diff mbox series

[FFmpeg-devel] avformat/mov: read PCM audio configuration box ('pcmC') if available

Message ID 20220607082618.64814-1-4rusxg@gmail.com
State New
Headers show
Series [FFmpeg-devel] avformat/mov: read PCM audio configuration box ('pcmC') if available | expand

Checks

Context Check Description
yinshiyou/make_loongarch64 success Make finished
yinshiyou/make_fate_loongarch64 success Make fate finished
andriy/make_armv7_RPi4 success Make finished
andriy/make_fate_armv7_RPi4 success Make fate finished

Commit Message

Ivan Baykalov June 7, 2022, 8:26 a.m. UTC 
For ipcm and fpcm streams, big-endian format is the default, but it can be changed
with additional 'pcmC' sub-atom of audio sample description.

Details can be found in ISO/IEC 23003-5:2020

Fixes ticket #9763
Fixes ticket #9790
---
 libavformat/mov.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)

Comments

Marton Balint June 19, 2022, 9:51 p.m. UTC | #1 
On Tue, 7 Jun 2022, Ivan Baykalov wrote:

> For ipcm and fpcm streams, big-endian format is the default, but it can be changed
> with additional 'pcmC' sub-atom of audio sample description.
>
> Details can be found in ISO/IEC 23003-5:2020
>
> Fixes ticket #9763
> Fixes ticket #9790

Thanks for this, I have factorized the duplicated code from 
existing endianness setting and also simplified your patch a bit. Will 
post it as a reply to this mail.

Regards,
Marton

> ---
> libavformat/mov.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 60 insertions(+)
>
> diff --git a/libavformat/mov.c b/libavformat/mov.c
> index d7be593a86..f71a470d9c 100644
> --- a/libavformat/mov.c
> +++ b/libavformat/mov.c
> @@ -7567,6 +7567,65 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
>     return atom.size;
> }
>
> +static int mov_read_pcmc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
> +{
> +    int version, format_flags, pcm_sample_size;
> +    AVStream *st;
> +
> +    if (atom.size < 6) {
> +        av_log(c->fc, AV_LOG_ERROR, "Empty pcmC box\n");
> +        return AVERROR_INVALIDDATA;
> +    }
> +
> +    version = avio_r8(pb);
> +    if (version) {
> +        av_log(c->fc, AV_LOG_WARNING, "Unsupported pcmC box version %d\n", version);
> +        return 0;
> +    }
> +
> +    avio_rb24(pb);  // flags
> +
> +    if (c->fc->nb_streams < 1)
> +        return 0;
> +    st = c->fc->streams[c->fc->nb_streams-1];
> +    if (!st || !st->codecpar)
> +        return 0;
> +
> +    format_flags = avio_r8(pb);
> +    if (format_flags == 1) { // indicates little-endian format. If not present, big-endian format is used
> +        if (st->codecpar->codec_tag == MKTAG('i','p','c','m')) {
> +            switch (st->codecpar->codec_id) {
> +                case AV_CODEC_ID_PCM_S16BE:
> +                    st->codecpar->codec_id = AV_CODEC_ID_PCM_S16LE;
> +                    break;
> +                case AV_CODEC_ID_PCM_S24BE:
> +                    st->codecpar->codec_id = AV_CODEC_ID_PCM_S24LE;
> +                    break;
> +                case AV_CODEC_ID_PCM_S32BE:
> +                    st->codecpar->codec_id = AV_CODEC_ID_PCM_S32LE;
> +                    break;
> +            }
> +        }
> +        else if (st->codecpar->codec_tag == MKTAG('f','p','c','m')) {
> +            switch (st->codecpar->codec_id) {
> +                case AV_CODEC_ID_PCM_F32BE:
> +                    st->codecpar->codec_id = AV_CODEC_ID_PCM_F32LE;
> +                    break;
> +                case AV_CODEC_ID_PCM_F64BE:
> +                    st->codecpar->codec_id = AV_CODEC_ID_PCM_F64LE;
> +                    break;
> +            }
> +        }
> +    }
> +
> +    pcm_sample_size = avio_r8(pb);
> +    if (pcm_sample_size != st->codecpar->bits_per_coded_sample) {
> +        av_log(c->fc, AV_LOG_WARNING, "Unexpected pcmC sample size (%d vs %d)\n", pcm_sample_size, st->codecpar->bits_per_coded_sample);
> +    }
> +
> +    return 0;
> +}
> +
> static const MOVParseTableEntry mov_default_parse_table[] = {
> { MKTAG('A','C','L','R'), mov_read_aclr },
> { MKTAG('A','P','R','G'), mov_read_avid },
> @@ -7670,6 +7729,7 @@ static const MOVParseTableEntry mov_default_parse_table[] = {
> { MKTAG('S','A','3','D'), mov_read_SA3D }, /* ambisonic audio box */
> { MKTAG('S','A','N','D'), mov_read_SAND }, /* non diegetic audio box */
> { MKTAG('i','l','o','c'), mov_read_iloc },
> +{ MKTAG('p','c','m','C'), mov_read_pcmc }, /* PCM configuration box */
> { 0, NULL }
> };
>
> -- 
> 2.35.1
>
> _______________________________________________
> 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".
>
diff mbox series

Patch

diff --git a/libavformat/mov.c b/libavformat/mov.c
index d7be593a86..f71a470d9c 100644
--- a/libavformat/mov.c
+++ b/libavformat/mov.c
@@ -7567,6 +7567,65 @@  static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     return atom.size;
 }
 
+static int mov_read_pcmc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
+{
+    int version, format_flags, pcm_sample_size;
+    AVStream *st;
+
+    if (atom.size < 6) {
+        av_log(c->fc, AV_LOG_ERROR, "Empty pcmC box\n");
+        return AVERROR_INVALIDDATA;
+    }
+
+    version = avio_r8(pb);
+    if (version) {
+        av_log(c->fc, AV_LOG_WARNING, "Unsupported pcmC box version %d\n", version);
+        return 0;
+    }
+
+    avio_rb24(pb);  // flags
+
+    if (c->fc->nb_streams < 1)
+        return 0;
+    st = c->fc->streams[c->fc->nb_streams-1];
+    if (!st || !st->codecpar)
+        return 0;
+
+    format_flags = avio_r8(pb);
+    if (format_flags == 1) { // indicates little-endian format. If not present, big-endian format is used
+        if (st->codecpar->codec_tag == MKTAG('i','p','c','m')) {
+            switch (st->codecpar->codec_id) {
+                case AV_CODEC_ID_PCM_S16BE:
+                    st->codecpar->codec_id = AV_CODEC_ID_PCM_S16LE;
+                    break;
+                case AV_CODEC_ID_PCM_S24BE:
+                    st->codecpar->codec_id = AV_CODEC_ID_PCM_S24LE;
+                    break;
+                case AV_CODEC_ID_PCM_S32BE:
+                    st->codecpar->codec_id = AV_CODEC_ID_PCM_S32LE;
+                    break;
+            }
+        }
+        else if (st->codecpar->codec_tag == MKTAG('f','p','c','m')) {
+            switch (st->codecpar->codec_id) {
+                case AV_CODEC_ID_PCM_F32BE:
+                    st->codecpar->codec_id = AV_CODEC_ID_PCM_F32LE;
+                    break;
+                case AV_CODEC_ID_PCM_F64BE:
+                    st->codecpar->codec_id = AV_CODEC_ID_PCM_F64LE;
+                    break;
+            }
+        }
+    }
+
+    pcm_sample_size = avio_r8(pb);
+    if (pcm_sample_size != st->codecpar->bits_per_coded_sample) {
+        av_log(c->fc, AV_LOG_WARNING, "Unexpected pcmC sample size (%d vs %d)\n", pcm_sample_size, st->codecpar->bits_per_coded_sample);
+    }
+
+    return 0;
+}
+
 static const MOVParseTableEntry mov_default_parse_table[] = {
 { MKTAG('A','C','L','R'), mov_read_aclr },
 { MKTAG('A','P','R','G'), mov_read_avid },
@@ -7670,6 +7729,7 @@  static const MOVParseTableEntry mov_default_parse_table[] = {
 { MKTAG('S','A','3','D'), mov_read_SA3D }, /* ambisonic audio box */
 { MKTAG('S','A','N','D'), mov_read_SAND }, /* non diegetic audio box */
 { MKTAG('i','l','o','c'), mov_read_iloc },
+{ MKTAG('p','c','m','C'), mov_read_pcmc }, /* PCM configuration box */
 { 0, NULL }
 };