16 x 16 to 64 x 64).
* Changed the layout code to have dynamic padding depending on main icon size.
* Fixed a problem with the "Auto Raise" feature where, when the pad was along
the bottom, you had to tip the top of the screen with the mouse for the pad
to raise...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28096 a95241bf-73f2-0310-859d-f6bbb57e9c96
new '-u' option, or let it generate one automatically (by building a hash over
the full path of the image).
* This is allows you to use our images in VirtualBox without having to readd
the hard drive with every rebuild.
* Enlarged the description section to 1024 bytes - this also prevents VirtualBox
from writing data beyond the description size.
* Added '-d' option to just dump info about an existing vmdk image file (only
monolithic mode is supported, though).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28093 a95241bf-73f2-0310-859d-f6bbb57e9c96
by tab indents everywhere.
* Remove special handling in map_physical_memory to handle page offset and
length. Opposed to BeOS, Haiku does both automatically.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28091 a95241bf-73f2-0310-859d-f6bbb57e9c96
written on load of the ACPI module.
* Fix waiting for a semaphore. It didn't ever use the timeout because it missed
the B_RELATIVE_TIMEOUT and the timeout value would've been wrong as well
since it didn't convert from milli- to microseconds.
* Do away with the hack of not actually using spinlocks because it apparently
didn't work on Dano. Now normal spinlocks are used.
* Also remove the atomic test and set function that was used for locking.
* Panic in case an interrupt handler is removed, because it cannot (yet) work.
* Use system_time() to instead of using gettimeofday() and converting.
* Fix reading PCI config, the width was used wrongly so nothing was returned.
* The physical memory read/write function didn't actually do anything or would
at worst have accessed unmapped memory. It now uses a bit of private VM
functionallity to actually implement reading and writing physical memory.
* Some style cleanup, more to come in the next commit.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28090 a95241bf-73f2-0310-859d-f6bbb57e9c96
* When the consumer does not want to consume a glyph, make
sure the advance values are being reset before breaking out of the
loop. These are used one more time after the loop.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28083 a95241bf-73f2-0310-859d-f6bbb57e9c96
gen_mattypes build tool, as the latter will try to use BeOS headers on BeOS
compatible host platforms and therefore breaks the build because of missing
files. This should work on all platforms, as with that the headers in the
repository are always used.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28076 a95241bf-73f2-0310-859d-f6bbb57e9c96
- handle line feeds
- warn when text is too long
- better control points, but it's still not correct
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28072 a95241bf-73f2-0310-859d-f6bbb57e9c96
* BlockAllocator::AllocateBlocks() was implemented pretty crappy: instead of
just remembering the best run on the first pass, it made a second pass through
all allocation groups when it couldn't fulfill the maximum request.
* Even worse, it would then also only allocate the first run that satisied the
minimum request. Now, it will always choose the best allocation, leading to
less fragmentation, and an improved runtime.
* Now mmlr hopefully won't need to wait 10 minutes for the bloc allocator to
create the swap file on his fragmented volume...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28071 a95241bf-73f2-0310-859d-f6bbb57e9c96
mounting by name failed).
* Also left some TODO comments in the code.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28069 a95241bf-73f2-0310-859d-f6bbb57e9c96
and will only show the "mount me read-only?" dialog when the file system
actually supports writing in the first place.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28067 a95241bf-73f2-0310-859d-f6bbb57e9c96
- handle dropped/pastes text as shapes with path (and style when with text_runs from StyledEdit)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28064 a95241bf-73f2-0310-859d-f6bbb57e9c96
Reimplemented the drag message over the team entries dragging. The previous
implementation used the menu bar tracking by faking a B_MOUSE_DOWN event. The
problem was that in Haiku menus are always sticky and therefor the tracking
thread was not exited when the user released the mouse (which was supposed to
trigger the drop event in the Deskbar). The new implementation follows the
drag in the asynchronous mouse hooks and uses it's own selection state in
TTeamMenuItem to highlight the eventual drop targets.
Fixes #2771.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28063 a95241bf-73f2-0310-859d-f6bbb57e9c96
Fixed a problem with dispatching B_MOUSE_MOVED messages to views which need
the transit event:
* If the app_server decided to send a B_MOUSE_MOVED to the previous mouse
containing window, it forgot to add the _feed_focus flag, which was a problem
if the message actually happened to contain tokens (views that registered
for events.) On the client side, only those views would receive the message,
while the regular last mouse moved view would not be notified at all.
* On the client side, never change fLastMouseMovedView if the message is not
targeted at the preferred handler. In the above situation, any "registered
for events views" would receive the message first, but viewUnderMouse would
be NULL and then when the regular last mouse moved view received it, it
resulted in the wrong transit (B_OUTSIDE_VIEW instead of B_EXITED_VIEW).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28059 a95241bf-73f2-0310-859d-f6bbb57e9c96
shows a bug in the app_server event dispatching which is going to be fixed
next.)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28058 a95241bf-73f2-0310-859d-f6bbb57e9c96
file system can write to files before mounting.
* Set the flag for all file systems that actually can write.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28055 a95241bf-73f2-0310-859d-f6bbb57e9c96
disk device API, and if that is the case, it will use the private
BFS_IOCTL_UPDATE_BOOT_BLOCK ioctl to update the boot code.
* Fixed inconsistent naming of "Bootcode" vs. "BootCode".
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28054 a95241bf-73f2-0310-859d-f6bbb57e9c96
the methods IsFile() and GetFilePath() to BDiskDevice, and
BDiskDeviceRoster::GetFileDeviceForPath().
* Added new syscalls to implement this functionality.
* Added new flag B_DISK_DEVICE_IS_FILE.
* Fixed wrong operator precedence assumption in the BDiskDevice class at
several places.
* Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28052 a95241bf-73f2-0310-859d-f6bbb57e9c96
* added opengl to build be api headers
* define USES_BE_API for gen_matypes
this should fix the build for Linux which don't provide GL headers :)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28050 a95241bf-73f2-0310-859d-f6bbb57e9c96
