* Move Messages id to a private header
* New constructor for RemoteDevice
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24376 a95241bf-73f2-0310-859d-f6bbb57e9c96
Check for memory allocation errors.
Added limit to maximum flavor format count (300).
No longer crashes when out_format_count is invalid for B_BUFFER_CONSUMER,
or in_format_count is invalid for B_BUFFER_PRODUCER.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24366 a95241bf-73f2-0310-859d-f6bbb57e9c96
* _Alloc() can now preserve the original reference count, only _Clone()
still initializes it to 1. As Karsten pointed out, this is necessary to
preserve the "shareable" status of the private data.
* I hope that's finally it. What happened to our testing suite, anyway? :-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24355 a95241bf-73f2-0310-859d-f6bbb57e9c96
_ReplaceAtPositions(), and _DoCharacterEscape() (we don't need to preserve
it, though, as it must be 1).
* Factored out an _Alloc() method which is now always called when the private
data is allocated. It also takes care of correct initialization (and thus
fixes the above problem).
* This fix finally allows turning on reference counting again, thanks Karsten!
* Minor cleanup, renamed "oldAdr"/"newAdr" to "oldString", resp. "newString".
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24348 a95241bf-73f2-0310-859d-f6bbb57e9c96
* _Realloc(), and _Detach[With]() may fail, but that wasn't accounted for
everywhere.
* The Append(), Prepend(), and Insert() char versions all caused their
backends to access invalid data (must use strncpy() instead of memcpy()
here).
* All Append(), Prepend(), and Insert() BString variants used an invalid
check, and would therefore just do nothing in certain situations like this
one:
BString a = "-";
BString b = a;
a.Append(b);
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24347 a95241bf-73f2-0310-859d-f6bbb57e9c96
copy constructors, effectively turning of references completely.
* Since that caused troubles (NetPositive now crashes when started), I
temporarily disabled references by letting _IsShareable() always return
false until the issue is resolved.
* _FreePrivateData() now sets the fPrivateData member to NULL, and is also
safe to be called when fPrivateData is NULL.
* Removed my comment about the threading problem in _Detach() and _DetachWith()
as that just couldn't happen.
* _Clone() must not use memcpy() as the string pointed to by "data" might not
be as long as "length".
* LockBuffer() now marks a string as unshareable.
* Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24345 a95241bf-73f2-0310-859d-f6bbb57e9c96
cleared which have no app_server link (B_BITMAP_NO_SERVER_LINK).
* Check the allocation of the BWindow in BBitmap for view accepting bitmaps.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24344 a95241bf-73f2-0310-859d-f6bbb57e9c96
truncated, if already existing. This problem could be experienced when
saving in Pe.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24329 a95241bf-73f2-0310-859d-f6bbb57e9c96
the new sematic of transfer_area so a message area is transfered into the right
teams' address space and it does not need to be cloned there anymore. Passing
by area is only used for messages bigger than a certain size (currently
hardcoded to 40KB) which should be somehow bound to the max port message size.
This makes passing large messages (i.e. > the port limit) possible, so for
example copy&paste of long text, image data, etc. should now work.
Got rid of the fClonedArea member as it is not necessary with the new design,
renamed shared_area to message_area in the private message_header, avoid
an unnecessary allocation of the header for the copy constructors, check
allocations in a few more places and some minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24321 a95241bf-73f2-0310-859d-f6bbb57e9c96
string stuff.
* It's still not thread-safe for all usage patterns, though, so we might want
to remove or disable it: if a string is shared between several threads, and
one of those starts to use a reference, all kinds of problems can happen.
* Some cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24312 a95241bf-73f2-0310-859d-f6bbb57e9c96
Tracked down the root cause of the issue worked around in r24228.
The behavior that was occurring in this case was as follows:
Vision created a BInvoker off the heap, containing a BMessage likewise
off the heap. It then called BAlert::Go with this invoker. When any of
the buttons in the BAlert were pushed, _SendMessage would enqueue the
message into the target looper (in this case, Vision's window) and wake
it up with write_port_etc. However, in some cases this would result in
a reschedule such that Vision's looper executed before _SendMessage() was
able to complete all its processing. Upon receiving this message, Vision
destroyed the BInvoker in question, which in turn deleted its owned
BMessage -- which was the message that was still in the middle of _SendMessage()!.
Consequently it would crash a few lines later when it hit IsSourceWaiting() and
tried to check flags off its header off the already destroyed this. To fix this,
we now do the AddMessage/write_port_etc last before returning. Also removed the
sanity checks added in r24228 so we don't mask other problems of similar nature.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24297 a95241bf-73f2-0310-859d-f6bbb57e9c96
still. This way keyboard menu navigation works much better.
Unfortunately I can't apply the same trick for BMenu since it opens the
submenu with a delay, and that won't work anymore.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24296 a95241bf-73f2-0310-859d-f6bbb57e9c96
would have returned the second item in place of the first. Also return
NULL, not false, when there are no "next items".
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24294 a95241bf-73f2-0310-859d-f6bbb57e9c96
MakeFocus(false) can not be trusted, since it is virtual and might not call
the BView version.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24293 a95241bf-73f2-0310-859d-f6bbb57e9c96
B_ASYNCHRONOUS_CONTROLS flag. If anyone does encounter an app that
breaks because of this, please let me know, but a few tests with various
apps seem to show no issues.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24290 a95241bf-73f2-0310-859d-f6bbb57e9c96
set up with a null replyTo, sometimes BMessage would crash
calling IsSourceWaiting() after delivering the message. This appeared
to be because fHeader was NULL, but I'm not entirely certain if this
is actually supposed to be possible, so this may be masking a different
bug. This was observable using the multiline paste spam BAlert in
Vision, which would sometimes but not always crash in Haiku after hitting
any of the buttons to dismiss it, though consistently when calling IsSourceWaiting()
from the private BMessage::_SendMessage().
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24228 a95241bf-73f2-0310-859d-f6bbb57e9c96
a BTextView in order to be able to display multiline
panel text (since BStringView can't handle this). However,
while they correctly set the background panel color, they
neglected to set the font style/color to that used by panel.
Fixed. This makes shutdown/restart dialogs properly color sensitive.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24226 a95241bf-73f2-0310-859d-f6bbb57e9c96
- no need to initialize the buffer on stack
- no need to initialize "buffer" to NULL
- renamed "buf" to stackBuffer
- enlarged buffer on stack to 16384 bytes (we have a minimum of 192 kB of
stack per thread, anyway).
- check the actual size of the stack buffer against the message's flattened
size instead of the one of its pointer.
- check if the allocation of the helper buffer failed, and return B_NO_MEMORY
in this case.
* Moved static helper functions to the top of the file.
* Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24204 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Allocate the buffer to flatten the message on the heap, if it's size is bigger then a given
buffer on the stack. It seem's to exceed the stack size (this might count for AddFlat() too).
Note: With this change one is able to copy the text into the clipboard (1mb), but it
is still impossible to paste it somewhere, as in BClipboard::_DownloadFromSystem()
SendMessage() fails transferring the data back in the reply msg because of the port size limit...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24196 a95241bf-73f2-0310-859d-f6bbb57e9c96
correct warning) for AbstractPointerListHelper. (libbe_build.so)
* I have had problems with implementing virtual functions inline in the
class declaration before, so I implemented the virtual destructor
externally.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24168 a95241bf-73f2-0310-859d-f6bbb57e9c96
weird text selection in BTextView() (for example, when an empty line was
part of the selection).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24142 a95241bf-73f2-0310-859d-f6bbb57e9c96
if the items were the same height.
- Modified _RecalcItemTops to allow us to specify a range instead of
just a starting point. This is useful for cases like Swap, where
only the items in between those being swapped need to be
recalculated.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24139 a95241bf-73f2-0310-859d-f6bbb57e9c96
line will be scrolled out of view. (Fixes text jumping one pixel up/down in
Vision with each new char you type into Visions text box.)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24136 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Renaming things in Tracker list mode no longer magically grows the text view.
* ScrollToOffset() is not supposed to depend on the existence of any scroll
bars, in R5 text views simply scroll to where they need to. This fixes
renaming things in Tracker when hitting the window bounds (text widget stops
growing and starts to autoscroll) and also the Text tool in WonderBrush.
* _ScrollToOffset() is therefor no longer needed.
* The insets of the text rect are not so interesting as the original width.
In auto resizing mode, the original width is important when there is no
container view. In this setup, the text rect auto resizing is mainly needed
for auto scrolling, but it should never shrink below the original size.
* Further improved auto scrolling for right aligned and center aligned text
views, it works like R5 now. Also take the line height into account when
checking for the bounds bottom. Removed extra spacing for vertical
scrolling.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24130 a95241bf-73f2-0310-859d-f6bbb57e9c96
NodeMonitor.h.
* The latter will be set in "statFields" for interim updates when you have
asked to get them via the former.
* BFS now uses the B_STAT_INTERIM_UPDATE flag for sending updates to actively
written files.
* This makes us more compatible with BeOS again; if you only asked for
B_WATCH_STAT, you will now only receive a notification if the file in
question has been closed.
* Tracker now uses B_WATCH_INTERIM_STAT to always get all updates (ie.
downloading a file will update its size and modification time in Tracker
periodically during the download).
* Wether "needsTrimming" was true or not has no influence on wether or not
the size index needs to be updated in BFS - only the actual file size is
stored there, not the on-disk size.
* Added a TODO comment in Inode::WriteAt() that it would actually need to
update the size index when changing the file size, not when the file has
been closed (but that's probably too slow).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24114 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Placed _BTextInput_ into BPrivate namespace.
* Made _BTextInput_::AlignTextRect() smarter, it centers the line vertically,
for the case that the BTextControl has a larger label font. Improved insets
for asthetics.
* Used _BTextInput_::AlignTextRect() consistently in BTextControl, no more
custom calls to SetTextRect(). Account for minimum vertical inset of 2
pixels in GetPreferredSize().
* Consistendly select all text when gaining focus in _BTextInput_.
* Override MouseDown() in case the control did not have focus before, or else
BTextView::MouseDown() will deselct the text again and place the cursor.
(in line with BeOS behavior)
* Removed unused fBool member from _BTextInput_ and other cleanup.
BTextView:
* Reimplemented BTextView::_AutoResize() so that it works well with
BTextControl and autoscrolling when the alignment is not B_ALIGN_LEFT.
I needed two new members for this, fLeftInset and fRightInset which are
the original insets from the fTextRects. It might currently be broken
for renaming things in Tracker, I will have to check. _AutoResize() no
longer messes up the fTextRect insets.
* Fixed stray carrets sometimes being left over, mostly when auto scrolling,
but I observed them in other cases as well.
* Prevent negative scrolling offsets when autoscrolling. Fixes weird scrolling
offsets when navigating to the left.
* Reset scrolling to B_ORIGIN when SetText() is called. Fixes for example
starting to type in the middle of the control in Vision when entering new
text and autoscrolling was triggered before.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24101 a95241bf-73f2-0310-859d-f6bbb57e9c96
with other controls. (BTextControl patch with the same change is upcomming, but
it includes many other changes I didn't want to mix in.)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24100 a95241bf-73f2-0310-859d-f6bbb57e9c96
* BListItems now store the top offset of the frame within the parent BListView.
* This allows binary searching the clicked item.
* ItemFrame() is now a cheap call.
* Fixed several bugs in the sorting code of BOutlineListView which lead to
crashes of client applications.
* Implemented previously unimplemented functions in BOutlineListView.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24092 a95241bf-73f2-0310-859d-f6bbb57e9c96
