Also note that BeOS doesn't seem to pick up the cursor this way, it only
works when we're doing this later (ie. in MouseMoved() or Pulse()).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16959 a95241bf-73f2-0310-859d-f6bbb57e9c96
Note, it looks like we translate the cursor shape differently than R5
(according to the docs, black is always opaque and ignores the transparency
bits).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16958 a95241bf-73f2-0310-859d-f6bbb57e9c96
it and rebuilding it on the server side (that causes a huge speed
up for regions containing many rects)
* There is a method in ServerLink that could have been used, but I
actually needed to add the direct BRegion support to LinkReceiver
* added LinkReceiver as a friend to BRegion class
* ServerApp and ServerWindow keep the CursorManager locked after they
have retrieved a cursor until they have called Acquire() on the
cursor. (Axel: what good is using atomic* stuff in Acquire() and
Release() if we have to protect this by a lock anyways?)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16957 a95241bf-73f2-0310-859d-f6bbb57e9c96
it only cures the symptoms, ie. bug #194 remains valid (broken file types when built
from Linux).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16954 a95241bf-73f2-0310-859d-f6bbb57e9c96
a window is closed, too (only happened when a new window was shown
before). This is done via the new Desktop::_SendFakeMouseMoved()
method. This fixes bug #342.
* The MouseFilter now always sets Desktop::fWindowUnderMouse, so that
one can differentiate between no window under mouse, and decorator
under mouse.
* EventDispatcher::SendFakeMouseMoved() now expects a BMessenger instead
of an EventTarget as target - this guarantees that it can safely be
called with any window now (instead of only the current window).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16953 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Implemented the functions needed by ideinfo/idestatus using this one.
* The IDE bus manager now disables DMA if the safemode settings ask for this.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16944 a95241bf-73f2-0310-859d-f6bbb57e9c96
The best font size for speed is now dynamically computed to fit too.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16933 a95241bf-73f2-0310-859d-f6bbb57e9c96
This fixes bug #360.
* Also removed no longer necessary undefining of _KERNEL_MODE, as we're now built
correctly.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16930 a95241bf-73f2-0310-859d-f6bbb57e9c96
- made 'active' variable volatile
Bugfixes:
- fixed deletion of mouse_device from fDevices list when the object is deleted.
- removed deadlock from RemoveDevice
- call UnregisterDevice from inside RemoveDevice
- terminate devicer watcher thread on read error
- skip "serial" directory always
- close file handle when initializing device watcher thread fails
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16927 a95241bf-73f2-0310-859d-f6bbb57e9c96
- keyboard_device now frees device_ref.name by itself when it's deleted
- made 'active' variable volatile
Bugfixes:
- delete keyboard_device from fDevices list when the object is deleted.
- removed deadlock from RemoveDevice
- call UnregisterDevice from inside RemoveDevice
- terminate devicer watcher thread on read error
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16926 a95241bf-73f2-0310-859d-f6bbb57e9c96
Right now, the size of the device is ignored in the second pass. Maybe this helps
with bug #357.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16917 a95241bf-73f2-0310-859d-f6bbb57e9c96
helpful but extensive comments in the code.
* Fixed possible wrong error values of LockLooperWithTimeout().
* AddFilter()/RemoveFilter() now check if the looper is locked in case this
handler belongs to a looper - as SetFilterList() already did.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@16911 a95241bf-73f2-0310-859d-f6bbb57e9c96
