Spring Batch之读数据—读记录跨多行文件（二十九）

一、跨多行文件

Spring Batch之读数据—Flat格式文件（二十四）_人……杰的博客-CSDN博客_flat文件

二、项目实例

1.项目框架

 

2.代码实现

(1)BatchMain.java

package com.xj.demo22;

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;
/**
 * @Author : xjfu
 * @Date : 2021/10/26 20:01
 * @Description : demo22 读记录跨多行文件
 */
public class BatchMain {
    public static void main(String[] args) {

        ApplicationContext context = new ClassPathXmlApplicationContext("demo22/job/demo22-job.xml");
        //Spring Batch的作业启动器,
        JobLauncher launcher = (JobLauncher) context.getBean("jobLauncher");
        //在batch.xml中配置的一个作业
        Job job  = (Job)context.getBean("billJob");

        try{
            //开始执行这个作业,获得处理结果(要运行的job,job参数对象)
            JobExecution result = launcher.run(job, new JobParameters());
            System.out.println(result.toString());
        }catch (Exception e){
            e.printStackTrace();
        }
    }
}

(2)CreditBill.java

package com.xj.demo22;

/**
 * @Author : xjfu
 * @Date : 2021/10/26 19:27
 * @Description :
 */
public class CreditBill {
    //银行卡账户ID
    private String accountID = "";
    //持卡人姓名
    private String name = "";
    //消费金额
    private double amount = 0;
    //消费日期
    private String date = "";
    //消费场所
    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;
    }

    @Override
    public String toString() {
        return this.accountID + "," + this.name + "," + this.amount + "," + this.date + "," + this.address;
    }
}

(3)CreditBillFieldSetMapper.java

package com.xj.demo22;

import org.springframework.batch.item.file.mapping.FieldSetMapper;
import org.springframework.batch.item.file.transform.FieldSet;
import org.springframework.validation.BindException;

public class CreditBillFieldSetMapper implements FieldSetMapper<CreditBill> {

	public CreditBill mapFieldSet(FieldSet fieldSet) throws BindException {
		CreditBill result = new CreditBill();
		result.setAccountID(fieldSet.readString("accountID"));
		result.setName(fieldSet.readString("name"));
		result.setAmount(fieldSet.readDouble("amount"));
		result.setDate(fieldSet.readString("date"));
		result.setAddress(fieldSet.readString("address"));
		return result;
	}
}

(4)CreditBillProcessor.java

package com.xj.demo22;

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;
	}
}

(5)MultiLineRecordSeparatorPolicy.java

package com.xj.demo22;

import org.springframework.batch.item.file.separator.RecordSeparatorPolicy;

public class MultiLineRecordSeparatorPolicy implements RecordSeparatorPolicy {
	//定义读取的分隔符号
	private String delimiter = ",";
	//分割符总数，给定的字符串包含的分隔符个数等于此值，则认为是一条完整记录
	private int count = 0;

	//定义一条记录的完整规则
	public boolean isEndOfRecord(String line) {
		return countDelimiter(line) == count;
	}

	public String postProcess(String record) {
		return record;
	}

	public String preProcess(String record) {
		return record;
	}

	//统计给定内容包含分隔符的个数
	private int countDelimiter(String s) {
		String tmp = s;
		int index = -1;
		int count = 0;
		while ((index=tmp.indexOf(","))!=-1) {
			tmp = tmp.substring(index+1);
			count++;
		}
		return count;
	}

	public String getDelimiter() {
		return delimiter;
	}

	public int getCount() {
		return count;
	}

	public void setDelimiter(String delimiter) {
		this.delimiter = delimiter;
	}

	public void setCount(int count) {
		this.count = count;
	}
}

(6)demo22-job.xml

<?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:batch="http://www.springframework.org/schema/batch"
       xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans.xsd http://www.springframework.org/schema/batch http://www.springframework.org/schema/batch/spring-batch.xsd">

    <!--导入文件-->
    <import resource="classpath:demo22/job/demo22-jobContext.xml"/>

    <!--定义名字为billJob的作业-->
    <batch:job id="billJob">
        <!--定义名字为billStep的作业步-->
        <batch:step id="billStep">
            <batch:tasklet transaction-manager="transactionManager">
                <!--定义读、处理、写操作，规定每处理两条数据，进行一次写入操作，这样可以提高写的效率-->
                <batch:chunk reader="csvItemReader" processor="creditBillProcessor" writer="csvItemWriter" commit-interval="2">
                </batch:chunk>
            </batch:tasklet>
        </batch:step>
    </batch:job>
</beans>

(7)demo22-jobContext.xml

<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"
       xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
       xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans.xsd">

    <!--定义作业仓库 Job执行期间的元数据存储在内存中-->
    <bean id="jobRepository" class="org.springframework.batch.core.repository.support.MapJobRepositoryFactoryBean">
    </bean>

    <!--定义作业调度器，用来启动job-->
    <bean id="jobLauncher" class="org.springframework.batch.core.launch.support.SimpleJobLauncher">
        <!--注入jobRepository-->
        <property name="jobRepository" ref="jobRepository"/>
    </bean>

    <!--定义事务管理器，用于Spring Batch框架中对数据操作提供事务能力-->
    <bean id="transactionManager" class="org.springframework.batch.support.transaction.ResourcelessTransactionManager"/>

    <!--使用FlatFileItemReader读文本文件-->
    <bean id="csvItemReader" class="org.springframework.batch.item.file.FlatFileItemReader" scope="step">
        <!--指定读取的资源文件-->
        <property name="resource" value="classpath:demo22/data/demo22-inputFile.csv"/>
        <property name="recordSeparatorPolicy" ref="multiLineRecordSeparatorPolicy"/>
        <property name="lineMapper" ref="lineMapper"/>
    </bean>

    <bean id="multiLineRecordSeparatorPolicy" class="com.xj.demo22.MultiLineRecordSeparatorPolicy">
        <!--定义分隔符号-->
        <property name="delimiter" value=","/>
        <!--定义4个分隔符为一条完整记录-->
        <property name="count" value="4"/>
    </bean>

    <!--声明行转换策略-->
    <bean id="lineMapper" class="org.springframework.batch.item.file.mapping.DefaultLineMapper" >
        <property name="lineTokenizer" ref="lineTokenizer" />
        <property name="fieldSetMapper" ref="creditBillFieldSetMapper"/>
    </bean>

    <bean id="lineTokenizer" class="org.springframework.batch.item.file.transform.DelimitedLineTokenizer">
        <property name="delimiter" value=","/>
        <property name="names" value="accountID,name,amount,date,address" />
    </bean>

    <bean id="creditBillFieldSetMapper" class="com.xj.demo22.CreditBillFieldSetMapper">
    </bean>

    <!--注入实体类-->
    <bean id="creditBill" class="com.xj.demo22.CreditBill" scope="prototype"/>

    <bean id="creditBillProcessor"  class="com.xj.demo22.CreditBillProcessor" scope="step"/>

    <!--写信用卡账单文件，CSV格式-->
    <bean id="csvItemWriter" class="org.springframework.batch.item.file.FlatFileItemWriter" scope="step">
        <!--要写入的文件位置,因为[classpath:]不是一个具体的目录,这里应当用[file:](从项目根目录开始)指明输出位置-->
        <property name="resource" value="file:src/main/resources/demo22/data/demo22-outputFile.csv"/>
        <!--[lineAggregator成员]指明行聚合器,用来将对象输出到文件时构造文件中的每行的格式-->
        <property name="lineAggregator">
            <!--这里使用Spring Batch自带的DelimitedLineAggregator来作为行聚合器(可以拼接一个个属性形成行)-->
            <bean class="org.springframework.batch.item.file.transform.DelimitedLineAggregator">
                <!--使用","拼接-->
                <property name="delimiter" value=","/>
                <!--fieldExtractor成员用来将Java类的属性组成的数组拼接成行字符串-->
                <property name="fieldExtractor">
                    <bean class="org.springframework.batch.item.file.transform.BeanWrapperFieldExtractor">
                        <property name="names" value="accountID,name,amount,date,address">
                        </property>
                    </bean>
                </property>
            </bean>
        </property>
    </bean>

</beans>

(8)demo22-inputFile.csv

4047390012345678,tom,100.00,2013-2-2 12:00:08
,Lu Jia Zui road
4047390012345678,tom,320.00,2013-2-3 10:35:21
,Lu Jia Zui road
4047390012345678,tom,674.70,2013-2-6 16:26:49
,South Linyi road
4047390012345678,tom,793.20,2013-2-9 15:15:37
,Longyang road
4047390012345678,tom,360.00,2013-2-11 11:12:38
,Longyang road
4047390012345678,tom,893.00,2013-2-28 20:34:19
,Hunan road

3.运行结果