【Apache Avro】quick start快速开始，示例教程

本教程涉及Avro的安装和示例代码的运行，avro与thrift有许多相似之处，可以参考alidata的这篇文章：http://www.alidata.org/archives/1307

本教程是参照Apache avro官网的quick start写的：http://avro.apache.org/docs/current/gettingstartedjava.html

1.下载avro-tools-1.7.5.jar

http://mirrors.cnnic.cn/apache/avro/avro-1.7.5/java/

2.使用avro-tools生成java代码

编写avro示例user.avrc

{"namespace": "example.avro",
 "type": "record",
 "name": "User",
 "fields": [
     {"name": "name", "type": "string"},
     {"name": "favorite_number",  "type": ["int", "null"]},
     {"name": "favorite_color", "type": ["string", "null"]}
 ]
}

在user.avrc所在的目录下执行：

java -jar /path/to/avro-tools-1.7.5.jar compile schema user.avsc .

将在该目录下生成./example/avro/User.java程序

3.maven构建eclipse工程编写java程序序列化和反序列化avro文件

maven的pom.xml文件如下：

<?xml version="1.0" encoding="UTF-8"?>

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">

  <modelVersion>4.0.0</modelVersion>

  <groupId>com.iflytek.cpcloud</groupId>
  <artifactId>avro-test</artifactId>
  <version>0.1.0-SNAPSHOT</version>

  <dependencies>
    <dependency>
      <groupId>log4j</groupId>
      <artifactId>log4j</artifactId>
      <version>1.2.17</version>
    </dependency>
    <dependency>
      <groupId>commons-logging</groupId>
      <artifactId>commons-logging</artifactId>
      <version>1.1.1</version>
    </dependency>
    <dependency>
      <groupId>commons-cli</groupId>
      <artifactId>commons-cli</artifactId>
      <version>1.2</version>
    </dependency>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>4.11</version>
    </dependency>
	<dependency>
	  <groupId>org.apache.avro</groupId>
      <artifactId>avro</artifactId>
    <version>1.7.5</version>
</dependency>
  </dependencies>

  <build>
    <plugins>
      <plugin>
	<artifactId>maven-assembly-plugin</artifactId>
	<version>2.2-beta-5</version>
	<configuration>
	  <descriptorRefs>
	    <descriptorRef>jar-with-dependencies</descriptorRef>
	  </descriptorRefs>
	</configuration>
      </plugin>
      <plugin>
	<groupId>org.apache.maven.plugins</groupId>
	<artifactId>maven-compiler-plugin</artifactId>
	<version>2.3.2</version>
	<configuration>
	  <source>1.6</source>
	  <target>1.6</target>
	  <encoding>UTF-8</encoding>
	</configuration>
      </plugin>
    </plugins>
  </build>

</project>

mvn构建eclipse工程

mvn eclipse:eclipse

在example.avro包中导入生成的上面使用avro-tools生成的User.java文件

将生成的工程导入的eclipse中

编写程序序列化和反序列号avro文件Test.java

package example.avro;

import java.io.File;
import java.io.IOException;

import org.apache.avro.file.DataFileReader;
import org.apache.avro.file.DataFileWriter;
import org.apache.avro.io.DatumReader;
import org.apache.avro.io.DatumWriter;
import org.apache.avro.specific.SpecificDatumReader;
import org.apache.avro.specific.SpecificDatumWriter;

public class Test {
  
 public static void main(String[] args) throws IOException {
   code(); 
   decode();
  }
  public static void code() throws IOException{
    User user1 = new User();
    user1.setName("Alyssa");
    user1.setFavoriteNumber(256);
    // Leave favorite color null
    
    // Alternate constructor
    User user2 = new User("Ben", 7, "red");
    
    // Construct via builder
    User user3 = User.newBuilder().setName("Charlie").setFavoriteColor("blue")
        .setFavoriteNumber(null).build();
    User user4 = new User("Jimmy", 7, "yellow");
    // Serialize user1 and user2 to disk
    File file = new File("users.avro");
    DatumWriter<User> userDatumWriter = new SpecificDatumWriter<User>(
        User.class);
    DataFileWriter<User> dataFileWriter = new DataFileWriter<User>(
        userDatumWriter);
    dataFileWriter.create(user1.getSchema(), new File("users.avro"));
    dataFileWriter.append(user1);
    dataFileWriter.append(user2);
    dataFileWriter.append(user3);
    dataFileWriter.append(user4);
    dataFileWriter.close();
  }
  
  public static void decode() throws IOException{
 // Deserialize Users from disk
    DatumReader<User> userDatumReader = new SpecificDatumReader<User>(User.class);
    File file = new File("users.avro");
    DataFileReader<User> dataFileReader = new DataFileReader<User>(file , userDatumReader);
    User user = null;
    while (dataFileReader.hasNext()) {
    // Reuse user object by passing it to next(). This saves us from
    // allocating and garbage collecting many objects for files with
    // many items.
    user = dataFileReader.next(user);
    System.out.println(user);
    }
  }
}

运行结果如下：

{"name": "Alyssa", "favorite_number": 256, "favorite_color": null}
{"name": "Ben", "favorite_number": 7, "favorite_color": "red"}
{"name": "Charlie", "favorite_number": null, "favorite_color": "blue"}
{"name": "Jimmy", "favorite_number": 7, "favorite_color": "yellow"}

会在eclipse工程的根目录下生成users.avro文件