数据采集工具之Canal

本文主要介绍canal采集mysql数据的tcp、datahub(kafka)模式如何实现

1、下载canal

https://aliyun-datahub.oss-cn-hangzhou.aliyuncs.com/tools/canal.deployer-1.1.5-SNAPSHOT.tar.gz

canal的原理类似于mysql的主从复制，canal模拟的是从节点拉取主节点的binlog数据 

2、TCP模式的实现

a、canal.properties

打开看看即可，不需要调整

#################################################
#########               common argument         #############
#################################################
# tcp bind ip
canal.ip =
# register ip to zookeeper
canal.register.ip =
canal.port = 11111
canal.metrics.pull.port = 11112
# canal instance user/passwd
# canal.user = canal
# canal.passwd = E3619321C1A937C46A0D8BD1DAC39F93B27D4458

# canal admin config
#canal.admin.manager = 127.0.0.1:8089
canal.admin.port = 11110
canal.admin.user = admin
canal.admin.passwd = 4ACFE3202A5FF5CF467898FC58AAB1D615029441

canal.zkServers =
# flush data to zk
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, rocketMQ, rabbitMQ
canal.serverMode = tcp
# flush meta cursor/parse position to file
canal.file.data.dir = ${canal.conf.dir}
canal.file.flush.period = 1000
## memory store RingBuffer size, should be Math.pow(2,n)
canal.instance.memory.buffer.size = 16384
## memory store RingBuffer used memory unit size , default 1kb
canal.instance.memory.buffer.memunit = 1024 
## meory store gets mode used MEMSIZE or ITEMSIZE
canal.instance.memory.batch.mode = MEMSIZE
canal.instance.memory.rawEntry = true

## detecing config
canal.instance.detecting.enable = false
#canal.instance.detecting.sql = insert into retl.xdual values(1,now()) on duplicate key update x=now()
canal.instance.detecting.sql = select 1
canal.instance.detecting.interval.time = 3
canal.instance.detecting.retry.threshold = 3
canal.instance.detecting.heartbeatHaEnable = false

# support maximum transaction size, more than the size of the transaction will be cut into multiple transactions delivery
canal.instance.transaction.size =  1024
# mysql fallback connected to new master should fallback times
canal.instance.fallbackIntervalInSeconds = 60

# network config
canal.instance.network.receiveBufferSize = 16384
canal.instance.network.sendBufferSize = 16384
canal.instance.network.soTimeout = 30

# binlog filter config
canal.instance.filter.druid.ddl = true
canal.instance.filter.query.dcl = false
canal.instance.filter.query.dml = false
canal.instance.filter.query.ddl = false
canal.instance.filter.table.error = false
canal.instance.filter.rows = false
canal.instance.filter.transaction.entry = false

# binlog format/image check
canal.instance.binlog.format = ROW,STATEMENT,MIXED 
canal.instance.binlog.image = FULL,MINIMAL,NOBLOB

# binlog ddl isolation
canal.instance.get.ddl.isolation = false

# parallel parser config
canal.instance.parser.parallel = true
## concurrent thread number, default 60% available processors, suggest not to exceed Runtime.getRuntime().availableProcessors()
#canal.instance.parser.parallelThreadSize = 16
## disruptor ringbuffer size, must be power of 2
canal.instance.parser.parallelBufferSize = 256

# table meta tsdb info
canal.instance.tsdb.enable = true
canal.instance.tsdb.dir = ${canal.file.data.dir:../conf}/${canal.instance.destination:}
canal.instance.tsdb.url = jdbc:h2:${canal.instance.tsdb.dir}/h2;CACHE_SIZE=1000;MODE=MYSQL;
canal.instance.tsdb.dbUsername = canal
canal.instance.tsdb.dbPassword = canal
# dump snapshot interval, default 24 hour
canal.instance.tsdb.snapshot.interval = 24
# purge snapshot expire , default 360 hour(15 days)
canal.instance.tsdb.snapshot.expire = 360

#################################################
#########               destinations            #############
#################################################
canal.destinations = example  ##这里可以设置多个逗号分开
# conf root dir
canal.conf.dir = ../conf
# auto scan instance dir add/remove and start/stop instance
canal.auto.scan = true
canal.auto.scan.interval = 5

canal.instance.tsdb.spring.xml = classpath:spring/tsdb/h2-tsdb.xml
#canal.instance.tsdb.spring.xml = classpath:spring/tsdb/mysql-tsdb.xml

canal.instance.global.mode = spring
canal.instance.global.lazy = false
canal.instance.global.manager.address = ${canal.admin.manager}
#canal.instance.global.spring.xml = classpath:spring/memory-instance.xml
canal.instance.global.spring.xml = classpath:spring/file-instance.xml
#canal.instance.global.spring.xml = classpath:spring/default-instance.xml

##################################################
#########             MQ Properties      #############
##################################################
canal.mq.flat.message = true
canal.mq.database.hash = true
canal.mq.parallel.thread.size = 8
canal.mq.canal.batch.size = 50
canal.mq.canal.fetch.timeout = 100
# Set this value to "cloud", if you want open message trace feature in aliyun.
canal.mq.access.channel = local

# aliyun ak/sk , support rds/mq
canal.aliyun.accessKey =
canal.aliyun.secretKey =
canal.aliyun.uid=

##################################################
#########                    Kafka                   #############
##################################################
kafka.bootstrap.servers = 127.0.0.1:9092
kafka.acks = all
kafka.compression.type = none
kafka.batch.size = 16384
kafka.linger.ms = 1
kafka.max.request.size = 1048576
kafka.buffer.memory = 33554432
kafka.max.in.flight.requests.per.connection = 1
kafka.retries = 0

canal.mq.kafka.kerberos.enable = false
canal.mq.kafka.kerberos.krb5.file = "../conf/kerberos/krb5.conf"
canal.mq.kafka.kerberos.jaas.file = "../conf/kerberos/jaas.conf"

##################################################
#########                   RocketMQ         #############
##################################################
rocketmq.producer.group = test
rocketmq.enable.message.trace = false
rocketmq.customized.trace.topic =
rocketmq.namespace =
rocketmq.namesrv.addr = 127.0.0.1:9876
rocketmq.retry.times.when.send.failed = 0
rocketmq.vip.channel.enabled = false

##################################################
#########                   RabbitMQ         #############
##################################################
rabbitmq.host =
rabbitmq.virtual.host =
rabbitmq.exchange =
rabbitmq.username =

 b、example/instance.properties

canal.instance.master.address=192.168.140.1:3306  ###修改为自己的mysql信息

#################################################
## mysql serverId , v1.0.26+ will autoGen
# canal.instance.mysql.slaveId=0

# enable gtid use true/false
canal.instance.gtidon=false

# position info
canal.instance.master.address=192.168.140.1:3306  ###修改为自己的mysql信息
canal.instance.master.journal.name=
canal.instance.master.position=
canal.instance.master.timestamp=
canal.instance.master.gtid=

# rds oss binlog
canal.instance.rds.accesskey=
canal.instance.rds.secretkey=
canal.instance.rds.instanceId=

# table meta tsdb info
canal.instance.tsdb.enable=true
#canal.instance.tsdb.url=jdbc:mysql://127.0.0.1:3306/canal_tsdb
#canal.instance.tsdb.dbUsername=canal
#canal.instance.tsdb.dbPassword=canal

#canal.instance.standby.address =
#canal.instance.standby.journal.name =
#canal.instance.standby.position =
#canal.instance.standby.timestamp =
#canal.instance.standby.gtid=

# username/password
canal.instance.dbUsername=flink
canal.instance.dbPassword=flink
canal.instance.connectionCharset = UTF-8
# enable druid Decrypt database password
canal.instance.enableDruid=false
#canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUCAwEAAQ==

# table regex
canal.instance.filter.regex=.*\\..*
# table black regex
canal.instance.filter.black.regex=
# table field filter(format: schema1.tableName1:field1/field2,schema2.tableName2:field1/field2)
#canal.instance.filter.field=test1.t_product:id/subject/keywords,test2.t_company:id/name/contact/ch
# table field black filter(format: schema1.tableName1:field1/field2,schema2.tableName2:field1/field2)
#canal.instance.filter.black.field=test1.t_product:subject/product_image,test2.t_company:id/name/contact/ch

# mq config
canal.mq.topic=example
# dynamic topic route by schema or table regex
#canal.mq.dynamicTopic=mytest1.user,mytest2\\..*,.*\\..*
canal.mq.partition=0
# hash partition config
#canal.mq.partitionsNum=3
#canal.mq.partitionHash=test.table:id^name,.*\\..*
#################################################

启动：bin/startup.sh

jps:

到此，canal服务端配置完成 

 c、canal客户端开发

依赖

<dependency>
      <groupId>com.alibaba.otter</groupId>
      <artifactId>canal.client</artifactId>
      <version>1.1.2</version>
    </dependency>

开发代码：

package com.tbea;

import com.alibaba.fastjson.JSONObject;
import com.alibaba.otter.canal.client.CanalConnector;
import com.alibaba.otter.canal.client.CanalConnectors;
import com.alibaba.otter.canal.protocol.CanalEntry;
import com.alibaba.otter.canal.protocol.Message;
import com.google.protobuf.ByteString;
import com.google.protobuf.InvalidProtocolBufferException;

import java.net.InetSocketAddress;
import java.util.List;

public class CanalClient {
    public static void main(String[] args) throws InterruptedException, InvalidProtocolBufferException {
        //获取链接
        CanalConnector canalConnector = CanalConnectors.newSingleConnector(
                new InetSocketAddress("192.168.140.129", 11111)
                , "example"
                , "", ""
        );

        //尝试获取新数据
        while (true){
            //todo 连接
            canalConnector.connect();
            //todo 订阅数据库
            canalConnector.subscribe("flinkcdc.*");
            //todo 批量拉取数据
            Message message = canalConnector.get(100);
            //todo 获取entry
            List<CanalEntry.Entry> entries = message.getEntries();
            //todo 遍历 判断集合状态
            if (entries.size()<=0){
                System.out.println("当次未抓取到数据，休息一会~~~~~~~");
                Thread.sleep(1000);
            }else {
                //遍历解析
                for (CanalEntry.Entry entry:entries){
                    //1.获取表名
                    String tableName = entry.getHeader().getTableName();
                    //2.获取类型
                    CanalEntry.EntryType entryType = entry.getEntryType();
                    //3.获取序列化数据
                    ByteString storeValue = entry.getStoreValue();
                    //4.判断entry是否rowdata类型
                    if (CanalEntry.EntryType.ROWDATA.equals(entryType)){
                        //5.反序列化数据
                        CanalEntry.RowChange rowChange = CanalEntry.RowChange.parseFrom(storeValue);
                        //6.获取当前事件操作类型
                        CanalEntry.EventType eventType = rowChange.getEventType();
                        //7.获取数据集
                        List<CanalEntry.RowData> rowDatasList = rowChange.getRowDatasList();

                        //8.遍历rowdatalist，并打印数据集
                        for (CanalEntry.RowData rowData:rowDatasList){
                            JSONObject beforeData = new JSONObject();
                            JSONObject afterData = new JSONObject();
                            List<CanalEntry.Column> beforeColumnsList = rowData.getBeforeColumnsList();
                            List<CanalEntry.Column> afterColumnsList = rowData.getAfterColumnsList();
                            for (CanalEntry.Column column:beforeColumnsList){
                                beforeData.put(column.getName(),column.getValue());
                            }
                            for (CanalEntry.Column column:afterColumnsList){
                                afterData.put(column.getName(),column.getValue());
                            }
                            System.out.println("Table:"+tableName+
                                    ",EventType:"+eventType+
                                    ",Before:"+beforeData+
                                    ",After:"+afterData);
                        }
                    }else {
                        System.out.println("数据类型不是所需要的");
                    }
                }
            }


        }

    }
}

执行：

到此，我们可以实时获取到mysql数据库的各种操作日志，接下来需要将数据写到哪里 可以按需实现。

3、kafka模式的实现

a.canal.properties

修改：canal.serverMode = kafka

    kafka信息：kafka.bootstrap.servers = 192.168.140.128:9092

#################################################
#########               common argument         #############
#################################################
# tcp bind ip
canal.ip =
# register ip to zookeeper
canal.register.ip =
canal.port = 11111
canal.metrics.pull.port = 11112
# canal instance user/passwd
# canal.user = canal
# canal.passwd = E3619321C1A937C46A0D8BD1DAC39F93B27D4458

# canal admin config
#canal.admin.manager = 127.0.0.1:8089
canal.admin.port = 11110
canal.admin.user = admin
canal.admin.passwd = 4ACFE3202A5FF5CF467898FC58AAB1D615029441

canal.zkServers =
# flush data to zk
canal.zookeeper.flush.period = 1000
canal.withoutNetty = false
# tcp, kafka, rocketMQ, rabbitMQ
canal.serverMode = kafka
# flush meta cursor/parse position to file
canal.file.data.dir = ${canal.conf.dir}
canal.file.flush.period = 1000
## memory store RingBuffer size, should be Math.pow(2,n)
canal.instance.memory.buffer.size = 16384
## memory store RingBuffer used memory unit size , default 1kb
canal.instance.memory.buffer.memunit = 1024 
## meory store gets mode used MEMSIZE or ITEMSIZE
canal.instance.memory.batch.mode = MEMSIZE
canal.instance.memory.rawEntry = true

## detecing config
canal.instance.detecting.enable = false
#canal.instance.detecting.sql = insert into retl.xdual values(1,now()) on duplicate key update x=now()
canal.instance.detecting.sql = select 1
canal.instance.detecting.interval.time = 3
canal.instance.detecting.retry.threshold = 3
canal.instance.detecting.heartbeatHaEnable = false

# support maximum transaction size, more than the size of the transaction will be cut into multiple transactions delivery
canal.instance.transaction.size =  1024
# mysql fallback connected to new master should fallback times
canal.instance.fallbackIntervalInSeconds = 60

# network config
canal.instance.network.receiveBufferSize = 16384
canal.instance.network.sendBufferSize = 16384
canal.instance.network.soTimeout = 30

# binlog filter config
canal.instance.filter.druid.ddl = true
canal.instance.filter.query.dcl = false
canal.instance.filter.query.dml = false
canal.instance.filter.query.ddl = false
canal.instance.filter.table.error = false
canal.instance.filter.rows = false
canal.instance.filter.transaction.entry = false

# binlog format/image check
canal.instance.binlog.format = ROW,STATEMENT,MIXED 
canal.instance.binlog.image = FULL,MINIMAL,NOBLOB

# binlog ddl isolation
canal.instance.get.ddl.isolation = false

# parallel parser config
canal.instance.parser.parallel = true
## concurrent thread number, default 60% available processors, suggest not to exceed Runtime.getRuntime().availableProcessors()
#canal.instance.parser.parallelThreadSize = 16
## disruptor ringbuffer size, must be power of 2
canal.instance.parser.parallelBufferSize = 256

# table meta tsdb info
canal.instance.tsdb.enable = true
canal.instance.tsdb.dir = ${canal.file.data.dir:../conf}/${canal.instance.destination:}
canal.instance.tsdb.url = jdbc:h2:${canal.instance.tsdb.dir}/h2;CACHE_SIZE=1000;MODE=MYSQL;
canal.instance.tsdb.dbUsername = canal
canal.instance.tsdb.dbPassword = canal
# dump snapshot interval, default 24 hour
canal.instance.tsdb.snapshot.interval = 24
# purge snapshot expire , default 360 hour(15 days)
canal.instance.tsdb.snapshot.expire = 360

#################################################
#########               destinations            #############
#################################################
canal.destinations = example
# conf root dir
canal.conf.dir = ../conf
# auto scan instance dir add/remove and start/stop instance
canal.auto.scan = true
canal.auto.scan.interval = 5

canal.instance.tsdb.spring.xml = classpath:spring/tsdb/h2-tsdb.xml
#canal.instance.tsdb.spring.xml = classpath:spring/tsdb/mysql-tsdb.xml

canal.instance.global.mode = spring
canal.instance.global.lazy = false
canal.instance.global.manager.address = ${canal.admin.manager}
#canal.instance.global.spring.xml = classpath:spring/memory-instance.xml
canal.instance.global.spring.xml = classpath:spring/file-instance.xml
#canal.instance.global.spring.xml = classpath:spring/default-instance.xml

##################################################
#########             MQ Properties      #############
##################################################
canal.mq.flat.message = true
canal.mq.database.hash = true
canal.mq.parallel.thread.size = 8
canal.mq.canal.batch.size = 50
canal.mq.canal.fetch.timeout = 100
# Set this value to "cloud", if you want open message trace feature in aliyun.
canal.mq.access.channel = local

# aliyun ak/sk , support rds/mq
canal.aliyun.accessKey =
canal.aliyun.secretKey =
canal.aliyun.uid=

##################################################
#########                    Kafka                   #############
##################################################
kafka.bootstrap.servers = 192.168.140.128:9092
kafka.acks = all
kafka.compression.type = none
kafka.batch.size = 16384
kafka.linger.ms = 1
kafka.max.request.size = 1048576
kafka.buffer.memory = 33554432
kafka.max.in.flight.requests.per.connection = 1
kafka.retries = 0

canal.mq.kafka.kerberos.enable = false
canal.mq.kafka.kerberos.krb5.file = "../conf/kerberos/krb5.conf"
canal.mq.kafka.kerberos.jaas.file = "../conf/kerberos/jaas.conf"

##################################################
#########                   RocketMQ         #############
##################################################
rocketmq.producer.group = test
rocketmq.enable.message.trace = false
rocketmq.customized.trace.topic =
rocketmq.namespace =
rocketmq.namesrv.addr = 127.0.0.1:9876
rocketmq.retry.times.when.send.failed = 0
rocketmq.vip.channel.enabled = false

##################################################
#########                   RabbitMQ         #############
##################################################
rabbitmq.host =
rabbitmq.virtual.host =
rabbitmq.exchange =
rabbitmq.username =
rabbitmq.password =

b、example/instance.properties

修改：canal.instance.master.address=192.168.140.1:3306

canal.instance.dbUsername=flink

canal.instance.dbPassword=flink

canal.mq.topic=mysql_binlogs

#################################################
## mysql serverId , v1.0.26+ will autoGen
# canal.instance.mysql.slaveId=0

# enable gtid use true/false
canal.instance.gtidon=false

# position info
canal.instance.master.address=192.168.140.1:3306
canal.instance.master.journal.name=
canal.instance.master.position=
canal.instance.master.timestamp=
canal.instance.master.gtid=

# rds oss binlog
canal.instance.rds.accesskey=
canal.instance.rds.secretkey=
canal.instance.rds.instanceId=

# table meta tsdb info
canal.instance.tsdb.enable=true
#canal.instance.tsdb.url=jdbc:mysql://127.0.0.1:3306/canal_tsdb
#canal.instance.tsdb.dbUsername=canal
#canal.instance.tsdb.dbPassword=canal

#canal.instance.standby.address =
#canal.instance.standby.journal.name =
#canal.instance.standby.position =
#canal.instance.standby.timestamp =
#canal.instance.standby.gtid=

# username/password
canal.instance.dbUsername=flink
canal.instance.dbPassword=flink
canal.instance.connectionCharset = UTF-8
# enable druid Decrypt database password
canal.instance.enableDruid=false
#canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUCAwEAAQ==

# table regex
canal.instance.filter.regex=.*\\..*
# table black regex
canal.instance.filter.black.regex=
# table field filter(format: schema1.tableName1:field1/field2,schema2.tableName2:field1/field2)
#canal.instance.filter.field=test1.t_product:id/subject/keywords,test2.t_company:id/name/contact/ch
# table field black filter(format: schema1.tableName1:field1/field2,schema2.tableName2:field1/field2)
#canal.instance.filter.black.field=test1.t_product:subject/product_image,test2.t_company:id/name/contact/ch

# mq config
canal.mq.topic=mysql_binlogs
# dynamic topic route by schema or table regex
#canal.mq.dynamicTopic=mytest1.user,mytest2\\..*,.*\\..*
canal.mq.partition=0
# hash partition config
#canal.mq.partitionsNum=3
#canal.mq.partitionHash=test.table:id^name,.*\\..*
#################################################

c、启动

startup.sh

d、查看数据生产情况

kafka-console-consumer.sh --bootstrap-server 192.168.140.128:9092 --topic mysql_binlogs --from-beginning

4、datahub兼容kafka的实现

配置如何实现啊

什么是Canal插件,如何使用Canal插件_数据总线 DataHub(DataHub)-阿里云帮助中心

看样子需要datahub兼容kafka的ip:port （私有云需要联系运维）

5、TCP模式+Datahub SDK实现

TCP配置及基本实现参考2

a、依赖

    <dependency>
      <groupId>com.aliyun.datahub</groupId>
      <artifactId>aliyun-sdk-datahub</artifactId>
      <version>2.25.1</version>
    </dependency>

b、代码实现

package com.tbea;

import com.alibaba.fastjson.JSONObject;
import com.alibaba.otter.canal.client.CanalConnector;
import com.alibaba.otter.canal.client.CanalConnectors;
import com.alibaba.otter.canal.protocol.CanalEntry;
import com.alibaba.otter.canal.protocol.Message;
import com.aliyun.datahub.client.DatahubClient;
import com.aliyun.datahub.client.DatahubClientBuilder;
import com.aliyun.datahub.client.auth.AliyunAccount;
import com.aliyun.datahub.client.common.DatahubConfig;
import com.aliyun.datahub.client.example.examples.Constant;
import com.aliyun.datahub.client.exception.*;
import com.aliyun.datahub.client.http.HttpConfig;
import com.aliyun.datahub.client.model.*;
import com.google.protobuf.ByteString;
import com.google.protobuf.InvalidProtocolBufferException;

import java.net.InetSocketAddress;
import java.util.ArrayList;
import java.util.List;

import static com.aliyun.datahub.client.example.examples.Constant.*;

public class CanalClient {

    static DatahubClient datahubClient = DatahubClientBuilder.newBuilder().setDatahubConfig(
                //Protocol可不设置，不设置默认使用PROTOBUF传输协议
                new DatahubConfig("https://datahub.cn-beijing-tbdg-d01.dh.res.bigdata.tbea.com",
                        new AliyunAccount("2Z8tAOpDPBm5LEkA", "Tlupsw2G0PdKGCRyPLucHjeESqoCla"))
        ).setHttpConfig(new HttpConfig().setCompressType(CompressType.LZ4)).build();

    public static void main(String[] args) throws InterruptedException, InvalidProtocolBufferException {
        //获取链接
        CanalConnector canalConnector = CanalConnectors.newSingleConnector(
                new InetSocketAddress("192.168.140.129", 11111)
                , "example"
                , "", ""
        );

        //尝试获取新数据
        while (true){
            //todo 连接
            canalConnector.connect();
            //todo 订阅数据库
            canalConnector.subscribe("flinkcdc.*");
            //todo 批量拉取数据
            Message message = canalConnector.get(100);
            //todo 获取entry
            List<CanalEntry.Entry> entries = message.getEntries();
            //todo 遍历 判断集合状态
            if (entries.size()<=0){
                System.out.println("当次未抓取到数据，休息一会~~~~~~~");
                Thread.sleep(1000);
            }else {
                //遍历解析
                for (CanalEntry.Entry entry:entries){
                    //1.获取表名
                    String tableName = entry.getHeader().getTableName();
                    String schemaName = entry.getHeader().getSchemaName();
                    //2.获取类型
                    CanalEntry.EntryType entryType = entry.getEntryType();
                    //3.获取序列化数据
                    ByteString storeValue = entry.getStoreValue();
                    //4.判断entry是否rowdata类型
                    if (CanalEntry.EntryType.ROWDATA.equals(entryType)){
                        //5.反序列化数据
                        CanalEntry.RowChange rowChange = CanalEntry.RowChange.parseFrom(storeValue);
                        //6.获取当前事件操作类型
                        CanalEntry.EventType eventType = rowChange.getEventType();
                        //7.获取数据集
                        List<CanalEntry.RowData> rowDatasList = rowChange.getRowDatasList();
                        JSONObject beforeData = new JSONObject();
                        JSONObject afterData = new JSONObject();
                        //8.遍历rowdatalist，并打印数据集
                        for (CanalEntry.RowData rowData:rowDatasList){

                            List<CanalEntry.Column> beforeColumnsList = rowData.getBeforeColumnsList();
                            List<CanalEntry.Column> afterColumnsList = rowData.getAfterColumnsList();
                            for (CanalEntry.Column column:beforeColumnsList){
                                beforeData.put(column.getName(),column.getValue());
                            }
                            for (CanalEntry.Column column:afterColumnsList){
                                afterData.put(column.getName(),column.getValue());
                            }
                            System.out.println("Table:"+tableName+
                                    ",EventType:"+eventType+
                                    ",Before:"+beforeData+
                                    ",After:"+afterData);

                        }
                        Binlog binlog = new Binlog(eventType.toString(), tableName, schemaName, beforeData.toJSONString(), afterData.toJSONString());
                        tupleExample("bigdata","tcp_canal",3,binlog);
                    }else {
                        System.out.println("数据类型不是所需要的");
                    }
                }
            }
        }
    }
    // 写入Tuple型数据
    public static void tupleExample(String project,String topic,int retryTimes,Binlog binlog) {
        DatahubClient datahubClient = DatahubClientBuilder.newBuilder().setDatahubConfig(
                //Protocol可不设置，不设置默认使用PROTOBUF传输协议
                new DatahubConfig("https://datahub.cn-*****************.com",
                        new AliyunAccount("************", "*************"))
        ).setHttpConfig(new HttpConfig().setCompressType(CompressType.LZ4)).build();
        // 获取schema
        RecordSchema recordSchema = datahubClient.getTopic(project,topic).getRecordSchema();
        // 生成十条数据
        List<RecordEntry> recordEntries = new ArrayList<>();

        RecordEntry recordEntry = new RecordEntry();
        // 对每条数据设置额外属性，例如ip 机器名等。可以不设置额外属性，不影响数据写入
        recordEntry.addAttribute("key1", "value1");
        TupleRecordData data = new TupleRecordData(recordSchema);
        data.setField("operate", binlog.getOperater());
        data.setField("tablename", binlog.getTableName());
        data.setField("databasename", binlog.getDatabaseName());
        data.setField("before", binlog.getBefore());
        data.setField("after", binlog.getAfter());
        recordEntry.setRecordData(data);
        recordEntries.add(recordEntry);

        try {
            PutRecordsResult result = datahubClient.putRecords(project, topic, recordEntries);
            int i = result.getFailedRecordCount();
            if (i > 0) {
                retry(datahubClient, result.getFailedRecords(), retryTimes, project, topic);
            }
        }  catch (DatahubClientException e) {
            System.out.println("requestId:" + e.getRequestId() + "\tmessage:" + e.getErrorMessage());
        }
    }
    //重试机制
    public static void retry(DatahubClient client, List<RecordEntry> records, int retryTimes, String project, String topic) {
        boolean suc = false;
        while (retryTimes != 0) {
            retryTimes = retryTimes - 1;
            PutRecordsResult recordsResult = client.putRecords(project, topic, records);
            if (recordsResult.getFailedRecordCount() > 0) {
                retry(client,recordsResult.getFailedRecords(),retryTimes,project,topic);
            }
            suc = true;
            break;
        }
        if (!suc) {
            System.out.println("retryFailure");
        }
    }
}

注意topic和代码的映射关系