nowhere, we still want to be able to automount them, even though the
notification is not for a device.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30720 a95241bf-73f2-0310-859d-f6bbb57e9c96
* During boot, the mount mode was ignored for any removable volumes, they
simply got mounted always.
* When automounting later, all partitions on all removable devices would
be mounted, not only the ones on the newly inserted device.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30719 a95241bf-73f2-0310-859d-f6bbb57e9c96
offering two choices for acute and diaeresis as well as allowing to switch
off each dead key completely.
* moved the textview on a line of its own such that the dead key menu and
the modifier-switching button live together on one line
* added enum dead_key_index and used it at a couple of places instead of
having to use the magic numbers 1-5
* refactored the actual updating of the fChars buffer from SetKey() into
_SetChars(), which is now being invoked by SetDeadKeyTrigger(), too
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30718 a95241bf-73f2-0310-859d-f6bbb57e9c96
bypassed, same for invoking "Mount All". Now, the "initial scan" parameter
is used to decide if the user should be alarmed. Basically, it means you
get to decide for every mounted volume if you want it rather read-only.
In the old code:
- If you wanted a stick mounted read-only, you had to go to "Tracker Settings"
and disabled auto-ejecting, unmount the stick, then re-mount to get it to
ask you for read-only mounting.
- But then, it would remember this setting, so when you unplugged the stick
and then replugged it, it would mount it read-only again. This may be nice
for later, but for now, I want to decide if I am willing to take the risk
each time.
* The new code also has the implication that when you plug a drive with more
than one partition, you are being asked for each one. I extended the alert
to also mention the partition name.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30716 a95241bf-73f2-0310-859d-f6bbb57e9c96
finishing transfers. The host controller might still be using some of those
structures. In the (unlikely) case that a freed memory chunk would be
immediately re-used and filled with new values this would lead the controller
to either find invalid values and assert a process error or it could follow
invalid list links leading to host system errors. We have to wait with freeing
until the controller processing the next frame to make sure this cannot happen.
The unlikely case should also have been the cause of bug #2481.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30714 a95241bf-73f2-0310-859d-f6bbb57e9c96
* This also paves the way for a different way to handle transfer freeing.
* Also fixes that errors in reappending would previously not be propagated to
the caller.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30712 a95241bf-73f2-0310-859d-f6bbb57e9c96
again. Especially not because it'd likely fail because we are now most probably
in the kernel.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30711 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Use those to make sure the size is retrieved correctly in all cases (which
it wasn't in the short packet tests).
* Don't detect short packets for control transfers as we need the status packet
to finish the transfer and cannot quit earlier.
* Only check for short packets when we also have the short packet flag set.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30710 a95241bf-73f2-0310-859d-f6bbb57e9c96
Fixes using the HDA driver with frame rates based on 44100Hz.
* Automatic white space cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30704 a95241bf-73f2-0310-859d-f6bbb57e9c96
for the third time. :P
- Implement CDDBServer class.
- Include relevant CDDB commands.
- Initial processing of CDDB data. Change device name.
This is close to be complete but I hit some cdda-fs bugs that need to be fixed
before I will finish this.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30703 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Copied ide_adapter.h as ata_adapter.h in attempt to further
separate the two stacks.
* Continued renaming stuff in drivers/bus/ATA.h
* Make all the busses/ata drivers include the new headers,
specifically ata_types.h, ata_adapter.h and bus/ATA.h,
they were all including ide_types and bus/IDE.h still
* Some renaming of global variables for coding style consistency
* Removed the promise driver from the build, it's not used on the
image and I don't believe it compiled even for the old IDE stack.
* There is no more Command Queueing in the new ATA stack, so I
removed the capability indication from the busses/ata drivers
and ata_adapter.h.
The new ATA stack still boots fine on my computer and I proof-read
the diff like two times. Basically, this was a careful search&replace
job only. The only things I am not sure about is renaming some
publishing related strings, but it seems to all work fine.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30700 a95241bf-73f2-0310-859d-f6bbb57e9c96
* fDragKey must be reset in MouseUp() as otherwise it is not possible to
drag a key from one keymap to the textview and then from the textview to the
same key of another keymap
* _HandleDeadKey() now ignores modifier keys as otherwise dead keys that
required pressing a modifier (like the tilde on the German keyboard) failed
to highlight the resulting characters
What's still missing is a way to edit the resulting characters for each dead key, but I am not yet sure how to do that in an elegant way
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30699 a95241bf-73f2-0310-859d-f6bbb57e9c96
Keymap preflet:
* obscure the cursor only if the textview has the focus
* initiate a drag not only if the cursor has moved to another index, but also
when the cursor has moved more than three pixels, since otherwise it was
impossible to drag the first character to the left or top of the view
(as the corresponding index was always zero)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30698 a95241bf-73f2-0310-859d-f6bbb57e9c96
so someone using it to trigger evaluation is highly unlikely, since he can
just press return/enter. But when DeskCalc is embedded into the Desktop, it
is convenient to clear the text view. (Clicking anywhere in DeskCalc already
gives the text view focus.)
* Automatic whitespace cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30697 a95241bf-73f2-0310-859d-f6bbb57e9c96
themselves in busses/ata instead of busses/ide.
* Re-introduce Francois change to install these drivers in busses/ata
when building with HAIKU_ATA_STACK = 1.
* Adopted the device manager to look for drivers in busses/ata
additionally to busses/ide.
This change works fine with a clean installation on a computer where I can
(and indeed have to) use the new ATA stack.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30695 a95241bf-73f2-0310-859d-f6bbb57e9c96
every code has been moved to and adopted in the new Disk Device API backend.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30692 a95241bf-73f2-0310-859d-f6bbb57e9c96
This make the end key work (trigger the scroll) if the last item is overlapping the bottom boundary.
This fixes bug #1820.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30689 a95241bf-73f2-0310-859d-f6bbb57e9c96
ResizeAllColumnsToPreferred().
* Automatic white space cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30683 a95241bf-73f2-0310-859d-f6bbb57e9c96
- When guessing the initial thread state for an unschedule event also check
the previous event, so we can decide whether the thread is still ready.
Previously the time to the first schedule event could be accounted
incorrectly.
- Made the main loop a bit more robust with respect to unexpected thread
states.
* The check boxes for latency and preemption time were labeled the wrong way
around.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30680 a95241bf-73f2-0310-859d-f6bbb57e9c96
For some reason, it was resizing the window to the size of the dragger frame :-) (the frame variable was reused to a different purpose)
Fixes ticket #3896
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30679 a95241bf-73f2-0310-859d-f6bbb57e9c96
-> Significant speed up, since there is much less app_server communication.
-> Much improved looks, since the line is now drawn as one connected line.
The StrokeLine(BPoint to) version cannot do this.
Hope I am not interfering, Ingo!
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30676 a95241bf-73f2-0310-859d-f6bbb57e9c96
publish themselves in busses/ide, so you cannot just move them to busses/ata
without changing that in the source as well. The object files are still built
in the separate busses/ata under generated.
* src/system/kernel/device_manager/device_manager.cpp also hardcodes
busses/ide in two places.
I tried changing all of this to add busses/ata, but my system remains
unbootable with the new ATA stack. I do have another system, and because
of the previous mixup in HaikuImage, there it installed the drivers in
busses/ide when building for the new ATA stack (by mistake), but those
drivers actually publish themselves in busses/ide, so this system actually
boots with the new ATA stack, because of the mixup. Therefore My change here
to install into busses/ide for either stack should be correct for now and should
actually fix building the *old* stack.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30671 a95241bf-73f2-0310-859d-f6bbb57e9c96
