MPlayer container format draft 0.01


                
			Intro:

Features / goals: 
	(supported by the format, not necessary by a specific implementation)

Simple
	use the same encoding for nearly all fields
	simple decoding, so slow cpus can handle it
Extendible
	no limit for the possible values for all fields (using universal vlc)
	allow adding of new headers in the future
	allow adding more fields at the end of headers
Compact
	~0.2% overhead, for normal bitrates
	index is <10kb per hour (1 keyframe every 3sec)
Error resistant
	seeking / playback without an index
	headers & index can be repeated
	audio packet reshuffle
	checksums to allow quick redownloading of damaged parts


        
			Definitions:

MUST	the specific part must be done to conform to this standard
SHOULD	its recommanded to be done that way but its not strictly required



			Syntax:

		Type definitions:
v
	value=0
	do{
		more_data			u(1)
		data				u(7)
		value= 128*value + data
	}while(more_data)
	value-=4
 
sz (zero terminated string)
	for(i=0; next_byte != 0; i++){
		string[i]			u(8)
	}
	zero_byte				f(8)

f(x)	n fixed bits
u(x)	unsigned number encoded in x bits in MSB first order


		Bitstream syntax:
packet header
	forward ptr				v
	backward ptr				v

align_byte
	while(not byte aligned)
		one				f(1)

reserved_bytes
	for(i=0; i<forward_ptr - length_of_non_reserved; i++)
		reserved			u(8)
  
main header:
	packet header
	main_startcode				f(64)
	version					v
	stream_count				v
	file_size				v
	length_in msec				v
	reserved_bytes
	checksum				u(32)

stream_header:
	packet_header
	stream_startcode			f(64)
	stream_id				v
	stream_class				v
	fourcc					v
	average_bitrate				v
	language_code				v
	time_base_nom				v
	time_base_denom				v
	lsb_timestamp_length			v
	fixed_fps				u(1)
	codec_specific_header_flag		u(1)
	reserved				u(6)

video_stream_header:
	stream_header
	width					v
	height					v
	sample_width				v
	sample_height				v
	colorspace_type				v
	depth					v
	reserved_bytes
	checksum				u(32)

audio_stream_header:
	stream_header
	samplerate				v
	channel_count				v
	sub_packet_size				v
	shuffle_type				v
	reserved_bytes
	checksum				u(32)

codec_specific_header:
	packet_header
	codec_specific_startcode		f(64)
	stream_id				v
	codec_specific data
	checksum
 
frame
	packet header
	if(keyframe){
		keyframe_startcode		f(64)
	}
	lsb_timestamp				u(lsb_timestamp_length)
	stream_id				u(log2_stream_count)
	priority				u(2)
	checksum_flag				u(1)
	msb_timestamp_flag			u(1)
	align_byte
	if(msb_timestamp_flag)
		msb_timestamp			v
	bitstream
        if(checksum_flag)
		checksum			u(32)

Index:
	packet header
	index_startcode				f(64)
	stream_id				v
	index_length				v
	for(i=0; i<index_length; i++){
		index_timestamp			v
		index_position			v
	}
	checksum				u(32)

info_header: (optional)
	packet header
	info_startcode				f(64)
	entry_count				v
	for(i=0; i<entry_count; i++){
		name				sz
		value				sz
        }
        checksum				u(32)
        

forward_ptr
backward_ptr
	pointer to the next / previous packet
	Note: a frame with 0 bytes means that its skiped

version
	0 for now

file_size
	size in bytes, can be 0 if not meaningfull (realtime streams, ...)

length_in_msec
	length of the file in milli seconds (can be 0 if realtime or such)

stream_id
	Note: streams with a lower relative class MUST have a lower relative id
	so a stream with class 0 MUST allways have a id which is lower then any
	stream with class > 0
	streams should use low ids 

stream_class
	0	video
	32	audio
	64	subtiles
	Note the remaining values are reserved and MUST NOT be used

fourcc
	identification for the codec
	example: 'h'<<24 + '2'<<16 + '6'<<8 + '4'
        
language_code 
	something like 'u'<<24 + 's'<<16 + 'e'<<8 + 'n' (US english), can be 0
	if unknown

time_base_nom / time_base_denom = time_base
	the number of timer ticks per second, this MUST be equal to the fps
	if the fixed_fps is 1
	time_base_denom MUST not be 0
	time_base_nom and time_base_denom MUST be relative prime
	time_base_nom MUST be < 2^15
	examples:
        	fps	time_base_nom	time_base_denom
		30	30		1
		29.97	30000		1001
		23.976	24000		1001

lsb_timestamp_length
	length in bits of the lsb_timestamp
	MUST be <16

fixed_fps
	1 indicates that the fps is fixed

codec_specific_header_flag
	1 indicates that this stream has a codec specific header
        
msb_timestamp_flag
	indicates that the msb_timestamp is coded
	MUST be 1 for keyframes
        
msb_timestamp
	most significant bits of the timestamp, SHOULD be 0 for the first frame
 
lsb_timestamp
	most significant bits of the timestamp in time_base precission, with 
	lsb_timestamp_length bits 
        Example: IBBP display order
		keyframe msb_timestamp=0 lsb_timestamp=0 -> timestamp=0
		frame                    lsb_timestamp=3 -> timestamp=3
		frame                    lsb_timestamp=1 -> timestamp=1
		frame                    lsb_timestamp=2 -> timestamp=2
		...
		keyframe msb_timestamp=1 lsb_timestamp=1 -> timestamp=257
		frame msb_timestamp=0    lsb_timestamp=255->timestamp=255
		frame msb_timestamp=1    lsb_timestamp=0 -> timestamp=256
		frame                    lsb_timestamp=4 -> timestamp=260
		frame                    lsb_timestamp=2 -> timestamp=258
		frame                    lsb_timestamp=3 -> timestamp=259

width/height
	MUST be set to the coded width/height

sample_width/sample_height (aspect ratio)
	sample_width is the horizontal distance between samples
	sample_width and sample_height MUST be relative prime if not zero
	MUST be 0 if unknown
        
depth
	for compatibility with some win32 codecs

priority
	if 0 then the frame isnt used as reference (b frame) and can be droped
	MUST be > 0 for keyframes

sub_packet_size
	size of an audio packet
	Note a subpacket MUST be in exactly one packet, it cannot be split

shuffle_type
	audio is often encoded in small fixed size packets, and to increase the
	error robustness these can be shuffled
	0 -> no shuffle
	1-16 -> interleave packets by 2^n 

checksum
	crc32 checksum using the generator polynomial=0x04c11db7 (same as ogg)

checksum_flag
	indicates that the frame_checksum is coded
	must be 1 for the last non keyframe before a keyframe
        
frame_checksum
	identical to checksum, but instead of covering just the current 
	packet, it covers all frames of the same stream id since the last
	checksum
	this field is only coded if checksum_flag=1
        
index_timestamp
	value in time_base precission, relative to the last index_timestamp

index_position
	position in bytes of the first byte of the keyframe header, relative
	to the last index_position

name
	the name of the info entry, valid names are
	"Author","Description","Copyright","Encoder","Title"
	Note: if someone needs some others, please tell us about them, so we can
	      add them to the official standard (if they are sane)

value
	
        

			Structure:

the headers MUST be in exactly the following order (to simplify demuxer design)
main header
stream_header (id=0)
codec_specific_header (id=0)
stream_header (id=1)
codec_specific_header (id=1)
...
stream_header (id=n)
codec_specific_header (id=n)

headers may be repated, but if they are then they MUST all be repeated together
and repeated headers MUST be identical

headers MUST be repeated every 10sec at least ? FIXME

the info_header can be repeated, it can also contain different names & values
each time
        
        
			Sample code (GPL, & untested)

typedef BufferContext{
	uint8_t *buf;
	uint8_t *buf_ptr;
}BufferContext;

static inline uint64_t get_bytes(BufferContext *bc, int count){
	uint64_t val=0;

	assert(count>0 && count<9)
        
	for(i=0; i<count; i++){
		val <<=8;
		val += *(bc->buf_ptr++);
	}
        
	return val;
}

static inline void put_bytes(BufferContext *bc, int count, uint64_t val){
	uint64_t val=0;

	assert(count>0 && count<9)

	for(i=count-1; i>=0; i--){
		*(bc->buf_ptr++)= val >> (8*i);
	}
        
	return val;
}

static inline uint64_t get_v(BufferContext *bc){
	uint64_t val= 0;

	for(;;){
		int tmp= *(bc->buf_ptr++);
		if(tmp&0x80)
			val= (val<<7) + tmp - 0x80;
		else
			return (val<<7) + tmp - 4;
	}
}

static inline void put_v(BufferContext *bc, uint64_t val){
	int i;
	val+=4;
        
	assert(val);

	for(i=56;; i-=8){
		if(val>>i) break;
	}

	for(;i>0; i-=8){
		*(bc->buf_ptr++)= 0x80 | (val>>i);
	}
	*(bc->buf_ptr++)= val&0x7F;
}

                
			Example stream
                
main header
video_stream_header (stream 0, video    jpjp, timebase 30, lsb_timestamp_length=8)
codec_specific_header (stream 0)
video_stream_header (stream 1  subtitle usen, timebase 30, lsb_timestamp_length=8)
video_stream_header (stream 2  subtitle atde, timebase 30, lsb_timestamp_length=8)
audio_stream_header (stream 3, audio    jpjp, timebase 1 , lsb_timestamp_length=8)
audio_stream_header (stream 4, audio    usen, timebase 1 , lsb_timestamp_length=8)
index (stream 0)
keyframe (stream 0, msb_timestamp=0, lsb_timestamp=0)
keyframe (stream 1, msb_timestamp=0, lsb_timestamp=0)
keyframe (stream 2, msb_timestamp=0, lsb_timestamp=0)
keyframe (stream 3, msb_timestamp=0, lsb_timestamp=0)
keyframe (stream 4, msb_timestamp=0, lsb_timestamp=0)
frame    (stream 0,                  lsb_timestamp=1)
frame    (stream 0,                  lsb_timestamp=2)
...
frame    (stream 0,                  lsb_timestamp=30)
keyframe (stream 3, msb_timestamp=0, lsb_timestamp=1)
keyframe (stream 4, msb_timestamp=0, lsb_timestamp=1)
frame    (stream 0,                  lsb_timestamp=31)
frame    (stream 0,                  lsb_timestamp=32)
...
frame    (stream 0,                  lsb_timestamp=60)
frame    (stream 1,                  lsb_timestamp=60)
frame    (stream 2,                  lsb_timestamp=60)
keyframe (stream 3, msb_timestamp=0, lsb_timestamp=2)
keyframe (stream 4, msb_timestamp=0, lsb_timestamp=2)
frame    (stream 0,                  lsb_timestamp=61)
frame    (stream 0,                  lsb_timestamp=62)
...
main header
video_stream_header (stream 0, video    jpjp, timebase 30, lsb_timestamp_length=8)
codec_specific_header (stream 0)
video_stream_header (stream 1  subtitle usen, timebase 30, lsb_timestamp_length=8)
video_stream_header (stream 2  subtitle atde, timebase 30, lsb_timestamp_length=8)
audio_stream_header (stream 3, audio    jpjp, timebase 1 , lsb_timestamp_length=8)
audio_stream_header (stream 4, audio    usen, timebase 1 , lsb_timestamp_length=8)
frame    (stream 0,                  lsb_timestamp=255)
frame    (stream 0, msb_timestamp=1  lsb_timestamp=0)
frame    (stream 0,                  lsb_timestamp=1)
frame    (stream 0,                  lsb_timestamp=2)
frame    (stream 1, msb_timestamp=1  lsb_timestamp=2)
frame    (stream 2, msb_timestamp=1  lsb_timestamp=2)
frame    (stream 0,                  lsb_timestamp=3)
frame    (stream 0,                  lsb_timestamp=4)
...
keyframe (stream 3, msb_timestamp=0, lsb_timestamp=9)
keyframe (stream 4, msb_timestamp=0, lsb_timestamp=9)
main header
video_stream_header (stream 0, video    jpjp, timebase 30, lsb_timestamp_length=8)
codec_specific_header (stream 0)
video_stream_header (stream 1  subtitle usen, timebase 30, lsb_timestamp_length=8)
video_stream_header (stream 2  subtitle atde, timebase 30, lsb_timestamp_length=8)
audio_stream_header (stream 3, audio    jpjp, timebase 1 , lsb_timestamp_length=8)
audio_stream_header (stream 4, audio    usen, timebase 1 , lsb_timestamp_length=8)
index (stream 0)