1 环境准备
1）在eclipse中创建一个java工程
2）在工程的根目录创建一个lib文件夹
3）解压kafka安装包，将安装包libs目录下的jar包拷贝到工程的lib目录下，并build path。
4）启动zk和kafka集群，在kafka集群中打开一个消费者
[atguigu@hadoop102 kafka]$ bin/kafka-console-consumer.sh --zookeeper hadoop102:2181 --topic first
2 Kafka生产者Java API
2.1 创建生产者（过时的API）
package com.atguigu.kafka;
import java.util.Properties;
importkafka.javaapi.producer.Producer;
importkafka.producer.KeyedMessage;
importkafka.producer.ProducerConfig;
publicclass OldProducer {
@SuppressWarnings("deprecation")
publicstaticvoid main(String[] args) {
Properties properties = new Properties();
properties.put("metadata.broker.list", "hadoop102:9092");
properties.put("request.required.acks", "1");
properties.put("serializer.class", "kafka.serializer.StringEncoder");
Producer<Integer, String> producer = new Producer<Integer,String>(new ProducerConfig(properties));
KeyedMessage<Integer, String> message = new KeyedMessage<Integer, String>("first", "hello world");
producer.send(message );
}
} |
2.2 创建生产者（新API）
package com.atguigu.kafka;
import java.util.Properties;
import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.Producer;
import org.apache.kafka.clients.producer.ProducerRecord;
publicclass NewProducer {
publicstaticvoid main(String[] args) {
Properties props = new Properties();
// Kafka服务端的主机名和端口号
props.put("bootstrap.servers", "hadoop103:9092");
// 等待所有副本节点的应答
props.put("acks", "all");
// 消息发送最大尝试次数
props.put("retries", 0);
// 一批消息处理大小
props.put("batch.size", 16384);
// 请求延时
props.put("linger.ms", 1);
// 发送缓存区内存大小
props.put("buffer.memory", 33554432);
// key序列化
props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
// value序列化
props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");
KafkaProducer<String, String> producer = new KafkaProducer<>(props);
for (int i = 0; i < 50; i++) {
producer.send(new ProducerRecord<String, String>("first", Integer.toString(i), "hello world-" + i));
}
producer.close();
}
} |
2.3 创建生产者带回调函数（新API）
package com.atguigu.kafka;
import java.util.Properties;
import org.apache.kafka.clients.producer.Callback;
import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.ProducerRecord;
import org.apache.kafka.clients.producer.RecordMetadata;
publicclass CallBackProducer {
publicstaticvoid main(String[] args) {
Properties props = new Properties();
// Kafka服务端的主机名和端口号
props.put("bootstrap.servers", "hadoop103:9092");
// 等待所有副本节点的应答
props.put("acks", "all");
// 消息发送最大尝试次数
props.put("retries", 0);
// 一批消息处理大小
props.put("batch.size", 16384);
// 增加服务端请求延时
props.put("linger.ms", 1);
// 发送缓存区内存大小
props.put("buffer.memory", 33554432);
// key序列化
props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
// value序列化
props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");
KafkaProducer<String, String> kafkaProducer = new KafkaProducer<>(props);
for (int i = 0; i < 50; i++) {
kafkaProducer.send(new ProducerRecord<String, String>("first", "hello" + i), new Callback() {
@Override
publicvoid onCompletion(RecordMetadata metadata, Exception exception) {
if (metadata != null) {
System.out.println(metadata.partition() + "---" + metadata.offset());
}
}
});
}
kafkaProducer.close();
}
} |
2.4 自定义分区生产者
0）需求：将所有数据存储到topic的第0号分区上
1）定义一个类实现Partitioner接口，重写里面的方法（过时API）
package com.atguigu.kafka;
importjava.util.Map;
importkafka.producer.Partitioner;
publicclass CustomPartitioner implementsPartitioner {
public CustomPartitioner() {
super();
}
@Override
publicint partition(Object key, int numPartitions) {
// 控制分区
return 0;
}
} |
2）自定义分区（新API）
package com.atguigu.kafka;
import java.util.Map;
import org.apache.kafka.clients.producer.Partitioner;
import org.apache.kafka.common.Cluster;
publicclass CustomPartitioner implements Partitioner {
@Override
publicvoid configure(Map<String, ?> configs) {
}
@Override
publicint partition(String topic, Object key, byte[] keyBytes, Object value, byte[] valueBytes, Cluster cluster) {
// 控制分区
return 0;
}
@Override
publicvoid close() {
}
} |
3）在代码中调用
package com.atguigu.kafka;
import java.util.Properties;
import org.apache.kafka.clients.producer.KafkaProducer;
import org.apache.kafka.clients.producer.Producer;
import org.apache.kafka.clients.producer.ProducerRecord;
publicclass PartitionerProducer {
publicstaticvoid main(String[] args) {
Properties props = new Properties();
// Kafka服务端的主机名和端口号
props.put("bootstrap.servers", "hadoop103:9092");
// 等待所有副本节点的应答
props.put("acks", "all");
// 消息发送最大尝试次数
props.put("retries", 0);
// 一批消息处理大小
props.put("batch.size", 16384);
// 增加服务端请求延时
props.put("linger.ms", 1);
// 发送缓存区内存大小
props.put("buffer.memory", 33554432);
// key序列化
props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
// value序列化
props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");
// 自定义分区
props.put("partitioner.class", "com.atguigu.kafka.CustomPartitioner");
Producer<String, String> producer = new KafkaProducer<>(props);
producer.send(new ProducerRecord<String, String>("first", "1", "atguigu"));
producer.close();
}
} |
4）测试
（1）在hadoop102上监控/opt/module/kafka/logs/目录下first主题3个分区的log日志动态变化情况
[atguigu@hadoop102 first-0]$ tail -f 00000000000000000000.log
[atguigu@hadoop102 first-1]$ tail -f 00000000000000000000.log
[atguigu@hadoop102 first-2]$ tail -f 00000000000000000000.log
（2）发现数据都存储到指定的分区了。
3 Kafka消费者Java API
0）在控制台创建发送者
[atguigu@hadoop104 kafka]$ bin/kafka-console-producer.sh --broker-list hadoop102:9092 --topic first
>hello world
1）创建消费者（过时API）
package com.atguigu.kafka.consume;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import kafka.consumer.Consumer;
importkafka.consumer.ConsumerConfig;
importkafka.consumer.ConsumerIterator;
importkafka.consumer.KafkaStream;
importkafka.javaapi.consumer.ConsumerConnector;
publicclass CustomConsumer {
@SuppressWarnings("deprecation")
publicstaticvoid main(String[] args) {
Properties properties = new Properties();
properties.put("zookeeper.connect", "hadoop102:2181");
properties.put("group.id", "g1");
properties.put("zookeeper.session.timeout.ms", "500");
properties.put("zookeeper.sync.time.ms", "250");
properties.put("auto.commit.interval.ms", "1000");
// 创建消费者连接器
ConsumerConnector consumer = Consumer.createJavaConsumerConnector(new ConsumerConfig(properties));
HashMap<String, Integer> topicCount = new HashMap<>();
topicCount.put("first", 1);
Map<String, List<KafkaStream<byte[], byte[]>>> consumerMap = consumer.createMessageStreams(topicCount);
KafkaStream<byte[], byte[]> stream = consumerMap.get("first").get(0);
ConsumerIterator<byte[], byte[]> it = stream.iterator();
while (it.hasNext()) {
System.out.println(new String(it.next().message()));
}
}
} |
2）官方提供案例（自动维护消费情况）（新API）
package com.atguigu.kafka.consume;
import java.util.Arrays;
import java.util.Properties;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
publicclass CustomNewConsumer {
publicstaticvoid main(String[] args) {
Properties props = new Properties();
// 定义kakfa 服务的地址，不需要将所有broker指定上
props.put("bootstrap.servers", "hadoop102:9092");
// 制定consumer group
props.put("group.id", "test");
// 是否自动确认offset
props.put("enable.auto.commit", "true");
// 自动确认offset的时间间隔
props.put("auto.commit.interval.ms", "1000");
// key的序列化类
props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
// value的序列化类
props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
// 定义consumer
KafkaConsumer<String, String> consumer = new KafkaConsumer<>(props);
// 消费者订阅的topic, 可同时订阅多个
consumer.subscribe(Arrays.asList("first", "second","third"));
while (true) {
// 读取数据，读取超时时间为100ms
ConsumerRecords<String, String> records = consumer.poll(100);
for (ConsumerRecord<String, String> record : records)
System.out.printf("offset = %d, key = %s, value = %s%n", record.offset(), record.key(), record.value());
}
}
} |
