递归目录只会深入一个文件

时间:2015-03-30 19:56:29

标签: file recursion erlang

我有以下代码:

find_info(File) ->
    case file:read_file_info(File) of
        {ok, Facts} -> 
            case Facts#file_info.type of
                directory -> directory;
                regular -> regular
            end;
        {error,Reason} -> exit(Reason)
    end.

find_files(Dir,Flag,Ending,Acc) -> 
    case file:list_dir(Dir) of
        {ok,A} -> find_files_helper(A,Dir,Flag,Acc,Ending);
        {_,_} -> Acc
    end. 

find_files_helper([H|Tail],Dir,Flag,Acc,Ending) ->
    A = find_info(filename:absname_join(Dir,H)),
    case A of
        directory -> 
            case Flag of
                true -> 
                    find_files(filename:absname_join(Dir,H),Flag,Ending,Acc ++ find_files_helper(Tail,Dir,Flag,Acc,Ending));
                false -> find_files_helper(Tail,Dir,Flag,Acc,Ending)
            end;
        regular -> 
        case filename:extension(H) of
            Ending -> find_files_helper(Tail,Dir,Flag,[to_md5_large(H)] ++ Acc, Ending);
            _ -> find_files_helper(Tail,Dir,Flag,Acc,Ending)
        end;
        {error,Reason} -> exit(Reason)
    end;
find_files_helper([],_,_,Acc,_) -> Acc.

但是每当我运行find_files / 4时,程序只会在崩溃之前深入一个文件。 说我有以下目录

home/
   a/
     ser.erl
   b/
   c/
file.erl
file2.erl

运行后,我会得到file.erl file2.erlser.erl的md5。但是,如果目录如下所示:

home/
   a/
     ser.erl
     back.erl
   b/
   c/
file.erl
file2.erl

然后整个程序崩溃了。我花了好几个小时在我的逻辑中寻找我所缺少的东西,但我不知道。

我得到的错误消息是函数p:to_md5_large / 1中的异常enoent。

如果这里需要md5,那就是:

to_md5_large(File)  ->

        case file:read_file(File) of
            {ok, <<B/binary>>} -> md5_helper(B,erlang:md5_init());
            {error,Reason} -> exit(Reason)
        end.

md5_helper(<<A:4/binary,B>>,Acc) -> md5_helper(B,erlang:md5_update(Acc,A));
md5_helper(A,Acc) -> 
    B =     erlang:md5_update(Acc,A),
    erlang:md5_final(B).

2 个答案:

答案 0 :(得分:1)

有一个功能可以帮到你:

fold_files(Dir, RegExp, Recursive, Fun, AccIn) -> AccOut

在你的情况下:

Result = filelib:fold_files(Dir, ".*\.erl", true, fun(X,Acc) -> {ok,B} = file:read_file(X), [erlang:md5(B)|Acc] end, []).

<强> [编辑]

@Bula:

由于两个原因,我没有直接回答你的问题:

  • 第一个是,在我写答案的时候,你没有提供你得到的错误类型。使用任何语言学习如何从错误报告中获取信息非常重要。在erlang中,大多数情况下,您会将错误类型设置为发生的行,查看文档,您将获得有关出错的非常有用的信息。顺便说一下,除非你想管理错误,否则我不鼓励你写下这样的话:

    case file:read_file(File) of
        {ok, <<B/binary>>} -> md5_helper(B,erlang:md5_init());
        {error,Reason} -> exit(Reason)
    end.
    

以下代码将执行相同的操作,更短,并且您将获得有问题的确切行号(它不是代码中的最佳示例,但它更短)

    {ok, <<B/binary>>} = file:read_file(File),
    md5_helper(B,erlang:md5_init()),
  • 第二个是我发现你的代码太大,无用的辅助函数。我认为尝试使用简洁易读的代码并尝试以正确的方式使用库函数非常重要。例如,您正在使用erlang:md5:init / 0,erlang:md5_update / 2和erlang:md5_final / 1,而单次调用erlang:md5 / 1就足够了。您使用它的方式是,当您通过块获取数据块时能够计算md5,这不是您的情况,并且您编写辅助函数的方式不允许使用此功能。

我不明白为什么你想要一个“部署”版本的代码,但我建议你另一个版本,我试图遵循我的建议(直接在shell中编写,所以它需要R17 +来定义递归匿名函数):o)

1> F = fun F(X,D,Ending) ->                                                                     
1>   {ok,StartD} = file:get_cwd(),        %% save current directory                                    
1>   ok = file:set_cwd(D),                %% move to the directory to explore                          
1>   R = case filelib:is_dir(X) of                                                                
1>     true ->                            %% if the element to analyze is a directory                                  
1>       {ok,Files} = file:list_dir(X),   %% getits content                                       
1>       [F(Y,X,Ending) || Y <- Files];   %% and recursively analyze all its elements             
1>     false -> 
1>       case filelib:is_regular(X) andalso (filename:extension(X) == Ending) of         
1>         true ->                        %% if it is a regular file with the right extension              
1>           {ok,B} = file:read_file(X),  %% read it                                               
1>           [erlang:md5(B)];             %% and calculate the md5 (must be return in a list                                            
1>                                        %% for consistancy with directory results)
1>         false ->                                                                                
1>           []                           %% in other cases (symlink, ...) return empty                                     
1>       end                                                                                       
1>   end,                                                                                        
1>   ok = file:set_cwd(StartD),           %% restore current directory                                    
1>   lists:flatten(R)                     %% flatten for nicer result                                       
1> end.                                                                                          
#Fun<erl_eval.42.90072148>
2> Md5 = fun(D) -> F(D,D,".erl") end.
#Fun<erl_eval.6.90072148>
3> Md5("C:/My programs/erl6.2/lib/stdlib-2.2").
[<<150,238,21,49,189,164,184,32,42,239,200,52,135,78,12,
   112>>,
 <<226,53,12,102,125,107,137,149,116,47,50,30,37,13,211,243>>,
 <<193,114,120,24,175,27,23,218,7,169,146,8,19,208,73,255>>,
 <<227,219,237,12,103,218,175,238,194,103,52,180,132,113,
   184,68>>,
 <<6,16,213,41,39,138,161,36,184,86,17,183,125,233,20,125>>,
 <<23,208,91,76,69,173,159,200,44,72,9,9,50,40,226,27>>,
 <<92,8,168,124,230,1,167,199,6,150,239,62,146,119,83,36>>,
 <<100,238,68,145,58,22,88,221,179,204,19,26,50,172,142,193>>,
 <<253,79,101,49,78,235,151,104,188,223,55,228,163,25,16,
   147>>,
 <<243,189,25,98,170,97,88,90,174,178,162,19,249,141,94,60>>,
 <<237,85,6,153,218,60,23,104,162,112,65,69,148,90,15,240>>,
 <<225,48,238,193,120,43,124,63,156,207,11,4,254,96,250,204>>,
 <<67,254,107,82,106,87,36,119,140,78,216,142,66,225,8,40>>,
 <<185,246,227,162,211,133,212,10,174,21,204,75,128,125,
   200,...>>,
 <<234,191,210,59,62,148,130,187,60,0,187,124,150,213,...>>,
 <<199,231,45,34,185,9,231,162,187,130,134,246,54,...>>,
 <<157,226,127,87,191,151,81,50,19,116,96,121,...>>,
 <<15,59,143,114,184,207,96,164,155,44,238,...>>,
 <<176,139,190,30,114,248,0,144,201,14,...>>,
 <<169,79,218,157,20,10,20,146,12,...>>,
 <<131,25,76,110,14,183,5,103,...>>,
 <<91,197,189,2,48,142,67,...>>,
 <<94,202,72,164,129,237,...>>,
 <<"^NQÙ¡8hÿèkàå"...>>,<<"ðÙ.Q"...>>,
 <<150,101,76,...>>,
 <<"A^ÏrÔ"...>>,<<"¹"...>>,<<...>>|...]
4>

答案 1 :(得分:1)

您收到enoent,因为当您不在back.erl所在的目录中时,您会将to_md5_large等文件名传递给back.erl。尝试传递完整的文件名。您已经在filename:absname_join(Dir,H)中调用了find_files_helper,因此只需将其保存到变量中,然后将该变量而不是H传递给to_md5_large