Create basic batch ingest sample

* Read from a file, apply processing, write to database
* Hook in Spring Cloud Task
* Ensure job can be registered and executed through data flow
* Create README documenting build steps and how to register / launch the job as a task via Data Flow shell
This commit is contained in:
Chris Schaefer
2017-11-03 16:48:38 -04:00
committed by David Turanski
parent 02fc1d308a
commit b68aaf2487
16 changed files with 773 additions and 1 deletions

View File

@@ -0,0 +1,18 @@
package org.springframework.ingest;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
import org.springframework.cloud.task.configuration.EnableTask;
/**
* Main entry point for the ingest sample application.
*
* @author Chris Schaefer
*/
@EnableTask
@SpringBootApplication
public class Application {
public static void main(String[] args) throws Exception {
SpringApplication.run(Application.class, args);
}
}

View File

@@ -0,0 +1,95 @@
package org.springframework.ingest.config;
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.configuration.annotation.StepScope;
import org.springframework.batch.core.launch.support.RunIdIncrementer;
import org.springframework.batch.item.ItemProcessor;
import org.springframework.batch.item.ItemStreamReader;
import org.springframework.batch.item.ItemWriter;
import org.springframework.batch.item.database.builder.JdbcBatchItemWriterBuilder;
import org.springframework.batch.item.file.builder.FlatFileItemReaderBuilder;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import org.springframework.core.io.ResourceLoader;
import org.springframework.ingest.domain.Person;
import org.springframework.ingest.mapper.fieldset.PersonFieldSetMapper;
import org.springframework.ingest.processor.PersonItemProcessor;
/**
* Class used to configure the batch job related beans.
*
* @author Chris Schaefer
*/
@Configuration
@EnableBatchProcessing
public class BatchConfiguration {
private final DataSource dataSource;
private final ResourceLoader resourceLoader;
private final JobBuilderFactory jobBuilderFactory;
private final StepBuilderFactory stepBuilderFactory;
@Autowired
public BatchConfiguration(final DataSource dataSource, final JobBuilderFactory jobBuilderFactory,
final StepBuilderFactory stepBuilderFactory,
final ResourceLoader resourceLoader) {
this.dataSource = dataSource;
this.resourceLoader = resourceLoader;
this.jobBuilderFactory = jobBuilderFactory;
this.stepBuilderFactory = stepBuilderFactory;
}
@Bean
@StepScope
public ItemStreamReader<Person> reader(@Value("#{jobParameters['filePath']}") String filePath) throws Exception {
return new FlatFileItemReaderBuilder<Person>()
.name("reader")
.resource(resourceLoader.getResource(filePath))
.delimited()
.names(new String[] {"firstName", "lastName"})
.fieldSetMapper(new PersonFieldSetMapper())
.build();
}
@Bean
public ItemProcessor<Person, Person> processor() {
return new PersonItemProcessor();
}
@Bean
public ItemWriter<Person> writer() {
return new JdbcBatchItemWriterBuilder<Person>()
.beanMapped()
.dataSource(this.dataSource)
.sql("INSERT INTO people (first_name, last_name) VALUES (:firstName, :lastName)")
.build();
}
@Bean
public Job ingestJob() throws Exception {
return jobBuilderFactory.get("ingestJob")
.incrementer(new RunIdIncrementer())
.flow(step1())
.end()
.build();
}
@Bean
public Step step1() throws Exception {
return stepBuilderFactory.get("ingest")
.<Person, Person>chunk(10)
.reader(reader(null))
.processor(processor())
.writer(writer())
.build();
}
}

View File

@@ -0,0 +1,29 @@
package org.springframework.ingest.domain;
/**
* Domain object representing data about a Person.
*
* @author Chris Schaefer
*/
public class Person {
private final String firstName;
private final String lastName;
public Person(final String firstName, final String lastName) {
this.firstName = firstName;
this.lastName = lastName;
}
public String getFirstName() {
return firstName;
}
public String getLastName() {
return lastName;
}
@Override
public String toString() {
return "First name: " + firstName + " , last name: " + lastName;
}
}

View File

@@ -0,0 +1,21 @@
package org.springframework.ingest.mapper.fieldset;
import org.springframework.batch.item.file.mapping.FieldSetMapper;
import org.springframework.batch.item.file.transform.FieldSet;
import org.springframework.ingest.domain.Person;
/**
* Maps the provided FieldSet into a Person object.
*
* @author Chris Schaefer
*/
public class PersonFieldSetMapper implements FieldSetMapper<Person> {
@Override
public Person mapFieldSet(FieldSet fieldSet) {
String firstName = fieldSet.readString(0);
String lastName = fieldSet.readString(1);
return new Person(firstName, lastName);
}
}

View File

@@ -0,0 +1,29 @@
package org.springframework.ingest.processor;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.batch.item.ItemProcessor;
import org.springframework.ingest.domain.Person;
/**
* Processes the providing record, transforming the data into
* uppercase characters.
*
* @author Chris Schaefer
*/
public class PersonItemProcessor implements ItemProcessor<Person, Person> {
private static final Logger LOGGER = LoggerFactory.getLogger(PersonItemProcessor.class);
@Override
public Person process(Person person) throws Exception {
String firstName = person.getFirstName().toUpperCase();
String lastName = person.getLastName().toUpperCase();
Person processedPerson = new Person(firstName, lastName);
LOGGER.info("Processed: " + person + " into: " + processedPerson);
return processedPerson;
}
}

View File

@@ -0,0 +1 @@
spring.application.name=fileIngest

View File

@@ -0,0 +1,5 @@
Jill,Doe
Joe,Doe
Justin,Doe
Jane,Doe
John,Doe
1 Jill Doe
2 Joe Doe
3 Justin Doe
4 Jane Doe
5 John Doe

View File

@@ -0,0 +1,7 @@
DROP TABLE people IF EXISTS;
CREATE TABLE people (
person_id BIGINT IDENTITY NOT NULL PRIMARY KEY,
first_name VARCHAR(20),
last_name VARCHAR(20)
);

View File

@@ -0,0 +1,120 @@
package org.springframework.ingest.config;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;
import org.springframework.batch.core.BatchStatus;
import org.springframework.batch.core.Job;
import org.springframework.batch.core.JobExecution;
import org.springframework.batch.core.JobParameters;
import org.springframework.batch.core.JobParametersBuilder;
import org.springframework.batch.core.Step;
import org.springframework.batch.core.launch.JobLauncher;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.context.annotation.AnnotationConfigApplicationContext;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import org.springframework.core.io.ResourceLoader;
import org.springframework.jdbc.core.JdbcTemplate;
import org.springframework.jdbc.datasource.embedded.EmbeddedDatabaseFactory;
import org.springframework.jdbc.datasource.init.DatabasePopulatorUtils;
import org.springframework.jdbc.datasource.init.ResourceDatabasePopulator;
import org.springframework.util.ClassUtils;
import java.util.List;
import java.util.Map;
import javax.annotation.PostConstruct;
import javax.sql.DataSource;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertNotNull;
/**
* BatchConfiguration test cases
*
* @author Chris Schaefer
*/
public class BatchConfigurationTests {
private static AnnotationConfigApplicationContext context;
@Before
public void createContext() {
context = new AnnotationConfigApplicationContext(new Class[] {
BatchConfiguration.class, BatchConfigurationTests.DataSourceConfiguration.class });
}
@After
public void closeContext() {
context.close();
}
@Test
public void testBatchConfigurationSuccess() throws Exception {
JobExecution jobExecution = testJob("classpath:data.csv");
assertEquals("Incorrect batch status", BatchStatus.COMPLETED, jobExecution.getStatus());
assertEquals("Invalid number of step executions", 1, jobExecution.getStepExecutions().size());
}
@Test
public void testBatchConfigurationFail() throws Exception {
JobExecution jobExecution = testJob("classpath:missing-data-file.csv");
assertEquals("Incorrect batch status", BatchStatus.FAILED, jobExecution.getStatus());
}
@Test
public void testBatchDataProcessing() throws Exception {
JobExecution jobExecution = testJob("classpath:data.csv");
assertEquals("Incorrect batch status", BatchStatus.COMPLETED, jobExecution.getStatus());
assertEquals("Invalid number of step executions", 1, jobExecution.getStepExecutions().size());
JdbcTemplate jdbcTemplate = new JdbcTemplate(context.getBean(DataSource.class));
List<Map<String, Object>> peopleList = jdbcTemplate.queryForList("select first_name, last_name from people");
assertEquals("Incorrect number of results", 5, peopleList.size());
for(Map<String, Object> person : peopleList) {
assertNotNull("Received null person", person);
String firstName = (String) person.get("first_name");
assertEquals("Invalid first name: " + firstName, firstName.toUpperCase(), firstName);
String lastName = (String) person.get("last_name");
assertEquals("Invalid last name: " + lastName, lastName.toUpperCase(), lastName);
}
}
private JobExecution testJob(String filePath) throws Exception {
Job job = context.getBean(Job.class);
JobLauncher jobLauncher = context.getBean(JobLauncher.class);
JobParameters jobParameters = new JobParametersBuilder()
.addString("filePath", filePath)
.toJobParameters();
return jobLauncher.run(job, jobParameters);
}
@Configuration
public static class DataSourceConfiguration {
@Autowired
private ResourceLoader resourceLoader;
@PostConstruct
protected void initialize() {
ResourceDatabasePopulator populator = new ResourceDatabasePopulator();
populator.addScript(resourceLoader.getResource(ClassUtils.addResourcePathToPackagePath(Step.class, "schema-hsqldb.sql")));
populator.addScript(resourceLoader.getResource("classpath:schema-all.sql"));
populator.setContinueOnError(true);
DatabasePopulatorUtils.execute(populator, dataSource());
}
@Bean
public DataSource dataSource() {
return new EmbeddedDatabaseFactory().getDatabase();
}
}
}

View File

@@ -0,0 +1,36 @@
package org.springframework.ingest.mapper.fieldset;
import org.junit.Test;
import org.springframework.batch.item.file.mapping.FieldSetMapper;
import org.springframework.batch.item.file.transform.DefaultFieldSet;
import org.springframework.batch.item.file.transform.FieldSet;
import org.springframework.ingest.domain.Person;
import static org.junit.Assert.assertNotNull;
import static org.junit.Assert.assertEquals;
/**
* Test cases for PersonFieldSetMapper.
*
* @author Chris Schaefer
*/
public class PersonFieldSetMapperTests {
private static final String[] TOKENS = new String[] { "jane", "doe" };
private static final String[] NAMES = new String[] { "firstName", "lastName" };
@Test
public void testPersonFieldMapping() throws Exception {
FieldSet fieldSet = new DefaultFieldSet(TOKENS, NAMES);
FieldSetMapper<Person> fieldSetMapper = new PersonFieldSetMapper();
Person person = fieldSetMapper.mapFieldSet(fieldSet);
assertNotNull("Received null Person", person);
assertNotNull("Received null first name", person.getFirstName());
assertNotNull("Received null last name", person.getLastName());
assertEquals("Received wrong first name", TOKENS[0], person.getFirstName());
assertEquals("Received wrong last name", TOKENS[1], person.getLastName());
}
}

View File

@@ -0,0 +1,35 @@
package org.springframework.ingest.processor;
import org.junit.Test;
import org.springframework.batch.item.ItemProcessor;
import org.springframework.ingest.domain.Person;
import static org.junit.Assert.assertNotNull;
import static org.junit.Assert.assertEquals;
/**
* Test cases for PersonItemProcessor.
*
* @author Chris Schaefer
*/
public class PersonItemProcessorTests {
private static final String FIRST_NAME = "jane";
private static final String LAST_NAME = "doe";
@Test
public void testPersonProcessing() throws Exception {
Person person = new Person(FIRST_NAME, LAST_NAME);
ItemProcessor<Person, Person> personItemProcessor = new PersonItemProcessor();
Person transformedPerson = personItemProcessor.process(person);
assertNotNull("Received null Person", transformedPerson);
assertNotNull("Received null first name", transformedPerson.getFirstName());
assertNotNull("Received null last name", transformedPerson.getLastName());
assertEquals("Invalid first name processing, should be uppercase",
person.getFirstName().toUpperCase(), transformedPerson.getFirstName());
assertEquals("Invalid last name processing, should be uppercase",
person.getLastName().toUpperCase(), transformedPerson.getLastName());
}
}