* the upcoming multibyte-implementation in libroot's ICU locale
backend is going to use this, so it's not good enough to provide
BReferenceable only in libbe.so
* use _DaysInMonth() instead of DaysInMonth(), as the latter only works
for valid dates, which we do not have if the day needs to be clamped
to the maximum value for the current month
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42719 a95241bf-73f2-0310-859d-f6bbb57e9c96
are the same (Eclipse was complaining about 'assignment to self', which got me
looking at the code ...)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42682 a95241bf-73f2-0310-859d-f6bbb57e9c96
[u]int32 and [u]int64 to avoid clashes with the int/unsigned int versions.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42165 a95241bf-73f2-0310-859d-f6bbb57e9c96
AcquireReference() now does, and adjust all callers that relied on the previous
return type.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42091 a95241bf-73f2-0310-859d-f6bbb57e9c96
Fix header order, ups never changed a libbe file before ;) thx Oliver. Add small optimization as pointed out by Ingo.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@41093 a95241bf-73f2-0310-859d-f6bbb57e9c96
* if _MakeWritable() fails, LockBuffer() must return NULL, not what
happens to be in fPrivateData
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40525 a95241bf-73f2-0310-859d-f6bbb57e9c96
* added some methods to find out easter sunday, ascension and pentecost days.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40116 a95241bf-73f2-0310-859d-f6bbb57e9c96
features:
* Some cosmetic adjustments of the API, like using references instead of
pointers, argument order, method names, etc.
* Added convenience template methods for archiving and unarchiving to BArchiver
and BUnarchiver.
* BUnarchiver (respectively the private BUnarchiveManager) explicitly deals with
object ownership, now. This is necessary since an error while unarchiving
could leave an already unarchived object without owning object, which would
result in it being leaked. The BUnarchiver::{Get,Find}Object() methods do now
have an optional parameter to specify whether object ownership shall be
transferred.
* Fixed incorrect header guard in headers/private/binary_compatibility/Global.h.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37538 a95241bf-73f2-0310-859d-f6bbb57e9c96
unarchiving protocol to support archival of arbitrary object graphs.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@37431 a95241bf-73f2-0310-859d-f6bbb57e9c96
is later used as parameter to memcpy(). Should fix r5623 (untested).
* Fixed coding style for some comments.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35944 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Let the AddHours(), Add*() return itself, so that they can be chained.
* Made the previous *Name() methods static and added non-static versions that
take the day/month of the object.
* Make BDateTime::Date/Time() return references (const or non-const).
* Fixed the BDateTime comparison operators.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35894 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Extended BTime, BDate and BDateTime with archiving functionality.
* Adjusted code which uses these classes, since including DateTime.h
already imports the classes from the BPrivate namespace.
* Moved DateTime.h into Support Kit. It is still in the BPrivate namespace,
as I am uncertain what to do with time_type and diff_type. I'd favor
moving the constants into the classes itself. Possibly removing the B_
prefix from them. Feedback welcome.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35772 a95241bf-73f2-0310-859d-f6bbb57e9c96
the corresponding normal functions but have a "Chars" in the name like
"MoveCharsInto" or "AppendChars". Also added CountBytes() and CharAt().
This should make everyday string handling with multibyte strings a bit easier.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@35371 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added operator== and !=
* Added check for list != this in operator=
* Added HasItem() and IndexOf() versions that take const void*, duplicating
the code, since I didn't want to introduce another function call in these
potentially time critical methods.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@34520 a95241bf-73f2-0310-859d-f6bbb57e9c96
typedef, so it's clearer which one is the preferred one.
* Added BReference, a clone of BPrivate::Reference.
BPrivate::{Referenceable,Reference} are being phased out. Only the B* versions
should be used.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33879 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Moved the private inline methods up in the source file, so they can actually
be inlined.
* UnlockBuffer(): Removed superfluous "if". Maybe the one who wrote it can have
a look and check whether something else was intended originally.
* _MakeWritable() (both versions): Removed the superfluous ref count increment
and the matching decrements.
* _Resize(): Fixed ref count ASSERT. It would always be triggered when called
from UnlockBuffer(), since the ref count is -1 in that case.
* Clarified some comments.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@31662 a95241bf-73f2-0310-859d-f6bbb57e9c96
the old names still exist as deprecated aliases for the time being.
* Introduced hooks FirstReferenceAcquired() and LastReferenceReleased(). Besides
added flexibility this also makes the deleteWhenUnreferenced constructor
parameter and the fDeleteWhenUnreferenced attribute superfluous, since the
"don't delete" behavior can be obtained by overriding LastReferenceReleased().
Parameter and attribute will be removed eventually.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@31367 a95241bf-73f2-0310-859d-f6bbb57e9c96
was used, two different threads could decide to share the same mutable string.
* Renamed some functions to make clearer what they do, ie. _Detach() is now
called _MakeWritable().
* Cleaned up some questionable semantics, like the const char* parameter in
_DetachWith() - you can now choose to copy the original string or not with
a boolean. This also makes sure that the string is actually copied when it
has to, which wasn't the case before (but that was no problem with the way
that function was used).
* Made the header compliant with our style guide.
* Further cleanup.
* All BString related unit tests are passed, so I guess I didn't break too
much :-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@30980 a95241bf-73f2-0310-859d-f6bbb57e9c96
better, though :-)
* Also fixed a mixup of the unintuitive argument order of our
atomic_test_and_set(); I guess I will change that sooner or later.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@29994 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
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
in duplicate work/checks. Instead the length is checked in the calling
functions.
* operator=(const char*) now checks if the passed pointer is the strings
own data pointer. I think it would have freed the memory before, not
sure though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@26378 a95241bf-73f2-0310-859d-f6bbb57e9c96
We now keep track of a lower bound as to when the list should scale
itself back down. When increasing the list size, we double the current,
with the lower bound set to 1/4 of the current size, not allowing it to
go any smaller than the block size. These combined allow us to do very
cheap tests to see if an operation requires a resize at all, and minimize
how often the list actually needs to be resized, since the difference in upper
and lower bounds prevents bouncing back and forth between a size in the case
of adding/removing an item while close to a boundary. All in all this should
make BList noticably more scalable when doing large numbers of add/remove
operations.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25946 a95241bf-73f2-0310-859d-f6bbb57e9c96
we now double/halve the current size of the list, starting with the constructor blocksize as a baseline.
This has the net effect that when doing large numbers of inserts/removes, the number of resize operations
needed scales logarithmically to the number of operations, which should yield a decent performance
improvement in such cases.
Review welcome. This does not yet affect ticket #2363 that I'm aware of, as I'm currently in the process
of attempting to find a copy of said app to test with.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25916 a95241bf-73f2-0310-859d-f6bbb57e9c96
There are many other calls that crash in BeOS when called with invalid args, should we attempt to sanitize them or call debugger() instead ?
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25372 a95241bf-73f2-0310-859d-f6bbb57e9c96
it couldn't find the class on first try. This fixes the problems mentioned
by Shinta as part of bug #2086.
* Got rid of GetNumber() - there is a POSIX function strtoul() for exactly
this purpose.
* demangle_class_name() can now fail.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25179 a95241bf-73f2-0310-859d-f6bbb57e9c96
instead, it will now use the image_id parameter to store errors in.
* find_instantiation_func() and validate_instantiation() will no longer
overwrite errno with B_OK.
* Made private functions static, and moved them to the top.
* If the class name starts with '_', it will now try to add a BPrivate namespace
in case it could not find the class. This should help with the compatibility
issues Shinta reported (also part of ticket #2086).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25124 a95241bf-73f2-0310-859d-f6bbb57e9c96
setting to force BLockers to be semaphore style. This may help with
debugging deadlocks.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25096 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
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
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
inherited from BView.
* BShelf::_AddReplicant() did not honour the fAllowZombies flag correctly; if
it wasn't allowed, no error message was given.
* Both of these changes fixes the crashing of the Deskbar as described in
bug #555.
* instantiate_object() now also fires a message to the syslog if the object's
image could not been loaded. Some cleanup, no longer resets errno.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22117 a95241bf-73f2-0310-859d-f6bbb57e9c96
