文件监听同步（canal 搭建）

在这里插入图片描述

参考文档

https://github.com/alibaba/canal/wiki/QuickStart

mysql开启bin-log日志

log_bin = /var/lib/mysql/bin-log
skip-name-resolve
binlog-format=ROW

创建canal对象

CREATE USER canal IDENTIFIED BY 'canal'; 
GRANT SELECT, REPLICATION SLAVE, REPLICATION CLIENT ON *.* TO 'canal'@'%';
flush privileges;

下载canal

wget https://github.com/alibaba/canal/releases/download/canal-1.1.4/canal.deployer-1.1.4.tar.gz

编写canal.properties

cat /usr/local/canal/conf/canal.properties
-----------------------------------------------------
#################################################
#########               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
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 = false
canal.instance.filter.query.dcl = false
#开启dml语句过滤
canal.instance.filter.query.dml = true
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

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

#################################################
#########               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                      #############
##################################################
canal.mq.servers = 127.0.0.1:6667
canal.mq.retries = 0
canal.mq.batchSize = 16384
canal.mq.maxRequestSize = 1048576
canal.mq.lingerMs = 100
canal.mq.bufferMemory = 33554432
canal.mq.canalBatchSize = 50
canal.mq.canalGetTimeout = 100
canal.mq.flatMessage = true
canal.mq.compressionType = none
canal.mq.acks = all
#canal.mq.properties. =
canal.mq.producerGroup = test
# Set this value to "cloud", if you want open message trace feature in aliyun.
canal.mq.accessChannel = local
# aliyun mq namespace
#canal.mq.namespace =

##################################################
#########     Kafka Kerberos Info    #############
##################################################
canal.mq.kafka.kerberos.enable = false
canal.mq.kafka.kerberos.krb5FilePath = "../conf/kerberos/krb5.conf"
canal.mq.kafka.kerberos.jaasFilePath = "../conf/kerberos/jaas.conf"

-----------------------------------------------------------------------------------------

编写instance.properties

cat /usr/local/canal/conf/example/instance.properties 
-----------------------------------------------------------------------------------------
#################################################
## 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=监听数据库IP: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=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
canal.instance.filter.regex=数据库.表
# 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,.*\\..*
#################################################

开启监听

/usr/local/canal/bin/startup.sh

java集成

maven项目集成
<dependency>
    <groupId>com.alibaba.otter</groupId>
    <artifactId>canal.client</artifactId>
    <version>1.1.0</version>
</dependency>

==================================
package com.alibaba.otter.canal.sample;
import java.net.InetSocketAddress;
import java.util.List;


import com.alibaba.otter.canal.client.CanalConnectors;
import com.alibaba.otter.canal.client.CanalConnector;
import com.alibaba.otter.canal.common.utils.AddressUtils;
import com.alibaba.otter.canal.protocol.Message;
import com.alibaba.otter.canal.protocol.CanalEntry.Column;
import com.alibaba.otter.canal.protocol.CanalEntry.Entry;
import com.alibaba.otter.canal.protocol.CanalEntry.EntryType;
import com.alibaba.otter.canal.protocol.CanalEntry.EventType;
import com.alibaba.otter.canal.protocol.CanalEntry.RowChange;
import com.alibaba.otter.canal.protocol.CanalEntry.RowData;


public class SimpleCanalClientExample {


public static void main(String args[]) {
    // 创建链接
    CanalConnector connector = CanalConnectors.newSingleConnector(new InetSocketAddress(AddressUtils.getHostIp(),
                                                                                        11111), "example", "", "");
    int batchSize = 1000;
    int emptyCount = 0;
    try {
        connector.connect();
        connector.subscribe(".*\\..*");
        connector.rollback();
        int totalEmptyCount = 120;
        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");
    } 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());
    }
}
}

来源：CSDN

作者：speed-snail

链接：https://blog.csdn.net/u010741721/article/details/103985311

标签

canal

otter