java brains) Spring Batch

Getting Started | Creating a Batch Service (spring.io)

Creating a Batch Service

basically we have a "JOB" to process. 

Inside "JOB" there are 3 steps. Reader, Processor , Writer

package io.javabrains.ipldashboard.data;

import java.time.LocalDate;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import org.springframework.batch.item.ItemProcessor;

import io.javabrains.ipldashboard.model.Match;

public class MatchDataProcessor implements ItemProcessor<MatchInput, Match> {
  private static final Logger log = LoggerFactory.getLogger(MatchDataProcessor.class);

  @Override
  public Match process(final MatchInput matchInput) throws Exception {

    Match match = new Match();
    match.setId(Long.parseLong(matchInput.getId()));
    match.setCity(matchInput.getCity());

    match.setDate(LocalDate.parse(matchInput.getDate()));

    match.setPlayerOfMatch(matchInput.getPlayer_of_match());
    match.setVenue(matchInput.getVenue());

    String firstInningsTeam, secondInningsTeam;

    if ("bat".equals(matchInput.getToss_decision()))
    {
      firstInningsTeam = matchInput.getToss_winner();
      secondInningsTeam = matchInput.getToss_winner().equals(matchInput.getTeam1()) 
      ? matchInput.getTeam2() : matchInput.getTeam1();
    }
    else
    {
      secondInningsTeam = matchInput.getToss_winner();
      firstInningsTeam = matchInput.getToss_winner().equals(matchInput.getTeam1()) 
      ? matchInput.getTeam2() : matchInput.getTeam1();
    }

    match.setTeam1(firstInningsTeam);
    match.setTeam2(secondInningsTeam);

    match.setTossWinner(matchInput.getToss_winner());
    match.setTossDecision(matchInput.getToss_decision());
    match.setResult(matchInput.getResult());
    match.setResultMargin(matchInput.getResult_margin());
    match.setUmpire1(matchInput.getUmpire1());
    match.setUmpire2(matchInput.getUmpire2());

    return match;
  }
}

First we implement "process" step. here MatchInput is raw csv file from kaggle and we wanted to process it and output as "Match" java class.

 

package io.javabrains.ipldashboard.data;

import javax.sql.DataSource;
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.batch.item.database.BeanPropertyItemSqlParameterSourceProvider;
import org.springframework.batch.item.database.JdbcBatchItemWriter;
import org.springframework.batch.item.database.builder.JdbcBatchItemWriterBuilder;
import org.springframework.batch.item.file.FlatFileItemReader;
import org.springframework.batch.item.file.builder.FlatFileItemReaderBuilder;
import org.springframework.batch.item.file.mapping.BeanWrapperFieldSetMapper;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import org.springframework.core.io.ClassPathResource;
import io.javabrains.ipldashboard.model.Match;

@Configuration
@EnableBatchProcessing
public class BatchConfig {

  private final String[] FIELD_NAMES = new String[] {
    "id","city","date","player_of_match","venue","neutral_venue","team1","team2","toss_winner","toss_decision","winner","result","result_margin","eliminator","method","umpire1","umpire2"
  };

  @Autowired
  public JobBuilderFactory jobBuilderFactory;

  @Autowired
  public StepBuilderFactory stepBuilderFactory;

  @Bean
  public FlatFileItemReader<MatchInput> reader() {
    return new FlatFileItemReaderBuilder<MatchInput>().name("MatchItemReader")
        .resource(new ClassPathResource("/match-data/match-data.csv")).delimited()
        .names(FIELD_NAMES)
        .fieldSetMapper(new BeanWrapperFieldSetMapper<MatchInput>() {
          {
            setTargetType(MatchInput.class);
          }
        }).build();
  }

  @Bean
  public MatchDataProcessor processor() {
    return new MatchDataProcessor();
  }

  @Bean
  public JdbcBatchItemWriter<Match> writer(DataSource dataSource) {
    return new JdbcBatchItemWriterBuilder<Match>()
        .itemSqlParameterSourceProvider(new BeanPropertyItemSqlParameterSourceProvider<>())
        .sql("INSERT INTO match (id,city,date,player_of_match,venue,team1,team2,toss_winner,toss_decision,match_winner,result,result_margin,umpire1,umpire2) "+
        " VALUES (:id,:city,:date,:playerOfMatch,:venue,:team1,:team2,:tossWinner,:tossDecision,:matchWinner,:result,:resultMargin,:umpire1,:umpire2)")
        .dataSource(dataSource).build();
  }

  @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<Match> writer) {
  return stepBuilderFactory.get("step1")
    .<MatchInput, Match> chunk(10)
    .reader(reader())
    .processor(processor())
    .writer(writer)
    .build();
}
}

here in step1 method we read 10 rows from our csv file and process it make it to Match.class format and writer we just print it on console.