读数据——从数据库中批量读取数据

下面以mysql为例，用spring batch批量从mysql数据库表users表中读取数据。
uers表目前数据以下：

下面用spring batch批量读取该表，首先配置数据源

#配置step执行多少次commit一次
spring.batch.chunk.size=4
#数据源配置
spring.datasource.url=jdbc:mysql://localhost:3306/lzj_database
spring.datasource.driver-class-name=com.mysql.jdbc.Driver
spring.datasource.username=root
spring.datasource.password=lzjlzj

配置读取user表的job做业

import java.sql.ResultSet;
import java.sql.SQLException;
import java.util.HashMap;
import java.util.Map;
import javax.sql.DataSource;
import org.springframework.batch.core.Job;
import org.springframework.batch.core.Step;
import org.springframework.batch.core.configuration.annotation.EnableBatchProcessing;
import org.springframework.batch.core.configuration.annotation.JobBuilderFactory;
import org.springframework.batch.core.configuration.annotation.StepBuilderFactory;
import org.springframework.batch.item.ItemReader;
import org.springframework.batch.item.database.JdbcPagingItemReader;
import org.springframework.batch.item.database.Order;
import org.springframework.batch.item.database.support.MySqlPagingQueryProvider;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import org.springframework.jdbc.core.RowMapper;

@EnableBatchProcessing
@Configuration
public class BatchConfig {

    @Autowired
    private StepBuilderFactory stepBuilderFactory;

    @Autowired
    private JobBuilderFactory jobBuilderFactory;

    @Autowired
    private DataSource dataSource;

    @Value("${spring.batch.chunk.size:3}")
    private int chunkSize;

    /*一、建立一个Job做业*/
    @Bean
    public Job databaseJob(){
        return jobBuilderFactory.get("dataBaseJob")
        .start(chunkStep())
        .build();
    }

    //2、建立一个step*/
    @Bean
    public Step chunkStep(){
        return stepBuilderFactory.get("chunkStep")
                .chunk(chunkSize)                                //每chunkSize次提交一次
                .reader(databaseItemReader())                    //读取数据库，并把库表中每列数据映射到工程中的User bean中
                .writer(list -> list.forEach(System.out::println))
                .allowStartIfComplete(true)
                .build();
    }

    /*三、读数据库配置*/
    @Bean
    public ItemReader<User> databaseItemReader(){
        JdbcPagingItemReader<User> reader = new JdbcPagingItemReader<>();
        reader.setDataSource(dataSource); //设置数据源
        reader.setFetchSize(2); //FetchSize设置为2，表示每次从数据库中,2条数据
        reader.setRowMapper(new UserRowMapper()); //把数据库表中每条数据映射到User对象中
        MySqlPagingQueryProvider queryProvider = new MySqlPagingQueryProvider();
        queryProvider.setSelectClause("*"); //设置查询的列
        queryProvider.setFromClause("from users"); //设置查询的表
        Map<String, Order> sortKeys = new HashMap<>(); //定义一个map，用于存放排序列
        sortKeys.put("id", Order.ASCENDING); //按id列升序排列
        sortKeys.put("age", Order.DESCENDING); //按age的降序排列
        queryProvider.setSortKeys(sortKeys); //设置排序列
        reader.setQueryProvider(queryProvider);
        return reader;
    }

    /*把数据库表中每条数据映射到User对象中*/
    public class UserRowMapper implements RowMapper<User>{
        @Override
        /*ResultSet数据库一条结果集；i表示当前行*/
        public User mapRow(ResultSet resultSet, int i) throws SQLException {
            return new User(resultSet.getInt("id"), resultSet.getString("name"), 
                    resultSet.getInt("age"));
        }

    }

}

运行该做业，输出内容以下：

……省略
User [id=1, name=Bob, age=15]
User [id=2, name=Tom, age=10]
User [id=3, name=lzj, age=25]
User [id=4, name=zhangsan, age=21]
User [id=5, name=zhangsan, age=21]
User [id=6, name=lisi, age=20]
User [id=7, name=lisi, age=20]
User [id=24, name=wanger, age=25]
User [id=25, name=wanger, age=25]
User [id=26, name=wanger, age=25]
User [id=27, name=wanger, age=25]
User [id=28, name=wanger, age=25]
User [id=29, name=wanger, age=25]
User [id=30, name=wanger, age=25]
User [id=31, name=wanger, age=25]
User [id=32, name=wanger, age=25]
User [id=33, name=wanger, age=25]

运行该做业后，会在数据库中生成Job的执行信息，生成表以下

查看batch_step_execution表

能够看出，共17条数据，commit了5次。由于chunkSize设置的是4，须要5次chunk才能执行完毕。