ffmpeg/doc/examples/demuxing_decoding.c

387 lines
14 KiB
C
Raw Normal View History

2012-08-29 23:41:30 +02:00
/*
* Copyright (c) 2012 Stefano Sabatini
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
/**
* @file
* Demuxing and decoding example.
2012-08-29 23:41:30 +02:00
*
* Show how to use the libavformat and libavcodec API to demux and
* decode audio and video data.
* @example doc/examples/demuxing_decoding.c
2012-08-29 23:41:30 +02:00
*/
#include <libavutil/imgutils.h>
#include <libavutil/samplefmt.h>
2012-08-29 23:41:30 +02:00
#include <libavutil/timestamp.h>
#include <libavformat/avformat.h>
static AVFormatContext *fmt_ctx = NULL;
static AVCodecContext *video_dec_ctx = NULL, *audio_dec_ctx;
static AVStream *video_stream = NULL, *audio_stream = NULL;
2012-08-29 23:41:30 +02:00
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;
2012-08-29 23:41:30 +02:00
static AVFrame *frame = NULL;
static AVPacket pkt;
static int video_frame_count = 0;
static int audio_frame_count = 0;
2012-08-29 23:41:30 +02:00
/* The different ways of decoding and managing data memory. You are not
* supposed to support all the modes in your application but pick the one most
* appropriate to your needs. Look for the use of api_mode in this example to
* see what are the differences of API usage between them */
enum {
API_MODE_OLD = 0, /* old method, deprecated */
API_MODE_NEW_API_REF_COUNT = 1, /* new method, using the frame reference counting */
API_MODE_NEW_API_NO_REF_COUNT = 2, /* new method, without reference counting */
};
static int api_mode = API_MODE_OLD;
2012-08-29 23:41:30 +02:00
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\n");
return ret;
}
if (*got_frame) {
printf("video_frame%s n:%d coded_n:%d pts:%s\n",
cached ? "(cached)" : "",
video_frame_count++, frame->coded_picture_number,
av_ts2timestr(frame->pts, &video_dec_ctx->time_base));
/* 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,
video_dec_ctx->pix_fmt, video_dec_ctx->width, video_dec_ctx->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\n");
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 the new API with reference counting, we own the data and need
* to de-reference it when we don't use it anymore */
if (*got_frame && api_mode == API_MODE_NEW_API_REF_COUNT)
av_frame_unref(frame);
return decoded;
}
static int open_codec_context(int *stream_idx,
AVFormatContext *fmt_ctx, enum AVMediaType type)
{
int ret;
AVStream *st;
AVCodecContext *dec_ctx = NULL;
AVCodec *dec = NULL;
AVDictionary *opts = NULL;
2012-08-29 23:41:30 +02:00
ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0);
2012-08-29 23:41:30 +02:00
if (ret < 0) {
fprintf(stderr, "Could not find %s stream in input file '%s'\n",
av_get_media_type_string(type), src_filename);
2012-08-29 23:41:30 +02:00
return ret;
} else {
*stream_idx = ret;
st = fmt_ctx->streams[*stream_idx];
/* find decoder for the stream */
dec_ctx = st->codec;
dec = avcodec_find_decoder(dec_ctx->codec_id);
if (!dec) {
fprintf(stderr, "Failed to find %s codec\n",
av_get_media_type_string(type));
return ret;
}
/* Init the decoders, with or without reference counting */
if (api_mode == API_MODE_NEW_API_REF_COUNT)
av_dict_set(&opts, "refcounted_frames", "1", 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;
}
2012-08-29 23:41:30 +02:00
}
return 0;
}
2012-08-29 23:41:30 +02:00
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;
2012-08-29 23:41:30 +02:00
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;
}
2012-08-29 23:41:30 +02:00
}
fprintf(stderr,
"sample format %s is not supported as output format\n",
av_get_sample_fmt_name(sample_fmt));
return -1;
2012-08-29 23:41:30 +02:00
}
int main (int argc, char **argv)
{
int ret = 0, got_frame;
2012-08-29 23:41:30 +02:00
if (argc != 4 && argc != 5) {
fprintf(stderr, "usage: %s [-refcount=<old|new_norefcount|new_refcount>] "
"input_file video_output_file audio_output_file\n"
2012-08-29 23:41:30 +02:00
"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. If unset, it's using\n"
"the classic old method.\n"
2012-08-29 23:41:30 +02:00
"\n", argv[0]);
exit(1);
}
if (argc == 5) {
const char *mode = argv[1] + strlen("-refcount=");
if (!strcmp(mode, "old")) api_mode = API_MODE_OLD;
else if (!strcmp(mode, "new_norefcount")) api_mode = API_MODE_NEW_API_NO_REF_COUNT;
else if (!strcmp(mode, "new_refcount")) api_mode = API_MODE_NEW_API_REF_COUNT;
else {
fprintf(stderr, "unknow mode '%s'\n", mode);
exit(1);
}
argv++;
}
2012-08-29 23:41:30 +02:00
src_filename = argv[1];
video_dst_filename = argv[2];
audio_dst_filename = argv[3];
2012-08-29 23:41:30 +02:00
/* register all formats and codecs */
av_register_all();
/* open input file, and allocate format context */
2012-08-29 23:41:30 +02:00
if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) {
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) {
fprintf(stderr, "Could not find stream information\n");
exit(1);
}
if (open_codec_context(&video_stream_idx, fmt_ctx, AVMEDIA_TYPE_VIDEO) >= 0) {
video_stream = fmt_ctx->streams[video_stream_idx];
video_dec_ctx = video_stream->codec;
2012-08-29 23:41:30 +02:00
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 */
ret = av_image_alloc(video_dst_data, video_dst_linesize,
video_dec_ctx->width, video_dec_ctx->height,
video_dec_ctx->pix_fmt, 1);
if (ret < 0) {
fprintf(stderr, "Could not allocate raw video buffer\n");
goto end;
}
video_dst_bufsize = ret;
2012-08-29 23:41:30 +02:00
}
if (open_codec_context(&audio_stream_idx, fmt_ctx, AVMEDIA_TYPE_AUDIO) >= 0) {
audio_stream = fmt_ctx->streams[audio_stream_idx];
audio_dec_ctx = audio_stream->codec;
audio_dst_file = fopen(audio_dst_filename, "wb");
if (!audio_dst_file) {
fprintf(stderr, "Could not open destination file %s\n", video_dst_filename);
ret = 1;
goto end;
}
2012-08-29 23:41:30 +02:00
}
/* dump input information to 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");
2012-08-29 23:41:30 +02:00
ret = 1;
goto end;
}
/* When using the new API, you need to use the libavutil/frame.h API, while
* the classic frame management is available in libavcodec */
if (api_mode == API_MODE_OLD)
frame = avcodec_alloc_frame();
else
frame = av_frame_alloc();
if (!frame) {
fprintf(stderr, "Could not allocate frame\n");
ret = AVERROR(ENOMEM);
2012-08-29 23:41:30 +02:00
goto end;
}
/* initialize packet, set data to NULL, let the demuxer fill it */
av_init_packet(&pkt);
pkt.data = NULL;
pkt.size = 0;
2012-08-29 23:41:30 +02:00
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);
2012-08-29 23:41:30 +02:00
/* read frames from the file */
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_free_packet(&orig_pkt);
}
2012-08-29 23:41:30 +02:00
/* flush cached frames */
pkt.data = NULL;
pkt.size = 0;
do {
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(video_dec_ctx->pix_fmt), video_dec_ctx->width, video_dec_ctx->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);
}
2012-08-29 23:41:30 +02:00
end:
avcodec_close(video_dec_ctx);
avcodec_close(audio_dec_ctx);
2012-08-29 23:41:30 +02:00
avformat_close_input(&fmt_ctx);
if (video_dst_file)
fclose(video_dst_file);
if (audio_dst_file)
fclose(audio_dst_file);
if (api_mode == API_MODE_OLD)
avcodec_free_frame(&frame);
else
av_frame_free(&frame);
av_free(video_dst_data[0]);
2012-08-29 23:41:30 +02:00
return ret < 0;
}