音频量化格式和相关的工具函数
- 类型说明
- 便捷的工具函数
av_get_sample_fmt_name
av_get_sample_fmt
av_get_alt_sample_fmt
av_get_packed_sample_fmt
av_get_planar_sample_fmt
av_get_sample_fmt_string
av_get_bytes_per_sample
av_sample_fmt_is_planar
av_sample_get_buffer_size
av_samples_fill_array
av_sample_alloc
av_samples_alloc_array_and_samples
av_samples_copy
av_samples_set_slience
类型说明
AVSampleFormat
/**
* Audio sample formats
*
* - The data described by the sample format is always in native-endian order.
* Sample values can be expressed by native C types, hence the lack of a signed
* 24-bit sample format even though it is a common raw audio data format.
*
* - The floating-point formats are based on full volume being in the range
* [-1.0, 1.0]. Any values outside this range are beyond full volume level.
*
* - The data layout as used in av_samples_fill_arrays() and elsewhere in FFmpeg
* (such as AVFrame in libavcodec) is as follows:
*
* @par
* For planar sample formats, each audio channel is in a separate data plane,
* and linesize is the buffer size, in bytes, for a single plane. All data
* planes must be the same size. For packed sample formats, only the first data
* plane is used, and samples for each channel are interleaved. In this case,
* linesize is the buffer size, in bytes, for the 1 plane.
*
*/
/*
*planar:每个音频数据通道位于不同的plane,且所有plane的数据长度是一致的, data[0] = LLL..., data[1] = RRR...。
* linesize表示单个plane的buffer size(以字节为单位)。
*packed:仅使用了第一个plane,且数据是交错存储的,data[0] = LRLRLR...。
* linesize表示单个plane的buffer size(以字节为单位)。。。(仅使用了一个plane == 单个plane)
*/
enum AVSampleFormat {
AV_SAMPLE_FMT_NONE = -1,
AV_SAMPLE_FMT_U8, ///< unsigned 8 bits
AV_SAMPLE_FMT_S16, ///< signed 16 bits
AV_SAMPLE_FMT_S32, ///< signed 32 bits
AV_SAMPLE_FMT_FLT, ///< float
AV_SAMPLE_FMT_DBL, ///< double
AV_SAMPLE_FMT_U8P, ///< unsigned 8 bits, planar
AV_SAMPLE_FMT_S16P, ///< signed 16 bits, planar
AV_SAMPLE_FMT_S32P, ///< signed 32 bits, planar
AV_SAMPLE_FMT_FLTP, ///< float, planar
AV_SAMPLE_FMT_DBLP, ///< double, planar
AV_SAMPLE_FMT_S64, ///< signed 64 bits
AV_SAMPLE_FMT_S64P, ///< signed 64 bits, planar
AV_SAMPLE_FMT_NB ///< Number of sample formats. DO NOT USE if linking dynamically
};
SampleFmtInfo
// 量化格式信息
typedef struct SampleFmtInfo {
char name[8]; // 量化格式名称
int bits; // bits >> 3 占据字节数量(1byte = 8bit ( 8 == 2 ** 3))
int planar; // 是否为planar格式,1是,0不是
enum AVSampleFormat altform; ///< planar<->packed alternative form,相反的格式
} SampleFmtInfo;
/** this table gives more information about formats */
// 量化格式参照表
static const SampleFmtInfo sample_fmt_info[AV_SAMPLE_FMT_NB] = {
[AV_SAMPLE_FMT_U8] = { .name = "u8", .bits = 8, .planar = 0, .altform = AV_SAMPLE_FMT_U8P },
[AV_SAMPLE_FMT_S16] = { .name = "s16", .bits = 16, .planar = 0, .altform = AV_SAMPLE_FMT_S16P },
[AV_SAMPLE_FMT_S32] = { .name = "s32", .bits = 32, .planar = 0, .altform = AV_SAMPLE_FMT_S32P },
[AV_SAMPLE_FMT_S64] = { .name = "s64", .bits = 64, .planar = 0, .altform = AV_SAMPLE_FMT_S64P },
[AV_SAMPLE_FMT_FLT] = { .name = "flt", .bits = 32, .planar = 0, .altform = AV_SAMPLE_FMT_FLTP },
[AV_SAMPLE_FMT_DBL] = { .name = "dbl", .bits = 64, .planar = 0, .altform = AV_SAMPLE_FMT_DBLP },
[AV_SAMPLE_FMT_U8P] = { .name = "u8p", .bits = 8, .planar = 1, .altform = AV_SAMPLE_FMT_U8 },
[AV_SAMPLE_FMT_S16P] = { .name = "s16p", .bits = 16, .planar = 1, .altform = AV_SAMPLE_FMT_S16 },
[AV_SAMPLE_FMT_S32P] = { .name = "s32p", .bits = 32, .planar = 1, .altform = AV_SAMPLE_FMT_S32 },
[AV_SAMPLE_FMT_S64P] = { .name = "s64p", .bits = 64, .planar = 1, .altform = AV_SAMPLE_FMT_S64 },
[AV_SAMPLE_FMT_FLTP] = { .name = "fltp", .bits = 32, .planar = 1, .altform = AV_SAMPLE_FMT_FLT },
[AV_SAMPLE_FMT_DBLP] = { .name = "dblp", .bits = 64, .planar = 1, .altform = AV_SAMPLE_FMT_DBL },
};
便捷的工具函数
av_get_sample_fmt_name
- brief:获取量化格式对应的字符串名称
- parameter: 量化格式
- return: 成功返回量化格式的字符串名称,失败返回NULL
/**
* Return the name of sample_fmt, or NULL if sample_fmt is not recognized.
*/
const char *av_get_sample_fmt_name(enum AVSampleFormat sample_fmt)
{
if (sample_fmt < 0 || sample_fmt >= AV_SAMPLE_FMT_NB)
return NULL;
return sample_fmt_info[sample_fmt].name;
}
av_get_sample_fmt
- 获取字符串名称对应的量化格式
- parameter: 量化格式的字符串名称
- return:成功返回对应的量化格式,失败返回AV_SAMPLE_FMT_NONE
/**
* Return a sample format corresponding to name, or AV_SAMPLE_FMT_NONE
* on error.
*/
enum AVSampleFormat av_get_sample_fmt(const char *name)
{
int i;
for (i = 0; i < AV_SAMPLE_FMT_NB; i++)
if (!strcmp(sample_fmt_info[i].name, name))
return i;
return AV_SAMPLE_FMT_NONE;
}
av_get_alt_sample_fmt
-
brief:获取相反的量化格式
-
parameter:sample_fmt:量化格式,planar:是否为planar格式
-
return:失败是返回AV_SAMPLE_FMT_NONE。
如果传递的sample_fmt已经采用请求的量化格式,则返回自己sample_fmt,比如 AV_SAMPLE_FMT_S16 = av_get_alt_sample_fmt(AV_SAMPLE_FMT_S16, 0);
否则返回对应的量化格式,比如AV_SAMPLE_FMT_S16P = av_get_alt_sample_fmt(AV_SAMPLE_FMT_S16, 1)。
/**
* Return the planar<->packed alternative form of the given sample format, or
* AV_SAMPLE_FMT_NONE on error. If the passed sample_fmt is already in the
* requested planar/packed format, the format returned is the same as the
* input.
*/
enum AVSampleFormat av_get_alt_sample_fmt(enum AVSampleFormat sample_fmt, int planar)
{
if (sample_fmt < 0 || sample_fmt >= AV_SAMPLE_FMT_NB)
return AV_SAMPLE_FMT_NONE;
if (sample_fmt_info[sample_fmt].planar == planar)
return sample_fmt;
return sample_fmt_info[sample_fmt].altform;
}
av_get_packed_sample_fmt
-
brief:返回packed格式的量化格式
-
parameter:sample_fmt请求的量化格式
-
return:失败返回AV_SAMPLE_FMT_NONE;
如果输入的已经是packed的格式,则返回自己sample_fmt。
否则返回对应的的packed格式的量化格式
/**
* Get the packed alternative form of the given sample format.
*
* If the passed sample_fmt is already in packed format, the format returned is
* the same as the input.
*
* @return the packed alternative form of the given sample format or
AV_SAMPLE_FMT_NONE on error.
*/
enum AVSampleFormat av_get_packed_sample_fmt(enum AVSampleFormat sample_fmt)
{
if (sample_fmt < 0 || sample_fmt >= AV_SAMPLE_FMT_NB)
return AV_SAMPLE_FMT_NONE;
if (sample_fmt_info[sample_fmt].planar)
return sample_fmt_info[sample_fmt].altform;
return sample_fmt;
}
av_get_planar_sample_fmt
-
brief:返回planar格式的量化格式
-
parameter:sample_fmt请求的量化格式
-
return:失败返回AV_SAMPLE_FMT_NONE;
如果输入的已经是planar的格式,则返回自己sample_fmt。
否则返回对应的的planar格式的量化格式
/**
* Get the planar alternative form of the given sample format.
*
* If the passed sample_fmt is already in planar format, the format returned is
* the same as the input.
*
* @return the planar alternative form of the given sample format or
AV_SAMPLE_FMT_NONE on error.
*/
enum AVSampleFormat av_get_planar_sample_fmt(enum AVSampleFormat sample_fmt)
{
if (sample_fmt < 0 || sample_fmt >= AV_SAMPLE_FMT_NB)
return AV_SAMPLE_FMT_NONE;
if (sample_fmt_info[sample_fmt].planar)
return sample_fmt;
return sample_fmt_info[sample_fmt].altform;
}
av_get_sample_fmt_string
- brief:获取指定量化格式的表示字符串,如果sample_fmt小于0,这返回描述信息头
- parameter:buf:描述字符串,buf_size, sample_fmt
- return:量化格式的对应字符串描述
/**
* Generate a string corresponding to the sample format with
* sample_fmt, or a header if sample_fmt is negative.
*
* @param buf the buffer where to write the string
* @param buf_size the size of buf
* @param sample_fmt the number of the sample format to print the
* corresponding info string, or a negative value to print the
* corresponding header.
* @return the pointer to the filled buffer or NULL if sample_fmt is
* unknown or in case of other errors
*/
char *av_get_sample_fmt_string (char *buf, int buf_size, enum AVSampleFormat sample_fmt)
{
/* print header */
if (sample_fmt < 0)
snprintf(buf, buf_size, "name " " depth");
else if (sample_fmt < AV_SAMPLE_FMT_NB) {
SampleFmtInfo info = sample_fmt_info[sample_fmt];
snprintf (buf, buf_size, "%-6s" " %2d ", info.name, info.bits);
}
return buf;
}
av_get_bytes_per_sample
- brief:获取指定量化格式的单个样本使用的字节数量
- parameter
- return:如果sample_fmt非法,返回0,成功返回占据字节数量
/**
* Return number of bytes per sample.
*
* @param sample_fmt the sample format
* @return number of bytes per sample or zero if unknown for the given
* sample format
*/
int av_get_bytes_per_sample(enum AVSampleFormat sample_fmt)
{
return sample_fmt < 0 || sample_fmt >= AV_SAMPLE_FMT_NB ?
0 : sample_fmt_info[sample_fmt].bits >> 3;
}
av_sample_fmt_is_planar
- brief:判断指定量化格式释放为planar格式
- parameter
- return:如果是planar格式则返回1,否则返回0
/**
* Check if the sample format is planar.
*
* @param sample_fmt the sample format to inspect
* @return 1 if the sample format is planar, 0 if it is interleaved
*/
int av_sample_fmt_is_planar(enum AVSampleFormat sample_fmt)
{
if (sample_fmt < 0 || sample_fmt >= AV_SAMPLE_FMT_NB)
return 0;
return sample_fmt_info[sample_fmt].planar;
}
av_sample_get_buffer_size
- brief:获取指定样本格式的缓冲区大小
- parameter:linesize单个plane的大小,nb_channels声音通道个数,nb_samples:帧率,sample_fmt, align对齐
- return:失败返回负数标示故障码,否则返回缓冲区大小
/**
* Get the required buffer size for the given audio parameters.
*
* @param[out] linesize calculated linesize, may be NULL
* @param nb_channels the number of channels
* @param nb_samples the number of samples in a single channel
* @param sample_fmt the sample format
* @param align buffer size alignment (0 = default, 1 = no alignment)
* @return required buffer size, or negative error code on failure
*/
int av_samples_get_buffer_size(int *linesize, int nb_channels, int nb_samples,
enum AVSampleFormat sample_fmt, int align)
{
int line_size;
int sample_size = av_get_bytes_per_sample(sample_fmt);
int planar = av_sample_fmt_is_planar(sample_fmt);
/* validate parameter ranges */
if (!sample_size || nb_samples <= 0 || nb_channels <= 0)
return AVERROR(EINVAL);
/* auto-select alignment if not specified */
if (!align) {
if (nb_samples > INT_MAX - 31)
return AVERROR(EINVAL);
align = 1;
nb_samples = FFALIGN(nb_samples, 32);
}
/* check for integer overflow */
if (nb_channels > INT_MAX / align ||
(int64_t)nb_channels * nb_samples > (INT_MAX - (align * nb_channels)) / sample_size)
return AVERROR(EINVAL);
line_size = planar ? FFALIGN(nb_samples * sample_size, align) :
FFALIGN(nb_samples * sample_size * nb_channels, align);
if (linesize)
*linesize = line_size;
return planar ? line_size * nb_channels : line_size;
}
av_samples_fill_array
-
brief:为指定sample_fmt格式的样本填充plane data和linesize
使用
char **audio_data
接受被填充的样本数据,对于packed数据,仅需要设置audio_data起始点即可, 对于planar数据,
*audio_data
表示不同的通道数据的起点 linesize:对于planar数据,linesize标示单个plane对齐后的数据大小
对于packed数据,linesize标示说有plane对齐后的数据大小总和
buf的buf_size必须足够大用来存储所有样本,否则audio_data会指向无效数据,可以通过
av_samples_get_buffer_size()
来计算 -
return:指定量化格式需要buf_size
/**
* Fill plane data pointers and linesize for samples with sample
* format sample_fmt.
*
* The audio_data array is filled with the pointers to the samples data planes:
* for planar, set the start point of each channel's data within the buffer,
* for packed, set the start point of the entire buffer only.
*
* The value pointed to by linesize is set to the aligned size of each
* channel's data buffer for planar layout, or to the aligned size of the
* buffer for all channels for packed layout.
*
* The buffer in buf must be big enough to contain all the samples
* (use av_samples_get_buffer_size() to compute its minimum size),
* otherwise the audio_data pointers will point to invalid data.
*
* @see enum AVSampleFormat
* The documentation for AVSampleFormat describes the data layout.
*
* @param[out] audio_data array to be filled with the pointer for each channel
* @param[out] linesize calculated linesize, may be NULL
* @param buf the pointer to a buffer containing the samples
* @param nb_channels the number of channels
* @param nb_samples the number of samples in a single channel
* @param sample_fmt the sample format
* @param align buffer size alignment (0 = default, 1 = no alignment)
* @return >=0 on success or a negative error code on failure
* @todo return minimum size in bytes required for the buffer in case
* of success at the next bump
*/
int av_samples_fill_arrays(uint8_t **audio_data, int *linesize,
const uint8_t *buf, int nb_channels, int nb_samples,
enum AVSampleFormat sample_fmt, int align)
{
int ch, planar, buf_size, line_size;
planar = av_sample_fmt_is_planar(sample_fmt);
buf_size = av_samples_get_buffer_size(&line_size, nb_channels, nb_samples,
sample_fmt, align);
if (buf_size < 0)
return buf_size;
// if planar to packed
audio_data[0] = (uint8_t *)buf;
for (ch = 1; planar && ch < nb_channels; ch++)
audio_data[ch] = audio_data[ch-1] + line_size;
if (linesize)
*linesize = line_size;
return buf_size;
}
av_sample_alloc
- brief:为指定格式的量化格式分配样本buffer,并且填充静音音频数据
- return:负数标示失败错误码,否则成功
/**
* Allocate a samples buffer for nb_samples samples, and fill data pointers and
* linesize accordingly.
* The allocated samples buffer can be freed by using av_freep(&audio_data[0])
* Allocated data will be initialized to silence.
*
* @see enum AVSampleFormat
* The documentation for AVSampleFormat describes the data layout.
*
* @param[out] audio_data array to be filled with the pointer for each channel
* @param[out] linesize aligned size for audio buffer(s), may be NULL
* @param nb_channels number of audio channels
* @param nb_samples number of samples per channel
* @param align buffer size alignment (0 = default, 1 = no alignment)
* @return >=0 on success or a negative error code on failure
* @todo return the size of the allocated buffer in case of success at the next bump
* @see av_samples_fill_arrays()
* @see av_samples_alloc_array_and_samples()
*/
int av_samples_alloc(uint8_t **audio_data, int *linesize, int nb_channels,
int nb_samples, enum AVSampleFormat sample_fmt, int align)
{
uint8_t *buf;
int size = av_samples_get_buffer_size(NULL, nb_channels, nb_samples,
sample_fmt, align);
if (size < 0)
return size;
buf = av_malloc(size);
if (!buf)
return AVERROR(ENOMEM);
size = av_samples_fill_arrays(audio_data, linesize, buf, nb_channels,
nb_samples, sample_fmt, align);
if (size < 0) {
av_free(buf);
return size;
}
av_samples_set_silence(audio_data, 0, nb_samples, nb_channels, sample_fmt);
return size;
}
av_samples_alloc_array_and_samples
- 同
av_sample_alloc()
/**
* Allocate a data pointers array, samples buffer for nb_samples
* samples, and fill data pointers and linesize accordingly.
*
* This is the same as av_samples_alloc(), but also allocates the data
* pointers array.
*
* @see av_samples_alloc()
*/
int av_samples_alloc_array_and_samples(uint8_t ***audio_data, int *linesize, int nb_channels,
int nb_samples, enum AVSampleFormat sample_fmt, int align)
{
int ret, nb_planes = av_sample_fmt_is_planar(sample_fmt) ? nb_channels : 1;
*audio_data = av_calloc(nb_planes, sizeof(**audio_data));
if (!*audio_data)
return AVERROR(ENOMEM);
ret = av_samples_alloc(*audio_data, linesize, nb_channels,
nb_samples, sample_fmt, align);
if (ret < 0)
av_freep(audio_data);
return ret;
}
av_samples_copy
/**
* Copy samples from src to dst.
*
* @param dst destination array of pointers to data planes
* @param src source array of pointers to data planes
* @param dst_offset offset in samples at which the data will be written to dst
* @param src_offset offset in samples at which the data will be read from src
* @param nb_samples number of samples to be copied
* @param nb_channels number of audio channels
* @param sample_fmt audio sample format
*/
int av_samples_copy(uint8_t **dst, uint8_t * const *src, int dst_offset,
int src_offset, int nb_samples, int nb_channels,
enum AVSampleFormat sample_fmt)
{
int planar = av_sample_fmt_is_planar(sample_fmt);
int planes = planar ? nb_channels : 1;
int block_align = av_get_bytes_per_sample(sample_fmt) * (planar ? 1 : nb_channels);
int data_size = nb_samples * block_align;
int i;
dst_offset *= block_align;
src_offset *= block_align;
if((dst[0] < src[0] ? src[0] - dst[0] : dst[0] - src[0]) >= data_size) {
for (i = 0; i < planes; i++)
memcpy(dst[i] + dst_offset, src[i] + src_offset, data_size);
} else {
for (i = 0; i < planes; i++)
memmove(dst[i] + dst_offset, src[i] + src_offset, data_size);
}
return 0;
}
av_samples_set_slience
/**
* Fill an audio buffer with silence.
*
* @param audio_data array of pointers to data planes
* @param offset offset in samples at which to start filling
* @param nb_samples number of samples to fill
* @param nb_channels number of audio channels
* @param sample_fmt audio sample format
*/
int av_samples_set_silence(uint8_t **audio_data, int offset, int nb_samples,
int nb_channels, enum AVSampleFormat sample_fmt)
{
int planar = av_sample_fmt_is_planar(sample_fmt);
int planes = planar ? nb_channels : 1;
int block_align = av_get_bytes_per_sample(sample_fmt) * (planar ? 1 : nb_channels);
int data_size = nb_samples * block_align;
int fill_char = (sample_fmt == AV_SAMPLE_FMT_U8 ||
sample_fmt == AV_SAMPLE_FMT_U8P) ? 0x80 : 0x00;
int i;
offset *= block_align;
for (i = 0; i < planes; i++)
memset(audio_data[i] + offset, fill_char, data_size);
return 0;
}