【Avro一】Avro入门

本文的目的主要是总结下基于Avro Schema代码生成,然后进行序列化和反序列化开发的基本流程。需要指出的是,Avro并不要求一定得根据Schema文件生成代码,这对于动态类型语言很有用。

 

1. 添加Maven依赖

 

<?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>learn</groupId>
    <artifactId>learn.avro</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <!--avro core-->
        <dependency>
            <groupId>org.apache.avro</groupId>
            <artifactId>avro</artifactId>
            <version>1.7.7</version>
        </dependency>
    </dependencies>
    <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>
                            <!--Maven goal that helps for code generation-->
                            <goal>schema</goal>
                            <goal>protocol</goal>
                            <goal>idl-protocol</goal>
                        </goals>
                        <configuration>

                            <!--sourceDirectory: where to find the schema file, schema: .avsc; protocol: .avpr-->
                            <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>
</project>

 

2.定义schema文件(users.avsc)

放置到src/main/avro目录下

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

namespace:包名

type: record表示记录,可以理解为几个field构成的一个record,类似于Java的JavaBean

name:类名

fiels:成员变量,favorite_number最后会解释成getFavoriteNumber和setFavoriteNumber

 

3. 生成User类

在Intellij Idea的Maven视图中,learn avro->Plugins->avro->avro:schema,右击avro:schema,执行Run Maven Build,生成schema对应的Java实体类

 

/**
 * Autogenerated by Avro
 * 
 * DO NOT EDIT DIRECTLY
 */
package examples.avro.simple;
@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 User.Builder newBuilder() {
    return new User.Builder();
  }
  
  /** Creates a new User RecordBuilder by copying an existing Builder */
  public static User.Builder newBuilder(User.Builder other) {
    return new User.Builder(other);
  }
  
  /** Creates a new User RecordBuilder by copying an existing User instance */
  public static User.Builder newBuilder(User other) {
    return new 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(User.SCHEMA$);
    }
    
    /** Creates a Builder by copying an existing Builder */
    private Builder(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(User other) {
            super(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 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 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 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 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 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 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);
      }
    }
  }
}

 

4. User类序列化和反序列化测试

package examples.avro.simple;

import java.io.File;
import java.io.Serializable;

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 UserTest {
    public static void main(String[] args) throws Exception {
        
        ///无参构造函数,依赖设值注入
        User user1 = new User();
        user1.setName("Alyssa");
        user1.setFavoriteNumber(256);
        //user1没有对favorite color赋值 
        ///注意:User并没有实现Java的Serializable接口
        System.out.println(user1 instanceof Serializable);
        ///重载的构造方法
        User user2 = new User("Ben", 7, "red");

        //使用builder构建对象
        User user3 = User.newBuilder()
                .setName("Charlie")
                .setFavoriteColor("blue")
                .setFavoriteNumber(null)
                .build();

        System.out.println(user3.getName() + "," + user3.getFavoriteColor());


        ///1. 序列化包含Schema和3个User对象到c:/users.avro文件
        DatumWriter<User> userDatumWriter = new SpecificDatumWriter<User>(User.class);
        DataFileWriter<User> dataFileWriter = new DataFileWriter<User>(userDatumWriter);   
        dataFileWriter.create(user1.getSchema(), new File("c:/users.avro"));
        dataFileWriter.append(user1);
        dataFileWriter.append(user2);
        dataFileWriter.append(user3);
        dataFileWriter.close();

        ///2. 从c:/users.avro文件反序列化对象
        DatumReader<User> userDatumReader = new SpecificDatumReader<User>(User.class);
        DataFileReader<User> dataFileReader = new DataFileReader<User>(new File("c:/users.avro"), 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);  ///输出JSON格式的数据,Avro对User类的toString进行了改写
        }
    }
}

 

 

 

 

 

 

 

 

 

你可能感兴趣的:(入门)