If the menu opens right under the mouse cursor, do not select or invoke an item
until the mouse is moved. Since this seems to break normal menu bars, I added
the check for fSuper. As a (bad?) side effect BMenuField menus also need mouse
movement before something is selected. If anything else is broken, let me know.
I'm committing this because it does remove some bad behavior in pop up menus
(unintentionally selecting items.)
We may also want to force the openAnyway behavior as discussed on the mailing
list in December.
In general though the menu handling code really should be redesigned/refactored.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40132 a95241bf-73f2-0310-859d-f6bbb57e9c96
Note, the BootManager might not work right now, anymore.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40130 a95241bf-73f2-0310-859d-f6bbb57e9c96
* I reused crc_table.cpp from the UDF filesystem and switched it to have the reversed algorithm,
then generated the table in CRCTable.cpp
* added a binary search for extent tree leaves.
* fixed a check in InodeAllocator::New().
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40129 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Modify MediaListItem to use the visitor pattern
* Use the visitor pattern for comparison of MediaListItem subclassed objects
* Use the visitor pattern in MediaWindow to propagate changes to NodeListItems.
* Rename and/or remove some message constants
* Rename SettingsItem class to NodeMenuItem
* Rename Settings2Item class to ChannelMenuItem
* Derive SettingsView from BGridView, and make it an abstract base class for two new classes, AudioSettingsView and VideoSettingsView.
* Have the SettingsView subclasses handle messages originating from their children (for the most part).
* Use a BCardLayout to hold our Audio/Video SettingsViews and our instantiated node view (when applicable).
* small changes
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40127 a95241bf-73f2-0310-859d-f6bbb57e9c96
most pages do now, albeit it's not perfect yet due to issues with BTextView,
and BScrollView that make them very inconvenient to use with the layout API.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40126 a95241bf-73f2-0310-859d-f6bbb57e9c96
pageOffset variable type from phys_addr_t to addr_t. Avoids potential width
difference when casting to pointer later (CID 4718).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40120 a95241bf-73f2-0310-859d-f6bbb57e9c96
variable type from phys_addr_t to addr_t. Avoids potential width difference
when casting to pointer later (CID 4719-4722).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40119 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
specifier to float constants. Hopefully I'm done with this now.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40110 a95241bf-73f2-0310-859d-f6bbb57e9c96
Also moved private methods to the bottom of source files.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40108 a95241bf-73f2-0310-859d-f6bbb57e9c96
differently in Germany, but NetworkTime was always setting my time 6 hours
ahead, no matter what time zone or whether I stored the time in local time or
GMT. Upon looking closer and doing some Googling I determined that the constant
Axel used for the number of seconds between 1900 and 2000 was off by 6 hours,
and that combined with the odd kUTCtoGMT constant resulted in the 6 hour
difference.
By just replacing the system_time_difference() function with a correct constant
for the number of seconds between 1900 and 1970 and getting rid of kUTCtoGMT it
now works for me (and at least one other person on #haiku-dev, thanks
kallisti5!) For those wondering NTP time is measured from 1900 hence the need
for this conversion.
I will now look into integrating this with the Time preflet.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40103 a95241bf-73f2-0310-859d-f6bbb57e9c96
Pretty much implements everything needed to set a swap volume once that is
implemented on the kernel side. This also improves the behavior of the Default
button.
A few changes I made:
- When the swap volume feature is turned on in the code, default to the boot
volume if the settings file does not have one set.
- Don't show the volumes menu field in the GUI if the swap volume feature is
not on.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40101 a95241bf-73f2-0310-859d-f6bbb57e9c96
So we need a little work-around to open both ends in the shell process to
avoid blocking. Apparently Haiku's FIFO implementation isn't quite conforming
yet.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40100 a95241bf-73f2-0310-859d-f6bbb57e9c96
Butterfly by Geoffry Song.
Leaves by Deyan Genovski and Geoffry Song.
Thanks guys!
I fixed a few coding violations and wrote the Jamfiles.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40098 a95241bf-73f2-0310-859d-f6bbb57e9c96
including also Haiku) using FIFOs instead of Unix sockets. Advantages:
* Multiple FS shells can run concurrently, since they no longer need a unique
address.
* Killing/aborting the build_haiku_image script will automatically tear down
the FS shell as well, so there shouldn't be any stray FS shell processes
anymore. Hopefully also fixes#5498.
So far only tested under Haiku.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40097 a95241bf-73f2-0310-859d-f6bbb57e9c96
that's the limit of the addr_t domain anyway.
* Defined IS_USER_ADDRESS() to !IS_KERNEL_ADDRESS(), which semantically it was
already, just more verbosely.
Should, in the future, avoid hundreds of useless Coverity tickets where the
macros are used.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40093 a95241bf-73f2-0310-859d-f6bbb57e9c96
Expanded search in every configuration, not only first. ELSA USB modem for instance
publish two configurations, the first one being a vendor-specific one for
Windows NT.
ACMDevice now don't assume anymore union functional descriptor is always there.
The data interface index can be found also in Call Management (CM) functional
descriptor.
(Style cleanup pending...)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40092 a95241bf-73f2-0310-859d-f6bbb57e9c96
Renamed USB_CDC_*_PARITY and USB_CDC_*_STOPBIT* to follow the usual
naming pattern.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40091 a95241bf-73f2-0310-859d-f6bbb57e9c96
based on Hamish Morrison's work on a GCI task. The changes I made from his
patch were to move this from preferences to apps (I think it is more of an app
than a preflet) and to change the name back to NetworkTime (he had made it
NTP, but most people probably won't know what that stands for.)
This also fixes#2412.
I noticed some changes this could use but wanted to add it before making any
changes so there is an SVN history of those changes. I'll probably also make an
icon in the next few days.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40088 a95241bf-73f2-0310-859d-f6bbb57e9c96
I assume if this wasn't wanted the ticket would have been closed, and I think
this is fine.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@40085 a95241bf-73f2-0310-859d-f6bbb57e9c96
