go - Goroutines，Channels，WaitGroups，然后选择(只是试图理解)

Question

我并不一定要尝试完成某些特定的事情，而只是了解goroutine， channel ， WaitGroup 和select(在 channel 上)如何一起使用。我正在编写一个简单的程序，该程序循环遍历URL的一部分，获取URL，然后基本上就结束了。一个简单的想法是，我希望所有获取都发生并返回，通过 channel 发送其数据，然后在所有获取发生后结束。我快到了，而且我知道我的选择中缺少要结束循环的内容，说“嘿， WaitGroup 现在是空的”，但是我不确定如何最好地做到这一点。介意看看并为我清理吗？现在一切正常，只是没有终止，所以很明显我缺少了一些东西，并且/或者不了解这些组件中的某些组件应该如何协同工作。

package main

import (
    "fmt"
    "io/ioutil"
    "net/http"
    "sync"
)

var urls = []string{
    "https://www.google.com1",
    "https://www.gentoo.org",
}

var wg sync.WaitGroup

// simple struct to store fetching
type urlObject struct {
    url     string
    success bool
    body    string
}

func getPage(url string, channelMain chan urlObject, channelError chan error) {

    // increment waitgroup, defer decrementing
    wg.Add(1)
    defer wg.Done()
    fmt.Println("fetching " + url)

    // create a urlObject
    uO := urlObject{
        url:     url,
        success: false,
    }

    // get URL
    response, getError := http.Get(url)

    // close response later on
    if response != nil {
        defer response.Body.Close()
    }

    // send error over error channel if one occurs
    if getError != nil {
        channelError <- getError
        return
    }

    // convert body to []byte
    body, conversionError := ioutil.ReadAll(response.Body)
    // convert []byte to string
    bodyString := string(body)

    // if a conversion error happens send it over the error channel
    if conversionError != nil {
        channelError <- conversionError
    } else {
        // if not send a urlObject over the main channel
        uO.success = true
        uO.body = bodyString
        channelMain <- uO
    }

}

func main() {

    var channelMain = make(chan urlObject)
    var channelError = make(chan error)

    for _, v := range urls {
        go getPage(v, channelMain, channelError)
    }

    // wait on goroutines to finish
    wg.Wait()

    for {
        select {
        case uO := <-channelMain:
            fmt.Println("completed " + uO.url)
        case err := <-channelError:
            fmt.Println("error: " + err.Error())
        }
    }

}

Answer 1

您需要进行以下更改:

正如人们提到的那样，您可能要在调用goroutine之前先在主函数中调用wg.Add(1)。这样，您知道它发生在defer wg.Done()调用之前。

您的 channel 读取将被阻止，除非您能找到一种方法来关闭goroutines中的 channel 或对其进行缓冲。可能最简单的方法是对其进行缓冲，例如var channelMain = make(chan urlObject, len(urls))

select语句中的break将仅退出选择，而不退出包含的for循环。您可以标记for循环并中断该循环，或使用某种条件变量。

游乐场链接到工作版本: https://play.golang.org/p/WH1fm2MhP-L

package main

import (
    "fmt"
    "io/ioutil"
    "net/http"
    "sync"
)

var urls = []string{
    "https://www.google.com1",
    "https://www.gentoo.org",
}

var wg sync.WaitGroup

// simple struct to store fetching
type urlObject struct {
    url     string
    success bool
    body    string
}

func getPage(url string, channelMain chan urlObject, channelError chan error) {

    // increment waitgroup, defer decrementing
    defer wg.Done()
    fmt.Println("fetching " + url)

    // create a urlObject
    uO := urlObject{
        url:     url,
        success: false,
    }

    // get URL
    response, getError := http.Get(url)

    // close response later on
    if response != nil {
        defer response.Body.Close()
    }

    // send error over error channel if one occurs
    if getError != nil {
        channelError <- getError
        return
    }

    // convert body to []byte
    body, conversionError := ioutil.ReadAll(response.Body)
    // convert []byte to string
    bodyString := string(body)

    // if a conversion error happens send it over the error channel
    if conversionError != nil {
        channelError <- conversionError
    } else {
        // if not send a urlObject over the main channel
        uO.success = true
        uO.body = bodyString
        channelMain <- uO
    }

}

func main() {

    var channelMain = make(chan urlObject, len(urls))
    var channelError = make(chan error, len(urls))

    for _, v := range urls {
        wg.Add(1)
        go getPage(v, channelMain, channelError)
    }

    // wait on goroutines to finish
    wg.Wait()

    for done := false; !done; {
        select {
        case uO := <-channelMain:
            fmt.Println("completed " + uO.url)
        case err := <-channelError:
            fmt.Println("error: " + err.Error())
        default:
            done = true
        }
    }

}