[FFmpeg-cvslog] avformat/mxfenc: support XAVC long gop

Baptiste Coudurier git at videolan.org
Mon May 20 22:00:15 EEST 2019


ffmpeg | branch: master | Baptiste Coudurier <baptiste.coudurier at gmail.com> | Thu Oct 18 13:37:05 2018 -0700| [b401a4ab8aa85c536bd9eee0da8f51551b66c70e] | committer: Baptiste Coudurier

avformat/mxfenc: support XAVC long gop

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=b401a4ab8aa85c536bd9eee0da8f51551b66c70e
---

 libavformat/Makefile |   2 +-
 libavformat/avc.c    | 186 ++++++++++++++++++++++++++++++++++++++++++++
 libavformat/avc.h    |  15 ++++
 libavformat/hevc.c   |  36 +--------
 libavformat/mxf.h    |   1 +
 libavformat/mxfenc.c | 213 ++++++++++++++++++++++++++++++++++++++++-----------
 6 files changed, 372 insertions(+), 81 deletions(-)

diff --git a/libavformat/Makefile b/libavformat/Makefile
index 99be60d184..df87c54a58 100644
--- a/libavformat/Makefile
+++ b/libavformat/Makefile
@@ -339,7 +339,7 @@ OBJS-$(CONFIG_MUSX_DEMUXER)              += musx.o
 OBJS-$(CONFIG_MV_DEMUXER)                += mvdec.o
 OBJS-$(CONFIG_MVI_DEMUXER)               += mvi.o
 OBJS-$(CONFIG_MXF_DEMUXER)               += mxfdec.o mxf.o
-OBJS-$(CONFIG_MXF_MUXER)                 += mxfenc.o mxf.o audiointerleave.o
+OBJS-$(CONFIG_MXF_MUXER)                 += mxfenc.o mxf.o audiointerleave.o avc.o
 OBJS-$(CONFIG_MXG_DEMUXER)               += mxg.o
 OBJS-$(CONFIG_NC_DEMUXER)                += ncdec.o
 OBJS-$(CONFIG_NISTSPHERE_DEMUXER)        += nistspheredec.o pcm.o
diff --git a/libavformat/avc.c b/libavformat/avc.c
index ec50033a04..a041e84357 100644
--- a/libavformat/avc.c
+++ b/libavformat/avc.c
@@ -21,6 +21,7 @@
 
 #include "libavutil/intreadwrite.h"
 #include "libavcodec/h264.h"
+#include "libavcodec/get_bits.h"
 #include "avformat.h"
 #include "avio.h"
 #include "avc.h"
@@ -241,3 +242,188 @@ const uint8_t *ff_avc_mp4_find_startcode(const uint8_t *start,
 
     return start + res;
 }
+
+uint8_t *ff_nal_unit_extract_rbsp(const uint8_t *src, uint32_t src_len,
+                                  uint32_t *dst_len, int header_len)
+{
+    uint8_t *dst;
+    uint32_t i, len;
+
+    dst = av_malloc(src_len + AV_INPUT_BUFFER_PADDING_SIZE);
+    if (!dst)
+        return NULL;
+
+    /* NAL unit header */
+    i = len = 0;
+    while (i < header_len && i < src_len)
+        dst[len++] = src[i++];
+
+    while (i + 2 < src_len)
+        if (!src[i] && !src[i + 1] && src[i + 2] == 3) {
+            dst[len++] = src[i++];
+            dst[len++] = src[i++];
+            i++; // remove emulation_prevention_three_byte
+        } else
+            dst[len++] = src[i++];
+
+    while (i < src_len)
+        dst[len++] = src[i++];
+
+    memset(dst + len, 0, AV_INPUT_BUFFER_PADDING_SIZE);
+
+    *dst_len = len;
+    return dst;
+}
+
+static const AVRational avc_sample_aspect_ratio[17] = {
+    {   0,  1 },
+    {   1,  1 },
+    {  12, 11 },
+    {  10, 11 },
+    {  16, 11 },
+    {  40, 33 },
+    {  24, 11 },
+    {  20, 11 },
+    {  32, 11 },
+    {  80, 33 },
+    {  18, 11 },
+    {  15, 11 },
+    {  64, 33 },
+    { 160, 99 },
+    {   4,  3 },
+    {   3,  2 },
+    {   2,  1 },
+};
+
+static inline int get_ue_golomb(GetBitContext *gb) {
+    int i;
+    for (i = 0; i < 32 && !get_bits1(gb); i++)
+        ;
+    return get_bitsz(gb, i) + (1 << i) - 1;
+}
+
+static inline int get_se_golomb(GetBitContext *gb) {
+    int v = get_ue_golomb(gb) + 1;
+    int sign = -(v & 1);
+    return ((v >> 1) ^ sign) - sign;
+}
+
+H264SequenceParameterSet *ff_avc_decode_sps(const uint8_t *buf, int buf_size)
+{
+    int i, j, ret, rbsp_size, aspect_ratio_idc, pic_order_cnt_type;
+    int num_ref_frames_in_pic_order_cnt_cycle;
+    int delta_scale, lastScale = 8, nextScale = 8;
+    int sizeOfScalingList;
+    H264SequenceParameterSet *sps = NULL;
+    GetBitContext gb;
+    uint8_t *rbsp_buf;
+
+    rbsp_buf = ff_nal_unit_extract_rbsp(buf, buf_size, &rbsp_size, 0);
+    if (!rbsp_buf)
+        return NULL;
+
+    ret = init_get_bits8(&gb, rbsp_buf, rbsp_size);
+    if (ret < 0)
+        goto end;
+
+    sps = av_mallocz(sizeof(*sps));
+    if (!sps)
+        goto end;
+
+    sps->profile_idc = get_bits(&gb, 8);
+    sps->constraint_set_flags |= get_bits1(&gb) << 0; // constraint_set0_flag
+    sps->constraint_set_flags |= get_bits1(&gb) << 1; // constraint_set1_flag
+    sps->constraint_set_flags |= get_bits1(&gb) << 2; // constraint_set2_flag
+    sps->constraint_set_flags |= get_bits1(&gb) << 3; // constraint_set3_flag
+    sps->constraint_set_flags |= get_bits1(&gb) << 4; // constraint_set4_flag
+    sps->constraint_set_flags |= get_bits1(&gb) << 5; // constraint_set5_flag
+    skip_bits(&gb, 2); // reserved_zero_2bits
+    sps->level_idc = get_bits(&gb, 8);
+    sps->id = get_ue_golomb(&gb);
+
+    if (sps->profile_idc == 100 || sps->profile_idc == 110 ||
+        sps->profile_idc == 122 || sps->profile_idc == 244 || sps->profile_idc ==  44 ||
+        sps->profile_idc ==  83 || sps->profile_idc ==  86 || sps->profile_idc == 118 ||
+        sps->profile_idc == 128 || sps->profile_idc == 138 || sps->profile_idc == 139 ||
+        sps->profile_idc == 134) {
+        sps->chroma_format_idc = get_ue_golomb(&gb); // chroma_format_idc
+        if (sps->chroma_format_idc == 3) {
+            skip_bits1(&gb); // separate_colour_plane_flag
+        }
+        sps->bit_depth_luma = get_ue_golomb(&gb) + 8;
+        get_ue_golomb(&gb); // bit_depth_chroma_minus8
+        skip_bits1(&gb); // qpprime_y_zero_transform_bypass_flag
+        if (get_bits1(&gb)) { // seq_scaling_matrix_present_flag
+            for (i = 0; i < ((sps->chroma_format_idc != 3) ? 8 : 12); i++) {
+                if (!get_bits1(&gb)) // seq_scaling_list_present_flag
+                    continue;
+                lastScale = 8;
+                nextScale = 8;
+                sizeOfScalingList = i < 6 ? 16 : 64;
+                for (j = 0; j < sizeOfScalingList; j++) {
+                    if (nextScale != 0) {
+                        delta_scale = get_se_golomb(&gb);
+                        nextScale = (lastScale + delta_scale) & 0xff;
+                    }
+                    lastScale = nextScale == 0 ? lastScale : nextScale;
+                }
+            }
+        }
+    } else {
+        sps->chroma_format_idc = 1;
+        sps->bit_depth_luma = 8;
+    }
+
+    get_ue_golomb(&gb); // log2_max_frame_num_minus4
+    pic_order_cnt_type = get_ue_golomb(&gb);
+
+    if (pic_order_cnt_type == 0) {
+        get_ue_golomb(&gb); // log2_max_pic_order_cnt_lsb_minus4
+    } else if (pic_order_cnt_type == 1) {
+        skip_bits1(&gb);    // delta_pic_order_always_zero
+        get_se_golomb(&gb); // offset_for_non_ref_pic
+        get_se_golomb(&gb); // offset_for_top_to_bottom_field
+        num_ref_frames_in_pic_order_cnt_cycle = get_ue_golomb(&gb);
+        for (i = 0; i < num_ref_frames_in_pic_order_cnt_cycle; i++)
+            get_se_golomb(&gb); // offset_for_ref_frame
+    }
+
+    get_ue_golomb(&gb); // max_num_ref_frames
+    skip_bits1(&gb); // gaps_in_frame_num_value_allowed_flag
+    get_ue_golomb(&gb); // pic_width_in_mbs_minus1
+    get_ue_golomb(&gb); // pic_height_in_map_units_minus1
+
+    sps->frame_mbs_only_flag = get_bits1(&gb);
+    if (!sps->frame_mbs_only_flag)
+        skip_bits1(&gb); // mb_adaptive_frame_field_flag
+
+    skip_bits1(&gb); // direct_8x8_inference_flag
+
+    if (get_bits1(&gb)) { // frame_cropping_flag
+        get_ue_golomb(&gb); // frame_crop_left_offset
+        get_ue_golomb(&gb); // frame_crop_right_offset
+        get_ue_golomb(&gb); // frame_crop_top_offset
+        get_ue_golomb(&gb); // frame_crop_bottom_offset
+    }
+
+    if (get_bits1(&gb)) { // vui_parameters_present_flag
+        if (get_bits1(&gb)) { // aspect_ratio_info_present_flag
+            aspect_ratio_idc = get_bits(&gb, 8);
+            if (aspect_ratio_idc == 0xff) {
+                sps->sar.num = get_bits(&gb, 16);
+                sps->sar.den = get_bits(&gb, 16);
+            } else if (aspect_ratio_idc < FF_ARRAY_ELEMS(avc_sample_aspect_ratio)) {
+                sps->sar = avc_sample_aspect_ratio[aspect_ratio_idc];
+            }
+        }
+    }
+
+    if (!sps->sar.den) {
+        sps->sar.num = 1;
+        sps->sar.den = 1;
+    }
+
+ end:
+    av_free(rbsp_buf);
+    return sps;
+}
diff --git a/libavformat/avc.h b/libavformat/avc.h
index c5e80ff650..a79bf9b2db 100644
--- a/libavformat/avc.h
+++ b/libavformat/avc.h
@@ -33,5 +33,20 @@ int ff_avc_write_annexb_extradata(const uint8_t *in, uint8_t **buf, int *size);
 const uint8_t *ff_avc_mp4_find_startcode(const uint8_t *start,
                                          const uint8_t *end,
                                          int nal_length_size);
+uint8_t *ff_nal_unit_extract_rbsp(const uint8_t *src, uint32_t src_len,
+                                  uint32_t *dst_len, int header_len);
+
+typedef struct {
+    uint8_t id;
+    uint8_t profile_idc;
+    uint8_t level_idc;
+    uint8_t constraint_set_flags;
+    uint8_t chroma_format_idc;
+    uint8_t bit_depth_luma;
+    uint8_t frame_mbs_only_flag;
+    AVRational sar;
+} H264SequenceParameterSet;
+
+H264SequenceParameterSet *ff_avc_decode_sps(const uint8_t *src, int src_len);
 
 #endif /* AVFORMAT_AVC_H */
diff --git a/libavformat/hevc.c b/libavformat/hevc.c
index 3628d5a028..c7c4be3441 100644
--- a/libavformat/hevc.c
+++ b/libavformat/hevc.c
@@ -643,40 +643,6 @@ static int hvcc_parse_pps(GetBitContext *gb,
     return 0;
 }
 
-static uint8_t *nal_unit_extract_rbsp(const uint8_t *src, uint32_t src_len,
-                                      uint32_t *dst_len)
-{
-    uint8_t *dst;
-    uint32_t i, len;
-
-    dst = av_malloc(src_len + AV_INPUT_BUFFER_PADDING_SIZE);
-    if (!dst)
-        return NULL;
-
-    /* NAL unit header (2 bytes) */
-    i = len = 0;
-    while (i < 2 && i < src_len)
-        dst[len++] = src[i++];
-
-    while (i + 2 < src_len)
-        if (!src[i] && !src[i + 1] && src[i + 2] == 3) {
-            dst[len++] = src[i++];
-            dst[len++] = src[i++];
-            i++; // remove emulation_prevention_three_byte
-        } else
-            dst[len++] = src[i++];
-
-    while (i < src_len)
-        dst[len++] = src[i++];
-
-    memset(dst + len, 0, AV_INPUT_BUFFER_PADDING_SIZE);
-
-    *dst_len = len;
-    return dst;
-}
-
-
-
 static void nal_unit_parse_header(GetBitContext *gb, uint8_t *nal_type)
 {
     skip_bits1(gb); // forbidden_zero_bit
@@ -753,7 +719,7 @@ static int hvcc_add_nal_unit(uint8_t *nal_buf, uint32_t nal_size,
     uint8_t *rbsp_buf;
     uint32_t rbsp_size;
 
-    rbsp_buf = nal_unit_extract_rbsp(nal_buf, nal_size, &rbsp_size);
+    rbsp_buf = ff_nal_unit_extract_rbsp(nal_buf, nal_size, &rbsp_size, 2);
     if (!rbsp_buf) {
         ret = AVERROR(ENOMEM);
         goto end;
diff --git a/libavformat/mxf.h b/libavformat/mxf.h
index 4394450dea..f32124f772 100644
--- a/libavformat/mxf.h
+++ b/libavformat/mxf.h
@@ -48,6 +48,7 @@ enum MXFMetadataSetType {
     EssenceGroup,
     TaggedValue,
     TapeDescriptor,
+    AVCSubDescriptor,
 };
 
 enum MXFFrameLayout {
diff --git a/libavformat/mxfenc.c b/libavformat/mxfenc.c
index 8c6db94865..b677f6af8e 100644
--- a/libavformat/mxfenc.c
+++ b/libavformat/mxfenc.c
@@ -49,12 +49,14 @@
 #include "libavcodec/bytestream.h"
 #include "libavcodec/dnxhddata.h"
 #include "libavcodec/dv_profile.h"
-#include "libavcodec/h264.h"
+#include "libavcodec/h264_ps.h"
+#include "libavcodec/golomb.h"
 #include "libavcodec/internal.h"
 #include "audiointerleave.h"
 #include "avformat.h"
 #include "avio_internal.h"
 #include "internal.h"
+#include "avc.h"
 #include "mxf.h"
 #include "config.h"
 
@@ -99,6 +101,7 @@ typedef struct MXFStreamContext {
     int max_gop;             ///< maximum gop size, used by mpeg-2 descriptor
     int b_picture_count;     ///< maximum number of consecutive b pictures, used in mpeg-2 descriptor
     int low_delay;           ///< low delay, used in mpeg-2 descriptor
+    int avc_intra;
 } MXFStreamContext;
 
 typedef struct MXFContainerEssenceEntry {
@@ -167,6 +170,7 @@ static const struct {
 static void mxf_write_wav_desc(AVFormatContext *s, AVStream *st);
 static void mxf_write_aes3_desc(AVFormatContext *s, AVStream *st);
 static void mxf_write_mpegvideo_desc(AVFormatContext *s, AVStream *st);
+static void mxf_write_h264_desc(AVFormatContext *s, AVStream *st);
 static void mxf_write_cdci_desc(AVFormatContext *s, AVStream *st);
 static void mxf_write_generic_sound_desc(AVFormatContext *s, AVStream *st);
 static void mxf_write_s436m_anc_desc(AVFormatContext *s, AVStream *st);
@@ -310,7 +314,7 @@ static const MXFContainerEssenceEntry mxf_essence_container_uls[] = {
     { { 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x0D,0x01,0x03,0x01,0x02,0x10,0x60,0x01 },
       { 0x06,0x0E,0x2B,0x34,0x01,0x02,0x01,0x01,0x0D,0x01,0x03,0x01,0x15,0x01,0x05,0x00 },
       { 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x00,0x00,0x00 },
-      mxf_write_mpegvideo_desc },
+      mxf_write_h264_desc },
     // S436M ANC
     { { 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x0D,0x01,0x03,0x01,0x02,0x0e,0x00,0x00 },
       { 0x06,0x0E,0x2B,0x34,0x01,0x02,0x01,0x01,0x0D,0x01,0x03,0x01,0x17,0x01,0x02,0x00 },
@@ -503,6 +507,13 @@ static const MXFLocalTagPair mxf_local_tag_batch[] = {
     { 0x3D0A, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x05,0x04,0x02,0x03,0x02,0x01,0x00,0x00,0x00}}, /* Block Align */
 };
 
+static const MXFLocalTagPair mxf_avc_subdescriptor_local_tags[] = {
+    { 0x8100, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x09,0x06,0x01,0x01,0x04,0x06,0x10,0x00,0x00}}, /* SubDescriptors */
+    { 0x8200, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x0E,0x04,0x01,0x06,0x06,0x01,0x0E,0x00,0x00}}, /* AVC Decoding Delay */
+    { 0x8201, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x0E,0x04,0x01,0x06,0x06,0x01,0x0A,0x00,0x00}}, /* AVC Profile */
+    { 0x8202, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x0E,0x04,0x01,0x06,0x06,0x01,0x0D,0x00,0x00}}, /* AVC Level */
+};
+
 static const MXFLocalTagPair mxf_user_comments_local_tag[] = {
     { 0x4406, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x02,0x03,0x02,0x01,0x02,0x0C,0x00,0x00,0x00}}, /* User Comments */
     { 0x5001, {0x06,0x0E,0x2B,0x34,0x01,0x01,0x01,0x02,0x03,0x02,0x01,0x02,0x09,0x01,0x00,0x00}}, /* Name */
@@ -584,15 +595,33 @@ static int mxf_get_essence_container_ul_index(enum AVCodecID id)
     return -1;
 }
 
+static void mxf_write_local_tags(AVIOContext *pb, const MXFLocalTagPair *local_tags, int count)
+{
+    int i;
+    for (i = 0; i < count; i++) {
+        avio_wb16(pb, local_tags[i].local_tag);
+        avio_write(pb, local_tags[i].uid, 16);
+    }
+}
+
 static void mxf_write_primer_pack(AVFormatContext *s)
 {
     MXFContext *mxf = s->priv_data;
     AVIOContext *pb = s->pb;
     int local_tag_number, i = 0;
+    int avc_tags_count = 0;
 
     local_tag_number = FF_ARRAY_ELEMS(mxf_local_tag_batch);
     local_tag_number += mxf->store_user_comments * FF_ARRAY_ELEMS(mxf_user_comments_local_tag);
 
+    for (i = 0; i < s->nb_streams; i++) {
+        MXFStreamContext *sc = s->streams[i]->priv_data;
+        if (s->streams[i]->codecpar->codec_id == AV_CODEC_ID_H264 && !sc->avc_intra) {
+            avc_tags_count = FF_ARRAY_ELEMS(mxf_avc_subdescriptor_local_tags);
+            local_tag_number += avc_tags_count;
+        }
+    }
+
     avio_write(pb, primer_pack_key, 16);
     klv_encode_ber_length(pb, local_tag_number * 18 + 8);
 
@@ -608,6 +637,8 @@ static void mxf_write_primer_pack(AVFormatContext *s)
             avio_wb16(pb, mxf_user_comments_local_tag[i].local_tag);
             avio_write(pb, mxf_user_comments_local_tag[i].uid, 16);
         }
+    if (avc_tags_count > 0)
+        mxf_write_local_tags(pb, mxf_avc_subdescriptor_local_tags, avc_tags_count);
 }
 
 static void mxf_write_local_tag(AVIOContext *pb, int size, int tag)
@@ -1126,6 +1157,8 @@ static const UID mxf_aes3_descriptor_key      = { 0x06,0x0E,0x2B,0x34,0x02,0x53,
 static const UID mxf_cdci_descriptor_key      = { 0x06,0x0E,0x2B,0x34,0x02,0x53,0x01,0x01,0x0D,0x01,0x01,0x01,0x01,0x01,0x28,0x00 };
 static const UID mxf_generic_sound_descriptor_key = { 0x06,0x0E,0x2B,0x34,0x02,0x53,0x01,0x01,0x0D,0x01,0x01,0x01,0x01,0x01,0x42,0x00 };
 
+static const UID mxf_avc_subdescriptor_key = { 0x06,0x0E,0x2B,0x34,0x02,0x53,0x01,0x01,0x0d,0x01,0x01,0x01,0x01,0x01,0x6E,0x00 };
+
 static int get_trc(UID ul, enum AVColorTransferCharacteristic trc)
 {
     switch (trc){
@@ -1317,6 +1350,13 @@ static int64_t mxf_write_cdci_common(AVFormatContext *s, AVStream *st, const UID
         avio_w8(pb, sc->field_dominance);
     }
 
+    if (st->codecpar->codec_id == AV_CODEC_ID_H264 && !sc->avc_intra) {
+        // write avc sub descriptor ref
+        mxf_write_local_tag(pb, 8 + 16, 0x8100);
+        mxf_write_refs_count(pb, 1);
+        mxf_write_uuid(pb, AVCSubDescriptor, 0);
+    }
+
     return pos;
 }
 
@@ -1329,10 +1369,50 @@ static void mxf_update_klv_size(AVIOContext *pb, int64_t pos)
     avio_seek(pb, cur_pos, SEEK_SET);
 }
 
+static void mxf_write_avc_subdesc(AVFormatContext *s, AVStream *st)
+{
+    AVIOContext *pb = s->pb;
+    int64_t pos;
+
+    avio_write(pb, mxf_avc_subdescriptor_key, 16);
+    klv_encode_ber4_length(pb, 0);
+    pos = avio_tell(pb);
+
+    mxf_write_local_tag(pb, 16, 0x3C0A);
+    mxf_write_uuid(pb, AVCSubDescriptor, 0);
+
+    mxf_write_local_tag(pb, 1, 0x8200);
+    avio_w8(pb, 0xFF); // AVC Decoding Delay, unknown
+
+    mxf_write_local_tag(pb, 1, 0x8201);
+    avio_w8(pb, st->codecpar->profile); // AVC Profile
+
+    mxf_write_local_tag(pb, 1, 0x8202);
+    avio_w8(pb, st->codecpar->level); // AVC Level
+
+    mxf_update_klv_size(s->pb, pos);
+}
+
 static void mxf_write_cdci_desc(AVFormatContext *s, AVStream *st)
 {
     int64_t pos = mxf_write_cdci_common(s, st, mxf_cdci_descriptor_key);
     mxf_update_klv_size(s->pb, pos);
+
+    if (st->codecpar->codec_id == AV_CODEC_ID_H264) {
+        mxf_write_avc_subdesc(s, st);
+    }
+}
+
+static void mxf_write_h264_desc(AVFormatContext *s, AVStream *st)
+{
+    MXFStreamContext *sc = st->priv_data;
+    if (sc->avc_intra) {
+        mxf_write_mpegvideo_desc(s, st);
+    } else {
+        int64_t pos = mxf_write_cdci_common(s, st, mxf_cdci_descriptor_key);
+        mxf_update_klv_size(s->pb, pos);
+        mxf_write_avc_subdesc(s, st);
+    }
 }
 
 static void mxf_write_s436m_anc_desc(AVFormatContext *s, AVStream *st)
@@ -2136,30 +2216,30 @@ static const struct {
     int frame_size;
     int profile;
     uint8_t interlaced;
-    int long_gop; // 1 or 0 when there are separate UIDs for Long GOP and Intra, -1 when Intra/LGOP detection can be ignored
+    int intra_only; // 1 or 0 when there are separate UIDs for Long GOP and Intra, -1 when Intra/LGOP detection can be ignored
 } mxf_h264_codec_uls[] = {
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x11,0x01 },      0,  66, 0, -1 }, // AVC Baseline, Unconstrained Coding
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x11,0x01 },      0,  66, 0, -1 }, // AVC Baseline
     {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x20,0x01 },      0,  77, 0, -1 }, // AVC Main
     {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x30,0x01 },      0,  88, 0, -1 }, // AVC Extended
     {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x40,0x01 },      0, 100, 0, -1 }, // AVC High
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x50,0x01 },      0, 110, 0,  1 }, // AVC High 10
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x60,0x01 },      0, 122, 0,  1 }, // AVC High 422
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x70,0x01 },      0, 244, 0,  1 }, // AVC High 444
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x20,0x01 },      0, 110, 0,  0 }, // AVC High 10 Intra
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x01 }, 232960,   0, 1,  0 }, // AVC Intra 50 1080i60
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x02 }, 281088,   0, 1,  0 }, // AVC Intra 50 1080i50
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x03 }, 232960,   0, 0,  0 }, // AVC Intra 50 1080p30
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x04 }, 281088,   0, 0,  0 }, // AVC Intra 50 1080p25
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x08 }, 116736,   0, 0,  0 }, // AVC Intra 50 720p60
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x09 }, 140800,   0, 0,  0 }, // AVC Intra 50 720p50
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x30,0x01 },      0, 122, 0,  0 }, // AVC High 422 Intra
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x01 }, 472576,   0, 1,  0 }, // AVC Intra 100 1080i60
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x02 }, 568832,   0, 1,  0 }, // AVC Intra 100 1080i50
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x03 }, 472576,   0, 0,  0 }, // AVC Intra 100 1080p30
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x04 }, 568832,   0, 0,  0 }, // AVC Intra 100 1080p25
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x08 }, 236544,   0, 0,  0 }, // AVC Intra 100 720p60
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x09 }, 284672,   0, 0,  0 }, // AVC Intra 100 720p50
-    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0d,0x04,0x01,0x02,0x02,0x01,0x32,0x40,0x01 },      0, 244, 0,  0 }, // AVC High 444 Intra
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x50,0x01 },      0, 110, 0,  0 }, // AVC High 10
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x60,0x01 },      0, 122, 0,  0 }, // AVC High 422
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x31,0x70,0x01 },      0, 244, 0,  0 }, // AVC High 444
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x20,0x01 },      0, 110, 0,  1 }, // AVC High 10 Intra
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x01 }, 232960, 110, 1,  1 }, // AVC High 10 Intra RP2027 Class 50 1080/59.94i
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x02 }, 281088, 110, 1,  1 }, // AVC High 10 Intra RP2027 Class 50 1080/50i
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x03 }, 232960, 110, 0,  1 }, // AVC High 10 Intra RP2027 Class 50 1080/29.97p
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x04 }, 281088, 110, 0,  1 }, // AVC High 10 Intra RP2027 Class 50 1080/25p
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x08 }, 116736, 110, 0,  1 }, // AVC High 10 Intra RP2027 Class 50 720/59.94p
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x21,0x09 }, 140800, 110, 0,  1 }, // AVC High 10 Intra RP2027 Class 50 720/50p
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x30,0x01 },      0, 122, 0,  1 }, // AVC High 422 Intra
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x01 }, 472576, 122, 1,  1 }, // AVC High 422 Intra RP2027 Class 100 1080/59.94i
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x02 }, 568832, 122, 1,  1 }, // AVC High 422 Intra RP2027 Class 100 1080/50i
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x03 }, 472576, 122, 0,  1 }, // AVC High 422 Intra RP2027 Class 100 1080/29.97p
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x04 }, 568832, 122, 0,  1 }, // AVC High 422 Intra RP2027 Class 100 1080/25p
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x08 }, 236544, 122, 0,  1 }, // AVC High 422 Intra RP2027 Class 100 720/59.94p
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0a,0x04,0x01,0x02,0x02,0x01,0x32,0x31,0x09 }, 284672, 122, 0,  1 }, // AVC High 422 Intra RP2027 Class 100 720/50p
+    {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0d,0x04,0x01,0x02,0x02,0x01,0x32,0x40,0x01 },      0, 244, 0,  1 }, // AVC High 444 Intra
     {{ 0x06,0x0E,0x2B,0x34,0x04,0x01,0x01,0x0d,0x04,0x01,0x02,0x02,0x01,0x32,0x50,0x01 },      0,  44, 0, -1 }, // AVC CAVLC 444
 };
 
@@ -2168,37 +2248,70 @@ static int mxf_parse_h264_frame(AVFormatContext *s, AVStream *st,
 {
     MXFContext *mxf = s->priv_data;
     MXFStreamContext *sc = st->priv_data;
-    AVCodecParameters *par = st->codecpar;
-    static const int mxf_h264_num_codec_uls = sizeof(mxf_h264_codec_uls) / sizeof(mxf_h264_codec_uls[0]);
+    H264SequenceParameterSet *sps = NULL;
+    GetBitContext gb;
     const uint8_t *buf = pkt->data;
     const uint8_t *buf_end = pkt->data + pkt->size;
+    const uint8_t *nal_end;
     uint32_t state = -1;
-    int long_gop = 0; // assume intra when there is no SPS header
     int extra_size = 512; // support AVC Intra files without SPS/PPS header
-    int i, frame_size;
-    uint8_t uid_found;
-
-    if (pkt->size > extra_size)
-        buf_end -= pkt->size - extra_size; // no need to parse beyond SPS/PPS header
+    int i, frame_size, slice_type, intra_only = 0;
 
     for (;;) {
         buf = avpriv_find_start_code(buf, buf_end, &state);
         if (buf >= buf_end)
             break;
-        --buf;
+
         switch (state & 0x1f) {
         case H264_NAL_SPS:
-            par->profile = buf[1];
-            long_gop = buf[2] & 0x10 ? 0 : 1; // constraint_set3_flag signals intra
             e->flags |= 0x40;
+
+            if (mxf->header_written)
+                break;
+
+            nal_end = ff_avc_find_startcode(buf, buf_end);
+            sps = ff_avc_decode_sps(buf, nal_end - buf);
+            if (!sps) {
+                av_log(s, AV_LOG_ERROR, "error parsing sps\n");
+                return 0;
+            }
+
+            sc->aspect_ratio.num = st->codecpar->width * sps->sar.num;
+            sc->aspect_ratio.den = st->codecpar->height * sps->sar.den;
+            av_reduce(&sc->aspect_ratio.num, &sc->aspect_ratio.den,
+                      sc->aspect_ratio.num, sc->aspect_ratio.den, 1024*1024);
+            intra_only = (sps->constraint_set_flags >> 3) & 1;
+            sc->interlaced = !sps->frame_mbs_only_flag;
+            sc->component_depth = sps->bit_depth_luma;
+
+            buf = nal_end;
             break;
         case H264_NAL_PPS:
             if (e->flags & 0x40) { // sequence header present
                 e->flags |= 0x80; // random access
                 extra_size = 0;
-                buf = buf_end;
             }
             break;
+        case H264_NAL_IDR_SLICE:
+            e->flags |= 0x04; // IDR Picture
+            buf = buf_end;
+            break;
+        case H264_NAL_SLICE:
+            init_get_bits8(&gb, buf, buf_end - buf);
+            get_ue_golomb_long(&gb); // skip first_mb_in_slice
+            slice_type = get_ue_golomb_31(&gb);
+            switch (slice_type % 5) {
+            case 0:
+                e->flags |= 0x20; // P Picture
+                e->flags |= 0x06; // P Picture
+                break;
+            case 1:
+                e->flags |= 0x30; // B Picture
+                e->flags |= 0x03; // non-referenced B Picture
+                break;
+            }
+            buf = buf_end;
+            break;
         default:
             break;
         }
@@ -2207,27 +2320,37 @@ static int mxf_parse_h264_frame(AVFormatContext *s, AVStream *st,
     if (mxf->header_written)
         return 1;
 
-    sc->aspect_ratio = (AVRational){ 16, 9 }; // 16:9 is mandatory for broadcast HD
-    sc->interlaced = par->field_order != AV_FIELD_PROGRESSIVE ? 1 : 0;
-
-    uid_found = 0;
+    if (!sps)
+        sc->interlaced = st->codecpar->field_order != AV_FIELD_PROGRESSIVE ? 1 : 0;
+    sc->codec_ul = NULL;
     frame_size = pkt->size + extra_size;
-    for (i = 0; i < mxf_h264_num_codec_uls; i++) {
+
+    for (i = 0; i < FF_ARRAY_ELEMS(mxf_h264_codec_uls); i++) {
         if (frame_size == mxf_h264_codec_uls[i].frame_size && sc->interlaced == mxf_h264_codec_uls[i].interlaced) {
             sc->codec_ul = &mxf_h264_codec_uls[i].uid;
             sc->component_depth = 10; // AVC Intra is always 10 Bit
+            sc->aspect_ratio = (AVRational){ 16, 9 }; // 16:9 is mandatory for broadcast HD
+            st->codecpar->profile = mxf_h264_codec_uls[i].profile;
+            sc->avc_intra = 1;
+            mxf->cbr_index = 1;
+            sc->frame_size = pkt->size;
             if (sc->interlaced)
                 sc->field_dominance = 1; // top field first is mandatory for AVC Intra
-            return 1;
-        } else if ((mxf_h264_codec_uls[i].profile == par->profile) &&
-                   ((mxf_h264_codec_uls[i].long_gop < 0) ||
-                   (mxf_h264_codec_uls[i].long_gop == long_gop))) {
+            break;
+        } else if (sps && mxf_h264_codec_uls[i].frame_size == 0 &&
+                   mxf_h264_codec_uls[i].profile == sps->profile_idc &&
+                   (mxf_h264_codec_uls[i].intra_only < 0 ||
+                    mxf_h264_codec_uls[i].intra_only == intra_only)) {
             sc->codec_ul = &mxf_h264_codec_uls[i].uid;
-            uid_found = 1;
+            st->codecpar->profile = sps->profile_idc;
+            st->codecpar->level = sps->level_idc;
+            // continue to check for avc intra
         }
     }
 
-    if (!uid_found) {
+    av_free(sps);
+
+    if (!sc->codec_ul) {
         av_log(s, AV_LOG_ERROR, "h264 profile not supported\n");
         return 0;
     }



More information about the ffmpeg-cvslog mailing list