Examples with DataFileStream org.apache.avro.file.DataFileStream used on opensource projects

Example 26 with DataFileStream

use of org.apache.avro.file.DataFileStream in project flink by apache.

the class RollingSinkITCase method testNonRollingAvroKeyValueWithoutCompressionWriter.

/**
	 * This tests {@link AvroKeyValueSinkWriter}
	 * with non-rolling output and without compression.
	 */
@Test
public void testNonRollingAvroKeyValueWithoutCompressionWriter() throws Exception {
    final int NUM_ELEMENTS = 20;
    final int PARALLELISM = 2;
    final String outPath = hdfsURI + "/avro-kv-no-comp-non-rolling-out";
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    env.setParallelism(PARALLELISM);
    DataStream<Tuple2<Integer, String>> source = env.addSource(new TestSourceFunction(NUM_ELEMENTS)).broadcast().filter(new OddEvenFilter());
    Map<String, String> properties = new HashMap<>();
    Schema keySchema = Schema.create(Type.INT);
    Schema valueSchema = Schema.create(Type.STRING);
    properties.put(AvroKeyValueSinkWriter.CONF_OUTPUT_KEY_SCHEMA, keySchema.toString());
    properties.put(AvroKeyValueSinkWriter.CONF_OUTPUT_VALUE_SCHEMA, valueSchema.toString());
    RollingSink<Tuple2<Integer, String>> sink = new RollingSink<Tuple2<Integer, String>>(outPath).setWriter(new AvroKeyValueSinkWriter<Integer, String>(properties)).setBucketer(new NonRollingBucketer()).setPartPrefix("part").setPendingPrefix("").setPendingSuffix("");
    source.addSink(sink);
    env.execute("RollingSink Avro KeyValue Writer Test");
    GenericData.setStringType(valueSchema, StringType.String);
    Schema elementSchema = AvroKeyValue.getSchema(keySchema, valueSchema);
    FSDataInputStream inStream = dfs.open(new Path(outPath + "/part-0-0"));
    SpecificDatumReader<GenericRecord> elementReader = new SpecificDatumReader<GenericRecord>(elementSchema);
    DataFileStream<GenericRecord> dataFileStream = new DataFileStream<GenericRecord>(inStream, elementReader);
    for (int i = 0; i < NUM_ELEMENTS; i += 2) {
        AvroKeyValue<Integer, String> wrappedEntry = new AvroKeyValue<Integer, String>(dataFileStream.next());
        int key = wrappedEntry.getKey().intValue();
        Assert.assertEquals(i, key);
        String value = wrappedEntry.getValue();
        Assert.assertEquals("message #" + i, value);
    }
    dataFileStream.close();
    inStream.close();
    inStream = dfs.open(new Path(outPath + "/part-1-0"));
    dataFileStream = new DataFileStream<GenericRecord>(inStream, elementReader);
    for (int i = 1; i < NUM_ELEMENTS; i += 2) {
        AvroKeyValue<Integer, String> wrappedEntry = new AvroKeyValue<Integer, String>(dataFileStream.next());
        int key = wrappedEntry.getKey().intValue();
        Assert.assertEquals(i, key);
        String value = wrappedEntry.getValue();
        Assert.assertEquals("message #" + i, value);
    }
    dataFileStream.close();
    inStream.close();
}

Example 27 with DataFileStream

use of org.apache.avro.file.DataFileStream in project flink by apache.

the class BucketingSinkTest method testUserDefinedConfiguration.

/**
	 * This tests user defined hdfs configuration
	 * @throws Exception
	 */
@Test
public void testUserDefinedConfiguration() throws Exception {
    final String outPath = hdfsURI + "/string-non-rolling-with-config";
    final int numElements = 20;
    Map<String, String> properties = new HashMap<>();
    Schema keySchema = Schema.create(Schema.Type.INT);
    Schema valueSchema = Schema.create(Schema.Type.STRING);
    properties.put(AvroKeyValueSinkWriter.CONF_OUTPUT_KEY_SCHEMA, keySchema.toString());
    properties.put(AvroKeyValueSinkWriter.CONF_OUTPUT_VALUE_SCHEMA, valueSchema.toString());
    properties.put(AvroKeyValueSinkWriter.CONF_COMPRESS, String.valueOf(true));
    properties.put(AvroKeyValueSinkWriter.CONF_COMPRESS_CODEC, DataFileConstants.SNAPPY_CODEC);
    Configuration conf = new Configuration();
    conf.set("io.file.buffer.size", "40960");
    BucketingSink<Tuple2<Integer, String>> sink = new BucketingSink<Tuple2<Integer, String>>(outPath).setFSConfig(conf).setWriter(new StreamWriterWithConfigCheck<Integer, String>(properties, "io.file.buffer.size", "40960")).setBucketer(new BasePathBucketer<Tuple2<Integer, String>>()).setPartPrefix(PART_PREFIX).setPendingPrefix("").setPendingSuffix("");
    OneInputStreamOperatorTestHarness<Tuple2<Integer, String>, Object> testHarness = createTestSink(sink, 1, 0);
    testHarness.setProcessingTime(0L);
    testHarness.setup();
    testHarness.open();
    for (int i = 0; i < numElements; i++) {
        testHarness.processElement(new StreamRecord<>(Tuple2.of(i, "message #" + Integer.toString(i))));
    }
    testHarness.close();
    GenericData.setStringType(valueSchema, GenericData.StringType.String);
    Schema elementSchema = AvroKeyValueSinkWriter.AvroKeyValue.getSchema(keySchema, valueSchema);
    FSDataInputStream inStream = dfs.open(new Path(outPath + "/" + PART_PREFIX + "-0-0"));
    SpecificDatumReader<GenericRecord> elementReader = new SpecificDatumReader<>(elementSchema);
    DataFileStream<GenericRecord> dataFileStream = new DataFileStream<>(inStream, elementReader);
    for (int i = 0; i < numElements; i++) {
        AvroKeyValueSinkWriter.AvroKeyValue<Integer, String> wrappedEntry = new AvroKeyValueSinkWriter.AvroKeyValue<>(dataFileStream.next());
        int key = wrappedEntry.getKey();
        Assert.assertEquals(i, key);
        String value = wrappedEntry.getValue();
        Assert.assertEquals("message #" + i, value);
    }
    dataFileStream.close();
    inStream.close();
}

Example 28 with DataFileStream

use of org.apache.avro.file.DataFileStream in project flink by apache.

the class BucketingSinkTest method testNonRollingAvroKeyValueWithCompressionWriter.

/**
	 * This tests {@link AvroKeyValueSinkWriter}
	 * with non-rolling output and with compression.
	 */
@Test
public void testNonRollingAvroKeyValueWithCompressionWriter() throws Exception {
    final String outPath = hdfsURI + "/avro-kv-no-comp-non-rolling-out";
    final int numElements = 20;
    Map<String, String> properties = new HashMap<>();
    Schema keySchema = Schema.create(Schema.Type.INT);
    Schema valueSchema = Schema.create(Schema.Type.STRING);
    properties.put(AvroKeyValueSinkWriter.CONF_OUTPUT_KEY_SCHEMA, keySchema.toString());
    properties.put(AvroKeyValueSinkWriter.CONF_OUTPUT_VALUE_SCHEMA, valueSchema.toString());
    properties.put(AvroKeyValueSinkWriter.CONF_COMPRESS, String.valueOf(true));
    properties.put(AvroKeyValueSinkWriter.CONF_COMPRESS_CODEC, DataFileConstants.SNAPPY_CODEC);
    BucketingSink<Tuple2<Integer, String>> sink = new BucketingSink<Tuple2<Integer, String>>(outPath).setWriter(new AvroKeyValueSinkWriter<Integer, String>(properties)).setBucketer(new BasePathBucketer<Tuple2<Integer, String>>()).setPartPrefix(PART_PREFIX).setPendingPrefix("").setPendingSuffix("");
    OneInputStreamOperatorTestHarness<Tuple2<Integer, String>, Object> testHarness = createTestSink(sink, 1, 0);
    testHarness.setProcessingTime(0L);
    testHarness.setup();
    testHarness.open();
    for (int i = 0; i < numElements; i++) {
        testHarness.processElement(new StreamRecord<>(Tuple2.of(i, "message #" + Integer.toString(i))));
    }
    testHarness.close();
    GenericData.setStringType(valueSchema, GenericData.StringType.String);
    Schema elementSchema = AvroKeyValueSinkWriter.AvroKeyValue.getSchema(keySchema, valueSchema);
    FSDataInputStream inStream = dfs.open(new Path(outPath + "/" + PART_PREFIX + "-0-0"));
    SpecificDatumReader<GenericRecord> elementReader = new SpecificDatumReader<>(elementSchema);
    DataFileStream<GenericRecord> dataFileStream = new DataFileStream<>(inStream, elementReader);
    for (int i = 0; i < numElements; i++) {
        AvroKeyValueSinkWriter.AvroKeyValue<Integer, String> wrappedEntry = new AvroKeyValueSinkWriter.AvroKeyValue<>(dataFileStream.next());
        int key = wrappedEntry.getKey();
        Assert.assertEquals(i, key);
        String value = wrappedEntry.getValue();
        Assert.assertEquals("message #" + i, value);
    }
    dataFileStream.close();
    inStream.close();
}

Example 29 with DataFileStream

use of org.apache.avro.file.DataFileStream in project pinot by linkedin.

the class SegmentTestUtils method getColumnNamesFromAvro.

public static List<String> getColumnNamesFromAvro(File avro) throws FileNotFoundException, IOException {
    List<String> ret = new ArrayList<String>();
    DataFileStream<GenericRecord> dataStream = new DataFileStream<GenericRecord>(new FileInputStream(avro), new GenericDatumReader<GenericRecord>());
    for (final Field field : dataStream.getSchema().getFields()) {
        ret.add(field.name());
    }
    return ret;
}

Example 30 with DataFileStream

use of org.apache.avro.file.DataFileStream in project pinot by linkedin.

the class SegmentTestUtils method extractSchemaFromAvro.

public static Schema extractSchemaFromAvro(File avroFile, Map<String, FieldType> fieldTypeMap, TimeUnit granularity) throws IOException {
    DataFileStream<GenericRecord> dataStream = new DataFileStream<>(new FileInputStream(avroFile), new GenericDatumReader<GenericRecord>());
    Schema schema = new Schema();
    for (final Field field : dataStream.getSchema().getFields()) {
        final String columnName = field.name();
        FieldType fieldType = fieldTypeMap.get(columnName);
        Preconditions.checkNotNull(fieldType);
        switch(fieldType) {
            case TIME:
                final TimeGranularitySpec gSpec = new TimeGranularitySpec(getColumnType(field), granularity, columnName);
                final TimeFieldSpec fSpec = new TimeFieldSpec(gSpec);
                schema.addField(fSpec);
                continue;
            case DIMENSION:
                final FieldSpec dimensionFieldSpec = new DimensionFieldSpec(columnName, getColumnType(field), isSingleValueField(field));
                schema.addField(dimensionFieldSpec);
                continue;
            case METRIC:
                final FieldSpec metricFieldSpec = new MetricFieldSpec(columnName, getColumnType(field));
                schema.addField(metricFieldSpec);
                continue;
            default:
                throw new UnsupportedOperationException("Unsupported field type: " + fieldType);
        }
    }
    dataStream.close();
    return schema;
}