Java读写avro例子

一、avro是一个数据序列化框架，可以高效得进行序列化和反序列化，支持C, C++, C#, Java, PHP, Python, 和Ruby语言。现在使用Java来读写。

二、环境搭建

　　1、下载avro-1.7.7.jar and avro-tools-1.7.7.jar两个jar包，放到指定文件目录。下载地址 http://www.trieuvan.com/apache/avro/avro-1.7.7/java/

　　　　我放到了D:\soft\avro 文件夹，在改目录下新建java文件夹，用来存放生成的Java代码

　  2、该目录下新建user.avsc文件，内容是：　　

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

 ]
}   

　　3、打开cmd，进入到该目录,执行命令生成User类,注意命令后面有个"."，表示生成的代码放在本目录下。

java -jar avro-tools-1.7.7.jar compile schema user.avsc java .

　　

　　在该文件夹下的Java文件下的../example/avro/目录下就会生成User.java文件。

　　4.使用eclipse新建maven项目，在pom.xml加入avro的依赖。　　

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

三、生成的User.java文件的内容如下。

　　把生成的User.java类复制到工程中，注意这个User.java里面生成的User类及其内部类的包名默认是user.avsc文件中的namespace的值，

　　在本例中也就是example.avro。需要全部替换为自己的包名。

　　最简单的方法就是把User.java中的example.avro全部替换为自己的包名。

/**
 * Autogenerated by Avro
 *
 * DO NOT EDIT DIRECTLY
 */
package example.avro;
@SuppressWarnings("all")
@org.apache.avro.specific.AvroGenerated
public class User extends org.apache.avro.specific.SpecificRecordBase implements org.apache.avro.specific.SpecificRecord {
  public static final org.apache.avro.Schema SCHEMA$ = new org.apache.avro.Schema.Parser().parse("{\"type\":\"record\",\"name\":\"User\",\"namespace\":\"example.avro\",\"fields\":[{\"name\":\"name\",\"type\":\"string\"},{\"name\":\"favorite_number\",\"type\":[\"int\",\"null\"]},{\"name\":\"favorite_color\",\"type\":[\"string\",\"null\"]}]}");
  public static org.apache.avro.Schema getClassSchema() { return SCHEMA$; }
  @Deprecated public java.lang.CharSequence name;
  @Deprecated public java.lang.Integer favorite_number;
  @Deprecated public java.lang.CharSequence favorite_color;

  /**
   * Default constructor.  Note that this does not initialize fields
   * to their default values from the schema.  If that is desired then
   * one should use <code>newBuilder()</code>.
   */
  public User() {}

  /**
   * All-args constructor.
   */
  public User(java.lang.CharSequence name, java.lang.Integer favorite_number, java.lang.CharSequence favorite_color) {
    this.name = name;
    this.favorite_number = favorite_number;
    this.favorite_color = favorite_color;
  }

  public org.apache.avro.Schema getSchema() { return SCHEMA$; }
  // Used by DatumWriter.  Applications should not call.
  public java.lang.Object get(int field$) {
    switch (field$) {
    case 0: return name;
    case 1: return favorite_number;
    case 2: return favorite_color;
    default: throw new org.apache.avro.AvroRuntimeException("Bad index");
    }
  }
  // Used by DatumReader.  Applications should not call.
  @SuppressWarnings(value="unchecked")
  public void put(int field$, java.lang.Object value$) {
    switch (field$) {
    case 0: name = (java.lang.CharSequence)value$; break;
    case 1: favorite_number = (java.lang.Integer)value$; break;
    case 2: favorite_color = (java.lang.CharSequence)value$; break;
    default: throw new org.apache.avro.AvroRuntimeException("Bad index");
    }
  }

  /**
   * Gets the value of the 'name' field.
   */
  public java.lang.CharSequence getName() {
    return name;
  }

  /**
   * Sets the value of the 'name' field.
   * @param value the value to set.
   */
  public void setName(java.lang.CharSequence value) {
    this.name = value;
  }

  /**
   * Gets the value of the 'favorite_number' field.
   */
  public java.lang.Integer getFavoriteNumber() {
    return favorite_number;
  }

  /**
   * Sets the value of the 'favorite_number' field.
   * @param value the value to set.
   */
  public void setFavoriteNumber(java.lang.Integer value) {
    this.favorite_number = value;
  }

  /**
   * Gets the value of the 'favorite_color' field.
   */
  public java.lang.CharSequence getFavoriteColor() {
    return favorite_color;
  }

  /**
   * Sets the value of the 'favorite_color' field.
   * @param value the value to set.
   */
  public void setFavoriteColor(java.lang.CharSequence value) {
    this.favorite_color = value;
  }

  /** Creates a new User RecordBuilder */
  public static example.avro.User.Builder newBuilder() {
    return new example.avro.User.Builder();
  }

  /** Creates a new User RecordBuilder by copying an existing Builder */
  public static example.avro.User.Builder newBuilder(example.avro.User.Builder other) {
    return new example.avro.User.Builder(other);
  }

  /** Creates a new User RecordBuilder by copying an existing User instance */
  public static example.avro.User.Builder newBuilder(example.avro.User other) {
    return new example.avro.User.Builder(other);
  }

  /**
   * RecordBuilder for User instances.
   */
  public static class Builder extends org.apache.avro.specific.SpecificRecordBuilderBase<User>
    implements org.apache.avro.data.RecordBuilder<User> {

    private java.lang.CharSequence name;
    private java.lang.Integer favorite_number;
    private java.lang.CharSequence favorite_color;

    /** Creates a new Builder */
    private Builder() {
      super(example.avro.User.SCHEMA$);
    }

    /** Creates a Builder by copying an existing Builder */
    private Builder(example.avro.User.Builder other) {
      super(other);
      if (isValidValue(fields()[0], other.name)) {
        this.name = data().deepCopy(fields()[0].schema(), other.name);
        fieldSetFlags()[0] = true;
      }
      if (isValidValue(fields()[1], other.favorite_number)) {
        this.favorite_number = data().deepCopy(fields()[1].schema(), other.favorite_number);
        fieldSetFlags()[1] = true;
      }
      if (isValidValue(fields()[2], other.favorite_color)) {
        this.favorite_color = data().deepCopy(fields()[2].schema(), other.favorite_color);
        fieldSetFlags()[2] = true;
      }
    }

    /** Creates a Builder by copying an existing User instance */
    private Builder(example.avro.User other) {
            super(example.avro.User.SCHEMA$);
      if (isValidValue(fields()[0], other.name)) {
        this.name = data().deepCopy(fields()[0].schema(), other.name);
        fieldSetFlags()[0] = true;
      }
      if (isValidValue(fields()[1], other.favorite_number)) {
        this.favorite_number = data().deepCopy(fields()[1].schema(), other.favorite_number);
        fieldSetFlags()[1] = true;
      }
      if (isValidValue(fields()[2], other.favorite_color)) {
        this.favorite_color = data().deepCopy(fields()[2].schema(), other.favorite_color);
        fieldSetFlags()[2] = true;
      }
    }

    /** Gets the value of the 'name' field */
    public java.lang.CharSequence getName() {
      return name;
    }

    /** Sets the value of the 'name' field */
    public example.avro.User.Builder setName(java.lang.CharSequence value) {
      validate(fields()[0], value);
      this.name = value;
      fieldSetFlags()[0] = true;
      return this;
    }

    /** Checks whether the 'name' field has been set */
    public boolean hasName() {
      return fieldSetFlags()[0];
    }

    /** Clears the value of the 'name' field */
    public example.avro.User.Builder clearName() {
      name = null;
      fieldSetFlags()[0] = false;
      return this;
    }

    /** Gets the value of the 'favorite_number' field */
    public java.lang.Integer getFavoriteNumber() {
      return favorite_number;
    }

    /** Sets the value of the 'favorite_number' field */
    public example.avro.User.Builder setFavoriteNumber(java.lang.Integer value) {
      validate(fields()[1], value);
      this.favorite_number = value;
      fieldSetFlags()[1] = true;
      return this;
    }

    /** Checks whether the 'favorite_number' field has been set */
    public boolean hasFavoriteNumber() {
      return fieldSetFlags()[1];
    }

    /** Clears the value of the 'favorite_number' field */
    public example.avro.User.Builder clearFavoriteNumber() {
      favorite_number = null;
      fieldSetFlags()[1] = false;
      return this;
    }

    /** Gets the value of the 'favorite_color' field */
    public java.lang.CharSequence getFavoriteColor() {
      return favorite_color;
    }

    /** Sets the value of the 'favorite_color' field */
    public example.avro.User.Builder setFavoriteColor(java.lang.CharSequence value) {
      validate(fields()[2], value);
      this.favorite_color = value;
      fieldSetFlags()[2] = true;
      return this;
    }

    /** Checks whether the 'favorite_color' field has been set */
    public boolean hasFavoriteColor() {
      return fieldSetFlags()[2];
    }

    /** Clears the value of the 'favorite_color' field */
    public example.avro.User.Builder clearFavoriteColor() {
      favorite_color = null;
      fieldSetFlags()[2] = false;
      return this;
    }

    @Override
    public User build() {
      try {
        User record = new User();
        record.name = fieldSetFlags()[0] ? this.name : (java.lang.CharSequence) defaultValue(fields()[0]);
        record.favorite_number = fieldSetFlags()[1] ? this.favorite_number : (java.lang.Integer) defaultValue(fields()[1]);
        record.favorite_color = fieldSetFlags()[2] ? this.favorite_color : (java.lang.CharSequence) defaultValue(fields()[2]);
        return record;
      } catch (Exception e) {
        throw new org.apache.avro.AvroRuntimeException(e);
      }
    }
  }
}

四、用Java实现序列化，即写avro文件。

　　新建一个Java类　　

　　　　 public static void main(String[] args) throws IOException {
　　　　 // 声明并初始化User对象
　　　　 // 方式一
　　　　 User user1 = new User();
        user1.setName("zhangsan");
        user1.setFavoriteNumber(21);
        user1.setFavoriteColor(null);
        
　　　　 // 方式二 使用构造函数
        // Alternate constructor
        User user2 = new User("Ben", 7, "red");
　　　　　　
 　　　　// 方式三，使用Build方式
        // Construct via builder
        User user3 = User.newBuilder()
                     .setName("Charlie")
                     .setFavoriteColor("blue")
                     .setFavoriteNumber(null)
                     .build();
        String path = "D:\\tmp\\user.avro"; // avro文件存放目录
        DatumWriter<User> userDatumWriter = new SpecificDatumWriter<User>(User.class);
        DataFileWriter<User> dataFileWriter = new DataFileWriter<User>(userDatumWriter);
        dataFileWriter.create(user1.getSchema(),  new File(path));
　　　　　// 把生成的user对象写入到avro文件
        dataFileWriter.append(user1);
        dataFileWriter.append(user2);
        dataFileWriter.append(user3);
        dataFileWriter.close();
}

　　run一下代码，查看指定文件目录是否生成了avro文件。

五、Java读取avro文件，即实现avro反序列化。

public static void main(String[] args) throws IOException {
       DatumReader<User> reader = new SpecificDatumReader<User>(User.class);
       DataFileReader<User> dataFileReader = new DataFileReader<User>(new File("D:\\tmp\\user.avro"), reader);
       User user = null;
       while (dataFileReader.hasNext()) {
            user = dataFileReader.next();
            System.out.println(user);
       }
}

运行结果：

{"name": "zhangsan", "favorite_number": 21, "favorite_color": null}
{"name": "Ben", "favorite_number": 7, "favorite_color": "red"}
{"name": "Charlie", "favorite_number": null, "favorite_color": "blue"}

至此，例子写完。