文章最后是ffmpeg解码的一个案例,我们先从把Codec所有核心函数列出来:
const AVCodec *dec = NULL;
AVCodecContext *dec_ctx
dec = avcodec_find_decoder_by_name("libx264");//avcodec_find_decoder
dec_ctx = avcodec_alloc_context3(dec);
avcodec_parameters_to_context(*dec_ctx, st->codecpar)
avcodec_open2(*dec_ctx, dec, NULL);
avcodec_send_packet(dec, pkt);
avcodec_receive_frame(dec, frame);
avcodec_free_context(&dec_ctx)
avcodec_close(dec_ctx);
dec = avcodec_find_decoder_by_name("libx264")
看代码:
const AVCodec *avcodec_find_encoder_by_name(const char *name)
{
return find_codec_by_name(name, av_codec_is_encoder);
}
const AVCodec *avcodec_find_decoder_by_name(const char *name)
{
return find_codec_by_name(name, av_codec_is_decoder);
}
static const AVCodec *find_codec_by_name(const char *name, int (*x)(const AVCodec *))
{
void *i = 0;
const AVCodec *p;
if (!name)
return NULL;
//主要就在这里循环寻找
while ((p = av_codec_iterate(&i))) {
if (!x(p))
continue;
if (strcmp(name, p->name) == 0)
return p;
}
return NULL;
}
//这里看如何迭代寻找codec
const AVCodec *av_codec_iterate(void **opaque)
{
uintptr_t i = (uintptr_t)*opaque;
const AVCodec *c = codec_list[i];
//这里表示只执行一次,所以关键是av_codec_init_static
ff_thread_once(&av_codec_static_init, av_codec_init_static);
if (c)
*opaque = (void*)(i + 1);
return c;
}
//看看这个只执行一次的关键函数在做什么
static AVOnce av_codec_static_init = AV_ONCE_INIT;
static void av_codec_init_static(void)
{
//codec_list这个数组是什么时候创建的?这是我们核心点,看下面
for (int i = 0; codec_list[i]; i++) {
if (codec_list[i]->init_static_data)
//这里调用每个codec的全局初始化函数
codec_list[i]->init_static_data((AVCodec*)codec_list[i]);
}
}
上面提到一个核心数组codec_list,所以核心在于codec_list这个数组:
// The iterate API is not usable with ossfuzz due to the excessive size of binaries created
#if CONFIG_OSSFUZZ
const AVCodec * codec_list[] = {
NULL,
NULL,
NULL
};
#else
#include "libavcodec/codec_list.c"
#endif
那么这个codec_list.c是哪来的呢?
下面是configure里面的一段,所以下述文件全是configure的时候生成的
print_enabled_components libavfilter/filter_list.c AVFilter filter_list $FILTER_LIST
print_enabled_components libavcodec/codec_list.c AVCodec codec_list $CODEC_LIST
print_enabled_components libavcodec/parser_list.c AVCodecParser parser_list $PARSER_LIST
print_enabled_components libavcodec/bsf_list.c AVBitStreamFilter bitstream_filters $BSF_LIST
print_enabled_components libavformat/demuxer_list.c AVInputFormat demuxer_list $DEMUXER_LIST
print_enabled_components libavformat/muxer_list.c AVOutputFormat muxer_list $MUXER_LIST
print_enabled_components libavdevice/indev_list.c AVInputFormat indev_list $INDEV_LIST
print_enabled_components libavdevice/outdev_list.c AVOutputFormat outdev_list $OUTDEV_LIST
print_enabled_components libavformat/protocol_list.c URLProtocol url_protocols $PROTOCOL_LIST
codec_list.c在configure的时候被生成,具体如下
static const AVCodec * const codec_list[] = {
&ff_a64multi_encoder,
&ff_a64multi5_encoder,
&ff_alias_pix_encoder,
...
&ff_comfortnoise_encoder,
&ff_dnxhd_encoder,
&ff_dpx_encoder,
&ff_dvvideo_encoder,
&ff_exr_encoder,
&ff_ffv1_encoder,
&ff_ffvhuff_encoder,
&ff_fits_encoder,
&ff_flashsv_encoder,
&ff_flashsv2_encoder,
&ff_flv_encoder,
&ff_gif_encoder,
&ff_h261_encoder,
&ff_h263_encoder,
&ff_h263p_encoder,
&ff_huffyuv_encoder,
...
&ff_pfm_encoder,
&ff_pgm_encoder,
...
&ff_idf_decoder,
&ff_av1_decoder,
&ff_h264_omx_decoder,
&ff_mpeg4_omx_decoder,
NULL };
总结一下调用:
avcodec_find_decoder_by_name()
find_codec_by_name()
av_codec_iterate()
av_codec_init_static()
AVCodec定义:
typedef struct AVCodec {
//这就是每个codec的名字
const char *name;
const char *long_name;
enum AVMediaType type;
enum AVCodecID id;
//关于cap有很多宏定义
int capabilities; //see AV_CODEC_CAP_*
uint8_t max_lowres; ///< maximum value for lowres supported by the decoder
const AVRational *supported_framerates; ///< array of supported framerates, or NULL if any, array is terminated by {0,0}
const enum AVPixelFormat *pix_fmts; ///< array of supported pixel formats, or NULL if unknown, array is terminated by -1
const int *supported_samplerates; ///< array of supported audio samplerates, or NULL if unknown, array is terminated by 0
const enum AVSampleFormat *sample_fmts; ///< array of supported sample formats, or NULL if unknown, array is terminated by -1
const uint64_t *channel_layouts; ///< array of support channel layouts, or NULL if unknown. array is terminated by 0
const AVClass *priv_class; ///< AVClass for the private context
const AVProfile *profiles; ///< array of recognized profiles, or NULL if unknown, array is terminated by
int caps_internal;
int priv_data_size;
int (*update_thread_context)(struct AVCodecContext *dst, const struct AVCodecContext *src);
int (*update_thread_context_for_user)(struct AVCodecContext *dst, const struct AVCodecContext *src);
const AVCodecDefault *defaults;
//从这里开始有9个回调函数,这也是我们编写codec插件的一些关键回调函数
//还记得这个init_static_data回调函数在什么时候调用吗
void (*init_static_data)(struct AVCodec *codec);
int (*init)(struct AVCodecContext *);
int (*encode_sub)(struct AVCodecContext *, uint8_t *buf, int buf_size,const struct AVSubtitle *sub);
int (*encode2)(struct AVCodecContext *avctx, struct AVPacket *avpkt,const struct AVFrame *frame, int *got_packet_ptr);
int (*decode)(struct AVCodecContext *avctx, void *outdata,int *got_frame_ptr, struct AVPacket *avpkt);
int (*close)(struct AVCodecContext *);
int (*receive_packet)(struct AVCodecContext *avctx, struct AVPacket *avpkt);
int (*receive_frame)(struct AVCodecContext *avctx, struct AVFrame *frame);
void (*flush)(struct AVCodecContext *);
const char *bsfs;
const struct AVCodecHWConfigInternal *const *hw_configs;
const uint32_t *codec_tags;
} AVCodec;
继续上面的find_codec_by_name(),我们重新把刚才代码贴上来,如下:
static const AVCodec *find_codec_by_name(const char *name, int (*x)(const AVCodec *))
{
void *i = 0;
const AVCodec *p;
if (!name)
return NULL;
//这里遍历寻找codec
while ((p = av_codec_iterate(&i))) {
if (!x(p))
continue;
//对比一下名称,一样的话就返回该codec
if (strcmp(name, p->name) == 0)
return p;
}
return NULL;
}
const AVCodec *av_codec_iterate(void **opaque)
{
uintptr_t i = (uintptr_t)*opaque;
const AVCodec *c = codec_list[i];
//这里是全局执行一次
ff_thread_once(&av_codec_static_init, av_codec_init_static);
if (c)
*opaque = (void*)(i + 1);
return c;
}
static void av_codec_init_static(void)
{
for (int i = 0; codec_list[i]; i++) {
if (codec_list[i]->init_static_data)
//这里是回调函数执行一下
codec_list[i]->init_static_data((AVCodec*)codec_list[i]);
}
}
上面是根据名称来寻找codec,下面看看根据codec id来寻找的流程,核心就是那么多相同id的,倒地选择哪一个?
const AVCodec *avcodec_find_decoder(enum AVCodecID id)
{
return find_codec(id, av_codec_is_decoder);
}
static const AVCodec *find_codec(enum AVCodecID id, int (*x)(const AVCodec *))
{
const AVCodec *p, *experimental = NULL;
void *i = 0;
//这里什么都没有做
id = remap_deprecated_codec_id(id);
while ((p = av_codec_iterate(&i))) {
if (!x(p))
continue;
//从这里看,应该就是排名最前的,只要其cap不是AV_CODEC_CAP_EXPERIMENTAL
if (p->id == id) {
if (p->capabilities & AV_CODEC_CAP_EXPERIMENTAL && !experimental) {
experimental = p;
} else
return p;
}
}
return experimental;
}
static enum AVCodecID remap_deprecated_codec_id(enum AVCodecID id)
{
switch(id){
//This is for future deprecatec codec ids, its empty since
//last major bump but will fill up again over time, please don't remove it
default : return id;
}
}
根据上面创建的codec来创建上下文。
dec_ctx = avcodec_alloc_context3(dec);
看函数之前我们先看上下文定义,AVCodecContext定义非常大,具体定义如下(一定不要嫌麻烦,哪怕看不懂也要一个一个看,这样后面会有点印象,千里之行始于足下,你着急好像也没什么用):
//这个table罗列了
#define OFFSET(x) offsetof(AVCodecContext,x)
//这里罗列了一个Option,为什么要罗列呢,这是因为AVCodecContext的很多字段可以通过Option来设置/获取 av_opt* / av_set/get*()
static const AVOption avcodec_options[] = {
{"b", "set bitrate (in bits/s)", OFFSET(bit_rate), AV_OPT_TYPE_INT64, {.i64 = AV_CODEC_DEFAULT_BITRATE }, 0, INT64_MAX, A|V|E},
...
}
/**
* You can use AVOptions (av_opt* / av_set/get*()) to access these fields from user
* applications.
* The name string for AVOptions options matches the associated command line
* parameter name and can be found in libavcodec/options_table.h
* The AVOption/command line parameter names differ in some cases from the C
* structure field names for historic reasons or brevity.
* sizeof(AVCodecContext) must not be used outside libav*.
*/
//我们可以在用户层通过AVOptions (av_opt* / av_set/get*()) 来设置它里面的参数,在avcodec.c文件中有一个avcodec_options table
//上面详细罗列了options的参数
typedef struct AVCodecContext {
/**
* information on struct for av_log
* - set by avcodec_alloc_context3
*/
const AVClass *av_class;
int log_level_offset;
enum AVMediaType codec_type; /* see AVMEDIA_TYPE_xxx */
//这个指针指向前面发现的codec
const struct AVCodec *codec;
enum AVCodecID codec_id; /* see AV_CODEC_ID_xxx */
/**
* fourcc (LSB first, so "ABCD" -> ('D'<<24) + ('C'<<16) + ('B'<<8) + 'A').
* This is used to work around some encoder bugs.
* A demuxer should set this to what is stored in the field used to identify the codec.
* If there are multiple such fields in a container then the demuxer should choose the one
* which maximizes the information about the used codec.
* If the codec tag field in a container is larger than 32 bits then the demuxer should
* remap the longer ID to 32 bits with a table or other structure. Alternatively a new
* extra_codec_tag + size could be added but for this a clear advantage must be demonstrated
* first.
* - encoding: Set by user, if not then the default based on codec_id will be used.
* - decoding: Set by user, will be converted to uppercase by libavcodec during init.
*/
unsigned int codec_tag;
void *priv_data;
/**
* Private context used for internal data.
*
* Unlike priv_data, this is not codec-specific. It is used in general
* libavcodec functions.
*/
//这个结构体是codec内部处理过程中的中介,内部数据的处理临时buf,pkt都要通过这里
struct AVCodecInternal *internal;
/**
* Private data of the user, can be used to carry app specific stuff.
* - encoding: Set by user.
* - decoding: Set by user.
*/
void *opaque;
/**
* the average bitrate
* - encoding: Set by user; unused for constant quantizer encoding.
* - decoding: Set by user, may be overwritten by libavcodec
* if this info is available in the stream
*/
//通过Option可以设置
int64_t bit_rate;
/**
* number of bits the bitstream is allowed to diverge from the reference.
* the reference can be CBR (for CBR pass1) or VBR (for pass2)
* - encoding: Set by user; unused for constant quantizer encoding.
* - decoding: unused
*/
//通过Option可以设置
int bit_rate_tolerance;
/**
* Global quality for codecs which cannot change it per frame.
* This should be proportional to MPEG-1/2/4 qscale.
* - encoding: Set by user.
* - decoding: unused
*/
int global_quality;
/**
* - encoding: Set by user.
* - decoding: unused
*/
int compression_level;
#define FF_COMPRESSION_DEFAULT -1
/**
* AV_CODEC_FLAG_*.
* - encoding: Set by user.
* - decoding: Set by user.
*/
int flags;
/**
* AV_CODEC_FLAG2_*
* - encoding: Set by user.
* - decoding: Set by user.
*/
int flags2;
/**
* some codecs need / can use extradata like Huffman tables.
* MJPEG: Huffman tables
* rv10: additional flags
* MPEG-4: global headers (they can be in the bitstream or here)
* The allocated memory should be AV_INPUT_BUFFER_PADDING_SIZE bytes larger
* than extradata_size to avoid problems if it is read with the bitstream reader.
* The bytewise contents of extradata must not depend on the architecture or CPU endianness.
* Must be allocated with the av_malloc() family of functions.
* - encoding: Set/allocated/freed by libavcodec.
* - decoding: Set/allocated/freed by user.
*/
//对于h264、265这里保存sps,pps,sei信息
uint8_t *extradata;
int extradata_size;
/**
* This is the fundamental unit of time (in seconds) in terms
* of which frame timestamps are represented. For fixed-fps content,
* timebase should be 1/framerate and timestamp increments should be
* identically 1.
* This often, but not always is the inverse of the frame rate or field rate
* for video. 1/time_base is not the average frame rate if the frame rate is not
* constant.
*
* Like containers, elementary streams also can store timestamps, 1/time_base
* is the unit in which these timestamps are specified.
* As example of such codec time base see ISO/IEC 14496-2:2001(E)
* vop_time_increment_resolution and fixed_vop_rate
* (fixed_vop_rate == 0 implies that it is different from the framerate)
*
* - encoding: MUST be set by user.
* - decoding: the use of this field for decoding is deprecated.
* Use framerate instead.
*/
AVRational time_base;
/**
* For some codecs, the time base is closer to the field rate than the frame rate.
* Most notably, H.264 and MPEG-2 specify time_base as half of frame duration
* if no telecine is used ...
*
* Set to time_base ticks per frame. Default 1, e.g., H.264/MPEG-2 set it to 2.
*/
int ticks_per_frame;
/**
* Codec delay.
*
* Encoding: Number of frames delay there will be from the encoder input to
* the decoder output. (we assume the decoder matches the spec)
* Decoding: Number of frames delay in addition to what a standard decoder
* as specified in the spec would produce.
*
* Video:
* Number of frames the decoded output will be delayed relative to the
* encoded input.
*
* Audio:
* For encoding, this field is unused (see initial_padding).
*
* For decoding, this is the number of samples the decoder needs to
* output before the decoder's output is valid. When seeking, you should
* start decoding this many samples prior to your desired seek point.
*
* - encoding: Set by libavcodec.
* - decoding: Set by libavcodec.
*/
int delay;
/* video only */
/**
* picture width / height.
*
* @note Those fields may not match the values of the last
* AVFrame output by avcodec_receive_frame() due frame
* reordering.
*
* - encoding: MUST be set by user.
* - decoding: May be set by the user before opening the decoder if known e.g.
* from the container. Some decoders will require the dimensions
* to be set by the caller. During decoding, the decoder may
* overwrite those values as required while parsing the data.
*/
int width, height;
/**
* Bitstream width / height, may be different from width/height e.g. when
* the decoded frame is cropped before being output or lowres is enabled.
*
* @note Those field may not match the value of the last
* AVFrame output by avcodec_receive_frame() due frame
* reordering.
*
* - encoding: unused
* - decoding: May be set by the user before opening the decoder if known
* e.g. from the container. During decoding, the decoder may
* overwrite those values as required while parsing the data.
*/
int coded_width, coded_height;
/**
* the number of pictures in a group of pictures, or 0 for intra_only
* - encoding: Set by user.
* - decoding: unused
*/
int gop_size;
/**
* Pixel format, see AV_PIX_FMT_xxx.
* May be set by the demuxer if known from headers.
* May be overridden by the decoder if it knows better.
*
* @note This field may not match the value of the last
* AVFrame output by avcodec_receive_frame() due frame
* reordering.
*
* - encoding: Set by user.
* - decoding: Set by user if known, overridden by libavcodec while
* parsing the data.
*/
enum AVPixelFormat pix_fmt;
/**
* If non NULL, 'draw_horiz_band' is called by the libavcodec
* decoder to draw a horizontal band. It improves cache usage. Not
* all codecs can do that. You must check the codec capabilities
* beforehand.
* When multithreading is used, it may be called from multiple threads
* at the same time; threads might draw different parts of the same AVFrame,
* or multiple AVFrames, and there is no guarantee that slices will be drawn
* in order.
* The function is also used by hardware acceleration APIs.
* It is called at least once during frame decoding to pass
* the data needed for hardware render.
* In that mode instead of pixel data, AVFrame points to
* a structure specific to the acceleration API. The application
* reads the structure and can change some fields to indicate progress
* or mark state.
* - encoding: unused
* - decoding: Set by user.
* @param height the height of the slice
* @param y the y position of the slice
* @param type 1->top field, 2->bottom field, 3->frame
* @param offset offset into the AVFrame.data from which the slice should be read
*/
void (*draw_horiz_band)(struct AVCodecContext *s,
const AVFrame *src, int offset[AV_NUM_DATA_POINTERS],
int y, int type, int height);
/**
* Callback to negotiate the pixel format. Decoding only, may be set by the
* caller before avcodec_open2().
*
* Called by some decoders to select the pixel format that will be used for
* the output frames. This is mainly used to set up hardware acceleration,
* then the provided format list contains the corresponding hwaccel pixel
* formats alongside the "software" one. The software pixel format may also
* be retrieved from \ref sw_pix_fmt.
*
* This callback will be called when the coded frame properties (such as
* resolution, pixel format, etc.) change and more than one output format is
* supported for those new properties. If a hardware pixel format is chosen
* and initialization for it fails, the callback may be called again
* immediately.
*
* This callback may be called from different threads if the decoder is
* multi-threaded, but not from more than one thread simultaneously.
*
* @param fmt list of formats which may be used in the current
* configuration, terminated by AV_PIX_FMT_NONE.
* @warning Behavior is undefined if the callback returns a value other
* than one of the formats in fmt or AV_PIX_FMT_NONE.
* @return the chosen format or AV_PIX_FMT_NONE
*/
enum AVPixelFormat (*get_format)(struct AVCodecContext *s, const enum AVPixelFormat * fmt);
/**
* maximum number of B-frames between non-B-frames
* Note: The output will be delayed by max_b_frames+1 relative to the input.
* - encoding: Set by user.
* - decoding: unused
*/
int max_b_frames;
/**
* qscale factor between IP and B-frames
* If > 0 then the last P-frame quantizer will be used (q= lastp_q*factor+offset).
* If < 0 then normal ratecontrol will be done (q= -normal_q*factor+offset).
* - encoding: Set by user.
* - decoding: unused
*/
float b_quant_factor;
/**
* qscale offset between IP and B-frames
* - encoding: Set by user.
* - decoding: unused
*/
float b_quant_offset;
/**
* Size of the frame reordering buffer in the decoder.
* For MPEG-2 it is 1 IPB or 0 low delay IP.
* - encoding: Set by libavcodec.
* - decoding: Set by libavcodec.
*/
int has_b_frames;
/**
* qscale factor between P- and I-frames
* If > 0 then the last P-frame quantizer will be used (q = lastp_q * factor + offset).
* If < 0 then normal ratecontrol will be done (q= -normal_q*factor+offset).
* - encoding: Set by user.
* - decoding: unused
*/
float i_quant_factor;
/**
* qscale offset between P and I-frames
* - encoding: Set by user.
* - decoding: unused
*/
float i_quant_offset;
/**
* luminance masking (0-> disabled)
* - encoding: Set by user.
* - decoding: unused
*/
float lumi_masking;
/**
* temporary complexity masking (0-> disabled)
* - encoding: Set by user.
* - decoding: unused
*/
float temporal_cplx_masking;
/**
* spatial complexity masking (0-> disabled)
* - encoding: Set by user.
* - decoding: unused
*/
float spatial_cplx_masking;
/**
* p block masking (0-> disabled)
* - encoding: Set by user.
* - decoding: unused
*/
float p_masking;
/**
* darkness masking (0-> disabled)
* - encoding: Set by user.
* - decoding: unused
*/
float dark_masking;
/**
* slice count
* - encoding: Set by libavcodec.
* - decoding: Set by user (or 0).
*/
int slice_count;
/**
* slice offsets in the frame in bytes
* - encoding: Set/allocated by libavcodec.
* - decoding: Set/allocated by user (or NULL).
*/
int *slice_offset;
/**
* sample aspect ratio (0 if unknown)
* That is the width of a pixel divided by the height of the pixel.
* Numerator and denominator must be relatively prime and smaller than 256 for some video standards.
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
AVRational sample_aspect_ratio;
/**
* motion estimation comparison function
* - encoding: Set by user.
* - decoding: unused
*/
int me_cmp;
/**
* subpixel motion estimation comparison function
* - encoding: Set by user.
* - decoding: unused
*/
int me_sub_cmp;
/**
* macroblock comparison function (not supported yet)
* - encoding: Set by user.
* - decoding: unused
*/
int mb_cmp;
/**
* interlaced DCT comparison function
* - encoding: Set by user.
* - decoding: unused
*/
int ildct_cmp;
#define FF_CMP_SAD 0
#define FF_CMP_SSE 1
#define FF_CMP_SATD 2
#define FF_CMP_DCT 3
#define FF_CMP_PSNR 4
#define FF_CMP_BIT 5
#define FF_CMP_RD 6
#define FF_CMP_ZERO 7
#define FF_CMP_VSAD 8
#define FF_CMP_VSSE 9
#define FF_CMP_NSSE 10
#define FF_CMP_W53 11
#define FF_CMP_W97 12
#define FF_CMP_DCTMAX 13
#define FF_CMP_DCT264 14
#define FF_CMP_MEDIAN_SAD 15
#define FF_CMP_CHROMA 256
/**
* ME diamond size & shape
* - encoding: Set by user.
* - decoding: unused
*/
int dia_size;
/**
* amount of previous MV predictors (2a+1 x 2a+1 square)
* - encoding: Set by user.
* - decoding: unused
*/
int last_predictor_count;
/**
* motion estimation prepass comparison function
* - encoding: Set by user.
* - decoding: unused
*/
int me_pre_cmp;
/**
* ME prepass diamond size & shape
* - encoding: Set by user.
* - decoding: unused
*/
int pre_dia_size;
/**
* subpel ME quality
* - encoding: Set by user.
* - decoding: unused
*/
int me_subpel_quality;
/**
* maximum motion estimation search range in subpel units
* If 0 then no limit.
*
* - encoding: Set by user.
* - decoding: unused
*/
int me_range;
/**
* slice flags
* - encoding: unused
* - decoding: Set by user.
*/
int slice_flags;
#define SLICE_FLAG_CODED_ORDER 0x0001 ///< draw_horiz_band() is called in coded order instead of display
#define SLICE_FLAG_ALLOW_FIELD 0x0002 ///< allow draw_horiz_band() with field slices (MPEG-2 field pics)
#define SLICE_FLAG_ALLOW_PLANE 0x0004 ///< allow draw_horiz_band() with 1 component at a time (SVQ1)
/**
* macroblock decision mode
* - encoding: Set by user.
* - decoding: unused
*/
int mb_decision;
#define FF_MB_DECISION_SIMPLE 0 ///< uses mb_cmp
#define FF_MB_DECISION_BITS 1 ///< chooses the one which needs the fewest bits
#define FF_MB_DECISION_RD 2 ///< rate distortion
/**
* custom intra quantization matrix
* Must be allocated with the av_malloc() family of functions, and will be freed in
* avcodec_free_context().
* - encoding: Set/allocated by user, freed by libavcodec. Can be NULL.
* - decoding: Set/allocated/freed by libavcodec.
*/
uint16_t *intra_matrix;
/**
* custom inter quantization matrix
* Must be allocated with the av_malloc() family of functions, and will be freed in
* avcodec_free_context().
* - encoding: Set/allocated by user, freed by libavcodec. Can be NULL.
* - decoding: Set/allocated/freed by libavcodec.
*/
uint16_t *inter_matrix;
/**
* precision of the intra DC coefficient - 8
* - encoding: Set by user.
* - decoding: Set by libavcodec
*/
int intra_dc_precision;
/**
* Number of macroblock rows at the top which are skipped.
* - encoding: unused
* - decoding: Set by user.
*/
int skip_top;
/**
* Number of macroblock rows at the bottom which are skipped.
* - encoding: unused
* - decoding: Set by user.
*/
int skip_bottom;
/**
* minimum MB Lagrange multiplier
* - encoding: Set by user.
* - decoding: unused
*/
int mb_lmin;
/**
* maximum MB Lagrange multiplier
* - encoding: Set by user.
* - decoding: unused
*/
int mb_lmax;
/**
* - encoding: Set by user.
* - decoding: unused
*/
int bidir_refine;
/**
* minimum GOP size
* - encoding: Set by user.
* - decoding: unused
*/
int keyint_min;
/**
* number of reference frames
* - encoding: Set by user.
* - decoding: Set by lavc.
*/
int refs;
/**
* Note: Value depends upon the compare function used for fullpel ME.
* - encoding: Set by user.
* - decoding: unused
*/
int mv0_threshold;
/**
* Chromaticity coordinates of the source primaries.
* - encoding: Set by user
* - decoding: Set by libavcodec
*/
enum AVColorPrimaries color_primaries;
/**
* Color Transfer Characteristic.
* - encoding: Set by user
* - decoding: Set by libavcodec
*/
enum AVColorTransferCharacteristic color_trc;
/**
* YUV colorspace type.
* - encoding: Set by user
* - decoding: Set by libavcodec
*/
enum AVColorSpace colorspace;
/**
* MPEG vs JPEG YUV range.
* - encoding: Set by user
* - decoding: Set by libavcodec
*/
enum AVColorRange color_range;
/**
* This defines the location of chroma samples.
* - encoding: Set by user
* - decoding: Set by libavcodec
*/
enum AVChromaLocation chroma_sample_location;
/**
* Number of slices.
* Indicates number of picture subdivisions. Used for parallelized
* decoding.
* - encoding: Set by user
* - decoding: unused
*/
int slices;
/** Field order
* - encoding: set by libavcodec
* - decoding: Set by user.
*/
enum AVFieldOrder field_order;
/* audio only */
int sample_rate; ///< samples per second
int channels; ///< number of audio channels
/**
* audio sample format
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
enum AVSampleFormat sample_fmt; ///< sample format
/* The following data should not be initialized. */
/**
* Number of samples per channel in an audio frame.
*
* - encoding: set by libavcodec in avcodec_open2(). Each submitted frame
* except the last must contain exactly frame_size samples per channel.
* May be 0 when the codec has AV_CODEC_CAP_VARIABLE_FRAME_SIZE set, then the
* frame size is not restricted.
* - decoding: may be set by some decoders to indicate constant frame size
*/
int frame_size;
/**
* Frame counter, set by libavcodec.
*
* - decoding: total number of frames returned from the decoder so far.
* - encoding: total number of frames passed to the encoder so far.
*
* @note the counter is not incremented if encoding/decoding resulted in
* an error.
*/
int frame_number;
/**
* number of bytes per packet if constant and known or 0
* Used by some WAV based audio codecs.
*/
int block_align;
/**
* Audio cutoff bandwidth (0 means "automatic")
* - encoding: Set by user.
* - decoding: unused
*/
int cutoff;
/**
* Audio channel layout.
* - encoding: set by user.
* - decoding: set by user, may be overwritten by libavcodec.
*/
uint64_t channel_layout;
/**
* Request decoder to use this channel layout if it can (0 for default)
* - encoding: unused
* - decoding: Set by user.
*/
uint64_t request_channel_layout;
/**
* Type of service that the audio stream conveys.
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
enum AVAudioServiceType audio_service_type;
/**
* desired sample format
* - encoding: Not used.
* - decoding: Set by user.
* Decoder will decode to this format if it can.
*/
enum AVSampleFormat request_sample_fmt;
/**
* This callback is called at the beginning of each frame to get data
* buffer(s) for it. There may be one contiguous buffer for all the data or
* there may be a buffer per each data plane or anything in between. What
* this means is, you may set however many entries in buf[] you feel necessary.
* Each buffer must be reference-counted using the AVBuffer API (see description
* of buf[] below).
*
* The following fields will be set in the frame before this callback is
* called:
* - format
* - width, height (video only)
* - sample_rate, channel_layout, nb_samples (audio only)
* Their values may differ from the corresponding values in
* AVCodecContext. This callback must use the frame values, not the codec
* context values, to calculate the required buffer size.
*
* This callback must fill the following fields in the frame:
* - data[]
* - linesize[]
* - extended_data:
* * if the data is planar audio with more than 8 channels, then this
* callback must allocate and fill extended_data to contain all pointers
* to all data planes. data[] must hold as many pointers as it can.
* extended_data must be allocated with av_malloc() and will be freed in
* av_frame_unref().
* * otherwise extended_data must point to data
* - buf[] must contain one or more pointers to AVBufferRef structures. Each of
* the frame's data and extended_data pointers must be contained in these. That
* is, one AVBufferRef for each allocated chunk of memory, not necessarily one
* AVBufferRef per data[] entry. See: av_buffer_create(), av_buffer_alloc(),
* and av_buffer_ref().
* - extended_buf and nb_extended_buf must be allocated with av_malloc() by
* this callback and filled with the extra buffers if there are more
* buffers than buf[] can hold. extended_buf will be freed in
* av_frame_unref().
*
* If AV_CODEC_CAP_DR1 is not set then get_buffer2() must call
* avcodec_default_get_buffer2() instead of providing buffers allocated by
* some other means.
*
* Each data plane must be aligned to the maximum required by the target
* CPU.
*
* @see avcodec_default_get_buffer2()
*
* Video:
*
* If AV_GET_BUFFER_FLAG_REF is set in flags then the frame may be reused
* (read and/or written to if it is writable) later by libavcodec.
*
* avcodec_align_dimensions2() should be used to find the required width and
* height, as they normally need to be rounded up to the next multiple of 16.
*
* Some decoders do not support linesizes changing between frames.
*
* If frame multithreading is used, this callback may be called from a
* different thread, but not from more than one at once. Does not need to be
* reentrant.
*
* @see avcodec_align_dimensions2()
*
* Audio:
*
* Decoders request a buffer of a particular size by setting
* AVFrame.nb_samples prior to calling get_buffer2(). The decoder may,
* however, utilize only part of the buffer by setting AVFrame.nb_samples
* to a smaller value in the output frame.
*
* As a convenience, av_samples_get_buffer_size() and
* av_samples_fill_arrays() in libavutil may be used by custom get_buffer2()
* functions to find the required data size and to fill data pointers and
* linesize. In AVFrame.linesize, only linesize[0] may be set for audio
* since all planes must be the same size.
*
* @see av_samples_get_buffer_size(), av_samples_fill_arrays()
*
* - encoding: unused
* - decoding: Set by libavcodec, user can override.
*/
int (*get_buffer2)(struct AVCodecContext *s, AVFrame *frame, int flags);
/* - encoding parameters */
float qcompress; ///< amount of qscale change between easy & hard scenes (0.0-1.0)
float qblur; ///< amount of qscale smoothing over time (0.0-1.0)
/**
* minimum quantizer
* - encoding: Set by user.
* - decoding: unused
*/
int qmin;
/**
* maximum quantizer
* - encoding: Set by user.
* - decoding: unused
*/
int qmax;
/**
* maximum quantizer difference between frames
* - encoding: Set by user.
* - decoding: unused
*/
int max_qdiff;
/**
* decoder bitstream buffer size
* - encoding: Set by user.
* - decoding: unused
*/
int rc_buffer_size;
/**
* ratecontrol override, see RcOverride
* - encoding: Allocated/set/freed by user.
* - decoding: unused
*/
int rc_override_count;
RcOverride *rc_override;
/**
* maximum bitrate
* - encoding: Set by user.
* - decoding: Set by user, may be overwritten by libavcodec.
*/
int64_t rc_max_rate;
/**
* minimum bitrate
* - encoding: Set by user.
* - decoding: unused
*/
int64_t rc_min_rate;
/**
* Ratecontrol attempt to use, at maximum, of what can be used without an underflow.
* - encoding: Set by user.
* - decoding: unused.
*/
float rc_max_available_vbv_use;
/**
* Ratecontrol attempt to use, at least, times the amount needed to prevent a vbv overflow.
* - encoding: Set by user.
* - decoding: unused.
*/
float rc_min_vbv_overflow_use;
/**
* Number of bits which should be loaded into the rc buffer before decoding starts.
* - encoding: Set by user.
* - decoding: unused
*/
int rc_initial_buffer_occupancy;
/**
* trellis RD quantization
* - encoding: Set by user.
* - decoding: unused
*/
int trellis;
/**
* pass1 encoding statistics output buffer
* - encoding: Set by libavcodec.
* - decoding: unused
*/
char *stats_out;
/**
* pass2 encoding statistics input buffer
* Concatenated stuff from stats_out of pass1 should be placed here.
* - encoding: Allocated/set/freed by user.
* - decoding: unused
*/
char *stats_in;
/**
* Work around bugs in encoders which sometimes cannot be detected automatically.
* - encoding: Set by user
* - decoding: Set by user
*/
int workaround_bugs;
#define FF_BUG_AUTODETECT 1 ///< autodetection
#define FF_BUG_XVID_ILACE 4
#define FF_BUG_UMP4 8
#define FF_BUG_NO_PADDING 16
#define FF_BUG_AMV 32
#define FF_BUG_QPEL_CHROMA 64
#define FF_BUG_STD_QPEL 128
#define FF_BUG_QPEL_CHROMA2 256
#define FF_BUG_DIRECT_BLOCKSIZE 512
#define FF_BUG_EDGE 1024
#define FF_BUG_HPEL_CHROMA 2048
#define FF_BUG_DC_CLIP 4096
#define FF_BUG_MS 8192 ///< Work around various bugs in Microsoft's broken decoders.
#define FF_BUG_TRUNCATED 16384
#define FF_BUG_IEDGE 32768
/**
* strictly follow the standard (MPEG-4, ...).
* - encoding: Set by user.
* - decoding: Set by user.
* Setting this to STRICT or higher means the encoder and decoder will
* generally do stupid things, whereas setting it to unofficial or lower
* will mean the encoder might produce output that is not supported by all
* spec-compliant decoders. Decoders don't differentiate between normal,
* unofficial and experimental (that is, they always try to decode things
* when they can) unless they are explicitly asked to behave stupidly
* (=strictly conform to the specs)
*/
int strict_std_compliance;
#define FF_COMPLIANCE_VERY_STRICT 2 ///< Strictly conform to an older more strict version of the spec or reference software.
#define FF_COMPLIANCE_STRICT 1 ///< Strictly conform to all the things in the spec no matter what consequences.
#define FF_COMPLIANCE_NORMAL 0
#define FF_COMPLIANCE_UNOFFICIAL -1 ///< Allow unofficial extensions
#define FF_COMPLIANCE_EXPERIMENTAL -2 ///< Allow nonstandardized experimental things.
/**
* error concealment flags
* - encoding: unused
* - decoding: Set by user.
*/
int error_concealment;
#define FF_EC_GUESS_MVS 1
#define FF_EC_DEBLOCK 2
#define FF_EC_FAVOR_INTER 256
/**
* debug
* - encoding: Set by user.
* - decoding: Set by user.
*/
int debug;
#define FF_DEBUG_PICT_INFO 1
#define FF_DEBUG_RC 2
#define FF_DEBUG_BITSTREAM 4
#define FF_DEBUG_MB_TYPE 8
#define FF_DEBUG_QP 16
#define FF_DEBUG_DCT_COEFF 0x00000040
#define FF_DEBUG_SKIP 0x00000080
#define FF_DEBUG_STARTCODE 0x00000100
#define FF_DEBUG_ER 0x00000400
#define FF_DEBUG_MMCO 0x00000800
#define FF_DEBUG_BUGS 0x00001000
#define FF_DEBUG_BUFFERS 0x00008000
#define FF_DEBUG_THREADS 0x00010000
#define FF_DEBUG_GREEN_MD 0x00800000
#define FF_DEBUG_NOMC 0x01000000
/**
* Error recognition; may misdetect some more or less valid parts as errors.
* - encoding: Set by user.
* - decoding: Set by user.
*/
int err_recognition;
/**
* Verify checksums embedded in the bitstream (could be of either encoded or
* decoded data, depending on the codec) and print an error message on mismatch.
* If AV_EF_EXPLODE is also set, a mismatching checksum will result in the
* decoder returning an error.
*/
#define AV_EF_CRCCHECK (1<<0)
#define AV_EF_BITSTREAM (1<<1) ///< detect bitstream specification deviations
#define AV_EF_BUFFER (1<<2) ///< detect improper bitstream length
#define AV_EF_EXPLODE (1<<3) ///< abort decoding on minor error detection
#define AV_EF_IGNORE_ERR (1<<15) ///< ignore errors and continue
#define AV_EF_CAREFUL (1<<16) ///< consider things that violate the spec, are fast to calculate and have not been seen in the wild as errors
#define AV_EF_COMPLIANT (1<<17) ///< consider all spec non compliances as errors
#define AV_EF_AGGRESSIVE (1<<18) ///< consider things that a sane encoder should not do as an error
/**
* opaque 64-bit number (generally a PTS) that will be reordered and
* output in AVFrame.reordered_opaque
* - encoding: Set by libavcodec to the reordered_opaque of the input
* frame corresponding to the last returned packet. Only
* supported by encoders with the
* AV_CODEC_CAP_ENCODER_REORDERED_OPAQUE capability.
* - decoding: Set by user.
*/
int64_t reordered_opaque;
/**
* Hardware accelerator in use
* - encoding: unused.
* - decoding: Set by libavcodec
*/
const struct AVHWAccel *hwaccel;
/**
* Hardware accelerator context.
* For some hardware accelerators, a global context needs to be
* provided by the user. In that case, this holds display-dependent
* data FFmpeg cannot instantiate itself. Please refer to the
* FFmpeg HW accelerator documentation to know how to fill this.
* - encoding: unused
* - decoding: Set by user
*/
void *hwaccel_context;
/**
* error
* - encoding: Set by libavcodec if flags & AV_CODEC_FLAG_PSNR.
* - decoding: unused
*/
uint64_t error[AV_NUM_DATA_POINTERS];
/**
* DCT algorithm, see FF_DCT_* below
* - encoding: Set by user.
* - decoding: unused
*/
int dct_algo;
#define FF_DCT_AUTO 0
#define FF_DCT_FASTINT 1
#define FF_DCT_INT 2
#define FF_DCT_MMX 3
#define FF_DCT_ALTIVEC 5
#define FF_DCT_FAAN 6
/**
* IDCT algorithm, see FF_IDCT_* below.
* - encoding: Set by user.
* - decoding: Set by user.
*/
int idct_algo;
#define FF_IDCT_AUTO 0
#define FF_IDCT_INT 1
#define FF_IDCT_SIMPLE 2
#define FF_IDCT_SIMPLEMMX 3
#define FF_IDCT_ARM 7
#define FF_IDCT_ALTIVEC 8
#define FF_IDCT_SIMPLEARM 10
#define FF_IDCT_XVID 14
#define FF_IDCT_SIMPLEARMV5TE 16
#define FF_IDCT_SIMPLEARMV6 17
#define FF_IDCT_FAAN 20
#define FF_IDCT_SIMPLENEON 22
#define FF_IDCT_NONE 24 /* Used by XvMC to extract IDCT coefficients with FF_IDCT_PERM_NONE */
#define FF_IDCT_SIMPLEAUTO 128
/**
* bits per sample/pixel from the demuxer (needed for huffyuv).
* - encoding: Set by libavcodec.
* - decoding: Set by user.
*/
int bits_per_coded_sample;
/**
* Bits per sample/pixel of internal libavcodec pixel/sample format.
* - encoding: set by user.
* - decoding: set by libavcodec.
*/
int bits_per_raw_sample;
/**
* low resolution decoding, 1-> 1/2 size, 2->1/4 size
* - encoding: unused
* - decoding: Set by user.
*/
int lowres;
/**
* thread count
* is used to decide how many independent tasks should be passed to execute()
* - encoding: Set by user.
* - decoding: Set by user.
*/
int thread_count;
/**
* Which multithreading methods to use.
* Use of FF_THREAD_FRAME will increase decoding delay by one frame per thread,
* so clients which cannot provide future frames should not use it.
*
* - encoding: Set by user, otherwise the default is used.
* - decoding: Set by user, otherwise the default is used.
*/
int thread_type;
#define FF_THREAD_FRAME 1 ///< Decode more than one frame at once
#define FF_THREAD_SLICE 2 ///< Decode more than one part of a single frame at once
/**
* Which multithreading methods are in use by the codec.
* - encoding: Set by libavcodec.
* - decoding: Set by libavcodec.
*/
int active_thread_type;
#if FF_API_THREAD_SAFE_CALLBACKS
/**
* Set by the client if its custom get_buffer() callback can be called
* synchronously from another thread, which allows faster multithreaded decoding.
* draw_horiz_band() will be called from other threads regardless of this setting.
* Ignored if the default get_buffer() is used.
* - encoding: Set by user.
* - decoding: Set by user.
*
* @deprecated the custom get_buffer2() callback should always be
* thread-safe. Thread-unsafe get_buffer2() implementations will be
* invalid starting with LIBAVCODEC_VERSION_MAJOR=60; in other words,
* libavcodec will behave as if this field was always set to 1.
* Callers that want to be forward compatible with future libavcodec
* versions should wrap access to this field in
* #if LIBAVCODEC_VERSION_MAJOR < 60
*/
attribute_deprecated
int thread_safe_callbacks;
#endif
/**
* The codec may call this to execute several independent things.
* It will return only after finishing all tasks.
* The user may replace this with some multithreaded implementation,
* the default implementation will execute the parts serially.
* @param count the number of things to execute
* - encoding: Set by libavcodec, user can override.
* - decoding: Set by libavcodec, user can override.
*/
int (*execute)(struct AVCodecContext *c, int (*func)(struct AVCodecContext *c2, void *arg), void *arg2, int *ret, int count, int size);
/**
* The codec may call this to execute several independent things.
* It will return only after finishing all tasks.
* The user may replace this with some multithreaded implementation,
* the default implementation will execute the parts serially.
* Also see avcodec_thread_init and e.g. the --enable-pthread configure option.
* @param c context passed also to func
* @param count the number of things to execute
* @param arg2 argument passed unchanged to func
* @param ret return values of executed functions, must have space for "count" values. May be NULL.
* @param func function that will be called count times, with jobnr from 0 to count-1.
* threadnr will be in the range 0 to c->thread_count-1 < MAX_THREADS and so that no
* two instances of func executing at the same time will have the same threadnr.
* @return always 0 currently, but code should handle a future improvement where when any call to func
* returns < 0 no further calls to func may be done and < 0 is returned.
* - encoding: Set by libavcodec, user can override.
* - decoding: Set by libavcodec, user can override.
*/
int (*execute2)(struct AVCodecContext *c, int (*func)(struct AVCodecContext *c2, void *arg, int jobnr, int threadnr), void *arg2, int *ret, int count);
/**
* noise vs. sse weight for the nsse comparison function
* - encoding: Set by user.
* - decoding: unused
*/
int nsse_weight;
/**
* profile
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
int profile;
#define FF_PROFILE_UNKNOWN -99
#define FF_PROFILE_RESERVED -100
#define FF_PROFILE_AAC_MAIN 0
#define FF_PROFILE_AAC_LOW 1
#define FF_PROFILE_AAC_SSR 2
#define FF_PROFILE_AAC_LTP 3
#define FF_PROFILE_AAC_HE 4
#define FF_PROFILE_AAC_HE_V2 28
#define FF_PROFILE_AAC_LD 22
#define FF_PROFILE_AAC_ELD 38
#define FF_PROFILE_MPEG2_AAC_LOW 128
#define FF_PROFILE_MPEG2_AAC_HE 131
#define FF_PROFILE_DNXHD 0
#define FF_PROFILE_DNXHR_LB 1
#define FF_PROFILE_DNXHR_SQ 2
#define FF_PROFILE_DNXHR_HQ 3
#define FF_PROFILE_DNXHR_HQX 4
#define FF_PROFILE_DNXHR_444 5
#define FF_PROFILE_DTS 20
#define FF_PROFILE_DTS_ES 30
#define FF_PROFILE_DTS_96_24 40
#define FF_PROFILE_DTS_HD_HRA 50
#define FF_PROFILE_DTS_HD_MA 60
#define FF_PROFILE_DTS_EXPRESS 70
#define FF_PROFILE_MPEG2_422 0
#define FF_PROFILE_MPEG2_HIGH 1
#define FF_PROFILE_MPEG2_SS 2
#define FF_PROFILE_MPEG2_SNR_SCALABLE 3
#define FF_PROFILE_MPEG2_MAIN 4
#define FF_PROFILE_MPEG2_SIMPLE 5
#define FF_PROFILE_H264_CONSTRAINED (1<<9) // 8+1; constraint_set1_flag
#define FF_PROFILE_H264_INTRA (1<<11) // 8+3; constraint_set3_flag
#define FF_PROFILE_H264_BASELINE 66
#define FF_PROFILE_H264_CONSTRAINED_BASELINE (66|FF_PROFILE_H264_CONSTRAINED)
#define FF_PROFILE_H264_MAIN 77
#define FF_PROFILE_H264_EXTENDED 88
#define FF_PROFILE_H264_HIGH 100
#define FF_PROFILE_H264_HIGH_10 110
#define FF_PROFILE_H264_HIGH_10_INTRA (110|FF_PROFILE_H264_INTRA)
#define FF_PROFILE_H264_MULTIVIEW_HIGH 118
#define FF_PROFILE_H264_HIGH_422 122
#define FF_PROFILE_H264_HIGH_422_INTRA (122|FF_PROFILE_H264_INTRA)
#define FF_PROFILE_H264_STEREO_HIGH 128
#define FF_PROFILE_H264_HIGH_444 144
#define FF_PROFILE_H264_HIGH_444_PREDICTIVE 244
#define FF_PROFILE_H264_HIGH_444_INTRA (244|FF_PROFILE_H264_INTRA)
#define FF_PROFILE_H264_CAVLC_444 44
#define FF_PROFILE_VC1_SIMPLE 0
#define FF_PROFILE_VC1_MAIN 1
#define FF_PROFILE_VC1_COMPLEX 2
#define FF_PROFILE_VC1_ADVANCED 3
#define FF_PROFILE_MPEG4_SIMPLE 0
#define FF_PROFILE_MPEG4_SIMPLE_SCALABLE 1
#define FF_PROFILE_MPEG4_CORE 2
#define FF_PROFILE_MPEG4_MAIN 3
#define FF_PROFILE_MPEG4_N_BIT 4
#define FF_PROFILE_MPEG4_SCALABLE_TEXTURE 5
#define FF_PROFILE_MPEG4_SIMPLE_FACE_ANIMATION 6
#define FF_PROFILE_MPEG4_BASIC_ANIMATED_TEXTURE 7
#define FF_PROFILE_MPEG4_HYBRID 8
#define FF_PROFILE_MPEG4_ADVANCED_REAL_TIME 9
#define FF_PROFILE_MPEG4_CORE_SCALABLE 10
#define FF_PROFILE_MPEG4_ADVANCED_CODING 11
#define FF_PROFILE_MPEG4_ADVANCED_CORE 12
#define FF_PROFILE_MPEG4_ADVANCED_SCALABLE_TEXTURE 13
#define FF_PROFILE_MPEG4_SIMPLE_STUDIO 14
#define FF_PROFILE_MPEG4_ADVANCED_SIMPLE 15
#define FF_PROFILE_JPEG2000_CSTREAM_RESTRICTION_0 1
#define FF_PROFILE_JPEG2000_CSTREAM_RESTRICTION_1 2
#define FF_PROFILE_JPEG2000_CSTREAM_NO_RESTRICTION 32768
#define FF_PROFILE_JPEG2000_DCINEMA_2K 3
#define FF_PROFILE_JPEG2000_DCINEMA_4K 4
#define FF_PROFILE_VP9_0 0
#define FF_PROFILE_VP9_1 1
#define FF_PROFILE_VP9_2 2
#define FF_PROFILE_VP9_3 3
#define FF_PROFILE_HEVC_MAIN 1
#define FF_PROFILE_HEVC_MAIN_10 2
#define FF_PROFILE_HEVC_MAIN_STILL_PICTURE 3
#define FF_PROFILE_HEVC_REXT 4
#define FF_PROFILE_VVC_MAIN_10 1
#define FF_PROFILE_VVC_MAIN_10_444 33
#define FF_PROFILE_AV1_MAIN 0
#define FF_PROFILE_AV1_HIGH 1
#define FF_PROFILE_AV1_PROFESSIONAL 2
#define FF_PROFILE_MJPEG_HUFFMAN_BASELINE_DCT 0xc0
#define FF_PROFILE_MJPEG_HUFFMAN_EXTENDED_SEQUENTIAL_DCT 0xc1
#define FF_PROFILE_MJPEG_HUFFMAN_PROGRESSIVE_DCT 0xc2
#define FF_PROFILE_MJPEG_HUFFMAN_LOSSLESS 0xc3
#define FF_PROFILE_MJPEG_JPEG_LS 0xf7
#define FF_PROFILE_SBC_MSBC 1
#define FF_PROFILE_PRORES_PROXY 0
#define FF_PROFILE_PRORES_LT 1
#define FF_PROFILE_PRORES_STANDARD 2
#define FF_PROFILE_PRORES_HQ 3
#define FF_PROFILE_PRORES_4444 4
#define FF_PROFILE_PRORES_XQ 5
#define FF_PROFILE_ARIB_PROFILE_A 0
#define FF_PROFILE_ARIB_PROFILE_C 1
#define FF_PROFILE_KLVA_SYNC 0
#define FF_PROFILE_KLVA_ASYNC 1
/**
* level
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
int level;
#define FF_LEVEL_UNKNOWN -99
/**
* Skip loop filtering for selected frames.
* - encoding: unused
* - decoding: Set by user.
*/
enum AVDiscard skip_loop_filter;
/**
* Skip IDCT/dequantization for selected frames.
* - encoding: unused
* - decoding: Set by user.
*/
enum AVDiscard skip_idct;
/**
* Skip decoding for selected frames.
* - encoding: unused
* - decoding: Set by user.
*/
enum AVDiscard skip_frame;
/**
* Header containing style information for text subtitles.
* For SUBTITLE_ASS subtitle type, it should contain the whole ASS
* [Script Info] and [V4+ Styles] section, plus the [Events] line and
* the Format line following. It shouldn't include any Dialogue line.
* - encoding: Set/allocated/freed by user (before avcodec_open2())
* - decoding: Set/allocated/freed by libavcodec (by avcodec_open2())
*/
uint8_t *subtitle_header;
int subtitle_header_size;
/**
* Audio only. The number of "priming" samples (padding) inserted by the
* encoder at the beginning of the audio. I.e. this number of leading
* decoded samples must be discarded by the caller to get the original audio
* without leading padding.
*
* - decoding: unused
* - encoding: Set by libavcodec. The timestamps on the output packets are
* adjusted by the encoder so that they always refer to the
* first sample of the data actually contained in the packet,
* including any added padding. E.g. if the timebase is
* 1/samplerate and the timestamp of the first input sample is
* 0, the timestamp of the first output packet will be
* -initial_padding.
*/
int initial_padding;
/**
* - decoding: For codecs that store a framerate value in the compressed
* bitstream, the decoder may export it here. { 0, 1} when
* unknown.
* - encoding: May be used to signal the framerate of CFR content to an
* encoder.
*/
AVRational framerate;
/**
* Nominal unaccelerated pixel format, see AV_PIX_FMT_xxx.
* - encoding: unused.
* - decoding: Set by libavcodec before calling get_format()
*/
enum AVPixelFormat sw_pix_fmt;
/**
* Timebase in which pkt_dts/pts and AVPacket.dts/pts are.
* - encoding unused.
* - decoding set by user.
*/
AVRational pkt_timebase;
/**
* AVCodecDescriptor
* - encoding: unused.
* - decoding: set by libavcodec.
*/
const AVCodecDescriptor *codec_descriptor;
/**
* Current statistics for PTS correction.
* - decoding: maintained and used by libavcodec, not intended to be used by user apps
* - encoding: unused
*/
int64_t pts_correction_num_faulty_pts; /// Number of incorrect PTS values so far
int64_t pts_correction_num_faulty_dts; /// Number of incorrect DTS values so far
int64_t pts_correction_last_pts; /// PTS of the last frame
int64_t pts_correction_last_dts; /// DTS of the last frame
/**
* Character encoding of the input subtitles file.
* - decoding: set by user
* - encoding: unused
*/
char *sub_charenc;
/**
* Subtitles character encoding mode. Formats or codecs might be adjusting
* this setting (if they are doing the conversion themselves for instance).
* - decoding: set by libavcodec
* - encoding: unused
*/
int sub_charenc_mode;
#define FF_SUB_CHARENC_MODE_DO_NOTHING -1 ///< do nothing (demuxer outputs a stream supposed to be already in UTF-8, or the codec is bitmap for instance)
#define FF_SUB_CHARENC_MODE_AUTOMATIC 0 ///< libavcodec will select the mode itself
#define FF_SUB_CHARENC_MODE_PRE_DECODER 1 ///< the AVPacket data needs to be recoded to UTF-8 before being fed to the decoder, requires iconv
#define FF_SUB_CHARENC_MODE_IGNORE 2 ///< neither convert the subtitles, nor check them for valid UTF-8
/**
* Skip processing alpha if supported by codec.
* Note that if the format uses pre-multiplied alpha (common with VP6,
* and recommended due to better video quality/compression)
* the image will look as if alpha-blended onto a black background.
* However for formats that do not use pre-multiplied alpha
* there might be serious artefacts (though e.g. libswscale currently
* assumes pre-multiplied alpha anyway).
*
* - decoding: set by user
* - encoding: unused
*/
int skip_alpha;
/**
* Number of samples to skip after a discontinuity
* - decoding: unused
* - encoding: set by libavcodec
*/
int seek_preroll;
#if FF_API_DEBUG_MV
/**
* @deprecated unused
*/
attribute_deprecated
int debug_mv;
#define FF_DEBUG_VIS_MV_P_FOR 0x00000001 //visualize forward predicted MVs of P frames
#define FF_DEBUG_VIS_MV_B_FOR 0x00000002 //visualize forward predicted MVs of B frames
#define FF_DEBUG_VIS_MV_B_BACK 0x00000004 //visualize backward predicted MVs of B frames
#endif
/**
* custom intra quantization matrix
* - encoding: Set by user, can be NULL.
* - decoding: unused.
*/
uint16_t *chroma_intra_matrix;
/**
* dump format separator.
* can be ", " or "\n " or anything else
* - encoding: Set by user.
* - decoding: Set by user.
*/
uint8_t *dump_separator;
/**
* ',' separated list of allowed decoders.
* If NULL then all are allowed
* - encoding: unused
* - decoding: set by user
*/
char *codec_whitelist;
/**
* Properties of the stream that gets decoded
* - encoding: unused
* - decoding: set by libavcodec
*/
unsigned properties;
#define FF_CODEC_PROPERTY_LOSSLESS 0x00000001
#define FF_CODEC_PROPERTY_CLOSED_CAPTIONS 0x00000002
#define FF_CODEC_PROPERTY_FILM_GRAIN 0x00000004
/**
* Additional data associated with the entire coded stream.
*
* - decoding: unused
* - encoding: may be set by libavcodec after avcodec_open2().
*/
AVPacketSideData *coded_side_data;
int nb_coded_side_data;
/**
* A reference to the AVHWFramesContext describing the input (for encoding)
* or output (decoding) frames. The reference is set by the caller and
* afterwards owned (and freed) by libavcodec - it should never be read by
* the caller after being set.
*
* - decoding: This field should be set by the caller from the get_format()
* callback. The previous reference (if any) will always be
* unreffed by libavcodec before the get_format() call.
*
* If the default get_buffer2() is used with a hwaccel pixel
* format, then this AVHWFramesContext will be used for
* allocating the frame buffers.
*
* - encoding: For hardware encoders configured to use a hwaccel pixel
* format, this field should be set by the caller to a reference
* to the AVHWFramesContext describing input frames.
* AVHWFramesContext.format must be equal to
* AVCodecContext.pix_fmt.
*
* This field should be set before avcodec_open2() is called.
*/
AVBufferRef *hw_frames_ctx;
#if FF_API_SUB_TEXT_FORMAT
/**
* @deprecated unused
*/
attribute_deprecated
int sub_text_format;
#define FF_SUB_TEXT_FMT_ASS 0
#endif
/**
* Audio only. The amount of padding (in samples) appended by the encoder to
* the end of the audio. I.e. this number of decoded samples must be
* discarded by the caller from the end of the stream to get the original
* audio without any trailing padding.
*
* - decoding: unused
* - encoding: unused
*/
int trailing_padding;
/**
* The number of pixels per image to maximally accept.
*
* - decoding: set by user
* - encoding: set by user
*/
int64_t max_pixels;
/**
* A reference to the AVHWDeviceContext describing the device which will
* be used by a hardware encoder/decoder. The reference is set by the
* caller and afterwards owned (and freed) by libavcodec.
*
* This should be used if either the codec device does not require
* hardware frames or any that are used are to be allocated internally by
* libavcodec. If the user wishes to supply any of the frames used as
* encoder input or decoder output then hw_frames_ctx should be used
* instead. When hw_frames_ctx is set in get_format() for a decoder, this
* field will be ignored while decoding the associated stream segment, but
* may again be used on a following one after another get_format() call.
*
* For both encoders and decoders this field should be set before
* avcodec_open2() is called and must not be written to thereafter.
*
* Note that some decoders may require this field to be set initially in
* order to support hw_frames_ctx at all - in that case, all frames
* contexts used must be created on the same device.
*/
AVBufferRef *hw_device_ctx;
/**
* Bit set of AV_HWACCEL_FLAG_* flags, which affect hardware accelerated
* decoding (if active).
* - encoding: unused
* - decoding: Set by user (either before avcodec_open2(), or in the
* AVCodecContext.get_format callback)
*/
int hwaccel_flags;
/**
* Video decoding only. Certain video codecs support cropping, meaning that
* only a sub-rectangle of the decoded frame is intended for display. This
* option controls how cropping is handled by libavcodec.
*
* When set to 1 (the default), libavcodec will apply cropping internally.
* I.e. it will modify the output frame width/height fields and offset the
* data pointers (only by as much as possible while preserving alignment, or
* by the full amount if the AV_CODEC_FLAG_UNALIGNED flag is set) so that
* the frames output by the decoder refer only to the cropped area. The
* crop_* fields of the output frames will be zero.
*
* When set to 0, the width/height fields of the output frames will be set
* to the coded dimensions and the crop_* fields will describe the cropping
* rectangle. Applying the cropping is left to the caller.
*
* @warning When hardware acceleration with opaque output frames is used,
* libavcodec is unable to apply cropping from the top/left border.
*
* @note when this option is set to zero, the width/height fields of the
* AVCodecContext and output AVFrames have different meanings. The codec
* context fields store display dimensions (with the coded dimensions in
* coded_width/height), while the frame fields store the coded dimensions
* (with the display dimensions being determined by the crop_* fields).
*/
int apply_cropping;
/*
* Video decoding only. Sets the number of extra hardware frames which
* the decoder will allocate for use by the caller. This must be set
* before avcodec_open2() is called.
*
* Some hardware decoders require all frames that they will use for
* output to be defined in advance before decoding starts. For such
* decoders, the hardware frame pool must therefore be of a fixed size.
* The extra frames set here are on top of any number that the decoder
* needs internally in order to operate normally (for example, frames
* used as reference pictures).
*/
int extra_hw_frames;
/**
* The percentage of damaged samples to discard a frame.
*
* - decoding: set by user
* - encoding: unused
*/
int discard_damaged_percentage;
/**
* The number of samples per frame to maximally accept.
*
* - decoding: set by user
* - encoding: set by user
*/
int64_t max_samples;
/**
* Bit set of AV_CODEC_EXPORT_DATA_* flags, which affects the kind of
* metadata exported in frame, packet, or coded stream side data by
* decoders and encoders.
*
* - decoding: set by user
* - encoding: set by user
*/
int export_side_data;
/**
* This callback is called at the beginning of each packet to get a data
* buffer for it.
*
* The following field will be set in the packet before this callback is
* called:
* - size
* This callback must use the above value to calculate the required buffer size,
* which must padded by at least AV_INPUT_BUFFER_PADDING_SIZE bytes.
*
* In some specific cases, the encoder may not use the entire buffer allocated by this
* callback. This will be reflected in the size value in the packet once returned by
* avcodec_receive_packet().
*
* This callback must fill the following fields in the packet:
* - data: alignment requirements for AVPacket apply, if any. Some architectures and
* encoders may benefit from having aligned data.
* - buf: must contain a pointer to an AVBufferRef structure. The packet's
* data pointer must be contained in it. See: av_buffer_create(), av_buffer_alloc(),
* and av_buffer_ref().
*
* If AV_CODEC_CAP_DR1 is not set then get_encode_buffer() must call
* avcodec_default_get_encode_buffer() instead of providing a buffer allocated by
* some other means.
*
* The flags field may contain a combination of AV_GET_ENCODE_BUFFER_FLAG_ flags.
* They may be used for example to hint what use the buffer may get after being
* created.
* Implementations of this callback may ignore flags they don't understand.
* If AV_GET_ENCODE_BUFFER_FLAG_REF is set in flags then the packet may be reused
* (read and/or written to if it is writable) later by libavcodec.
*
* This callback must be thread-safe, as when frame threading is used, it may
* be called from multiple threads simultaneously.
*
* @see avcodec_default_get_encode_buffer()
*
* - encoding: Set by libavcodec, user can override.
* - decoding: unused
*/
int (*get_encode_buffer)(struct AVCodecContext *s, AVPacket *pkt, int flags);
} AVCodecContext;
AVCodecInternal结构体是codec内部数据的一个结构体
typedef struct EncodeSimpleContext {
AVFrame *in_frame;
} EncodeSimpleContext;
typedef struct AVCodecInternal {
/**
* When using frame-threaded decoding, this field is set for the first
* worker thread (e.g. to decode extradata just once).
*/
int is_copy;
/**
* An audio frame with less than required samples has been submitted and
* padded with silence. Reject all subsequent frames.
*/
int last_audio_frame;
AVBufferRef *pool;
void *thread_ctx;
/**
* This packet is used to hold the packet given to decoders
* implementing the .decode API; it is unused by the generic
* code for decoders implementing the .receive_frame API and
* may be freely used (but not freed) by them with the caveat
* that the packet will be unreferenced generically in
* avcodec_flush_buffers().
*/
//这个in_pkt主要用来hold送入解码的pkt
AVPacket *in_pkt;
AVBSFContext *bsf;
/**
* Properties (timestamps+side data) extracted from the last packet passed
* for decoding.
*/
AVPacket *last_pkt_props;
AVFifoBuffer *pkt_props;
/**
* temporary buffer used for encoders to store their bitstream
*/
//临时buf
uint8_t *byte_buffer;
unsigned int byte_buffer_size;
/**
* This is set to AV_PKT_FLAG_KEY for encoders that encode intra-only
* formats (i.e. whose codec descriptor has AV_CODEC_PROP_INTRA_ONLY set).
* This is used to set said flag generically for said encoders.
*/
int intra_only_flag;
void *frame_thread_encoder;
EncodeSimpleContext es;
/**
* If this is set, then AVCodec->close (if existing) needs to be called
* for the parent AVCodecContext.
*/
int needs_close;
/**
* Number of audio samples to skip at the start of the next decoded frame
*/
int skip_samples;
/**
* hwaccel-specific private data
*/
void *hwaccel_priv_data;
/**
* checks API usage: after codec draining, flush is required to resume operation
*/
int draining;
/**
* buffers for using new encode/decode API through legacy API
*/
AVPacket *buffer_pkt;
AVFrame *buffer_frame;
int draining_done;
int showed_multi_packet_warning;
int skip_samples_multiplier;
/* to prevent infinite loop on errors when draining */
int nb_draining_errors;
/* used when avctx flag AV_CODEC_FLAG_DROPCHANGED is set */
int changed_frames_dropped;
int initial_format;
int initial_width, initial_height;
int initial_sample_rate;
int initial_channels;
uint64_t initial_channel_layout;
} AVCodecInternal;
看完了上面两个非常重要的结构体定义,接下来看代码
/**
* Allocate an AVCodecContext and set its fields to default values. The
* resulting struct should be freed with avcodec_free_context().
*
* @param codec if non-NULL, allocate private data and initialize defaults
* for the given codec. It is illegal to then call avcodec_open2()
* with a different codec.
* If NULL, then the codec-specific defaults won't be initialized,
* which may result in suboptimal default settings (this is
* important mainly for encoders, e.g. libx264).
*
* @return An AVCodecContext filled with default values or NULL on failure.
*/
AVCodecContext *avcodec_alloc_context3(const AVCodec *codec);
AVCodecContext *avcodec_alloc_context3(const AVCodec *codec)
{
AVCodecContext *avctx= av_malloc(sizeof(AVCodecContext));
if (!avctx)
return NULL;
//设置默认值
if (init_context_defaults(avctx, codec) < 0) {
av_free(avctx);
return NULL;
}
return avctx;
}
static const AVClass av_codec_context_class = {
.class_name = "AVCodecContext",
.item_name = context_to_name,
.option = avcodec_options,
.version = LIBAVUTIL_VERSION_INT,
.log_level_offset_offset = offsetof(AVCodecContext, log_level_offset),
.child_next = codec_child_next,
.child_class_iterate = codec_child_class_iterate,
.category = AV_CLASS_CATEGORY_ENCODER,
.get_category = get_category,
};
//下面是初始化AVCodecContext ,设置一些默认值
static int init_context_defaults(AVCodecContext *s, const AVCodec *codec)
{
int flags=0;
//这里清空
memset(s, 0, sizeof(AVCodecContext));
s->av_class = &av_codec_context_class;
s->codec_type = codec ? codec->type : AVMEDIA_TYPE_UNKNOWN;
if (codec) {
s->codec = codec;
s->codec_id = codec->id;
}
if(s->codec_type == AVMEDIA_TYPE_AUDIO)
flags= AV_OPT_FLAG_AUDIO_PARAM;
else if(s->codec_type == AVMEDIA_TYPE_VIDEO)
flags= AV_OPT_FLAG_VIDEO_PARAM;
else if(s->codec_type == AVMEDIA_TYPE_SUBTITLE)
flags= AV_OPT_FLAG_SUBTITLE_PARAM;
av_opt_set_defaults2(s, flags, flags);
//从这里开始设置默认值
s->time_base = (AVRational){0,1};
s->framerate = (AVRational){ 0, 1 };
s->pkt_timebase = (AVRational){ 0, 1 };
//这是几个默认的回调函数
s->get_buffer2 = avcodec_default_get_buffer2;
s->get_format = avcodec_default_get_format;
s->get_encode_buffer = avcodec_default_get_encode_buffer;
s->execute = avcodec_default_execute;
s->execute2 = avcodec_default_execute2;
s->sample_aspect_ratio = (AVRational){0,1};
s->pix_fmt = AV_PIX_FMT_NONE;
s->sw_pix_fmt = AV_PIX_FMT_NONE;
s->sample_fmt = AV_SAMPLE_FMT_NONE;
s->reordered_opaque = AV_NOPTS_VALUE;
//下面这一段是为了设置AVCodecContext Option选项的代码,保证可以通过Option来设置AVCodecContext 内的参数
//如果像仔细看,可以看AVOption.c这个文件
if(codec && codec->priv_data_size){
s->priv_data = av_mallocz(codec->priv_data_size);
if (!s->priv_data)
return AVERROR(ENOMEM);
if(codec->priv_class){
*(const AVClass**)s->priv_data = codec->priv_class;
av_opt_set_defaults(s->priv_data);
}
}
//继续设置一些默认值
if (codec && codec->defaults) {
int ret;
//struct AVCodecDefault {
// const uint8_t *key;
// const uint8_t *value;
// };
const AVCodecDefault *d = codec->defaults;
while (d->key) {
ret = av_opt_set(s, d->key, d->value, 0);
av_assert0(ret >= 0);
d++;
}
}
return 0;
}
*avcodec_open2(dec_ctx, dec, NULL);
上面的代码其实非常简单,接下看稍微难一点的。
//第三个参数可以传递option
int attribute_align_arg avcodec_open2(AVCodecContext *avctx, const AVCodec *codec, AVDictionary **options)
{
int ret = 0;
AVCodecInternal *avci;
//int avcodec_is_open(AVCodecContext *s) return !!s->internal;
if (avcodec_is_open(avctx))
return 0;
if (!codec && !avctx->codec) {
av_log(avctx, AV_LOG_ERROR, "No codec provided to avcodec_open2()\n");
return AVERROR(EINVAL);
}
if (codec && avctx->codec && codec != avctx->codec) {
av_log(avctx, AV_LOG_ERROR, "This AVCodecContext was allocated for %s, "
"but %s passed to avcodec_open2()\n", avctx->codec->name, codec->name);
return AVERROR(EINVAL);
}
if (!codec)
codec = avctx->codec;
if ((avctx->codec_type == AVMEDIA_TYPE_UNKNOWN || avctx->codec_type == codec->type) &&
avctx->codec_id == AV_CODEC_ID_NONE) {
avctx->codec_type = codec->type;
avctx->codec_id = codec->id;
}
if (avctx->codec_id != codec->id || (avctx->codec_type != codec->type &&
avctx->codec_type != AVMEDIA_TYPE_ATTACHMENT)) {
av_log(avctx, AV_LOG_ERROR, "Codec type or id mismatches\n");
return AVERROR(EINVAL);
}
//这里简单赋值,还记得这个avctx->codec定义吗?
avctx->codec = codec;
if (avctx->extradata_size < 0 || avctx->extradata_size >= FF_MAX_EXTRADATA_SIZE)
return AVERROR(EINVAL);
lock_avcodec(codec);
//分配空间,这个是上面提到的解码中间用到的解耦固体
avci = av_mallocz(sizeof(*avci));
if (!avci) {
ret = AVERROR(ENOMEM);
goto end;
}
//这个结构体这里完成复制
avctx->internal = avci;
avci->buffer_frame = av_frame_alloc();
avci->buffer_pkt = av_packet_alloc();
avci->es.in_frame = av_frame_alloc();
avci->in_pkt = av_packet_alloc();
avci->last_pkt_props = av_packet_alloc();
avci->pkt_props = av_fifo_alloc(sizeof(*avci->last_pkt_props));
if (!avci->buffer_frame || !avci->buffer_pkt ||
!avci->es.in_frame || !avci->in_pkt ||
!avci->last_pkt_props || !avci->pkt_props) {
ret = AVERROR(ENOMEM);
goto free_and_end;
}
avci->skip_samples_multiplier = 1;
//下面这一块都是option system的相关代码
if (codec->priv_data_size > 0) {
//如果为null,还记得吗,前面已经设置过一次了,这次来个二次保证
if (!avctx->priv_data) {
avctx->priv_data = av_mallocz(codec->priv_data_size);
if (!avctx->priv_data) {
ret = AVERROR(ENOMEM);
goto free_and_end;
}
if (codec->priv_class) {
//codec的赋值给avctx
*(const AVClass **)avctx->priv_data = codec->priv_class;
av_opt_set_defaults(avctx->priv_data);
}
}
if (codec->priv_class && (ret = av_opt_set_dict(avctx->priv_data, options)) < 0)
goto free_and_end;
} else {
avctx->priv_data = NULL;
}
//通过option为avctx设置参数
if ((ret = av_opt_set_dict(avctx, options)) < 0)
goto free_and_end;
//检查白名单
if (avctx->codec_whitelist && av_match_list(codec->name, avctx->codec_whitelist, ',') <= 0) {
av_log(avctx, AV_LOG_ERROR, "Codec (%s) not on whitelist \'%s\'\n", codec->name, avctx->codec_whitelist);
ret = AVERROR(EINVAL);
goto free_and_end;
}
//ff_set_dimensions中调用了关键的尺寸检测函数,这个在后面介绍,有时候我们使用ffmpeg发现某个尺寸无效时,就是这个地方的问题
//暂时可以不看,你大概了解到这里时检查编解码尺寸的一个地方,后面慢慢来分析
// only call ff_set_dimensions() for non H.264/VP6F/DXV codecs so as not to overwrite previously setup dimensions
if (!(avctx->coded_width && avctx->coded_height && avctx->width && avctx->height &&
(avctx->codec_id == AV_CODEC_ID_H264 || avctx->codec_id == AV_CODEC_ID_VP6F || avctx->codec_id == AV_CODEC_ID_DXV))) {
if (avctx->coded_width && avctx->coded_height)
ret = ff_set_dimensions(avctx, avctx->coded_width, avctx->coded_height);
else if (avctx->width && avctx->height)
ret = ff_set_dimensions(avctx, avctx->width, avctx->height);
if (ret < 0)
goto free_and_end;
}
//检查尺寸,有些尺寸是不合适的,会直接返回
if ((avctx->coded_width || avctx->coded_height || avctx->width || avctx->height)
&& ( av_image_check_size2(avctx->coded_width, avctx->coded_height, avctx->max_pixels, AV_PIX_FMT_NONE, 0, avctx) < 0
|| av_image_check_size2(avctx->width, avctx->height, avctx->max_pixels, AV_PIX_FMT_NONE, 0, avctx) < 0)) {
av_log(avctx, AV_LOG_WARNING, "Ignoring invalid width/height values\n");
ff_set_dimensions(avctx, 0, 0);
}
if (avctx->width > 0 && avctx->height > 0) {
if (av_image_check_sar(avctx->width, avctx->height,
avctx->sample_aspect_ratio) < 0) {
av_log(avctx, AV_LOG_WARNING, "ignoring invalid SAR: %u/%u\n",
avctx->sample_aspect_ratio.num,
avctx->sample_aspect_ratio.den);
avctx->sample_aspect_ratio = (AVRational){ 0, 1 };
}
}
if (avctx->channels > FF_SANE_NB_CHANNELS || avctx->channels < 0) {
av_log(avctx, AV_LOG_ERROR, "Too many or invalid channels: %d\n", avctx->channels);
ret = AVERROR(EINVAL);
goto free_and_end;
}
if (avctx->sample_rate < 0) {
av_log(avctx, AV_LOG_ERROR, "Invalid sample rate: %d\n", avctx->sample_rate);
ret = AVERROR(EINVAL);
goto free_and_end;
}
if (avctx->block_align < 0) {
av_log(avctx, AV_LOG_ERROR, "Invalid block align: %d\n", avctx->block_align);
ret = AVERROR(EINVAL);
goto free_and_end;
}
avctx->frame_number = 0;
avctx->codec_descriptor = avcodec_descriptor_get(avctx->codec_id);
if ((avctx->codec->capabilities & AV_CODEC_CAP_EXPERIMENTAL) &&
avctx->strict_std_compliance > FF_COMPLIANCE_EXPERIMENTAL) {
const char *codec_string = av_codec_is_encoder(codec) ? "encoder" : "decoder";
const AVCodec *codec2;
av_log(avctx, AV_LOG_ERROR,
"The %s '%s' is experimental but experimental codecs are not enabled, "
"add '-strict %d' if you want to use it.\n",
codec_string, codec->name, FF_COMPLIANCE_EXPERIMENTAL);
codec2 = av_codec_is_encoder(codec) ? avcodec_find_encoder(codec->id) : avcodec_find_decoder(codec->id);
if (!(codec2->capabilities & AV_CODEC_CAP_EXPERIMENTAL))
av_log(avctx, AV_LOG_ERROR, "Alternatively use the non experimental %s '%s'.\n",
codec_string, codec2->name);
ret = AVERROR_EXPERIMENTAL;
goto free_and_end;
}
if (avctx->codec_type == AVMEDIA_TYPE_AUDIO &&
(!avctx->time_base.num || !avctx->time_base.den)) {
avctx->time_base.num = 1;
avctx->time_base.den = avctx->sample_rate;
}
//这里进行预初始化,会初始化bsf,av_bsf_init(avci->bsf)
if (av_codec_is_encoder(avctx->codec))
ret = ff_encode_preinit(avctx);
else
ret = ff_decode_preinit(avctx);
if (ret < 0)
goto free_and_end;
if (!HAVE_THREADS)
av_log(avctx, AV_LOG_WARNING, "Warning: not compiled with thread support, using thread emulation\n");
if (CONFIG_FRAME_THREAD_ENCODER && av_codec_is_encoder(avctx->codec)) {
unlock_avcodec(codec); //we will instantiate a few encoders thus kick the counter to prevent false detection of a problem
ret = ff_frame_thread_encoder_init(avctx);
lock_avcodec(codec);
if (ret < 0)
goto free_and_end;
}
if (HAVE_THREADS && !(avci->frame_thread_encoder && (avctx->active_thread_type&FF_THREAD_FRAME))) {
ret = ff_thread_init(avctx);
if (ret < 0) {
goto free_and_end;
}
}
if (!HAVE_THREADS && !(codec->caps_internal & FF_CODEC_CAP_AUTO_THREADS))
avctx->thread_count = 1;
if (!(avctx->active_thread_type & FF_THREAD_FRAME) || avci->frame_thread_encoder) {
if (avctx->codec->init) {
//这里调用init函数
ret = avctx->codec->init(avctx);
if (ret < 0) {
avci->needs_close = avctx->codec->caps_internal & FF_CODEC_CAP_INIT_CLEANUP;
goto free_and_end;
}
}
avci->needs_close = 1;
}
ret=0;
if (av_codec_is_decoder(avctx->codec)) {
if (!avctx->bit_rate)
avctx->bit_rate = get_bit_rate(avctx);
/* validate channel layout from the decoder */
if (avctx->channel_layout) {
int channels = av_get_channel_layout_nb_channels(avctx->channel_layout);
if (!avctx->channels)
avctx->channels = channels;
else if (channels != avctx->channels) {
char buf[512];
av_get_channel_layout_string(buf, sizeof(buf), -1, avctx->channel_layout);
av_log(avctx, AV_LOG_WARNING,
"Channel layout '%s' with %d channels does not match specified number of channels %d: "
"ignoring specified channel layout\n",
buf, channels, avctx->channels);
avctx->channel_layout = 0;
}
}
if (avctx->channels && avctx->channels < 0 ||
avctx->channels > FF_SANE_NB_CHANNELS) {
ret = AVERROR(EINVAL);
goto free_and_end;
}
if (avctx->bits_per_coded_sample < 0) {
ret = AVERROR(EINVAL);
goto free_and_end;
}
#if FF_API_AVCTX_TIMEBASE
if (avctx->framerate.num > 0 && avctx->framerate.den > 0)
avctx->time_base = av_inv_q(av_mul_q(avctx->framerate, (AVRational){avctx->ticks_per_frame, 1}));
#endif
}
if (codec->priv_class)
av_assert0(*(const AVClass **)avctx->priv_data == codec->priv_class);
end:
unlock_avcodec(codec);
return ret;
free_and_end:
avcodec_close(avctx);
goto end;
}
接着看ff_decode_preinit()
int ff_decode_preinit(AVCodecContext *avctx)
{
int ret = 0;
/* if the decoder init function was already called previously,
* free the already allocated subtitle_header before overwriting it */
av_freep(&avctx->subtitle_header);
#if FF_API_THREAD_SAFE_CALLBACKS
FF_DISABLE_DEPRECATION_WARNINGS
if ((avctx->thread_type & FF_THREAD_FRAME) &&
avctx->get_buffer2 != avcodec_default_get_buffer2 &&
!avctx->thread_safe_callbacks) {
av_log(avctx, AV_LOG_WARNING, "Requested frame threading with a "
"custom get_buffer2() implementation which is not marked as "
"thread safe. This is not supported anymore, make your "
"callback thread-safe.\n");
}
FF_ENABLE_DEPRECATION_WARNINGS
#endif
if (avctx->codec_type == AVMEDIA_TYPE_AUDIO && avctx->channels == 0 &&
!(avctx->codec->capabilities & AV_CODEC_CAP_CHANNEL_CONF)) {
av_log(avctx, AV_LOG_ERROR, "Decoder requires channel count but channels not set\n");
return AVERROR(EINVAL);
}
if (avctx->codec->max_lowres < avctx->lowres || avctx->lowres < 0) {
av_log(avctx, AV_LOG_WARNING, "The maximum value for lowres supported by the decoder is %d\n",
avctx->codec->max_lowres);
avctx->lowres = avctx->codec->max_lowres;
}
if (avctx->sub_charenc) {
if (avctx->codec_type != AVMEDIA_TYPE_SUBTITLE) {
av_log(avctx, AV_LOG_ERROR, "Character encoding is only "
"supported with subtitles codecs\n");
return AVERROR(EINVAL);
} else if (avctx->codec_descriptor->props & AV_CODEC_PROP_BITMAP_SUB) {
av_log(avctx, AV_LOG_WARNING, "Codec '%s' is bitmap-based, "
"subtitles character encoding will be ignored\n",
avctx->codec_descriptor->name);
avctx->sub_charenc_mode = FF_SUB_CHARENC_MODE_DO_NOTHING;
} else {
/* input character encoding is set for a text based subtitle
* codec at this point */
if (avctx->sub_charenc_mode == FF_SUB_CHARENC_MODE_AUTOMATIC)
avctx->sub_charenc_mode = FF_SUB_CHARENC_MODE_PRE_DECODER;
if (avctx->sub_charenc_mode == FF_SUB_CHARENC_MODE_PRE_DECODER) {
#if CONFIG_ICONV
iconv_t cd = iconv_open("UTF-8", avctx->sub_charenc);
if (cd == (iconv_t)-1) {
ret = AVERROR(errno);
av_log(avctx, AV_LOG_ERROR, "Unable to open iconv context "
"with input character encoding \"%s\"\n", avctx->sub_charenc);
return ret;
}
iconv_close(cd);
#else
av_log(avctx, AV_LOG_ERROR, "Character encoding subtitles "
"conversion needs a libavcodec built with iconv support "
"for this codec\n");
return AVERROR(ENOSYS);
#endif
}
}
}
avctx->pts_correction_num_faulty_pts =
avctx->pts_correction_num_faulty_dts = 0;
avctx->pts_correction_last_pts =
avctx->pts_correction_last_dts = INT64_MIN;
if ( !CONFIG_GRAY && avctx->flags & AV_CODEC_FLAG_GRAY
&& avctx->codec_descriptor->type == AVMEDIA_TYPE_VIDEO)
av_log(avctx, AV_LOG_WARNING,
"gray decoding requested but not enabled at configuration time\n");
if (avctx->flags2 & AV_CODEC_FLAG2_EXPORT_MVS) {
avctx->export_side_data |= AV_CODEC_EXPORT_DATA_MVS;
}
ret = decode_bsfs_init(avctx);
if (ret < 0)
return ret;
return 0;
}
static int decode_bsfs_init(AVCodecContext *avctx)
{
AVCodecInternal *avci = avctx->internal;
int ret;
if (avci->bsf)
return 0;
//这里调用bsf
ret = av_bsf_list_parse_str(avctx->codec->bsfs, &avci->bsf);
if (ret < 0) {
av_log(avctx, AV_LOG_ERROR, "Error parsing decoder bitstream filters '%s': %s\n", avctx->codec->bsfs, av_err2str(ret));
if (ret != AVERROR(ENOMEM))
ret = AVERROR_BUG;
goto fail;
}
/* We do not currently have an API for passing the input timebase into decoders,
* but no filters used here should actually need it.
* So we make up some plausible-looking number (the MPEG 90kHz timebase) */
avci->bsf->time_base_in = (AVRational){ 1, 90000 };
ret = avcodec_parameters_from_context(avci->bsf->par_in, avctx);
if (ret < 0)
goto fail;
ret = av_bsf_init(avci->bsf);
if (ret < 0)
goto fail;
return 0;
fail:
av_bsf_free(&avci->bsf);
return ret;
}
上面提到一个非常中要的检查函数ff_set_dimensions()
:
/**
* Check that the provided frame dimensions are valid and set them on the codec
* context.
*/
int ff_set_dimensions(AVCodecContext *s, int width, int height);
int ff_set_dimensions(AVCodecContext *s, int width, int height)
{
int ret = av_image_check_size2(width, height, s->max_pixels, AV_PIX_FMT_NONE, 0, s);
if (ret < 0)
width = height = 0;
s->coded_width = width;
s->coded_height = height;
s->width = AV_CEIL_RSHIFT(width, s->lowres);
s->height = AV_CEIL_RSHIFT(height, s->lowres);
return ret;
}
/**
* Check if the given dimension of an image is valid, meaning that all
* bytes of a plane of an image with the specified pix_fmt can be addressed
* with a signed int.
*
* @param w the width of the picture
* @param h the height of the picture
* @param max_pixels the maximum number of pixels the user wants to accept
* @param pix_fmt the pixel format, can be AV_PIX_FMT_NONE if unknown.
* @param log_offset the offset to sum to the log level for logging with log_ctx
* @param log_ctx the parent logging context, it may be NULL
* @return >= 0 if valid, a negative error code otherwise
* */
int av_image_check_size2(unsigned int w, unsigned int h, int64_t max_pixels, enum AVPixelFormat pix_fmt, int log_offset, void *log_ctx)
{
ImgUtils imgutils = {
.class = &imgutils_class,
.log_offset = log_offset,
.log_ctx = log_ctx,
};
int64_t stride = av_image_get_linesize(pix_fmt, w, 0);
if (stride <= 0)
stride = 8LL*w;
stride += 128*8;
//这里进行了尺寸大小限定
if ((int)w<=0 || (int)h<=0 || stride >= INT_MAX || stride*(uint64_t)(h+128) >= INT_MAX) {
av_log(&imgutils, AV_LOG_ERROR, "Picture size %ux%u is invalid\n", w, h);
return AVERROR(EINVAL);
}
if (max_pixels < INT64_MAX) {
if (w*(int64_t)h > max_pixels) {
av_log(&imgutils, AV_LOG_ERROR,
"Picture size %ux%u exceeds specified max pixel count %"PRId64", see the documentation if you wish to increase it\n",
w, h, max_pixels);
return AVERROR(EINVAL);
}
}
return 0;
}
int av_image_get_linesize(enum AVPixelFormat pix_fmt, int width, int plane)
{
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(pix_fmt);
int max_step [4]; /* max pixel step for each plane */
int max_step_comp[4]; /* the component for each plane which has the max pixel step */
if (!desc || desc->flags & AV_PIX_FMT_FLAG_HWACCEL)
return AVERROR(EINVAL);
av_image_fill_max_pixsteps(max_step, max_step_comp, desc);
return image_get_linesize(width, plane, max_step[plane], max_step_comp[plane], desc);
}
/**
* @return a pixel format descriptor for provided pixel format or NULL if
* this pixel format is unknown.
*/
const AVPixFmtDescriptor *av_pix_fmt_desc_get(enum AVPixelFormat pix_fmt)
{
if (pix_fmt < 0 || pix_fmt >= AV_PIX_FMT_NB)
return NULL;
return &av_pix_fmt_descriptors[pix_fmt];
}
static const AVPixFmtDescriptor av_pix_fmt_descriptors[AV_PIX_FMT_NB] = {
[AV_PIX_FMT_YUV420P] = {
.name = "yuv420p",
.nb_components = 3,
.log2_chroma_w = 1,
.log2_chroma_h = 1,
.comp = {
{ 0, 1, 0, 0, 8 }, /* Y */
{ 1, 1, 0, 0, 8 }, /* U */
{ 2, 1, 0, 0, 8 }, /* V */
},
.flags = AV_PIX_FMT_FLAG_PLANAR,
},
...
}
/**
* Descriptor that unambiguously describes how the bits of a pixel are
* stored in the up to 4 data planes of an image. It also stores the
* subsampling factors and number of components.
*
* @note This is separate of the colorspace (RGB, YCbCr, YPbPr, JPEG-style YUV
* and all the YUV variants) AVPixFmtDescriptor just stores how values
* are stored not what these values represent.
*/
typedef struct AVPixFmtDescriptor {
const char *name;
uint8_t nb_components; ///< The number of components each pixel has, (1-4)
/**
* Amount to shift the luma width right to find the chroma width.
* For YV12 this is 1 for example.
* chroma_width = AV_CEIL_RSHIFT(luma_width, log2_chroma_w)
* The note above is needed to ensure rounding up.
* This value only refers to the chroma components.
*/
uint8_t log2_chroma_w;
/**
* Amount to shift the luma height right to find the chroma height.
* For YV12 this is 1 for example.
* chroma_height= AV_CEIL_RSHIFT(luma_height, log2_chroma_h)
* The note above is needed to ensure rounding up.
* This value only refers to the chroma components.
*/
uint8_t log2_chroma_h;
/**
* Combination of AV_PIX_FMT_FLAG_... flags.
*/
uint64_t flags;
/**
* Parameters that describe how pixels are packed.
* If the format has 1 or 2 components, then luma is 0.
* If the format has 3 or 4 components:
* if the RGB flag is set then 0 is red, 1 is green and 2 is blue;
* otherwise 0 is luma, 1 is chroma-U and 2 is chroma-V.
*
* If present, the Alpha channel is always the last component.
*/
AVComponentDescriptor comp[4];
/**
* Alternative comma-separated names.
*/
const char *alias;
} AVPixFmtDescriptor;
typedef struct AVComponentDescriptor {
/**
* Which of the 4 planes contains the component.
*/
int plane;
/**
* Number of elements between 2 horizontally consecutive pixels.
* Elements are bits for bitstream formats, bytes otherwise.
*/
int step;
/**
* Number of elements before the component of the first pixel.
* Elements are bits for bitstream formats, bytes otherwise.
*/
int offset;
/**
* Number of least significant bits that must be shifted away
* to get the value.
*/
int shift;
/**
* Number of bits in the component.
*/
int depth;
} AVComponentDescriptor;
void av_image_fill_max_pixsteps(int max_pixsteps[4], int max_pixstep_comps[4],
const AVPixFmtDescriptor *pixdesc)
{
int i;
memset(max_pixsteps, 0, 4*sizeof(max_pixsteps[0]));
if (max_pixstep_comps)
memset(max_pixstep_comps, 0, 4*sizeof(max_pixstep_comps[0]));
for (i = 0; i < 4; i++) {
const AVComponentDescriptor *comp = &(pixdesc->comp[i]);
if (comp->step > max_pixsteps[comp->plane]) {
max_pixsteps[comp->plane] = comp->step;
if (max_pixstep_comps)
max_pixstep_comps[comp->plane] = i;
}
}
}
static inline
int image_get_linesize(int width, int plane,
int max_step, int max_step_comp,
const AVPixFmtDescriptor *desc)
{
int s, shifted_w, linesize;
if (!desc)
return AVERROR(EINVAL);
if (width < 0)
return AVERROR(EINVAL);
s = (max_step_comp == 1 || max_step_comp == 2) ? desc->log2_chroma_w : 0;
shifted_w = ((width + (1 << s) - 1)) >> s;
if (shifted_w && max_step > INT_MAX / shifted_w)
return AVERROR(EINVAL);
linesize = max_step * shifted_w;
if (desc->flags & AV_PIX_FMT_FLAG_BITSTREAM)
linesize = (linesize + 7) >> 3;
return linesize;
}
avcodec_send_packet(dec, pkt);
int attribute_align_arg avcodec_send_packet(AVCodecContext *avctx, const AVPacket *avpkt)
{
AVCodecInternal *avci = avctx->internal;
int ret;
if (!avcodec_is_open(avctx) || !av_codec_is_decoder(avctx->codec))
return AVERROR(EINVAL);
if (avctx->internal->draining)
return AVERROR_EOF;
if (avpkt && !avpkt->size && avpkt->data)
return AVERROR(EINVAL);
av_packet_unref(avci->buffer_pkt);
if (avpkt && (avpkt->data || avpkt->side_data_elems)) {
//从这里获取到pkt的引用,还记得avci这个变量的作用吗?
ret = av_packet_ref(avci->buffer_pkt, avpkt);
if (ret < 0)
return ret;
}
//bsf过滤模块
ret = av_bsf_send_packet(avci->bsf, avci->buffer_pkt);
if (ret < 0) {
av_packet_unref(avci->buffer_pkt);
return ret;
}
//这个buf里面会缓存数据
if (!avci->buffer_frame->buf[0]) {
//如果有数据,会存放在avci->buffer_frame中
ret = decode_receive_frame_internal(avctx, avci->buffer_frame);
if (ret < 0 && ret != AVERROR(EAGAIN) && ret != AVERROR_EOF)
return ret;
}
return 0;
}
static int decode_receive_frame_internal(AVCodecContext *avctx, AVFrame *frame)
{
AVCodecInternal *avci = avctx->internal;
int ret;
av_assert0(!frame->buf[0]);
if (avctx->codec->receive_frame) {
//这里调用回调receive_frame
ret = avctx->codec->receive_frame(avctx, frame);
if (ret != AVERROR(EAGAIN))
av_packet_unref(avci->last_pkt_props);
} else
ret = decode_simple_receive_frame(avctx, frame);
if (ret == AVERROR_EOF)
avci->draining_done = 1;
if (!(avctx->codec->caps_internal & FF_CODEC_CAP_SETS_FRAME_PROPS) &&
IS_EMPTY(avci->last_pkt_props) && av_fifo_size(avci->pkt_props) >= sizeof(*avci->last_pkt_props))
av_fifo_generic_read(avci->pkt_props,
avci->last_pkt_props, sizeof(*avci->last_pkt_props), NULL);
if (!ret) {
//如果有数据会进入到这里来
frame->best_effort_timestamp = guess_correct_pts(avctx,
frame->pts,
frame->pkt_dts);
/* the only case where decode data is not set should be decoders
* that do not call ff_get_buffer() */
av_assert0((frame->private_ref && frame->private_ref->size == sizeof(FrameDecodeData)) ||
!(avctx->codec->capabilities & AV_CODEC_CAP_DR1));
if (frame->private_ref) {
//
FrameDecodeData *fdd = (FrameDecodeData*)frame->private_ref->data;
if (fdd->post_process) {
//这里一般没有设置.一般不处理
ret = fdd->post_process(avctx, frame);
if (ret < 0) {
av_frame_unref(frame);
return ret;
}
}
}
}
/* free the per-frame decode data */
av_buffer_unref(&frame->private_ref);
return ret;
}
static int decode_simple_receive_frame(AVCodecContext *avctx, AVFrame *frame)
{
int ret;
int64_t discarded_samples = 0;
//第一轮如果没有取到数据,这里会一直循环到第二轮,ret=-11,才跳出
//下次跳出是在ff_decode_get_packet返回位ret<0的时候
//但是如果frame取到数据就会直接跳出
while (!frame->buf[0]) {
if (discarded_samples > avctx->max_samples)
return AVERROR(EAGAIN);
ret = decode_simple_internal(avctx, frame, &discarded_samples);
if (ret < 0)
return ret;
}
return 0;
}
/*
* The core of the receive_frame_wrapper for the decoders implementing
* the simple API. Certain decoders might consume partial packets without
* returning any output, so this function needs to be called in a loop until it
* returns EAGAIN.
**/
static inline int decode_simple_internal(AVCodecContext *avctx, AVFrame *frame, int64_t *discarded_samples)
{
AVCodecInternal *avci = avctx->internal;
AVPacket *const pkt = avci->in_pkt;
int got_frame, actual_got_frame;
int ret;
if (!pkt->data && !avci->draining) {
av_packet_unref(pkt);
// ret = av_bsf_receive_packet(avci->bsf, pkt);
ret = ff_decode_get_packet(avctx, pkt);
if (ret < 0 && ret != AVERROR_EOF)
return ret;
}
// Some codecs (at least wma lossless) will crash when feeding drain packets
// after EOF was signaled.
if (avci->draining_done)
return AVERROR_EOF;
if (!pkt->data &&
!(avctx->codec->capabilities & AV_CODEC_CAP_DELAY ||
avctx->active_thread_type & FF_THREAD_FRAME))
return AVERROR_EOF;
got_frame = 0;
if (HAVE_THREADS && avctx->active_thread_type & FF_THREAD_FRAME) {
ret = ff_thread_decode_frame(avctx, frame, &got_frame, pkt);
} else {
//回调函数
ret = avctx->codec->decode(avctx, frame, &got_frame, pkt);
if (!(avctx->codec->caps_internal & FF_CODEC_CAP_SETS_PKT_DTS))
frame->pkt_dts = pkt->dts;
if (avctx->codec->type == AVMEDIA_TYPE_VIDEO) {
if(!avctx->has_b_frames)
frame->pkt_pos = pkt->pos;
//FIXME these should be under if(!avctx->has_b_frames)
/* get_buffer is supposed to set frame parameters */
if (!(avctx->codec->capabilities & AV_CODEC_CAP_DR1)) {
if (!frame->sample_aspect_ratio.num) frame->sample_aspect_ratio = avctx->sample_aspect_ratio;
if (!frame->width) frame->width = avctx->width;
if (!frame->height) frame->height = avctx->height;
if (frame->format == AV_PIX_FMT_NONE) frame->format = avctx->pix_fmt;
}
}
}
emms_c();
actual_got_frame = got_frame;
if (avctx->codec->type == AVMEDIA_TYPE_VIDEO) {
if (frame->flags & AV_FRAME_FLAG_DISCARD)
got_frame = 0;
} else if (avctx->codec->type == AVMEDIA_TYPE_AUDIO) {
...
}
if (!got_frame)
av_frame_unref(frame);
#if FF_API_FLAG_TRUNCATED
if (ret >= 0 && avctx->codec->type == AVMEDIA_TYPE_VIDEO && !(avctx->flags & AV_CODEC_FLAG_TRUNCATED))
#else
if (ret >= 0 && avctx->codec->type == AVMEDIA_TYPE_VIDEO)
#endif
ret = pkt->size;
#if FF_API_AVCTX_TIMEBASE
//修改时间基准,每次都会进入
if (avctx->framerate.num > 0 && avctx->framerate.den > 0)
avctx->time_base = av_inv_q(av_mul_q(avctx->framerate, (AVRational){avctx->ticks_per_frame, 1}));
#endif
/* do not stop draining when actual_got_frame != 0 or ret < 0 */
/* got_frame == 0 but actual_got_frame != 0 when frame is discarded */
if (avci->draining && !actual_got_frame) {
if (ret < 0) {
/* prevent infinite loop if a decoder wrongly always return error on draining */
/* reasonable nb_errors_max = maximum b frames + thread count */
int nb_errors_max = 20 + (HAVE_THREADS && avctx->active_thread_type & FF_THREAD_FRAME ?
avctx->thread_count : 1);
if (avci->nb_draining_errors++ >= nb_errors_max) {
av_log(avctx, AV_LOG_ERROR, "Too many errors when draining, this is a bug. "
"Stop draining and force EOF.\n");
avci->draining_done = 1;
ret = AVERROR_BUG;
}
} else {
avci->draining_done = 1;
}
}
if (ret >= pkt->size || ret < 0) {
av_packet_unref(pkt);
av_packet_unref(avci->last_pkt_props);
} else {
int consumed = ret;
pkt->data += consumed;
pkt->size -= consumed;
pkt->pts = AV_NOPTS_VALUE;
pkt->dts = AV_NOPTS_VALUE;
if (!(avctx->codec->caps_internal & FF_CODEC_CAP_SETS_FRAME_PROPS)) {
avci->last_pkt_props->size -= consumed; // See extract_packet_props() comment.
avci->last_pkt_props->pts = AV_NOPTS_VALUE;
avci->last_pkt_props->dts = AV_NOPTS_VALUE;
}
}
if (got_frame)
av_assert0(frame->buf[0]);
return ret < 0 ? ret : 0;
}
avcodec_receive_frame(dec, frame);
int attribute_align_arg avcodec_receive_frame(AVCodecContext *avctx, AVFrame *frame)
{
AVCodecInternal *avci = avctx->internal;
int ret, changed;
av_frame_unref(frame);
if (!avcodec_is_open(avctx) || !av_codec_is_decoder(avctx->codec))
return AVERROR(EINVAL);
//注意这里呀,如果buffer-frame有数据,就直接把引用传递给frame,否则进入下一个函数
if (avci->buffer_frame->buf[0]) {
av_frame_move_ref(frame, avci->buffer_frame);
} else {
//再次调用,只是本次frame是外部传入的,上次是avci->buffer_frame
ret = decode_receive_frame_internal(avctx, frame);
if (ret < 0)
return ret;
}
if (avctx->codec_type == AVMEDIA_TYPE_VIDEO) {
//这里可以crop,裁剪,解码后可以在这里裁剪
// size_t crop_top;
// size_t crop_bottom;
// size_t crop_left;
// size_t crop_right;
// 上面是frame的成员变量
ret = apply_cropping(avctx, frame);
if (ret < 0) {
av_frame_unref(frame);
return ret;
}
}
avctx->frame_number++;
if (avctx->flags & AV_CODEC_FLAG_DROPCHANGED) {
if (avctx->frame_number == 1) {
avci->initial_format = frame->format;
switch(avctx->codec_type) {
case AVMEDIA_TYPE_VIDEO:
avci->initial_width = frame->width;
avci->initial_height = frame->height;
break;
case AVMEDIA_TYPE_AUDIO:
avci->initial_sample_rate = frame->sample_rate ? frame->sample_rate :
avctx->sample_rate;
avci->initial_channels = frame->channels;
avci->initial_channel_layout = frame->channel_layout;
break;
}
}
if (avctx->frame_number > 1) {
changed = avci->initial_format != frame->format;
switch(avctx->codec_type) {
case AVMEDIA_TYPE_VIDEO:
changed |= avci->initial_width != frame->width ||
avci->initial_height != frame->height;
break;
case AVMEDIA_TYPE_AUDIO:
changed |= avci->initial_sample_rate != frame->sample_rate ||
avci->initial_sample_rate != avctx->sample_rate ||
avci->initial_channels != frame->channels ||
avci->initial_channel_layout != frame->channel_layout;
break;
}
if (changed) {
avci->changed_frames_dropped++;
av_log(avctx, AV_LOG_INFO, "dropped changed frame #%d pts %"PRId64
" drop count: %d \n",
avctx->frame_number, frame->pts,
avci->changed_frames_dropped);
av_frame_unref(frame);
return AVERROR_INPUT_CHANGED;
}
}
}
return 0;
}
static int decode_receive_frame_internal(AVCodecContext *avctx, AVFrame *frame)
{
AVCodecInternal *avci = avctx->internal;
int ret;
av_assert0(!frame->buf[0]);
if (avctx->codec->receive_frame) {
ret = avctx->codec->receive_frame(avctx, frame);
if (ret != AVERROR(EAGAIN))
av_packet_unref(avci->last_pkt_props);
} else
ret = decode_simple_receive_frame(avctx, frame);
if (ret == AVERROR_EOF)
avci->draining_done = 1;
if (!(avctx->codec->caps_internal & FF_CODEC_CAP_SETS_FRAME_PROPS) &&
IS_EMPTY(avci->last_pkt_props) && av_fifo_size(avci->pkt_props) >= sizeof(*avci->last_pkt_props))
av_fifo_generic_read(avci->pkt_props,
avci->last_pkt_props, sizeof(*avci->last_pkt_props), NULL);
if (!ret) {
frame->best_effort_timestamp = guess_correct_pts(avctx,
frame->pts,
frame->pkt_dts);
/* the only case where decode data is not set should be decoders
* that do not call ff_get_buffer() */
av_assert0((frame->private_ref && frame->private_ref->size == sizeof(FrameDecodeData)) ||
!(avctx->codec->capabilities & AV_CODEC_CAP_DR1));
if (frame->private_ref) {
FrameDecodeData *fdd = (FrameDecodeData*)frame->private_ref->data;
if (fdd->post_process) {
ret = fdd->post_process(avctx, frame);
if (ret < 0) {
av_frame_unref(frame);
return ret;
}
}
}
}
/* free the per-frame decode data */
av_buffer_unref(&frame->private_ref);
return ret;
}
#ifdef __cplusplus
extern "C" {
#endif
#include
#include
#include
#include
#include
#include "libavutil/log.h"
#ifdef __cplusplus
}
#endif
#include
static AVFormatContext * fmt_ctx = NULL;
static AVCodecContext * video_dec_ctx = NULL;
static int width, height;
static enum AVPixelFormat pix_fmt;
static AVStream * video_stream = NULL;
static const char * src_filename = NULL;
static const char * video_dst_filename = NULL;
static FILE * video_dst_file = NULL;
static uint8_t *video_dst_data[4] = {NULL};
static int video_dst_linesize[4];
static int video_dst_bufsize;
static int video_stream_idx = -1;
static AVFrame * frame = NULL;
static AVPacket *pkt = NULL;
static int video_frame_count = 0;
static int output_video_frame(AVFrame *frame) {
if (frame->width != width || frame->height != height || frame->format != pix_fmt) {
/* To handle this change, one could call av_image_alloc again and
* decode the following frames into another rawvideo file. */
printf(
"Error: Width, height and pixel format have to be "
"constant in a rawvideo file, but the width, height or "
"pixel format of the input video changed:\n"
"old: width = %d, height = %d, format = %s\n"
"new: width = %d, height = %d, format = %s\n",
width, height, av_get_pix_fmt_name(pix_fmt), frame->width, frame->height,
av_get_pix_fmt_name(AVPixelFormat(frame->format)));
return -1;
}
video_frame_count++;
// printf("video_frame n:%d coded_n:%d\n", video_frame_count++,
// frame->coded_picture_number);
/* copy decoded frame to destination buffer:
* this is required since rawvideo expects non aligned data */
av_image_copy(video_dst_data, video_dst_linesize, (const uint8_t **)(frame->data),
frame->linesize, pix_fmt, width, height);
/* write to rawvideo file */
fwrite(video_dst_data[0], 1, video_dst_bufsize, video_dst_file);
return 0;
}
static int decode_packet(AVCodecContext *dec, const AVPacket *pkt) {
int ret = 0;
// submit the packet to the decoder
ret = avcodec_send_packet(dec, pkt);
if (ret < 0) {
// printf("Error submitting a packet for decoding (%s)\n", av_err2str(ret));
return ret;
}
// get all the available frames from the decoder
while (ret >= 0) {
ret = avcodec_receive_frame(dec, frame);
if (ret < 0) {
// those two return values are special and mean there is no output
// frame available, but there were no errors during decoding
if (ret == AVERROR_EOF || ret == AVERROR(EAGAIN))
return 0;
// printf("Error during decoding (%s)\n", av_err2str(ret));
return ret;
}
// write the frame data to output file
if (dec->codec->type == AVMEDIA_TYPE_VIDEO)
ret = output_video_frame(frame);
av_frame_unref(frame);
if (ret < 0)
return ret;
}
return 0;
}
static int open_codec_context(int *stream_idx, AVCodecContext **dec_ctx,
AVFormatContext *fmt_ctx, enum AVMediaType type) {
int ret, stream_index;
AVStream * st;
const AVCodec *dec = NULL;
ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0);
if (ret < 0) {
printf("Could not find %s stream in input file '%s'\n", av_get_media_type_string(type),
src_filename);
return ret;
} else {
stream_index = ret;
st = fmt_ctx->streams[stream_index];
/* find decoder for the stream */
// dec = avcodec_find_decoder(st->codecpar->codec_id);
// if (!dec) {
// printf("Failed to find %s codec\n", av_get_media_type_string(type));
// return AVERROR(EINVAL);
// }
dec = avcodec_find_decoder_by_name("h264dec_omx");
if (!dec) {
printf("Codec not found\n");
exit(1);
}
/* Allocate a codec context for the decoder */
*dec_ctx = avcodec_alloc_context3(dec);
if (!*dec_ctx) {
printf(
"Failed to allocate the %s codec context\n", av_get_media_type_string(type));
return AVERROR(ENOMEM);
}
/* Copy codec parameters from input stream to output codec context */
if ((ret = avcodec_parameters_to_context(*dec_ctx, st->codecpar)) < 0) {
printf("Failed to copy %s codec parameters to decoder context\n",
av_get_media_type_string(type));
return ret;
}
/* Init the decoders */
if ((ret = avcodec_open2(*dec_ctx, dec, NULL)) < 0) {
printf("Failed to open %s codec\n", av_get_media_type_string(type));
return ret;
}
*stream_idx = stream_index;
}
return 0;
}
static FILE *fp_log;
#define LOG_BUF_PREFIX_SIZE 512
#define LOG_BUF_SIZE 1024
static char logBufPrefix[LOG_BUF_PREFIX_SIZE];
static char logBuffer[LOG_BUF_SIZE];
static pthread_mutex_t cb_av_log_lock;
typedef void (*ffmpeg_log_callback)(void *ptr, int level, const char *fmt, va_list vl);
static void log_callback_null(void *ptr, int level, const char *fmt, va_list vl) {
FILE *fp = (FILE *)fp_log;
int cnt;
pthread_mutex_lock(&cb_av_log_lock);
cnt = snprintf(logBufPrefix, LOG_BUF_PREFIX_SIZE, "%s", fmt);
cnt = vsnprintf(logBuffer, LOG_BUF_SIZE, logBufPrefix, vl);
fprintf(fp, "%s", logBuffer);
fflush(fp);
pthread_mutex_unlock(&cb_av_log_lock);
}
int main(int argc, char **argv) {
int ret = 0;
if (argc != 3) {
printf(
"usage: %s input_file video_output_file\n"
"API example program to show how to read frames from an input file.\n"
"This program reads frames from a file, decodes them, and writes decoded\n"
"video frames to a rawvideo file named video_output_file, and decoded\n",
argv[0]);
exit(1);
}
fp_log = fopen("debug.log", "w+");
if (NULL == fp_log) {
printf("cant open log file %s\n", "debug.log");
return 0;
}
ffmpeg_log_callback fptrLog = log_callback_null;
/* END */
av_log_set_level(AV_LOG_TRACE);
// av_log_set_flags(AV_LOG_SKIP_REPEATED);
av_log_set_callback(fptrLog);
src_filename = argv[1];
video_dst_filename = argv[2];
/* open input file, and allocate format context */
if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) {
printf("Could not open source file %s\n", src_filename);
exit(1);
}
/* retrieve stream information */
if (avformat_find_stream_info(fmt_ctx, NULL) < 0) {
printf("Could not find stream information\n");
exit(1);
}
if (open_codec_context(&video_stream_idx, &video_dec_ctx, fmt_ctx, AVMEDIA_TYPE_VIDEO) >=
0) {
video_stream = fmt_ctx->streams[video_stream_idx];
video_dst_file = fopen(video_dst_filename, "wb");
if (!video_dst_file) {
printf("Could not open destination file %s\n", video_dst_filename);
ret = 1;
goto end;
}
/* allocate image where the decoded image will be put */
width = video_dec_ctx->width;
height = video_dec_ctx->height;
pix_fmt = video_dec_ctx->pix_fmt;
ret = av_image_alloc(video_dst_data, video_dst_linesize, width, height, pix_fmt, 1);
if (ret < 0) {
printf("Could not allocate raw video buffer\n");
goto end;
}
video_dst_bufsize = ret;
}
/* dump input information to stderr */
av_dump_format(fmt_ctx, 0, src_filename, 0);
frame = av_frame_alloc();
if (!frame) {
printf("Could not allocate frame\n");
ret = AVERROR(ENOMEM);
goto end;
}
pkt = av_packet_alloc();
if (!pkt) {
printf("Could not allocate packet\n");
ret = AVERROR(ENOMEM);
goto end;
}
if (video_stream)
printf("Demuxing video from file '%s' into '%s'\n", src_filename, video_dst_filename);
/* read frames from the file */
while (av_read_frame(fmt_ctx, pkt) >= 0) {
// check if the packet belongs to a stream we are interested in, otherwise
// skip it
if (pkt->stream_index == video_stream_idx)
ret = decode_packet(video_dec_ctx, pkt);
av_packet_unref(pkt);
if (ret < 0)
break;
}
/* flush the decoders */
if (video_dec_ctx)
decode_packet(video_dec_ctx, NULL);
printf("Demuxing and decode succeeded.\n");
if (video_stream) {
printf(
"Play the output video file with the command:\n"
"ffplay -f rawvideo -pix_fmt %s -video_size %dx%d %s\n",
av_get_pix_fmt_name(pix_fmt), width, height, video_dst_filename);
}
printf("all video_frame n:%d \n", video_frame_count++);
end:
avcodec_free_context(&video_dec_ctx);
avformat_close_input(&fmt_ctx);
if (video_dst_file)
fclose(video_dst_file);
av_packet_free(&pkt);
av_frame_free(&frame);
av_free(video_dst_data[0]);
fclose(fp_log);
return ret < 0;
}
CMakeLists.txt
# CMake 最低版本号要求
cmake_minimum_required (VERSION 3.5)
# 项目信息
project (ffmdecoder-Demo1)
set(EXECUTABLE_OUTPUT_PATH ${PROJECT_BINARY_DIR}/bin)
set(CMAKE_BUILD_TYPE "Debug")
set(CMAKE_CXX_FLAGS_DEBUG "$ENV{CXXFLAGS} -O0 -Wall -g -fpermissive")
set(CMAKE_CXX_FLAGS_RELEASE "$ENV{CXXFLAGS} -O3 -Wall -fpermissive")
set(root_path /workspace/depends)
#dependencies
# set(ENV{PKG_CONFIG_PATH} "${root_path}/simple-x86-omx-ffmpeg5.0/lib/pkgconfig")
set(ENV{PKG_CONFIG_PATH} "${root_path}/simple-x86-omx-ffmpeg5.0/lib/pkgconfig")
find_package(PkgConfig)
pkg_check_modules(FFMPEG REQUIRED libavformat libavutil libavcodec)
message(STATUS "=== FFMPEG_LIBRARIES: ${FFMPEG_LIBRARIES}")
message(STATUS "=== FFMPEG_INCLUDE_DIRS: ${FFMPEG_INCLUDE_DIRS}")
message(STATUS "=== FFMPEG_LIBRARY_DIRS: ${FFMPEG_LIBRARY_DIRS}")
message(STATUS "=== FFMPEG_CFLAGS: ${FFMPEG_CFLAGS}")
FOREACH(flag ${FFMPEG_CFLAGS})
SET(EXTRA_CFLGAS "${EXTRA_CFLGAS} ${flag}")
ENDFOREACH(flag)
SET(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${EXTRA_CFLGAS}")
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${EXTRA_CFLGAS}")
include_directories(${FFMPEG_INCLUDE_DIRS} )
link_directories(${FFMPEG_LIBRARY_DIRS})
set(SOURCES main.cpp)
# 指定生成目标
add_executable(FFm_Dec ${SOURCES})
target_link_libraries(FFm_Dec ${FFMPEG_LIBRARIES})