ffmpeg/libswresample/swresample.h

470 lines
16 KiB
C
Raw Normal View History

/*
* Copyright (C) 2011-2013 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 SWRESAMPLE_SWRESAMPLE_H
#define SWRESAMPLE_SWRESAMPLE_H
2011-11-17 10:20:29 +00:00
/**
* @file
* @ingroup lswr
2011-11-17 10:20:29 +00:00
* libswresample public header
*/
/**
* @defgroup lswr Libswresample
* @{
*
* Libswresample (lswr) is a library that handles audio resampling, sample
* format conversion and mixing.
*
* Interaction with lswr is done through SwrContext, which is
* allocated with swr_alloc() or swr_alloc_set_opts(). It is opaque, so all parameters
* must be set with the @ref avoptions API.
*
* The first thing you will need to do in order to use lswr is to allocate
* SwrContext. This can be done with swr_alloc() or swr_alloc_set_opts(). If you
* are using the former, you must set options through the @ref avoptions API.
* The latter function provides the same feature, but it allows you to set some
* common options in the same statement.
*
* For example the following code will setup conversion from planar float sample
* format to interleaved signed 16-bit integer, downsampling from 48kHz to
* 44.1kHz and downmixing from 5.1 channels to stereo (using the default mixing
* matrix). This is using the swr_alloc() function.
* @code
* SwrContext *swr = swr_alloc();
* av_opt_set_channel_layout(swr, "in_channel_layout", AV_CH_LAYOUT_5POINT1, 0);
* av_opt_set_channel_layout(swr, "out_channel_layout", AV_CH_LAYOUT_STEREO, 0);
* av_opt_set_int(swr, "in_sample_rate", 48000, 0);
* av_opt_set_int(swr, "out_sample_rate", 44100, 0);
* av_opt_set_sample_fmt(swr, "in_sample_fmt", AV_SAMPLE_FMT_FLTP, 0);
* av_opt_set_sample_fmt(swr, "out_sample_fmt", AV_SAMPLE_FMT_S16, 0);
* @endcode
*
* The same job can be done using swr_alloc_set_opts() as well:
* @code
* SwrContext *swr = swr_alloc_set_opts(NULL, // we're allocating a new context
* AV_CH_LAYOUT_STEREO, // out_ch_layout
* AV_SAMPLE_FMT_S16, // out_sample_fmt
* 44100, // out_sample_rate
* AV_CH_LAYOUT_5POINT1, // in_ch_layout
* AV_SAMPLE_FMT_FLTP, // in_sample_fmt
* 48000, // in_sample_rate
* 0, // log_offset
* NULL); // log_ctx
* @endcode
*
* Once all values have been set, it must be initialized with swr_init(). If
* you need to change the conversion parameters, you can change the parameters
* using @ref AVOptions, as described above in the first example; or by using
* swr_alloc_set_opts(), but with the first argument the allocated context.
* You must then call swr_init() again.
*
* The conversion itself is done by repeatedly calling swr_convert().
* Note that the samples may get buffered in swr if you provide insufficient
* output space or if sample rate conversion is done, which requires "future"
* samples. Samples that do not require future input can be retrieved at any
* time by using swr_convert() (in_count can be set to 0).
* At the end of conversion the resampling buffer can be flushed by calling
* swr_convert() with NULL in and 0 in_count.
*
* The samples used in the conversion process can be managed with the libavutil
* @ref lavu_sampmanip "samples manipulation" API, including av_samples_alloc()
* function used in the following example.
*
* The delay between input and output, can at any time be found by using
* swr_get_delay().
*
* The following code demonstrates the conversion loop assuming the parameters
* from above and caller-defined functions get_input() and handle_output():
* @code
* uint8_t **input;
* int in_samples;
*
* while (get_input(&input, &in_samples)) {
* uint8_t *output;
* int out_samples = av_rescale_rnd(swr_get_delay(swr, 48000) +
* in_samples, 44100, 48000, AV_ROUND_UP);
* av_samples_alloc(&output, NULL, 2, out_samples,
* AV_SAMPLE_FMT_S16, 0);
* out_samples = swr_convert(swr, &output, out_samples,
* input, in_samples);
* handle_output(output, out_samples);
* av_freep(&output);
2013-09-29 21:37:46 +00:00
* }
* @endcode
*
* When the conversion is finished, the conversion
* context and everything associated with it must be freed with swr_free().
* A swr_close() function is also available, but it exists mainly for
* compatibility with libavresample, and is not required to be called.
*
* There will be no memory leak if the data is not completely flushed before
* swr_free().
*/
#include <stdint.h>
#include "libavutil/samplefmt.h"
#include "libswresample/version.h"
#if LIBSWRESAMPLE_VERSION_MAJOR < 1
#define SWR_CH_MAX 32 ///< Maximum number of channels
#endif
/**
* @name Option constants
* These constants are used for the @ref avoptions interface for lswr.
* @{
*
*/
2011-11-17 10:20:29 +00:00
#define SWR_FLAG_RESAMPLE 1 ///< Force resampling even if equal sample rate
//TODO use int resample ?
//long term TODO can we enable this dynamically?
/** Dithering algorithms */
enum SwrDitherType {
SWR_DITHER_NONE = 0,
SWR_DITHER_RECTANGULAR,
SWR_DITHER_TRIANGULAR,
SWR_DITHER_TRIANGULAR_HIGHPASS,
SWR_DITHER_NS = 64, ///< not part of API/ABI
SWR_DITHER_NS_LIPSHITZ,
SWR_DITHER_NS_F_WEIGHTED,
SWR_DITHER_NS_MODIFIED_E_WEIGHTED,
SWR_DITHER_NS_IMPROVED_E_WEIGHTED,
SWR_DITHER_NS_SHIBATA,
SWR_DITHER_NS_LOW_SHIBATA,
SWR_DITHER_NS_HIGH_SHIBATA,
SWR_DITHER_NB, ///< not part of API/ABI
};
/** Resampling Engines */
enum SwrEngine {
SWR_ENGINE_SWR, /**< SW Resampler */
SWR_ENGINE_SOXR, /**< SoX Resampler */
SWR_ENGINE_NB, ///< not part of API/ABI
};
/** Resampling Filter Types */
enum SwrFilterType {
SWR_FILTER_TYPE_CUBIC, /**< Cubic */
SWR_FILTER_TYPE_BLACKMAN_NUTTALL, /**< Blackman Nuttall Windowed Sinc */
SWR_FILTER_TYPE_KAISER, /**< Kaiser Windowed Sinc */
};
/**
* @}
*/
/**
* The libswresample context. Unlike libavcodec and libavformat, this structure
* is opaque. This means that if you would like to set options, you must use
* the @ref avoptions API and cannot directly set values to members of the
* structure.
*/
typedef struct SwrContext SwrContext;
/**
* Get the AVClass for SwrContext. It can be used in combination with
* AV_OPT_SEARCH_FAKE_OBJ for examining options.
*
* @see av_opt_find().
* @return the AVClass of SwrContext
*/
const AVClass *swr_get_class(void);
/**
* @name SwrContext constructor functions
* @{
*/
/**
* Allocate SwrContext.
2011-11-17 10:20:29 +00:00
*
* If you use this function you will need to set the parameters (manually or
* with swr_alloc_set_opts()) before calling swr_init().
*
* @see swr_alloc_set_opts(), swr_init(), swr_free()
* @return NULL on error, allocated context otherwise
*/
struct SwrContext *swr_alloc(void);
/**
* Initialize context after user parameters have been set.
2011-11-17 10:20:29 +00:00
*
* @param[in,out] s Swr context to initialize
2011-11-17 10:20:29 +00:00
* @return AVERROR error code in case of failure.
*/
int swr_init(struct SwrContext *s);
/**
* Check whether an swr context has been initialized or not.
*
* @param[in] s Swr context to check
* @see swr_init()
* @return positive if it has been initialized, 0 if not initialized
*/
int swr_is_initialized(struct SwrContext *s);
/**
2011-11-17 10:20:29 +00:00
* Allocate SwrContext if needed and set/reset common parameters.
*
* This function does not require s to be allocated with swr_alloc(). On the
* other hand, swr_alloc() can use swr_alloc_set_opts() to set the parameters
* on the allocated context.
*
* @param s existing Swr context if available, or NULL if not
2011-11-17 10:20:29 +00:00
* @param out_ch_layout output channel layout (AV_CH_LAYOUT_*)
2011-11-24 03:30:32 +00:00
* @param out_sample_fmt output sample format (AV_SAMPLE_FMT_*).
2011-11-17 10:20:29 +00:00
* @param out_sample_rate output sample rate (frequency in Hz)
* @param in_ch_layout input channel layout (AV_CH_LAYOUT_*)
2011-11-24 03:30:32 +00:00
* @param in_sample_fmt input sample format (AV_SAMPLE_FMT_*).
2011-11-17 10:20:29 +00:00
* @param in_sample_rate input sample rate (frequency in Hz)
* @param log_offset logging level offset
* @param log_ctx parent logging context, can be NULL
*
* @see swr_init(), swr_free()
* @return NULL on error, allocated context otherwise
*/
struct SwrContext *swr_alloc_set_opts(struct SwrContext *s,
int64_t out_ch_layout, enum AVSampleFormat out_sample_fmt, int out_sample_rate,
int64_t in_ch_layout, enum AVSampleFormat in_sample_fmt, int in_sample_rate,
int log_offset, void *log_ctx);
/**
* @}
*
* @name SwrContext destructor functions
* @{
*/
/**
2011-11-17 10:20:29 +00:00
* Free the given SwrContext and set the pointer to NULL.
*
* @param[in] s a pointer to a pointer to Swr context
*/
void swr_free(struct SwrContext **s);
/**
* Closes the context so that swr_is_initialized() returns 0.
*
* The context can be brought back to life by running swr_init(),
* swr_init() can also be used without swr_close().
* This function is mainly provided for simplifying the usecase
* where one tries to support libavresample and libswresample.
*
* @param[in,out] s Swr context to be closed
*/
void swr_close(struct SwrContext *s);
/**
* @}
*
* @name Core conversion functions
* @{
*/
/** Convert audio.
*
2011-11-17 10:20:29 +00:00
* in and in_count can be set to 0 to flush the last few samples out at the
* end.
*
* If more input is provided than output space then the input will be buffered.
* You can avoid this buffering by providing more output space than input.
* Conversion will run directly without copying whenever possible.
*
2011-11-17 10:20:29 +00:00
* @param s allocated Swr context, with parameters set
* @param out output buffers, only the first one need be set in case of packed audio
* @param out_count amount of space available for output in samples per channel
* @param in input buffers, only the first one need to be set in case of packed audio
* @param in_count number of input samples available in one channel
*
2012-02-27 18:01:53 +00:00
* @return number of samples output per channel, negative value on error
*/
int swr_convert(struct SwrContext *s, uint8_t **out, int out_count,
const uint8_t **in , int in_count);
/**
* Convert the next timestamp from input to output
* timestamps are in 1/(in_sample_rate * out_sample_rate) units.
*
* @note There are 2 slightly differently behaving modes.
* @li When automatic timestamp compensation is not used, (min_compensation >= FLT_MAX)
* in this case timestamps will be passed through with delays compensated
* @li When automatic timestamp compensation is used, (min_compensation < FLT_MAX)
* in this case the output timestamps will match output sample numbers.
* See ffmpeg-resampler(1) for the two modes of compensation.
*
* @param s[in] initialized Swr context
* @param pts[in] timestamp for the next input sample, INT64_MIN if unknown
* @see swr_set_compensation(), swr_drop_output(), and swr_inject_silence() are
* function used internally for timestamp compensation.
* @return the output timestamp for the next output sample
*/
int64_t swr_next_pts(struct SwrContext *s, int64_t pts);
/**
* @}
*
* @name Low-level option setting functions
* These functons provide a means to set low-level options that is not possible
* with the AVOption API.
* @{
*/
2011-11-17 10:20:29 +00:00
/**
* Activate resampling compensation ("soft" compensation). This function is
* internally called when needed in swr_next_pts().
*
* @param[in,out] s allocated Swr context. If it is not initialized,
* or SWR_FLAG_RESAMPLE is not set, swr_init() is
* called with the flag set.
* @param[in] sample_delta delta in PTS per sample
* @param[in] compensation_distance number of samples to compensate for
* @return >= 0 on success, AVERROR error codes if:
* @li @c s is NULL,
* @li @c compensation_distance is less than 0,
* @li @c compensation_distance is 0 but sample_delta is not,
* @li compensation unsupported by resampler, or
* @li swr_init() fails when called.
2011-11-17 10:20:29 +00:00
*/
int swr_set_compensation(struct SwrContext *s, int sample_delta, int compensation_distance);
/**
* Set a customized input channel mapping.
*
* @param[in,out] s allocated Swr context, not yet initialized
* @param[in] channel_map customized input channel mapping (array of channel
* indexes, -1 for a muted channel)
* @return >= 0 on success, or AVERROR error code in case of failure.
*/
int swr_set_channel_mapping(struct SwrContext *s, const int *channel_map);
2012-02-16 10:26:32 +00:00
/**
* Set a customized remix matrix.
*
* @param s allocated Swr context, not yet initialized
* @param matrix remix coefficients; matrix[i + stride * o] is
* the weight of input channel i in output channel o
* @param stride offset between lines of the matrix
* @return >= 0 on success, or AVERROR error code in case of failure.
2012-02-16 10:26:32 +00:00
*/
int swr_set_matrix(struct SwrContext *s, const double *matrix, int stride);
/**
* @}
*
* @name Sample handling functions
* @{
*/
/**
* Drops the specified number of output samples.
*
* This function, along with swr_inject_silence(), is called by swr_next_pts()
* if needed for "hard" compensation.
*
* @param s allocated Swr context
* @param count number of samples to be dropped
*
* @return >= 0 on success, or a negative AVERROR code on failure
*/
int swr_drop_output(struct SwrContext *s, int count);
/**
* Injects the specified number of silence samples.
*
* This function, along with swr_drop_output(), is called by swr_next_pts()
* if needed for "hard" compensation.
*
* @param s allocated Swr context
* @param count number of samples to be dropped
*
* @return >= 0 on success, or a negative AVERROR code on failure
*/
int swr_inject_silence(struct SwrContext *s, int count);
/**
* Gets the delay the next input sample will experience relative to the next output sample.
*
* Swresample can buffer data if more input has been provided than available
* output space, also converting between sample rates needs a delay.
* This function returns the sum of all such delays.
* The exact delay is not necessarily an integer value in either input or
* output sample rate. Especially when downsampling by a large value, the
* output sample rate may be a poor choice to represent the delay, similarly
* for upsampling and the input sample rate.
*
* @param s swr context
* @param base timebase in which the returned delay will be:
* @li if it's set to 1 the returned delay is in seconds
* @li if it's set to 1000 the returned delay is in milliseconds
* @li if it's set to the input sample rate then the returned
* delay is in input samples
* @li if it's set to the output sample rate then the returned
* delay is in output samples
* @li if it's the least common multiple of in_sample_rate and
* out_sample_rate then an exact rounding-free delay will be
* returned
* @returns the delay in 1 / @c base units.
*/
int64_t swr_get_delay(struct SwrContext *s, int64_t base);
/**
* @}
*
* @name Configuration accessors
* @{
*/
/**
* Return the @ref LIBSWRESAMPLE_VERSION_INT constant.
*
* This is useful to check if the build-time libswresample has the same version
* as the run-time one.
*
* @returns the unsigned int-typed version
*/
unsigned swresample_version(void);
/**
* Return the swr build-time configuration.
*
* @returns the build-time @c ./configure flags
*/
const char *swresample_configuration(void);
/**
* Return the swr license.
*
* @returns the license of libswresample, determined at build-time
*/
const char *swresample_license(void);
/**
* @}
* @}
*/
#endif /* SWRESAMPLE_SWRESAMPLE_H */