如何将我的JSON字符串使用Avro二进制编码转换成字节数组？

Question

我有一个实际的JSON字符串，需要将其Avro二进制编码为字节数组。在阅读了Apache Avro规范后，我编写了以下代码。

我不确定这是否是正确的方法。有人能否看一下我尝试进行Avro二进制编码的方式是否正确？我使用的是Apache Avro 1.7.7版本。

public class AvroTest {

    private static final String json = "{" + "\"name\":\"Frank\"," + "\"age\":47" + "}";
    private static final String schema = "{ \"type\":\"record\", \"namespace\":\"foo\", \"name\":\"Person\", \"fields\":[ { \"name\":\"name\", \"type\":\"string\" }, { \"name\":\"age\", \"type\":\"int\" } ] }";

    public static void main(String[] args) throws IOException {
        byte[] data = jsonToAvro(json, schema);

        String jsonString = avroToJson(data, schema);
        System.out.println(jsonString);
    }

    /**
     * Convert JSON to avro binary array.
     * 
     * @param json
     * @param schemaStr
     * @return
     * @throws IOException
     */
    public static byte[] jsonToAvro(String json, String schemaStr) throws IOException {
        InputStream input = null;
        GenericDatumWriter<Object> writer = null;
        Encoder encoder = null;
        ByteArrayOutputStream output = null;
        try {
            Schema schema = new Schema.Parser().parse(schemaStr);
            DatumReader<Object> reader = new GenericDatumReader<Object>(schema);
            input = new ByteArrayInputStream(json.getBytes());
            output = new ByteArrayOutputStream();
            DataInputStream din = new DataInputStream(input);
            writer = new GenericDatumWriter<Object>(schema);
            Decoder decoder = DecoderFactory.get().jsonDecoder(schema, din);
            encoder = EncoderFactory.get().binaryEncoder(output, null);
            Object datum;
            while (true) {
                try {
                    datum = reader.read(null, decoder);
                } catch (EOFException eofe) {
                    break;
                }
                writer.write(datum, encoder);
            }
            encoder.flush();
            return output.toByteArray();
        } finally {
            try {
                input.close();
            } catch (Exception e) {
            }
        }
    }

    /**
     * Convert Avro binary byte array back to JSON String.
     * 
     * @param avro
     * @param schemaStr
     * @return
     * @throws IOException
     */
    public static String avroToJson(byte[] avro, String schemaStr) throws IOException {
        boolean pretty = false;
        GenericDatumReader<Object> reader = null;
        JsonEncoder encoder = null;
        ByteArrayOutputStream output = null;
        try {
            Schema schema = new Schema.Parser().parse(schemaStr);
            reader = new GenericDatumReader<Object>(schema);
            InputStream input = new ByteArrayInputStream(avro);
            output = new ByteArrayOutputStream();
            DatumWriter<Object> writer = new GenericDatumWriter<Object>(schema);
            encoder = EncoderFactory.get().jsonEncoder(schema, output, pretty);
            Decoder decoder = DecoderFactory.get().binaryDecoder(input, null);
            Object datum;
            while (true) {
                try {
                    datum = reader.read(null, decoder);
                } catch (EOFException eofe) {
                    break;
                }
                writer.write(datum, encoder);
            }
            encoder.flush();
            output.flush();
            return new String(output.toByteArray());
        } finally {

        }
    }

}

- john

Answer 1

看起来至少是有效的。不过可以简化一下：循环是无用的，因为有多个对象会导致无效的JSON。此外，预解析模式以避免不必要的模式解析可能也是一个好主意。

以下是我的版本：

public class AvroTest {

    private static final String JSON = "{" + "\"name\":\"Frank\"," + "\"age\":47" + "}";
    private static final Schema SCHEMA = new Schema.Parser().parse("{ \"type\":\"record\", \"namespace\":\"foo\", \"name\":\"Person\", \"fields\":[ { \"name\":\"name\", \"type\":\"string\" }, { \"name\":\"age\", \"type\":\"int\" } ] }");

    public static void main(String[] args) throws IOException {
        byte[] data = jsonToAvro(JSON, SCHEMA);

        String jsonString = avroToJson(data, SCHEMA);
        System.out.println(jsonString);
    }

    /**
     * Convert JSON to avro binary array.
     * 
     * @param json
     * @param schema
     * @return
     * @throws IOException
     */
    public static byte[] jsonToAvro(String json, Schema schema) throws IOException {
        DatumReader<Object> reader = new GenericDatumReader<>(schema);
        GenericDatumWriter<Object> writer = new GenericDatumWriter<>(schema);
        ByteArrayOutputStream output = new ByteArrayOutputStream();
        Decoder decoder = DecoderFactory.get().jsonDecoder(schema, json);
        Encoder encoder = EncoderFactory.get().binaryEncoder(output, null);
        Object datum = reader.read(null, decoder);
        writer.write(datum, encoder);
        encoder.flush();
        return output.toByteArray();
    }

    /**
     * Convert Avro binary byte array back to JSON String.
     * 
     * @param avro
     * @param schema
     * @return
     * @throws IOException
     */
    public static String avroToJson(byte[] avro, Schema schema) throws IOException {
        boolean pretty = false;
        GenericDatumReader<Object> reader = new GenericDatumReader<>(schema);
        DatumWriter<Object> writer = new GenericDatumWriter<>(schema);
        ByteArrayOutputStream output = new ByteArrayOutputStream();
        JsonEncoder encoder = EncoderFactory.get().jsonEncoder(schema, output, pretty);
        Decoder decoder = DecoderFactory.get().binaryDecoder(avro, null);
        Object datum = reader.read(null, decoder);
        writer.write(datum, encoder);
        encoder.flush();
        output.flush();
        return new String(output.toByteArray(), "UTF-8");
    }
}

- Maurice Perry