ffmpeg: add -map_channel option.

Based on an initial work by Baptiste Coudurier.

Changelog

@@ -72,6 +72,7 @@ easier to use. The changes are:
 - Prores encoder
 - Video Decoder Acceleration (VDA) HWAccel module.
 - replacement Indeo 3 decoder
+- new ffmpeg option: -map_channel
 
 version 0.8:
 

doc/ffmpeg.texi

@@ -721,6 +721,44 @@ ffmpeg -i INPUT -map 0 -map -0:a:1 OUTPUT
 
 Note that using this option disables the default mappings for this output file.
 
+@item -map_channel [@var{input_file_id}.@var{stream_specifier}.@var{channel_id}|-1][:@var{output_file_id}.@var{stream_specifier}]
+Map an audio channel from a given input to an output. If
+@var{output_file_id}.@var{stream_specifier} are not set, the audio channel will
+be mapped on all the audio streams.
+
+Using "-1" instead of
+@var{input_file_id}.@var{stream_specifier}.@var{channel_id} will map a muted
+channel.
+
+For example, assuming @var{INPUT} is a stereo audio file, you can switch the
+two audio channels with the following command:
+@example
+ffmpeg -i INPUT -map_channel 0.0.1 -map_channel 0.0.0 OUTPUT
+@end example
+
+If you want to mute the first channel and keep the second:
+@example
+ffmpeg -i INPUT -map_channel -1 -map_channel 0.0.1 OUTPUT
+@end example
+
+The order of the "-map_channel" option specifies the order of the channels in
+the output stream. The output channel layout is guessed from the number of
+channels mapped (mono if one "-map_channel", stereo if two, etc.). Using "-ac"
+in combination of "-map_channel" makes the channel gain levels to be updated if
+channel layouts don't match (for instance two "-map_channel" options and "-ac
+6").
+
+You can also extract each channel of an @var{INPUT} to specific outputs; the
+following command extract each channel of the audio stream (file 0, stream 0)
+to the respective @var{OUTPUT_CH0} and @var{OUTPUT_CH1}:
+@example
+ffmpeg -i INPUT -map_channel 0.0.0 OUTPUT_CH0 -map_channel 0.0.1 OUTPUT_CH1
+@end example
+
+Note that "-map_channel" is currently limited to the scope of one input for
+each output; you can't for example use it to pick multiple input audio files
+and mix them into one single output.
+
 @item -map_metadata[:@var{metadata_type}][:@var{index}] @var{infile}[:@var{metadata_type}][:@var{index}] (@emph{output,per-metadata})
 Set metadata information of the next output file from @var{infile}. Note that
 those are file indices (zero-based), not filenames.

ffplay.c

@@ -2077,7 +2077,7 @@ static int audio_decode_frame(VideoState *is, double *pts_ptr)
                     swr_free(&is->swr_ctx);
                 is->swr_ctx = swr_alloc2(NULL, is->audio_tgt_channel_layout, is->audio_tgt_fmt, is->audio_tgt_freq,
                                                dec_channel_layout,          dec->sample_fmt,   dec->sample_rate,
-                                               0, NULL);
+                                               NULL, 0, NULL);
                 if (!is->swr_ctx || swr_init(is->swr_ctx) < 0) {
                     fprintf(stderr, "Cannot create sample rate converter for conversion of %d Hz %s %d channels to %d Hz %s %d channels!\n",
                         dec->sample_rate,

libswresample/audioconvert.c

@@ -35,11 +35,13 @@
 struct AVAudioConvert {
     int channels;
     int fmt_pair;
+    const int *ch_map;
 };
 
 AVAudioConvert *swr_audio_convert_alloc(enum AVSampleFormat out_fmt,
                                         enum AVSampleFormat in_fmt,
-                                        int channels, int flags)
+                                        int channels, const int *ch_map,
+                                        int flags)
 {
     AVAudioConvert *ctx;
     ctx = av_malloc(sizeof(AVAudioConvert));
@@ -47,6 +49,7 @@ AVAudioConvert *swr_audio_convert_alloc(enum AVSampleFormat out_fmt,
         return NULL;
     ctx->channels = channels;
     ctx->fmt_pair = out_fmt + AV_SAMPLE_FMT_NB*in_fmt;
+    ctx->ch_map   = ch_map;
     return ctx;
 }
 
@@ -58,15 +61,17 @@ void swr_audio_convert_free(AVAudioConvert **ctx)
 int swr_audio_convert(AVAudioConvert *ctx, AudioData *out, AudioData*in, int len)
 {
     int ch;
+    const uint8_t null_input[8] = {0};
 
     av_assert0(ctx->channels == out->ch_count);
 
     //FIXME optimize common cases
 
     for(ch=0; ch<ctx->channels; ch++){
-        const int is= (in ->planar ? 1 : in->ch_count) * in->bps;
+        const int ich= ctx->ch_map ? ctx->ch_map[ch] : ch;
+        const int is= ich < 0 ? 0 : (in->planar ? 1 : in->ch_count) * in->bps;
         const int os= (out->planar ? 1 :out->ch_count) *out->bps;
-        const uint8_t *pi= in ->ch[ch];
+        const uint8_t *pi= ich < 0 ? null_input : in->ch[ich];
         uint8_t       *po= out->ch[ch];
         uint8_t *end= po + os*len;
         if(!po)

libswresample/audioconvert.h

@@ -42,11 +42,14 @@ typedef struct AVAudioConvert AVAudioConvert;
  * @param in_fmt Input sample format
  * @param channels Number of channels
  * @param flags See AV_CPU_FLAG_xx
+ * @param ch_map list of the channels id to pick from the source stream, NULL
+ *               if all channels must be selected
  * @return NULL on error
  */
 AVAudioConvert *swr_audio_convert_alloc(enum AVSampleFormat out_fmt,
                                         enum AVSampleFormat in_fmt,
-                                        int channels, int flags);
+                                        int channels, const int *ch_map,
+                                        int flags);
 
 /**
  * Free audio sample format converter context.

libswresample/swresample.c

@@ -38,6 +38,7 @@
 static const AVOption options[]={
 {"ich",  "input channel count", OFFSET( in.ch_count   ), AV_OPT_TYPE_INT, {.dbl=2}, 1, SWR_CH_MAX, 0},
 {"och", "output channel count", OFFSET(out.ch_count   ), AV_OPT_TYPE_INT, {.dbl=2}, 1, SWR_CH_MAX, 0},
+{"uch",   "used channel count", OFFSET(used_ch_count  ), AV_OPT_TYPE_INT, {.dbl=2}, 1, SWR_CH_MAX, 0},
 {"isr",  "input sample rate"  , OFFSET( in_sample_rate), AV_OPT_TYPE_INT, {.dbl=48000}, 1, INT_MAX, 0},
 {"osr", "output sample rate"  , OFFSET(out_sample_rate), AV_OPT_TYPE_INT, {.dbl=48000}, 1, INT_MAX, 0},
 //{"ip" ,  "input planar"       , OFFSET( in.planar     ), AV_OPT_TYPE_INT, {.dbl=0},    0,       1, 0},
@@ -76,7 +77,7 @@ SwrContext *swr_alloc(void){
 
 SwrContext *swr_alloc2(struct SwrContext *s, int64_t out_ch_layout, enum AVSampleFormat out_sample_fmt, int out_sample_rate,
                        int64_t  in_ch_layout, enum AVSampleFormat  in_sample_fmt, int  in_sample_rate,
-                       int log_offset, void *log_ctx){
+                       const int *channel_map, int log_offset, void *log_ctx){
     if(!s) s= swr_alloc();
     if(!s) return NULL;
 
@@ -90,9 +91,11 @@ SwrContext *swr_alloc2(struct SwrContext *s, int64_t out_ch_layout, enum AVSampl
     av_set_int(s, "isf", in_sample_fmt);
     av_set_int(s, "isr", in_sample_rate);
 
+    s->channel_map = channel_map;
     s-> in.ch_count= av_get_channel_layout_nb_channels(s-> in_ch_layout);
     s->out.ch_count= av_get_channel_layout_nb_channels(s->out_ch_layout);
     s->int_sample_fmt = AV_SAMPLE_FMT_S16;
+    s->used_ch_count= s-> in.ch_count;
 
     return s;
 }
@@ -167,13 +170,16 @@ int swr_init(SwrContext *s){
         return -1;
     }
 
-    if(s-> in.ch_count && s-> in_ch_layout && s->in.ch_count != av_get_channel_layout_nb_channels(s-> in_ch_layout)){
-        av_log(s, AV_LOG_WARNING, "Input channel layout has a different number of channels than there actually is, ignoring layout\n");
+    if(!s->used_ch_count)
+        s->used_ch_count= s->in.ch_count;
+
+    if(s->used_ch_count && s-> in_ch_layout && s->used_ch_count != av_get_channel_layout_nb_channels(s-> in_ch_layout)){
+        av_log(s, AV_LOG_WARNING, "Input channel layout has a different number of channels than the number of used channels, ignoring layout\n");
         s-> in_ch_layout= 0;
     }
 
     if(!s-> in_ch_layout)
-        s-> in_ch_layout= av_get_default_channel_layout(s->in.ch_count);
+        s-> in_ch_layout= av_get_default_channel_layout(s->used_ch_count);
     if(!s->out_ch_layout)
         s->out_ch_layout= av_get_default_channel_layout(s->out.ch_count);
 
@@ -182,10 +188,13 @@ int swr_init(SwrContext *s){
 #define RSC 1 //FIXME finetune
     if(!s-> in.ch_count)
         s-> in.ch_count= av_get_channel_layout_nb_channels(s-> in_ch_layout);
+    if(!s->used_ch_count)
+        s->used_ch_count= s->in.ch_count;
     if(!s->out.ch_count)
         s->out.ch_count= av_get_channel_layout_nb_channels(s->out_ch_layout);
 
 av_assert0(s-> in.ch_count);
+av_assert0(s->used_ch_count);
 av_assert0(s->out.ch_count);
     s->resample_first= RSC*s->out.ch_count/s->in.ch_count - RSC < s->out_sample_rate/(float)s-> in_sample_rate - 1.0;
 
@@ -193,22 +202,27 @@ av_assert0(s->out.ch_count);
     s->int_bps= av_get_bits_per_sample_fmt(s->int_sample_fmt)/8;
     s->out.bps= av_get_bits_per_sample_fmt(s->out_sample_fmt)/8;
 
-    if(!s->resample && !s->rematrix){
+    if(!s->resample && !s->rematrix && !s->channel_map){
         s->full_convert = swr_audio_convert_alloc(s->out_sample_fmt,
-                                                  s-> in_sample_fmt, s-> in.ch_count, 0);
+                                                  s-> in_sample_fmt, s-> in.ch_count, NULL, 0);
         return 0;
     }
 
     s->in_convert = swr_audio_convert_alloc(s->int_sample_fmt,
-                                            s-> in_sample_fmt, s-> in.ch_count, 0);
+                                            s-> in_sample_fmt, s->used_ch_count, s->channel_map, 0);
     s->out_convert= swr_audio_convert_alloc(s->out_sample_fmt,
-                                            s->int_sample_fmt, s->out.ch_count, 0);
+                                            s->int_sample_fmt, s->out.ch_count, NULL, 0);
 
 
     s->postin= s->in;
     s->preout= s->out;
     s->midbuf= s->in;
     s->in_buffer= s->in;
+    if(s->channel_map){
+        s->postin.ch_count=
+        s->midbuf.ch_count=
+        s->in_buffer.ch_count= s->used_ch_count;
+    }
     if(!s->resample_first){
         s->midbuf.ch_count= s->out.ch_count;
         s->in_buffer.ch_count = s->out.ch_count;
@@ -325,7 +339,7 @@ int swr_convert(struct SwrContext *s, uint8_t *out_arg[SWR_CH_MAX], int out_coun
     if((ret=realloc_audio(&s->postin, in_count))<0)
         return ret;
     if(s->resample_first){
-        av_assert0(s->midbuf.ch_count ==  s-> in.ch_count);
+        av_assert0(s->midbuf.ch_count == s->used_ch_count);
         if((ret=realloc_audio(&s->midbuf, out_count))<0)
             return ret;
     }else{

libswresample/swresample.h

@@ -25,7 +25,7 @@
 #include "libavutil/samplefmt.h"
 
 #define LIBSWRESAMPLE_VERSION_MAJOR 0
-#define LIBSWRESAMPLE_VERSION_MINOR 1
+#define LIBSWRESAMPLE_VERSION_MINOR 2
 #define LIBSWRESAMPLE_VERSION_MICRO 0
 
 #define SWR_CH_MAX 16
@@ -57,7 +57,7 @@ int swr_init(struct SwrContext *s);
  */
 struct SwrContext *swr_alloc2(struct SwrContext *s, int64_t out_ch_layout, enum AVSampleFormat out_sample_fmt, int out_sample_rate,
                               int64_t  in_ch_layout, enum AVSampleFormat  in_sample_fmt, int  in_sample_rate,
-                              int log_offset, void *log_ctx);
+                              const int *channel_map, int log_offset, void *log_ctx);
 
 /**
  * Free the given SwrContext.

libswresample/swresample_internal.h

@@ -45,6 +45,8 @@ typedef struct SwrContext {          //FIXME find unused fields
     int     out_sample_rate;
     int flags;
     float slev, clev, rematrix_volume;
+    const int *channel_map;             ///< channel index (or -1 if muted channel) map
+    int used_ch_count;                  ///< number of used channels (mapped channel count if channel_map, otherwise in.ch_count)
 
     //below are private
     int int_bps;

libswresample/swresample_test.c

@@ -131,9 +131,11 @@ int main(int argc, char **argv){
                                in_sample_rate, out_sample_rate,
                                av_get_sample_fmt_name(in_sample_fmt), av_get_sample_fmt_name(out_sample_fmt));
                         forw_ctx  = swr_alloc2(forw_ctx, out_ch_layout, out_sample_fmt+planar_out, out_sample_rate,
-                                                                  in_ch_layout,  in_sample_fmt+planar_in ,  in_sample_rate, 0, 0);
-                        backw_ctx = swr_alloc2(backw_ctx,in_ch_layout,  in_sample_fmt,  in_sample_rate,
-                                                                 out_ch_layout, out_sample_fmt+planar_out, out_sample_rate, 0, 0);
+                                                          in_ch_layout,  in_sample_fmt+planar_in ,  in_sample_rate,
+                                                          NULL, 0, 0);
+                        backw_ctx = swr_alloc2(backw_ctx,in_ch_layout,  in_sample_fmt,             in_sample_rate,
+                                                        out_ch_layout, out_sample_fmt+planar_out, out_sample_rate,
+                                                        NULL, 0, 0);
                         if(swr_init( forw_ctx) < 0)
                             fprintf(stderr, "swr_init(->) failed\n");
                         if(swr_init(backw_ctx) < 0)

tests/Makefile

@@ -30,6 +30,14 @@ tests/data/asynth-16000-1.sw: tests/audiogen$(HOSTEXESUF)
 	@mkdir -p tests/data
 	$(M)./$< $@ 16000 1
 
+tests/data/mapchan-6ch.sw: tests/audiogen$(HOSTEXESUF)
+	@mkdir -p tests/data
+	$(M)./$< $@ 22050 6
+
+tests/data/mapchan-mono.sw: tests/audiogen$(HOSTEXESUF)
+	@mkdir -p tests/data
+	$(M)./$< $@ 22050 1
+
 tests/data/asynth%.sw tests/vsynth%/00.pgm: TAG = GEN
 
 include $(SRC_PATH)/tests/fate.mak

tests/fate2.mak

@@ -137,6 +137,18 @@ FATE_TESTS += fate-g722enc
 fate-g722enc: tests/data/asynth-16000-1.sw
 fate-g722enc: CMD = md5 -ar 16000 -ac 1 -f s16le -i $(TARGET_PATH)/tests/data/asynth-16000-1.sw -acodec g722 -ac 1 -f g722
 
+FATE_TESTS += fate-mapchan-6ch-extract-2
+fate-mapchan-6ch-extract-2: tests/data/mapchan-6ch.sw
+fate-mapchan-6ch-extract-2: CMD = avconv -ar 22050 -ac 6 -i $(TARGET_PATH)/tests/data/mapchan-6ch.sw -map_channel 0.0.0 -f wav md5: -map_channel 0.0.1 -f wav md5:
+
+FATE_TESTS += fate-mapchan-6ch-extract-2-downmix-mono
+fate-mapchan-6ch-extract-2-downmix-mono: tests/data/mapchan-6ch.sw
+fate-mapchan-6ch-extract-2-downmix-mono: CMD = md5 -ar 22050 -ac 6 -i $(TARGET_PATH)/tests/data/mapchan-6ch.sw -map_channel 0.0.1 -map_channel 0.0.0 -ac 1 -f wav
+
+FATE_TESTS += fate-mapchan-silent-mono
+fate-mapchan-silent-mono: tests/data/mapchan-mono.sw
+fate-mapchan-silent-mono: CMD = md5 -ar 22050 -ac 1 -i $(TARGET_PATH)/tests/data/mapchan-mono.sw -map_channel -1 -map_channel 0.0.0 -f wav
+
 FATE_TESTS += fate-msmpeg4v1
 fate-msmpeg4v1: CMD = framecrc -flags +bitexact -dct fastint -idct simple -i $(SAMPLES)/msmpeg4v1/mpg4.avi -an
 

tests/ref/fate/mapchan-6ch-extract-2

+6f091fe8c0be88c75921731dc9f74314
+5c2d162b9024329eb367295d37b8ca0a

tests/ref/fate/mapchan-6ch-extract-2-downmix-mono

+959645ed73e6d08d8f1e947eac5d0b92

tests/ref/fate/mapchan-silent-mono

+4f5148f08587a4b9794aa52aec7852ac