1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
extern "C" {
#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;

/* Enable or disable frame reference counting. You are not supposed to support
* both paths in your application but pick the one most appropriate to your
* needs. Look for the use of refcount in this example to see what are the
* differences of API usage between them. */
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);//解码帧 已经弃用不再维护
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) {//帧大小不对
/* 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);//复制帧数据到video_dst_data和video_dst_linesize 因为是rawvideo

/* 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);//解码音频 已经放弃维护
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);//该帧的大小

if (*got_frame) {
size_t unpadded_linesize = frame->nb_samples * av_get_bytes_per_sample(frame->format);//采样数*采样样本大小
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);//对于plane是可以的 planar需要使用libswresample or libavfilter进行优化
}
}

/* 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;
}

static int open_codec_context(int *stream_idx,
AVCodecContext **dec_ctx, AVFormatContext *fmt_ctx, enum AVMediaType type)//根据type从fmt_ctx中返回stream_idx和dec_ctx
{
int ret, stream_index;
AVStream *st;
AVCodec *dec = NULL;
AVDictionary *opts = NULL;

ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0);//根据type 查找流的下标
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;
st = fmt_ctx->streams[stream_index];

/* find decoder for the stream */
dec = avcodec_find_decoder(st->codecpar->codec_id);//根据流保存的编码id 找到解码器
if (!dec) {
fprintf(stderr, "Failed to find %s codec\n",
av_get_media_type_string(type));
return AVERROR(EINVAL);
}

/* Allocate a codec context for the decoder */
*dec_ctx = avcodec_alloc_context3(dec);//根据编解码器 为ctx分配空间和初始化
if (!*dec_ctx) {
fprintf(stderr, "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) {//将codecpar的字段替换dec_ctx内相应的字段
fprintf(stderr, "Failed to copy %s codec parameters to decoder context\n",
av_get_media_type_string(type));
return ret;
}

/* Init the decoders, with or without reference counting */
av_dict_set(&opts, "refcounted_frames", refcount ? "1" : "0", 0);//设置AVDictionary属性
if ((ret = avcodec_open2(*dec_ctx, dec, &opts)) < 0) {//根据AVcode初始化一个编解码上下文
fprintf(stderr, "Failed to open %s codec\n",
av_get_media_type_string(type));
return ret;
}
*stream_idx = stream_index;
}

return 0;
}

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);//大小端
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]);//refcount 引用计数帧系统,但是保存副本的时间比编码长
exit(1);
}
if (argc == 5 && !strcmp(argv[1], "-refcount")) {
refcount = 1;
argv++;
}
src_filename = argv[1];
video_dst_filename = argv[2];
audio_dst_filename = argv[3];

/* open input file, and allocate format context */
if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) {//打开输入流,并且读取文件头 fmt_ctx为NULL时 不必再调用avformat_alloc_context
fprintf(stderr, "Could not open source file %s\n", src_filename);
exit(1);
}

/* retrieve stream information */
if (avformat_find_stream_info(fmt_ctx, NULL) < 0) {//查找流信息
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) {//查找视频流 并得到编码器
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;
}

/* 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);//根据width height pix_fmt分配video_dst_data和video_dst_linesize的一张图片
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) {//查找音频流 并得到编码器
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 input information to stderr */
av_dump_format(fmt_ctx, 0, src_filename, 0);//打印输入输出封装上下文

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();//初始化帧
if (!frame) {
fprintf(stderr, "Could not allocate frame\n");
ret = AVERROR(ENOMEM);
goto end;
}

/* initialize packet, set data to NULL, let the demuxer fill it */
av_init_packet(&pkt);//初始化压缩包
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);

/* read frames from the file */
while (av_read_frame(fmt_ctx, &pkt) >= 0) {
AVPacket orig_pkt = pkt;
do {
ret = decode_packet(&got_frame, 0);//解码一帧
if (ret < 0)
break;
pkt.data += ret;//数据指针移动
pkt.size -= ret;//数据长度减少
} while (pkt.size > 0);
av_packet_unref(&orig_pkt);//删掉缓存
}

/* flush cached frames */
pkt.data = NULL;
pkt.size = 0;
do {
decode_packet(&got_frame, 1);
} while (got_frame);//清除缓存中的帧

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);
}

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);//释放视频解码器
avcodec_free_context(&audio_dec_ctx);//释放音频解码器
avformat_close_input(&fmt_ctx);//释放封装上下文
if (video_dst_file)
fclose(video_dst_file);
if (audio_dst_file)
fclose(audio_dst_file);
av_frame_free(&frame);//释放帧
av_free(video_dst_data[0]);//释放图片

return ret < 0;
}