The unflatten time is now reduced to about a third of the current BMessage implementation but it's still
about half as quick as R5 (we're talking about microseconds here).
A third version of BMessage that operates purely on a flat buffer is in the works. We'll see which one
will be faster for normal uses.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13821 a95241bf-73f2-0310-859d-f6bbb57e9c96
Passes all unit tests now and works on Haiku too. Speed is not yet optimized and Message2.cpp is still not cleaned up.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13785 a95241bf-73f2-0310-859d-f6bbb57e9c96
It's currently really broken so don't even try to test it, but you can still review it ;-).
Message2.cpp is not yet cleaned - more to come...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13784 a95241bf-73f2-0310-859d-f6bbb57e9c96
use it. It is not (yet) included in the build and won't break anything.
As we now only have thin wrappers around the *Data() functions, the templatized implementation does
not make much sense anymore and wouldn't work either.
I started this new implementation to be as clean as possible. Instead of using a std::map and
BDataBuffer it uses BList and BMallocIO. It passes the unit tests and it even seems to be a bit quicker
in some tests (but not as quick as the R5 one).
Flattening/Unflattening does not work yet so you can't use it under Haiku right now. It's completely work in progress (I started it just 4 hours ago).
Shout if you see something completely broken, reviews welcome.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13776 a95241bf-73f2-0310-859d-f6bbb57e9c96
