Canal入门及使用

Canal概述：

         canal是由Alibaba开源的一个基于binlog的增量日志组件，其核心原理是canal伪装成Mysql的slave，发送dump协议获取binlog，解析并存储起来给客户端消费。

Canal的工作流程：

                     

1. canal模拟mysql slave的交互协议，伪装自己为mysql slave，向mysql master发送dump协议
2. mysql master收到dump请求，开始推送binary log给slave(也就是canal)
3. canal解析binary log对象(原始为byte流)

Canal下载地址： https://github.com/alibaba/canal/releases

Canal 单机模式使用流程：

                    1.开启Mysql数据库binlog,并设置为row格式

                    2.为数据库创建用户，并赋予REPLICATION SLAVE, REPLICATION CLIENT的权限,否则用这些用户连接canal时，无法读取binlog. (默认的root账户肯定也可以)

                    3.解压下载的canal.deployer-1.1.1.tar.gz到指定的任意目录                                                      

  mkdir  canal

  tar -zxvf  canal.deployer-1.1.1.tar.gz

                    4.进入解压目录进行配置修改

vi canal/conf/example/instance.properties

#################################################
## mysql serverId
canal.instance.mysql.slaveId = 1234
#position info，需要改成自己的数据库信息
canal.instance.master.address = 127.0.0.1:3306
canal.instance.master.journal.name =
canal.instance.master.position =
canal.instance.master.timestamp =


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


#username/password，需要改成自己的数据库信息
canal.instance.dbUsername = canal

canal.instance.dbPassword = canal
canal.instance.defaultDatabaseName =
canal.instance.connectionCharset = UTF-8


#table regex
canal.instance.filter.regex = .\..


#################################################

             5.启动canal

sh bin/startup.sh

             6.查看日志是否正常启动

vi logs/canal/canal.log

具体instance的日志
vi logs/example/example.log

              7.编写java client 程序

                

   <dependencies>
    <dependency>
        <groupId>com.alibaba.otter</groupId>
        <artifactId>canal.client</artifactId>
        <version>1.1.1</version>
    </dependency>
   </dependencies>

package com.mytest.canal;

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.InvalidProtocolBufferException;
import com.mytest.canal.bean.CanalStuMsgBean;
import com.mytest.canal.bean.CanalStuScoreBean;
import com.mytest.canal.bean.StudentMsgBean;
import com.mytest.canal.bean.StuentScoreBean;
import com.mytest.kafka.KafkaProduceUtils;
import com.mytest.utils.DateUtil;

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

public class CanalClientTest {

    private static KafkaProduceUtils kafkaProduceUtils;
    public  static StringBuilder builder = new StringBuilder();

    public static void main(String args[]) {

     //   kafkaProduceUtils = new KafkaProduceUtils("my_test_topic");
        // 创建链接
        CanalConnector connector = CanalConnectors.newSingleConnector(new InetSocketAddress("127.0.0.1",
                11111), "example", "", "");
        int batchSize = 1000;
        int emptyCount = 0;
        try {
            connector.connect();
            connector.subscribe(".*\\..*");
            connector.rollback();
            int totalEmptyCount = 12000;
            while (emptyCount < totalEmptyCount) {
                Message message = connector.getWithoutAck(batchSize); // 获取指定数量的数据
                long batchId = message.getId();
                int size = message.getEntries().size();
                if (batchId == -1 || size == 0) {
                    emptyCount++;
                    System.out.println("empty count : " + emptyCount);
                    try {
                        Thread.sleep(1000);
                    } catch (InterruptedException e) {
                    }
                } else {
                    emptyCount = 0;
                    System.out.printf("message[batchId=%s,size=%s] \n", batchId, size);
                    printEntry(message.getEntries());
                }

                connector.ack(batchId); // 提交确认
                // connector.rollback(batchId); // 处理失败, 回滚数据
            }

            System.out.println("empty too many times, exit");
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            connector.disconnect();
        }
    }



    private static void printEntry(List<Entry> entrys) {
        for (Entry entry : entrys) {
            if (entry.getEntryType() == EntryType.TRANSACTIONBEGIN || entry.getEntryType() == EntryType.TRANSACTIONEND) {
                continue;
            }

            RowChange rowChage = null;
            try {
                rowChage = RowChange.parseFrom(entry.getStoreValue());
            } catch (Exception e) {
                throw new RuntimeException("ERROR ## parser of eromanga-event has an error , data:" + entry.toString(),
                        e);
            }

            EventType eventType = rowChage.getEventType();
            System.out.println(String.format("================&gt; binlog[%s:%s] , name[%s,%s] , eventType : %s",
                    entry.getHeader().getLogfileName(), entry.getHeader().getLogfileOffset(),
                    entry.getHeader().getSchemaName(), entry.getHeader().getTableName(),
                    eventType));

            for (RowData rowData : rowChage.getRowDatasList()) {
                if (eventType == EventType.DELETE) {
                    printColumn(rowData.getBeforeColumnsList());
                } else if (eventType == EventType.INSERT) {
                    printColumn(rowData.getAfterColumnsList());
                } else {
                    System.out.println("-------&gt; before");
                    printColumn(rowData.getBeforeColumnsList());
                    System.out.println("-------&gt; after");
                    printColumn(rowData.getAfterColumnsList());
                }
            }
        }
    }

    private static void printColumn(List<Column> columns) {
        for (Column column : columns) {
            System.out.println(column.getName() + " : " + column.getValue() + "    update=" + column.getUpdated());
        }
    }
}

 

     8.运行上述java程序

     9.对mysql数据库进行操作，建表，插入数据，观察java client端是否有对应数据库日志打印出来

     10.关闭java client,  关闭 canal server

sh bin/stop.sh

本文参考地址为canal github地址:   https://github.com/alibaba/canal/wiki