Java连接Kafka

一、依赖

<?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>

    <groupId>kafkademo</groupId>
    <artifactId>kafkademo</artifactId>
    <version>1</version>
    <dependencies>
        <dependency>
            <groupId>org.apache.avro</groupId>
            <artifactId>avro</artifactId>
            <version>1.7.7</version>
        </dependency>
        <dependency>
            <groupId>com.twitter</groupId>
            <artifactId>bijection-avro_2.11</artifactId>
            <version>0.9.6</version>
        </dependency>
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.58</version>
        </dependency>
        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka-clients</artifactId>
            <version>2.2.0</version>
        </dependency>
        <dependency>
            <groupId>com.oracle</groupId>
            <artifactId>ojdbc6</artifactId>
            <version>11.2.0.3</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.8.0</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

</project>

二、Java连接Kafka

import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONObject;
import com.alibaba.fastjson.serializer.SerializerFeature;
import com.twitter.bijection.Injection;
import com.twitter.bijection.avro.GenericAvroCodecs;
import org.apache.avro.Schema;
import org.apache.avro.generic.GenericRecord;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;

import java.time.Duration;
import java.util.Collections;
import java.util.Properties;

/**
 * kafka消费者
 **/
public class KafkaConsumerDemo {
    private KafkaConsumer<String, byte[]> consumer;
    private KafkaConsumer<String, String> schemaConsumer;

    /**
     * 配置schemaTopic主题的消费者获取主题
     * @param groupId 组名
     */
    private void initSchemaConsumer(String groupId) {
        Properties p = new Properties();
        p.put("bootstrap.servers", "192.168.163.130:9092");
        p.put("group.id", groupId.toUpperCase());
        p.put("reset.beginning", true);
        p.put("auto.offset.reset", "earliest");
        p.put("enable.auto.commit", false);
        p.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        p.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        p.put("max.poll.interval.ms", 300000);
        p.put("max.poll.records", 100);
        this.schemaConsumer = new KafkaConsumer<>(p);
    }

    /**
     * 初始化表的主题的消费者，获取数据
     * @param groupId 组名
     */
    private void initConsumer(String groupId) {
        Properties p = new Properties();
        p.put("bootstrap.servers", "192.168.163.130:9092");
        p.put("group.id", groupId);
        p.put("reset.beginning", true);
        p.put("auto.offset.reset", "earliest");
        p.put("enable.auto.commit", false);
        p.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        p.put("value.deserializer", "org.apache.kafka.common.serialization.ByteArrayDeserializer");
        p.put("max.poll.interval.ms", 300000);
        p.put("max.poll.records", 100);
        this.consumer = new KafkaConsumer<>(p);
    }

    /**
     * 获取schema的arvo格式字符串
     * @param tableName 表名
     * @return schema的arvo格式字符串
     */
    private String getSchema(String tableName) {
        String topic = "schemaTopic";
        initSchemaConsumer(topic);
        String result = "";
        schemaConsumer.subscribe(Collections.singletonList(topic));
        ConsumerRecords<String, String> records = schemaConsumer.poll(Duration.ofMillis(10000));
        for (ConsumerRecord record : records) {
            if (tableName.toUpperCase().equals(record.key().toString().split("\\.")[1])) {
                result = record.value().toString();
            }
        }
        return result;
    }

    /**
     * 获取数据
     * @param tableName 表名
     * @param schemaValue schema的avro格式字符串
     */
    private void getData(String tableName, String schemaValue) {
        initConsumer(tableName.toUpperCase());
        Schema schema = new Schema.Parser().parse(schemaValue);
        consumer.subscribe(Collections.singletonList(tableName.toUpperCase()));
        ConsumerRecords<String, byte[]> records = consumer.poll(Duration.ofMillis(10000));
        for (ConsumerRecord record : records) {
            JSONObject json = parseAvroRecord(record, schema);
            System.out.println("1:" + JSON.toJSONString(json, SerializerFeature.WriteMapNullValue));
        }
    }

    /**
     * 解析二进制avro数据
     * @param record 一条记录
     * @param schema schema
     * @return 返回JSONObject
     */
    private JSONObject parseAvroRecord(ConsumerRecord<String, byte[]> record, Schema schema){
        Injection<GenericRecord, byte[]> injection = GenericAvroCodecs.toBinary(schema);
        GenericRecord record1 = injection.invert(record.value()).get();
        return JSONObject.parseObject(record1.toString());
    }
    public static void main(String[] args) {
        KafkaConsumerDemo kc = new KafkaConsumerDemo();
        String schema1 = SchemaUtils.getAvroOfTable("oracle.jdbc.OracleDriver", "jdbc:oracle:thin:@192.168.163.130:1521:syzbj2js",
                "scott", "scott", "scott", "student");
        kc.getData("student", schema1);
    }
}