Examples with GenericDatumWriter org.apache.avro.generic.GenericDatumWriter used on opensource projects

Example 6 with GenericDatumWriter

use of org.apache.avro.generic.GenericDatumWriter in project druid by druid-io.

the class SchemaRegistryBasedAvroBytesDecoderTest method getAvroDatum.

byte[] getAvroDatum(Schema schema, GenericRecord someAvroDatum) throws IOException {
    ByteArrayOutputStream out = new ByteArrayOutputStream();
    DatumWriter<GenericRecord> writer = new GenericDatumWriter<GenericRecord>(schema);
    writer.write(someAvroDatum, EncoderFactory.get().directBinaryEncoder(out, null));
    return out.toByteArray();
}

Example 7 with GenericDatumWriter

use of org.apache.avro.generic.GenericDatumWriter in project haivvreo by jghoman.

the class AvroContainerOutputFormat method getHiveRecordWriter.

@Override
public FileSinkOperator.RecordWriter getHiveRecordWriter(JobConf jobConf, Path path, Class<? extends Writable> valueClass, boolean isCompressed, Properties properties, Progressable progressable) throws IOException {
    Schema schema;
    try {
        schema = HaivvreoUtils.determineSchemaOrThrowException(jobConf, properties);
    } catch (HaivvreoException e) {
        throw new IOException(e);
    }
    GenericDatumWriter<GenericRecord> gdw = new GenericDatumWriter<GenericRecord>(schema);
    DataFileWriter<GenericRecord> dfw = new DataFileWriter<GenericRecord>(gdw);
    if (isCompressed) {
        int level = jobConf.getInt(DEFLATE_LEVEL_KEY, DEFAULT_DEFLATE_LEVEL);
        String codecName = jobConf.get(OUTPUT_CODEC, DEFLATE_CODEC);
        CodecFactory factory = codecName.equals(DEFLATE_CODEC) ? CodecFactory.deflateCodec(level) : CodecFactory.fromString(codecName);
        dfw.setCodec(factory);
    }
    dfw.create(schema, path.getFileSystem(jobConf).create(path));
    return new AvroGenericRecordWriter(dfw);
}

Example 8 with GenericDatumWriter

use of org.apache.avro.generic.GenericDatumWriter in project rest.li by linkedin.

the class AvroUtil method jsonFromGenericRecord.

public static String jsonFromGenericRecord(GenericRecord record) throws IOException {
    GenericDatumWriter<GenericRecord> writer = new GenericDatumWriter<GenericRecord>();
    ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
    AvroAdapter avroAdapter = AvroAdapterFinder.getAvroAdapter();
    Encoder jsonEncoder = avroAdapter.createJsonEncoder(record.getSchema(), outputStream);
    writer.setSchema(record.getSchema());
    writer.write(record, jsonEncoder);
    jsonEncoder.flush();
    return outputStream.toString();
}

Example 9 with GenericDatumWriter

use of org.apache.avro.generic.GenericDatumWriter in project databus by linkedin.

the class RelayEventGenerator method populateEvents.

int populateEvents(String source, short id, GenericRecord record, DbusEventKey key, byte[] schemaId, DbusEventsStatisticsCollector statsCollector, DbusEventBufferAppendable buffer) {
    if (record != null && key != null) {
        try {
            // Serialize the row
            ByteArrayOutputStream bos = new ByteArrayOutputStream();
            Encoder encoder = new BinaryEncoder(bos);
            GenericDatumWriter<GenericRecord> writer = new GenericDatumWriter<GenericRecord>(record.getSchema());
            writer.write(record, encoder);
            byte[] serializedValue = bos.toByteArray();
            short pPartitionId = RngUtils.randomPositiveShort();
            short lPartitionId = RngUtils.randomPositiveShort();
            long timeStamp = System.currentTimeMillis() * 1000000;
            buffer.appendEvent(key, pPartitionId, lPartitionId, timeStamp, id, schemaId, serializedValue, false, statsCollector);
            return 1;
        } catch (IOException io) {
            LOG.error("Cannot create byte stream payload: " + source);
        }
    }
    return 0;
}

Example 10 with GenericDatumWriter

use of org.apache.avro.generic.GenericDatumWriter in project databus by linkedin.

the class GoldenGateEventProducer method addEventToBuffer.

/**
   *
   * @param dbUpdates  The dbUpdates present in the current transaction
   * @param ti The meta information about the transaction. (See TransactionInfo class for more details).
   * @throws DatabusException
   * @throws UnsupportedKeyException
   */
protected void addEventToBuffer(List<TransactionState.PerSourceTransactionalUpdate> dbUpdates, TransactionInfo ti) throws DatabusException, UnsupportedKeyException {
    if (dbUpdates.size() == 0)
        throw new DatabusException("Cannot handle empty dbUpdates");
    long scn = ti.getScn();
    long timestamp = ti.getTransactionTimeStampNs();
    EventSourceStatistics globalStats = getSource(GLOBAL_SOURCE_ID).getStatisticsBean();
    /**
     * We skip the start scn of the relay, we have already added a EOP for this SCN in the buffer.
     * Why is this not a problem ?
     * There are two cases:
     * 1. When we use the earliest/latest scn if there is no maxScn (We don't really have a start point). So it's really OK to miss the first event.
     * 2. If it's the maxSCN, then event was already seen by the relay.
     */
    if (scn == _startPrevScn.get()) {
        _log.info("Skipping this transaction, EOP already send for this event");
        return;
    }
    getEventBuffer().startEvents();
    int eventsInTransactionCount = 0;
    List<EventReaderSummary> summaries = new ArrayList<EventReaderSummary>();
    for (int i = 0; i < dbUpdates.size(); ++i) {
        GenericRecord record = null;
        TransactionState.PerSourceTransactionalUpdate perSourceUpdate = dbUpdates.get(i);
        short sourceId = (short) perSourceUpdate.getSourceId();
        // prepare stats collection per source
        EventSourceStatistics perSourceStats = getSource(sourceId).getStatisticsBean();
        Iterator<DbUpdateState.DBUpdateImage> dbUpdateIterator = perSourceUpdate.getDbUpdatesSet().iterator();
        int eventsInDbUpdate = 0;
        long dbUpdatesEventsSize = 0;
        long startDbUpdatesMs = System.currentTimeMillis();
        while (//TODO verify if there is any case where we need to rollback.
        dbUpdateIterator.hasNext()) {
            DbUpdateState.DBUpdateImage dbUpdate = dbUpdateIterator.next();
            //Construct the Databus Event key, determine the key type and construct the key
            Object keyObj = obtainKey(dbUpdate);
            DbusEventKey eventKey = new DbusEventKey(keyObj);
            //Get the logicalparition id
            PartitionFunction partitionFunction = _partitionFunctionHashMap.get((int) sourceId);
            short lPartitionId = partitionFunction.getPartition(eventKey);
            record = dbUpdate.getGenericRecord();
            //Write the event to the buffer
            if (record == null)
                throw new DatabusException("Cannot write event to buffer because record = " + record);
            if (record.getSchema() == null)
                throw new DatabusException("The record does not have a schema (null schema)");
            try {
                //Collect stats on number of dbUpdates for one source
                eventsInDbUpdate++;
                //Count of all the events in the current transaction
                eventsInTransactionCount++;
                // Serialize the row
                ByteArrayOutputStream bos = new ByteArrayOutputStream();
                Encoder encoder = new BinaryEncoder(bos);
                GenericDatumWriter<GenericRecord> writer = new GenericDatumWriter<GenericRecord>(record.getSchema());
                writer.write(record, encoder);
                byte[] serializedValue = bos.toByteArray();
                //Get the md5 for the schema
                SchemaId schemaId = SchemaId.createWithMd5(dbUpdate.getSchema());
                //Determine the operation type and convert to dbus opcode
                DbusOpcode opCode;
                if (dbUpdate.getOpType() == DbUpdateState.DBUpdateImage.OpType.INSERT || dbUpdate.getOpType() == DbUpdateState.DBUpdateImage.OpType.UPDATE) {
                    opCode = DbusOpcode.UPSERT;
                    if (_log.isDebugEnabled())
                        _log.debug("The event with scn " + scn + " is INSERT/UPDATE");
                } else if (dbUpdate.getOpType() == DbUpdateState.DBUpdateImage.OpType.DELETE) {
                    opCode = DbusOpcode.DELETE;
                    if (_log.isDebugEnabled())
                        _log.debug("The event with scn " + scn + " is DELETE");
                } else {
                    throw new DatabusException("Unknown opcode from dbUpdate for event with scn:" + scn);
                }
                //Construct the dbusEvent info
                DbusEventInfo dbusEventInfo = new DbusEventInfo(opCode, scn, (short) _pConfig.getId(), lPartitionId, timestamp, sourceId, schemaId.getByteArray(), serializedValue, false, false);
                dbusEventInfo.setReplicated(dbUpdate.isReplicated());
                perSourceStats.addEventCycle(1, ti.getTransactionTimeRead(), serializedValue.length, scn);
                globalStats.addEventCycle(1, ti.getTransactionTimeRead(), serializedValue.length, scn);
                long tsEnd = System.currentTimeMillis();
                perSourceStats.addTimeOfLastDBAccess(tsEnd);
                globalStats.addTimeOfLastDBAccess(tsEnd);
                //Append to the event buffer
                getEventBuffer().appendEvent(eventKey, dbusEventInfo, _statsCollector);
                _rc.incrementEventCount();
                dbUpdatesEventsSize += serializedValue.length;
            } catch (IOException io) {
                perSourceStats.addError();
                globalStats.addEmptyEventCycle();
                _log.error("Cannot create byte stream payload: " + dbUpdates.get(i).getSourceId());
            }
        }
        long endDbUpdatesMs = System.currentTimeMillis();
        long dbUpdatesElapsedTimeMs = endDbUpdatesMs - startDbUpdatesMs;
        // Log Event Summary at logical source level
        EventReaderSummary summary = new EventReaderSummary(sourceId, _monitoredSources.get(sourceId).getSourceName(), scn, eventsInDbUpdate, dbUpdatesEventsSize, -1L, /* Not supported */
        dbUpdatesElapsedTimeMs, timestamp, timestamp, -1L);
        if (_eventsLog.isInfoEnabled()) {
            _eventsLog.info(summary.toString());
        }
        summaries.add(summary);
        if (_log.isDebugEnabled())
            _log.debug("There are " + eventsInDbUpdate + " events seen in the current dbUpdate");
    }
    // Log Event Summary at Physical source level
    ReadEventCycleSummary summary = new ReadEventCycleSummary(_pConfig.getName(), summaries, scn, -1);
    if (_eventsLog.isInfoEnabled()) {
        _eventsLog.info(summary.toString());
    }
    _log.info("Writing " + eventsInTransactionCount + " events from transaction with scn: " + scn);
    if (scn <= 0)
        throw new DatabusException("Unable to write events to buffer because of negative/zero scn: " + scn);
    getEventBuffer().endEvents(scn, _statsCollector);
    _scn.set(scn);
    if (getMaxScnReaderWriter() != null) {
        try {
            getMaxScnReaderWriter().saveMaxScn(_scn.get());
        } catch (DatabusException e) {
            _log.error("Cannot save scn = " + _scn + " for physical source = " + getName(), e);
        }
    }
}