从 POJO 到 Avro Record 的通用转换

java avro

2022-09-02 10:07:00

我正在寻找一种以通用方式将POJO转换为avro对象的方法。该实现应该对 POJO 类的任何更改都是健壮的。我已经实现了它，但明确填写了avro记录（请参阅下面的示例）。

有没有办法摆脱硬编码的字段名称，只填写对象中的avro记录？反射是唯一的方法，还是avro提供了这种开箱即用的功能？

import java.util.Date;
import java.util.HashMap;
import java.util.Map;

import org.apache.avro.Schema;
import org.apache.avro.generic.GenericData.Record;
import org.apache.avro.reflect.ReflectData;

public class PojoToAvroExample {

    static class PojoParent {
        public final Map<String, String> aMap = new HashMap<String, String>();
        public final Map<String, Integer> anotherMap = new HashMap<String, Integer>();
    }

    static class Pojo extends PojoParent {
        public String uid;
        public Date eventTime;
    }

    static Pojo createPojo() {
        Pojo foo = new Pojo();
        foo.uid = "123";
        foo.eventTime = new Date();
        foo.aMap.put("key", "val");
        foo.anotherMap.put("key", 42);
        return foo;
    }

    public static void main(String[] args) {
        // extract the avro schema corresponding to Pojo class
        Schema schema = ReflectData.get().getSchema(Pojo.class);
        System.out.println("extracted avro schema: " + schema);
        // create avro record corresponding to schema
        Record avroRecord = new Record(schema);
        System.out.println("corresponding empty avro record: " + avroRecord);

        Pojo foo = createPojo();
        // TODO: to be replaced by generic variant:
        // something like avroRecord.importValuesFrom(foo);
        avroRecord.put("uid", foo.uid);
        avroRecord.put("eventTime", foo.eventTime);
        avroRecord.put("aMap", foo.aMap);
        avroRecord.put("anotherMap", foo.anotherMap);
        System.out.println("expected avro record: " + avroRecord);
    }
}

答案 1

你在使用春天吗？

我使用Spring功能为此构建了一个映射器。但是也可以通过原始反射实用程序构建这样的映射器：

import org.apache.avro.Schema;
import org.apache.avro.generic.GenericData;
import org.apache.avro.reflect.ReflectData;
import org.springframework.beans.PropertyAccessorFactory;
import org.springframework.util.Assert;

public class GenericRecordMapper {

    public static GenericData.Record mapObjectToRecord(Object object) {
        Assert.notNull(object, "object must not be null");
        final Schema schema = ReflectData.get().getSchema(object.getClass());
        final GenericData.Record record = new GenericData.Record(schema);
        schema.getFields().forEach(r -> record.put(r.name(), PropertyAccessorFactory.forDirectFieldAccess(object).getPropertyValue(r.name())));
        return record;
    }

    public static <T> T mapRecordToObject(GenericData.Record record, T object) {
        Assert.notNull(record, "record must not be null");
        Assert.notNull(object, "object must not be null");
        final Schema schema = ReflectData.get().getSchema(object.getClass());
        Assert.isTrue(schema.getFields().equals(record.getSchema().getFields()), "Schema fields didn't match");
        record.getSchema().getFields().forEach(d -> PropertyAccessorFactory.forDirectFieldAccess(object).setPropertyValue(d.name(), record.get(d.name()) == null ? record.get(d.name()) : record.get(d.name()).toString()));
        return object;
    }

}

使用此映射器，您可以生成一个 GenericData.Record，该数据记录可以轻松序列化为 avro。当您反序列化 Avro ByteArray 时，您可以使用它从反序列化记录重建 POJO：

序列化

byte[] serialized = avroSerializer.serialize("topic", GenericRecordMapper.mapObjectToRecord(yourPojo));

反序列化

GenericData.Record deserialized = (GenericData.Record) avroDeserializer.deserialize("topic", serialized);

YourPojo yourPojo = GenericRecordMapper.mapRecordToObject(deserialized, new YourPojo());

答案 2

这是转换的通用方法

public static <V> byte[] toBytesGeneric(final V v, final Class<V> cls) {
        final ByteArrayOutputStream bout = new ByteArrayOutputStream();
        final Schema schema = ReflectData.get().getSchema(cls);
        final DatumWriter<V> writer = new ReflectDatumWriter<V>(schema);
        final BinaryEncoder binEncoder = EncoderFactory.get().binaryEncoder(bout, null);
        try {
            writer.write(v, binEncoder);
            binEncoder.flush();
        } catch (final Exception e) {
            throw new RuntimeException(e);
        }


        return bout.toByteArray();
    }

public static void main(String[] args) {
    PojoClass pojoObject = new PojoClass();
    toBytesGeneric(pojoObject, PojoClass.class);
}