package de.juplo.kafka.wordcount.splitter;
import lombok.extern.slf4j.Slf4j;
-import org.apache.kafka.clients.consumer.ConsumerConfig;
-import org.apache.kafka.common.serialization.Serdes;
import org.apache.kafka.streams.KafkaStreams;
import org.apache.kafka.streams.StreamsBuilder;
-import org.apache.kafka.streams.StreamsConfig;
-import org.apache.kafka.streams.kstream.Consumed;
import org.apache.kafka.streams.kstream.KStream;
-import org.apache.kafka.streams.kstream.Produced;
-import org.springframework.boot.SpringApplication;
-import org.springframework.context.ConfigurableApplicationContext;
-import org.springframework.kafka.support.serializer.JsonSerde;
-import org.springframework.stereotype.Component;
-import jakarta.annotation.PostConstruct;
-import jakarta.annotation.PreDestroy;
import java.util.Arrays;
import java.util.Properties;
-import java.util.concurrent.CompletableFuture;
import java.util.regex.Pattern;
-import static org.apache.kafka.streams.errors.StreamsUncaughtExceptionHandler.StreamThreadExceptionResponse.SHUTDOWN_CLIENT;
-
@Slf4j
-@Component
public class SplitterStreamProcessor
{
- final static Pattern PATTERN = Pattern.compile("\\W+");
+ final static Pattern PATTERN = Pattern.compile("[^\\p{IsAlphabetic}]+");
public final KafkaStreams streams;
public SplitterStreamProcessor(
- SplitterApplicationProperties properties,
- ConfigurableApplicationContext context)
+ String inputTopic,
+ String outputTopic,
+ Properties properties)
{
StreamsBuilder builder = new StreamsBuilder();
- JsonSerde<Recording> recordSerde =
- new JsonSerde<>(Recording.class).ignoreTypeHeaders();
- JsonSerde<Word> wordSerde =
- new JsonSerde<>(Word.class).noTypeInfo();
-
- KStream<String, Recording> source = builder.stream(
- properties.getInputTopic(),
- Consumed.with(Serdes.String(), recordSerde));
+ KStream<String, Recording> source = builder.stream(inputTopic);
source
.flatMapValues(recording -> Arrays
.stream(PATTERN.split(recording.getSentence()))
.map(word -> Word.of(recording.getUser(), word))
.toList())
- .to(properties.getOutputTopic(), Produced.with(Serdes.String(), wordSerde));
-
- Properties props = new Properties();
- props.put(StreamsConfig.APPLICATION_ID_CONFIG, properties.getApplicationId());
- props.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, properties.getBootstrapServer());
- props.put(StreamsConfig.DEFAULT_KEY_SERDE_CLASS_CONFIG, Serdes.String().getClass().getName());
- props.put(StreamsConfig.DEFAULT_VALUE_SERDE_CLASS_CONFIG, JsonSerde.class.getName());
- props.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
+ .to(outputTopic);
- streams = new KafkaStreams(builder.build(), props);
- streams.setUncaughtExceptionHandler((Throwable e) ->
- {
- log.error("Unexpected error!", e);
- CompletableFuture.runAsync(() ->
- {
- log.info("Stopping application...");
- SpringApplication.exit(context, () -> 1);
- });
- return SHUTDOWN_CLIENT;
- });
+ streams = new KafkaStreams(builder.build(), properties);
}
- @PostConstruct
public void start()
{
log.info("Starting Stream-Processor");
streams.start();
}
- @PreDestroy
public void stop()
{
log.info("Stopping Stream-Processor");