The method was called after _sending_ all the messages, not after receiving
them all. This fixes the scroll validity check in AddPosesCompleted in list
mode (bug mentioned in my last commit).
We can now close#2441, tracker windows should now be completely persistant
with regard to scrolling now, in all modes (spatial mode, single window
mode in list or icon mode). \o/
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28210 a95241bf-73f2-0310-859d-f6bbb57e9c96
list mode) or switching dir in single window navigation. Fixes the other half of the problem in #2441. Left some
todos.
I discovered an other bug that can add a random offset after finishing adding poses.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28205 a95241bf-73f2-0310-859d-f6bbb57e9c96
selected item which does not make much sense. Disabled the checkmark.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28201 a95241bf-73f2-0310-859d-f6bbb57e9c96
* fixed LineHeight() for the case when the textview does not yet contain
anything - instead of returning 0 we now return the lineheight of the
default style (or the textview's font).
Fixes#2231
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28194 a95241bf-73f2-0310-859d-f6bbb57e9c96
bool return type. Did I mention this was an unstable Haiku extension?
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28181 a95241bf-73f2-0310-859d-f6bbb57e9c96
of taking the contents of the columns, it would always use the file name
instead.
* That uncovered another bug, though: WidgetText::Text() tried to cast everything
to StringAttributeText, but GenericAttributeText is actually used for most
columns.
* Therefore, GenericAttributeText is now a subclass from StringAttributeText.
* Extended the type ahead to take other columns into account, and made it also
find strings in the middle (like a filter) as a second choice.
* Whitespace cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28180 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Improved the naming of the menu entry that removes a replicant from a shelf
to be less frightning.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28177 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added a new class BAffineTransform, currently in the BPrivate namespace
and the inofficial "shared kit".
* Extended BPolygon to be transformable by a BAffineTransform.
Thanks a lot!
Minor fixes by myself:
* The class accidentally still derived from agg::trans_affine.
* Added then missing comparator operators.
* Swapped the BPoint* and count arguments of Apply(), since that seems
to be the more common order in the other Be API.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28176 a95241bf-73f2-0310-859d-f6bbb57e9c96
the data of two BMessages and allows recursive comparison (BMessage inside
BMessage). Note that using this API might require you to recompile your app in
the path to R1.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28174 a95241bf-73f2-0310-859d-f6bbb57e9c96
successfully loading the saved state. Reworked the logic to make that work properly (this also needed checking if the state read succeeded). This
fixes part of #2441. There is still an issue when sometimes the view state is not saved properly, more tomorrow!
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28158 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Fix the calculation of the fTextRect member. The BeOS behavior (and also the
previous Haiku behavior) was to recalculate the "bottom" always. This was not
taken care of in SetTextRect() (needs to override the passed bottom).
* The insets are already tracked in fLayoutData, use this in
_UpdateScrollBars() to calculate the correct data width/height (an
improvement over the BeOS behavior it seems).
* Try to minimize the need to call _Refresh(), which reduces flickering a whole
lot.
* Fix several instances where fTextRect was recalculated based on Bounds() and
the saved insets, where it was broken when the BTextView was scrolled.
Fixes#2784.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28151 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Resolved TODO: The type of the gradient is no longer encoded twice in the
app_server link protocoll.
* Moved instantiation of the BGradient into the LinkReceiver::ReadGradient()
method.
* Check success for (at least) ReadGradient() in ServerWindow.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28150 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Fixed a general problem with respect to overriding of the reserved
virtual function slots: instead of statically invoking the method
that corresponds to the reserved slot on the class that contains the
slot, we now invoke the virtual Perform() method. Perform() then dispatches
the method invocation to the "proper" class, i.e. the highest class in the
hierarchy that actually implements the requested method.
This fixes a crash in apps that use liblayout's MSlider class and
should fix one or other spurious bug with old apps or libraries, too.
* added new header folder 'binary_compatibility' that contains files that
define the method codes and data structures required by Perform()
* looked for and implemented all used reserved virtual slot functions to
invoke Perform() where necessary or to pass on the method call statically
(for slots that were already maintained by Be)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28124 a95241bf-73f2-0310-859d-f6bbb57e9c96
wrong version of ConvertFromScreen() was now used, resulting in the calculation
being computed and thrown away. This broke BMenu, probably amongst other things.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28118 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Implemented BGradient, BGradientLinear, BGradientRadial,
BGradientDiamond, BGradientConic and BGradientRadialFocus
new Interface Kit classes.
* Implemented all the (AGG-based) backend necessary in
the app_server to render gradients (Painter, DrawingEngine)
* app_server/View can convert a BGradient layout to screen
coordinates.
* Added BGradient methods of the Fill* methods in BView.
* Implemented a test app and added it to the image as a
demo.
* Adopted Icon-O-Matic and libs/icon in order to avoid
clashing with the new BGradient class. Re-use some
parts where possible.
Awesome work, Artur! Thanks a lot. Now a more modern
looking GUI has just become much easier to implement! :-)
TODO:
* Remove the need to have gradient type twice in the
app_server protocol.
* Refactor some parts of the patch to remove duplicated
code (Painter, DrawingEngine).
* Adopt the BPicture protocol to know about BGradients.
* Review some parts of the BArchivable implementation.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28109 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
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
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
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
* In _StealMouseMessage(), don't maintain fLastMouseMovedView, instead,
prevent B_MOUSE_MOVED message from being stolen that are important for
detecting transit changes. The point is that some apps (like Tracker) are
shooting themselves in the foot because they steal mouse messages via
GetMouse() in one place, but then rely on sane transit values in another
place. The way it works now, the view in question may get notified of the
same mouse moved coordinate twice, once via GetMouse() and once via
MouseMoved().
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28002 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Exit the function early in case of error, instead of maintaining the error
until the end.
* Separate more clearly the condition that a file type is available at all
versus not. This removes a redundancy when falling back to the generic
file icon.
* Add retrieving the icon from the super type. Even check if there is a
preferred app for the super type that supplies an icon before using the
icon of the super type itself.
Hopefully I didn't introduce new errors, but that the super type icon was not
used was the main problem I tried to fix.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@27990 a95241bf-73f2-0310-859d-f6bbb57e9c96
* added some convenient functions, operator etc...
* reused parts of the patch by Stephen Deken, thanks
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@27954 a95241bf-73f2-0310-859d-f6bbb57e9c96
* grab the fLooper pointer in some more functions, just to play save
* remove wrong comment in UnlockLooper, since it's obviously possible to change fLooper
In case we remove the handler from the loopers handler list, we need to grab the looper
pointer first, since calling RemoveHandler(...) will call BHandler::SetLooper(...) thus
setting fLooper to NULL and calling UnlockLooper did nothing, leaving the looper locked.
Thanks Maurice for pointing out that 26383 broke Cortex, the wires where not draw and the
app was locked somehow.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@27872 a95241bf-73f2-0310-859d-f6bbb57e9c96
