it should be renamed to do_owner_and_lock_check().
Removed looper locking again, since it's not needed, then. Thanks to
Adi for the hint.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12743 a95241bf-73f2-0310-859d-f6bbb57e9c96
communication, the port's reply port is no longer sent to the app_server (as it
knows where to reply to, anyway).
Also made sure the view's looper is locked while getting the coords - I guess
BPortLink doesn't like to be written to from two different threads :-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12742 a95241bf-73f2-0310-859d-f6bbb57e9c96
for the default button does), but at least, the window itself is updated now :-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12739 a95241bf-73f2-0310-859d-f6bbb57e9c96
Added some preferences applications to the image. Some of them even start
(DataTranslations, Keyboard), most will bring down the app_server, or miss
libtracker.so.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12735 a95241bf-73f2-0310-859d-f6bbb57e9c96
install interrupt handlers in init_driver().
The downside of this is that you can now only use F12 to drop into
the debugger when the console appeared (not before).
This way, the driver no longer causes ps2_hid to not be able to
disable or enable the keyboard (which means you can keep them both
installed without worries).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12732 a95241bf-73f2-0310-859d-f6bbb57e9c96
- there can only be one _UPDATE_ message at a time in the queue so we
can stop searching after we hit the first one
- mouse coordinates are always send in screen coordinates (unlike R5,
which means this is a compatibility problem), so we need to convert
them even for the current view.
Apps should now work with the old synchronous controls method (even
though their drawing updates look clumsy and are slow compared to
asynchronous controls for whatever reason).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12730 a95241bf-73f2-0310-859d-f6bbb57e9c96
Not yet used, though - we probably need to rearrange the source files a bit.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12727 a95241bf-73f2-0310-859d-f6bbb57e9c96
myriad of small bugs here and there, as well as some very odd coding techniques:
- the "Minimize" property was not handled
- the "Minimize" property was not settable
- the property/scripting stuff was horrible, anyway
- there are more and better error codes than B_ERROR (could someone tell the
app_server guys? :))
- added some ToDo items here and there
- and much more I don't remember
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12723 a95241bf-73f2-0310-859d-f6bbb57e9c96
messages from the port.
BView::GetMouse() now calls this function if it was called from the window's
thread and thus blocking the message loop.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12716 a95241bf-73f2-0310-859d-f6bbb57e9c96
just those before the first mouse message.
This should be more correct and look better.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12715 a95241bf-73f2-0310-859d-f6bbb57e9c96
- it returned on _UPDATE_ messages without a mouse position
- it no longer calls DispatchMessage() for everything anymore,
however, it will still call BWindow::DispatchMessage() directly
for _UPDATE_ messages
- it didn't care for B_MOUSE_DOWN messages
- it didn't unlock the queue in case it found a message.
(this message actually reflects the differences to r12683 of this
file, but the newer one r12705 was even more broken, but in other
ways)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12714 a95241bf-73f2-0310-859d-f6bbb57e9c96
Looks like that, when called with "true" as third parameter,
it "eats" all the input messages like B_MOUSE_UP/B_MOUSE_MOVED. That means our implementation isn't correct.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12699 a95241bf-73f2-0310-859d-f6bbb57e9c96