如何使用maven进行avro序列化

maven导入avro：

<dependency>
    <groupId>org.apache.avro</groupId>
    <artifactId>avro</artifactId>
    <version>1.7.7</version>
</dependency>

maven导入avro的构建插件：

<build>
    <plugins>
        <plugin>
            <groupId>org.apache.avro</groupId>
            <artifactId>avro-maven-plugin</artifactId>
            <version>1.7.7</version>
            <executions>
                <execution>
                    <phase>generate-sources</phase>
                    <goals>
                        <goal>schema</goal>
                        <goal>protocol</goal>
                        <goal>idl-protocol</goal>
                    </goals>
                    <configuration>
                        <!-- 源目录，用于存放 avro的schema文件及protocol文件 ,如果没加如下配置，那么默认从/src/main/avro下面找avsc文件，生成的java文件放到target/generated-sources/avro下面-->
                        <sourceDirectory> ${project.basedir}/src/main/avro/</sourceDirectory>
                        <outputDirectory> ${project.basedir}/src/main/java/</outputDirectory>
                    </configuration>
                </execution>
            </executions>
        </plugin>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-compiler-plugin</artifactId>
            <configuration>
                <source>1.7</source>
                <target>1.7</target>
            </configuration>
        </plugin>
    </plugins>
</build>

在${project.basedir}/src/main/avro/ 下导入json文件，就是所谓的数据schema

 

{
   "namespace":"user_machine_learning",
   "type":"record",
   "name":"product",
   "fields":[
          {"name":"product_id","type":"string","default":"null"},
          {"name":"company_name","type":"string","default":"null"},
          {"name":"product_info","type":"string","default":"null"},
          {"name":"direction","type":"string","default":"null"}   
    ]
}

maven和schema构建好之后需要进行install，然后就会在 ${project.basedir}/src/main/avro/ 目录下产生构建好的序列化代码，这个代码只需要使用java进行调用即可

使用java进行序列化和反序列化的操作：

public class Test_avro {
    public static void main(String[] args) throws IOException {

        //TODO 序列化操作
        product pro = product.newBuilder().build();
        pro.setProductId("1");
        pro.setCompanyName("这是一个测试");
        pro.setProductInfo("测试的详细说明");
        pro.setDirection("1");
        //将生成的数据保存到本地文件中
        File file = new File("/Users/niutao/Desktop/avro_test/user.avro");
        DatumWriter<product> productDatumWriter = new SpecificDatumWriter<product>(product.class);
        DataFileWriter<product> dataFileWriter = new DataFileWriter<product>(productDatumWriter);
        dataFileWriter.create(product.getClassSchema() , file);
        dataFileWriter.append(pro);
        dataFileWriter.close();

        //TODO 反序列
        DatumReader<product> productDatumReader = new SpecificDatumReader<product>(product.class);
        DataFileReader<product> productDataFileReader = new DataFileReader<product>(file , productDatumReader);
        product pro_reader = null;
        while (productDataFileReader.hasNext()){
            pro_reader = productDataFileReader.next();
            System.out.println(pro_reader);
        }
    }
}