the listview use all the available additional size. But works far better
than before.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28708 a95241bf-73f2-0310-859d-f6bbb57e9c96
now resize with the tab view. There is probably a more elegant way overriding
DoLayout(), but this should do for the time being.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28706 a95241bf-73f2-0310-859d-f6bbb57e9c96
* The BTabView can now be used with layout management. In this setup, children
views are managed by a BCardLayout and are hidden/shown instead of removed/
added when (de)activated.
Thanks a lot!
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28701 a95241bf-73f2-0310-859d-f6bbb57e9c96
to a window already. If not, we fall back to using the BList-based search.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28696 a95241bf-73f2-0310-859d-f6bbb57e9c96
take advantage of this fact to make use of binary search in
IndexOf(BListItem *), rather than using BList's linear search.
Also use this mechanism to speed up HasItem(BListItem *).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28694 a95241bf-73f2-0310-859d-f6bbb57e9c96
popup menu that hasn't yet been completely dismissed, it's possible to hit a
debugger call because the menu's view tries to add itself to the menu window
before the previous menu instance has removed it. This was quite easy to
hit with things like BColumnListView's column title context menu, since there
is no notification for when the menu was dismissed without invoking an item,
and thus double right clicking quickly enough would hit the debugger. Go()
now checks if the menu's tracking thread is still up, and if it is, waits for
it to go away before trying to start another instance. Fixes ticket #3146.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28693 a95241bf-73f2-0310-859d-f6bbb57e9c96
otherwise if it tries to make use of any positional information in the
subsequent call to Update() (i.e. calls to ItemFrame(), or Top(), it will
get back bogus coordinates. This should correctly fix the problems seen with
Themes, possibly amongst others.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28692 a95241bf-73f2-0310-859d-f6bbb57e9c96
- "correcting" the offset to 0 is not what should happen.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28688 a95241bf-73f2-0310-859d-f6bbb57e9c96
listeners immediately if there was already something in the queue. Factored
out a tty_readable() out of tty_notify_if_available() that tty_select()
now uses.
* This fixes bug #3148.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28687 a95241bf-73f2-0310-859d-f6bbb57e9c96
* check specific node ids for nodes declared as inputs which are really beepers
* when unmuting/setting amp on the input amplifier, iterate on each input instead of only the first one
* also unmute/set amp on the output and input amplifiers for the input and output paths, respectively
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28683 a95241bf-73f2-0310-859d-f6bbb57e9c96
I'm not sure how this affects the build as I still got a valid image and only
saw the MIME error after Joseph pointed it out. In fact I am quite sure the SGI
MIME type was still in the build. I assume that only the broken sniffer rule
was missing.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28681 a95241bf-73f2-0310-859d-f6bbb57e9c96
for. This allows snippets from ShowImage made in these formats to be opened.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28680 a95241bf-73f2-0310-859d-f6bbb57e9c96
We now ask the app_server for the window tab's height instead of
hardcoding it.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28678 a95241bf-73f2-0310-859d-f6bbb57e9c96
worked because (status_t)B_OK == (off_t)0.
* The translator_id version of Translate() does a (probably unnecessary?)
Identify(), but then forgets to seek the source BPositionIO back to 0
before calling translator's Translate(). This was the reason for none of
the WonderBrush Translation Kit export formats to work.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28676 a95241bf-73f2-0310-859d-f6bbb57e9c96
broke everything. If the added item has no chance to calculate it's height,
_RecalcItemTops() won't work of course. Whatever this was supposed to fix,
there has to be a correct way.
* Override BView::SetFont() to update all the items. I remember wanting to
implement this, that's why I refactored a _FontChanged() method, but I
obviousy never did...
* Moved the AttachedToWindow() and FrameMoved() implementations to a more
logical position in the file.
* Implement B_PAGE_UP/DOWN key presses. Don't know if that's what the BeOS
implementation did, will check later.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28671 a95241bf-73f2-0310-859d-f6bbb57e9c96
values. The implementation needs to sum up fractional movement, not
truncate to zero. Before this change, the mouse would be pretty much unusable
at lower speeds/acceleration. Now it is guaranteed to move.
* No need to memset() before ioctl(), the driver does that anyways.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28669 a95241bf-73f2-0310-859d-f6bbb57e9c96
DataTranslations list view. This should fix it. MessageReceived() was not
forwarding to the immediate inherited class.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28665 a95241bf-73f2-0310-859d-f6bbb57e9c96
a message.
* The DesktopSettings class is now using that to send the new
AS_SYSTEM_FONT_CHANGED message to all windows.
* The ServerWindow now propagates font changes to its decorator, causing it
to update its drawing. That means changing the bold font in the "Fonts"
preferences application will instantly change all window titles.
* Factored out a _RebuildAndRedrawAfterWindowChange() out of several Desktop
methods, simplifying some code.
* The DefaultDecorator no longer calls _DoLayout() twice (through SetLook()),
but instead calls the new _UpdateFont() method now also called by
FontsChanged(), and SetLook().
* BWindow::GetDecoratorSettings() now also includes "tab frame" BRect with the
exact footprint of the tab, allowing apps to know the size of the tab to
position itself accordingly.
* Automatic white space cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28664 a95241bf-73f2-0310-859d-f6bbb57e9c96
it to the stream. This caused Read()/Write() to need two syscalls for nothing
(this only caused the actual stream to share the same position with the
BBufferIO, something you just cannot rely on when using buffered I/O).
* Anyway, this reduces the time VirtualBox needs to open some RAW test images
from over 4 minutes to less than 15 seconds...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28662 a95241bf-73f2-0310-859d-f6bbb57e9c96
It's getting annoying having to maintain so many identical driver lists... maybe those should be factored out in some way...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28654 a95241bf-73f2-0310-859d-f6bbb57e9c96
