Merge branch 'eugenp:master' into master

This commit is contained in:
Ashish Gupta
2021-08-24 16:22:08 +05:30
committed by GitHub
142 changed files with 12263 additions and 2521 deletions
@@ -8,6 +8,9 @@ import java.util.PriorityQueue;
import java.util.Queue;
import java.util.stream.Collectors;
import lombok.extern.slf4j.Slf4j;
@Slf4j
public class RouteFinder<T extends GraphNode> {
private final Graph<T> graph;
private final Scorer<T> nextNodeScorer;
@@ -28,11 +31,11 @@ public class RouteFinder<T extends GraphNode> {
openSet.add(start);
while (!openSet.isEmpty()) {
System.out.println("Open Set contains: " + openSet.stream().map(RouteNode::getCurrent).collect(Collectors.toSet()));
log.debug("Open Set contains: " + openSet.stream().map(RouteNode::getCurrent).collect(Collectors.toSet()));
RouteNode<T> next = openSet.poll();
System.out.println("Looking at node: " + next);
log.debug("Looking at node: " + next);
if (next.getCurrent().equals(to)) {
System.out.println("Found our destination!");
log.debug("Found our destination!");
List<T> route = new ArrayList<>();
RouteNode<T> current = next;
@@ -41,7 +44,7 @@ public class RouteFinder<T extends GraphNode> {
current = allNodes.get(current.getPrevious());
} while (current != null);
System.out.println("Route: " + route);
log.debug("Route: " + route);
return route;
}
@@ -55,7 +58,7 @@ public class RouteFinder<T extends GraphNode> {
nextNode.setRouteScore(newScore);
nextNode.setEstimatedScore(newScore + targetScorer.computeCost(connection, to));
openSet.add(nextNode);
System.out.println("Found a better route to node: " + nextNode);
log.debug("Found a better route to node: " + nextNode);
}
});
}
@@ -1,5 +1,7 @@
package com.baeldung.algorithms.astar.underground;
import static org.assertj.core.api.Assertions.assertThat;
import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
@@ -10,9 +12,13 @@ import java.util.stream.Stream;
import com.baeldung.algorithms.astar.Graph;
import com.baeldung.algorithms.astar.RouteFinder;
import lombok.extern.slf4j.Slf4j;
import org.junit.Before;
import org.junit.Test;
@Slf4j
public class RouteFinderIntegrationTest {
private Graph<Station> underground;
@@ -637,7 +643,8 @@ public class RouteFinderIntegrationTest {
@Test
public void findRoute() {
List<Station> route = routeFinder.findRoute(underground.getNode("74"), underground.getNode("7"));
assertThat(route).size().isPositive();
System.out.println(route.stream().map(Station::getName).collect(Collectors.toList()));
route.stream().map(Station::getName).collect(Collectors.toList()).forEach(station -> log.debug(station));
}
}
+18
View File
@@ -0,0 +1,18 @@
## Apache Kafka
This module contains articles about Apache Kafka.
### Relevant articles
- [Kafka Streams vs Kafka Consumer](https://www.baeldung.com/java-kafka-streams-vs-kafka-consumer)
- [Kafka Topic Creation Using Java](https://www.baeldung.com/kafka-topic-creation)
- [Using Kafka MockConsumer](https://www.baeldung.com/kafka-mockconsumer)
- [Using Kafka MockProducer](https://www.baeldung.com/kafka-mockproducer)
- [Introduction to KafkaStreams in Java](https://www.baeldung.com/java-kafka-streams)
- [Introduction to Kafka Connectors](https://www.baeldung.com/kafka-connectors-guide)
- [Kafka Connect Example with MQTT and MongoDB](https://www.baeldung.com/kafka-connect-mqtt-mongodb)
- [Building a Data Pipeline with Flink and Kafka](https://www.baeldung.com/kafka-flink-data-pipeline)
- [Exactly Once Processing in Kafka with Java](https://www.baeldung.com/kafka-exactly-once)
##### Building the project
You can build the project from the command line using: *mvn clean install*, or in an IDE.
+180
View File
@@ -0,0 +1,180 @@
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<artifactId>apache-kafka</artifactId>
<name>apache-kafka</name>
<parent>
<groupId>com.baeldung</groupId>
<artifactId>parent-modules</artifactId>
<version>1.0.0-SNAPSHOT</version>
</parent>
<dependencies>
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka-clients</artifactId>
<version>${kafka.version}</version>
</dependency>
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka-streams</artifactId>
<version>${kafka.version}</version>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
<version>${org.slf4j.version}</version>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
<version>${org.slf4j.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-kafka-0.11_2.11</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-java_2.11</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-core</artifactId>
<version>${flink.version}</version>
<exclusions>
<exclusion>
<artifactId>commons-logging</artifactId>
<groupId>commons-logging</groupId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-java</artifactId>
<version>${flink.version}</version>
<exclusions>
<exclusion>
<artifactId>commons-logging</artifactId>
<groupId>commons-logging</groupId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-test-utils_2.11</artifactId>
<version>${flink.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<version>${guava.version}</version>
</dependency>
<dependency>
<groupId>org.awaitility</groupId>
<artifactId>awaitility</artifactId>
<version>${awaitility.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.awaitility</groupId>
<artifactId>awaitility-proxy</artifactId>
<version>${awaitility.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.datatype</groupId>
<artifactId>jackson-datatype-jsr310</artifactId>
<version>${jackson.version}</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
<version>${jackson.version}</version>
</dependency>
<dependency>
<groupId>org.assertj</groupId>
<artifactId>assertj-core</artifactId>
<version>${assertj.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.testcontainers</groupId>
<artifactId>kafka</artifactId>
<version>${testcontainers-kafka.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.testcontainers</groupId>
<artifactId>junit-jupiter</artifactId>
<version>${testcontainers-jupiter.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>${org.apache.spark.spark-core.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>${org.apache.spark.spark-core.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-graphx_2.11</artifactId>
<version>${org.apache.spark.spark-core.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>${org.apache.spark.spark-core.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-mllib_2.11</artifactId>
<version>${org.apache.spark.spark-core.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
<version>${org.apache.spark.spark-core.version}</version>
</dependency>
<dependency>
<groupId>com.datastax.spark</groupId>
<artifactId>spark-cassandra-connector_2.11</artifactId>
<version>${com.datastax.spark.spark-cassandra-connector.version}</version>
</dependency>
<dependency>
<groupId>com.datastax.spark</groupId>
<artifactId>spark-cassandra-connector-java_2.11</artifactId>
<version>${com.datastax.spark.spark-cassandra-connector-java.version}</version>
</dependency>
</dependencies>
<properties>
<assertj.version>3.6.2</assertj.version>
<kafka.version>2.8.0</kafka.version>
<testcontainers-kafka.version>1.15.3</testcontainers-kafka.version>
<testcontainers-jupiter.version>1.15.3</testcontainers-jupiter.version>
<flink.version>1.5.0</flink.version>
<awaitility.version>3.0.0</awaitility.version>
<guava.version>29.0-jre</guava.version>
<org.apache.spark.spark-core.version>2.4.8</org.apache.spark.spark-core.version>
<graphframes.version>0.8.1-spark3.0-s_2.12</graphframes.version>
<com.datastax.spark.spark-cassandra-connector.version>2.5.2</com.datastax.spark.spark-cassandra-connector.version>
<com.datastax.spark.spark-cassandra-connector-java.version>1.6.0-M1</com.datastax.spark.spark-cassandra-connector-java.version>
</properties>
</project>
@@ -0,0 +1,70 @@
package com.baeldung.flink;
import com.baeldung.flink.model.Backup;
import com.baeldung.flink.model.InputMessage;
import com.baeldung.flink.operator.BackupAggregator;
import com.baeldung.flink.operator.InputMessageTimestampAssigner;
import com.baeldung.flink.operator.WordsCapitalizer;
import org.apache.flink.streaming.api.TimeCharacteristic;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer011;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer011;
import static com.baeldung.flink.connector.Consumers.*;
import static com.baeldung.flink.connector.Producers.*;
public class FlinkDataPipeline {
public static void capitalize() throws Exception {
String inputTopic = "flink_input";
String outputTopic = "flink_output";
String consumerGroup = "baeldung";
String address = "localhost:9092";
StreamExecutionEnvironment environment = StreamExecutionEnvironment.getExecutionEnvironment();
FlinkKafkaConsumer011<String> flinkKafkaConsumer = createStringConsumerForTopic(inputTopic, address, consumerGroup);
flinkKafkaConsumer.setStartFromEarliest();
DataStream<String> stringInputStream = environment.addSource(flinkKafkaConsumer);
FlinkKafkaProducer011<String> flinkKafkaProducer = createStringProducer(outputTopic, address);
stringInputStream.map(new WordsCapitalizer())
.addSink(flinkKafkaProducer);
environment.execute();
}
public static void createBackup() throws Exception {
String inputTopic = "flink_input";
String outputTopic = "flink_output";
String consumerGroup = "baeldung";
String kafkaAddress = "localhost:9092";
StreamExecutionEnvironment environment = StreamExecutionEnvironment.getExecutionEnvironment();
environment.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);
FlinkKafkaConsumer011<InputMessage> flinkKafkaConsumer = createInputMessageConsumer(inputTopic, kafkaAddress, consumerGroup);
flinkKafkaConsumer.setStartFromEarliest();
flinkKafkaConsumer.assignTimestampsAndWatermarks(new InputMessageTimestampAssigner());
FlinkKafkaProducer011<Backup> flinkKafkaProducer = createBackupProducer(outputTopic, kafkaAddress);
DataStream<InputMessage> inputMessagesStream = environment.addSource(flinkKafkaConsumer);
inputMessagesStream.timeWindowAll(Time.hours(24))
.aggregate(new BackupAggregator())
.addSink(flinkKafkaProducer);
environment.execute();
}
public static void main(String[] args) throws Exception {
createBackup();
}
}
@@ -9,23 +9,20 @@ import java.util.Properties;
public class Consumers {
public static FlinkKafkaConsumer011<String> createStringConsumerForTopic(
String topic, String kafkaAddress, String kafkaGroup ) {
Properties props = new Properties();
props.setProperty("bootstrap.servers", kafkaAddress);
props.setProperty("group.id",kafkaGroup);
FlinkKafkaConsumer011<String> consumer =
new FlinkKafkaConsumer011<>(topic, new SimpleStringSchema(),props);
public static FlinkKafkaConsumer011<String> createStringConsumerForTopic(String topic, String kafkaAddress, String kafkaGroup) {
Properties props = new Properties();
props.setProperty("bootstrap.servers", kafkaAddress);
props.setProperty("group.id", kafkaGroup);
FlinkKafkaConsumer011<String> consumer = new FlinkKafkaConsumer011<>(topic, new SimpleStringSchema(), props);
return consumer;
}
return consumer;
}
public static FlinkKafkaConsumer011<InputMessage> createInputMessageConsumer(String topic, String kafkaAddress, String kafkaGroup ) {
public static FlinkKafkaConsumer011<InputMessage> createInputMessageConsumer(String topic, String kafkaAddress, String kafkaGroup) {
Properties properties = new Properties();
properties.setProperty("bootstrap.servers", kafkaAddress);
properties.setProperty("group.id",kafkaGroup);
FlinkKafkaConsumer011<InputMessage> consumer = new FlinkKafkaConsumer011<InputMessage>(
topic, new InputMessageDeserializationSchema(),properties);
properties.setProperty("group.id", kafkaGroup);
FlinkKafkaConsumer011<InputMessage> consumer = new FlinkKafkaConsumer011<InputMessage>(topic, new InputMessageDeserializationSchema(), properties);
return consumer;
}
@@ -18,6 +18,7 @@ public class InputMessage {
public String getSender() {
return sender;
}
public void setSender(String sender) {
this.sender = sender;
}
@@ -55,12 +56,14 @@ public class InputMessage {
@Override
public boolean equals(Object o) {
if (this == o) return true;
if (o == null || getClass() != o.getClass()) return false;
if (this == o)
return true;
if (o == null || getClass() != o.getClass())
return false;
InputMessage message1 = (InputMessage) o;
return Objects.equal(sender, message1.sender) &&
Objects.equal(recipient, message1.recipient) &&
Objects.equal(sentAt, message1.sentAt) &&
return Objects.equal(sender, message1.sender) &&
Objects.equal(recipient, message1.recipient) &&
Objects.equal(sentAt, message1.sentAt) &&
Objects.equal(message, message1.message);
}
@@ -0,0 +1,34 @@
package com.baeldung.flink.operator;
import com.baeldung.flink.model.Backup;
import com.baeldung.flink.model.InputMessage;
import org.apache.flink.api.common.functions.AggregateFunction;
import java.time.LocalDateTime;
import java.util.ArrayList;
import java.util.List;
public class BackupAggregator implements AggregateFunction<InputMessage, List<InputMessage>, Backup> {
@Override
public List<InputMessage> createAccumulator() {
return new ArrayList<>();
}
@Override
public List<InputMessage> add(InputMessage inputMessage, List<InputMessage> inputMessages) {
inputMessages.add(inputMessage);
return inputMessages;
}
@Override
public Backup getResult(List<InputMessage> inputMessages) {
Backup backup = new Backup(inputMessages, LocalDateTime.now());
return backup;
}
@Override
public List<InputMessage> merge(List<InputMessage> inputMessages, List<InputMessage> acc1) {
inputMessages.addAll(acc1);
return inputMessages;
}
}
@@ -12,7 +12,9 @@ public class InputMessageTimestampAssigner implements AssignerWithPunctuatedWate
@Override
public long extractTimestamp(InputMessage element, long previousElementTimestamp) {
ZoneId zoneId = ZoneId.systemDefault();
return element.getSentAt().atZone(zoneId).toEpochSecond() * 1000;
return element.getSentAt()
.atZone(zoneId)
.toEpochSecond() * 1000;
}
@Nullable
@@ -9,8 +9,7 @@ import org.apache.flink.api.common.serialization.SerializationSchema;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
public class BackupSerializationSchema
implements SerializationSchema<Backup> {
public class BackupSerializationSchema implements SerializationSchema<Backup> {
static ObjectMapper objectMapper = new ObjectMapper().registerModule(new JavaTimeModule());
@@ -18,7 +17,7 @@ public class BackupSerializationSchema
@Override
public byte[] serialize(Backup backupMessage) {
if(objectMapper == null) {
if (objectMapper == null) {
objectMapper.setVisibility(PropertyAccessor.FIELD, JsonAutoDetect.Visibility.ANY);
objectMapper = new ObjectMapper().registerModule(new JavaTimeModule());
}
@@ -8,12 +8,10 @@ import org.apache.flink.api.common.typeinfo.TypeInformation;
import java.io.IOException;
public class InputMessageDeserializationSchema implements
DeserializationSchema<InputMessage> {
public class InputMessageDeserializationSchema implements DeserializationSchema<InputMessage> {
static ObjectMapper objectMapper = new ObjectMapper().registerModule(new JavaTimeModule());
@Override
public InputMessage deserialize(byte[] bytes) throws IOException {
@@ -27,11 +27,11 @@ public class KafkaTopicApplication {
short replicationFactor = 1;
NewTopic newTopic = new NewTopic(topicName, partitions, replicationFactor);
CreateTopicsResult result = admin.createTopics(
Collections.singleton(newTopic));
CreateTopicsResult result = admin.createTopics(Collections.singleton(newTopic));
// get the async result for the new topic creation
KafkaFuture<Void> future = result.values().get(topicName);
KafkaFuture<Void> future = result.values()
.get(topicName);
// call get() to block until topic creation has completed or failed
future.get();
@@ -47,15 +47,13 @@ public class KafkaTopicApplication {
short replicationFactor = 1;
NewTopic newTopic = new NewTopic(topicName, partitions, replicationFactor);
CreateTopicsOptions topicOptions = new CreateTopicsOptions()
.validateOnly(true)
.retryOnQuotaViolation(true);
CreateTopicsOptions topicOptions = new CreateTopicsOptions().validateOnly(true)
.retryOnQuotaViolation(true);
CreateTopicsResult result = admin.createTopics(
Collections.singleton(newTopic), topicOptions
);
CreateTopicsResult result = admin.createTopics(Collections.singleton(newTopic), topicOptions);
KafkaFuture<Void> future = result.values().get(topicName);
KafkaFuture<Void> future = result.values()
.get(topicName);
future.get();
}
}
@@ -72,14 +70,12 @@ public class KafkaTopicApplication {
Map<String, String> newTopicConfig = new HashMap<>();
newTopicConfig.put(TopicConfig.CLEANUP_POLICY_CONFIG, TopicConfig.CLEANUP_POLICY_COMPACT);
newTopicConfig.put(TopicConfig.COMPRESSION_TYPE_CONFIG, "lz4");
NewTopic newTopic = new NewTopic(topicName, partitions, replicationFactor)
.configs(newTopicConfig);
NewTopic newTopic = new NewTopic(topicName, partitions, replicationFactor).configs(newTopicConfig);
CreateTopicsResult result = admin.createTopics(
Collections.singleton(newTopic)
);
CreateTopicsResult result = admin.createTopics(Collections.singleton(newTopic));
KafkaFuture<Void> future = result.values().get(topicName);
KafkaFuture<Void> future = result.values()
.get(topicName);
future.get();
}
}
@@ -19,9 +19,7 @@ public class CountryPopulationConsumer {
private java.util.function.Consumer<Throwable> exceptionConsumer;
private java.util.function.Consumer<CountryPopulation> countryPopulationConsumer;
public CountryPopulationConsumer(
Consumer<String, Integer> consumer, java.util.function.Consumer<Throwable> exceptionConsumer,
java.util.function.Consumer<CountryPopulation> countryPopulationConsumer) {
public CountryPopulationConsumer(Consumer<String, Integer> consumer, java.util.function.Consumer<Throwable> exceptionConsumer, java.util.function.Consumer<CountryPopulation> countryPopulationConsumer) {
this.consumer = consumer;
this.exceptionConsumer = exceptionConsumer;
this.countryPopulationConsumer = countryPopulationConsumer;
@@ -1,4 +1,4 @@
package com.baeldung.kafka;
package com.baeldung.kafka.exactlyonce;
import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.ProducerRecord;
@@ -24,16 +24,16 @@ public class TransactionalMessageProducer {
producer.initTransactions();
try{
try {
producer.beginTransaction();
Stream.of(DATA_MESSAGE_1, DATA_MESSAGE_2).forEach(s -> producer.send(
new ProducerRecord<String, String>("input", null, s)));
Stream.of(DATA_MESSAGE_1, DATA_MESSAGE_2)
.forEach(s -> producer.send(new ProducerRecord<String, String>("input", null, s)));
producer.commitTransaction();
}catch (KafkaException e){
} catch (KafkaException e) {
producer.abortTransaction();
@@ -1,4 +1,4 @@
package com.baeldung.kafka;
package com.baeldung.kafka.exactlyonce;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
@@ -43,10 +43,11 @@ public class TransactionalWordCount {
ConsumerRecords<String, String> records = consumer.poll(ofSeconds(60));
Map<String, Integer> wordCountMap = records.records(new TopicPartition(INPUT_TOPIC, 0))
.stream()
.flatMap(record -> Stream.of(record.value().split(" ")))
.map(word -> Tuple.of(word, 1))
.collect(Collectors.toMap(tuple -> tuple.getKey(), t1 -> t1.getValue(), (v1, v2) -> v1 + v2));
.stream()
.flatMap(record -> Stream.of(record.value()
.split(" ")))
.map(word -> Tuple.of(word, 1))
.collect(Collectors.toMap(tuple -> tuple.getKey(), t1 -> t1.getValue(), (v1, v2) -> v1 + v2));
producer.beginTransaction();
@@ -56,7 +57,8 @@ public class TransactionalWordCount {
for (TopicPartition partition : records.partitions()) {
List<ConsumerRecord<String, String>> partitionedRecords = records.records(partition);
long offset = partitionedRecords.get(partitionedRecords.size() - 1).offset();
long offset = partitionedRecords.get(partitionedRecords.size() - 1)
.offset();
offsetsToCommit.put(partition, new OffsetAndMetadata(offset + 1));
}
@@ -72,7 +74,6 @@ public class TransactionalWordCount {
}
}
private static KafkaConsumer<String, String> createKafkaConsumer() {
@@ -1,4 +1,4 @@
package com.baeldung.kafka;
package com.baeldung.kafka.exactlyonce;
public class Tuple {
@@ -10,8 +10,8 @@ public class Tuple {
this.value = value;
}
public static Tuple of(String key, Integer value){
return new Tuple(key,value);
public static Tuple of(String key, Integer value) {
return new Tuple(key, value);
}
public String getKey() {
@@ -15,8 +15,7 @@ public class KafkaProducer {
}
public Future<RecordMetadata> send(String key, String value) {
ProducerRecord record = new ProducerRecord("topic_sports_news",
key, value);
ProducerRecord record = new ProducerRecord("topic_sports_news", key, value);
return producer.send(record);
}
@@ -36,5 +35,4 @@ public class KafkaProducer {
producer.commitTransaction();
}
}

Some files were not shown because too many files have changed in this diff Show More