flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From fhueske <...@git.apache.org>
Subject [GitHub] flink pull request #3663: [FLINK-3871] [table] Add Kafka TableSource with Av...
Date Tue, 25 Apr 2017 16:38:55 GMT
Github user fhueske commented on a diff in the pull request:

    https://github.com/apache/flink/pull/3663#discussion_r113241182
  
    --- Diff: flink-connectors/flink-connector-kafka-base/src/main/java/org/apache/flink/streaming/util/serialization/AvroRowDeserializationSchema.java
---
    @@ -0,0 +1,157 @@
    +/*
    + * Licensed to the Apache Software Foundation (ASF) under one or more
    + * contributor license agreements.  See the NOTICE file distributed with
    + * this work for additional information regarding copyright ownership.
    + * The ASF licenses this file to You under the Apache License, Version 2.0
    + * (the "License"); you may not use this file except in compliance with
    + * the License.  You may obtain a copy of the License at
    + *
    + *    http://www.apache.org/licenses/LICENSE-2.0
    + *
    + * Unless required by applicable law or agreed to in writing, software
    + * distributed under the License is distributed on an "AS IS" BASIS,
    + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    + * See the License for the specific language governing permissions and
    + * limitations under the License.
    + */
    +package org.apache.flink.streaming.util.serialization;
    +
    +import java.io.ByteArrayInputStream;
    +import java.io.IOException;
    +import java.util.List;
    +import org.apache.avro.Schema;
    +import org.apache.avro.generic.GenericData;
    +import org.apache.avro.generic.GenericRecord;
    +import org.apache.avro.io.DatumReader;
    +import org.apache.avro.io.Decoder;
    +import org.apache.avro.io.DecoderFactory;
    +import org.apache.avro.reflect.ReflectDatumReader;
    +import org.apache.avro.specific.SpecificData;
    +import org.apache.avro.specific.SpecificRecord;
    +import org.apache.avro.util.Utf8;
    +import org.apache.flink.types.Row;
    +import org.apache.flink.util.Preconditions;
    +
    +/**
    + * Deserialization schema from Avro bytes over {@link SpecificRecord} to {@link Row}.
    + *
    + * Deserializes the <code>byte[]</code> messages into (nested) Flink Rows.
    + *
    + * {@link Utf8} is converted to regular Java Strings.
    + */
    +public class AvroRowDeserializationSchema extends AbstractDeserializationSchema<Row>
{
    +
    +	/**
    +	 * Schema for deterministic field order.
    +	 */
    +	private final Schema schema;
    +
    +	/**
    +	 * Reader that deserializes byte array into a record.
    +	 */
    +	private final DatumReader<GenericRecord> datumReader;
    +
    +	/**
    +	 * Input stream to read message from.
    +	 */
    +	private final MutableByteArrayInputStream inputStream;
    +
    +	/**
    +	 * Avro decoder that decodes binary data
    +	 */
    +	private final Decoder decoder;
    +
    +	/**
    +	 * Record to deserialize byte array to.
    +	 */
    +	private GenericRecord record;
    +
    +	/**
    +	 * Creates a Avro deserialization schema for the given record.
    +	 *
    +	 * @param recordClazz Avro record class used to deserialize Avro's record to Flink's
row
    +	 */
    +	@SuppressWarnings("unchecked")
    +	public AvroRowDeserializationSchema(Class<? extends SpecificRecord> recordClazz)
{
    +		Preconditions.checkNotNull(recordClazz, "Avro record class must not be null.");
    +		this.schema = SpecificData.get().getSchema(recordClazz);
    +		this.datumReader = new ReflectDatumReader<>(schema);
    +		this.record = new GenericData.Record(schema);
    --- End diff --
    
    We can use a specific record here. We have the class for it.
    ```
    this.record = (SpecificRecord) SpecificData.newInstance(recordClazz, schema);
    ```


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message