详解Spring Batch 轻量级批处理框架实践

实践内容

从 MariaDB 一张表内读 10 万条记录，经处理后写到 MongoDB 。

具体实现

1、新建 Spring Boot 应用，依赖如下：

    <!-- Web 应用 -->
    <dependency>
      <groupId>org.springframework.boot</groupId>
      <artifactId>spring-boot-starter-web</artifactId>
      <exclusions>
        <exclusion>
          <groupId>org.springframework.boot</groupId>
          <artifactId>spring-boot-starter-logging</artifactId>
        </exclusion>
        <exclusion>
          <groupId>org.springframework.boot</groupId>
          <artifactId>spring-boot-starter-tomcat</artifactId>
        </exclusion>
      </exclusions>
    </dependency>

    <!-- Web 容器 undertow -->
    <dependency>
      <groupId>org.springframework.boot</groupId>
      <artifactId>spring-boot-starter-undertow</artifactId>
    </dependency>

    <!-- 日志 Log4j2 -->
    <dependency>
      <groupId>org.springframework.boot</groupId>
      <artifactId>spring-boot-starter-log4j2</artifactId>
    </dependency>

    <!-- MongoDB -->
    <dependency>
      <groupId>org.springframework.boot</groupId>
      <artifactId>spring-boot-starter-data-mongodb</artifactId>
    </dependency>

    <!-- Brantch -->
    <dependency>
      <groupId>org.springframework.boot</groupId>
      <artifactId>spring-boot-starter-batch</artifactId>
    </dependency>

    <!-- Mariadb 驱动 -->
    <dependency>
      <groupId>org.mariadb.jdbc</groupId>
      <artifactId>mariadb-java-client</artifactId>
      <version>2.0.2</version>
    </dependency>

    <!-- Lombok 代码简化 -->
    <dependency>
      <groupId>org.projectlombok</groupId>
      <artifactId>lombok</artifactId>
      <version>1.16.14</version>
    </dependency>

2、创建一张表，并生成 10 万条数据

DROP TABLE people IF EXISTS;

CREATE TABLE people (
  id BIGINT IDENTITY NOT NULL PRIMARY KEY,
  first_name VARCHAR(20),
  last_name VARCHAR(20)
);

3、创建 Person 类

@Data
public class Person {
  private Long id;
  private String lastName;
  private String firstName;
}

4、创建一个中间处理器 PersonItemProcessor

import org.springframework.batch.item.ItemProcessor;

@Log4j2
public class PersonItemProcessor implements ItemProcessor<Person, Person> {

  @Override
  public Person process(final Person person) throws Exception {
    final String firstName = person.getFirstName().toUpperCase();
    final String lastName = person.getLastName().toUpperCase();

    final Person transformedPerson = new Person(firstName, lastName);

    log.info("Converting (" + person + ") into (" + transformedPerson + ")");

    return transformedPerson;
  }

}

5、创建 PersonMapper，用户数据库映射

public class PersonMapper implements RowMapper {

  private static final String ID_COLUMN = "id";
  private static final String NICKNAME_COLUMN = "first_name";
  private static final String EMAIL_COLUMN = "last_name";


  @Override
  public Object mapRow(ResultSet resultSet, int i) throws SQLException {
    Person user = new Person();
    person.setId(resultSet.getLong(ID_COLUMN));
    person.setNickname(resultSet.getString(NICKNAME_COLUMN));
    person.setEmail(resultSet.getString(EMAIL_COLUMN));
    return person;
  }
}

6、创建任务完成的监听 JobCompletionNotificationListener

@Log4j2
@Component
public class JobCompletionNotificationListener extends JobExecutionListenerSupport {

  @Override
  public void afterJob(JobExecution jobExecution) {
    if(jobExecution.getStatus() == BatchStatus.COMPLETED) {
      log.info("!!! JOB FINISHED! Time to verify the results");
    }
  }
}

7、构建批处理任务 BatchConfiguration

@Configuration
@EnableBatchProcessing
public class BatchConfiguration {

  @Autowired
  public JobBuilderFactory jobBuilderFactory;

  @Autowired
  public StepBuilderFactory stepBuilderFactory;

  @Autowired
  public DataSource dataSource;
  
  @Autowired
  public MongoTemplate mongoTemplate;

  @Bean
  public JdbcCursorItemReader<Person> reader(){
    JdbcCursorItemReader<Person> itemReader = new JdbcCursorItemReader<Person>();
    itemReader.setDataSource(dataSource);
    itemReader.setSql("select id, nickname, email from people");
    itemReader.setRowMapper(new PersonMapper());
    return itemReader;
  }

  @Bean
  public PersonItemProcessor processor() {
    return new PersonItemProcessor();
  }
  
  @Bean
  MongoItemWriter<Person> writer(){
    MongoItemWriter<Person> itemWriter = new MongoItemWriter<Person>();
    itemWriter.setTemplate(mongoTemplate);
    itemWriter.setCollection("branch");
    return itemWriter;
  }

  @Bean
  public Step step() {
    return stepBuilderFactory.get("step")
        .<Person, Person> chunk(10)
        .reader(reader())
        .processor(processor())
        .writer(writer())
        .build();
  }

  @Bean
  public Job importUserJob(JobCompletionNotificationListener listener) {
    return jobBuilderFactory.get("importUserJob")
        .incrementer(new RunIdIncrementer())
        .listener(listener)
        .flow(step())
        .end()
        .build();
  }

}

任务处理结果

0出错，耗时 2 分钟左右，测试机 Mac

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持小牛知识库。