dca: extract core substream's embedded downmix coeffcient codes, if present.

As per ETSI TS 102 114 V1.4.1 specification.

Signed-off-by: Anton Khirnov <anton@khirnov.net>

2 files changed, 165 insertions, 33 deletions

diff --git a/libavcodec/dcadata.h b/libavcodec/dcadata.h
index c4841fbac8..156a2c3350 100644
--- a/libavcodec/dcadata.h
+++ b/libavcodec/dcadata.h
@@ -7505,6 +7505,52 @@ DECLARE_ALIGNED(16, static const float, lfe_fir_128)[] =
     0.01724460535, 0.47964480519, 0.48503074050, 0.01805862412,
 };
 
+/*
+ * D.11 Look-up Table for Downmix Scale Factors
+ *
+ * Note that the range of the entries in DmixTable[] is between -60 dB and 0 dB
+ * with addition of -inf (|DMixCoeff| = 0), which is coded with a DmixCode = 0.
+ * Furthermore, the range [-60 to 0] is subdivided into 3 regions, each with a
+ * different grid resolution:
+ *
+ * 1) [-60.000 to -30] with resolution of 0.500 dB
+ * 2) [-29.750 to -15] with resolution of 0.250 dB
+ * 3) [-14.875 to   0] with resolution of 0.125 dB
+ */
+static const float dca_dmixtable[241] = {
+    0.001000, 0.001059, 0.001122, 0.001189, 0.001259, 0.001334, 0.001413, 0.001496,
+    0.001585, 0.001679, 0.001778, 0.001884, 0.001995, 0.002113, 0.002239, 0.002371,
+    0.002512, 0.002661, 0.002818, 0.002985, 0.003162, 0.003350, 0.003548, 0.003758,
+    0.003981, 0.004217, 0.004467, 0.004732, 0.005012, 0.005309, 0.005623, 0.005957,
+    0.006310, 0.006683, 0.007079, 0.007499, 0.007943, 0.008414, 0.008913, 0.009441,
+    0.010000, 0.010593, 0.011220, 0.011885, 0.012589, 0.013335, 0.014125, 0.014962,
+    0.015849, 0.016788, 0.017783, 0.018836, 0.019953, 0.021135, 0.022387, 0.023714,
+    0.025119, 0.026607, 0.028184, 0.029854, 0.031623, 0.032546, 0.033497, 0.034475,
+    0.035481, 0.036517, 0.037584, 0.038681, 0.039811, 0.040973, 0.042170, 0.043401,
+    0.044668, 0.045973, 0.047315, 0.048697, 0.050119, 0.051582, 0.053088, 0.054639,
+    0.056234, 0.057876, 0.059566, 0.061306, 0.063096, 0.064938, 0.066834, 0.068786,
+    0.070795, 0.072862, 0.074989, 0.077179, 0.079433, 0.081752, 0.084140, 0.086596,
+    0.089125, 0.091728, 0.094406, 0.097163, 0.100000, 0.102920, 0.105925, 0.109018,
+    0.112202, 0.115478, 0.118850, 0.122321, 0.125893, 0.129569, 0.133352, 0.137246,
+    0.141254, 0.145378, 0.149624, 0.153993, 0.158489, 0.163117, 0.167880, 0.172783,
+    0.177828, 0.180406, 0.183021, 0.185674, 0.188365, 0.191095, 0.193865, 0.196675,
+    0.199526, 0.202418, 0.205353, 0.208329, 0.211349, 0.214412, 0.217520, 0.220673,
+    0.223872, 0.227117, 0.230409, 0.233749, 0.237137, 0.240575, 0.244062, 0.247600,
+    0.251189, 0.254830, 0.258523, 0.262271, 0.266073, 0.269929, 0.273842, 0.277811,
+    0.281838, 0.285924, 0.290068, 0.294273, 0.298538, 0.302866, 0.307256, 0.311709,
+    0.316228, 0.320812, 0.325462, 0.330179, 0.334965, 0.339821, 0.344747, 0.349744,
+    0.354813, 0.359956, 0.365174, 0.370467, 0.375837, 0.381285, 0.386812, 0.392419,
+    0.398107, 0.403878, 0.409732, 0.415671, 0.421697, 0.427809, 0.434010, 0.440301,
+    0.446684, 0.453158, 0.459727, 0.466391, 0.473151, 0.480010, 0.486968, 0.494026,
+    0.501187, 0.508452, 0.515822, 0.523299, 0.530884, 0.538580, 0.546387, 0.554307,
+    0.562341, 0.570493, 0.578762, 0.587151, 0.595662, 0.604296, 0.613056, 0.621942,
+    0.630957, 0.640103, 0.649382, 0.658795, 0.668344, 0.678032, 0.687860, 0.697831,
+    0.707107, 0.718208, 0.728618, 0.739180, 0.749894, 0.760764, 0.771792, 0.782979,
+    0.794328, 0.805842, 0.817523, 0.829373, 0.841395, 0.853591, 0.865964, 0.878517,
+    0.891251, 0.904170, 0.917276, 0.930572, 0.944061, 0.957745, 0.971628, 0.985712,
+    1.000000,
+};
+
 static const float dca_default_coeffs[10][5][2] = {
     { { 0.707946, 0.707946 },                                                                                                 }, // A
     { { 1.000000, 0.000000 }, { 0.000000, 1.000000 },                                                                         }, // A + B (dual mono)
diff --git a/libavcodec/dcadec.c b/libavcodec/dcadec.c
index eb229ce98e..cf1da8c09b 100644
--- a/libavcodec/dcadec.c
+++ b/libavcodec/dcadec.c
@@ -339,6 +339,13 @@ typedef struct {
     float downmix_coef[DCA_PRIM_CHANNELS_MAX][2];                ///< stereo downmix coefficients
     int dynrange_coef;                                           ///< dynamic range coefficient
 
+    /* Core substream's embedded downmix coefficients (cf. ETSI TS 102 114 V1.4.1)
+     * Input:  primary audio channels (incl. LFE if present)
+     * Output: downmix audio channels (up to 4, no LFE) */
+    uint8_t  core_downmix;                                       ///< embedded downmix coefficients available
+    uint8_t  core_downmix_amode;                                 ///< audio channel arrangement of embedded downmix
+    uint16_t core_downmix_codes[DCA_PRIM_CHANNELS_MAX + 1][4];   ///< embedded downmix coefficients (9-bit codes)
+
     int high_freq_vq[DCA_PRIM_CHANNELS_MAX][DCA_SUBBANDS];       ///< VQ encoded high frequency subbands
 
     float lfe_data[2 * DCA_LFE_MAX * (DCA_BLOCKS_MAX + 4)];      ///< Low frequency effect data
@@ -796,25 +803,6 @@ static int dca_subframe_header(DCAContext *s, int base_channel, int block_index)
         }
     }
 
-    /* Stereo downmix coefficients */
-    if (!base_channel && s->prim_channels > 2) {
-        int am = s->amode & DCA_CHANNEL_MASK;
-        if (am >= FF_ARRAY_ELEMS(dca_default_coeffs)) {
-            av_log(s->avctx, AV_LOG_ERROR,
-                   "Invalid channel mode %d\n", am);
-            return AVERROR_INVALIDDATA;
-        }
-        if (s->prim_channels > FF_ARRAY_ELEMS(dca_default_coeffs[0])) {
-            avpriv_request_sample(s->avctx, "Downmixing %d channels",
-                                  s->prim_channels);
-            return AVERROR_PATCHWELCOME;
-        }
-        for (j = base_channel; j < s->prim_channels; j++) {
-            s->downmix_coef[j][0] = dca_default_coeffs[am][j][0];
-            s->downmix_coef[j][1] = dca_default_coeffs[am][j][1];
-        }
-    }
-
     /* Dynamic range coefficient */
     if (!base_channel && s->dynrange)
         s->dynrange_coef = get_bits(&s->gb, 8);
@@ -909,16 +897,6 @@ static int dca_subframe_header(DCAContext *s, int base_channel, int block_index)
             av_log(s->avctx, AV_LOG_DEBUG, "\n");
         }
     }
-    if (!base_channel && s->prim_channels > 2) {
-        av_log(s->avctx, AV_LOG_DEBUG, "Downmix coeffs:\n");
-        for (j = 0; j < s->prim_channels; j++) {
-            av_log(s->avctx, AV_LOG_DEBUG, "Channel 0, %d = %f\n", j,
-                   s->downmix_coef[j][0]);
-            av_log(s->avctx, AV_LOG_DEBUG, "Channel 1, %d = %f\n", j,
-                   s->downmix_coef[j][1]);
-        }
-        av_log(s->avctx, AV_LOG_DEBUG, "\n");
-    }
     for (j = base_channel; j < s->prim_channels; j++)
         for (k = s->vq_start_subband[j]; k < s->subband_activity[j]; k++)
             av_log(s->avctx, AV_LOG_DEBUG, "VQ index: %i\n", s->high_freq_vq[j][k]);
@@ -1292,7 +1270,7 @@ static int dca_filter_channels(DCAContext *s, int block_index)
 
 static int dca_subframe_footer(DCAContext *s, int base_channel)
 {
-    int aux_data_count = 0, i;
+    int in, out, aux_data_count, aux_data_end, reserved;
 
     /*
      * Unpack optional information
@@ -1303,11 +1281,74 @@ static int dca_subframe_footer(DCAContext *s, int base_channel)
         if (s->timestamp)
             skip_bits_long(&s->gb, 32);
 
-        if (s->aux_data)
+        if (s->aux_data) {
             aux_data_count = get_bits(&s->gb, 6);
 
-        for (i = 0; i < aux_data_count; i++)
-            get_bits(&s->gb, 8);
+            // align (32-bit)
+            skip_bits_long(&s->gb, (-get_bits_count(&s->gb)) & 31);
+
+            aux_data_end = 8 * aux_data_count + get_bits_count(&s->gb);
+
+            if (get_bits_long(&s->gb, 32) != 0x9A1105A0) // nSYNCAUX
+                return AVERROR_INVALIDDATA;
+
+            if (get_bits1(&s->gb)) { // bAUXTimeStampFlag
+                avpriv_request_sample(s->avctx,
+                                      "Auxiliary Decode Time Stamp Flag");
+                // align (4-bit)
+                skip_bits(&s->gb, (-get_bits_count(&s->gb)) & 4);
+                // 44 bits: nMSByte (8), nMarker (4), nLSByte (28), nMarker (4)
+                skip_bits_long(&s->gb, 44);
+            }
+
+            if ((s->core_downmix = get_bits1(&s->gb))) {
+                switch (get_bits(&s->gb, 3)) {
+                case 0:
+                    s->core_downmix_amode = DCA_MONO;
+                    break;
+                case 1:
+                    s->core_downmix_amode = DCA_STEREO;
+                    break;
+                case 2:
+                    s->core_downmix_amode = DCA_STEREO_TOTAL;
+                    break;
+                case 3:
+                    s->core_downmix_amode = DCA_3F;
+                    break;
+                case 4:
+                    s->core_downmix_amode = DCA_2F1R;
+                    break;
+                case 5:
+                    s->core_downmix_amode = DCA_2F2R;
+                    break;
+                case 6:
+                    s->core_downmix_amode = DCA_3F1R;
+                    break;
+                default:
+                    return AVERROR_INVALIDDATA;
+                }
+                for (out = 0; out < dca_channels[s->core_downmix_amode]; out++) {
+                    for (in = 0; in < s->prim_channels + !!s->lfe; in++) {
+                        uint16_t tmp = get_bits(&s->gb, 9);
+                        if ((tmp & 0xFF) > 241)
+                            return AVERROR_INVALIDDATA;
+                        s->core_downmix_codes[in][out] = tmp;
+                    }
+                }
+            }
+
+            align_get_bits(&s->gb); // byte align
+            skip_bits(&s->gb, 16);  // nAUXCRC16
+
+            // additional data (reserved, cf. ETSI TS 102 114 V1.4.1)
+            if ((reserved = (aux_data_end - get_bits_count(&s->gb))) < 0)
+                return AVERROR_INVALIDDATA;
+            else if (reserved) {
+                avpriv_request_sample(s->avctx,
+                                      "Core auxiliary data reserved content");
+                skip_bits_long(&s->gb, reserved);
+            }
+        }
 
         if (s->crc_present && s->dynrange)
             get_bits(&s->gb, 16);
@@ -1822,6 +1863,51 @@ FF_ENABLE_DEPRECATION_WARNINGS
             channels = 2;
             s->output = DCA_STEREO;
             avctx->channel_layout = AV_CH_LAYOUT_STEREO;
+
+            /* Stereo downmix coefficients
+             *
+             * The decoder can only downmix to 2-channel, so we need to ensure
+             * embedded downmix coefficients are actually targeting 2-channel.
+             *
+             * Coefficients for the LFE channel are ignored (not supported) */
+            if (s->core_downmix && (s->core_downmix_amode == DCA_STEREO ||
+                                    s->core_downmix_amode == DCA_STEREO_TOTAL)) {
+                int sign, code;
+                for (i = 0; i < s->prim_channels; i++) {
+                    sign = s->core_downmix_codes[i][0] & 0x100 ? 1 : -1;
+                    code = s->core_downmix_codes[i][0] & 0x0FF;
+                    s->downmix_coef[i][0] = (!code ? 0.0f :
+                                             sign * dca_dmixtable[code - 1]);
+                    sign = s->core_downmix_codes[i][1] & 0x100 ? 1 : -1;
+                    code = s->core_downmix_codes[i][1] & 0x0FF;
+                    s->downmix_coef[i][1] = (!code ? 0.0f :
+                                             sign * dca_dmixtable[code - 1]);
+                }
+            } else {
+                int am = s->amode & DCA_CHANNEL_MASK;
+                if (am >= FF_ARRAY_ELEMS(dca_default_coeffs)) {
+                    av_log(s->avctx, AV_LOG_ERROR,
+                           "Invalid channel mode %d\n", am);
+                    return AVERROR_INVALIDDATA;
+                }
+                if (s->prim_channels > FF_ARRAY_ELEMS(dca_default_coeffs[0])) {
+                    avpriv_request_sample(s->avctx, "Downmixing %d channels",
+                                          s->prim_channels);
+                    return AVERROR_PATCHWELCOME;
+                }
+                for (i = 0; i < s->prim_channels; i++) {
+                    s->downmix_coef[i][0] = dca_default_coeffs[am][i][0];
+                    s->downmix_coef[i][1] = dca_default_coeffs[am][i][1];
+                }
+            }
+            av_dlog(s->avctx, "Stereo downmix coeffs:\n");
+            for (i = 0; i < s->prim_channels; i++) {
+                av_dlog(s->avctx, "L, input channel %d = %f\n", i,
+                        s->downmix_coef[i][0]);
+                av_dlog(s->avctx, "R, input channel %d = %f\n", i,
+                        s->downmix_coef[i][1]);
+            }
+            av_dlog(s->avctx, "\n");
         }
     } else {
         av_log(avctx, AV_LOG_ERROR, "Non standard configuration %d !\n", s->amode);