一、Canal介绍
1、应用场景
在前面的统计分析功能中,我们采取了服务调用获取统计数据,这样耦合度高,效率相对较低,目前我采取另一种实现方式,通过实时同步数据库表的方式实现,例如我们要统计每天注册与登录人数,我们只需把会员表同步到统计库中,实现本地统计就可以了,这样效率更高,耦合度更低,Canal就是一个很好的数据库同步工具。canal是阿里巴巴旗下的一款开源项目,纯Java开发。基于数据库增量日志解析,提供增量数据订阅&消费,目前主要支持了MySQL。
2、Canal环境搭建
canal的原理是基于mysql binlog技术,所以这里一定需要开启mysql的binlog写入功能
开启mysql服务: service mysql start
(1)检查binlog功能是否有开启
(2)如果显示状态为OFF表示该功能未开启,开启binlog功能
(3)在mysql里面添加以下的相关用户和权限
3、下载安装Canal服务
下载地址: https://github.com/alibaba/canal/releases
(1)下载之后,放到目录中,解压文件
cd /usr/local/canal
canal.deployer-1.1.4.tar.gz
tar zxvf canal.deployer-1.1.4.tar.gz
(2)修改配置文件
vi conf/example/instance.properties
注:
mysql 数据解析关注的表,Perl正则表达式.
多个正则之间以逗号(,)分隔,转义符需要双斜杠(\)
常见例子:
- 所有表:. or .\..*
- canal schema下所有表: canal\..*
- canal下的以canal打头的表:canal\.canal.*
- canal schema下的一张表:canal.test1
- 多个规则组合使用:canal\..*,mysql.test1,mysql.test2 (逗号分隔)
注意:此过滤条件只针对row模式的数据有效(ps. mixed/statement因为不解析sql,所以无法准确提取tableName进行过滤)
(3)进入bin目录下启动
sh bin/startup.sh
二、创建canal_client模块
1、创建canal_client模块
2、引入相关依赖
<dependencies>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-web</artifactId>
</dependency>
<!--mysql-->
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
</dependency>
<dependency>
<groupId>commons-dbutils</groupId>
<artifactId>commons-dbutils</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-jdbc</artifactId>
</dependency>
<dependency>
<groupId>com.alibaba.otter</groupId>
<artifactId>canal.client</artifactId>
</dependency>
</dependencies>
3、创建application.yml配置文件
server:
port: 8009
spring:
application:
name: caner_clientedu
profiles:
active: dev
datasource:
driver-class-name: com.mysql.cj.jdbc.Driver
url: jdbc:mysql://localhost:3306/education?serverTimezone=Asia/Shanghai&useUnicode=true&characterEncoding=utf-8&zeroDateTimeBehavior=convertToNull&useSSL=false&allowPublicKeyRetrieval=true
username: root
password: 419520
4、编写canal客户端类
package com.xingchen.canel.client;
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 org.apache.commons.dbutils.DbUtils;
import org.apache.commons.dbutils.QueryRunner;
import org.springframework.stereotype.Component;
import javax.annotation.Resource;
import javax.sql.DataSource;
import java.net.InetSocketAddress;
import java.sql.Connection;
import java.sql.SQLException;
import java.util.List;
import java.util.Queue;
import java.util.concurrent.ConcurrentLinkedQueue;
@Component
public class CanalClient {
//sql队列
private Queue<String> SQL_QUEUE = new ConcurrentLinkedQueue<>();
@Resource
private DataSource dataSource;
/**
* canal入库方法
*/
public void run() {
CanalConnector connector = CanalConnectors.newSingleConnector(new InetSocketAddress("192.168.88.135",
11111), "example", "", "");
int batchSize = 1000;
try {
connector.connect();
connector.subscribe(".*\\..*");
connector.rollback();
try {
while (true) {
//尝试从master那边拉去数据batchSize条记录,有多少取多少
Message message = connector.getWithoutAck(batchSize);
long batchId = message.getId();
int size = message.getEntries().size();
if (batchId == -1 || size == 0) {
Thread.sleep(1000);
} else {
dataHandle(message.getEntries());
}
connector.ack(batchId);
//当队列里面堆积的sql大于一定数值的时候就模拟执行
if (SQL_QUEUE.size() >= 1) {
executeQueueSql();
}
}
} catch (InterruptedException e) {
e.printStackTrace();
} catch (InvalidProtocolBufferException e) {
e.printStackTrace();
}
} finally {
connector.disconnect();
}
}
/**
* 模拟执行队列里面的sql语句
*/
public void executeQueueSql() {
int size = SQL_QUEUE.size();
for (int i = 0; i < size; i++) {
String sql = SQL_QUEUE.poll();
System.out.println("[sql]----> " + sql);
this.execute(sql.toString());
}
}
/**
* 数据处理
*
* @param entrys
*/
private void dataHandle(List<Entry> entrys) throws InvalidProtocolBufferException {
for (Entry entry : entrys) {
if (EntryType.ROWDATA == entry.getEntryType()) {
RowChange rowChange = RowChange.parseFrom(entry.getStoreValue());
EventType eventType = rowChange.getEventType();
if (eventType == EventType.DELETE) {
saveDeleteSql(entry);
} else if (eventType == EventType.UPDATE) {
saveUpdateSql(entry);
} else if (eventType == EventType.INSERT) {
saveInsertSql(entry);
}
}
}
}
/**
* 保存更新语句
*
* @param entry
*/
private void saveUpdateSql(Entry entry) {
try {
RowChange rowChange = RowChange.parseFrom(entry.getStoreValue());
List<RowData> rowDatasList = rowChange.getRowDatasList();
for (RowData rowData : rowDatasList) {
List<Column> newColumnList = rowData.getAfterColumnsList();
StringBuffer sql = new StringBuffer("update " + entry.getHeader().getTableName() + " set ");
for (int i = 0; i < newColumnList.size(); i++) {
sql.append(" " + newColumnList.get(i).getName()
+ " = '" + newColumnList.get(i).getValue() + "'");
if (i != newColumnList.size() - 1) {
sql.append(",");
}
}
sql.append(" where ");
List<Column> oldColumnList = rowData.getBeforeColumnsList();
for (Column column : oldColumnList) {
if (column.getIsKey()) {
//暂时只支持单一主键
sql.append(column.getName() + "=" + column.getValue());
break;
}
}
SQL_QUEUE.add(sql.toString());
}
} catch (InvalidProtocolBufferException e) {
e.printStackTrace();
}
}
/**
* 保存删除语句
*
* @param entry
*/
private void saveDeleteSql(Entry entry) {
try {
RowChange rowChange = RowChange.parseFrom(entry.getStoreValue());
List<RowData> rowDatasList = rowChange.getRowDatasList();
for (RowData rowData : rowDatasList) {
List<Column> columnList = rowData.getBeforeColumnsList();
StringBuffer sql = new StringBuffer("delete from " + entry.getHeader().getTableName() + " where ");
for (Column column : columnList) {
if (column.getIsKey()) {
//暂时只支持单一主键
sql.append(column.getName() + "=" + column.getValue());
break;
}
}
SQL_QUEUE.add(sql.toString());
}
} catch (InvalidProtocolBufferException e) {
e.printStackTrace();
}
}
/**
* 保存插入语句
*
* @param entry
*/
private void saveInsertSql(Entry entry) {
try {
RowChange rowChange = RowChange.parseFrom(entry.getStoreValue());
List<RowData> rowDatasList = rowChange.getRowDatasList();
for (RowData rowData : rowDatasList) {
List<Column> columnList = rowData.getAfterColumnsList();
StringBuffer sql = new StringBuffer("insert into " + entry.getHeader().getTableName() + " (");
for (int i = 0; i < columnList.size(); i++) {
sql.append(columnList.get(i).getName());
if (i != columnList.size() - 1) {
sql.append(",");
}
}
sql.append(") VALUES (");
for (int i = 0; i < columnList.size(); i++) {
sql.append("'" + columnList.get(i).getValue() + "'");
if (i != columnList.size() - 1) {
sql.append(",");
}
}
sql.append(")");
SQL_QUEUE.add(sql.toString());
}
} catch (InvalidProtocolBufferException e) {
e.printStackTrace();
}
}
/**
* 入库
* @param sql
*/
public void execute(String sql) {
Connection con = null;
try {
if(null == sql) return;
con = dataSource.getConnection();
QueryRunner qr = new QueryRunner();
int row = qr.execute(con, sql);
System.out.println("update: "+ row);
} catch (SQLException e) {
e.printStackTrace();
} finally {
DbUtils.closeQuietly(con);
}
}
}
5、创建启动类
package com.xingchen.canel;
import com.xingchen.canel.client.CanalClient;
import org.springframework.boot.CommandLineRunner;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
import javax.annotation.Resource;
@SpringBootApplication
public class CanalApplication implements CommandLineRunner{
@Resource
private CanalClient canalClient;
public static void main(String[] args) {
SpringApplication.run(CanalApplication.class, args);
}
@Override
public void run(String... args) throws Exception {
canalClient.run();
}
}