如果代码被编译为控制台程序或作为fsi --use:Program.fs --exec --quiet运行，一些线程将在完成之前终止。有什么方法可以等待所有线程结束？
这个问题可以描述为“存在多个MailboxProcessers时程序退出问题”。
输出示例
（注意最后一行被截断，最后一个输出函数 ( printfn "[Main] after crawl") 永远不会执行。）
[主要] 爬行前 [爬取] 返回结果前 代理 1 抓取的 http://news.google.com。 [主管] 达到上限 代理 5 完成。 http://www.gstatic.com/news/img/favicon.ico 由代理 1 抓取。 [主管] 达到上限 代理 1 完成。 http://www.google.com/imghp?hl=en&tab=ni 由代理 4 抓取。 [主管] 达到上限 代理 4 完成。 http://www.google.com/webhp?hl=en&tab=nw 由代理 2 抓取。 [主管] 达到上限 代理 2 完成。 http://news.google。
代码
编辑：添加了几个System.Threading.Thread.CurrentThread.IsBackground <- false.
open System
open System.Collections.Concurrent
open System.Collections.Generic
open System.IO
open System.Net
open System.Text.RegularExpressions
module Helpers =
type Message =
| Done
| Mailbox of MailboxProcessor<Message>
| Stop
| Url of string option
| Start of AsyncReplyChannel<unit>
// Gates the number of crawling agents.
[<Literal>]
let Gate = 5
// Extracts links from HTML.
let extractLinks html =
let pattern1 = "(?i)href\\s*=\\s*(\"|\')/?((?!#.*|/\B|" +
"mailto:|location\.|javascript:)[^\"\']+)(\"|\')"
let pattern2 = "(?i)^https?"
let links =
[
for x in Regex(pattern1).Matches(html) do
yield x.Groups.[2].Value
]
|> List.filter (fun x -> Regex(pattern2).IsMatch(x))
links
// Fetches a Web page.
let fetch (url : string) =
try
let req = WebRequest.Create(url) :?> HttpWebRequest
req.UserAgent <- "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)"
req.Timeout <- 5000
use resp = req.GetResponse()
let content = resp.ContentType
let isHtml = Regex("html").IsMatch(content)
match isHtml with
| true -> use stream = resp.GetResponseStream()
use reader = new StreamReader(stream)
let html = reader.ReadToEnd()
Some html
| false -> None
with
| _ -> None
let collectLinks url =
let html = fetch url
match html with
| Some x -> extractLinks x
| None -> []
open Helpers
// Creates a mailbox that synchronizes printing to the console (so
// that two calls to 'printfn' do not interleave when printing)
let printer =
MailboxProcessor.Start(fun x -> async {
while true do
let! str = x.Receive()
System.Threading.Thread.CurrentThread.IsBackground <- false
printfn "%s" str })
// Hides standard 'printfn' function (formats the string using
// 'kprintf' and then posts the result to the printer agent.
let printfn fmt =
Printf.kprintf printer.Post fmt
let crawl url limit =
// Concurrent queue for saving collected urls.
let q = ConcurrentQueue<string>()
// Holds crawled URLs.
let set = HashSet<string>()
let supervisor =
MailboxProcessor.Start(fun x -> async {
System.Threading.Thread.CurrentThread.IsBackground <- false
// The agent expects to receive 'Start' message first - the message
// carries a reply channel that is used to notify the caller
// when the agent completes crawling.
let! start = x.Receive()
let repl =
match start with
| Start repl -> repl
| _ -> failwith "Expected Start message!"
let rec loop run =
async {
let! msg = x.Receive()
match msg with
| Mailbox(mailbox) ->
let count = set.Count
if count < limit - 1 && run then
let url = q.TryDequeue()
match url with
| true, str -> if not (set.Contains str) then
let set'= set.Add str
mailbox.Post <| Url(Some str)
return! loop run
else
mailbox.Post <| Url None
return! loop run
| _ -> mailbox.Post <| Url None
return! loop run
else
printfn "[supervisor] reached limit"
// Wait for finishing
mailbox.Post Stop
return! loop run
| Stop -> printfn "[Supervisor] stop"; return! loop false
| Start _ -> failwith "Unexpected start message!"
| Url _ -> failwith "Unexpected URL message!"
| Done -> printfn "[Supervisor] Supervisor is done."
(x :> IDisposable).Dispose()
// Notify the caller that the agent has completed
repl.Reply(())
}
do! loop true })
let urlCollector =
MailboxProcessor.Start(fun y ->
let rec loop count =
async {
System.Threading.Thread.CurrentThread.IsBackground <- false
let! msg = y.TryReceive(6000)
match msg with
| Some message ->
match message with
| Url u ->
match u with
| Some url -> q.Enqueue url
return! loop count
| None -> return! loop count
| _ ->
match count with
| Gate -> (y :> IDisposable).Dispose()
printfn "[urlCollector] URL collector is done."
supervisor.Post Done
| _ -> return! loop (count + 1)
| None -> supervisor.Post Stop
return! loop count
}
loop 1)
/// Initializes a crawling agent.
let crawler id =
MailboxProcessor.Start(fun inbox ->
let rec loop() =
async {
System.Threading.Thread.CurrentThread.IsBackground <- false
let! msg = inbox.Receive()
match msg with
| Url x ->
match x with
| Some url ->
let links = collectLinks url
printfn "%s crawled by agent %d." url id
for link in links do
urlCollector.Post <| Url (Some link)
supervisor.Post(Mailbox(inbox))
return! loop()
| None -> supervisor.Post(Mailbox(inbox))
return! loop()
| _ -> printfn "Agent %d is done." id
urlCollector.Post Done
(inbox :> IDisposable).Dispose()
}
loop())
// Send 'Start' message to the main agent. The result
// is asynchronous workflow that will complete when the
// agent crawling completes
let result = supervisor.PostAndAsyncReply(Start)
// Spawn the crawlers.
let crawlers =
[
for i in 1 .. Gate do
yield crawler i
]
// Post the first messages.
crawlers.Head.Post <| Url (Some url)
crawlers.Tail |> List.iter (fun ag -> ag.Post <| Url None)
printfn "[Crawl] before return result"
result
// Example:
printfn "[Main] before crawl"
crawl "http://news.google.com" 5
|> Async.RunSynchronously
printfn "[Main] after crawl"