mirror of https://git.ffmpeg.org/ffmpeg.git
171 lines
10 KiB
C
171 lines
10 KiB
C
/*
|
|
* Copyright (C) 2011-2012 Michael Niedermayer (michaelni@gmx.at)
|
|
*
|
|
* 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
|
|
*/
|
|
|
|
#ifndef SWR_INTERNAL_H
|
|
#define SWR_INTERNAL_H
|
|
|
|
#include "swresample.h"
|
|
#include "libavutil/channel_layout.h"
|
|
#include "config.h"
|
|
|
|
#define SQRT3_2 1.22474487139158904909 /* sqrt(3/2) */
|
|
|
|
#if ARCH_X86_64
|
|
typedef int64_t integer;
|
|
#else
|
|
typedef int integer;
|
|
#endif
|
|
|
|
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);
|
|
|
|
typedef struct AudioData{
|
|
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
|
|
enum AVSampleFormat fmt; ///< sample format
|
|
} AudioData;
|
|
|
|
struct SwrContext {
|
|
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
|
|
enum AVSampleFormat int_sample_fmt; ///< internal sample format (AV_SAMPLE_FMT_FLTP or AV_SAMPLE_FMT_S16P)
|
|
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
|
|
float slev; ///< surround mixing level
|
|
float clev; ///< center mixing level
|
|
float lfe_mix_level; ///< LFE mixing level
|
|
float rematrix_volume; ///< rematrixing volume coefficient
|
|
enum AVMatrixEncoding matrix_encoding; /**< matrixed stereo encoding */
|
|
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)
|
|
enum SwrEngine engine;
|
|
enum SwrDitherType dither_method;
|
|
int dither_pos;
|
|
float dither_scale;
|
|
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 */
|
|
double cutoff; /**< resampling cutoff frequency (swr: 6dB point; soxr: 0dB point). 1.0 corresponds to half the output sample rate */
|
|
enum SwrFilterType filter_type; /**< swr resampling filter type */
|
|
int kaiser_beta; /**< swr beta value for Kaiser window (only applicable if filter_type == AV_FILTER_TYPE_KAISER) */
|
|
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 */
|
|
|
|
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
|
|
|
|
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)
|
|
int rematrix_custom; ///< flag to indicate that a custom matrix has been defined
|
|
|
|
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)
|
|
AudioData dither; ///< noise used for dithering
|
|
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
|
|
int flushed; ///< 1 if data is to be flushed and no further input is expected
|
|
int64_t outpts; ///< output PTS
|
|
int drop_output; ///< number of output samples to drop
|
|
|
|
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
|
|
struct Resampler const *resampler; ///< resampler virtual function table
|
|
|
|
float matrix[SWR_CH_MAX][SWR_CH_MAX]; ///< floating point rematrixing coefficients
|
|
uint8_t *native_matrix;
|
|
uint8_t *native_one;
|
|
uint8_t *native_simd_matrix;
|
|
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
|
|
mix_1_1_func_type *mix_1_1_f;
|
|
mix_1_1_func_type *mix_1_1_simd;
|
|
|
|
mix_2_1_func_type *mix_2_1_f;
|
|
mix_2_1_func_type *mix_2_1_simd;
|
|
|
|
mix_any_func_type *mix_any_f;
|
|
|
|
/* TODO: callbacks for ASM optimizations */
|
|
};
|
|
|
|
typedef struct ResampleContext * (* resample_init_func)(struct ResampleContext *c, int out_rate, int in_rate, int filter_size, int phase_shift, int linear,
|
|
double cutoff, enum AVSampleFormat format, enum SwrFilterType filter_type, int kaiser_beta, double precision, int cheby);
|
|
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);
|
|
|
|
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;
|
|
};
|
|
|
|
extern struct Resampler const swri_resampler;
|
|
|
|
int swri_realloc_audio(AudioData *a, int count);
|
|
int swri_resample_int16(struct ResampleContext *c, int16_t *dst, const int16_t *src, int *consumed, int src_size, int dst_size, int update_ctx);
|
|
int swri_resample_int32(struct ResampleContext *c, int32_t *dst, const int32_t *src, int *consumed, int src_size, int dst_size, int update_ctx);
|
|
int swri_resample_float(struct ResampleContext *c, float *dst, const float *src, int *consumed, int src_size, int dst_size, int update_ctx);
|
|
int swri_resample_double(struct ResampleContext *c,double *dst, const double *src, int *consumed, int src_size, int dst_size, int update_ctx);
|
|
|
|
int swri_rematrix_init(SwrContext *s);
|
|
void swri_rematrix_free(SwrContext *s);
|
|
int swri_rematrix(SwrContext *s, AudioData *out, AudioData *in, int len, int mustcopy);
|
|
void swri_rematrix_init_x86(struct SwrContext *s);
|
|
|
|
void swri_get_dither(SwrContext *s, void *dst, int len, unsigned seed, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt);
|
|
|
|
void swri_audio_convert_init_arm(struct AudioConvert *ac,
|
|
enum AVSampleFormat out_fmt,
|
|
enum AVSampleFormat in_fmt,
|
|
int channels);
|
|
void swri_audio_convert_init_x86(struct AudioConvert *ac,
|
|
enum AVSampleFormat out_fmt,
|
|
enum AVSampleFormat in_fmt,
|
|
int channels);
|
|
#endif
|