本文要介绍的结构体是 AVFormatContext.
描述了媒体文件的构成及基本信息，是统领全局的基本结构体，贯穿程序始终，很多函数都要用它作为参数
AVFormatContext 源码比较长，就补贴在这里了，位置在 libavformat/avformat.h,
创建方式
AVFormatContext 有两种种创建方式，
- avformat_alloc_context(…)
- avformat_open_input(…)
avformat_alloc_context
在一些场景里，我们自己会通过 avformat_alloc_context 先创建 AVFormatContext，在传给 avformat_alloc_context() 函数之前做一些微调
。 一个常见的场景是，我们要自定义读取输入数据的方式来替代 lavf 的内如 I/O 层。 要实现，则要通过 avio_alloc_context() 创建自己的 AVIOContext, 传递读取的回调。 然后将 AVIOContext 赋值给 AVFormatContext 的 pb 字段。
函数的定义非常简单，
AVFormatContext* avformat_alloc_context (void)
由于在执行 avformat_open_input() 之前，通常是不知道将要读取流的格式的，
这样在预先创建 context 就没办法设置 demuxer 私有的选项。代替的方式是，首选项应该包含在 AVDictionary 里传递给 avformat_open_input，完成设置
AVDictionary *options = NULL;
av_dict_set(&options, "video_size", "640x480", 0);
av_dict_set(&options, "pixel_format", "rgb24", 0);
if (avformat_open_input(&s, url, NULL, &options) < 0)
abort();
av_dict_free(&options);
avformat_open_input
可以通过 avformat_open_input(…) 打开指定的文件，并且读取 header 信息到 AVFormatContext。
/** 打开一个 stream，读取都首地址
* 返回 0：成功，negative AVERROR：失败
*/
int avformat_open_input(AVFormatContext ** ps,
const char * url,
AVInputFormat * fmt,
AVDictionary ** options
)
未打开编解码器，必须使用 avformat_close_input() 关闭流。
参数：
- ps：指向用户提供的 AVFormatContext (avformat_alloc_context 分配). 可以为 NULL, 则 AVFormatContext 由该函数自己创建并赋值. 注意，一个用户提供的 AVFormatContext 在出现异常时将会被释放.
- url： 要打开的流 url
- fmt：如果不为 NULL，该参数会强制指定输入的格式.否则自动检测
- options： dictionary 由 AVFormatContext 和 demuxer-private 选项填充. 当找不到 url 的 stream 时，该参数被销毁，由一个包含 首选项 的 dict。 可为 NULL
注意:
如果要自定义 IO，要预先分配 AVIOContext，然后赋值给 AVFormatContext的 pb 字段，例子查看 AVIOContext一文 .
一些格式可能没有 header 或者没有存储足够的信息， 这时推荐调用 avformat_find_stream_info() 来读取和解码一些帧来查找丢失的信息。
Example
我们通过例子来进一步了解它，
读取 metadata信息
#include <stdio.h>
#include <libavformat/avformat.h>
#include <libavutil/dict.h>
int main (int argc, char **argv)
{
AVFormatContext *fmt_ctx = NULL;
AVDictionaryEntry *tag = NULL;
int ret;
if (argc != 2) {
printf("usage: %s <input_file>\n"
"example program to demonstrate the use of the libavformat metadata API.\n"
"\n", argv[0]);
return 1;
}
// 打开 argv[1] stream 赋值给 fmt_ctx
if ((ret = avformat_open_input(&fmt_ctx, argv[1], NULL, NULL)))
return ret;
// 从 AVFormatContext 读取 metadata 信息
while ((tag = av_dict_get(fmt_ctx->metadata, "", tag, AV_DICT_IGNORE_SUFFIX)))
printf("%s=%s\n", tag->key, tag->value);
// 关闭 AVFormatContext
avformat_close_input(&fmt_ctx);
return 0;
}
Demuxing & decoding
如何使用 libavformat 和 libavcodec API 来分解和解码音视频data。
#include <libavutil/imgutils.h>
#include <libavutil/samplefmt.h>
#include <libavutil/timestamp.h>
#include <libavformat/avformat.h>
static AVFormatContext *fmt_ctx = NULL;
static AVCodecContext *video_dec_ctx = NULL, *audio_dec_ctx;
static int width, height;
static enum AVPixelFormat pix_fmt;
static AVStream *video_stream = NULL, *audio_stream = NULL;
static const char *src_filename = NULL;
static const char *video_dst_filename = NULL;
static const char *audio_dst_filename = NULL;
static FILE *video_dst_file = NULL;
static FILE *audio_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, audio_stream_idx = -1;
static AVFrame *frame = NULL;
static AVPacket pkt;
static int video_frame_count = 0;
static int audio_frame_count = 0;
static int refcount = 0;
static int decode_packet(int *got_frame, int cached)
{
int ret = 0;
int decoded = pkt.size;
*got_frame = 0;
if (pkt.stream_index == video_stream_idx) {
/* decode video frame */
ret = avcodec_decode_video2(video_dec_ctx, frame, got_frame, &pkt);
if (ret < 0) {
fprintf(stderr, "Error decoding video frame (%s)\n", av_err2str(ret));
return ret;
}
if (*got_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. */
fprintf(stderr, "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(frame->format));
return -1;
}
printf("video_frame%s n:%d coded_n:%d\n",
cached ? "(cached)" : "",
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);
}
} else if (pkt.stream_index == audio_stream_idx) {
/* decode audio frame */
ret = avcodec_decode_audio4(audio_dec_ctx, frame, got_frame, &pkt);
if (ret < 0) {
fprintf(stderr, "Error decoding audio frame (%s)\n", av_err2str(ret));
return ret;
}
/* Some audio decoders decode only part of the packet, and have to be
* called again with the remainder of the packet data.
* Sample: fate-suite/lossless-audio/luckynight-partial.shn
* Also, some decoders might over-read the packet. */
decoded = FFMIN(ret, pkt.size);
if (*got_frame) {
size_t unpadded_linesize = frame->nb_samples * av_get_bytes_per_sample(frame->format);
printf("audio_frame%s n:%d nb_samples:%d pts:%s\n",
cached ? "(cached)" : "",
audio_frame_count++, frame->nb_samples,
av_ts2timestr(frame->pts, &audio_dec_ctx->time_base));
/* Write the raw audio data samples of the first plane. This works
* fine for packed formats (e.g. AV_SAMPLE_FMT_S16). However,
* most audio decoders output planar audio, which uses a separate
* plane of audio samples for each channel (e.g. AV_SAMPLE_FMT_S16P).
* In other words, this code will write only the first audio channel
* in these cases.
* You should use libswresample or libavfilter to convert the frame
* to packed data. */
fwrite(frame->extended_data[0], 1, unpadded_linesize, audio_dst_file);
}
}
/* If we use frame reference counting, we own the data and need
* to de-reference it when we don't use it anymore */
if (*got_frame && refcount)
av_frame_unref(frame);
return decoded;
}
/** 初始化 AVCodecContext */
static int open_codec_context(int *stream_idx,
AVCodecContext **dec_ctx, AVFormatContext *fmt_ctx, enum AVMediaType type)
{
int ret, stream_index;
AVStream *st;
AVCodec *dec = NULL;
AVDictionary *opts = NULL;
// 根据参数从 AVFormatContext 中找到合适的 stream index
ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0);
if (ret < 0) {
fprintf(stderr, "Could not find %s stream in input file '%s'\n",
av_get_media_type_string(type), src_filename);
return ret;
} else {
stream_index = ret;
// 从 AVFormatContext 拿到AVStream
st = fmt_ctx->streams[stream_index];
/* 找到 stream 的解码器 */
dec = avcodec_find_decoder(st->codecpar->codec_id);
if (!dec) {
fprintf(stderr, "Failed to find %s codec\n",
av_get_media_type_string(type));
return AVERROR(EINVAL);
}
/* 为 decoder 分配一个解码器 context */
*dec_ctx = avcodec_alloc_context3(dec);
if (!*dec_ctx) {
fprintf(stderr, "Failed to allocate the %s codec context\n",
av_get_media_type_string(type));
return AVERROR(ENOMEM);
}
/* 从输入流 Copy 解码参数给输出解码器 context */
if ((ret = avcodec_parameters_to_context(*dec_ctx, st->codecpar)) < 0) {
fprintf(stderr, "Failed to copy %s codec parameters to decoder context\n",
av_get_media_type_string(type));
return ret;
}
/* 初始化 decoders, 是否启用引用计数 */
av_dict_set(&opts, "refcounted_frames", refcount ? "1" : "0", 0);
if ((ret = avcodec_open2(*dec_ctx, dec, &opts)) < 0) {
fprintf(stderr, "Failed to open %s codec\n",
av_get_media_type_string(type));
return ret;
}
*stream_idx = stream_index;
}
return 0;
}
/** 从 采样 format 获取 format */
static int get_format_from_sample_fmt(const char **fmt,
enum AVSampleFormat sample_fmt)
{
int i;
struct sample_fmt_entry {
enum AVSampleFormat sample_fmt;
const char *fmt_be, *fmt_le;
} sample_fmt_entries[] = {
{ AV_SAMPLE_FMT_U8, "u8", "u8" },
{ AV_SAMPLE_FMT_S16, "s16be", "s16le" },
{ AV_SAMPLE_FMT_S32, "s32be", "s32le" },
{ AV_SAMPLE_FMT_FLT, "f32be", "f32le" },
{ AV_SAMPLE_FMT_DBL, "f64be", "f64le" },
};
*fmt = NULL;
for (i = 0; i < FF_ARRAY_ELEMS(sample_fmt_entries); i++) {
struct sample_fmt_entry *entry = &sample_fmt_entries[i];
if (sample_fmt == entry->sample_fmt) {
*fmt = AV_NE(entry->fmt_be, entry->fmt_le);
return 0;
}
}
fprintf(stderr,
"sample format %s is not supported as output format\n",
av_get_sample_fmt_name(sample_fmt));
return -1;
}
int main (int argc, char **argv)
{
int ret = 0, got_frame;
if (argc != 4 && argc != 5) {
fprintf(stderr, "usage: %s [-refcount] input_file video_output_file audio_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"
"audio frames to a rawaudio file named audio_output_file.\n\n"
"If the -refcount option is specified, the program use the\n"
"reference counting frame system which allows keeping a copy of\n"
"the data for longer than one decode call.\n"
"\n", argv[0]);
exit(1);
}
if (argc == 5 && !strcmp(argv[1], "-refcount")) {
refcount = 1;
argv++;
}
// 输入输出文件参数
src_filename = argv[1];
video_dst_filename = argv[2];
audio_dst_filename = argv[3];
/* 打开文件，初始化 AVFormatContext */
if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) {
fprintf(stderr, "Could not open source file %s\n", src_filename);
exit(1);
}
/* 检索 stream 信息 */
if (avformat_find_stream_info(fmt_ctx, NULL) < 0) {
fprintf(stderr, "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) {
fprintf(stderr, "Could not open destination file %s\n", video_dst_filename);
ret = 1;
goto end;
}
/* 分配 image */
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) {
fprintf(stderr, "Could not allocate raw video buffer\n");
goto end;
}
video_dst_bufsize = ret;
}
if (open_codec_context(&audio_stream_idx, &audio_dec_ctx, fmt_ctx, AVMEDIA_TYPE_AUDIO) >= 0) {
audio_stream = fmt_ctx->streams[audio_stream_idx];
audio_dst_file = fopen(audio_dst_filename, "wb");
if (!audio_dst_file) {
fprintf(stderr, "Could not open destination file %s\n", audio_dst_filename);
ret = 1;
goto end;
}
}
/* dump 输入流信息到 stderr */
av_dump_format(fmt_ctx, 0, src_filename, 0);
if (!audio_stream && !video_stream) {
fprintf(stderr, "Could not find audio or video stream in the input, aborting\n");
ret = 1;
goto end;
}
frame = av_frame_alloc();
if (!frame) {
fprintf(stderr, "Could not allocate frame\n");
ret = AVERROR(ENOMEM);
goto end;
}
/* 初始化 packet data 为 NULL, 让 demuxer 完成赋值 */
av_init_packet(&pkt);
pkt.data = NULL;
pkt.size = 0;
if (video_stream)
printf("Demuxing video from file '%s' into '%s'\n", src_filename, video_dst_filename);
if (audio_stream)
printf("Demuxing audio from file '%s' into '%s'\n", src_filename, audio_dst_filename);
/* 从 fmt_ctx 读取帧信息 */
while (av_read_frame(fmt_ctx, &pkt) >= 0) {
AVPacket orig_pkt = pkt;
do {
ret = decode_packet(&got_frame, 0);
if (ret < 0)
break;
pkt.data += ret;
pkt.size -= ret;
} while (pkt.size > 0);
av_packet_unref(&orig_pkt);
}
/* flush 缓存的 frames */
pkt.data = NULL;
pkt.size = 0;
do {
// 解码
decode_packet(&got_frame, 1);
} while (got_frame);
printf("Demuxing 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);
}
// 处理音频流
if (audio_stream) {
enum AVSampleFormat sfmt = audio_dec_ctx->sample_fmt;
int n_channels = audio_dec_ctx->channels;
const char *fmt;
if (av_sample_fmt_is_planar(sfmt)) {
const char *packed = av_get_sample_fmt_name(sfmt);
printf("Warning: the sample format the decoder produced is planar "
"(%s). This example will output the first channel only.\n",
packed ? packed : "?");
sfmt = av_get_packed_sample_fmt(sfmt);
n_channels = 1;
}
if ((ret = get_format_from_sample_fmt(&fmt, sfmt)) < 0)
goto end;
printf("Play the output audio file with the command:\n"
"ffplay -f %s -ac %d -ar %d %s\n",
fmt, n_channels, audio_dec_ctx->sample_rate,
audio_dst_filename);
}
end:
avcodec_free_context(&video_dec_ctx);
avcodec_free_context(&audio_dec_ctx);
avformat_close_input(&fmt_ctx);
if (video_dst_file)
fclose(video_dst_file);
if (audio_dst_file)
fclose(audio_dst_file);
av_frame_free(&frame);
av_free(video_dst_data[0]);
return ret < 0;
}
