void H264or5VideoStreamParser
::removeEmulationBytes(u_int8_t* nalUnitCopy, unsigned maxSize, unsigned& nalUnitCopySize) {
u_int8_t* nalUnitOrig = fStartOfFrame + fOutputStartCodeSize;
unsigned const numBytesInNALunit = fTo - nalUnitOrig;
nalUnitCopySize
= removeH264or5EmulationBytes(nalUnitCopy, maxSize, nalUnitOrig, numBytesInNALunit);
}
char const* H264VideoRTPSink::auxSDPLine() {
liveLogInfo(" H264VideoRTPSink::auxSDPLine \n");
// Generate a new "a=fmtp:" line each time, using our SPS and PPS (if we have them),
// otherwise parameters from our framer source (in case they've changed since the last time that
// we were called):
H264or5VideoStreamFramer* framerSource = NULL;
u_int8_t* vpsDummy = NULL; unsigned vpsDummySize = 0;
u_int8_t* sps = fSPS; unsigned spsSize = fSPSSize;
u_int8_t* pps = fPPS; unsigned ppsSize = fPPSSize;
if (sps == NULL || pps == NULL) {
// We need to get SPS and PPS from our framer source:
if (fOurFragmenter == NULL) return NULL; // we don't yet have a fragmenter (and therefore not a source)
framerSource = (H264or5VideoStreamFramer*)(fOurFragmenter->inputSource());
if (framerSource == NULL) return NULL; // we don't yet have a source
framerSource->getVPSandSPSandPPS(vpsDummy, vpsDummySize, sps, spsSize, pps, ppsSize);
if (sps == NULL || pps == NULL) return NULL; // our source isn't ready
}
// Set up the "a=fmtp:" SDP line for this stream:
u_int8_t* spsWEB = new u_int8_t[spsSize]; // "WEB" means "Without Emulation Bytes"
unsigned spsWEBSize = removeH264or5EmulationBytes(spsWEB, spsSize, sps, spsSize);
if (spsWEBSize < 4) { // Bad SPS size => assume our source isn't ready
delete[] spsWEB;
return NULL;
}
u_int32_t profileLevelId = (spsWEB[1]<<16) | (spsWEB[2]<<8) | spsWEB[3];
delete[] spsWEB;
char* sps_base64 = base64Encode((char*)sps, spsSize);
char* pps_base64 = base64Encode((char*)pps, ppsSize);
char const* fmtpFmt =
"a=fmtp:%d packetization-mode=1"
";profile-level-id=%06X"
";sprop-parameter-sets=%s,%s\r\n";
unsigned fmtpFmtSize = strlen(fmtpFmt)
+ 3 /* max char len */
+ 6 /* 3 bytes in hex */
+ strlen(sps_base64) + strlen(pps_base64);
char* fmtp = new char[fmtpFmtSize];
sprintf(fmtp, fmtpFmt,
rtpPayloadType(),
profileLevelId,
sps_base64, pps_base64);
delete[] sps_base64;
delete[] pps_base64;
delete[] fFmtpSDPLine; fFmtpSDPLine = fmtp;
return fFmtpSDPLine;
}
void H264or5VideoStreamFramer::saveCopyOfVPS(u_int8_t* from, unsigned size) {
if (from == NULL) return;
delete[] fLastSeenVPS;
fLastSeenVPS = new u_int8_t[size];
memmove(fLastSeenVPS, from, size);
fLastSeenVPSSize = size;
// We also make another copy - without 'emulation bytes', to extract parameters that we need:
u_int8_t vps[VPS_MAX_SIZE];
unsigned vpsSize
= removeH264or5EmulationBytes(vps, VPS_MAX_SIZE, fLastSeenVPS, fLastSeenVPSSize);
// Extract the first 12 'profile_tier_level' bytes:
if (vpsSize >= 6/*'profile_tier_level' offset*/ + 12/*num 'profile_tier_level' bytes*/) {
memmove(fProfileTierLevelHeaderBytes, &vps[6], 12);
}
}
void H264or5VideoStreamFramer::saveCopyOfSPS(u_int8_t* from, unsigned size) {
if (from == NULL) return;
delete[] fLastSeenSPS;
fLastSeenSPS = new u_int8_t[size];
memmove(fLastSeenSPS, from, size);
fLastSeenSPSSize = size;
// We also make another copy - without 'emulation bytes', to extract parameters that we need:
u_int8_t sps[SPS_MAX_SIZE];
unsigned spsSize
= removeH264or5EmulationBytes(sps, SPS_MAX_SIZE, fLastSeenSPS, fLastSeenSPSSize);
if (fHNumber == 264) {
// Extract the first 3 bytes of the SPS (after the nal_unit_header byte) as 'profile_level_id'
if (spsSize >= 1/*'profile_level_id' offset within SPS*/ + 3/*num bytes needed*/) {
fProfileLevelId = (sps[1]<<16) | (sps[2]<<8) | sps[3];
}
} else { // 265
// Extract the first 12 'profile_tier_level' bytes:
if (spsSize >= 3/*'profile_tier_level' offset*/ + 12/*num 'profile_tier_level' bytes*/) {
memmove(fProfileTierLevelHeaderBytes, &sps[3], 12);
}
}
}
H264StreamParser::H264StreamParser(uint8_t* sps, unsigned spsSize)
: _sps(SPS_MAX_SIZE), _width(0), _height(0), _framerate(0)
{
spsSize = removeH264or5EmulationBytes(_sps.data(), _sps.size(), sps, spsSize);
BitVector bv(_sps.data(), 0, spsSize * 8);
bv.skipBits(8); // forbidden_zero_bit; nal_ref_idc; nal_unit_type
unsigned profile_idc = bv.getBits(8);
bv.skipBits(8); // 6 constraint_setN_flag and "reserved_zero_2bits" at the end
bv.skipBits(8); // level_idc
unsigned seq_parameter_set_id = bv.get_expGolomb();
unsigned chroma_format_idc = 1;
Boolean separate_colour_plane_flag = False;
if (profile_idc == 100 || // High profile
profile_idc == 110 || // High10 profile
profile_idc == 122 || // High422 profile
profile_idc == 244 || // High444 Predictive profile
profile_idc == 44 || // Cavlc444 profile
profile_idc == 83 || // Scalable Constrained High profile (SVC)
profile_idc == 86 || // Scalable High Intra profile (SVC)
profile_idc == 118 || // Stereo High profile (MVC)
profile_idc == 128 || // Multiview High profile (MVC)
profile_idc == 138 || // Multiview Depth High profile (MVCD)
profile_idc == 144) // old High444 profile
{
chroma_format_idc = bv.get_expGolomb();
if (chroma_format_idc == 3)
separate_colour_plane_flag = bv.get1BitBoolean();
bv.get_expGolomb(); // bit_depth_luma_minus8
bv.get_expGolomb(); // bit_depth_chroma_minus8
bv.skipBits(1); // qpprime_y_zero_transform_bypass_flag
Boolean seq_scaling_matrix_present_flag = bv.get1BitBoolean();
if (seq_scaling_matrix_present_flag)
{
for (int i = 0; i < ((chroma_format_idc != 3) ? 8 : 12); ++i)
{
Boolean seq_scaling_list_present_flag = bv.get1BitBoolean();
if (seq_scaling_list_present_flag)
{
// Decode scaling matrices
unsigned sizeOfScalingList = i < 6 ? 16 : 64;
unsigned lastScale = 8;
unsigned nextScale = 8;
for (unsigned j = 0; j < sizeOfScalingList; ++j)
{
if (nextScale != 0)
{
unsigned delta_scale = bv.get_expGolomb();
nextScale = (lastScale + delta_scale + 256) % 256;
}
lastScale = (nextScale == 0) ? lastScale : nextScale;
}
}
}
}
}
unsigned log2_max_frame_num_minus4 = bv.get_expGolomb();
unsigned pic_order_cnt_type = bv.get_expGolomb();
if (pic_order_cnt_type == 0)
{
bv.get_expGolomb(); // log2_max_pic_order_cnt_lsb_minus4
}
else if (pic_order_cnt_type == 1)
{
bv.skipBits(1); // delta_pic_order_always_zero_flag
bv.get_expGolomb(); // offset_for_non_ref_pic SIGNED!
bv.get_expGolomb(); // offset_for_top_to_bottom_field SIGNED!
unsigned num_ref_frames_in_pic_order_cnt_cycle = bv.get_expGolomb();
for (unsigned i = 0; i < num_ref_frames_in_pic_order_cnt_cycle; ++i)
bv.get_expGolomb(); // offset_for_ref_frame[i] SIGNED!
}
unsigned num_ref_frames = bv.get_expGolomb();
Boolean gaps_in_frame_num_value_allowed_flag = bv.get1BitBoolean();
unsigned pic_width_in_mbs_minus1 = bv.get_expGolomb();
unsigned pic_height_in_map_units_minus1 = bv.get_expGolomb();
Boolean frame_mbs_only_flag = bv.get1BitBoolean();
if (!frame_mbs_only_flag)
bv.skipBits(1); // mb_adaptive_frame_field_flag
bv.skipBits(1); // direct_8x8_inference_flag
Boolean frame_cropping_flag = bv.get1BitBoolean();
unsigned frame_crop_left_offset = 0, frame_crop_right_offset = 0, frame_crop_top_offset = 0,
frame_crop_bottom_offset = 0;
if (frame_cropping_flag)
{
frame_crop_left_offset = bv.get_expGolomb();
frame_crop_right_offset = bv.get_expGolomb();
frame_crop_top_offset = bv.get_expGolomb();
frame_crop_bottom_offset = bv.get_expGolomb();
}
// Formula taken from MediaInfo
_width = (pic_width_in_mbs_minus1 + 1) * 16;
_height = (pic_height_in_map_units_minus1 + 1) * 16 * (2 - frame_mbs_only_flag);
unsigned chromaArrayType = separate_colour_plane_flag ? 0 : chroma_format_idc;
unsigned cropUnitX = subWidthChroma[chromaArrayType];
unsigned cropUnitY = subHeightChroma[chromaArrayType] * (2 - frame_mbs_only_flag);
_width -= (frame_crop_left_offset + frame_crop_right_offset) * cropUnitX;
_height -= (frame_crop_top_offset + frame_crop_bottom_offset) * cropUnitY;
Boolean vui_parameters_present_flag = bv.get1BitBoolean();
if (vui_parameters_present_flag)
{
// Decode VUI
Boolean aspect_ratio_info_present_flag = bv.get1BitBoolean();
if (aspect_ratio_info_present_flag)
{
unsigned aspect_ratio_idc = bv.getBits(8);
if (aspect_ratio_idc == 255 /*Extended_SAR*/)
bv.skipBits(32); // sar_width(16); sar_height(16)
}
Boolean overscan_info_present_flag = bv.get1BitBoolean();
if (overscan_info_present_flag)
bv.skipBits(1); // overscan_appropriate_flag
Boolean video_signal_type_present_flag = bv.get1BitBoolean();
if (video_signal_type_present_flag)
{
bv.skipBits(4); // video_format(3); video_full_range_flag(1)
Boolean colour_description_present_flag = bv.get1BitBoolean();
if (colour_description_present_flag)
bv.skipBits(24); // colour_primaries(8); transfer_characteristics(8);
// matrix_coefficients(8)
}
Boolean chroma_loc_info_present_flag = bv.get1BitBoolean();
if (chroma_loc_info_present_flag)
{
bv.get_expGolomb(); // chroma_sample_loc_type_top_field
bv.get_expGolomb(); // chroma_sample_loc_type_bottom_field
}
Boolean timing_info_present_flag = bv.get1BitBoolean();
if (timing_info_present_flag)
{
unsigned num_units_in_tick = bv.getBits(32);
unsigned time_scale = bv.getBits(32);
Boolean fixed_frame_rate_flag = bv.get1BitBoolean();
_framerate = (double)time_scale / (double)num_units_in_tick / 2.0;
}
}
}
char const* H265VideoRTPSink::auxSDPLine() {
// Generate a new "a=fmtp:" line each time, using our VPS, SPS and PPS (if we have them),
// otherwise parameters from our framer source (in case they've changed since the last time that
// we were called):
H264or5VideoStreamFramer* framerSource = NULL;
u_int8_t* vps = fVPS; unsigned vpsSize = fVPSSize;
u_int8_t* sps = fSPS; unsigned spsSize = fSPSSize;
u_int8_t* pps = fPPS; unsigned ppsSize = fPPSSize;
if (vps == NULL || sps == NULL || pps == NULL) {
// We need to get VPS, SPS and PPS from our framer source:
if (fOurFragmenter == NULL) return NULL; // we don't yet have a fragmenter (and therefore not a source)
framerSource = (H264or5VideoStreamFramer*)(fOurFragmenter->inputSource());
if (framerSource == NULL) return NULL; // we don't yet have a source
framerSource->getVPSandSPSandPPS(vps, vpsSize, sps, spsSize, pps, ppsSize);
if (vps == NULL || sps == NULL || pps == NULL) {
return NULL; // our source isn't ready
}
}
// Set up the "a=fmtp:" SDP line for this stream.
u_int8_t* vpsWEB = new u_int8_t[vpsSize]; // "WEB" means "Without Emulation Bytes"
unsigned vpsWEBSize = removeH264or5EmulationBytes(vpsWEB, vpsSize, vps, vpsSize);
if (vpsWEBSize < 6/*'profile_tier_level' offset*/ + 12/*num 'profile_tier_level' bytes*/) {
// Bad VPS size => assume our source isn't ready
delete[] vpsWEB;
return NULL;
}
u_int8_t const* profileTierLevelHeaderBytes = &vpsWEB[6];
unsigned profileSpace = profileTierLevelHeaderBytes[0]>>6; // general_profile_space
unsigned profileId = profileTierLevelHeaderBytes[0]&0x1F; // general_profile_idc
unsigned tierFlag = (profileTierLevelHeaderBytes[0]>>5)&0x1; // general_tier_flag
unsigned levelId = profileTierLevelHeaderBytes[11]; // general_level_idc
u_int8_t const* interop_constraints = &profileTierLevelHeaderBytes[5];
char interopConstraintsStr[100];
sprintf(interopConstraintsStr, "%02X%02X%02X%02X%02X%02X",
interop_constraints[0], interop_constraints[1], interop_constraints[2],
interop_constraints[3], interop_constraints[4], interop_constraints[5]);
delete[] vpsWEB;
char* sprop_vps = base64Encode((char*)vps, vpsSize);
char* sprop_sps = base64Encode((char*)sps, spsSize);
char* sprop_pps = base64Encode((char*)pps, ppsSize);
char const* fmtpFmt =
"a=fmtp:%d profile-space=%u"
";profile-id=%u"
";tier-flag=%u"
";level-id=%u"
";interop-constraints=%s"
";sprop-vps=%s"
";sprop-sps=%s"
";sprop-pps=%s\r\n";
unsigned fmtpFmtSize = strlen(fmtpFmt)
+ 3 /* max num chars: rtpPayloadType */ + 20 /* max num chars: profile_space */
+ 20 /* max num chars: profile_id */
+ 20 /* max num chars: tier_flag */
+ 20 /* max num chars: level_id */
+ strlen(interopConstraintsStr)
+ strlen(sprop_vps)
+ strlen(sprop_sps)
+ strlen(sprop_pps);
char* fmtp = new char[fmtpFmtSize];
sprintf(fmtp, fmtpFmt,
rtpPayloadType(), profileSpace,
profileId,
tierFlag,
levelId,
interopConstraintsStr,
sprop_vps,
sprop_sps,
sprop_pps);
delete[] sprop_vps;
delete[] sprop_sps;
delete[] sprop_pps;
delete[] fFmtpSDPLine; fFmtpSDPLine = fmtp;
return fFmtpSDPLine;
}