[FFmpeg-devel] [PATCH] libavcodec/mpeg12dec: extract embedded CC of particular type only

[Ivan Baykalov]

Some streams contain closed caption data embedded using several wrapping
types. For example stream can contain CC wrapped as ATSC A53 packets +
the same data wrapped as SCTE-20 packets. Prior to the patch CC data was
extracted from both types of packets, so it gave duplicated character
pairs on the output.

Now we calculate some statistics which CC types appear more often in the
stream and extract the data from a single type only. If at some point
the other CC type becomes more active, we switch to this new type.

Fixes ticket #9724.
---
 libavcodec/mpeg12dec.c | 44 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/libavcodec/mpeg12dec.c b/libavcodec/mpeg12dec.c
index e9bde48f7a..f7e54ef0a9 100644
--- a/libavcodec/mpeg12dec.c
+++ b/libavcodec/mpeg12dec.c
@@ -58,6 +58,14 @@
 
 #define A53_MAX_CC_COUNT 2000
 
+typedef enum CcType {
+    CC_TYPE_UNKNOWN = -1,
+    CC_TYPE_A53 = 0,
+    CC_TYPE_SCTE20,
+    CC_TYPE_DVD,
+    CC_TYPE_COUNT
+} CcType;
+
 typedef struct Mpeg1Context {
     MpegEncContext mpeg_enc_ctx;
     int mpeg_enc_ctx_allocated; /* true if decoding context allocated */
@@ -81,6 +89,7 @@ typedef struct Mpeg1Context {
     int first_slice;
     int extradata_decoded;
     int64_t timecode_frame_start;  /*< GOP timecode frame start number, in non drop frame format */
+    int cc_packet_count[CC_TYPE_COUNT];
 } Mpeg1Context;
 
 #define MB_TYPE_ZERO_MV   0x20000000
@@ -2198,6 +2207,32 @@ static int vcr2_init_sequence(AVCodecContext *avctx)
     return 0;
 }
 
+static int cc_type_is_selected(Mpeg1Context *s1, CcType type)
+{
+    int max = 0;
+    int max_index = -1;
+    int sum = 0;
+    av_assert0(type >= 0 && type < CC_TYPE_COUNT);
+    s1->cc_packet_count[type]++;
+
+    for (int i = 0; i < CC_TYPE_COUNT; i++) {
+        if (s1->cc_packet_count[i] > max) {
+            max = s1->cc_packet_count[i];
+            max_index = i;
+        }
+        sum += s1->cc_packet_count[i];
+    }
+
+    if (sum < 2 || sum > 20) {
+        // reset statistics, but give some advantage to the current selection
+        // to avoid frequent switching between the types
+        memset(s1->cc_packet_count, 0, sizeof(s1->cc_packet_count));
+        s1->cc_packet_count[max_index] = 2;
+    }
+
+    return type == max_index;
+}
+
 static int mpeg_decode_a53_cc(AVCodecContext *avctx,
                               const uint8_t *p, int buf_size)
 {
@@ -2217,6 +2252,9 @@ static int mpeg_decode_a53_cc(AVCodecContext *avctx,
             if (new_size > 3*A53_MAX_CC_COUNT)
                 return AVERROR(EINVAL);
 
+            if (!cc_type_is_selected(s1, CC_TYPE_A53))
+                return 0;
+
             ret = av_buffer_realloc(&s1->a53_buf_ref, new_size);
             if (ret >= 0)
                 memcpy(s1->a53_buf_ref->data + old_size, p + 7, cc_count * UINT64_C(3));
@@ -2240,6 +2278,9 @@ static int mpeg_decode_a53_cc(AVCodecContext *avctx,
             if (new_size > 3*A53_MAX_CC_COUNT)
                 return AVERROR(EINVAL);
 
+            if (!cc_type_is_selected(s1, CC_TYPE_SCTE20))
+                return 0;
+
             ret = av_buffer_realloc(&s1->a53_buf_ref, new_size);
             if (ret >= 0) {
                 uint8_t field, cc1, cc2;
@@ -2310,6 +2351,9 @@ static int mpeg_decode_a53_cc(AVCodecContext *avctx,
             if (new_size > 3*A53_MAX_CC_COUNT)
                 return AVERROR(EINVAL);
 
+            if (!cc_type_is_selected(s1, CC_TYPE_DVD))
+                return 0;
+
             ret = av_buffer_realloc(&s1->a53_buf_ref, new_size);
             if (ret >= 0) {
                 uint8_t field1 = !!(p[4] & 0x80);
-- 
2.35.1