golang连接kafka消费进ES操作

作者: 你是我遥不可及的梦i39507074
来源: 51数据库
2021-08-25

1.首先初始化conf配置把kafka和es的地址配置好还有一个日志方便查看

配置信息如下用到的库是

github.com/astaxie/beego/config
[logs]
log_level = debug
log_path = "./logs/log_transfer.log"
[kafka]
server_addr = 192.168.0.134:9092
topic = nginx_log
[es]
addr = http://192.168.0.134:9200/

2.读取conf配置存取进结构体

type logconfig struct {
  kafkaaddr string
  esaddr string
  logpath string
  loglevel string
  topic string
}
var (
   logconfig *logconfig
)

3.读取conf配置代码如下

func initconfig(conftype string,filename string)(err error) {
   conf, err := config. newconfig(conftype,filename)
   if err != nil {
    fmt. println( "new config faild,err:",err)
     return
  }
   logconfig = &logconfig{}
   logconfig.loglevel = conf. string( "logs::log_level")
   if len(logconfig.loglevel) == 0 {
     logconfig.loglevel = "debug"
  }
   logconfig.logpath = conf. string( "logs::log_path")
   if len(logconfig.logpath) == 0 {
     logconfig.logpath = "./logs"
  }
   logconfig.kafkaaddr = conf. string( "kafka::server_addr")
   if len(logconfig.kafkaaddr) == 0 {
     err = fmt. errorf( "invalid kafka addr err")
     return
  }
   logconfig.esaddr = conf. string( "es::addr")
   if len(logconfig.esaddr) == 0 {
     err = fmt. errorf( "invalid es addr err")
     return
  }
   logconfig.topic = conf. string( "kafka::topic")
   if len(logconfig.topic) == 0 {
     err = fmt. errorf( "invalid topic addr err")
     return
  }
   return
}

4.完成了initconfig的初始化

5.初始化initlogger

func convertloglevel(level string) int {
   switch(level) {
     case "debug":
       return logs.leveldebug
     case "warn":
       return logs.levelwarn
     case "info":
       return logs.levelinfo
     case "trace":
       return logs.leveltrace
  }
   return logs.leveldebug
}
func initlogger(logpath string, loglevel string) (err error) {
   config := make( map[ string] interface{})
  config[ "filename"] = logpath
  config[ "level"] = convertloglevel(loglevel)
   configstr, err := json. marshal(config)
   if err!= nil {
    fmt. println( "marshal failed,err:",err)
     return
  }
  logs. setlogger(logs.adapterfile, string(configstr))
   return
}

6.初始化kafka

type kafkaclient struct {
  client sarama.consumer
  addr string
  topic string
  wg sync.waitgroup
}
var (
   kafkaclient *kafkaclient
)
func initkafka(addr string,topic string)(err error) {
   kafkaclient = &kafkaclient{}
   consumer, err := sarama. newconsumer(strings. split(addr, ","), nil)
   if err != nil {
    logs. error( "failed to strat consumer :",err)
     return 
  }
   kafkaclient.client = consumer
   kafkaclient.addr = addr
   kafkaclient.topic = topic
   return
}

7.初始化es

gopkg.in/olivere/elastic.v2 // 这个是操作es的库

type logmessage struct {
  app string
  topic string
  message string
}
var (
   esclient *elastic.client
)
func inites(addr string)(err error) {
  
   client, err := elastic. newclient(elastic. setsniff( false),elastic. seturl(addr))
   if err != nil {
    fmt. println( "connect es error",err)
     return
  }
   esclient = client
   return
}

8.干活把kafka的数据写入es

github.com/shopify/sarama 这个是操作kafka的驱动库

func run()(err error) {
  fmt. println( "run")
   partitionlist, err := kafkaclient.client. partitions(kafkaclient.topic)
   if err != nil {
    logs. error( "ini failed ,err:%v",err)
    fmt. printf( "ini failed ,err:%v",err)
     return
  }
   for partition := range partitionlist {
    fmt. println( "for进入")
     pc, errret := kafkaclient.client. consumepartition(kafkaclient.topic, int32(partition),sarama.offsetnewest)
     if errret != nil {
       err = errret
      logs. error( "failed to start consumer for partition %d: %s \n ",partition,err)
      fmt. printf( "failed to start consumer for partition %d: %s \n ",partition,err)
       return
    }
     defer pc. asyncclose()
    fmt. println( "马上进入协程")
    kafkaclient.wg. add( 1)
     go func(pc sarama.partitionconsumer){
      fmt. println( "进来了")
      
       for msg := range pc. messages() {
        fmt. println( "func执行")
        logs. debug( "partition:%d,offset:%d,key:%s,value:%s",msg.partition,msg.offset, string(msg.key), string(msg.value))
         //fmt.println()
         err = sendtoes(kafkaclient.topic,msg.value)
         if err != nil {
          logs. warn( "send to es failed,err:%v",err)
        }
      }
      kafkaclient.wg. done()
    }(pc)    
  }
  kafkaclient.wg. wait()
  fmt. println( "协程执行完毕")
   return
}

上面代码是读kafka消费数据通过sendtoes这个函数发送至es里面

sendtoes代码如下

func sendtoes(topic string,data [] byte) (err error) {
   msg := &logmessage{}
   msg.topic = topic
   msg.message = string(data)
   _, err = esclient. index().
       index(topic).
       type(topic).
       bodyjson(msg).
       do()
     if err != nil {
      
       return
    }
   return
}

index就是索引名称

index().type().bodyjson().do()这样的写法是链式执行操作

9.写完了基本操作后再写一个模拟写入数据进kafka的数据代码如下

func main() {
config := sarama. newconfig()
config.producer.requiredacks = sarama.waitforall
config.producer.partitioner = sarama.newrandompartitioner
config.producer.return.successes = true
client, err := sarama. newsyncproducer([] string{ "127.0.0.1:9092"}, config)
if err != nil {
fmt. println( "producer close,err:", err)
return
}
defer client. close()
var n int= 0
for {
n++
msg := &sarama.producermessage{}
msg.topic = "nginx_log"
msg.value = sarama. stringencoder( "this is a good test,hello maomaochong!!," + strconv. itoa(n))
pid, offset, err := client. sendmessage(msg)
if err != nil {
fmt. println( "send message failed,", err)
return
}
fmt. printf( "pid:%v offset:%v \n ", pid, offset)
time. sleep(time.second * 2)
}
}

这个就是生产者往kafka里面写入数据进去消费

10.我们启动我们的kafka 注意kafka依赖于zookeeper 先启动zk然后启动kafka

我这里用的是zookeeper-3.4.12网上有下载

启动zk