使用Spring Batch实现大数据处理的操作方法

<dependencies>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-batch</artifactId>
    </dependency>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-data-jpa</artifactId>
    </dependency>
    <dependency>
        <groupId>org.hsqldb</groupId>
        <artifactId>hsqldb</artifactId>
        <scope>runtime</scope>
    </dependency>
</dependencies>

spring.datasource.url=jdbc:hsqldb:mem:testdb
spring.datasource.username=sa
spring.datasource.password=
spring.datasource.driver-class-name=org.hsqldb.jdbc.JDBCDriver
spring.batch.initialize-schema=always

package cn.juwatech.batch;
import javax.persistence.Entity;
import javax.persistence.GeneratedValue;
import javax.persistence.GenerationType;
import javax.persistence.Id;
@Entity
public class Person {
    @Id
    @GeneratedValue(strategy = GenerationType.IDENTITY)
    private Long id;
    private String firstName;
    private String lastName;
    // getters and setters
}

package cn.juwatech.batch;
import org.springframework.batch.item.file.FlatFileItemReader;
import org.springframework.batch.item.file.mapping.BeanWrapperFieldSetMapper;
import org.springframework.batch.item.file.mapping.DefaultLineMapper;
import org.springframework.batch.item.file.transform.DelimitedLineTokenizer;
import org.springframework.context.annotation.Bean;
import org.springframework.core.io.ClassPathResource;
public class BatchConfiguration {
    @Bean
    public FlatFileItemReader<Person> reader() {
        FlatFileItemReader<Person> reader = new FlatFileItemReader<>();
        reader.setResource(new ClassPathResource("sample-data.csv"));
        reader.setLineMapper(new DefaultLineMapper<Person>() {{
            setLineTokenizer(new DelimitedLineTokenizer() {{
                setNames(new String[] { "firstName", "lastName" });
            }});
            setFieldSetMapper(new BeanWrapperFieldSetMapper<Person>() {{
                setTargetType(Person.class);
            }});
        }});
        return reader;
    }
}

package cn.juwatech.batch;
import org.springframework.batch.item.ItemProcessor;
public class PersonItemProcessor implements ItemProcessor<Person, Person> {
    @Override
    public Person process(Person person) throws Exception {
        person.setLastName(person.getLastName().toUpperCase());
        return person;
    }
}

package cn.juwatech.batch;
import org.springframework.batch.item.database.BeanPropertyItemSqlParameterSourceProvider;
import org.springframework.batch.item.database.JdbcBatchItemWriter;
import org.springframework.context.annotation.Bean;
import org.springframework.jdbc.core.JdbcTemplate;
import javax.sql.DataSource;
public class BatchConfiguration {
    @Bean
    public JdbcBatchItemWriter<Person> writer(DataSource dataSource) {
        JdbcBatchItemWriter<Person> writer = new JdbcBatchItemWriter<>();
        writer.setItemSqlParameterSourceProvider(new BeanPropertyItemSqlParameterSourceProvider<>());
        writer.setSql("INSERT INTO person (first_name, last_name) VALUES (:firstName, :lastName)");
        writer.setDataSource(dataSource);
        return writer;
    }
}

package cn.juwatech.batch;
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.core.launch.support.RunIdIncrementer;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
@Configuration
@EnableBatchProcessing
public class BatchConfiguration {
    private final JobBuilderFactory jobBuilderFactory;
    private final StepBuilderFactory stepBuilderFactory;
    public BatchConfiguration(JobBuilderFactory jobBuilderFactory, StepBuilderFactory stepBuilderFactory) {
        this.jobBuilderFactory = jobBuilderFactory;
        this.stepBuilderFactory = stepBuilderFactory;
    }
    @Bean
    public Job importUserJob(JobCompletionNotificationListener listener, Step step1) {
        return jobBuilderFactory.get("importUserJob")
                .incrementer(new RunIdIncrementer())
                .listener(listener)
                .flow(step1)
                .end()
                .build();
    }
    @Bean
    public Step step1(JdbcBatchItemWriter<Person> writer) {
        return stepBuilderFactory.get("step1")
                .<Person, Person> chunk(10)
                .reader(reader())
                .processor(processor())
                .writer(writer)
                .build();
    }
    @Bean
    public PersonItemProcessor processor() {
        return new PersonItemProcessor();
    }
}

package cn.juwatech.batch;
import org.springframework.batch.core.Job;
import org.springframework.batch.core.launch.JobLauncher;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.CommandLineRunner;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
@SpringBootApplication
public class BatchApplication implements CommandLineRunner {
    @Autowired
    private JobLauncher jobLauncher;
    @Autowired
    private Job job;
    public static void main(String[] args) {
        SpringApplication.run(BatchApplication.class, args);
    }
    @Override
    public void run(String... args) throws Exception {
        jobLauncher.run(job, new JobParameters());
    }
}