wmaprodec.c File Reference

wmapro decoder implementation Wmapro is an MDCT based codec comparable to wma standard or AAC. More...

#include <inttypes.h>
#include "libavutil/ffmath.h"
#include "libavutil/float_dsp.h"
#include "libavutil/intfloat.h"
#include "libavutil/intreadwrite.h"
#include "avcodec.h"
#include "internal.h"
#include "get_bits.h"
#include "put_bits.h"
#include "wmaprodata.h"
#include "sinewin.h"
#include "wma.h"
#include "wma_common.h"

Classes
struct	WMAProChannelCtx
	frame specific decoder context for a single channel More...
struct	WMAProChannelGrp
	channel group for channel transformations More...
struct	WMAProDecodeCtx
	main decoder context More...
struct	XMADecodeCtx

Macros
#define	WMAPRO_MAX_CHANNELS   8
	current decoder limitations More...
#define	MAX_SUBFRAMES   32
	max number of subframes per channel
#define	MAX_BANDS   29
	max number of scale factor bands
#define	MAX_FRAMESIZE   32768
	maximum compressed frame size
#define	XMA_MAX_STREAMS   8
#define	XMA_MAX_CHANNELS_STREAM   2
#define	XMA_MAX_CHANNELS   (XMA_MAX_STREAMS * XMA_MAX_CHANNELS_STREAM)
#define	WMAPRO_BLOCK_MIN_BITS   6
	log2 of min block size
#define	WMAPRO_BLOCK_MAX_BITS   13
	log2 of max block size
#define	WMAPRO_BLOCK_MIN_SIZE   (1 << WMAPRO_BLOCK_MIN_BITS)
	minimum block size
#define	WMAPRO_BLOCK_MAX_SIZE   (1 << WMAPRO_BLOCK_MAX_BITS)
	maximum block size
#define	WMAPRO_BLOCK_SIZES   (WMAPRO_BLOCK_MAX_BITS - WMAPRO_BLOCK_MIN_BITS + 1)
	possible block sizes
#define	VLCBITS   9
#define	SCALEVLCBITS   8
#define	VEC4MAXDEPTH   ((HUFF_VEC4_MAXBITS+VLCBITS-1)/VLCBITS)
#define	VEC2MAXDEPTH   ((HUFF_VEC2_MAXBITS+VLCBITS-1)/VLCBITS)
#define	VEC1MAXDEPTH   ((HUFF_VEC1_MAXBITS+VLCBITS-1)/VLCBITS)
#define	SCALEMAXDEPTH   ((HUFF_SCALE_MAXBITS+SCALEVLCBITS-1)/SCALEVLCBITS)
#define	SCALERLMAXDEPTH   ((HUFF_SCALE_RL_MAXBITS+VLCBITS-1)/VLCBITS)
#define	PRINT(a, b)   av_log(s->avctx, AV_LOG_DEBUG, " %s = %d\n", a, b);
#define	PRINT_HEX(a, b)   av_log(s->avctx, AV_LOG_DEBUG, " %s = %"PRIx32"\n", a, b);

Typedefs
typedef struct WMAProChannelCtx	WMAProChannelCtx
	frame specific decoder context for a single channel
typedef struct WMAProChannelGrp	WMAProChannelGrp
	channel group for channel transformations
typedef struct WMAProDecodeCtx	WMAProDecodeCtx
	main decoder context
typedef struct XMADecodeCtx	XMADecodeCtx

Variables
AVCodec	ff_wmapro_decoder
	wmapro decoder More...
AVCodec	ff_xma1_decoder
AVCodec	ff_xma2_decoder

Detailed Description

wmapro decoder implementation Wmapro is an MDCT based codec comparable to wma standard or AAC.

The decoding therefore consists of the following steps:

• bitstream decoding
• reconstruction of per-channel data
• rescaling and inverse quantization
• IMDCT
• windowing and overlapp-add

The compressed wmapro bitstream is split into individual packets. Every such packet contains one or more wma frames. The compressed frames may have a variable length and frames may cross packet boundaries. Common to all wmapro frames is the number of samples that are stored in a frame. The number of samples and a few other decode flags are stored as extradata that has to be passed to the decoder.

The wmapro frames themselves are again split into a variable number of subframes. Every subframe contains the data for 2^N time domain samples where N varies between 7 and 12.

Example wmapro bitstream (in samples):

|| packet 0 || packet 1 || packet 2 packets

|| frame 0 || frame 1 || frame 2 || frames

|| | | || | | | || || subframes of channel 0

|| | | || | | | || || subframes of channel 1

The frame layouts for the individual channels of a wma frame does not need to be the same.

However, if the offsets and lengths of several subframes of a frame are the same, the subframes of the channels can be grouped. Every group may then use special coding techniques like M/S stereo coding to improve the compression ratio. These channel transformations do not need to be applied to a whole subframe. Instead, they can also work on individual scale factor bands (see below). The coefficients that carry the audio signal in the frequency domain are transmitted as huffman-coded vectors with 4, 2 and 1 elements. In addition to that, the encoder can switch to a runlevel coding scheme by transmitting subframe_length / 128 zero coefficients.

Before the audio signal can be converted to the time domain, the coefficients have to be rescaled and inverse quantized. A subframe is therefore split into several scale factor bands that get scaled individually. Scale factors are submitted for every frame but they might be shared between the subframes of a channel. Scale factors are initially DPCM-coded. Once scale factors are shared, the differences are transmitted as runlevel codes. Every subframe length and offset combination in the frame layout shares a common quantization factor that can be adjusted for every channel by a modifier. After the inverse quantization, the coefficients get processed by an IMDCT. The resulting values are then windowed with a sine window and the first half of the values are added to the second half of the output from the previous subframe in order to reconstruct the output samples.

Macro Definition Documentation

WMAPRO_MAX_CHANNELS

#define WMAPRO_MAX_CHANNELS   8

current decoder limitations

max number of handled channels

Variable Documentation

ff_wmapro_decoder

AVCodec ff_wmapro_decoder

Initial value:

= {
    .name           = "wmapro",
    .long_name      = NULL_IF_CONFIG_SMALL("Windows Media Audio 9 Professional"),
    .type           = AVMEDIA_TYPE_AUDIO,
    .id             = AV_CODEC_ID_WMAPRO,
    .priv_data_size = sizeof(WMAProDecodeCtx),
    .init           = wmapro_decode_init,
    .close          = wmapro_decode_end,
    .decode         = wmapro_decode_packet,
    .capabilities   = AV_CODEC_CAP_SUBFRAMES | AV_CODEC_CAP_DR1,
    .flush          = wmapro_flush,
    .sample_fmts    = (const enum AVSampleFormat[]) { AV_SAMPLE_FMT_FLTP,
                                                      AV_SAMPLE_FMT_NONE },
}

wmapro decoder

ff_xma1_decoder

AVCodec ff_xma1_decoder

Initial value:

= {
    .name           = "xma1",
    .long_name      = NULL_IF_CONFIG_SMALL("Xbox Media Audio 1"),
    .type           = AVMEDIA_TYPE_AUDIO,
    .id             = AV_CODEC_ID_XMA1,
    .priv_data_size = sizeof(XMADecodeCtx),
    .init           = xma_decode_init,
    .close          = xma_decode_end,
    .decode         = xma_decode_packet,
    .capabilities   = AV_CODEC_CAP_SUBFRAMES | AV_CODEC_CAP_DR1,
    .sample_fmts    = (const enum AVSampleFormat[]) { AV_SAMPLE_FMT_FLTP,
                                                      AV_SAMPLE_FMT_NONE },
}

ff_xma2_decoder

AVCodec ff_xma2_decoder

Initial value:

= {
    .name           = "xma2",
    .long_name      = NULL_IF_CONFIG_SMALL("Xbox Media Audio 2"),
    .type           = AVMEDIA_TYPE_AUDIO,
    .id             = AV_CODEC_ID_XMA2,
    .priv_data_size = sizeof(XMADecodeCtx),
    .init           = xma_decode_init,
    .close          = xma_decode_end,
    .decode         = xma_decode_packet,
    .flush          = xma_flush,
    .capabilities   = AV_CODEC_CAP_SUBFRAMES | AV_CODEC_CAP_DR1,
    .sample_fmts    = (const enum AVSampleFormat[]) { AV_SAMPLE_FMT_FLTP,
                                                      AV_SAMPLE_FMT_NONE },
}