DirectShow codec).
Required changes:
- codecs.conf entry (of course).
- Allow opening files with “.col” in the file name, just like “vp3” and “.fpf”
already was allowed. (CineForm expects to be able to do this, presumably
for some color management code.)
- In registry.c, fake a few registry keys that the codec expects the installer
to have written. Also, change a few magic numbers (0, 2) to the appropriate
constants (ERROR_SUCCESS, ERROR_FILE_NOT_FOUND) where appropriate, so the code
is easier to follow.
SMP works fine, but seemingly performs suboptimally (e.g., on my dual-core
laptop, CineForm performs better if I lie to it and tell it I have four cores).
I don't know if this is inherent in the codec, or some inefficiency in the
emulated synchronization primitives.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@31196 b3059339-0415-0410-9bf9-f77b7e298cf2
loader/module.c:618: warning: 'MODULE_DecRefCount' defined but not used
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@31195 b3059339-0415-0410-9bf9-f77b7e298cf2
loader/wine/msacm.h:693: warning: function declaration isn't a prototype
loader/wine/msacm.h:901: warning: function declaration isn't a prototype
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@31003 b3059339-0415-0410-9bf9-f77b7e298cf2
since it's now statically allocated and will not be reallocated if a new
allocation comes along.
This also fixes an issue where the mutex would not always be properly
unlocked, leading to deadlocks. I thought I'd committed that ages ago,
but obviously not, and it broke CineForm initialization.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30957 b3059339-0415-0410-9bf9-f77b7e298cf2
These paths have been deprecated a long time ago, just searching the
default binary codec path is enough nowadays.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30955 b3059339-0415-0410-9bf9-f77b7e298cf2
These files now contain different functions related to path handling.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30943 b3059339-0415-0410-9bf9-f77b7e298cf2
This fixes compilation with the Win32 loader disabled but other binary
codec loaders enabled.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30942 b3059339-0415-0410-9bf9-f77b7e298cf2
It's time we move to 2010: Announce Windows XP SP2 to codecs instead of Win95
OSR2.
Note: We still don't support the *Ex fields in the version info struct
properly (we shouldn't really overwrite the structure size, but rather check
it to see if it's safe to fill the extra fields). No codec I've found seems
to care.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30927 b3059339-0415-0410-9bf9-f77b7e298cf2
Don't hardcode dwNumberOfProcessors=1 for Win32 anymore; the mutex/event code
is still far from perfect, but now good enough that I can't find any codecs
that breaks with this (tested on a quad with various codecs). This tells
codecs they can use more than one core if they want to (some already did, by
launching multiple threads even when told there was only a single core).
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30926 b3059339-0415-0410-9bf9-f77b7e298cf2
InitializeCriticalSectionAndSpinCount returns a nonzero value on success,
and some codecs (notably VP7) seemingly got confused when it didn't, if and
only if we tried to emulate NT or newer.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30913 b3059339-0415-0410-9bf9-f77b7e298cf2
are in place.
Add codecs.conf entry for both codecs, and qt_comp.h entry for ProRes
(not used except for debugging, so mainly for completeness). Both work
with -demuxer mov only, as all other QuickTime binary codecs.
AIC support is for OS X only, and untested.
Split out from a patch Andrew Wason (r e c t a l o g i c <at> rectalogic
<dot> com) posted in June.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30901 b3059339-0415-0410-9bf9-f77b7e298cf2
different structure, and CreateMutexW, CreateEventW and CreateSemaphoreW as
simple wrappers around the A versions.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30900 b3059339-0415-0410-9bf9-f77b7e298cf2
friends) instead of the unsupported, internal ones (ImageCodecBeginBand
etc.). This is a prerequisite for, among others, Apple ProRes 4:2:2 support,
and simplifies the file by quite a bit.
Tested on Linux with all existing QuickTime codecs I could get to work in the
first place; qt261, qtavui, qtsvq3 have no change. qtcvid appears to not give
bit-exact the same output as before, but it looks just the same in playback
to me. qt3ivx stops crashing on exit (so works better than before). With some
extra patches and a codecs.conf entry, ProRes 4:2:2 also works, including on
Linux.
Since codec initialization is now actually done on decoder init instead of on
first frame, fallback should also work a bit better (although usually, qtvideo
is last in the chain). Also made the decoder complain explicitly if the
demuxer data is not there (ie., the user tried to run without -demuxer mov).
This patch is a cleaned up version of what Andrew Wason (rectalogic A
rectalogic D com) posted to mplayer-dev-eng in June.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30899 b3059339-0415-0410-9bf9-f77b7e298cf2
Nowadays MPlayer does not use the codecs from other installed programs.
A runtime setting will soon take over the rare case that binary codecs
should be searched for in non-standard directories.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30888 b3059339-0415-0410-9bf9-f77b7e298cf2
DirectShow specifies that a filter (codec) can expect JoinFilterGraph
to be called, and store a reference to the graph manager. Implement a
very bare-bones graph manager (all functions are stubs, and no extra
interfaces are implemented) and give it to the codec on init.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30866 b3059339-0415-0410-9bf9-f77b7e298cf2
The dpi value for QuickTime codecs is stored as Fixed16 (16.16 fixed-point),
not int. Correct the output value accordingly.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30865 b3059339-0415-0410-9bf9-f77b7e298cf2
Relatively simplistic implementations of ResumeThread (stub) and
SignalObjectAndWait (bAlertable is ignored). Both are needed for ProRes 4:2:2
support on Linux.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30861 b3059339-0415-0410-9bf9-f77b7e298cf2
For some reason commit e306174952, which
replaced translation macro names with the corresponding English
strings, also collapsed multiple consecutive space characters into
one. Change most of these back. In a couple of cases the amount of
whitespace is important for alignment, and for the rest it at least
keeps the strings closer to the existing translations.
The OSErr type on Mac OS X is int16_t, not int32_t (see
http://developer.apple.com/mac/library/documentation/QuickTime/Reference/QTRef_DataTypes/Reference/reference.html).
The upper 16 bits will typically be something random (they're entirely
undefined). Change the type so it's right; a few places tried to compensate
for this by masking out the upper bits, but a few places also missed them,
which made for unpredictable behavior.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30854 b3059339-0415-0410-9bf9-f77b7e298cf2
Implement Win32 mutexes; they used to just be mapped on top of events, which
is not the same thing at all.
The implementation is pretty much the obvious one, similar to the
current critical section implementation and the semaphore implementation;
a single lock count protected by a pthread mutex, and an event lockers can
sleep on to know when the mutex is available.
Also make CreateMutexA and ReleaseMutex available even if QuickTime codecs
support is not configured.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@30853 b3059339-0415-0410-9bf9-f77b7e298cf2
