http://d.puremagic.com/issues/show_bug.cgi?id=885

           Summary: Recursion into folders with FindFirstFileA/FindNextFileA
                    behaves incorrectly
           Product: D
           Version: 1.001
          Platform: PC
        OS/Version: Windows
            Status: NEW
          Severity: major
          Priority: P2
         Component: www.digitalmars.com
        AssignedTo: bugzilla@digitalmars.com
        ReportedBy: fdp@mcs.be


The accompanying program was used to find files in a (quite huge) directory structure using a regex expression.  When I noticed that some files that were there were not found, I added a line to print the directories that get 'visited'.  That's where I noticed that some directories were not recursed into.  Furthermore this behaviour is not constant; the directories that are skipt are not always the same ones.  Thinking of a memory problem, I also experimented by adding fullCollect and genCollect calls at various places and this had indeed an influence on which directories were skipped.

Here is the code:


import std.c.windows.windows;
import std.path;
import std.stdio;
import std.regexp;
import std.utf;

void visit (char[] p_strFolder, RegExp p_patt)
{
   writefln (">>> ", p_strFolder); // added for debugging purposes
   WIN32_FIND_DATA fd;
   char[] strSpec = join (p_strFolder, "*");
   HANDLE h = FindFirstFileA (cast(char*)strSpec, &fd);
   bool bOK = h != INVALID_HANDLE_VALUE;
   while (bOK)
   {
      wchar[] wbuf;

      size_t clength = std.string.strlen(fd.cFileName.ptr);
         // Convert cFileName[] to unicode
      size_t wlength =
MultiByteToWideChar(0,0,fd.cFileName.ptr,clength,null,0);
      if (wlength > wbuf.length)
      {
         wbuf.length = wlength;
      }
      size_t n =
MultiByteToWideChar(0,0,fd.cFileName.ptr,clength,cast(wchar*)wbuf,wlength);
      assert(n == wlength);
         // toUTF8() returns a new buffer
      char[] strName = std.utf.toUTF8(wbuf[0 .. wlength]);

      if ((fd.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY) != 0)
      {
         if (0 != std.string.cmp (strName, ".")  &&
             0 != std.string.cmp (strName, "..") &&
             0 != std.string.cmp (strName, ".svn"))
         {
            visit (join (p_strFolder, strName), p_patt);
         }
      }
      else
      {
         char[] strFullName = join (p_strFolder, strName);
         if (-1 != p_patt.find(std.string.tolower (strFullName)))
         {
           // removed code for debugging purposes
         }
      }
      bOK = cast(bool)FindNextFileA (h, &fd);
   }
   FindClose (h);
}

void main (char [][] p_args)
{
   if (p_args.length == 1)
   {
      visit (curdir, RegExp ("."));
   }
   else
   {
      visit (p_args[1], RegExp (std.string.tolower (p_args[1])));
   }
}

PS: I just tested on 1.002 also and the behaviour is the same.


-- 

d-bugmail@puremagic.com wrote:
> http://d.puremagic.com/issues/show_bug.cgi?id=885
> 
>            Summary: Recursion into folders with FindFirstFileA/FindNextFileA
>                     behaves incorrectly
>            Product: D
>            Version: 1.001
>           Platform: PC
>         OS/Version: Windows
>             Status: NEW
>           Severity: major
>           Priority: P2
>          Component: www.digitalmars.com
>         AssignedTo: bugzilla@digitalmars.com
>         ReportedBy: fdp@mcs.be
> 
> 
> The accompanying program was used to find files in a (quite huge) directory
> structure using a regex expression.  When I noticed that some files that were
> there were not found, I added a line to print the directories that get
> 'visited'.  That's where I noticed that some directories were not recursed
> into.  Furthermore this behaviour is not constant; the directories that are
> skipt are not always the same ones.  Thinking of a memory problem, I also
> experimented by adding fullCollect and genCollect calls at various places and
> this had indeed an influence on which directories were skipped.
> 
> Here is the code:
> 
> 
> import std.c.windows.windows;
> import std.path;
> import std.stdio;
> import std.regexp;
> import std.utf;
> 
> void visit (char[] p_strFolder, RegExp p_patt)
> {
>    writefln (">>> ", p_strFolder); // added for debugging purposes
>    WIN32_FIND_DATA fd;
>    char[] strSpec = join (p_strFolder, "*");
>    HANDLE h = FindFirstFileA (cast(char*)strSpec, &fd);
>    bool bOK = h != INVALID_HANDLE_VALUE;
>    while (bOK)
>    {
>       wchar[] wbuf;
> 
>       size_t clength = std.string.strlen(fd.cFileName.ptr);
>          // Convert cFileName[] to unicode
>       size_t wlength =
> MultiByteToWideChar(0,0,fd.cFileName.ptr,clength,null,0);
>       if (wlength > wbuf.length)
>       {
>          wbuf.length = wlength;
>       }
>       size_t n =
> MultiByteToWideChar(0,0,fd.cFileName.ptr,clength,cast(wchar*)wbuf,wlength);
>       assert(n == wlength);
>          // toUTF8() returns a new buffer
>       char[] strName = std.utf.toUTF8(wbuf[0 .. wlength]);
> 
>       if ((fd.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY) != 0)
>       {
>          if (0 != std.string.cmp (strName, ".")  &&
>              0 != std.string.cmp (strName, "..") &&
>              0 != std.string.cmp (strName, ".svn"))
>          {
>             visit (join (p_strFolder, strName), p_patt);
>          }
>       }
>       else
>       {
>          char[] strFullName = join (p_strFolder, strName);
>          if (-1 != p_patt.find(std.string.tolower (strFullName)))
>          {
>            // removed code for debugging purposes
>          }
>       }
>       bOK = cast(bool)FindNextFileA (h, &fd);
>    }
>    FindClose (h);
> }
> 
> void main (char [][] p_args)
> {
>    if (p_args.length == 1)
>    {
>       visit (curdir, RegExp ("."));
>    }
>    else
>    {
>       visit (p_args[1], RegExp (std.string.tolower (p_args[1])));
>    }
> }
> 
> PS: I just tested on 1.002 also and the behaviour is the same.
> 
> 

You're certain FindFirst() et al can be recursed like this? IIRC, they maintain some global state?

http://d.puremagic.com/issues/show_bug.cgi?id=885





------- Comment #1 from bugzilla@digitalmars.com  2007-01-27 23:01 -------
Could you try this again with DMD 1.004?


-- 

http://d.puremagic.com/issues/show_bug.cgi?id=885





------- Comment #2 from fdp@mcs.be  2007-01-29 00:37 -------
(In reply to comment #0)
> The accompanying program was used to find files in a (quite huge) directory structure using a regex expression.  When I noticed that some files that were there were not found, I added a line to print the directories that get 'visited'.  That's where I noticed that some directories were not recursed into.  Furthermore this behaviour is not constant; the directories that are skipt are not always the same ones.  Thinking of a memory problem, I also experimented by adding fullCollect and genCollect calls at various places and this had indeed an influence on which directories were skipped.
> 
> Here is the code:
> 
> 
> import std.c.windows.windows;
> import std.path;
> import std.stdio;
> import std.regexp;
> import std.utf;
> 
> void visit (char[] p_strFolder, RegExp p_patt)
> {
>    writefln (">>> ", p_strFolder); // added for debugging purposes
>    WIN32_FIND_DATA fd;
>    char[] strSpec = join (p_strFolder, "*");
>    HANDLE h = FindFirstFileA (cast(char*)strSpec, &fd);
>    bool bOK = h != INVALID_HANDLE_VALUE;
>    while (bOK)
>    {
>       wchar[] wbuf;
> 
>       size_t clength = std.string.strlen(fd.cFileName.ptr);
>          // Convert cFileName[] to unicode
>       size_t wlength =
> MultiByteToWideChar(0,0,fd.cFileName.ptr,clength,null,0);
>       if (wlength > wbuf.length)
>       {
>          wbuf.length = wlength;
>       }
>       size_t n =
> MultiByteToWideChar(0,0,fd.cFileName.ptr,clength,cast(wchar*)wbuf,wlength);
>       assert(n == wlength);
>          // toUTF8() returns a new buffer
>       char[] strName = std.utf.toUTF8(wbuf[0 .. wlength]);
> 
>       if ((fd.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY) != 0)
>       {
>          if (0 != std.string.cmp (strName, ".")  &&
>              0 != std.string.cmp (strName, "..") &&
>              0 != std.string.cmp (strName, ".svn"))
>          {
>             visit (join (p_strFolder, strName), p_patt);
>          }
>       }
>       else
>       {
>          char[] strFullName = join (p_strFolder, strName);
>          if (-1 != p_patt.find(std.string.tolower (strFullName)))
>          {
>            // removed code for debugging purposes
>          }
>       }
>       bOK = cast(bool)FindNextFileA (h, &fd);
>    }
>    FindClose (h);
> }
> 
> void main (char [][] p_args)
> {
>    if (p_args.length == 1)
>    {
>       visit (curdir, RegExp ("."));
>    }
>    else
>    {
>       visit (p_args[1], RegExp (std.string.tolower (p_args[1])));
>    }
> }
> 
> PS: I just tested on 1.002 also and the behaviour is the same.
> 

(In reply to comment #1)
> Could you try this again with DMD 1.004?
> 

I regret to say that the problem persists in 1.004.


-- 

http://d.puremagic.com/issues/show_bug.cgi?id=885


fdp@mcs.be changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |RESOLVED
         Resolution|                            |INVALID




------- Comment #3 from fdp@mcs.be  2007-02-26 07:41 -------
My mistake, sorry; had to use toStringz instead of just cast(char*) in the
line:
HANDLE h = FindFirstFileA (cast(char*)strSpec, &fd);

sorry for the trouble


--