예제를 통한 학습: Go 언어를 사용하여 분산 시스템 구축

func Mapper(text string) []KeyValue{
    var kvs []KeyValue
    words := strings.Fields(strings.ToLower(text))//分割单词并转换为小写
    for _,word := range words{
        kvs = append(kvs,KeyValue{word,"1"})
    }
    return kvs
}

func Reducer(key string, values []string) string{
    count := 0
    for _,val := range values{
        v, _ := strconv.Atoi(val)
        count += v
    }
    return strconv.Itoa(count)//将count转换为string类型
}

func main(){
    tasks := make(chan string, 100)
    results := make(chan []KeyValue)//结果集
    workers := 10//工作goroutine数量
    for i:=0;i<workers;i++{
        go doMapReduce(tasks,results)
    }
    go func(){
        for {
            select {
            case <- time.After(10*time.Second):
                close(tasks)
                fmt.Println("Tasks emptied!")
                return
            default:
                tasks <- GetBigData()//GetBigData用来获取大量的文本数据
            }
        }
    }()
    for range results{
        //输出结果
    }
}
//主函数中的doMapReduce函数
func doMapReduce(tasks <-chan string, results chan<- []KeyValue){
    for task := range tasks{
        //Map阶段
        kvs := Mapper(task)
        //Shuffle阶段
        sort.Sort(ByKey(kvs))//按照key排序
        groups := groupBy(kvs)
        //Reduce阶段
        var res []KeyValue
        for k,v := range groups{
            res = append(res,KeyValue{k,Reducer(k,v)})
        }
        results <- res
    }
}

func simhash(text string) uint64{
    //SimHash算法
}
func similarity(s1,s2 uint64) float64{
    //计算两个哈希值之间的相似度
}

func main(){
    var data []string
    for i:=0;i<20;i++{
        data = append(data,GetBigData())
    }
    var hashes []uint64
    for _,text := range data{
        hashes = append(hashes,simhash(text))
    }
    //查找相似文本
    for i:=0;i<len(hashes)-1;i++{
        for j:=i+1;j<len(hashes);j++{
            if(similarity(hashes[i],hashes[j]) > 0.95){
                fmt.Printf("'%v' and '%v' are similar!
",data[i],data[j])
            }
        }
    }
}