeedsRunner.class)
public void testWriteThenReadGeneratedClassWithSchemaString() throws Throwable {
 testWriteThenReadGeneratedClass(
   AvroIO.writeGenericRecords(SCHEMA.toString()),
   AvroIO.readGenericRecords(SCHEMA.toString()));
}

@Test
@Category(NeedsRunner.class)
public void testWriteThenReadGeneratedClassWithSchema() throws Throwable {
 testWriteThenReadGeneratedClass(
   AvroIO.writeGenericRecords(SCHEMA), AvroIO.readGenericRecords(SCHEMA));
}

@Test
@Category(ValidatesRunner.class)
public void testPrimitiveReadDisplayData() {
 DisplayDataEvaluator evaluator = DisplayDataEvaluator.create();
 AvroIO.Read<GenericRecord> read =
   AvroIO.readGenericRecords(Schema.create(Schema.Type.STRING)).from("/foo.*");
 Set<DisplayData> displayData = evaluator.displayDataForPrimitiveSourceTransforms(read);
 assertThat(
   "AvroIO.Read should include the file pattern in its primitive transform",
   displayData,
   hasItem(hasDisplayItem("filePattern")));
}

  readPipeline.apply(
    "read_" + prefix,
    AvroIO.readGenericRecords(schemaFromPrefix(prefix)).from(expectedFilepattern));
PAssert.that(records).containsInAnyOrder(expectedElements.get(prefix));