Win32 look nasty, how to make it look better by custom skins?
I mean something like Adobe products, iTunes, Autodesk 3dsmax and Softimage XSI, Windows media player, Blender, Comodo firewall, Winamp, Babylon client, and few download managers etc.;
there are many similar applications out there but I can't find any proper tutorial or guideline, it looks like secret recipe!
only -two- tutorials available online:
old and useless: http://www.codeproject.com/Articles/20497/Draw-Skin-Window-Using-Pure-Win32-API
only cover opaque background (and this is what I avoid, I need more about GUI components):
http://www.flipcode.com/archives/Win32_Window_Skinning.shtml
Is there any book or proper guideline to learn how to build skins for Win32api?
Edit: I accept David Rodríguez comment, down there ↓↓
I have done this before using C++ Builder. The approach I took was to create a form, set it to be borderless and color the entire form the same color. Then I set the form transparency to this color. I then add images to the form which create the desired skin.
I'm sure this can all be done through standard win APIs, but I can't describe (or advise) doing it solely through API calls.
The operating system handles "skinning" for you automatically.
In "classic" mode (or Windows 2000 and earlier versions), this gets you a, well classic-looking interface. The windows are drawn just like they always were since Windows 95. Presumably, this is what you are referring to when you say that "Win32 look nasty". However, you need to realize that many people like this look and specifically choose to enable it on their machines. [WARNING: Personal opinion coming up!] I'm one of those people, and judging from the screenshots that get posted here from developers' machines, I'm definitely not the only one.
Windows XP actually introducing the "skinning" or theming engine, which lives in a set of Windows DLLs. By explicitly linking to version 6 of ComCtl32.dll, your application would automatically get these visual effects. Some people said this version of Windows looked "Fisher-Price", while others were perfectly happy with the term "gaudy". The option was retained to allow the user to switch to the "classic" theme (as described above), if desired.
Windows Vista completely overhauled Windows's theming engine and introduced a new UI known as "Aero". This provides flashy-looking windows and controls, complete with transparency effects—that is, as long as your graphics card supports it. Again, by explicitly linking to version 6 of ComCtl32.dll, your application would automatically get all of these styles applied.
It's worth noting that through all of this, Microsoft has provided users with the ability to customize the colors (and fonts and other things) used in the user interface. For example, Aero defaults to blue. If you don't like blue, you can change it. I change my UI colors periodically for fun and to re-energize myself. If you can't read or don't like the font, you change it, too.
Thus, if you choose to do something different with your application, defining your own custom color palette and ignoring the options chosen by the user through the provided customization interface, your app is going to look broken and stick out like a sore thumb on the user's desktop. When designing a UI, the last thing you want to do is to be or look different.
In short, upgrade your computer to Windows Vista or later and enable the Aero interface if you want flashy. Don't override the user or try to custom draw all of your controls. You'll just end up with an application that is hard to use, doesn't work as expected, is a pain in the rear to maintain, and just generally looks worse than if you'd simply left it alone.
Related
I'm making a GUI application in C++.
Is there a simple way to make the narrator of windows 10 to speak some text ?
Given of course that it is currently active.
A trick that sometimes works is to select some text in a text field and then focus it briefly. But
It doesn't work all the time
The focus is moved out and back. Even if it's for a short time, it's invasive and may disturb whatever the user is currently doing
The text field must be present at some place on screen, what is not always desired
If possible, I would like a solution without these three issues.
Other screen readers, in particular Jaws and NVDA, provide API to do this.
I'm even the author of a library, UniversalSpeech, which allow to make the currently running screen reader, if any, to speak text, abstracting the need to detect yourself which one is running.
Given that the narrator has greatly improved with the last 3 or 4 releases of windows 10, it would probably be interesting to support it, not only in my own program and for my particular usecase, but for everybody in my library.
However, I can't find any documentation or anything telling me if the narrator has an API similar to those of Jaws or NVDA.
In fact if there is currently no such API for Narrator, it would probably be interesting to suggest Microsoft to add one.
Note that this question is different from such as this one
where the answer suggests to use speech API directly. Using screen readers API and not speech API directly has great benefits:
Screen reader users are used to specific voice settings (voice, rate, pitch, language and regional accents, etc.). The default settings set in the control panel may not at all be similar. It implies
whether the user must configure speech settings in the control panel, what is global for all applications; not very good
and/or managing application-specific speech settings in a business application which isn't at all devoted to speech stuff; it would be rather strange to find speech settings in a financial app for example.
Using both screen reader and independent speech engine simultenously means that both can speak at the same time, what is of course extremely annoying. In fact in practice it happens quite often, I have already tested.
So, is there a simple way to make narrator to speak some text ?
My program is in C++, the library is in C, so in theory I have access to the whole winapi, through LoadLibrary/GetProcAddress if needed.
Please don't give any C# or VisualStudio-dependent solution.
Thank you.
After quite a while, I answer my own question !
IN fact, the simplest to make narrator speak something is probably to:
Define some label as being a live region
When something has to be spoken by narrator, change the text in the label and then send an update notification
Turning a label into a live region and sending a notification whenever the text changes is explained here:
https://learn.microsoft.com/en-us/accessibility-tools-docs/items/win32/text_livesetting
Live setting can be set to 0=off, 1=polite and 2=assertive. The meaning of polite and assertive are the same as in WAI ARIA.
Though as present (april 2021), narrator always interrupts speech as soon as the text of the label is replaced, even in polite mode.
What changes in assertive mode is that the text even take priority against interruptions due to normal keyboard navigation, i.e. you may not hear where you are when pressing tab, arrow keys, etc.
For that reason, I don't recommand it at all.
Note also that live setting only works on static text controls (win32 STATIC window class).
It is totally ignored when applied to text fields and text areas (win32 EDIT window class).
The label with live setting still works when placed off-screen or even hidden.
As far as I know, Microsoft Narrator doesn't expose the API for developers, and you can suggest a feature for it using Feedback App on Windows 10.
I want to achieve the same behavior as in a live region, i.e. have some text read by the SR as it appears at the bottom of a multiline rich text field, but in a native GUI app. For info, I'm using WXWidgets.
You can use the UI automation events to subscribe the property change of rich text field so that you can get notified when the text is updated. And since you are using third-party control, you also need to implement providers for any third party controls that do not include a provider. And below are links about UI automation provides and
UI Automation events for your reference:
UI Automation Events Overview
UI Automation Providers Overview
OpenGL is great in creating UI (specially in games) and it is highly portable. Is it unusual that an ordinary (not graphically intensive) application uses OpenGL for its UI? And if not, why? Is it about performance or ease of use?
For example, an Apple developer can use ready to use buttons and sliders, etc provided by Apple; he can also create the UI using OpenGL. The second method makes the code more flexible and portable. Why people don't do this?
Does using OpenGL makes sense if portability is our goal?
There's a lot more to UI than graphics.
As one example fonts. Rendering Chinese, Japanese, Korean, Arabic, Thai in the right directions with the write strokes etc it a TON of work. There are whole teams dedicated to that topic at Microsoft, Google, Apple, Adobe and other companies. If you go straight to GL you're going to have to solve that problem yourself.
Another example, native controls. iOS users expect certain controls to work a certain way. Android users expect something different. For a game that's usually not a problem, games usually have a very unique UI. Apps on the other hand are generally expected to stick to the conventions of their target platform. Generally users get upset when the controls don't match their native platform. Using GL for your UI means you won't get the native controls.
Similarly text editing is a very platform specific feature. Is it drag to select, right click to select, hold to select? What keys go which way, how do they work? Is it Ctrl-V or ⌘-V. All of that is platform dependent as well. You can use the native text editing controls and have the problem solved or you can use GL and have to reproduce not only all the code to edit text but try to make it work the right way on each platform in each configuration. Does your GL text editor handle Japanese keyboards? German Keyboards? Does it handle Input Method Editors for CJK and others?
So, it's more a matter of the right tool for the right job. There are whole UI platforms written on top of GL. Before Metal OSX was probably one of them (or still is?) But if you skip that and build your UI directly on GL you'll end up having to implement all those in-between pieces.
Certainly GL might be the right way to go for certain non-game apps. Paper comes to mind as an app that could be 98% GL and therefore gain portablility. On the other hand Evernote is probably on the far other side. It needs to handle every language, different fonts, input for users with disabilities, etc. All of that is built into the OS, not GL.
Yes, what you suggest is possible. Just have a look at Blender. Blender implements its own UI using OpenGL, for the exact portability reasons you gave.
However there's a lot more to user interfaces than just getting things drawn to the screen. Event management, input handling, interoperability with other applications. All that depends on functions that are not covered by OpenGL.
But there are cross platform application framework libraries, like Qt. And the whole drawing stuff makes only a small portion of what those frameworks do.
One problem you run into when using OpenGL for drawing the GUI though is, that there's a huge variation on the OpenGL profiles supported by the systems out there. It can vary from a mere OpenGL-1.1 software fallback on a old Windows XP machine, over OpenGL-1.4 on Windows Vista machine with only the default drivers installed by the Windows setup, up to OpenGL-4.5 on the same machine once that user installs the proper drivers. And the way you use OpenGL-4.5 is largely incompatible to OpenGL-1.4.
For a UI toolkit written with a OpenGL backend this means that you must implement at least three codepaths: A OpenGL-1.1 variant that uses the fixed function pipeline and client side vertex arrays. A OpenGL-3 compatibility profile. And a OpenGL-4 core profile.
This much more work than just using the OS specific methods, which you have to use anyway to create the window and get user input with.
i work on a Windows CE 6.0 Image and added a Audio driver to my Solution (my solution is based on a image without audio). Sound works fine but i dont know how i can add the standard Windows CE 6.0 Sound Settings dialog to the control panel.
MSDN says the following:
"The Windows CE Control Panel allows users to set a variety of system-wide properties, such as mouse sensitivity, network setup, and the desktop color scheme. You can select specific functionality to include in your Control Panel by specifying them in your Cesysgen.bat file."
Can anyone explain how this works exactly via Cesysgen.bat? In my project i cant find any entry for cplmain in my Cesysgen.bat.
Could it be that those standard Applets are integrated into the control panel automatically? (maybe with "getProcAddress()" when a specific driver is loaded?) - This idea comes from "cplmain.def", there is written:
EXPORTS
CPlApplet
; These functions are exported for componentization
; We use GetProcAddress on ourselves to dynamically discover
; what components we have
I found a quite good explanation from Andrew Pearson here:
http://www.itlisting.org/4-windows-ce-embedded/a57eef4103191b7a.aspx
but i tried a few different things an nothing worked! So this confuses me even more. The only statement there i really understand now is:
The control panel, unfortunately, is about the single most confusing thing
to build in the whole tree.
Yes it is! Would be nice if anyone had an idea.
Kind regards,
Martin
I've created custom control panel applets before, and to be honest, trying to modify the existing applet is about the worst thing you can try. Generally what I do is just create a whole new applet, which is really just a DLL renamed to have a .cpl extension and that exports the CPlApplet entry point.
There's an example in MSDN that shows the expected values the OS will pass in to get your icon, tell you to start and those types of things.
Basically just build your own applet as a completely separate project, then include it in the MODULES section of your BIB file. Don't even mess with the existing train wreck of control panel code.
I have to create something similar to Report Builder and SSRS or Open RPT but for a MFC application.
The idea is to be able to create and edit a template for reports that have to be printed afterwards. I am not confined to using MFC (I am allowed to use C#, QT, etc..), but whatever I use, it has to integrate in a MFC document application and be able to do drag and drop/resize and edit of containers (for example tables, image containers, etc).
There are some options that I considered (but they all seem overkill):
XPS, it allows for easy printing but it does not allow for editing/drag and drop.
DirectDraw, but this seems like a lot of work and I do not know if/how the printing functionality can be implemented.
QGraphicsView from QT, but I am afraid of the complications that can arise because of the integration part.
Are there any components that I can use? It does not have to be free (but that would be nice), but I should be able to integrate it in my application without installing additional software on the clients machine.
Note: I use MFC9 with Visual Studio 2010. And the target PCs have Windows 7 and Windows 8 installed.
All major components vendors have this kind of control in a way or another, my personal choice is DevExpress, but you can also look at Telerik, Syncfusion and others, just be sure that the Report Designer component can be redistributed to your end users.
We have a set of applications that basically display a bunch of bitmaps and text, then allow user to press "buttons" (certain bitmaps) that cause actions to occur.
We currently have these implemented using DirectX and a bunch of code to place the bitmaps and handle the button-presses. But we'd like to have the following features:
portable to Linux
some sort of "editor" that would allow us to lay out screens without hard-coding locations of elements in code
animation
we need to be able to overlay video
not resource intensive (these terminals don't have a lot of memory or CPU)
we're currently using C++, so management would prefer that, but other languages would be considered
We'd prefer a free, open-source solution, but would be willing to buy something if it is not too expensive. (We have a couple dozen developers, and tens of thousands of terminals deployed.)
We don't like the common GUI toolkits or widgets. We want something that has more of the look of a game than of a dialog box.
Any suggestions for off-the-shelf stuff we could use?
Maybe the way to go is something like Clutter or Allegro. If you check in this article at ArsTechnica what they are using Clutter for, you might get an idea how to use it. I don't know for sure if it works on Windows, but I'm pretty sure it does, considering it only depends on libraries that are supported under Windows.
You could try wxWidgets (it has wxBitmapButton) or try to implement your own solution using SDL for all of the graphics.
"We don't like the common GUI toolkits or widgets. We want something that has more of the look of a game than of a dialog box."
You realize that Trolltech's QT has a style sheet language for widgets? Take a look at their white paper, specifically page 60
http://trolltech.com/pdf/qt43-whitepaper-us.pdf
Going over your other requirements:
portable to Linux
Yes. Also supports Windows, Mac, and embedded environments.
some sort of "editor" that would allow us to lay out screens without hard-coding locations of elements in code
Qt's Designer is a very nice tool. I use it all the time.
animation
Qt supports this.
we need to be able to overlay video
Qt supports this.
not resource intensive (these terminals don't have a lot of memory or CPU)
This might be the fly in the ointment. You could check out Qt's embedded option. I've never used that myself.
we're currently using C++, so management would prefer that, but other languages would be considered
Qt is for C++ and works with all major compilers.
We'd prefer a free, open-source solution, but would be willing to buy something if it is not too expensive. (We have a couple dozen developers, and tens of thousands of terminals deployed.)
Qt has both open-source and closed source options.