如何使用canal监控mysql数据库实现elasticsearch索引实时更新

log-bin=mysql-bin # 开启 binlog
binlog-format=ROW # 选择 ROW 模式
server_id=1 # 配置 replaction 不要和 canal 的 slaveId 重复

CREATE USER canal IDENTIFIED BY ‘canal’;
GRANT SELECT, REPLICATION SLAVE, REPLICATION CLIENT ON *.* TO ‘canal’@’%’;
FLUSH PRIVILEGES;

##################################################
######### RabbitMQ #############
# 提前建好 用户、vhost、exchange
##################################################
rabbitmq.host = 192.168.1.171:5672
rabbitmq.virtual.host = sql
rabbitmq.exchange = sqlBinLogExchange
rabbitmq.username = admin
rabbitmq.password = admin
rabbitmq.deliveryMode = Direct

#################################################
## mysql serverId , v1.0.26+ will autoGen
# canal.instance.mysql.slaveId=0
# enable gtid use true/false
canal.instance.gtidon=false
# position info 写连接即可，其他省略，会自动获取
canal.instance.master.address=192.168.1.175:3306
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 先前建好的数据库用户名密码
canal.instance.dbUsername=canal
canal.instance.dbPassword=canal
canal.instance.connectionCharset = UTF-8
# enable druid Decrypt database password
canal.instance.enableDruid=false
#canal.instance.pwdPublicKey=MFwwDQYJKoZIhvcNAQEBBQADSwAwSAJBALK4BUxdDltRRE5/zXpVEVPUgunvscYFtEip3pmLlhrWpacX7y7GCMo2/JM6LeHmiiNdH1FWgGCpUfircSwlWKUCAwEAAQ==
# table regex 只监控部分表
canal.instance.filter.regex=.*\\.cms_base_content
# table black regex
canal.instance.filter.black.regex=mysql\\.slave_.*
# 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 这个是routerkey，要配置
canal.mq.topic=anhui_szf
# 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,.*\\..*
#canal.mq.dynamicTopicPartitionNum=test.*:4,mycanal:6

package com.alibaba.otter.canal.connector.rabbitmq.producer;
… … 省略
@SPI(“rabbitmq”)
public class CanalRabbitMQProducer extends AbstractMQProducer implements CanalMQProducer {
// 需要监控的操作类型
private static final String OPERATE_TYPE = “UPDATE,INSERT,DELETE”;
// 更新时，需要触发发送mq的字段
private static final String[] KEY_FIELDS = new String[]{“COLUMN_ID”,”TITLE”,”REDIRECT_LINK”,”IMAGE_LINK”,
“IS_PUBLISH”,”PUBLISH_DATE”,”RECORD_STATUS”,”IS_TOP”,”AUTHOR”,”REMARKS”,”TO_FILEID”,”UPDATE_USER_ID”};
// 数据处理时，需要保留的字段（需把标题等传值过去，已删除数据这些查不到了）
private static final String[] HOLD_FIELDS = new String[]{“ID”, “SITE_ID”, “COLUMN_ID”, “RECORD_STATUS”, “TITLE”};
… … 省略
private void send(MQDestination canalDestination, String topicName, Message messageSub) {
if (!mqProperties.isFlatMessage()) {
byte[] message = CanalMessageSerializerUtil.serializer(messageSub, mqProperties.isFilterTransactionEntry());
if (logger.isDebugEnabled()) {
logger.debug(“send message:{} to destination:{}”, message, canalDestination.getCanalDestination());
}
sendMessage(topicName, message);
} else {
// 并发构造
MQMessageUtils.EntryRowData[] datas = MQMessageUtils.buildMessageData(messageSub, buildExecutor);
// 串行分区
List<FlatMessage> flatMessages = MQMessageUtils.messageConverter(datas, messageSub.getId());
for (FlatMessage flatMessage : flatMessages) {
if (!OPERATE_TYPE.contains(flatMessage.getType())) {
continue;
}
// 只有设置的关键字段更新，才会触发消息发送
if (“UPDATE”.equals(flatMessage.getType())) {
List<Map<String, String>> olds = flatMessage.getOld();
if (olds.size() > 0) {
Map<String, String> param = olds.get(0);
// 判断更新字段是否包含重要字段，不包含则跳过
boolean isSkip = true;
for (String keyField : KEY_FIELDS) {
if (param.containsKey(keyField) || param.containsKey(keyField.toLowerCase())) {
isSkip = false;
break;
}
}
if (isSkip) {
continue;
}
// 取出data里面的ID和RECORD_STATUS，只保留这个字段的值，其余的舍弃
if (null != flatMessage.getData()) {
List<Map<String, String>> data = flatMessage.getData();
if (!data.isEmpty()) {
List<Map<String, String>> newData = new ArrayList<>();
for(Map<String, String> map : data) {
Map<String, String> newMap = new HashMap<>(8);
for (String field : HOLD_FIELDS) {
if (map.containsKey(field) || map.containsKey(field.toLowerCase())) {
newMap.put(field, map.get(field));
}
newData.add(newMap);
flatMessage.setData(newData);
// 不需要的字段注释掉，较少网络传输消耗
flatMessage.setMysqlType(null);
flatMessage.setSqlType(null);
flatMessage.setOld(null);
flatMessage.setIsDdl(null);
logger.info(“====================================”);
logger.info(JSON.toJSONString(flatMessage));
byte[] message = JSON.toJSONBytes(flatMessage, SerializerFeature.WriteMapNullValue);
if (logger.isDebugEnabled()) {
logger.debug(“send message:{} to destination:{}”, message, canalDestination.getCanalDestination());
sendMessage(topicName, message);
}
}
… … 省略
}

package cn.lonsun.core.middleware.rabbitmq;
import cn.lonsun.core.util.SpringContextHolder;
import cn.lonsun.es.internal.service.IIndexService;
import cn.lonsun.es.internal.service.impl.IndexServiceImpl;
import cn.lonsun.es.vo.MessageVO;
import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONObject;
import com.rabbitmq.client.Channel;
import com.rabbitmq.client.GetResponse;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.amqp.core.Message;
import org.springframework.amqp.rabbit.core.ChannelAwareMessageListener;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.data.redis.core.RedisTemplate;
import org.springframework.stereotype.Component;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
/**
* @author yanyulin
* @ClassName: MessageListenerBean
* @Description: RabbitMQ消息接收者
* @date 2022-3-14 15:25
* @version: 1.0
*/
@Component
public class MessageListenerBean implements ChannelAwareMessageListener {
private static Logger log = LoggerFactory.getLogger(MessageListenerBean.class);
@Autowired
private RedisTemplate redisTemplate;
// 一次处理多少条消息，考虑es写入性能（文本较大时，单个索引可能很大），一次处理200条，模拟剩余多少条，使用2
private static final int BATCH_DEAL_COUNT = 2;
// mq里待消费线程缓存KEY
public static final String WAIT_DEAL = “wait_deal”;
// 集合编码
private String code;
@Override
public void onMessage(Message message, Channel channel) throws IOException {
Thread thread=Thread.currentThread();
long maxDeliveryTag = 0;
String queuName = message.getMessageProperties().getConsumerQueue();
// 消费前，更新剩余待消费消息数量
redisTemplate.opsForValue().set(code + “_” + WAIT_DEAL, channel.messageCount(queuName) + 1);
System.out.println(“==============>” + code + “=” + redisTemplate.opsForValue().get(code + “_” + WAIT_DEAL));
List<MessageVO> messageVOList = new ArrayList<>();
List<GetResponse> responseList = new ArrayList<>();
while (responseList.size() < BATCH_DEAL_COUNT) {
// 需要设置false，手动ack
GetResponse getResponse = channel.basicGet(queuName, false);
if (getResponse == null) {
byte[] body = message.getBody();
String str = new String(body);
log.info(code + ” deliveryTag:{} message:{} ThreadId is:{} ConsumerTag:{} Queue:{} channel:{}”
,maxDeliveryTag,str,thread.getId(),message.getMessageProperties().getConsumerTag()
,message.getMessageProperties().getConsumerQueue(),channel.getChannelNumber());
// 开始消费
MessageVO messageVO = JSONObject.parseObject(str,MessageVO.class);
log.debug(“监听数据库cms_base_content表变更记录消息,消息内容： {} “, JSON.toJSONString(messageVO));
messageVOList.add(messageVO);
break;
}
responseList.add(getResponse);
maxDeliveryTag = getResponse.getEnvelope().getDeliveryTag();
}
try{
if (!responseList.isEmpty()) {
for (GetResponse response : responseList) {
byte[] body = response.getBody();
String str = new String(body);
log.info(code + ” deliveryTag:{} message:{} ThreadId is:{} ConsumerTag:{} Queue:{} channel:{}”
,maxDeliveryTag,str,thread.getId(),message.getMessageProperties().getConsumerTag()
,message.getMessageProperties().getConsumerQueue(),channel.getChannelNumber());
// 开始消费
MessageVO messageVO = JSONObject.parseObject(str,MessageVO.class);
log.debug(“监听数据库cms_base_content表变更记录消息,消息内容： {} “, JSON.toJSONString(messageVO));
messageVOList.add(messageVO);
}
IIndexService indexService = SpringContextHolder.getBean(IndexServiceImpl.class);
indexService.batchDealIndex(messageVOList, code);
channel.basicAck(maxDeliveryTag, true);
// Ack后，更新剩余待消费消息数量
redisTemplate.opsForValue().set(code + “_” + WAIT_DEAL, channel.messageCount(queuName));
System.out.println(“==============>” + code + “=” + redisTemplate.opsForValue().get(code + “_” + WAIT_DEAL));
}catch(Throwable e){
log.error(“监听前台访问记录消息,deliveryTag： {} “,maxDeliveryTag,e);
//成功收到消息
try {
channel.basicNack(maxDeliveryTag,true,true);
} catch (IOException e1) {
log.error(“ack 异常, 消息队列可能出现无法消费情况, 请及时处理”,e1);
}
public MessageListenerBean() {
public MessageListenerBean(String code) {
this.code = code;
}