增加健壮性后的完整示例

让我们改进 Messager 程序以增加该程序的健壮性：

%%% Message passing utility.  
%%% User interface:
%%% login(Name)
%%%     One user at a time can log in from each Erlang node in the
%%%     system messenger: and choose a suitable Name. If the Name
%%%     is already logged in at another node or if someone else is
%%%     already logged in at the same node, login will be rejected
%%%     with a suitable error message.
%%% logoff()
%%%     Logs off anybody at that node
%%% message(ToName, Message)
%%%     sends Message to ToName. Error messages if the user of this 
%%%     function is not logged on or if ToName is not logged on at
%%%     any node.
%%%
%%% One node in the network of Erlang nodes runs a server which maintains
%%% data about the logged on users. The server is registered as "messenger"
%%% Each node where there is a user logged on runs a client process registered
%%% as "mess_client" 
%%%
%%% Protocol between the client processes and the server
%%% ----------------------------------------------------
%%% 
%%% To server: {ClientPid, logon, UserName}
%%% Reply {messenger, stop, user_exists_at_other_node} stops the client
%%% Reply {messenger, logged_on} logon was successful
%%%
%%% When the client terminates for some reason
%%% To server: {'EXIT', ClientPid, Reason}
%%%
%%% To server: {ClientPid, message_to, ToName, Message} send a message
%%% Reply: {messenger, stop, you_are_not_logged_on} stops the client
%%% Reply: {messenger, receiver_not_found} no user with this name logged on
%%% Reply: {messenger, sent} Message has been sent (but no guarantee)
%%%
%%% To client: {message_from, Name, Message},
%%%
%%% Protocol between the "commands" and the client
%%% ---------------------------------------------- 
%%%
%%% Started: messenger:client(Server_Node, Name)
%%% To client: logoff
%%% To client: {message_to, ToName, Message}
%%%
%%% Configuration: change the server_node() function to return the
%%% name of the node where the messenger server runs

-module(messenger).
-export([start_server/0, server/0, 
         logon/1, logoff/0, message/2, client/2]).

%%% Change the function below to return the name of the node where the
%%% messenger server runs
server_node() ->
    messenger@super.

%%% This is the server process for the "messenger"
%%% the user list has the format [{ClientPid1, Name1},{ClientPid22, Name2},...]
server() ->
    process_flag(trap_exit, true),
    server([]).

server(User_List) ->
    receive
        {From, logon, Name} ->
            New_User_List = server_logon(From, Name, User_List),
            server(New_User_List);
        {'EXIT', From, _} ->
            New_User_List = server_logoff(From, User_List),
            server(New_User_List);
        {From, message_to, To, Message} ->
            server_transfer(From, To, Message, User_List),
            io:format("list is now: ~p~n", [User_List]),
            server(User_List)
    end.

%%% Start the server
start_server() ->
    register(messenger, spawn(messenger, server, [])).

%%% Server adds a new user to the user list
server_logon(From, Name, User_List) ->
    %% check if logged on anywhere else
    case lists:keymember(Name, 2, User_List) of
        true ->
            From ! {messenger, stop, user_exists_at_other_node},  %reject logon
            User_List;
        false ->
            From ! {messenger, logged_on},
            link(From),
            [{From, Name} | User_List]        %add user to the list
    end.

%%% Server deletes a user from the user list
server_logoff(From, User_List) ->
    lists:keydelete(From, 1, User_List).

%%% Server transfers a message between user
server_transfer(From, To, Message, User_List) ->
    %% check that the user is logged on and who he is
    case lists:keysearch(From, 1, User_List) of
        false ->
            From ! {messenger, stop, you_are_not_logged_on};
        {value, {_, Name}} ->
            server_transfer(From, Name, To, Message, User_List)
    end.

%%% If the user exists, send the message
server_transfer(From, Name, To, Message, User_List) ->
    %% Find the receiver and send the message
    case lists:keysearch(To, 2, User_List) of
        false ->
            From ! {messenger, receiver_not_found};
        {value, {ToPid, To}} ->
            ToPid ! {message_from, Name, Message}, 
            From ! {messenger, sent} 
    end.

%%% User Commands
logon(Name) ->
    case whereis(mess_client) of 
        undefined ->
            register(mess_client, 
                     spawn(messenger, client, [server_node(), Name]));
        _ -> already_logged_on
    end.

logoff() ->
    mess_client ! logoff.

message(ToName, Message) ->
    case whereis(mess_client) of % Test if the client is running
        undefined ->
            not_logged_on;
        _ -> mess_client ! {message_to, ToName, Message},
             ok
end.

%%% The client process which runs on each user node
client(Server_Node, Name) ->
    {messenger, Server_Node} ! {self(), logon, Name},
    await_result(),
    client(Server_Node).

client(Server_Node) ->
    receive
        logoff ->
            exit(normal);
        {message_to, ToName, Message} ->
            {messenger, Server_Node} ! {self(), message_to, ToName, Message},
            await_result();
        {message_from, FromName, Message} ->
            io:format("Message from ~p: ~p~n", [FromName, Message])
    end,
    client(Server_Node).

%%% wait for a response from the server
await_result() ->
    receive
        {messenger, stop, Why} -> % Stop the client 
            io:format("~p~n", [Why]),
            exit(normal);
        {messenger, What} ->  % Normal response
            io:format("~p~n", [What])
    after 5000 ->
            io:format("No response from server~n", []),
            exit(timeout)
    end.

主要有如下几处改动:

Messager 服务器捕捉进程退出。如果它收到进程终止信号，{'EXIT',From,Reason}，则说明客户端进程已经终止或者由于下面的原因变得不可达：

• 用户主动退出登录（取消了 “logoff” 消息）。
• 与客户端连接的网络已经断开。
• 客户进程所处的结点崩溃。
• 客户进程执行了某些非法操作。

如果收到上面所述的退出信号，服务器调用 server_logoff 函数将 {From, Name} 元组从 User_Lists 列表中删除。如果服务端所在的结点崩溃了，那么系统将将自动产生进程终止信号，并将其发送给所有的客户端进程：'EXIT',MessengerPID,noconnection}，客户端进程收到该消息后会终止自身。

同样，在 await_result 函数中引入了一个 5 秒钟的定时器。也就是说，如果服务器 5 秒钟之类没有回复客户端，则客户端终止执行。这个只是在服务端与客户端建立连接前的登录阶段需要。

一个非常有意思的例子是如果客户端在服务端建立连接前终止会发生什么情况呢？需要特别注意，如果一个进程与另一个不存在的进程建立连接，则会收到一个终止信号 {'EXIT',From, noproc}。这就好像连接建立后进程立马就结束了一样。