Spring Batch

@Configuration
@RequiredArgsConstructor
public class OrderExportJobConfig {

    @Bean
    public Job orderExportJob(JobRepository jobRepository, Step exportStep) {
        return new JobBuilder("orderExportJob", jobRepository)
            .incrementer(new RunIdIncrementer()) // lets the same job be re-run; see "Idempotency"
            .start(exportStep)
            .build();
    }

    @Bean
    public Step exportStep(JobRepository jobRepository,
                           PlatformTransactionManager txManager, // Boot's, injected — do NOT new one up
                           ItemReader<Order> reader,
                           ItemProcessor<Order, OrderRow> processor,
                           ItemWriter<OrderRow> writer) {
        return new StepBuilder("exportStep", jobRepository)
            .<Order, OrderRow>chunk(500, txManager) // chunk size is the commit interval — and a TX boundary
            .reader(reader)
            .processor(processor)
            .writer(writer)
            .faultTolerant()
            .skip(FlatFileParseException.class)
            .skipLimit(50)
            .build();
    }
}

JobInstanceAlreadyCompleteException: A job instance already exists and is complete

// Option A — RunIdIncrementer on the job (above) + JobLauncherApplicationRunner bumps run.id each launch.
// Option B — add a unique identifying parameter yourself when launching:
JobParameters params = new JobParametersBuilder()
    .addString("status", "COMPLETED")              // identifying — part of the instance key
    .addLong("run.id", System.currentTimeMillis()) // identifying & unique — makes each run a new instance
    .toJobParameters();

.addString("requestId", requestId, false) // non-identifying — excluded from the instance key

@Bean
@StepScope // required: late-binds jobParameters at step execution, not context startup
public JpaPagingItemReader<Order> orderReader(
        EntityManagerFactory emf,
        @Value("#{jobParameters['status']}") String status) {
    return new JpaPagingItemReaderBuilder<Order>()
        .name("orderReader")
        .entityManagerFactory(emf)
        .queryString("SELECT o FROM Order o WHERE o.status = :status ORDER BY o.id") // ORDER BY is MANDATORY
        .parameterValues(Map.of("status", OrderStatus.valueOf(status)))
        .pageSize(500) // keep pageSize == chunk size
        .build();
}

@Component
public class OrderProcessor implements ItemProcessor<Order, OrderRow> {
    @Override
    public OrderRow process(Order order) {
        if (order.getTotal().isZero()) {
            return null; // ⚠️ null = FILTER this item; it is NOT written and NOT an error
        }
        return OrderRow.from(order);
    }
}

@Override
public void write(Chunk<? extends OrderRow> chunk) { // was List<? extends T> in 4.x
    repository.saveAll(chunk.getItems());
}

@Bean
public JdbcBatchItemWriter<OrderRow> orderWriter(DataSource dataSource) {
    return new JdbcBatchItemWriterBuilder<OrderRow>()
        .dataSource(dataSource)
        .sql("INSERT INTO order_export (id, total) VALUES (:id, :total)")
        .beanMapped()
        .build();
}

spring:
  batch:
    job:
      enabled: false           # don't run jobs on app startup; we trigger them ourselves
    jdbc:
      initialize-schema: never # manage BATCH_* tables with Flyway in prod (see below)

@Component
@RequiredArgsConstructor
public class OrderExportScheduler {

    private final JobLauncher jobLauncher;
    private final Job orderExportJob;

    @Scheduled(cron = "0 0 2 * * *")
    public void runNightly() throws JobExecutionException {
        JobParameters params = new JobParametersBuilder()
            .addString("status", "COMPLETED")
            .addLong("run.id", System.currentTimeMillis())
            .toJobParameters();
        jobLauncher.run(orderExportJob, params);
    }
}