1
0
mirror of https://github.com/mpv-player/mpv synced 2024-12-24 15:52:25 +00:00
Commit Graph

763 Commits

Author SHA1 Message Date
wm4
0e97808fc5 player: show AV-desync message in all framedrop modes
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.
2014-11-01 01:06:22 +01:00
wm4
3f3a6b13bd sub: remove osd_get_sub()
Trades one strange thing against another, but seems slightly less
strange.
2014-11-01 00:02:01 +01:00
wm4
13d408fe8d sub: be more flexible about changes to how subtitles are rendered
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.
2014-10-31 23:43:22 +01:00
wm4
b17585e636 player: change framedrop display in the status line
Hopefully less confusing, and hopefully doesn't exceed the terminal
width in any situation.
2014-10-31 01:01:58 +01:00
wm4
6ddd2b8e03 player: improve exit message in some scenarios
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.
2014-10-31 00:51:52 +01:00
wm4
2bb02879aa player: don't display zero duration for files with unknown duration
On OSD/terminal, just don't display the duration if unavailable.

Make the "length" property unavailable if duration is unavailable.
2014-10-29 21:54:59 +01:00
wm4
2c320fb609 player: add an option to abort playback on partial init failures
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).
2014-10-28 20:30:12 +01:00
wm4
0c71ae0528 player: handle DVB demuxer reloading correctly
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.
2014-10-28 20:30:12 +01:00
wm4
65db3291b3 client API: better error reporting
Give somewhat more information on playback failure.
2014-10-28 20:30:12 +01:00
wm4
3cde02fe22 client API: add an enum for mpv_event_end_file.reason
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.
2014-10-28 20:30:12 +01:00
wm4
77b06fa017 player: handle edition reloading slightly differently
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).
2014-10-28 20:30:12 +01:00
Alessandro Ghedini
650e889752 command: play the correct entry with loadfile ... append-play
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.
2014-10-27 21:50:43 +01:00
wm4
963edf5765 player: don't spam video-reconfig event
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).
2014-10-27 21:05:21 +01:00
Alessandro Ghedini
c18cf4394d command: try 'icy-title' metadata for media-title as well 2014-10-27 16:21:50 +01:00
wm4
dced2aa81b command: add audio-device property
Meant for changing the --audio-device at runtime.
2014-10-27 12:18:25 +01:00
wm4
d5b081152a audio: add command/function to reload audio output
Anticipated use: simple solution for dealing with audio APIs which
request configuration changes via events.
2014-10-27 11:52:42 +01:00
wm4
f2d51171f7 lua: subprocess: fix dumb 2014-10-26 01:52:31 +02:00
wm4
d0643fa02d lua: subprocess: tunnel stderr through mp_log
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.
2014-10-26 01:40:36 +02:00
wm4
38546d5a99 lua: parse_json(): fix inverted condition for trail argument
It accidentally had the opposite meaning.
2014-10-26 01:40:36 +02:00
wm4
0cfada604d lua: subprocess: don't distinguish pipe errors/EOF
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.
2014-10-26 01:40:36 +02:00
wm4
9b45b48c46 Drop libquvi support
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.
2014-10-25 20:18:22 +02:00
wm4
5b91f89852 lua: fix some more lua_tostring() mistakes
Why can't it just raise an error?
2014-10-25 17:20:25 +02:00
wm4
ef252b2314 lua: lua_tostring() on an error value can return NULL
Lua is so clever it allows values that can't be converted to strings, in
which case lua_tostring() returns NULL. Trigger undefined behavior.
2014-10-24 21:57:06 +02:00
wm4
55e3dab7eb command: finish hook execution if client fails
Translation: if the (to be added) youtube-dl Lua script crashes, don't
wait forever when opening something.
2014-10-24 21:57:02 +02:00
wm4
f1481df0b6 command: add vo-configured property
So a client API user can know when a window is created or destroyed.

Also might be useful for the OSC: it could disable itself if video is
disabled.

Before this commit, there were only indirect ways of detecting this.
2014-10-24 15:34:53 +02:00
wm4
96b339fc07 player: disable --force-window if VO fails
Otherwise, it'd retry creating the window all the time.
2014-10-24 15:34:39 +02:00
wm4
f4ad398b28 video: send MPV_EVENT_VIDEO_RECONFIG on uninit
This event basically means "something about video changed", and uninit
is certainly an important change.
2014-10-24 15:34:28 +02:00
wm4
db86eaad3d player: adjust uninit order of components
Most things should be allowed to access the client API unconditionally
(for example for sending events), so move destroying the client API
down. Also, mp_uninit_ipc() should happen before the point at which all
clients are shutdown, or there will be a small time window in which new
clients can be created after destroying them all.
2014-10-24 15:34:04 +02:00
wm4
986d15ea9c command: fix debug output
It was a bit ugly/annoying.
2014-10-24 13:42:02 +02:00
ChrisK2
223d9b6bc9 osc: make text squuezing layout dependent
Wether and when the text of a button should be squeezed when it
gets too long can now be configured in the layout:

lo.button.maxchars = <number>
nil = no squeezing (default)

If the button text has more than <maxchars> characters, it will
be squeezed to the estimated width of <maxchars>.
2014-10-24 01:56:15 +02:00
ChrisK2
bff5948f00 osc: make tooltip_an default property 2014-10-24 01:16:04 +02:00
wm4
c9234d769d player: fix exiting if both audio and video fail initializing
The player was supposed to exit playback if both video and audio failed
to initialize (or if one of the streams was not selected when the other
stream failed). This didn't work; for one this check was missing from
one of the failure paths. And more importantly, both checked the
current_track array incorrectly.

Fix these issues, and move the failure handling code into a common
function.

CC: @mpv-player/stable
2014-10-23 18:31:43 +02:00
wm4
626dcf1772 lua: fix non-sense
Let's actually test our code next time.
2014-10-23 15:13:05 +02:00
wm4
7cf18a8db9 client API: print properties set with -v
Useful for debugging. Considered doing this in command.c, but it's
easier here.
2014-10-23 15:13:05 +02:00
wm4
dd77f0d37e command: print executed commands with -v 2014-10-23 15:13:05 +02:00
wm4
7e27663b7b command: add a "cached" mode to sub_add
This avoids reloading a subtitle if it was already added. In all cases,
the subtitle is selected.
2014-10-23 13:13:23 +02:00
Martin Herkt
5a3c6563e4 osc.lua: add “bottombar” and “topbar” layouts 2014-10-23 13:02:32 +02:00
wm4
41c91d87d6 command: return error on invalid/absent IDs with ff-sid/ff-aid
Instead of just disabling the stream.

Also, check if the selected track has the right type, or we'd crash.
2014-10-23 12:03:26 +02:00
wm4
be950351d9 player: show busy symbol on OSD if seeking takes too long
Same as it's done on the terminal.
2014-10-22 16:11:44 +02:00
wm4
65ba6f9f57 lua: don't let temporary values take the place of arguments
Because Lua is so terrible, it's easy to confuse temporary values pushed
to the Lua stack with arguments if the arguments are checked after that.

Add a hack that should fix this.
2014-10-22 01:10:15 +02:00
wm4
7eb047b241 command: make reverse cycle_values match up with forward one
The behavior of reverse cycling (with the "!reverse" magic value) was a
bit weird and acted with a "delay". This was because the command set the
value the _next_ command should use. Change this and make each command
invocation select and use the next command directly. This requires an
"uninitialized" special index in the counter, but that is no problem at
all.
2014-10-21 23:55:32 +02:00
wm4
4d5903f915 command: fix video-rotate update when paused
Due to the way video-rotate currently works, the state will be
automatically updated once new video is decoded. So the filter chain
doesn't need to be reinitialized automatically, but there is a need to
trigger the video instant refresh code path instead.

Also move the support function closer to an annoying similar yet
different function. They probably can be unified next time major changes
are done to this code.
2014-10-21 23:34:56 +02:00
wm4
bd315dfaf9 lua: don't use "output" as identifier
I suspect this clashes with libcs,w hich define "stdout" as macro.
Hopefully fixes #1206.
2014-10-21 13:44:21 +02:00
wm4
bc1893e036 command: add cursor-autohide property
Allows properly changing/updating the cursor state. Useful for client
API window embedding, because the host application may not want the mpv
window to grab mouse input, and this has to manually handle the cursor.
Changing the cursor of foreign windows is usually not sane.

It might make sense to allow changing the cursor icon, but that would be
much more complicated, so I won't add it unless someone actually
requests it.
2014-10-21 13:42:15 +02:00
wm4
0fa9e2bff0 command: add playback-abort property
Now this is obscure.
2014-10-21 13:38:41 +02:00
wm4
cdbc865ad0 command: add video-rotate property 2014-10-21 13:31:30 +02:00
wm4
f0f83ff366 player: add stream selection by ffmpeg index
Apparently using the stream index is the best way to refer to the same
streams across multiple FFmpeg-using programs, even if the stream index
itself is rarely meaningful in any way.

For Matroska, there are some possible problems, depending how FFmpeg
actually adds streams. Normally they seem to match though.
2014-10-21 13:19:20 +02:00
wm4
bcc3d72995 sd_lavc: strictly letter-box PGS subtitles
Getting subtitle scaling and positioning right even if there are video
filters, which completely change the image (like cropping), doesn't seem
to have a single, correct solution. To some degree, the results are
arbitrary, so we may as well do what is most useful to the user.

In this case, if the PGS resolution aspect ratio and the video output
aspect ratio mismatch, letter-box it, instead of stretching the subs
over the video frame. (This will require additional fixes, should it
turn out that there are PGS subtitles which are stretched by design.)

Fixes #1205.
2014-10-21 11:37:32 +02:00
Kevin Mitchell
599c510902 command: add field-dominance property 2014-10-21 00:55:15 +02:00
wm4
40d6b5ca85 lua: add convenience function for hooks
So the user doesn't have to care about the awkward low-level details.
2014-10-21 00:38:56 +02:00