* Remove duplicated code
* Add new feature flag field introduced with Ryzen
* Add a few missing Intel cache descriptors
* Don't show 80000007 on Intel. Reserved.
* Clean up language to not show "AMD" flags on Intel
...to find files with .pdb extension
Code was subtly wrong in 2 cases:
1) File that ended in pdb but not an extension e.g. filepdb
erroneously included
2) File that ended in .PDB or other case erroneously skipped
Better do a recheck on 32 bit first, my old checks from a few
months ago doesn't seem valid anymore.
This reverts commit 7212666f4a36fcd7d04e19676128df38ef4fdcdd.
Even on 32 bit machines the default is to use 64 bit addresses
because of PAE. Haiku currently forces 32 bit addresses which
probably should be fixed.
See achaiku.h: define ACPI_32BIT_PHYSICAL_ADDRESS
This corrects hrev50847. Turns out we need 8 lines for normal
files and symlinks, not 7. Fixes #13308.
The "Opens with:" label used the decreased font size set in
src/kits/tracker/InfoWindow.cpp:894. Increase font size by 2 again
for the label.
This reverts commit 945566ff43583e4f8102b4440c88f53dae775cb4.
As discussed on the mailing lists and with Humdinger off-list:
* The general design concensus tends slightly towards DejaVu, as metrics
of DejaVu look much better (DejaVu 12 and Noto 13 are roughly the same size,
but Noto has much wider margins with that)
* While Noto does have a wider set of fonts with support for lots of
different languages, DejaVu actually has built-in support for more
Unicode languages (the default Noto has, as far as I can tell, only
Latin/Greek/Cyrillic [2416 glyphs], while DejaVu also has Armenian, Georgian,
and a few other scripts too [5119 glyphs].)
* The worse rendering of DejaVu appears to have been somewhat rectified by
disabling the average-based subpixel filter in app_server.
* When --host-only is used, HAIKU_*ARCH is undefined.
* Various architecture variables are undefined resulting
in architecture dependant code paths getting called
recursively.
(blah/Jamfile loads blah//Jamfile vs blah/x86/Jamfile)
* Another option is setting HAIKU_*ARCH to the host arch
if undefined, but that might have unintended impacts.
It fails, of course, because it hasn't been ported to the new stack.
(I made an attempt at that, but quickly wound up in code that I didn't
understand enough to migrated...)
Update all in-tree consumers of the BJson API to match. Also added
const-qualifiers to the BString versions of the API, and added the leading
"_" to the header guards.
As found on http://seriot.ch/parsing_json.php -- anything using the API
presently with valid JSON should have no troubles, but more valid JSON
that previously didn't work now does (e.g. JSON with root array nodes, not
root map nodes), and invalid JSON that silently succeeded before now fails.
Not all the bad cases from that testsuite now fail, and not all of the good
ones pass, but the few that remain are odd things that wouldn't map well to
the BMessage API (e.g. root string nodes, etc.) or are other behaviors that
make sense to leave as they are for compatibility reasons.
