summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* manpage: update --playlist commentswm42014-11-022-9/+10
| | | | | | | | | | | | | | Using the --playlist option is no longer recommended. A while ago, mpv rewrote all playlist parsers and added some minimal security mechanisms (like not allowing local file access or unsafe protocols in remote playlists). Further, mpv can load playlists by passing them as normal file arguments, without the option. Now, --playlist is needed only in these situations: 1) loading plaintext files 2) disabling additional security mechanisms (e.g. using a remote playlist to play local files)
* osd: properly wakeup when the OSD function disappearswm42014-11-011-3/+10
| | | | Fixes #1236.
* cocoa: fix fullscreen delay when pausedStefano Pigozzi2014-11-011-2/+2
| | | | | | NSDisableScreenUpdates came to hunt me in the end and when mpv was paused, it did wait for a frame that never came (because of interaction with the live resizing code)!
* build: remove bundle support from wafStefano Pigozzi2014-11-011-0/+1
| | | | Use TOOLS/osxbundle.py instead. It's just better and less hacky.
* ipc: make it possible to receive log messageswm42014-11-012-0/+23
| | | | | The receiving part was implemented, but since no messages are enabled by default, it couldn't be used.
* ipc: add a command to retrieve API versionwm42014-11-012-0/+8
|
* ipc: verify resume/suspend commandswm42014-11-011-4/+16
| | | | | Calling mpv_resume() too often is considered an API usage violation, and will trigger an internal assertion somewhere.
* manpage: ipc: fix command name for observe_propertywm42014-11-011-1/+1
|
* build: remove bundle support from wafStefano Pigozzi2014-11-012-30/+1
| | | | Use TOOLS/osxbundle.py instead. It's just better and less hacky.
* player: update meaning of drop_frame_cntwm42014-11-015-12/+12
| | | | | Rename the variable, update comments, and update the documentation of the property which returns its value.
* player: show AV-desync message in all framedrop modeswm42014-11-011-2/+1
| | | | | | | | | | | | This was shown only if decoder-framedropping was enabled, and only if at least 50 frames were dropped by it. Since drop_frame_cnt used to mean "number of late frames", this code made sense, but this is not the case anymore: drop_frame_cnt can be even 0, all while video gets hopelessly behind audio. One problem with this is that short desync spikes (which usually can probably dealt with) will also cause this message to be shown. If it gets triggered too often, the code will need to be adjusted.
* build: fix 'ar' invocation when cross-compilingwm42014-11-011-1/+3
| | | | | | | | This shouldn't use the host's 'ar' when building static libs. It only worked until now because Linux 'ar' is usually built with PE support. Couldn't confirm whether it works, because this dumb crap is just broken when cross-compiling to mingw.
* cache: don't relay STREAM_CTRL_AVSEEK if it's unsupportedwm42014-11-011-0/+4
| | | | | | | | Thanks to STREAM_CTRL_HAS_AVSEEK, we actually know whether CTRL_AVSEEK is implemented at all, and we can avoid a blocking wait on the cache if demux_lavf sends CTRL_AVSEEK even if it won't wait. I'm hoping this can't currently happen, but why hope if we can explicitly prevent it. It'll make us more robust against future changes in libavformat.
* sub: remove osd_get_sub()wm42014-11-015-13/+7
| | | | | Trades one strange thing against another, but seems slightly less strange.
* command: don't require whitespace before ';' or '#'wm42014-10-311-4/+1
| | | | | | | This change is probably too simplistic, but most things appear to work, so I don't care about that now. Fixes #1232.
* sub: be more flexible about changes to how subtitles are renderedwm42014-10-311-20/+32
| | | | | | | | | For example, if --force-window is used, and video is switched off during playback, then you need to redecide the rendering method to get subs displayed correctly. Do this by moving the state setup code into a function, and call it on every frame.
* osdep: potentially fix compilation on OpenBSDwm42014-10-311-0/+1
| | | | | The <pthread_np.h> header expects that <pthread.h> was already included. We were including <pthread.h> only later via our threads.h.
* ao_alsa: don't make snd_pcm_hw_params_set_buffer_time_near() error fatalwm42014-10-311-1/+7
| | | | | | | | | | | | | Apparently this can "sometimes" return an error. In my opinion, this should never return an error: neither the semantics of the function, nor the ALSA documentation or ALSA sample code seem to indicate that a failure is to be expected. I'm not perfectly sure about this though (I blame ALSA being a weird, big, underdocumented API). Since it causes problems for some users, and since there is really no reason why we should abort on such an error, turn it into a warning. Fixes #1231.
* player: change framedrop display in the status linewm42014-10-312-12/+14
| | | | | Hopefully less confusing, and hopefully doesn't exceed the terminal width in any situation.
* player: improve exit message in some scenarioswm42014-10-313-63/+58
| | | | | | | | | | | | | | If you played e.g. an audio-only file and something bad happened that interrupted playback, the exit message could say "No files played". This was awkward, so show a different message in this case. Also overhaul how the exit status is reported in order to make this easier. This includes things such as not reporting a playback error when loading playlists (playlists contain no video or audio, which was considered an error). Not sure if I'm happy with this, but for now it seems like a slight improvement.
* options: accept --audio-channels=autowm42014-10-302-2/+4
| | | | This sounds much more intuitive, while "empty" was a bit of a WTF.
* demux_lavf, stream_lavf: drop local buffers on time-seekswm42014-10-302-3/+8
| | | | | There was chance that some data was left in various local buffers after time-seeks. Probably doesn't actually matter.
* demux_lavf: mark as seekable if protocol supports seeking by timewm42014-10-304-0/+11
| | | | | | | | | | | | Basically, this will mark the demuxer as seekable with rtmp* and mmsh protocols. These protocols have network-level time seeking, and whether you can seek on the byte level does not matter. Until now, seeking was typically only enabled because of the cache, and a (nonsensical) warning was shown accordingly. It still could happen that the server doesn't actually support thse requests (or simply rejects them), so this is somewhat imperfect.
* demux_playlist: redirect ASF streaming to mmsh://wm42014-10-301-14/+30
| | | | | | | | | | | | I'm not sure if this could be done in libavformat instead. Probably not, because libavformat doesn't seem to have any mechanism for trying one protocol and reverting (or redirecting) to another one if needed. This commit is sort of a hack too, because it redirects the URL by pretending the http:// link is a playlist containing the mmsh:// link. The list of mime types is borrowed from MPlayer (which has completely different code to handle this).
* client API: qthelper: add set_option_variant()wm42014-10-302-0/+11
|
* vo_opengl: draw OSD twice in 3D mode casewm42014-10-293-7/+57
| | | | | | | | | | | | | Apparently this is needed for correct 3D mode subtitles. In general, it seems you need to duplicate the whole "GUI", so it's done for all OSD elements. This doesn't handle the "duplication" of the mouse pointer. Instead, the mouse can be used for the top/left field only. Also, it's possible that we should "compress" the OSD in the direction it's duplicated, but I don't know about that. Fixes #1124, at least partially.
* input: cascade-load input.confwm42014-10-291-8/+6
| | | | | If there are several input.confs in the set of valid config paths, load them all.
* demux: fix demux_seek signaturewm42014-10-292-2/+2
| | | | Probably doesn't matter much.
* demux: move some seek flag sanitation to generic codewm42014-10-292-10/+15
| | | | No reason why only demux_mkv.c should do this.
* demux_mkv: implement percentage seeking with no indexwm42014-10-291-22/+24
| | | | It was implemented only for the case the index exists (pretty useless).
* demux_mkv: export packet file positionwm42014-10-291-0/+1
| | | | | This gives us approximate fallback playback percentage position if the duration is unknown.
* player: don't display zero duration for files with unknown durationwm42014-10-294-17/+22
| | | | | | On OSD/terminal, just don't display the duration if unavailable. Make the "length" property unavailable if duration is unavailable.
* player: add an option to abort playback on partial init failureswm42014-10-287-3/+16
| | | | | | This is probably what libmpv users want; and it also improves error reporting (or we'd have to add a way to communicate such mid-playback failures as events).
* player: handle DVB demuxer reloading correctlywm42014-10-281-2/+2
| | | | | | | | This was probably done incorrectly in cases when the currently selected channel had no data. I'm not sure if this codepath is functional at all, though. Maybe not. Untested due to lack of DVB hardware.
* client API: better error reportingwm42014-10-288-25/+92
| | | | Give somewhat more information on playback failure.
* client API: add an enum for mpv_event_end_file.reasonwm42014-10-283-12/+30
| | | | | | | | | Using magic integer values was an attempt to keep the API less verbose. But it was probably not a good idea. Reason 1 (restart) is not made explicit, because it is not used anymore starting with the previous commit. For ABI compatibility, the value is left as a hole in the enum.
* player: handle edition reloading slightly differentlywm42014-10-283-11/+11
| | | | | | | Use the codepath that is normally used for DVD/BD title switching and DVB channel switching. Removes some extra artifacts from the client API: now MPV_EVENT_END_FILE will never be called on reloads (and neither is MPV_EVENT_START_FILE).
* demux: seek to position 0 when loading, instead of restoring itwm42014-10-281-7/+7
| | | | | | | | | | This was originally done for DVD/BD/DVB, where the start position could be something different from 0, and seeking back to 0 would mess it up completely. Since we're not quite sure that these streams are unseekable, we can simplify this somewhat, and also make sure we also start at 0 for normal files. Helps a little bit with the following edition reloading commit.
* client API: clarify statement about thread-safetywm42014-10-281-5/+6
| | | | | | | | | The only reason for mpv_wait_event() not being thread-safe is that it returns a pointer to a mpv_event struct member in the mpv_handle context, which in turn is done for ABI-safety (user doesn't allocate or manage the struct), and to avoid the need additional memory management. Some users were interpreting this incorrectly.
* coreaudio: only list output devicesStefano Pigozzi2014-10-281-0/+12
|
* manpage: clarify loadfile append-play modewm42014-10-281-1/+3
| | | | Documents the behavior introduced with the previous commit.
* command: play the correct entry with loadfile ... append-playAlessandro Ghedini2014-10-271-1/+1
| | | | | The playlist may be non-empty even if the player is idle. Instead of playing the first entry, play the entry that was just added.
* player: don't spam video-reconfig eventwm42014-10-271-1/+1
| | | | | | | | Without --force-window, this is called on every iteration or so, and calling uninit_video_out() sends the video-reconfig event. Avoid sending redundant events. Fixes #1225 (using an alternative patch).
* cocoa: fix small leakStefano Pigozzi2014-10-271-0/+1
|
* libmpv: cocoa: fix view leak on uninitStefano Pigozzi2014-10-271-4/+6
| | | | | The code was lacking a -removeFromSuperview call which resulted in a leak on our part if the parent view in the client was not released.
* libmpv: cocoa: add basic menuStefano Pigozzi2014-10-271-10/+7
|
* command: try 'icy-title' metadata for media-title as wellAlessandro Ghedini2014-10-271-0/+3
|
* x11: fix display FPS detection for interlaced modeswm42014-10-271-1/+6
| | | | | | | | | In interlaced modes, we output fields, not complete frames, so the framerate doubles. The method to calculate this was borrowed from xrandr code. Hopefully fixes #1224.
* dxva2: use gpu_memcpy with unmatched stridesJames Ross-Gowan2014-10-271-8/+29
| | | | Like memcpy_pic, this checks if the strides match first.
* command: add audio-device propertywm42014-10-272-0/+24
| | | | Meant for changing the --audio-device at runtime.
* audio: add command/function to reload audio outputwm42014-10-276-1/+29
| | | | | Anticipated use: simple solution for dealing with audio APIs which request configuration changes via events.
* dxva2: fix copying surfaces with different strideJames Ross-Gowan2014-10-271-10/+18
|
* dxva2: fix crash on initialization failurewm42014-10-261-0/+2
| | | | If dxva2_init() fails, dxva2_uninit() will be called twice.
* TOOLS/lua/autoload: fix operation outside of working dirwm42014-10-261-3/+7
| | | | Fixes #1222. (This commit is based on a patch posted there.)
* TOOLS/lua/autoload: don't shadow local variablewm42014-10-261-4/+4
| | | | "dir" is already used somewhere above. This was ok, but not nice.
* manpage: options: various fixesAlessandro Ghedini2014-10-261-9/+9
|
* dxva2: gpu_memcpy: fix build for GCC 4.8.3James Ross-Gowan2014-10-261-3/+10
|
* vo_direct3d: support nv12/nv21 directlywm42014-10-261-0/+8
|
* video: clarify what IMFMT_DXVA2 iswm42014-10-261-1/+1
|
* dxva2: use optimized memcpyJames Ross-Gowan2014-10-263-12/+165
| | | | | | At least on my machine, reading back the frame with system memcpy is slower than just using software rendering. Use the optimized gpu_memcpy from LAV to speed things up.
* lua: subprocess: fix dumbwm42014-10-261-1/+1
|
* lua: subprocess: tunnel stderr through mp_logwm42014-10-261-20/+63
| | | | | | | | | | | Pretty much a fringe-feature, but also it's awkward if something appears on the terminal with no indication for the source. This is made quite awkward by the fact that stderr and stdout could be closed at different times, and that poll() doesn't accept "holes" in its FD list. Invalid (.e.g negative) FDs just make it return immediately, as required by the standard. So sparse_poll() takes care of the messy details.
* osdep: add helper for creating a sane pipe()wm42014-10-262-4/+21
| | | | | Or in other words, a pipe that has the CLOEXEC flag set. Needed since Linux' pipe2() is not in POSIX yet.
* lua: parse_json(): fix inverted condition for trail argumentwm42014-10-261-1/+1
| | | | It accidentally had the opposite meaning.
* lua: subprocess: don't distinguish pipe errors/EOFwm42014-10-261-7/+4
| | | | | | | What was the purpose of that? Probably none. Also simplify another thing: if we get the cancel signal through FD, there's no reason to check it separately.
* build: fix Lua detectionStefano Pigozzi2014-10-251-2/+4
| | | | | | | | | | | | | We need to manually define the flag since we are using a separate identifier for each of the Lua checks. This was done before 9b45b48 by the composed check with a define_key (see waftools/checks/generic.py). The pkg-config check was the only one to not redefine a define key because Waf already does that automatically when we call the generated function with the same identifier as the generator function. Now if they are called with two different arguments we will get two different definitions. Fixes #1218
* Drop libquvi supportwm42014-10-2521-555/+12
| | | | | | | | | | | No development activity (or even any sign of life) for almost a year. A replacement based on youtube-dl will probably be provided before the next mpv release. Ask on the IRC channel if you want to test. Simplify the Lua check too: libquvi linking against a different Lua version than mpv was a frequent issue, but with libquvi gone, no direct dependency uses Lua, and such a clash is rather unlikely.
* video: initial dxva2 supportwm42014-10-259-2/+623
| | | | | Shamelessly stolen from ffmpeg. It probably doesn't work - you can debug it yourself.
* manpage: use the proper environment variable for CSIDL_APPDATAwm42014-10-251-4/+8
|
* tv: remove some differences between immediate/normal modewm42014-10-251-38/+23
| | | | | | | | | | | The immediate mode (which is the default) uses a tiny ringbuffer and doesn't grab timestamps. This leads to quite bad behavior due to the fact that there's an additional buffer between playloop and TV code (the demuxer thread, which doesn't exist in MPlayer). Always grab the timestamps and use a decently-sized buffer. I still have no clue what I'm doing, and hacked it until it appeared to work. Report regressions if you experience any.
* tv: reduce waiting loop from 10ms to 1mswm42014-10-251-2/+2
| | | | | | | | | | | | I can't believe how shitty this (MPlayer-derived) code is. Maybe it should be fixed or be replaced with using libavdevice, but that doesn't seem worth the effort. Anyway, for now reduce the time it's blocking to wait for new frames from 10ms to 1ms, because 10ms might be a bit too tight: it could deliver the frame up to 10ms late - now it's only up to 1ms. (And yes, it does that instead of using condition variables. It also abuses volatile variables as atomics. It's hilarious.)
* lua: fix some more lua_tostring() mistakeswm42014-10-251-1/+3
| | | | Why can't it just raise an error?
* build: enable cdda:// by default againwm42014-10-251-1/+0
| | | | | | Apparently people want this. (