* non-editable textviews no longer draw the caret
* the cursor keys scroll immediately, not only when the (invisible) caret
reaches the views bounds
* HOME/END work more reliably
* any selection stays active throughout keyboard navigation
Tested with AboutSystem, Mail, StyledEdit and Beam - seems to work ok
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30756 a95241bf-73f2-0310-859d-f6bbb57e9c96
allowing optional prepending of a string to the symbol names.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30750 a95241bf-73f2-0310-859d-f6bbb57e9c96
the "files" is, the actual bitrate of the CD is higher because of error
correction).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30749 a95241bf-73f2-0310-859d-f6bbb57e9c96
determine (or guess) Haiku version and ABI and use those for compatibility
decisions.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30747 a95241bf-73f2-0310-859d-f6bbb57e9c96
I've found it pretty silly that the Keymap preflet would document all my
keypresses although I'm doing something elsewhere
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30745 a95241bf-73f2-0310-859d-f6bbb57e9c96
they only cannot be launched anymore once you acknowledge that request.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30744 a95241bf-73f2-0310-859d-f6bbb57e9c96
- Added it to the image.
- Anyone wants to come up with an icon for it? :)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30736 a95241bf-73f2-0310-859d-f6bbb57e9c96
* fixed a couple of issues with respect to internal/external naming of
keymaps and the respective files, hopefully such that there's always one
keymap active in the view: either one that has been selected or (Current)
if any changes have been applied
* replaced the dead-key-menubar with a menufield (thanks Axel, looking much
better)
cleanup:
* removed remnants of Use-button (message constant and switch-case)
* dropped 'Save' menu item, as it wasn't implemented anyway and would now
never be enabled
* removed fFirstTime, as it caused problems, but did not serve any purpose
anymore
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30734 a95241bf-73f2-0310-859d-f6bbb57e9c96
get the old shutdown dialog back, but with the additional option to reboot
instead.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30731 a95241bf-73f2-0310-859d-f6bbb57e9c96
and the kernel read those values from the shared object (if available). In the
runtime loader this should eventually replace the gcc version guessing method
currently used (at least for shared objects built for Haiku). The optional
packages need to be rebuilt first, though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30729 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added missing macro B_HAIKU_VERSION. Also added a version macro for alpha 1
-- it doesn't seem unlikely that the API will change between alpha 1 and R1.
* Added new macro B_HAIKU_ABI indicating which ABI is used (gcc 2/4).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30727 a95241bf-73f2-0310-859d-f6bbb57e9c96
parent.
* Additionally, when a vnode is deleted, the new BaseDevice::Removed() method is
called that will remove the device from its parent if needed, and delete it
then.
* This should fix#3856.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30726 a95241bf-73f2-0310-859d-f6bbb57e9c96
mentioned that they tend to forget pressing it (including me, of course), in
effect losing all changes.
The way the code currently works, having it didn't really make sense IMO,
as any change will only ever be applied to the "current" keymap. If you want
to keep your keymap more persistently, you need to save it into a named file,
anyway.
Please give it a try and shout if this is unacceptable.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30723 a95241bf-73f2-0310-859d-f6bbb57e9c96
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
