Spring Batch: Intro I -- Tasklet & Read-Process-Write example

1. Intro to Spring Batch

    1) Spring Batch is a framework for Batch Processing - Execution of a series of Jobs.

    2) Each "Job" contains many "Steps". And one "Step" can be a single "tasklet" or a "READ-PROCESS-WRITE" task.

 

2. An overview of Spring Batch

 

3. Example for Tasklet

    A sample tasklet delete all files under a specific folder.

    context.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-3.2.xsd">

	<import resource="../jobs/tasklet.xml" />

	<bean id="jobLauncher"
		class="org.springframework.batch.core.launch.support.SimpleJobLauncher">
		<property name="jobRepository" ref="jobRepository" />
	</bean>

	<bean id="jobRepository"
		class="org.springframework.batch.core.repository.support.MapJobRepositoryFactoryBean">
		<property name="transactionManager" ref="transactionManager" />
	</bean>

	<bean id="transactionManager"
		class="org.springframework.batch.support.transaction.ResourcelessTransactionManager" />
</beans>

    tasklet.xml

<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"
	xmlns:batch="http://www.springframework.org/schema/batch" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://www.springframework.org/schema/batch
		http://www.springframework.org/schema/batch/spring-batch-2.2.xsd
		http://www.springframework.org/schema/beans 
		http://www.springframework.org/schema/beans/spring-beans-3.2.xsd">

	<batch:job id="taskletExampleJob">
		<batch:step id="cleanFolder">
			<batch:tasklet ref="cleanResourceFolderTasklet" />
		</batch:step>
	</batch:job>
	<bean id="cleanResourceFolderTasklet" class="edu.xmu.spring.batch.tasklet.CleanResourceFolderTasklet">
		<property name="directory" value="file:csv/bak" />
	</bean>
</beans>

    App.java

package edu.xmu.spring.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.support.ClassPathXmlApplicationContext;

public class App {
    public static void main(String[] args) {

	ClassPathXmlApplicationContext context = new ClassPathXmlApplicationContext(
		new String[] { "spring/batch/config/context.xml" });

	JobLauncher jobLauncher = (JobLauncher) context.getBean("jobLauncher");
	Job job = (Job) context.getBean("taskletExampleJob");

	JobExecution execution;
	try {
	    execution = jobLauncher.run(job, new JobParameters());
	    System.out.println("Exit Status : " + execution.getStatus());
	} catch (Exception e) {
	    e.printStackTrace();
	}

	System.out.println("Done");

	context.close();
    }
}

    CleanResourceFolderTasklet.java

package edu.xmu.spring.batch.tasklet;

import java.io.File;

import org.springframework.batch.core.StepContribution;
import org.springframework.batch.core.UnexpectedJobExecutionException;
import org.springframework.batch.core.scope.context.ChunkContext;
import org.springframework.batch.core.step.tasklet.Tasklet;
import org.springframework.batch.repeat.RepeatStatus;
import org.springframework.beans.factory.InitializingBean;
import org.springframework.core.io.Resource;
import org.springframework.util.Assert;

public class CleanResourceFolderTasklet implements Tasklet, InitializingBean {
    private Resource directory;

    @Override
    public RepeatStatus execute(StepContribution contribution,
	    ChunkContext chunkContext) throws Exception {
	File dir = directory.getFile();
	Assert.state(dir.isDirectory());

	File[] files = dir.listFiles();
	for (int i = 0; i < files.length; i++) {
	    boolean deleted = files[i].delete();
	    if (!deleted) {
		throw new UnexpectedJobExecutionException(
			"Could not delete file " + files[i].getPath());
	    } else {
		System.out.println(files[i].getPath() + " is deleted!");
	    }
	}
	return RepeatStatus.FINISHED;
    }

    @Override
    public void afterPropertiesSet() throws Exception {
	Assert.notNull(directory, "directory must be set");
    }

    public Resource getDirectory() {
	return directory;
    }

    public void setDirectory(Resource directory) {
	this.directory = directory;
    }

}

 

4. Example for Job(Read-Process-Write)

    Read from csv and write to csv.

    context.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-3.2.xsd">

	<import resource="../jobs/job.xml" />

	<bean id="jobLauncher"
		class="org.springframework.batch.core.launch.support.SimpleJobLauncher">
		<property name="jobRepository" ref="jobRepository" />
	</bean>

	<bean id="jobRepository"
		class="org.springframework.batch.core.repository.support.MapJobRepositoryFactoryBean">
		<property name="transactionManager" ref="transactionManager" />
	</bean>

	<bean id="transactionManager"
		class="org.springframework.batch.support.transaction.ResourcelessTransactionManager" />
</beans>

    job.xml

<?xml version="1.0" encoding="UTF-8"?>
<beans xmlns="http://www.springframework.org/schema/beans"
	xmlns:batch="http://www.springframework.org/schema/batch" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://www.springframework.org/schema/batch
		http://www.springframework.org/schema/batch/spring-batch-2.2.xsd
		http://www.springframework.org/schema/beans 
		http://www.springframework.org/schema/beans/spring-beans-3.2.xsd">

	<batch:job id="readProcessWriteExampleJob">
		<batch:step id="readAndWriteStep">
			<batch:tasklet>
				<batch:chunk reader="cvsFileItemReader" processor="csvItemProcessor"
					writer="csvItemWriter" commit-interval="10" />
			</batch:tasklet>
		</batch:step>
	</batch:job>

	<bean id="cvsFileItemReader" class="org.springframework.batch.item.file.FlatFileItemReader">
		<property name="resource" value="file:csv/input/user.csv" />
		<property name="lineMapper">
			<bean class="org.springframework.batch.item.file.mapping.DefaultLineMapper">
				<property name="lineTokenizer">
					<bean
						class="org.springframework.batch.item.file.transform.DelimitedLineTokenizer">
						<property name="names" value="id, name, password" />
					</bean>
				</property>
				<property name="fieldSetMapper">
					<bean class="edu.xmu.spring.batch.UserFieldSetMapper" />
				</property>
			</bean>
		</property>
	</bean>

	<bean id="csvItemProcessor" class="edu.xmu.spring.batch.processor.UserCsvItemProcessor" />

	<bean id="csvItemWriter" class="org.springframework.batch.item.file.FlatFileItemWriter">
		<property name="resource" value="file:csv/output/user.csv" />
		<property name="lineAggregator">
			<bean
				class="org.springframework.batch.item.file.transform.DelimitedLineAggregator">
				<property name="fieldExtractor">
					<bean
						class="org.springframework.batch.item.file.transform.BeanWrapperFieldExtractor">
						<property name="names" value="id, username, password" />
					</bean>
				</property>
			</bean>
		</property>
	</bean>
</beans>

    User.java

package edu.xmu.spring.batch.model;

public class User {
    private int id;
    private String username;
    private String password;

    public int getId() {
	return id;
    }

    public void setId(int id) {
	this.id = id;
    }

    public String getUsername() {
	return username;
    }

    public void setUsername(String username) {
	this.username = username;
    }

    public String getPassword() {
	return password;
    }

    public void setPassword(String password) {
	this.password = password;
    }

}

 

    UserFieldSetMapper.java

package edu.xmu.spring.batch;

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

import edu.xmu.spring.batch.model.User;

public class UserFieldSetMapper implements FieldSetMapper<User> {

    @Override
    public User mapFieldSet(FieldSet fieldSet) throws BindException {
	User user = new User();
	user.setId(fieldSet.readInt("id"));
	user.setUsername(fieldSet.readString("name"));
	user.setPassword(fieldSet.readString("password"));
	return user;

    }
}

    UserCsvItemProcessor.java

package edu.xmu.spring.batch.processor;

import org.springframework.batch.item.ItemProcessor;

import edu.xmu.spring.batch.model.User;

public class UserCsvItemProcessor implements ItemProcessor<User, User> {

    @Override
    public User process(User item) throws Exception {
	item.setUsername(item.getUsername().replace(',', '-'));
	item.setPassword(item.getPassword().replace(',', '-'));
	return item;
    }

}

    App.java

package edu.xmu.spring.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.support.ClassPathXmlApplicationContext;

public class App {
    public static void main(String[] args) {

	ClassPathXmlApplicationContext context = new ClassPathXmlApplicationContext(
		new String[] { "spring/batch/config/context.xml" });

	JobLauncher jobLauncher = (JobLauncher) context.getBean("jobLauncher");
	Job job = (Job) context.getBean("readProcessWriteExampleJob");

	JobExecution execution;
	try {
	    execution = jobLauncher.run(job, new JobParameters());
	    System.out.println("Exit Status : " + execution.getStatus());
	} catch (Exception e) {
	    e.printStackTrace();
	}

	System.out.println("Done");

	context.close();
    }
}

    pom.xml

<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>edu.xmu.spring.batch</groupId>
	<artifactId>spring-batch</artifactId>
	<version>0.0.1-SNAPSHOT</version>

	<properties>
		<spring.version>3.2.2.RELEASE</spring.version>
		<spring.batch.version>2.2.0.RELEASE</spring.batch.version>
		<junit.version>4.11</junit.version>
	</properties>

	<dependencies>
		<!-- Spring Core -->
		<dependency>
			<groupId>org.springframework</groupId>
			<artifactId>spring-core</artifactId>
			<version>${spring.version}</version>
		</dependency>
		<!-- Spring Batch dependencies -->
		<dependency>
			<groupId>org.springframework.batch</groupId>
			<artifactId>spring-batch-core</artifactId>
			<version>${spring.batch.version}</version>
		</dependency>
		<dependency>
			<groupId>org.springframework.batch</groupId>
			<artifactId>spring-batch-infrastructure</artifactId>
			<version>${spring.batch.version}</version>
		</dependency>
	</dependencies>
</project>

 

Reference Links:

1) http://www.mkyong.com/spring-batch/