but operates "read-only".
* Added FindKeyFrame() method to ReaderPlugin, see above.
* Reformated ReaderPlugin header. Added const qualifier to Source() method.
* Small cleanups in BMediaTrack::SeekToTime() and SeekToFrame(). Added TODOs
with regards to "seeking" in decoders, wich should IMHO be revised. (Codecs
cannot seek in the stream, they only get fed chunk data. The only thing they
can do is reset themselves in preparation for a discontinuity of the chunk
data...)
* Implemented BMediaTrack::FindKeyframeByXX() methods via the new
MediaExtractor::FindKeyFrame() method.
* Implemented Seek() and FindKeyFrame() methods in the Reader base class,
returning B_NOT_SUPPORTED. I think this makes sense and also I don't have
to adapt all existing Reader plugins for the new FindKeyFrame() call. :-)
* Implemeneted FindKeyFrame() in the avi_reader. The OpenDMLFile class
gets Seek() extended for a "read-only" mode. Currently the implementation
is broken (as before) with regards to keyframes. These were ignored before
and I have not changed them to actually support the seek flags with regards
to keyframes. That's the interesting TODO...
* Some reformatting here and there in avi_reader code, sorry for the mixup.
The only actual change is the support for the read-only flag to Seek().
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24495 a95241bf-73f2-0310-859d-f6bbb57e9c96
modules, I left the one from MediaExtractor::CreateDecoder, since it also
mentions the stream index.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24491 a95241bf-73f2-0310-859d-f6bbb57e9c96
check if mouse is over a submenu and then if it's over the current menu.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24479 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Fixed all but one compiler warnings in libmedia.so.
* Truncated lines to 80 char width where I looked at code.
* Turned printf()s into TRACE/ERROR calls in MediaExtractor.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24478 a95241bf-73f2-0310-859d-f6bbb57e9c96
is 0, in which case it is almost save to assume it is a keyframe. Added
TODO though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24474 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Turn off tracing in the Media Kit.
* Notify of unimplemented functions regardless of tracing.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24473 a95241bf-73f2-0310-859d-f6bbb57e9c96
* fTrackList was deleted with delete, but needed delete[].
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24472 a95241bf-73f2-0310-859d-f6bbb57e9c96
Invalidate() on SetMaxValue(). This should probably be revisited in
the future whenever we break binary compat. TODO note added to that
effect.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24468 a95241bf-73f2-0310-859d-f6bbb57e9c96
locked.
* Removed some long and useless comments.
* Other minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24445 a95241bf-73f2-0310-859d-f6bbb57e9c96
readlink() function. It is no longer required to null-terminate the
string, shall not fail, if the buffer is too small, and shall return
the length of the string actually written into the buffer.
* Adjusted rootfs, devfs, and bfs accordingly. Also adjusted their
read_stat() hooks to return the correct symlink length in st_size.
* Our readlink() does now comply to the standard (and BeOS).
Additionally if the buffer is big enough it is nice to non-conforming
apps and null-terminates it.
* BSymLink::ReadLink() explicitly null-terminates the string now.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24425 a95241bf-73f2-0310-859d-f6bbb57e9c96
would cause various incorrect behavior, best observed in the form of Deskbar crashing if you tried to drag and drop
a large replicant (i.e. Workspaces) onto it.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24418 a95241bf-73f2-0310-859d-f6bbb57e9c96
Tracker now persisting its desktop replicants across sessions.
This may not completely handle zombies properly though, I had
nothing to test that case with.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24409 a95241bf-73f2-0310-859d-f6bbb57e9c96
Move implementation from LocalDevice for retrieving the BluetoothServer Messenger
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24385 a95241bf-73f2-0310-859d-f6bbb57e9c96
* 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
