mirror of https://git.ffmpeg.org/ffmpeg.git
621 lines
19 KiB
C
621 lines
19 KiB
C
/*
|
|
* This file is part of Libav.
|
|
*
|
|
* Libav 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.
|
|
*
|
|
* Libav 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 Libav; if not, write to the Free Software
|
|
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*/
|
|
|
|
/**
|
|
* @file
|
|
* @ingroup lavu_frame
|
|
* reference-counted frame API
|
|
*/
|
|
|
|
#ifndef AVUTIL_FRAME_H
|
|
#define AVUTIL_FRAME_H
|
|
|
|
#include <stddef.h>
|
|
#include <stdint.h>
|
|
|
|
#include "avutil.h"
|
|
#include "buffer.h"
|
|
#include "dict.h"
|
|
#include "rational.h"
|
|
#include "samplefmt.h"
|
|
#include "pixfmt.h"
|
|
#include "version.h"
|
|
|
|
|
|
/**
|
|
* @defgroup lavu_frame AVFrame
|
|
* @ingroup lavu_data
|
|
*
|
|
* @{
|
|
* AVFrame is an abstraction for reference-counted raw multimedia data.
|
|
*/
|
|
|
|
enum AVFrameSideDataType {
|
|
/**
|
|
* The data is the AVPanScan struct defined in libavcodec.
|
|
*/
|
|
AV_FRAME_DATA_PANSCAN,
|
|
/**
|
|
* ATSC A53 Part 4 Closed Captions.
|
|
* A53 CC bitstream is stored as uint8_t in AVFrameSideData.data.
|
|
* The number of bytes of CC data is AVFrameSideData.size.
|
|
*/
|
|
AV_FRAME_DATA_A53_CC,
|
|
/**
|
|
* Stereoscopic 3d metadata.
|
|
* The data is the AVStereo3D struct defined in libavutil/stereo3d.h.
|
|
*/
|
|
AV_FRAME_DATA_STEREO3D,
|
|
/**
|
|
* The data is the AVMatrixEncoding enum defined in libavutil/channel_layout.h.
|
|
*/
|
|
AV_FRAME_DATA_MATRIXENCODING,
|
|
/**
|
|
* Metadata relevant to a downmix procedure.
|
|
* The data is the AVDownmixInfo struct defined in libavutil/downmix_info.h.
|
|
*/
|
|
AV_FRAME_DATA_DOWNMIX_INFO,
|
|
/**
|
|
* ReplayGain information in the form of the AVReplayGain struct.
|
|
*/
|
|
AV_FRAME_DATA_REPLAYGAIN,
|
|
/**
|
|
* This side data contains a 3x3 transformation matrix describing an affine
|
|
* transformation that needs to be applied to the frame for correct
|
|
* presentation.
|
|
*
|
|
* See libavutil/display.h for a detailed description of the data.
|
|
*/
|
|
AV_FRAME_DATA_DISPLAYMATRIX,
|
|
/**
|
|
* Active Format Description data consisting of a single byte as specified
|
|
* in ETSI TS 101 154 using enum AVActiveFormatDescription.
|
|
*/
|
|
AV_FRAME_DATA_AFD,
|
|
|
|
/**
|
|
* This side data must be associated with an audio frame and corresponds to
|
|
* enum AVAudioServiceType defined in avcodec.h.
|
|
*/
|
|
AV_FRAME_DATA_AUDIO_SERVICE_TYPE,
|
|
|
|
/**
|
|
* The data represents the AVSphericalMapping structure defined in
|
|
* libavutil/spherical.h.
|
|
*/
|
|
AV_FRAME_DATA_SPHERICAL,
|
|
};
|
|
|
|
enum AVActiveFormatDescription {
|
|
AV_AFD_SAME = 8,
|
|
AV_AFD_4_3 = 9,
|
|
AV_AFD_16_9 = 10,
|
|
AV_AFD_14_9 = 11,
|
|
AV_AFD_4_3_SP_14_9 = 13,
|
|
AV_AFD_16_9_SP_14_9 = 14,
|
|
AV_AFD_SP_4_3 = 15,
|
|
};
|
|
|
|
typedef struct AVFrameSideData {
|
|
enum AVFrameSideDataType type;
|
|
uint8_t *data;
|
|
int size;
|
|
AVDictionary *metadata;
|
|
} AVFrameSideData;
|
|
|
|
/**
|
|
* This structure describes decoded (raw) audio or video data.
|
|
*
|
|
* AVFrame must be allocated using av_frame_alloc(). Note that this only
|
|
* allocates the AVFrame itself, the buffers for the data must be managed
|
|
* through other means (see below).
|
|
* AVFrame must be freed with av_frame_free().
|
|
*
|
|
* AVFrame is typically allocated once and then reused multiple times to hold
|
|
* different data (e.g. a single AVFrame to hold frames received from a
|
|
* decoder). In such a case, av_frame_unref() will free any references held by
|
|
* the frame and reset it to its original clean state before it
|
|
* is reused again.
|
|
*
|
|
* The data described by an AVFrame is usually reference counted through the
|
|
* AVBuffer API. The underlying buffer references are stored in AVFrame.buf /
|
|
* AVFrame.extended_buf. An AVFrame is considered to be reference counted if at
|
|
* least one reference is set, i.e. if AVFrame.buf[0] != NULL. In such a case,
|
|
* every single data plane must be contained in one of the buffers in
|
|
* AVFrame.buf or AVFrame.extended_buf.
|
|
* There may be a single buffer for all the data, or one separate buffer for
|
|
* each plane, or anything in between.
|
|
*
|
|
* sizeof(AVFrame) is not a part of the public ABI, so new fields may be added
|
|
* to the end with a minor bump.
|
|
*/
|
|
typedef struct AVFrame {
|
|
#define AV_NUM_DATA_POINTERS 8
|
|
/**
|
|
* pointer to the picture/channel planes.
|
|
* This might be different from the first allocated byte
|
|
*/
|
|
uint8_t *data[AV_NUM_DATA_POINTERS];
|
|
|
|
/**
|
|
* For video, size in bytes of each picture line.
|
|
* For audio, size in bytes of each plane.
|
|
*
|
|
* For audio, only linesize[0] may be set. For planar audio, each channel
|
|
* plane must be the same size.
|
|
*
|
|
* @note The linesize may be larger than the size of usable data -- there
|
|
* may be extra padding present for performance reasons.
|
|
*/
|
|
int linesize[AV_NUM_DATA_POINTERS];
|
|
|
|
/**
|
|
* pointers to the data planes/channels.
|
|
*
|
|
* For video, this should simply point to data[].
|
|
*
|
|
* For planar audio, each channel has a separate data pointer, and
|
|
* linesize[0] contains the size of each channel buffer.
|
|
* For packed audio, there is just one data pointer, and linesize[0]
|
|
* contains the total size of the buffer for all channels.
|
|
*
|
|
* Note: Both data and extended_data should always be set in a valid frame,
|
|
* but for planar audio with more channels that can fit in data,
|
|
* extended_data must be used in order to access all channels.
|
|
*/
|
|
uint8_t **extended_data;
|
|
|
|
/**
|
|
* @name Video dimensions
|
|
* Video frames only. The coded dimensions (in pixels) of the video frame,
|
|
* i.e. the size of the rectangle that contains some well-defined values.
|
|
*
|
|
* @note The part of the frame intended for display/presentation is further
|
|
* restricted by the @ref cropping "Cropping rectangle".
|
|
* @{
|
|
*/
|
|
int width, height;
|
|
/**
|
|
* @}
|
|
*/
|
|
|
|
/**
|
|
* number of audio samples (per channel) described by this frame
|
|
*/
|
|
int nb_samples;
|
|
|
|
/**
|
|
* format of the frame, -1 if unknown or unset
|
|
* Values correspond to enum AVPixelFormat for video frames,
|
|
* enum AVSampleFormat for audio)
|
|
*/
|
|
int format;
|
|
|
|
/**
|
|
* 1 -> keyframe, 0-> not
|
|
*/
|
|
int key_frame;
|
|
|
|
/**
|
|
* Picture type of the frame.
|
|
*/
|
|
enum AVPictureType pict_type;
|
|
|
|
/**
|
|
* Sample aspect ratio for the video frame, 0/1 if unknown/unspecified.
|
|
*/
|
|
AVRational sample_aspect_ratio;
|
|
|
|
/**
|
|
* Presentation timestamp in time_base units (time when frame should be shown to user).
|
|
*/
|
|
int64_t pts;
|
|
|
|
#if FF_API_PKT_PTS
|
|
/**
|
|
* PTS copied from the AVPacket that was decoded to produce this frame.
|
|
* @deprecated use the pts field instead
|
|
*/
|
|
attribute_deprecated
|
|
int64_t pkt_pts;
|
|
#endif
|
|
|
|
/**
|
|
* DTS copied from the AVPacket that triggered returning this frame.
|
|
*/
|
|
int64_t pkt_dts;
|
|
|
|
/**
|
|
* picture number in bitstream order
|
|
*/
|
|
int coded_picture_number;
|
|
/**
|
|
* picture number in display order
|
|
*/
|
|
int display_picture_number;
|
|
|
|
/**
|
|
* quality (between 1 (good) and FF_LAMBDA_MAX (bad))
|
|
*/
|
|
int quality;
|
|
|
|
/**
|
|
* for some private data of the user
|
|
*/
|
|
void *opaque;
|
|
|
|
#if FF_API_ERROR_FRAME
|
|
/**
|
|
* @deprecated unused
|
|
*/
|
|
attribute_deprecated
|
|
uint64_t error[AV_NUM_DATA_POINTERS];
|
|
#endif
|
|
|
|
/**
|
|
* When decoding, this signals how much the picture must be delayed.
|
|
* extra_delay = repeat_pict / (2*fps)
|
|
*/
|
|
int repeat_pict;
|
|
|
|
/**
|
|
* The content of the picture is interlaced.
|
|
*/
|
|
int interlaced_frame;
|
|
|
|
/**
|
|
* If the content is interlaced, is top field displayed first.
|
|
*/
|
|
int top_field_first;
|
|
|
|
/**
|
|
* Tell user application that palette has changed from previous frame.
|
|
*/
|
|
int palette_has_changed;
|
|
|
|
/**
|
|
* reordered opaque 64 bits (generally an integer or a double precision float
|
|
* PTS but can be anything).
|
|
* The user sets AVCodecContext.reordered_opaque to represent the input at
|
|
* that time,
|
|
* the decoder reorders values as needed and sets AVFrame.reordered_opaque
|
|
* to exactly one of the values provided by the user through AVCodecContext.reordered_opaque
|
|
*/
|
|
int64_t reordered_opaque;
|
|
|
|
/**
|
|
* Sample rate of the audio data.
|
|
*/
|
|
int sample_rate;
|
|
|
|
/**
|
|
* Channel layout of the audio data.
|
|
*/
|
|
uint64_t channel_layout;
|
|
|
|
/**
|
|
* AVBuffer references backing the data for this frame. If all elements of
|
|
* this array are NULL, then this frame is not reference counted. This array
|
|
* must be filled contiguously -- if buf[i] is non-NULL then buf[j] must
|
|
* also be non-NULL for all j < i.
|
|
*
|
|
* There may be at most one AVBuffer per data plane, so for video this array
|
|
* always contains all the references. For planar audio with more than
|
|
* AV_NUM_DATA_POINTERS channels, there may be more buffers than can fit in
|
|
* this array. Then the extra AVBufferRef pointers are stored in the
|
|
* extended_buf array.
|
|
*/
|
|
AVBufferRef *buf[AV_NUM_DATA_POINTERS];
|
|
|
|
/**
|
|
* For planar audio which requires more than AV_NUM_DATA_POINTERS
|
|
* AVBufferRef pointers, this array will hold all the references which
|
|
* cannot fit into AVFrame.buf.
|
|
*
|
|
* Note that this is different from AVFrame.extended_data, which always
|
|
* contains all the pointers. This array only contains the extra pointers,
|
|
* which cannot fit into AVFrame.buf.
|
|
*
|
|
* This array is always allocated using av_malloc() by whoever constructs
|
|
* the frame. It is freed in av_frame_unref().
|
|
*/
|
|
AVBufferRef **extended_buf;
|
|
/**
|
|
* Number of elements in extended_buf.
|
|
*/
|
|
int nb_extended_buf;
|
|
|
|
AVFrameSideData **side_data;
|
|
int nb_side_data;
|
|
|
|
/**
|
|
* @defgroup lavu_frame_flags AV_FRAME_FLAGS
|
|
* Flags describing additional frame properties.
|
|
*
|
|
* @{
|
|
*/
|
|
|
|
/**
|
|
* The frame data may be corrupted, e.g. due to decoding errors.
|
|
*/
|
|
#define AV_FRAME_FLAG_CORRUPT (1 << 0)
|
|
/**
|
|
* @}
|
|
*/
|
|
|
|
/**
|
|
* Frame flags, a combination of @ref lavu_frame_flags
|
|
*/
|
|
int flags;
|
|
|
|
enum AVColorRange color_range;
|
|
|
|
enum AVColorPrimaries color_primaries;
|
|
|
|
enum AVColorTransferCharacteristic color_trc;
|
|
|
|
enum AVColorSpace colorspace;
|
|
|
|
enum AVChromaLocation chroma_location;
|
|
|
|
/**
|
|
* For hwaccel-format frames, this should be a reference to the
|
|
* AVHWFramesContext describing the frame.
|
|
*/
|
|
AVBufferRef *hw_frames_ctx;
|
|
|
|
/**
|
|
* @anchor cropping
|
|
* @name Cropping
|
|
* Video frames only. The number of pixels to discard from the the
|
|
* top/bottom/left/right border of the frame to obtain the sub-rectangle of
|
|
* the frame intended for presentation.
|
|
* @{
|
|
*/
|
|
size_t crop_top;
|
|
size_t crop_bottom;
|
|
size_t crop_left;
|
|
size_t crop_right;
|
|
/**
|
|
* @}
|
|
*/
|
|
|
|
/**
|
|
* AVBufferRef for free use by the API user. Libav will never check the
|
|
* contents of the buffer ref. Libav calls av_buffer_unref() on it when
|
|
* the frame is unreferenced. av_frame_copy_props() calls create a new
|
|
* reference with av_buffer_ref() for the target frame's opaque_ref field.
|
|
*
|
|
* This is unrelated to the opaque field, although it serves a similar
|
|
* purpose.
|
|
*/
|
|
AVBufferRef *opaque_ref;
|
|
} AVFrame;
|
|
|
|
/**
|
|
* Allocate an AVFrame and set its fields to default values. The resulting
|
|
* struct must be freed using av_frame_free().
|
|
*
|
|
* @return An AVFrame filled with default values or NULL on failure.
|
|
*
|
|
* @note this only allocates the AVFrame itself, not the data buffers. Those
|
|
* must be allocated through other means, e.g. with av_frame_get_buffer() or
|
|
* manually.
|
|
*/
|
|
AVFrame *av_frame_alloc(void);
|
|
|
|
/**
|
|
* Free the frame and any dynamically allocated objects in it,
|
|
* e.g. extended_data. If the frame is reference counted, it will be
|
|
* unreferenced first.
|
|
*
|
|
* @param frame frame to be freed. The pointer will be set to NULL.
|
|
*/
|
|
void av_frame_free(AVFrame **frame);
|
|
|
|
/**
|
|
* Set up a new reference to the data described by the source frame.
|
|
*
|
|
* Copy frame properties from src to dst and create a new reference for each
|
|
* AVBufferRef from src.
|
|
*
|
|
* If src is not reference counted, new buffers are allocated and the data is
|
|
* copied.
|
|
*
|
|
* @warning: dst MUST have been either unreferenced with av_frame_unref(dst),
|
|
* or newly allocated with av_frame_alloc() before calling this
|
|
* function, or undefined behavior will occur.
|
|
*
|
|
* @return 0 on success, a negative AVERROR on error
|
|
*/
|
|
int av_frame_ref(AVFrame *dst, const AVFrame *src);
|
|
|
|
/**
|
|
* Create a new frame that references the same data as src.
|
|
*
|
|
* This is a shortcut for av_frame_alloc()+av_frame_ref().
|
|
*
|
|
* @return newly created AVFrame on success, NULL on error.
|
|
*/
|
|
AVFrame *av_frame_clone(const AVFrame *src);
|
|
|
|
/**
|
|
* Unreference all the buffers referenced by frame and reset the frame fields.
|
|
*/
|
|
void av_frame_unref(AVFrame *frame);
|
|
|
|
/**
|
|
* Move everything contained in src to dst and reset src.
|
|
*
|
|
* @warning: dst is not unreferenced, but directly overwritten without reading
|
|
* or deallocating its contents. Call av_frame_unref(dst) manually
|
|
* before calling this function to ensure that no memory is leaked.
|
|
*/
|
|
void av_frame_move_ref(AVFrame *dst, AVFrame *src);
|
|
|
|
/**
|
|
* Allocate new buffer(s) for audio or video data.
|
|
*
|
|
* The following fields must be set on frame before calling this function:
|
|
* - format (pixel format for video, sample format for audio)
|
|
* - width and height for video
|
|
* - nb_samples and channel_layout for audio
|
|
*
|
|
* This function will fill AVFrame.data and AVFrame.buf arrays and, if
|
|
* necessary, allocate and fill AVFrame.extended_data and AVFrame.extended_buf.
|
|
* For planar formats, one buffer will be allocated for each plane.
|
|
*
|
|
* @warning: if frame already has been allocated, calling this function will
|
|
* leak memory. In addition, undefined behavior can occur in certain
|
|
* cases.
|
|
*
|
|
* @param frame frame in which to store the new buffers.
|
|
* @param align Required buffer size alignment. If equal to 0, alignment will be
|
|
* chosen automatically for the current CPU. It is highly
|
|
* recommended to pass 0 here unless you know what you are doing.
|
|
*
|
|
* @return 0 on success, a negative AVERROR on error.
|
|
*/
|
|
int av_frame_get_buffer(AVFrame *frame, int align);
|
|
|
|
/**
|
|
* Check if the frame data is writable.
|
|
*
|
|
* @return A positive value if the frame data is writable (which is true if and
|
|
* only if each of the underlying buffers has only one reference, namely the one
|
|
* stored in this frame). Return 0 otherwise.
|
|
*
|
|
* If 1 is returned the answer is valid until av_buffer_ref() is called on any
|
|
* of the underlying AVBufferRefs (e.g. through av_frame_ref() or directly).
|
|
*
|
|
* @see av_frame_make_writable(), av_buffer_is_writable()
|
|
*/
|
|
int av_frame_is_writable(AVFrame *frame);
|
|
|
|
/**
|
|
* Ensure that the frame data is writable, avoiding data copy if possible.
|
|
*
|
|
* Do nothing if the frame is writable, allocate new buffers and copy the data
|
|
* if it is not.
|
|
*
|
|
* @return 0 on success, a negative AVERROR on error.
|
|
*
|
|
* @see av_frame_is_writable(), av_buffer_is_writable(),
|
|
* av_buffer_make_writable()
|
|
*/
|
|
int av_frame_make_writable(AVFrame *frame);
|
|
|
|
/**
|
|
* Copy the frame data from src to dst.
|
|
*
|
|
* This function does not allocate anything, dst must be already initialized and
|
|
* allocated with the same parameters as src.
|
|
*
|
|
* This function only copies the frame data (i.e. the contents of the data /
|
|
* extended data arrays), not any other properties.
|
|
*
|
|
* @return >= 0 on success, a negative AVERROR on error.
|
|
*/
|
|
int av_frame_copy(AVFrame *dst, const AVFrame *src);
|
|
|
|
/**
|
|
* Copy only "metadata" fields from src to dst.
|
|
*
|
|
* Metadata for the purpose of this function are those fields that do not affect
|
|
* the data layout in the buffers. E.g. pts, sample rate (for audio) or sample
|
|
* aspect ratio (for video), but not width/height or channel layout.
|
|
* Side data is also copied.
|
|
*/
|
|
int av_frame_copy_props(AVFrame *dst, const AVFrame *src);
|
|
|
|
/**
|
|
* Get the buffer reference a given data plane is stored in.
|
|
*
|
|
* @param plane index of the data plane of interest in frame->extended_data.
|
|
*
|
|
* @return the buffer reference that contains the plane or NULL if the input
|
|
* frame is not valid.
|
|
*/
|
|
AVBufferRef *av_frame_get_plane_buffer(AVFrame *frame, int plane);
|
|
|
|
/**
|
|
* Add a new side data to a frame.
|
|
*
|
|
* @param frame a frame to which the side data should be added
|
|
* @param type type of the added side data
|
|
* @param size size of the side data
|
|
*
|
|
* @return newly added side data on success, NULL on error
|
|
*/
|
|
AVFrameSideData *av_frame_new_side_data(AVFrame *frame,
|
|
enum AVFrameSideDataType type,
|
|
int size);
|
|
|
|
/**
|
|
* @return a pointer to the side data of a given type on success, NULL if there
|
|
* is no side data with such type in this frame.
|
|
*/
|
|
AVFrameSideData *av_frame_get_side_data(const AVFrame *frame,
|
|
enum AVFrameSideDataType type);
|
|
|
|
/**
|
|
* If side data of the supplied type exists in the frame, free it and remove it
|
|
* from the frame.
|
|
*/
|
|
void av_frame_remove_side_data(AVFrame *frame, enum AVFrameSideDataType type);
|
|
|
|
|
|
/**
|
|
* Flags for frame cropping.
|
|
*/
|
|
enum {
|
|
/**
|
|
* Apply the maximum possible cropping, even if it requires setting the
|
|
* AVFrame.data[] entries to unaligned pointers. Passing unaligned data
|
|
* to Libav API is generally not allowed, and causes undefined behavior
|
|
* (such as crashes). You can pass unaligned data only to Libav APIs that
|
|
* are explicitly documented to accept it. Use this flag only if you
|
|
* absolutely know what you are doing.
|
|
*/
|
|
AV_FRAME_CROP_UNALIGNED = 1 << 0,
|
|
};
|
|
|
|
/**
|
|
* Crop the given video AVFrame according to its crop_left/crop_top/crop_right/
|
|
* crop_bottom fields. If cropping is successful, the function will adjust the
|
|
* data pointers and the width/height fields, and set the crop fields to 0.
|
|
*
|
|
* In all cases, the cropping boundaries will be rounded to the inherent
|
|
* alignment of the pixel format. In some cases, such as for opaque hwaccel
|
|
* formats, the left/top cropping is ignored. The crop fields are set to 0 even
|
|
* if the cropping was rounded or ignored.
|
|
*
|
|
* @param frame the frame which should be cropped
|
|
* @param flags Some combination of AV_FRAME_CROP_* flags, or 0.
|
|
*
|
|
* @return >= 0 on success, a negative AVERROR on error. If the cropping fields
|
|
* were invalid, AVERROR(ERANGE) is returned, and nothing is changed.
|
|
*/
|
|
int av_frame_apply_cropping(AVFrame *frame, int flags);
|
|
|
|
/**
|
|
* @}
|
|
*/
|
|
|
|
#endif /* AVUTIL_FRAME_H */
|