b5875b91 |
/* |
ba1314c2 |
* Copyright (C) 2011-2013 Michael Niedermayer (michaelni@gmx.at) |
b5875b91 |
*
* This file is part of libswresample
*
* libswresample is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* libswresample is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with libswresample; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
|
180f9a09 |
#ifndef SWRESAMPLE_SWRESAMPLE_INTERNAL_H
#define SWRESAMPLE_SWRESAMPLE_INTERNAL_H |
b5875b91 |
#include "swresample.h" |
1acd2f6b |
#include "libavutil/channel_layout.h" |
d23e8f53 |
#include "config.h" |
c5278cb8 |
|
a77401e1 |
#define SWR_CH_MAX 64 |
97f8c7a0 |
|
c5278cb8 |
#define SQRT3_2 1.22474487139158904909 /* sqrt(3/2) */ |
b5875b91 |
|
82742294 |
#define NS_TAPS 20
|
d23e8f53 |
#if ARCH_X86_64
typedef int64_t integer;
#else
typedef int integer;
#endif |
aab5a452 |
|
d23e8f53 |
typedef void (mix_1_1_func_type)(void *out, const void *in, void *coeffp, integer index, integer len);
typedef void (mix_2_1_func_type)(void *out, const void *in1, const void *in2, void *coeffp, integer index1, integer index2, integer len);
typedef void (mix_any_func_type)(uint8_t **out, const uint8_t **in1, void *coeffp, integer len); |
ca30ae12 |
|
b5875b91 |
typedef struct AudioData{ |
4c0bad51 |
uint8_t *ch[SWR_CH_MAX]; ///< samples buffer per channel
uint8_t *data; ///< samples buffer
int ch_count; ///< number of channels
int bps; ///< bytes per sample
int count; ///< number of samples
int planar; ///< 1 if planar audio, 0 otherwise |
106789df |
enum AVSampleFormat fmt; ///< sample format |
b5875b91 |
} AudioData;
|
3ab19706 |
struct DitherContext { |
9d7ae727 |
int method; |
fca51256 |
int noise_pos; |
3ab19706 |
float scale; |
ead3a2a3 |
float noise_scale; ///< Noise scale |
3ab19706 |
int ns_taps; ///< Noise shaping dither taps
float ns_scale; ///< Noise shaping dither scale
float ns_scale_1; ///< Noise shaping dither scale^-1
int ns_pos; ///< Noise shaping dither position
float ns_coeffs[NS_TAPS]; ///< Noise shaping filter coefficients
float ns_errors[SWR_CH_MAX][2*NS_TAPS];
AudioData noise; ///< noise used for dithering |
39a6e02f |
AudioData temp; ///< temporary storage when writing into the input buffer isn't possible |
8b3affda |
int output_sample_bits; ///< the number of used output bits, needed to scale dither correctly |
3ab19706 |
};
|
6efd0ba9 |
typedef struct ResampleContext * (* resample_init_func)(struct ResampleContext *c, int out_rate, int in_rate, int filter_size, int phase_shift, int linear, |
b8c6e5a6 |
double cutoff, enum AVSampleFormat format, enum SwrFilterType filter_type, double kaiser_beta, double precision, int cheby, int exact_rational); |
6efd0ba9 |
typedef void (* resample_free_func)(struct ResampleContext **c);
typedef int (* multiple_resample_func)(struct ResampleContext *c, AudioData *dst, int dst_size, AudioData *src, int src_size, int *consumed);
typedef int (* resample_flush_func)(struct SwrContext *c);
typedef int (* set_compensation_func)(struct ResampleContext *c, int sample_delta, int compensation_distance);
typedef int64_t (* get_delay_func)(struct SwrContext *s, int64_t base);
typedef int (* invert_initial_buffer_func)(struct ResampleContext *c, AudioData *dst, const AudioData *src, int src_size, int *dst_idx, int *dst_count); |
cc17b43d |
typedef int64_t (* get_out_samples_func)(struct SwrContext *s, int in_samples); |
6efd0ba9 |
struct Resampler {
resample_init_func init;
resample_free_func free;
multiple_resample_func multiple_resample;
resample_flush_func flush;
set_compensation_func set_compensation;
get_delay_func get_delay;
invert_initial_buffer_func invert_initial_buffer; |
cc17b43d |
get_out_samples_func get_out_samples; |
6efd0ba9 |
};
extern struct Resampler const swri_resampler; |
4d00860a |
extern struct Resampler const swri_soxr_resampler; |
6efd0ba9 |
|
ac6798db |
struct SwrContext { |
4c0bad51 |
const AVClass *av_class; ///< AVClass used for AVOption and av_log()
int log_level_offset; ///< logging level offset
void *log_ctx; ///< parent logging context
enum AVSampleFormat in_sample_fmt; ///< input sample format |
edbde522 |
enum AVSampleFormat int_sample_fmt; ///< internal sample format (AV_SAMPLE_FMT_FLTP or AV_SAMPLE_FMT_S16P) |
4c0bad51 |
enum AVSampleFormat out_sample_fmt; ///< output sample format
int64_t in_ch_layout; ///< input channel layout
int64_t out_ch_layout; ///< output channel layout
int in_sample_rate; ///< input sample rate
int out_sample_rate; ///< output sample rate
int flags; ///< miscellaneous flags such as SWR_FLAG_RESAMPLE |
f03afd5d |
float slev; ///< surround mixing level |
4c0bad51 |
float clev; ///< center mixing level |
6d5bf67f |
float lfe_mix_level; ///< LFE mixing level |
4c0bad51 |
float rematrix_volume; ///< rematrixing volume coefficient |
e2b71846 |
float rematrix_maxval; ///< maximum value for rematrixing output |
9d7ae727 |
int matrix_encoding; /**< matrixed stereo encoding */ |
4c0bad51 |
const int *channel_map; ///< channel index (or -1 if muted channel) map
int used_ch_count; ///< number of used input channels (mapped channel count if channel_map, otherwise in.ch_count) |
9d7ae727 |
int engine; |
3ab19706 |
|
d7b9cb2f |
int user_in_ch_count; ///< User set input channel count
int user_out_ch_count; ///< User set output channel count
int user_used_ch_count; ///< User set used channel count |
80a28c75 |
int64_t user_in_ch_layout; ///< User set input channel layout
int64_t user_out_ch_layout; ///< User set output channel layout |
d4325b2f |
enum AVSampleFormat user_int_sample_fmt; ///< User set internal sample format |
30b2611e |
int user_dither_method; ///< User set dither method |
d7b9cb2f |
|
3ab19706 |
struct DitherContext dither; |
82742294 |
|
da958795 |
int filter_size; /**< length of each FIR filter in the resampling filterbank relative to the cutoff frequency */
int phase_shift; /**< log2 of the number of entries in the resampling polyphase filterbank */
int linear_interp; /**< if 1 then the resampling FIR filter will be linearly interpolated */ |
b8c6e5a6 |
int exact_rational; /**< if 1 then enable non power of 2 phase_count */ |
8d9a5033 |
double cutoff; /**< resampling cutoff frequency (swr: 6dB point; soxr: 0dB point). 1.0 corresponds to half the output sample rate */ |
9d7ae727 |
int filter_type; /**< swr resampling filter type */ |
1bed09a3 |
double kaiser_beta; /**< swr beta value for Kaiser window (only applicable if filter_type == AV_FILTER_TYPE_KAISER) */ |
8d9a5033 |
double precision; /**< soxr resampling precision (in bits) */
int cheby; /**< soxr: if 1 then passband rolloff will be none (Chebyshev) & irrational ratio approximation precision will be higher */ |
b5875b91 |
|
8d9a5033 |
float min_compensation; ///< swr minimum below which no compensation will happen
float min_hard_compensation; ///< swr minimum below which no silence inject / sample drop will happen
float soft_compensation_duration; ///< swr duration over which soft compensation is applied
float max_soft_compensation; ///< swr maximum soft compensation in seconds over soft_compensation_duration
float async; ///< swr simple 1 parameter async, similar to ffmpegs -async |
00cae867 |
int64_t firstpts_in_samples; ///< swr first pts in samples |
72a242c9 |
|
4c0bad51 |
int resample_first; ///< 1 if resampling must come first, 0 if rematrixing
int rematrix; ///< flag to indicate if rematrixing is needed (basically if input and output layouts mismatch) |
560b224f |
int rematrix_custom; ///< flag to indicate that a custom matrix has been defined |
b5875b91 |
|
4c0bad51 |
AudioData in; ///< input audio data
AudioData postin; ///< post-input audio data: used for rematrix/resample
AudioData midbuf; ///< intermediate audio data (postin/preout)
AudioData preout; ///< pre-output audio data: used for rematrix/resample
AudioData out; ///< converted output audio data
AudioData in_buffer; ///< cached audio data (convert and resample purpose) |
db4e0eca |
AudioData silence; ///< temporary with silence |
dc658842 |
AudioData drop_temp; ///< temporary used to discard output |
4c0bad51 |
int in_buffer_index; ///< cached buffer position
int in_buffer_count; ///< cached buffer length
int resample_in_constraint; ///< 1 if the input end was reach before the output end, 0 otherwise |
4f16153d |
int flushed; ///< 1 if data is to be flushed and no further input is expected |
72a242c9 |
int64_t outpts; ///< output PTS |
00cae867 |
int64_t firstpts; ///< first PTS |
f88f705a |
int drop_output; ///< number of output samples to drop |
c70c6be2 |
double delayed_samples_fixup; ///< soxr 0.1.1: needed to fixup delayed_samples after flush has been called. |
b5875b91 |
|
4c0bad51 |
struct AudioConvert *in_convert; ///< input conversion context
struct AudioConvert *out_convert; ///< output conversion context
struct AudioConvert *full_convert; ///< full conversion context (single conversion for input and output)
struct ResampleContext *resample; ///< resampling context |
5a5d7074 |
struct Resampler const *resampler; ///< resampler virtual function table |
b5875b91 |
|
740f5105 |
double matrix[SWR_CH_MAX][SWR_CH_MAX]; ///< floating point rematrixing coefficients
float matrix_flt[SWR_CH_MAX][SWR_CH_MAX]; ///< single precision floating point rematrixing coefficients |
00fea26f |
uint8_t *native_matrix;
uint8_t *native_one; |
4cfc9208 |
uint8_t *native_simd_one; |
48a45f81 |
uint8_t *native_simd_matrix; |
4fef94c6 |
int32_t matrix32[SWR_CH_MAX][SWR_CH_MAX]; ///< 17.15 fixed point rematrixing coefficients
uint8_t matrix_ch[SWR_CH_MAX][SWR_CH_MAX+1]; ///< Lists of input channels per output channel that have non zero rematrixing coefficients |
aab5a452 |
mix_1_1_func_type *mix_1_1_f; |
9abbbf75 |
mix_1_1_func_type *mix_1_1_simd;
|
aab5a452 |
mix_2_1_func_type *mix_2_1_f; |
9abbbf75 |
mix_2_1_func_type *mix_2_1_simd; |
b5875b91 |
|
ca30ae12 |
mix_any_func_type *mix_any_f;
|
4c0bad51 |
/* TODO: callbacks for ASM optimizations */ |
ac6798db |
}; |
b5875b91 |
|
ef62f573 |
av_warn_unused_result |
431dcc49 |
int swri_realloc_audio(AudioData *a, int count); |
b5875b91 |
|
2eec9812 |
void swri_noise_shaping_int16 (SwrContext *s, AudioData *dsts, const AudioData *srcs, const AudioData *noises, int count);
void swri_noise_shaping_int32 (SwrContext *s, AudioData *dsts, const AudioData *srcs, const AudioData *noises, int count);
void swri_noise_shaping_float (SwrContext *s, AudioData *dsts, const AudioData *srcs, const AudioData *noises, int count);
void swri_noise_shaping_double(SwrContext *s, AudioData *dsts, const AudioData *srcs, const AudioData *noises, int count); |
82742294 |
|
ef62f573 |
av_warn_unused_result |
c4deb90c |
int swri_rematrix_init(SwrContext *s); |
00fea26f |
void swri_rematrix_free(SwrContext *s); |
c4deb90c |
int swri_rematrix(SwrContext *s, AudioData *out, AudioData *in, int len, int mustcopy); |
b74ecb82 |
int swri_rematrix_init_x86(struct SwrContext *s); |
db2eadb2 |
|
ef62f573 |
av_warn_unused_result |
196b885a |
int swri_get_dither(SwrContext *s, void *dst, int len, unsigned seed, enum AVSampleFormat noise_fmt); |
ef62f573 |
av_warn_unused_result |
3ef06f34 |
int swri_dither_init(SwrContext *s, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt); |
4c0bad51 |
|
7c51f5bd |
void swri_audio_convert_init_aarch64(struct AudioConvert *ac,
enum AVSampleFormat out_fmt,
enum AVSampleFormat in_fmt,
int channels); |
0eebde07 |
void swri_audio_convert_init_arm(struct AudioConvert *ac,
enum AVSampleFormat out_fmt,
enum AVSampleFormat in_fmt,
int channels); |
bcc66ff0 |
void swri_audio_convert_init_x86(struct AudioConvert *ac,
enum AVSampleFormat out_fmt,
enum AVSampleFormat in_fmt,
int channels); |
4d00860a |
|
b5875b91 |
#endif |