Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
 help / color / mirror / Atom feed
From: toots@rastageeks.org
To: ffmpeg-devel@ffmpeg.org
Cc: thilo.borgmann@mail.de, Romain Beauxis <toots@rastageeks.org>,
	epirat07@gmail.com
Subject: [FFmpeg-devel] [PATCH 3/4] libavdevice/avfoundation.m: use setAudioSettings, extend supported formats
Date: Sun, 30 Jan 2022 11:30:47 -0600
Message-ID: <20220130173045.32690-4-toots@rastageeks.org> (raw)
In-Reply-To: <20220130173045.32690-1-toots@rastageeks.org>

From: Romain Beauxis <toots@rastageeks.org>

This patch reworks the workflow for audio input to extend the range of supported input formats and delegate to the underlying OS the task of converting audio input format.

Previous version of these changes used the AudioConverter API to perform audio conversion explicitly however, it was found to be bug prone with issues seemingly coming from the underlying OS.

This fixes: https://trac.ffmpeg.org/ticket/9502

Signed-off-by: Romain Beauxis <toots@rastageeks.org>
---
 libavdevice/avfoundation.m | 206 ++++++++++++-------------------------
 1 file changed, 63 insertions(+), 143 deletions(-)

diff --git a/libavdevice/avfoundation.m b/libavdevice/avfoundation.m
index a837042a6d..db9501445d 100644
--- a/libavdevice/avfoundation.m
+++ b/libavdevice/avfoundation.m
@@ -96,6 +96,11 @@
     AVRational      framerate;
     int             width, height;
 
+    int             channels;
+    int             big_endian;
+    int             sample_rate;
+    enum AVSampleFormat sample_format;
+
     int             capture_cursor;
     int             capture_mouse_clicks;
     int             capture_raw_data;
@@ -114,17 +119,6 @@
 
     int             num_video_devices;
 
-    int             audio_channels;
-    int             audio_bits_per_sample;
-    int             audio_float;
-    int             audio_be;
-    int             audio_signed_integer;
-    int             audio_packed;
-    int             audio_non_interleaved;
-
-    int32_t         *audio_buffer;
-    int             audio_buffer_size;
-
     enum AVPixelFormat pixel_format;
 
     AVCaptureSession         *capture_session;
@@ -301,14 +295,6 @@ static void destroy_context(AVFContext* ctx)
     ctx->audio_output    = NULL;
     ctx->avf_delegate    = NULL;
     ctx->avf_audio_delegate = NULL;
-
-    av_freep(&ctx->audio_buffer);
-
-    pthread_mutex_destroy(&ctx->frame_lock);
-
-    if (ctx->current_frame) {
-        CFRelease(ctx->current_frame);
-    }
 }
 
 static void parse_device_name(AVFormatContext *s)
@@ -674,88 +660,62 @@ static int get_video_config(AVFormatContext *s)
 static int get_audio_config(AVFormatContext *s)
 {
     AVFContext *ctx = (AVFContext*)s->priv_data;
-    CMFormatDescriptionRef format_desc;
-    AVStream* stream = avformat_new_stream(s, NULL);
+    AVStream* stream;
+    int bits_per_sample, is_float;
 
-    if (!stream) {
-        return 1;
-    }
+    enum AVCodecID codec_id = av_get_pcm_codec(ctx->sample_format, ctx->big_endian);
 
-    // Take stream info from the first frame.
-    while (ctx->audio_frames_captured < 1) {
-        CFRunLoopRunInMode(kCFRunLoopDefaultMode, 0.1, YES);
+    if (codec_id == AV_CODEC_ID_NONE) {
+       av_log(ctx, AV_LOG_ERROR, "Error: invalid sample format!\n");
+       return AVERROR(EINVAL);
     }
 
-    lock_frames(ctx);
-
-    ctx->audio_stream_index = stream->index;
-
-    avpriv_set_pts_info(stream, 64, 1, avf_time_base);
-
-    format_desc = CMSampleBufferGetFormatDescription(ctx->current_audio_frame);
-    const AudioStreamBasicDescription *basic_desc = CMAudioFormatDescriptionGetStreamBasicDescription(format_desc);
+    switch (ctx->sample_format) {
+        case AV_SAMPLE_FMT_S16:
+            bits_per_sample = 16;
+            is_float = 0;
+            break;
+        case AV_SAMPLE_FMT_S32:
+            bits_per_sample = 32;
+            is_float = 0;
+            break;
+        case AV_SAMPLE_FMT_FLT:
+            bits_per_sample = 32;
+            is_float = 1;
+            break;
+        default:
+            av_log(ctx, AV_LOG_ERROR, "Error: invalid sample format!\n");
+            unlock_frames(ctx);
+            return AVERROR(EINVAL);
+    }
 
-    if (!basic_desc) {
+    [ctx->audio_output setAudioSettings:@{
+        AVFormatIDKey:               @(kAudioFormatLinearPCM),
+        AVLinearPCMBitDepthKey:      @(bits_per_sample),
+        AVLinearPCMIsFloatKey:       @(is_float),
+        AVLinearPCMIsBigEndianKey:   @(ctx->big_endian),
+        AVNumberOfChannelsKey:       @(ctx->channels),
+        AVLinearPCMIsNonInterleaved: @NO,
+        AVSampleRateKey:             @(ctx->sample_rate)
+    }];
+
+    stream = avformat_new_stream(s, NULL);
+    if (!stream) {
         unlock_frames(ctx);
-        av_log(s, AV_LOG_ERROR, "audio format not available\n");
-        return 1;
+        return -1;
     }
 
+    avpriv_set_pts_info(stream, 64, 1, avf_time_base);
+
     stream->codecpar->codec_type     = AVMEDIA_TYPE_AUDIO;
-    stream->codecpar->sample_rate    = basic_desc->mSampleRate;
-    stream->codecpar->channels       = basic_desc->mChannelsPerFrame;
+    stream->codecpar->sample_rate    = ctx->sample_rate;
+    stream->codecpar->channels       = ctx->channels;
     stream->codecpar->channel_layout = av_get_default_channel_layout(stream->codecpar->channels);
+    stream->codecpar->codec_id       = codec_id;
 
-    ctx->audio_channels        = basic_desc->mChannelsPerFrame;
-    ctx->audio_bits_per_sample = basic_desc->mBitsPerChannel;
-    ctx->audio_float           = basic_desc->mFormatFlags & kAudioFormatFlagIsFloat;
-    ctx->audio_be              = basic_desc->mFormatFlags & kAudioFormatFlagIsBigEndian;
-    ctx->audio_signed_integer  = basic_desc->mFormatFlags & kAudioFormatFlagIsSignedInteger;
-    ctx->audio_packed          = basic_desc->mFormatFlags & kAudioFormatFlagIsPacked;
-    ctx->audio_non_interleaved = basic_desc->mFormatFlags & kAudioFormatFlagIsNonInterleaved;
-
-    if (basic_desc->mFormatID == kAudioFormatLinearPCM &&
-        ctx->audio_float &&
-        ctx->audio_bits_per_sample == 32 &&
-        ctx->audio_packed) {
-        stream->codecpar->codec_id = ctx->audio_be ? AV_CODEC_ID_PCM_F32BE : AV_CODEC_ID_PCM_F32LE;
-    } else if (basic_desc->mFormatID == kAudioFormatLinearPCM &&
-        ctx->audio_signed_integer &&
-        ctx->audio_bits_per_sample == 16 &&
-        ctx->audio_packed) {
-        stream->codecpar->codec_id = ctx->audio_be ? AV_CODEC_ID_PCM_S16BE : AV_CODEC_ID_PCM_S16LE;
-    } else if (basic_desc->mFormatID == kAudioFormatLinearPCM &&
-        ctx->audio_signed_integer &&
-        ctx->audio_bits_per_sample == 24 &&
-        ctx->audio_packed) {
-        stream->codecpar->codec_id = ctx->audio_be ? AV_CODEC_ID_PCM_S24BE : AV_CODEC_ID_PCM_S24LE;
-    } else if (basic_desc->mFormatID == kAudioFormatLinearPCM &&
-        ctx->audio_signed_integer &&
-        ctx->audio_bits_per_sample == 32 &&
-        ctx->audio_packed) {
-        stream->codecpar->codec_id = ctx->audio_be ? AV_CODEC_ID_PCM_S32BE : AV_CODEC_ID_PCM_S32LE;
-    } else {
-        unlock_frames(ctx);
-        av_log(s, AV_LOG_ERROR, "audio format is not supported\n");
-        return 1;
-    }
-
-    if (ctx->audio_non_interleaved) {
-        CMBlockBufferRef block_buffer = CMSampleBufferGetDataBuffer(ctx->current_audio_frame);
-        ctx->audio_buffer_size        = CMBlockBufferGetDataLength(block_buffer);
-        ctx->audio_buffer             = av_malloc(ctx->audio_buffer_size);
-        if (!ctx->audio_buffer) {
-            unlock_frames(ctx);
-            av_log(s, AV_LOG_ERROR, "error allocating audio buffer\n");
-            return 1;
-        }
-    }
-
-    CFRelease(ctx->current_audio_frame);
-    ctx->current_audio_frame = nil;
+    ctx->audio_stream_index = stream->index;
 
     unlock_frames(ctx);
-
     return 0;
 }
 
@@ -1056,6 +1016,7 @@ static int avf_read_header(AVFormatContext *s)
         goto fail;
     }
     if (audio_device && add_audio_device(s, audio_device)) {
+        goto fail;
     }
 
     [ctx->capture_session startRunning];
@@ -1129,6 +1090,7 @@ static int copy_cvpixelbuffer(AVFormatContext *s,
 
 static int avf_read_packet(AVFormatContext *s, AVPacket *pkt)
 {
+    OSStatus ret;
     AVFContext* ctx = (AVFContext*)s->priv_data;
 
     do {
@@ -1172,7 +1134,7 @@ static int avf_read_packet(AVFormatContext *s, AVPacket *pkt)
                 status = copy_cvpixelbuffer(s, image_buffer, pkt);
             } else {
                 status = 0;
-                OSStatus ret = CMBlockBufferCopyDataBytes(block_buffer, 0, pkt->size, pkt->data);
+                ret = CMBlockBufferCopyDataBytes(block_buffer, 0, pkt->size, pkt->data);
                 if (ret != kCMBlockBufferNoErr) {
                     status = AVERROR(EIO);
                 }
@@ -1186,19 +1148,17 @@ static int avf_read_packet(AVFormatContext *s, AVPacket *pkt)
             }
         } else if (ctx->current_audio_frame != nil) {
             CMBlockBufferRef block_buffer = CMSampleBufferGetDataBuffer(ctx->current_audio_frame);
-            int block_buffer_size         = CMBlockBufferGetDataLength(block_buffer);
 
-            if (!block_buffer || !block_buffer_size) {
-                unlock_frames(ctx);
-                return AVERROR(EIO);
-            }
+            size_t buffer_size = CMBlockBufferGetDataLength(block_buffer);
 
-            if (ctx->audio_non_interleaved && block_buffer_size > ctx->audio_buffer_size) {
+            int status = av_new_packet(pkt, buffer_size);
+            if (status < 0) {
                 unlock_frames(ctx);
-                return AVERROR_BUFFER_TOO_SMALL;
+                return status;
             }
 
-            if (av_new_packet(pkt, block_buffer_size) < 0) {
+            ret = CMBlockBufferCopyDataBytes(block_buffer, 0, pkt->size, pkt->data);
+            if (ret != kCMBlockBufferNoErr) {
                 unlock_frames(ctx);
                 return AVERROR(EIO);
             }
@@ -1214,54 +1174,10 @@ static int avf_read_packet(AVFormatContext *s, AVPacket *pkt)
             pkt->stream_index  = ctx->audio_stream_index;
             pkt->flags        |= AV_PKT_FLAG_KEY;
 
-            if (ctx->audio_non_interleaved) {
-                int sample, c, shift, num_samples;
-
-                OSStatus ret = CMBlockBufferCopyDataBytes(block_buffer, 0, pkt->size, ctx->audio_buffer);
-                if (ret != kCMBlockBufferNoErr) {
-                    unlock_frames(ctx);
-                    return AVERROR(EIO);
-                }
-
-                num_samples = pkt->size / (ctx->audio_channels * (ctx->audio_bits_per_sample >> 3));
-
-                // transform decoded frame into output format
-                #define INTERLEAVE_OUTPUT(bps)                                         \
-                {                                                                      \
-                    int##bps##_t **src;                                                \
-                    int##bps##_t *dest;                                                \
-                    src = av_malloc(ctx->audio_channels * sizeof(int##bps##_t*));      \
-                    if (!src) {                                                        \
-                        unlock_frames(ctx);                                            \
-                        return AVERROR(EIO);                                           \
-                    }                                                                  \
-                                                                                       \
-                    for (c = 0; c < ctx->audio_channels; c++) {                        \
-                        src[c] = ((int##bps##_t*)ctx->audio_buffer) + c * num_samples; \
-                    }                                                                  \
-                    dest  = (int##bps##_t*)pkt->data;                                  \
-                    shift = bps - ctx->audio_bits_per_sample;                          \
-                    for (sample = 0; sample < num_samples; sample++)                   \
-                        for (c = 0; c < ctx->audio_channels; c++)                      \
-                            *dest++ = src[c][sample] << shift;                         \
-                    av_freep(&src);                                                    \
-                }
-
-                if (ctx->audio_bits_per_sample <= 16) {
-                    INTERLEAVE_OUTPUT(16)
-                } else {
-                    INTERLEAVE_OUTPUT(32)
-                }
-            } else {
-                OSStatus ret = CMBlockBufferCopyDataBytes(block_buffer, 0, pkt->size, pkt->data);
-                if (ret != kCMBlockBufferNoErr) {
-                    unlock_frames(ctx);
-                    return AVERROR(EIO);
-                }
-            }
-
             CFRelease(ctx->current_audio_frame);
             ctx->current_audio_frame = nil;
+
+            unlock_frames(ctx);
         } else {
             pkt->data = NULL;
             unlock_frames(ctx);
@@ -1286,6 +1202,10 @@ static int avf_close(AVFormatContext *s)
 }
 
 static const AVOption options[] = {
+    { "channels", "number of audio channels", offsetof(AVFContext, channels), AV_OPT_TYPE_INT, {.i64=2}, 0, INT_MAX, AV_OPT_FLAG_ENCODING_PARAM },
+    { "sample_rate", "audio sample rate", offsetof(AVFContext, sample_rate), AV_OPT_TYPE_INT, {.i64=44100}, 0, INT_MAX, AV_OPT_FLAG_ENCODING_PARAM },
+    { "big_endian", "return big endian samples for audio data", offsetof(AVFContext, big_endian), AV_OPT_TYPE_BOOL, {.i64=0}, 0, 1, AV_OPT_FLAG_ENCODING_PARAM },
+    { "sample_format", "audio sample format", offsetof(AVFContext, sample_format), AV_OPT_TYPE_INT, {.i64=AV_SAMPLE_FMT_S16}, 0, INT_MAX, AV_OPT_FLAG_ENCODING_PARAM },
     { "list_devices", "list available devices", offsetof(AVFContext, list_devices), AV_OPT_TYPE_BOOL, {.i64=0}, 0, 1, AV_OPT_FLAG_DECODING_PARAM },
     { "video_device_index", "select video device by index for devices with same name (starts at 0)", offsetof(AVFContext, video_device_index), AV_OPT_TYPE_INT, {.i64 = -1}, -1, INT_MAX, AV_OPT_FLAG_DECODING_PARAM },
     { "audio_device_index", "select audio device by index for devices with same name (starts at 0)", offsetof(AVFContext, audio_device_index), AV_OPT_TYPE_INT, {.i64 = -1}, -1, INT_MAX, AV_OPT_FLAG_DECODING_PARAM },
-- 
2.32.0 (Apple Git-132)

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".

  parent reply	other threads:[~2022-01-30 17:35 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-30 17:30 [FFmpeg-devel] [PATCH 0/4] Cleanup avfoundation input toots
2022-01-30 17:30 ` [FFmpeg-devel] [PATCH 1/4] Use appropriate method for device discovery, fix crash with bogus device index toots
2022-01-31 10:10   ` Thilo Borgmann
2022-01-31 14:19     ` Romain Beauxis
2022-01-30 17:30 ` [FFmpeg-devel] [PATCH 2/4] libavdevice/avfoundation.m: Allow to select devices by unique ID toots
2022-01-30 17:30 ` toots [this message]
2022-01-30 17:30 ` [FFmpeg-devel] [PATCH 4/4] libavdevice/avfoundation.m: Replace mutex-based concurrency handling in avfoundation.m by a thread-safe fifo queue with maximum length toots

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220130173045.32690-4-toots@rastageeks.org \
    --to=toots@rastageeks.org \
    --cc=epirat07@gmail.com \
    --cc=ffmpeg-devel@ffmpeg.org \
    --cc=thilo.borgmann@mail.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
		ffmpegdev@gitmailbox.com
	public-inbox-index ffmpegdev

Example config snippet for mirrors.


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git