Getting the bitmap in and out of a CGIPLUS Image class - C / C++ / MFC Discussion Boards

Re: problem about alloc memory in another library and free in the main project

kcynic21-Dec-07 19:41

21-Dec-07 19:41

Thanks for your help.But I have some questions about the two options.
1.I believe the option 1 will work,but I want to know,if I should free a lot of heap blocks with different types,I have to define some DLL_free overides?
2.To option 2,I am sorry that,I do not know how to do it.In another word,how should I set this step by step?

Re: problem about alloc memory in another library and free in the main project

kcynic21-Dec-07 21:05

kcynic

21-Dec-07 21:05

I also find that their would be some problems about option 1.
Because if I fixed the delete crash,the following code like:
//in the caller
std::string str_temp = get_a_string(...);
...//do something
str_temp = get_another_string(...);//the same run-time error occur again here
...//do something

//in the library
std::string get_a_string(...)
{
std::string str;
...
str = ...;
return str;
}
function get_another_string return a string,too.
If export a DLL_free can fix the error,how about such error?

Number Lock activation

Larry Mills Sr21-Dec-07 13:52

Larry Mills Sr

21-Dec-07 13:52

I recently transfered settings from my laptop to my new desktop. Doing so the laptop doesn't have a "Number Lock" key; so it eliminated the one on my new desktop. Does anyone know I can change the desktop back. I have no idea what to change.

Re: Number Lock activation

Mark Salsbery21-Dec-07 14:59

Mark Salsbery

21-Dec-07 14:59

Which OS? Maybe this will help...

How to enable the NUM LOCK key for the logon screen (2000/XP)[^]
(use HKEY_CURRENT_USER\Control Panel\Keyboard key for per-user setting)

Mark

Mark Salsbery
Microsoft MVP - Visual C++
Java | [Coffee]

Re: Number Lock activation

Larry Mills Sr22-Dec-07 9:50

Larry Mills Sr

22-Dec-07 9:50

You was correct - except it was under HKEY_USERS\Control Panel\Keyboard
A C++ programming language novice, but striving to learn

.RC file formating differences

KayakCoder21-Dec-07 10:40

KayakCoder

21-Dec-07 10:40

I work in an office with 8 developers and we all work on different parts of the same application. We all use DevStudio 2005 and work in primarily native C++. Recently when modifying dialogs some of the developer's systems modify the .rc file in such a way as to prevent more than 80 characters per line. Whereas developer's DevStudios allow the .rc files to have more than 80 characters per line. When we go to integrate our changes a 30 line difference ends up being lost in 1000's of lines of reformated data.

I have searched far and wide to find how to fix this very irritating problem. We have checked the MSN website, help, and other sites to no avail. We have also compared the registry setting for DevStudio under the HKEY_CURRENT_USER to see it there was any common difference. We all have service pack 1 installed. Any help or suggestions would be greatly appreciated, thanks.

I hate programming today (project conflict/calling convention conflict, ... )

Maximilien21-Dec-07 7:24

Maximilien

21-Dec-07 7:24

I think my karma wants me to go home instead of staying at work today.

I'm using Dundas Grid compiled into a static lib that I want to link into a simple wizard dialog based application.

In the dialog header I have :

#pragma once
#include "Dundas_Grid/Include/UGCtrl.h"
...

class CtestGridDlg : public CDialog
{
// Construction
public:
	CtestGridDlg(CWnd* pParent = NULL);	// standard constructor
//// standard stuff

protected:
  CUGCtrl m_Grid;
};

and when the dialog class gets created, it all barfs up.

BOOL CtestGridApp::InitInstance()
{
/// standard InitInstance stuff ...
	CtestGridDlg dlg;  /// < ---- after this line, <code>this</code> becomes <code>NULL</code>.
	m_pMainWnd = &dlg;
/// ...

When CtestGridDlg is constructed, it will construct the CUGCtrl class and in that constructor something happens that completly messes up the memory.

In my project, I have 1 library (Dundas grid) and my wizard based dialog application, nothing else.

I have checked that both library and main application have "MFC in Shared DLL" , not using ATL, using multi-byte character sets, are build using the same calling conventions ( __cdecl (/Gd)) , the same runtime library ( Multi-threaded Debug DLL (/MDd) ), There are no additional macros or #define.

Now, I'm at a loss at what I have to look for in my project; The same sources work in our main source trunk, the settings are the same.

Any ideas before I start thinking throwing my computer across the room ?

Thanks and merry whatever.

Maximilien Lincourt
Your Head A Splode - Strong Bad

Getting the bitmap in and out of a CGIPLUS Image class

Anthony Appleyard21-Dec-07 6:39

Anthony Appleyard

21-Dec-07 6:39

I am sorry to ask so many queries, but:-

Thanks to previous help, I have got my graphics program adapted from Borland C++ 4.5 to Visual C++ 2008. When it is to read a JPG file, I have got as far as reading the file into a GDI+ 'class Image'. But please, how can I:-

Extract from a GDI+ `class Image' the contained image information data as described by a Windows BITMAPINFO and BITMAP?

Given a set of image information data in a Windows BITMAPINFO and BITMAP, create a GDI+ `class Image' using that data or a copy of it?

I have searched around in http://msdn2.microsoft.com/en-us/library/---- and not found what I was looking for.

Re: Getting the bitmap in and out of a CGIPLUS Image class

Mark Salsbery21-Dec-07 7:32

Mark Salsbery

21-Dec-07 7:32

One way to obtain a GDI bitmap from a GDI+ Bitmap is to use
Bitmap::GetHBITMAP() to get a copy as a GDI HBITMAP, something like:

Bitmap MyBitmap(L"C:\\some.jpg");

Color clr(0x00,0x00,0x00);
HBITMAP hbm;
MyBitmap.GetHBITMAP(clr, &hbm);

//BITMAP bm;
//::GetObject(hbm, sizeof(BITMAP), &bm);

You can also build a DIBSection and extract the pixel data yourself,
something like:

Bitmap MyBitmap(L"C:\\some.jpg");

WORD BitsPerPixel = 24;
int BytesPerRow = (((MyBitmap.GetWidth() * (long)BitsPerPixel + 31L) &(~31L)) / 8L);
int PixelDataSize = MyBitmap.GetHeight() * BytesPerRow;

BITMAPINFO BitmapInfo;

BITMAPINFOHEADER *pBMIH = &BitmapInfo.bmiHeader;
pBMIH->biSize = sizeof(BITMAPINFOHEADER);
pBMIH->biWidth = MyBitmap.GetWidth();
pBMIH->biHeight = MyBitmap.GetHeight(); // positive indicates bottom-up DIB
pBMIH->biPlanes = 1;
pBMIH->biBitCount = BitsPerPixel;
pBMIH->biCompression = BI_RGB;
pBMIH->biSizeImage = PixelDataSize;
pBMIH->biXPelsPerMeter = 0;
pBMIH->biYPelsPerMeter = 0;
pBMIH->biClrUsed = 0;
pBMIH->biClrImportant = 0;

BYTE *pPixelDataBytes = 0;
HBITMAP hBitmap = CreateDIBSection(NULL, &BitmapInfo, DIB_RGB_COLORS, (void **)&pPixelDataBytes , NULL, 0); 

BitmapData bmData;
Rect bmRect(0, 0, MyBitmap.GetWidth(), MyBitmap.GetHeight()); 
MyBitmap.LockBits(&bmRect, ImageLockModeRead, PixelFormat24bppRGB, &bmData); 

BYTE *pCurrentSourceByte = (BYTE *)bmData.Scan0;
// DIBsection is bottom-up...start at the bottom row...
BYTE *pCurrentDestinationByte = pPixelDataBytes + ((MyBitmap.GetHeight() - 1) * BytesPerRow);
// ... and work our way up
int DestinationStride = -BytesPerRow;

for (UINT CurY = 0; CurY < MyBitmap.GetHeight(); ++CurY)
{
	// copy one row of pixel data
	memcpy(pCurrentDestinationByte, pCurrentSourceByte, BytesPerRow);

	pCurrentSourceByte += bmData.Stride;
	pCurrentDestinationByte += DestinationStride;
}

MyBitmap.UnlockBits(&bmData);

Mark

Mark Salsbery
Microsoft MVP - Visual C++
Java | [Coffee]

Re: Getting the bitmap in and out of a CGIPLUS Image class

Anthony Appleyard21-Dec-07 12:19

Anthony Appleyard

21-Dec-07 12:19

Thanks; but after the line

Bitmap MyBitmap(L"C:\\some.jpg");

please how can I check if the read failed?

Re: Getting the bitmap in and out of a CGIPLUS Image class

Mark Salsbery21-Dec-07 12:39

Mark Salsbery

21-Dec-07 12:39

Anthony Appleyard wrote:
how can I check if the read failed?

using namespace Gdiplus;

...

Bitmap MyBitmap(L"C:\\some.jpg");

if (Ok != MyBitmap.GetLastStatus())
{
   // Load failed
}

Mark

Mark Salsbery
Microsoft MVP - Visual C++
Java | [Coffee]

Re: Getting the bitmap in and out of a CGIPLUS Image class [modified]

Anthony Appleyard21-Dec-07 23:29

Anthony Appleyard

21-Dec-07 23:29

Thanks for your help here.

However, the function as it now stands (without text which I commented out to track the bug down)) is:

short jpgread (image&I,char*filename){
int i,n=strlen(filename),CurY; WCHAR fn[600];
for(i=0;i<=n;i++) fn[i]=filename[i];
using namespace Gdiplus;
GdiplusStartupInput gdiplusStartupInput;
ULONG_PTR gdiplusToken;
GdiplusStartup(&gdiplusToken, &gdiplusStartupInput, NULL);
Bitmap MyBitmap(fn);
GdiplusShutdown(gdiplusToken);
return 1;}

which causes

Unhandled exception at 0x73826a6a in ppp_vc.exe: 0xC0000005: Access violation reading location 0x011b227c.

in the function

inline Image::~Image() { DllExports::GdipDisposeImage(nativeImage);}

in GdiPlusBitmap.h

The stack frame dropdown says that this was called by
Gdiplus:Image::~Image() (line 92), which was called by
Gdiplus:Bitmap::Bitmap() + 0x2b bytes, which was called by
the jpgread() shown here.

I was compiling in the mode "align struct elements on multiples of 1".
-------------------
If I remove the line
Bitmap MyBitmap(fn);
the function runs through without error-exiting (but does nothing useful).

I inserted statements giving values to the elements of the struct gdiplusStartupInput, but it still error-exited in Image::~Image().

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Please also, how can I put an existing HBITMAPINFO and HBIPMAP into a `class Image' or `class Bitmap' and then output it to a JPG file?
<div class="ForumMod">modified on Saturday, December 22, 2007 5:58:56 AM</div>

Re: Getting the bitmap in and out of a CGIPLUS Image class

Mark Salsbery22-Dec-07 7:06

Mark Salsbery

22-Dec-07 7:06

Anthony Appleyard wrote:
for(i=0;i<=n;i++) fn[i]=filename[i];

I'm not sure how you got that to compile, but you
need to actually convert the char string to a
WCHAR string before passing it to the constructor.

One way is with the ATL string conversion macros....

#include <AtlConv.h>
...

using namespace Gdiplus;
...

short jpgread (image&I, char*filename)
{
//   int CurY; 

   GdiplusStartupInput gdiplusStartupInput;
   ULONG_PTR gdiplusToken;
   GdiplusStartup(&gdiplusToken, &gdiplusStartupInput, NULL);

   // converts ANSI string to WCHAR string
   CA2W wcharfilename(filename);

   Bitmap MyBitmap(wcharfilename);

   GdiplusShutdown(gdiplusToken);
   return 1;
}

Mark Salsbery
Microsoft MVP - Visual C++
Java | [Coffee]

Re: Getting the bitmap in and out of a CGIPLUS Image class

poda18-Mar-10 19:53

poda

18-Mar-10 19:53

GdiplusShutdown must be called out of scope of the Bitmap object.
The Unhandled exception arise because the GdiplusShutdown function is called
before the Bitmap object is destructed.So define Bitmap object within { }.

<br />
short jpgread (image&I, char*filename)<br />
{<br />
//   int CurY; <br />
<br />
   GdiplusStartupInput gdiplusStartupInput;<br />
   ULONG_PTR gdiplusToken;<br />
   GdiplusStartup(&gdiplusToken, &gdiplusStartupInput, NULL);<br />
   {<br />
      // converts ANSI string to WCHAR string<br />
      CA2W wcharfilename(filename);<br />
<br />
      Bitmap MyBitmap(wcharfilename);<br />
   }//MyBitmap goes out of scope here<br />
   GdiplusShutdown(gdiplusToken);<br />
   return 1;<br />
}<br />
<br />

GDI+ Why does the trick fail, one Rect to two Points

followait21-Dec-07 6:16

followait

21-Dec-07 6:16

Graphis g;
Rect rt;
...
g.TransformPoints(CoordinateSpaceWorld,CoordinateSpacePage,(Point*)&rt,2);

BTW the way, for example, there are two ways to do invalidate:
a. Invalide(FALSE)
b. Calculate a rect to invalidate(calc bound box including a bound box of a rotated rect, and do Rect::Union about 3 times, and with some if...else...),and do InvalidateRect

In OnDraw, only copy a memory Grahpics to the screen.
Which is more efficient?

Re: GDI+ Why does the trick fail, one Rect to two Points

Mark Salsbery21-Dec-07 6:26

Mark Salsbery

21-Dec-07 6:26

followait wrote:
Why does the trick fail, one Rect to two Points

Maybe because a Gdiplus::Rect is a point and a size, not two points.

followait wrote:
Which is more efficient?

I'm not sure what you're asking. The less pixels rendered to the screen,
the more efficient drawing will be. Unless your calculated rect is always
close to the size of the entire window, using method b should always be more
efficient.

Mark

Mark Salsbery
Microsoft MVP - Visual C++
Java | [Coffee]

Re: GDI+ Why does the trick fail, one Rect to two Points

followait21-Dec-07 7:45

followait

21-Dec-07 7:45

about the invaliate question

Because it is a little complex to calculated the rectangle, which needs to be redrawn, also the code became less clear. Here is a sample code:

Rect rt;
if (m_pCtrlBoxSizing) {
    m_pCtrlBoxSizing->GetBoundRect(&rt);
} else if (m_pCtrlBoxRotating) {
    m_pCtrlBoxRotating->GetBoundRect(&rt);
} else if (m_pCtrlBoxMoving) {
    m_pCtrlBoxMoving->GetBoundRect(&rt);
}
Rect::Union(rt,rt,m_HotRt);
InvalidateRect(&CRect(rt.GetLeft(),
    rt.GetTop(),
    rt.GetRight(),
    rt.GetBottom()),FALSE);

or with a simple line

Invalidate(FALSE);

In OnDraw, there is only a bitblt

Re: GDI+ Why does the trick fail, one Rect to two Points

Mark Salsbery21-Dec-07 8:48

Mark Salsbery

21-Dec-07 8:48

Only you can decide what's more important - clear code or
performance. +-10 simple lines of code isn't all that unclear
IMO Smile | :)

Of course, at some point, calculating an update region could
take longer than drawing all the pixels. That's application
specific - you'll have to determine that.

I personally have always got better performance by using update
rects/regions over full redraws. That's in my applications.

Cheers,
Mark

Mark Salsbery
Microsoft MVP - Visual C++
Java | [Coffee]

GDI+ A transformation from world coordinate to page coordinate makes picture foggy

followait21-Dec-07 6:08

followait

21-Dec-07 6:08

Any way to make it more clear?

Re: GDI+ A transformation from world coordinate to page coordinate makes picture foggy

CPallini21-Dec-07 6:49

CPallini

21-Dec-07 6:49

Maybe you need resampling; GDI+ is able to, see, for instance http://www.codeproject.com/KB/GDI-plus/imgresizoutperfgdiplus.aspx[^]

Smile | :)

If the Lord God Almighty had consulted me before embarking upon the Creation, I would have recommended something simpler.
-- Alfonso the Wise, 13th Century King of Castile.

[my articles]

GetUserName() return "SYSTEM" FOR SYSTEM PROCESS

vicky0000021-Dec-07 4:25

vicky00000

21-Dec-07 4:25

For getting the user name in, we are call the GetUserName() in the Application context, in which case we get it right if the Application is launched form logged in user.

But in case of system process GetUserName() return "SYSTEM" as current user.

There is any API or Method to get the current user name in system process?

THANKS IN ADVANCE

Re: GetUserName() return "SYSTEM" FOR SYSTEM PROCESS

myshketer21-Dec-07 5:05

myshketer

21-Dec-07 5:05

Look at regestry
key
HKEY_CURRENT_USER\Software\Microsoft\Windows\CurrentVersion\Explorer
value
Logon User Name

Re: GetUserName() return "SYSTEM" FOR SYSTEM PROCESS

vicky0000021-Dec-07 6:02

vicky00000

21-Dec-07 6:02

the value at HKEY_CURRENT_USER\Software\Microsoft\Windows\CurrentVersion\Explorer

a

Re: GetUserName() return "SYSTEM" FOR SYSTEM PROCESS

Mark Salsbery21-Dec-07 6:35

Mark Salsbery

21-Dec-07 6:35

myshketer wrote:
HKEY_CURRENT_USER

How will that work from a service running as a different "user"?

Mark

Mark Salsbery
Microsoft MVP - Visual C++
Java | [Coffee]

Re: GetUserName() return "SYSTEM" FOR SYSTEM PROCESS

Mark Salsbery21-Dec-07 7:44

Mark Salsbery

21-Dec-07 7:44

For systems with fast user switching (XP+) where more than one user
can be logged on at the same time, maybe something like this:

#include <WtsApi32.h>  // link to WtsApi32.lib
...
DWORD dwSessionId = WTSGetActiveConsoleSessionId();
if (0xFFFFFFFF != dwSessionId)
{
    LPTSTR pUserNameStr = 0;
    DWORD dwBytesReturned = 0;

    if (WTSQuerySessionInformation(WTS_CURRENT_SERVER_HANDLE, dwSessionId, WTSUserName, &pUserNameStr, &dwBytesReturned))
    {
        // ... use pUserNameStr ...

        WTSFreeMemory(pUserNameStr);
    }
}

Mark

Mark Salsbery
Microsoft MVP - Visual C++
Java | [Coffee]

Use Ctrl+Left/Right to switch messages, Ctrl+Up/Down to switch threads, Ctrl+Shift+Left/Right to switch pages.