PrefHandler now exports a static method GetDefaultPath() which gets the
path to the default settings file (using find_directory(), of course).
Disabled locale support; should be easy to reenable when needed again, though.
Made all the PrefHandler getters a lot more robust (could easily crash when asking
for an unknown item).
Some cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13853 a95241bf-73f2-0310-859d-f6bbb57e9c96
changed the way prefs is stored, so that we have default settings
general cleanup
time sliders are now linked together as on R5
password window is centered onscreen
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13849 a95241bf-73f2-0310-859d-f6bbb57e9c96
added ScreenSaver.cpp to ScreenSaver preferences to have Matrix working
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13828 a95241bf-73f2-0310-859d-f6bbb57e9c96
Also, BLocker now accepts NULL as a name and won't crash anymore in that case
("some BLocker" is then chosen as name).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13826 a95241bf-73f2-0310-859d-f6bbb57e9c96
Removed unused stuff.
The app_server now deletes itself when done (and therefore must not be
allocated on the stack anymore).
The cursor handling should be moved over to the desktop as well.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13825 a95241bf-73f2-0310-859d-f6bbb57e9c96
creation/deletion (and management) over to that class.
ServerApp now gets a desktop pointer, and no longer uses gDesktop.
Converted private MessageLooper::_MessagePort() to a public method MessagePort()
so that the looper can be addressed from elsewhere without using PostMessage().
Added a real basic message loop to MessageLooper::_MessageLoop().
BApplication now only asks the app_server to get its desktop object which should
now be used for everything that's not in the realm of the application.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13824 a95241bf-73f2-0310-859d-f6bbb57e9c96
is read one clock edge too late. This bit is driven low by
slave (as any other input data bits from slave) when the clock
is LOW. The current code did read the bit after the clock was
driven high again.
From OpenBSD (from FreeBSD).
Another small change
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13822 a95241bf-73f2-0310-859d-f6bbb57e9c96
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
* Added the respective case statement in AppServer::DispatchMessage().
The code that actually activates the app is still missing.
* Removed the remnants of the old way of notifying the registrar about
what app got activated (the activated client window did that).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13820 a95241bf-73f2-0310-859d-f6bbb57e9c96
class runs it, too.
No real message processing is done yet, though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13816 a95241bf-73f2-0310-859d-f6bbb57e9c96
the MessageLooper class - the other part is called from there as virtual
_PrepareQuit().
Moved the class documentation to the source file.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13815 a95241bf-73f2-0310-859d-f6bbb57e9c96
be improved a bit (Quit() and _MessageLooper() are empty right now).
Removed ServerApp::PingTarget().
Hopefully cleared some confusion about ServerApp::fClientLooperPort and fClientToken
(previously fHandlerToken), even if it's currently unused.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13807 a95241bf-73f2-0310-859d-f6bbb57e9c96
- when undoing the first change, any later change would make that first change reappear
- in hex mode editing, changes were not merged because they changed the same byte
Updated version info.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13801 a95241bf-73f2-0310-859d-f6bbb57e9c96
their path could be invalid in other contexts (e.g. the debug server might
be unabled to find them). This seems to be what BeOS does, too.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13796 a95241bf-73f2-0310-859d-f6bbb57e9c96
user application performs a division by zero or causes a general
protection fault. For some exceptions (e.g. machine check) I wasn't
quite sure whether they can be caused by user apps at all, so we panic()
in those cases. Wouldn't harm, if someone more knowledgable would check
this, though.
* Removed the unused fault handling stuff, respectively moved the little
that was used into x86/arch_int.c.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13795 a95241bf-73f2-0310-859d-f6bbb57e9c96
grist caused bfd to be compiled using gdb's config.h. This made it think
Haiku had no fcntl() and thus assumed shared objects were opened r/w instead
of read-only, which made it write back data when closing the files. So this
fixes the problem that gdb damages the shared objects it had loaded.
Basically two questions remain:
1) Why does BFD write something into the files that makes them invalid?
2) Why was it possible to write something into the read-only opened files?
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13791 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
CDDB data is written in R5 format with the exception of CD:key (still figuring out what to do about that)
Fixed some update notification problems with changing CDs
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13777 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
* Print the debugger message in case the debugged team called debugger(),
and the description of an occurred exception respectively.
* Properly keep gdb's internal thread list up to date. This fixes the
problem that an attached debugger always resumed all threads of the
debugged team.
* A bit of cleanup of the attaching code.
Discovered an ugly bug: When invoking gdb with an executable -- regardless
of whether attaching gdb to a running process or just starting a debugger
session with the executable -- the executable is modified. I tested with
"crashing_app" and in the second debug session gdb fails to read the debug
info from the file and encounters a weird error when closing the file:
"No space left on device." I have the suspicion that this is another bug
in Axel's VM/file cache pet. :-P
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13775 a95241bf-73f2-0310-859d-f6bbb57e9c96
with the thread lock held, which might have caused a panic later on, if there
was another thread waiting for the death stack semaphore.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13769 a95241bf-73f2-0310-859d-f6bbb57e9c96
into account when remapping the pages read-only; it could have overwritten valid
page mappings this way. This was also the reason for the Terminal to crash - it
does now work as it should, although some keys don't work (like tab completion)).
vm_copy_area() no longer always sets B_KERNEL_WRITE_AREA if no kernel protection
was specified, but mirrors the userland protection (for example, the x86 MMU is
not able to have a page writable in kernel but not in userland). This caused
some areas to be read/write when read-only would have been enough.
vm_copy_area() now panics when vm_copy_on_write_area() fails - that's of course
no real solution, but it's bettern than letting it silently fail.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13768 a95241bf-73f2-0310-859d-f6bbb57e9c96
Lookup now handles inexact matches
CDAudioDevice now detects all available CD drives
Fixed a minor bug in updating the track list when changing CDs
CDDB content files are now stored in R5's location - /boot/home/cd
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13764 a95241bf-73f2-0310-859d-f6bbb57e9c96
implementations (e.g. SVR4) don't do that, but I don't see how it could
work otherwise. Maybe other systems place the executable's code exactly
where specified in the executable and hence noone ever noticed...
Anyway, this makes stack traces (and probably other things that were broken
before) work with an attached gdb.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13762 a95241bf-73f2-0310-859d-f6bbb57e9c96
Should be better moved into resources next time. Will see...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13758 a95241bf-73f2-0310-859d-f6bbb57e9c96
"look-through" area in Terminal, and probably ShowImage as well.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13743 a95241bf-73f2-0310-859d-f6bbb57e9c96
ServerWindow printed the title in its destructor after freeing it (with debug output turned on).
Calmed it down a bit, too (disabled "listening on port...").
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13741 a95241bf-73f2-0310-859d-f6bbb57e9c96
Moved the alert to TermApp, too - TermWindow now only forwards the B_ABOUT_REQUESTED message.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13737 a95241bf-73f2-0310-859d-f6bbb57e9c96
There are some double entries (like TermApp.cpp and TerminalApp.cpp, so
it still needs a further cleanup).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13734 a95241bf-73f2-0310-859d-f6bbb57e9c96
to his developer branch. Maybe he wants to integrate the changes, too, whatever
he has done.
Removed unused files (muterm-2.3.zip, Jamfile - both still in history).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13732 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Moved setting the default cursor from ServerScreen to Desktop
* Getting the default cursor is now done using the CursorManager
* Removed outdated setcursor from SysCursor.cpp (we have a new implementation by now)
* Renamed SysCursor.cpp to CursorSet.cpp as that's what it is
* Moved headers/private/app/SysCursor.h to headers/private/servers/app/CursorSet.h
* Removed some unneeded header includes along the way
There remains {set|get}_syscursor now in CursorSet.cpp. Serverside for these are not implemented
and they are obvious hacks. Do we need to keep them?
Also this commit _would_ break Appearance, but 1) all the related code is currently commented out
with the comment "cursor set management belongs in another app" and 2) it is already broken
because of ColorSet.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13726 a95241bf-73f2-0310-859d-f6bbb57e9c96
concerned shared object's file, which probably is a bit overkill) and added
respective comments.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13725 a95241bf-73f2-0310-859d-f6bbb57e9c96
Deskbar to initiate the shutdown process asynchronously. Couldn't test it,
because opening the Be menu doesn't work:
***PANIC: BW: Can't find view with ID: 19 !***
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13722 a95241bf-73f2-0310-859d-f6bbb57e9c96
the desktop's settings, you have to do something like this:
DesktopSettings settings(desktop);
settings.SetMouseMode(mode);
The advantage of this is that this object is fully locked, and cannot lead to
corrupted settings anymore. Also, the settings will stay the same until you
delete the object again.
Updated all accesses to use this new API.
Removed no longer used FFM messages.
Implemented AS_{GET|SET}_MENU_INFO for future use.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13719 a95241bf-73f2-0310-859d-f6bbb57e9c96
Added a comment to load_menu_settings() - I think that stuff should be moved into the server.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13718 a95241bf-73f2-0310-859d-f6bbb57e9c96
the opportunity to show the "System is now ready to reboot" alert.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13714 a95241bf-73f2-0310-859d-f6bbb57e9c96
debug_server uses this feature to print stack traces with symbols.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13698 a95241bf-73f2-0310-859d-f6bbb57e9c96
need to transfer the ownership, when handing over the team to another
debugger.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13696 a95241bf-73f2-0310-859d-f6bbb57e9c96
- introduced new ScreenManager and VirtualScreen classes
- removed screen handling from RootLayer
- removed multiple screen/root layer stuff from Desktop, it's
now using a VirtualScreen object instead
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13686 a95241bf-73f2-0310-859d-f6bbb57e9c96
one alert, when two threads of a team crash. Now we have a per team queue
of debug messages and a thread per team that processes them (that is
usually only the first one). The application class does nothing anymore.
* Implemented debugger handover:
- In case of normal apps, when the relevant servers needed for GUI are
running, we show an alert and, if requested, start a MiniTerminal with
gdb for the crashed team. I couldn't really test it, since alerts don't
seem to work, respectively crash the app server (usually both ;-).
- In case the app server crashes, we always start a consoled with gdb.
This does indeed seem to work.
A gdb attached to a team is not really useful yet, since the shared object
relocations seem to be incorrect, so "bt" is not giving any useful info.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13684 a95241bf-73f2-0310-859d-f6bbb57e9c96
is sent to a debugger when the debugged team has been successfully handed
over to another debugger.
* Fixed handling of B_DEBUG_MESSAGE_PREPARE_HANDOVER. We don't send a reply.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13683 a95241bf-73f2-0310-859d-f6bbb57e9c96
specified via options -l and -s. An arbitrary program can be run in the
terminal instead of a shell.
* Console::fState was never initialized which could cause the terminal to
not print anything.
* stdin, -out, and -err were set in MiniView::Start() and in
MiniView::ExecuteShell(). Thus resetting them in the latter method after
executing the shell had no effect. Removed it in the former method and
now reset them after loading, but before resuming the shell.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13676 a95241bf-73f2-0310-859d-f6bbb57e9c96
allocating a buffer and copying your data into it, when you have data to
send in several chunks (for example, this could be used by BMessage, as
suggested by Ingo Weinhold).
Code is untested, but should work.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13667 a95241bf-73f2-0310-859d-f6bbb57e9c96
a new iovec array, but only freed them on (early) error.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13666 a95241bf-73f2-0310-859d-f6bbb57e9c96
optimazation for ReplaceFlat() (also done for AddFlat() before).
Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13662 a95241bf-73f2-0310-859d-f6bbb57e9c96
This is needed in case the on-disk representation of a file changes (due to reorganization/defragmentation).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13660 a95241bf-73f2-0310-859d-f6bbb57e9c96
I think BMessageBody::FindData<>, BMessageBody::AddData<>, BMessageBody::ReplaceData<> could be untemplatized
Works here, not unit tested though
Axel, please review this.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13653 a95241bf-73f2-0310-859d-f6bbb57e9c96
This was the cause for some apps to put their settings files to the current
directory, and also that Tracker did not find some icons (from the icons
it installed in the MIME database).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13645 a95241bf-73f2-0310-859d-f6bbb57e9c96
Time display is updated when player is stopped
Turning off shuffle really takes it out of shuffle mode
Can change tracks while the CD player is not playing
Improved responsiveness of screen updates when changing tracks
Total disc time calculation is fixed
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13644 a95241bf-73f2-0310-859d-f6bbb57e9c96
shutdown (input, app, debug server, and registrar).
* Fixed crashing bug, if the shutdown was aborted before the window was
created.
* The text of the confirmation alert depends on whether we reboot or
shut down.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13643 a95241bf-73f2-0310-859d-f6bbb57e9c96
