BString::Private class to access BString internals

Add HashValue() methods to BString

* Added bool and double BString::operator<<() versions.
* Removed the clashing operator in JobSetupDlg. Automatic whitespace
cleanup.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42387 a95241bf-73f2-0310-859d-f6bbb57e9c96

operation <<(): Use the standard types [unsigned] long [long] instead of
[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

Add BString::IsEmpty() method.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@41242 a95241bf-73f2-0310-859d-f6bbb57e9c96

Rename and a small simplification. Thanks, Clemens and Ingo.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40756 a95241bf-73f2-0310-859d-f6bbb57e9c96

Cleanup. Efficiency makerover.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40720 a95241bf-73f2-0310-859d-f6bbb57e9c96

BString::SetToArguments(). Forgot the header. :I

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40697 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fix build error in IMAP client due to incorrect inequality check in one of BString's inlines. Fixes #6439.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@38075 a95241bf-73f2-0310-859d-f6bbb57e9c96

Adding utf-8 aware version of most functions to BString. They are named after
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 desperately missing Trim() method.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32035 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Made _Allocate() static.
* 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

Added (const char*) cast operator. That makes BString more convenient to pass
around, particularly returning it from methods instead of a const char*, if the
object stores the string as a BString anyway, thus leveraging CoW.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@31354 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Fixed a race condition in the former _Detach*() functions: since atomic_get()
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

* _Realloc() did not initialize the reference count either.
* _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

* As found by Karsten, the reference count was not initialized in
_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

* After my last change, _IsShareable() was called on the wrong string in the
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

* Fixed a bunch or concurreny bugs and memory leaks of the new reference
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

* fixed coding style...


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24103 a95241bf-73f2-0310-859d-f6bbb57e9c96

Patch by Julun: implements a refcounted BString. Thank You!


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24102 a95241bf-73f2-0310-859d-f6bbb57e9c96

Cleanup.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@19731 a95241bf-73f2-0310-859d-f6bbb57e9c96

Another patch from Oliver Tappe: BString behaves better when the user supplies out-of bounds values in Insert(), Remove(), etc.
Code is refactored, and it fully complies with our guidelines.
Tests have been updated too (hint: try the replace tests with R5 and our implementation...)


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@5348 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added missing _DoReplace().


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@2718 a95241bf-73f2-0310-859d-f6bbb57e9c96

Corrected some inaccuracies imported from the BeOS headers:
CapitalizeEachWord() DOESN'T capitalize words separated by spaces, it
capitalizes words separated by non alphabethical characters.
FindLast(char, int32) prototype was misleading.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@2008 a95241bf-73f2-0310-859d-f6bbb57e9c96

fixed newline at end of file.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1215 a95241bf-73f2-0310-859d-f6bbb57e9c96

fixed a typo


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1193 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added a first BString header


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@987 a95241bf-73f2-0310-859d-f6bbb57e9c96

This file shadows Be's header. So if it doesn't contain anything, iclude at least the original header.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@17 a95241bf-73f2-0310-859d-f6bbb57e9c96

It is accomplished ...


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@10 a95241bf-73f2-0310-859d-f6bbb57e9c96

BString::Private class to access BString internals

Add HashValue() methods to BString

* Added bool and double BString::operator<<() versions.
* Removed the clashing operator in JobSetupDlg. Automatic whitespace
cleanup.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42387 a95241bf-73f2-0310-859d-f6bbb57e9c96

operation <<(): Use the standard types [unsigned] long [long] instead of
[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

Add BString::IsEmpty() method.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@41242 a95241bf-73f2-0310-859d-f6bbb57e9c96

Rename and a small simplification. Thanks, Clemens and Ingo.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40756 a95241bf-73f2-0310-859d-f6bbb57e9c96

Cleanup. Efficiency makerover.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40720 a95241bf-73f2-0310-859d-f6bbb57e9c96

BString::SetToArguments(). Forgot the header. :I

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40697 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fix build error in IMAP client due to incorrect inequality check in one of BString's inlines. Fixes #6439.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@38075 a95241bf-73f2-0310-859d-f6bbb57e9c96

Adding utf-8 aware version of most functions to BString. They are named after
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 desperately missing Trim() method.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32035 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Made _Allocate() static.
* 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

Added (const char*) cast operator. That makes BString more convenient to pass
around, particularly returning it from methods instead of a const char*, if the
object stores the string as a BString anyway, thus leveraging CoW.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@31354 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Fixed a race condition in the former _Detach*() functions: since atomic_get()
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

* _Realloc() did not initialize the reference count either.
* _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

* As found by Karsten, the reference count was not initialized in
_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

* After my last change, _IsShareable() was called on the wrong string in the
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

* Fixed a bunch or concurreny bugs and memory leaks of the new reference
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

* fixed coding style...


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24103 a95241bf-73f2-0310-859d-f6bbb57e9c96

Patch by Julun: implements a refcounted BString. Thank You!


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@24102 a95241bf-73f2-0310-859d-f6bbb57e9c96

Cleanup.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@19731 a95241bf-73f2-0310-859d-f6bbb57e9c96

Another patch from Oliver Tappe: BString behaves better when the user supplies out-of bounds values in Insert(), Remove(), etc.
Code is refactored, and it fully complies with our guidelines.
Tests have been updated too (hint: try the replace tests with R5 and our implementation...)


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@5348 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added missing _DoReplace().


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@2718 a95241bf-73f2-0310-859d-f6bbb57e9c96

Corrected some inaccuracies imported from the BeOS headers:
CapitalizeEachWord() DOESN'T capitalize words separated by spaces, it
capitalizes words separated by non alphabethical characters.
FindLast(char, int32) prototype was misleading.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@2008 a95241bf-73f2-0310-859d-f6bbb57e9c96

fixed newline at end of file.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1215 a95241bf-73f2-0310-859d-f6bbb57e9c96

fixed a typo


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@1193 a95241bf-73f2-0310-859d-f6bbb57e9c96

Added a first BString header


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@987 a95241bf-73f2-0310-859d-f6bbb57e9c96

This file shadows Be's header. So if it doesn't contain anything, iclude at least the original header.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@17 a95241bf-73f2-0310-859d-f6bbb57e9c96

It is accomplished ...


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@10 a95241bf-73f2-0310-859d-f6bbb57e9c96