springbatch入门练习（第一篇）

先搞懂几个概念

Job Respository: 作业仓库，负责Job、Step执行过程中的状态保存

Job launcher: 作业调度器，提供执行Job的入口

Job：作业，由多个step组成，封装整个批处理操作

Step：作业步，Job的一个执行环节，由多个或者一个step组装成Job

Tasklet：step中具体执行逻辑的操作，可以重复执行，可以设置具体的同步、异步操作等

Chunk: 给定数量Item的集合，可以定义对Chunk的读操作、处理操作、写操作、提交间隔等

Item：一条数据记录

ItemReader：从数据源中读取Item

ItemProcessor：在Item写入数据源之前，对数据进行处理

ItemWriter：将Item批量写入数据源

实战部分

使用maven创建的工程

<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>core-batch</groupId>
  <artifactId>core-batch</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <packaging>jar</packaging>

  <name>core-batch</name>
  <url>http://maven.apache.org</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
  </properties>

  <dependencies>
     <dependency>
         <groupId>org.springframework.batch</groupId>
         <artifactId>spring-batch-infrastructure</artifactId>
         <version>3.0.1.RELEASE</version>
    </dependency>
    <dependency>
        <groupId>org.springframework.batch</groupId>
        <artifactId>spring-batch-core</artifactId>
        <version>3.0.1.RELEASE</version>
    </dependency>
    <dependency>
        <groupId>org.springframework.batch</groupId>
        <artifactId>spring-batch-test</artifactId>
        <version>3.0.1.RELEASE</version>
    </dependency>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>3.8.1</version>
      <scope>test</scope>
    </dependency>
  </dependencies>
</project>

定义对象领域

package com.batman.core.batch;

//定义领域对象
public class CreditBill {
    private String accountID = "";
    private String name = "";
    private double amount = 0;
    private String date;
    private String address;
    
    public String getAccountID() {
        return accountID;
    }
    public void setAccountID(String accountID) {
        this.accountID = accountID;
    }
    public String getName() {
        return name;
    }
    public void setName(String name) {
        this.name = name;
    }
    public double getAmount() {
        return amount;
    }
    public void setAmount(double amount) {
        this.amount = amount;
    }
    public String getDate() {
        return date;
    }
    public void setDate(String date) {
        this.date = date;
    }
    public String getAddress() {
        return address;
    }
    public void setAddress(String address) {
        this.address = address;
    }
    
}

定义数据处理类

package com.batman.core.batch;

import org.springframework.batch.item.ItemProcessor;

public class CreditBillProcessor implements ItemProcessor<CreditBill, CreditBill>{

    public CreditBill process(CreditBill bill) throws Exception {
        System.out.println(bill.toString());
        return bill;
    }
}

创建配置文件

<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"    
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" 
    xmlns:p="http://www.springframework.org/schema/p"    
    xmlns:tx="http://www.springframework.org/schema/tx" 
    xmlns:aop="http://www.springframework.org/schema/aop"    
    xmlns:context="http://www.springframework.org/schema/context"    
    xsi:schemaLocation="http://www.springframework.org/schema/beans  
    http://www.springframework.org/schema/beans/spring-beans-3.0.xsd  
    http://www.springframework.org/schema/tx  
    http://www.springframework.org/schema/tx/spring-tx-3.0.xsd  
    http://www.springframework.org/schema/aop  
    http://www.springframework.org/schema/aop/spring-aop-3.0.xsd  
    http://www.springframework.org/schema/context  
    http://www.springframework.org/schema/context/spring-context-2.5.xsd"    
    default-autowire="byName">
    <!-- 配置任务仓库 -->
    <bean id="jobRepository" 
        class="org.springframework.batch.core.repository.support.MapJobRepositoryFactoryBean">
    </bean>
    <!-- 配置任务调度器  用来启动Job-->
    <bean id="jobLauncher" 
        class="org.springframework.batch.core.launch.support.SimpleJobLauncher">
        <property name="jobRepository" ref="jobRepository"/>
    </bean>
    <!-- 配置事务管理器 -->
    <bean id="transactionManager" 
        class="org.springframework.batch.support.transaction.ResourcelessTransactionManager"/>
</beans>

创建job

<?xml version="1.0" encoding="UTF-8"?>
<bean:beans xmlns="http://www.springframework.org/schema/batch"    
    xmlns:bean="http://www.springframework.org/schema/beans" 
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"    
    xmlns:p="http://www.springframework.org/schema/p" 
    xmlns:tx="http://www.springframework.org/schema/tx"    
    xmlns:aop="http://www.springframework.org/schema/aop" 
    xmlns:context="http://www.springframework.org/schema/context"    
    xsi:schemaLocation="http://www.springframework.org/schema/beans 
    http://www.springframework.org/schema/beans/spring-beans-3.0.xsd  
    http://www.springframework.org/schema/tx 
    http://www.springframework.org/schema/tx/spring-tx-3.0.xsd  
    http://www.springframework.org/schema/aop 
    http://www.springframework.org/schema/aop/spring-aop-3.0.xsd  
    http://www.springframework.org/schema/context 
    http://www.springframework.org/schema/context/spring-context-2.5.xsd
    http://www.springframework.org/schema/batch 
    http://www.springframework.org/schema/batch/spring-batch-2.2.xsd">
    <bean:import resource="classpath:job-context.xml"/>
    <!-- 定义一个批处理作业 -->
    <job id="billJob">
        <!-- 定义个billStep的作业步，有一个面向批的操作组成 -->
        <step id="billStep">
            <!-- 定义批处理操作采用定义的事务管理器，负责批处理中事务管理操作 -->
            <tasklet transaction-manager="transactionManager">
                <!-- 定义了面向批的操作，定义了读操作csvItemReader,处理操作 creditBillProcessor，写操作csvItemWriter
                 commit-interval表示提交间隔的大小，即每处理两条数据进行一次写操作-->
                <chunk reader="csvItemReader" writer="csvItemWriter" 
                    processor="creditBillProcessor" commit-interval="2">
                </chunk>
            </tasklet>
        </step>
    </job>
    <!-- 读取信用卡账单文件,CSV格式 -->
    <bean:bean id="csvItemReader"
        class="org.springframework.batch.item.file.FlatFileItemReader" 
        scope="step">
        <!-- 读取文件资源 -->
        <bean:property name="resource" value="classpath:credit-card-bill-201303.csv"/>
        <!-- 通过lineMapper可以把文本中的一行转换成领域对象CreditBill -->
        <bean:property name="lineMapper">
            <bean:bean 
                class="org.springframework.batch.item.file.mapping.DefaultLineMapper">
                <!-- 定义文本中的分割符号 -->
                <bean:property name="lineTokenizer" ref="lineTokenizer"/>
                <!-- 根据lineTokenizer中定义的names属性映射到creditBill中，最终组装成信用卡账单对象 -->
                <bean:property name="fieldSetMapper">
                    <bean:bean class="org.springframework.batch.item.file.mapping.BeanWrapperFieldSetMapper">
                        <bean:property name="prototypeBeanName" value="creditBill">
                        </bean:property>
                    </bean:bean>
                </bean:property>
            </bean:bean>
        </bean:property>
    </bean:bean>
    <!-- lineTokenizer -->
    <bean:bean id="lineTokenizer" 
        class="org.springframework.batch.item.file.transform.DelimitedLineTokenizer">
        <bean:property name="delimiter" value=","/>
        <bean:property name="names">
            <bean:list>
                <bean:value>accountID</bean:value>
                <bean:value>name</bean:value>
                <bean:value>amount</bean:value>
                <bean:value>date</bean:value>
                <bean:value>address</bean:value>
            </bean:list>
        </bean:property>
    </bean:bean>
    
    <!-- 写信用卡账单文件，CSV格式 -->
    <bean:bean id="csvItemWriter" 
        class="org.springframework.batch.item.file.FlatFileItemWriter" 
        scope="step">
        <bean:property name="resource" value="file:target/outputFile.csv"/>
        <bean:property name="lineAggregator">
            <bean:bean 
                class="org.springframework.batch.item.file.transform.DelimitedLineAggregator">
                <bean:property name="delimiter" value=","></bean:property>
                <bean:property name="fieldExtractor">
                    <bean:bean 
                        class="org.springframework.batch.item.file.transform.BeanWrapperFieldExtractor">
                        <bean:property name="names" 
                             value="accountID,name,amount,date,address">
                        </bean:property>
                    </bean:bean>
                </bean:property>
            </bean:bean>
        </bean:property>
    </bean:bean>
    
    <bean:bean id="creditBill" scope="prototype"
        class="com.batman.core.batch.CreditBill">
    </bean:bean>
    <!-- 负责处理读入的数据 -->
    <bean:bean id="creditBillProcessor" scope="step"
        class="com.batman.core.batch.CreditBillProcessor">
    </bean:bean>
</bean:beans>

创建main

package com.batman.core.batch;

import org.springframework.batch.core.Job;
import org.springframework.batch.core.JobExecution;
import org.springframework.batch.core.JobParameters;
import org.springframework.batch.core.launch.JobLauncher;
import org.springframework.context.ApplicationContext;
import org.springframework.context.support.ClassPathXmlApplicationContext;

public class JobLaunch {
    public static void main(String[] args) {
        ApplicationContext context = new ClassPathXmlApplicationContext(
                "job.xml");
        //获取作业调度器
        JobLauncher launcher = (JobLauncher) context.getBean("jobLauncher");
        //获取任务对象
        Job job = (Job) context.getBean("billJob");
        try {
            //通过JobLauncher的run方法执行billJob任务
            JobExecution result = launcher.run(job, new JobParameters());
            System.out.println(result.toString());
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

}