胡斌 / merge_av

转到一个项目
Toggle navigation Toggle navigation pinning
胡斌
f6f4d7a0 1 parent c73db2f8

first commit of using ffmpeg code

内嵌 并排对比
正在显示 2 个修改的文件 包含 613 行增加 和 316 行删除
... ... @@ -21,6 +21,11 @@ enum media_type{
mt_av = 3,
};
enum media_role {
mr_teacher =0,
mr_student =1,
};
enum timestamp_type{
tt_start = 0,
tt_end = 1,
... ... @@ -33,7 +38,7 @@ public:
string name;
int index;
media_type m_type;
int channel;
media_role m_rote;
int rotate; //degree,0,90,180 ...
};
... ... @@ -47,8 +52,8 @@ public:
float duration;
int index;
int channel;
media_type m_type;
media_role m_rote;
timestamp_type t_type;
};
... ... @@ -120,40 +125,24 @@ char acodec_param[1024];
char pip_param[1024];
char pip1_param[1024];
bool first_time_set = false;
float start_time = 0.0f;
void init_read_file() {
first_time_set = false;
start_time = 0.0f;
}
void addinfo(string t, string name, bool bstart){
void addinfo(float t, string name, bool bstart,media_role role){
media_type mtype = name.substr(name.length() - 4, name.length()) == ".aac" ? mt_audio : mt_video;
if (bstart) {
fileinfo f;
f.start_time = atof(t.c_str());
f.start_time = t;
f.end_time = f.start_time;
f.name = name;
f.m_type = mtype;
f.m_rote = role;
f.rotate = 0;
if (!first_time_set) {
first_time_set = true;
start_time = f.start_time;
}
f.start_time -= start_time;
media_files.push_back(f);
}
else {
int i;
for (i = 0; i < media_files.size(); i++) {
if (media_files[i].name == name) {
media_files[i].end_time = atof(t.c_str());
media_files[i].end_time -= start_time;
media_files[i].end_time = t;
break;
}
}
... ... @@ -187,7 +176,6 @@ void addinfo(float start, float duration, string name, int channel){
f.end_time = f.start_time + duration;
f.name = name;
f.m_type = mtype;
f.channel = channel;
media_files.push_back(f);
}
... ... @@ -680,7 +668,6 @@ void add_media_infos()
m.end_time = f.end_time;
m.m_type = f.m_type;
m.t_type = tt_start;
m.channel = f.channel;
m.duration = f.end_time - f.start_time;
m.type_time = m.start_time;
m.rotate = f.rotate;
... ... @@ -847,54 +834,6 @@ int find_video_between_the_audio()
return video_index;
}
int merge_video_pip(vector<media_info> & files)
{
char ch0_file[1024], ch1_file[1024];
vector<string> merge_video_files;
media_info ch0_start, ch0_end, ch1_start, ch1_end;
if (files[0].channel == 0) {
ch0_start = files[0];
ch0_end = files[2];
ch1_start = files[1];
ch1_end = files[3];
}
else {
ch0_start = files[1];
ch0_end = files[3];
ch1_start = files[0];
ch1_end = files[2];
}
if (ch0_start.type_time - ch0_start.start_time > 0.10 || ch0_end.end_time - ch0_end.type_time > 0.10) {
sprintf(ch0_file, "%d_%s", nf, ch0_start.name.c_str());
split_av(ch0_start.name.c_str(), ch0_start.type_time - ch0_start.start_time, ch0_end.type_time - ch0_start.type_time, ch0_file);
tmp_files.push_back(ch0_file);
}
else{
strcpy(ch0_file, ch0_start.name.c_str());
}
if (ch1_start.type_time - ch1_start.start_time > 0.10 || ch1_end.end_time - ch1_end.type_time > 0.10) {
sprintf(ch1_file, "%d_%s", nf, ch1_start.name.c_str());
split_av(ch1_start.name.c_str(), ch1_start.type_time - ch1_start.start_time, ch1_end.type_time - ch1_start.type_time, ch1_file);
tmp_files.push_back(ch1_file);
}
else{
strcpy(ch1_file, ch1_start.name.c_str());
}
sprintf(destfile, "%d.ts", nf);
merge_video_pip(ch0_file, ch1_file, destfile);
merged_files.push_back(destfile);
nf++;
return 0;
}
int transcode_file(vector<media_info> files)
{
... ... @@ -952,10 +891,6 @@ bool is_audio_start(int index)
return (sorted_infos[index].m_type == mt_audio && sorted_infos[index].t_type == tt_start);
}
bool is_ch0_start(int index)
{
return (sorted_infos[index].channel == 0 && sorted_infos[index].t_type == tt_start);
}
int split_audio_for_video(int audio_start,vector<media_info> & result)
... ... @@ -1362,159 +1297,7 @@ int process_va_files()
return 0;
}
int process_merged_files()
{
char outputfile[1024];
vector<media_info> cur_processing;
int nOutPutFile = 0;
float start_time;
bool is_start = true;
string start_file;
while (sorted_infos.size())
{
int channel = sorted_infos[0].channel;
if (sorted_infos[1].index == sorted_infos[0].index)
{
get_front_info(1, cur_processing);
transcode_file(cur_processing);
}
else if (sorted_infos[1].type_time - sorted_infos[0].type_time > 0.2) {
split_ch0_for_no_process(cur_processing);
transcode_file(cur_processing);
}
else {
split_ch0_for_ch1( cur_processing);
merge_video_pip(cur_processing);
}
//if the duration between the processed end and the start of not processed is large than 200 ms, reopen a new file
if (is_start){
start_time = cur_processing[0].start_time;
start_file = cur_processing[0].name;
is_start = false;
}
if (is_need_output(nOutPutFile, cur_processing, start_file.c_str(), outputfile, PIP_PREFIX)){
nOutPutFile++;
concate_files_and_adjust_timecode(outputfile);
save_out_info(start_time, outputfile);
is_start = true;
}
}
return 0;
}
int process_record_file_to_ts()
{
//don't split video, for a video, using merged audios to mix with it
//for audio, mix with video or jpg
char outputfile[1024];
init_merge_av();
if (!media_files.size()){
return 0;
}
fp_out_info = fopen(out_info_file, "wt");
// judge if it is only one type
media_type mt = media_files[0].m_type;
bool only_one_type = true;
for (int i = 1; i < media_files.size(); i++){
if (mt != media_files[i].m_type){
only_one_type = false;
break;
}
}
if (only_one_type){
if (mt == mt_audio) {
for (int i = 0; i < media_files.size(); i++){
fileinfo audio = media_files[i];
get_output_file_name(i, audio.name.c_str(), MERGED_PREFIX, outputfile);
merge_audio_pic(audio.name.c_str(), blank_pic_file, outputfile);
save_out_info(audio.start_time, outputfile);
}
}
else {
for (int i = 0; i < media_files.size(); i++){
fileinfo video = media_files[i];
get_output_file_name(i, video.name.c_str(), MERGED_PREFIX, outputfile);
merge_video_silence(video, silence_aac_file, destfile);
save_out_info(video.start_time, outputfile);
}
}
}
else {
process_va_files();
}
if (fp_out_info) {
fclose(fp_out_info);
}
return 0;
}
int process_merged_files_to_pip_files()
{
//don't split video, for a video, using merged audios to mix with it
//for audio, mix with video or jpg
char outputfile[1024];
if (!media_files.size()){
return 0;
}
init_merge_pip();
fp_out_info = fopen(out_info_file, "wt");
process_merged_files();
if (fp_out_info) {
fclose(fp_out_info);
}
return 0;
}
int readfile(const char * filename)
{
init_read_file();
media_files.clear();
ifstream fin(filename);
if (!fin) {
return -1;
}
const int LINE_LENGTH = 1000;
char str[LINE_LENGTH];
while (fin.getline(str, LINE_LENGTH))
{
vector < string > res;
split(str, " ", res);
if (res.size() >= 3) {
if (res[2] == "create"){
addinfo(res[0], res[1], true);
}
else if (res[2] == "close") {
addinfo(res[0], res[1], false);
}
else if (res[2] == "info") {
if (res.size() > 5) {
const char * pInfo = res[5].c_str();
if (!strncmp(pInfo, "rotation=", 9)){
addinfo(res[0].c_str(), res[1].c_str(), pInfo + 9);
}
}
}
}
}
return 0;
}
// parse the filename like 4165000_20180203013327202.aac
#define get_sub_str_to_x(x , source, len, result) strncpy(x, source, len); x[len] = 0; source += len; result = atoi(x);
... ... @@ -1524,8 +1307,12 @@ float get_start_time_from_filename(const char * filename)
int year, month, day, hour, min, sec, minsec;
char buf[5];
const char * start = strstr(filename, "_");
const char * end = strstr(start + 1, "_");
if (end) {//get the next
start = end;
}
start++;
const char * end = strstr(start, ".");
end = strstr(start, ".");
get_sub_str_to_x(buf, start, 4, year);
... ... @@ -1552,37 +1339,43 @@ float get_start_time_from_filename(const char * filename)
return (float)(t) + minsec / 1000.0;
}
vector<string> all_input_files_for_pip;
int readfile(const char * filename, int channel)
int readfile(const char * filename, media_role role)
{
init_read_file();
ifstream fin(filename);
if (!fin) {
return -1;
}
float start_time = get_start_time_from_filename(filename);
const int LINE_LENGTH = 1000;
char str[LINE_LENGTH];
float start_time;
bool bstart_time = true;
while (fin.getline(str, LINE_LENGTH))
{
vector < string > res;
split(str, " ", res);
if (res.size() == 3) {
if (bstart_time) {
start_time = get_start_time_from_filename(res[2].c_str() + strlen(MERGED_PREFIX));
bstart_time = false;
if (res.size() >= 3) {
if (res[2] == "create"){
addinfo(start_time + atof(res[0].c_str()), res[1], true, role);
}
else if (res[2] == "close") {
addinfo(start_time + atof(res[0].c_str()), res[1], false, role);
}
else if (res[2] == "info") {
if (res.size() > 5) {
const char * pInfo = res[5].c_str();
if (!strncmp(pInfo, "rotation=", 9)){
addinfo(res[0].c_str(), res[1].c_str(), pInfo + 9);
}
}
}
addinfo(atof(res[0].c_str()) + start_time ,atof(res[1].c_str()) , res[2], channel);
all_input_files_for_pip.push_back(res[2]);
}
}
return 0;
}
vector<string> all_input_files_for_pip;
void load_codec_param()
{
... ... @@ -1645,7 +1438,7 @@ void get_outinfo_file_name(char * input)
strcat(out_info_file, "_out.txt");
}
int process_record_info_to_ts(char * record_info, vector<string> & merged_info1, vector<string> & merged_info2)
int load_record_info(char * record_info)
{
ifstream fin(record_info);
if (!fin) {
... ... @@ -1657,6 +1450,9 @@ int process_record_info_to_ts(char * record_info, vector<string> & merged_info1,
bool bInTeacher = false;
bool bInStudent = false;
int nstudent = 0;
media_files.clear();
while (fin.getline(str, LINE_LENGTH))
{
if (!strncmp(str, "teacher:", 8)){
... ... @@ -1673,40 +1469,26 @@ int process_record_info_to_ts(char * record_info, vector<string> & merged_info1,
continue;//assume the file name > 20
}
else if (bInTeacher){
readfile(str);
get_outinfo_file_name(str);
merged_info1.push_back(out_info_file);
process_record_file_to_ts();
readfile(str, mr_teacher);
}
else if (bInStudent){
readfile(str);
get_outinfo_file_name(str);
merged_info2.push_back(out_info_file);
process_record_file_to_ts();
readfile(str, mr_student);
}
}
unifiy_start_time();
add_media_infos();
return 0;
}
//#define TEST
int main(int argc, char * argv[])
{
#ifdef TEST
const char * video = "D:\\media\\talk\\20181112\\talk915_824250397_105638\\137786519_20181112105817677.ts";
const char * dest = "D:\\media\\talk\\20181112\\talk915_824250397_105638\\137786519_20181112105817677.ts.jpg";
get_config_path();
load_codec_param();
init_merge_av();
get_video_last_frame_jpeg(video, dest);
merge_pic_silence(dest, 1.56, "D:\\media\\talk\\20181112\\talk915_824250397_105638\\137786519_20181112105817677_last_s156.ts");
#endif
if (argc < 2) {
printf(" merge_pip 1.0.2\n");
printf(" run ffmpeg to merge video files to one pip video according to record info file,\nusage:");
printf(" merge_pip 2.0.0\n");
printf(" merge video files to one pip video according to record info file,\nusage:");
printf("\n %s record_info_filename [-p] [-k]", argv[0]);
printf("\n -p :only print the command,don't run ffmpeg");
printf("\n -k :keep the temp files");
printf("\n -d :individual files for different time segment");
printf("\n\n");
return -1;
... ... @@ -1716,85 +1498,598 @@ int main(int argc, char * argv[])
load_codec_param();
bool bmerge_files = true;
for (int i = 2; i < argc; i++){
if (!strcmp(argv[i], "-p")){
only_print = true;
if (!strcmp(argv[i], "-d")){
out_one_video = false;
}
else if (!strcmp(argv[i], "-k")){
keep_tmp_files = true;
}
else if (!strcmp(argv[i], "-n")){
bmerge_files = false;
load_record_info(argv[1]);
}
#define __STDC_FORMAT_MACROS
#include <stdint.h>
#include <inttypes.h>
extern "C" {
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavfilter/avfiltergraph.h>
#include <libavfilter/buffersink.h>
#include <libavfilter/buffersrc.h>
#include <libavutil/opt.h>
#include <libavutil/pixdesc.h>
}
#ifdef WIN32
#pragma comment(lib, "avcodec.lib")
#pragma comment(lib, "avdevice.lib")
#pragma comment(lib, "avfilter.lib")
#pragma comment(lib, "avformat.lib")
#pragma comment(lib, "avutil.lib")
#pragma comment(lib, "postproc.lib")
#pragma comment(lib, "swresample.lib")
#pragma comment(lib, "swscale.lib")
#endif
#if _MSC_VER
#define snprintf _snprintf
#define PRIu64 "I64u"
#define PRId64 "I64d"
#define PRIx64 "I64x"
#define PRIX64 "I64X"
#endif
static AVFormatContext *ifmt_ctx;
static AVFormatContext *ofmt_ctx;
typedef struct FilteringContext {
AVFilterContext *buffersink_ctx;
AVFilterContext *buffersrc_ctx;
AVFilterGraph *filter_graph;
} FilteringContext;
static FilteringContext *filter_ctx;
static int open_input_file(const char *filename)
{
int ret;
unsigned int i;
ifmt_ctx = NULL;
if ((ret = avformat_open_input(&ifmt_ctx, filename, NULL, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
return ret;
}
else if (!strcmp(argv[i], "-d")){
out_one_video = false;
if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
return ret;
}
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
AVStream *stream;
AVCodecContext *codec_ctx;
stream = ifmt_ctx->streams[i];
codec_ctx = stream->codec;
/* Reencode video & audio and remux subtitles etc. */
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
/* Open decoder */
ret = avcodec_open2(codec_ctx,
avcodec_find_decoder(codec_ctx->codec_id), NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
return ret;
}
}
}
av_dump_format(ifmt_ctx, 0, filename, 0);
return 0;
}
static int open_output_file(const char *filename)
{
AVStream *out_stream;
AVStream *in_stream;
AVCodecContext *dec_ctx, *enc_ctx;
AVCodec *encoder;
int ret;
unsigned int i;
ofmt_ctx = NULL;
avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, filename);
if (!ofmt_ctx) {
av_log(NULL, AV_LOG_ERROR, "Could not create output context\n");
return AVERROR_UNKNOWN;
}
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
out_stream = avformat_new_stream(ofmt_ctx, NULL);
if (!out_stream) {
av_log(NULL, AV_LOG_ERROR, "Failed allocating output stream\n");
return AVERROR_UNKNOWN;
}
in_stream = ifmt_ctx->streams[i];
dec_ctx = in_stream->codec;
enc_ctx = out_stream->codec;
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
/* in this example, we choose transcoding to same codec */
encoder = avcodec_find_encoder(dec_ctx->codec_id);
if (!encoder) {
av_log(NULL, AV_LOG_FATAL, "Necessary encoder not found\n");
return AVERROR_INVALIDDATA;
}
/* In this example, we transcode to same properties (picture size,
* sample rate etc.). These properties can be changed for output
* streams easily using filters */
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
enc_ctx->height = dec_ctx->height;
enc_ctx->width = dec_ctx->width;
enc_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio;
/* take first format from list of supported formats */
enc_ctx->pix_fmt = encoder->pix_fmts[0];
/* video time_base can be set to whatever is handy and supported by encoder */
enc_ctx->time_base = dec_ctx->time_base;
}
else {
enc_ctx->sample_rate = dec_ctx->sample_rate;
enc_ctx->channel_layout = dec_ctx->channel_layout;
enc_ctx->channels = av_get_channel_layout_nb_channels(enc_ctx->channel_layout);
/* take first format from list of supported formats */
enc_ctx->sample_fmt = encoder->sample_fmts[0];
enc_ctx->time_base.num = 1;
enc_ctx->time_base.den = enc_ctx->sample_rate;
}
vector<string> merged_info1;
vector<string> merged_info2;
#if 0
if (bmerge_files) {
if (readfile(argv[1]) < 0) {
printf("open file: %s error", argv[1]);
return -2;
/* Third parameter can be used to pass settings to encoder */
ret = avcodec_open2(enc_ctx, encoder, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open video encoder for stream #%u\n", i);
return ret;
}
}
else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) {
av_log(NULL, AV_LOG_FATAL, "Elementary stream #%d is of unknown type, cannot proceed\n", i);
return AVERROR_INVALIDDATA;
}
else {
/* if this stream must be remuxed */
ret = avcodec_copy_context(ofmt_ctx->streams[i]->codec,
ifmt_ctx->streams[i]->codec);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Copying stream context failed\n");
return ret;
}
}
get_outinfo_file_name(argv[1]);
strcpy(merged_info1, out_info_file);
process_record_file_to_ts();
if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
enc_ctx->flags |= CODEC_FLAG_GLOBAL_HEADER;
}
av_dump_format(ofmt_ctx, 0, filename, 1);
if (!(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) {
ret = avio_open(&ofmt_ctx->pb, filename, AVIO_FLAG_WRITE);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Could not open output file '%s'", filename);
return ret;
}
}
if (readfile(argv[2]) < 0) {
printf("open file: %s error", argv[1]);
return -2;
/* init muxer, write output file header */
ret = avformat_write_header(ofmt_ctx, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error occurred when opening output file\n");
return ret;
}
get_outinfo_file_name(argv[2]);
strcpy(merged_info2, out_info_file);
process_record_file_to_ts();
return 0;
}
static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx,
AVCodecContext *enc_ctx, const char *filter_spec)
{
char args[512];
int ret = 0;
AVFilter *buffersrc = NULL;
AVFilter *buffersink = NULL;
AVFilterContext *buffersrc_ctx = NULL;
AVFilterContext *buffersink_ctx = NULL;
AVFilterInOut *outputs = avfilter_inout_alloc();
AVFilterInOut *inputs = avfilter_inout_alloc();
AVFilterGraph *filter_graph = avfilter_graph_alloc();
if (!outputs || !inputs || !filter_graph) {
ret = AVERROR(ENOMEM);
goto end;
}
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
buffersrc = avfilter_get_by_name("buffer");
buffersink = avfilter_get_by_name("buffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}
snprintf(args, sizeof(args),
"video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
dec_ctx->time_base.num, dec_ctx->time_base.den,
dec_ctx->sample_aspect_ratio.num,
dec_ctx->sample_aspect_ratio.den);
ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer source\n");
goto end;
}
ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer sink\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "pix_fmts",
(uint8_t*)&enc_ctx->pix_fmt, sizeof(enc_ctx->pix_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n");
goto end;
}
}
else if (dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
buffersrc = avfilter_get_by_name("abuffer");
buffersink = avfilter_get_by_name("abuffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}
if (!dec_ctx->channel_layout)
dec_ctx->channel_layout =
av_get_default_channel_layout(dec_ctx->channels);
sprintf(args, //sizeof(args),
"time_base=%d/%d:sample_rate=%d:sample_fmt=%s:channel_layout=0x%"PRIx64,
dec_ctx->time_base.num, dec_ctx->time_base.den, dec_ctx->sample_rate,
av_get_sample_fmt_name(dec_ctx->sample_fmt),
dec_ctx->channel_layout);
ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer source\n");
goto end;
}
ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer sink\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "sample_fmts",
(uint8_t*)&enc_ctx->sample_fmt, sizeof(enc_ctx->sample_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample format\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "channel_layouts",
(uint8_t*)&enc_ctx->channel_layout,
sizeof(enc_ctx->channel_layout), AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output channel layout\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "sample_rates",
(uint8_t*)&enc_ctx->sample_rate, sizeof(enc_ctx->sample_rate),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample rate\n");
goto end;
}
}
else {
strcpy(merged_info1, argv[1]);
strcpy(merged_info2, argv[2]);
ret = AVERROR_UNKNOWN;
goto end;
}
#else
process_record_info_to_ts(argv[1], merged_info1, merged_info2);
#endif
/* Endpoints for the filter graph. */
outputs->name = av_strdup("in");
outputs->filter_ctx = buffersrc_ctx;
outputs->pad_idx = 0;
outputs->next = NULL;
media_files.clear();
for (int i = 0; i < merged_info1.size(); i++) {
if (readfile(merged_info1[i].c_str(), 0) < 0) {
printf("open file: %s error", merged_info1[i].c_str());
return -2;
inputs->name = av_strdup("out");
inputs->filter_ctx = buffersink_ctx;
inputs->pad_idx = 0;
inputs->next = NULL;
if (!outputs->name || !inputs->name) {
ret = AVERROR(ENOMEM);
goto end;
}
if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec,
&inputs, &outputs, NULL)) < 0)
goto end;
if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
goto end;
/* Fill FilteringContext */
fctx->buffersrc_ctx = buffersrc_ctx;
fctx->buffersink_ctx = buffersink_ctx;
fctx->filter_graph = filter_graph;
end:
avfilter_inout_free(&inputs);
avfilter_inout_free(&outputs);
return ret;
}
static int init_filters(void)
{
const char *filter_spec;
unsigned int i;
int ret;
filter_ctx = (FilteringContext *)av_malloc_array(ifmt_ctx->nb_streams, sizeof(*filter_ctx));
if (!filter_ctx)
return AVERROR(ENOMEM);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
filter_ctx[i].buffersrc_ctx = NULL;
filter_ctx[i].buffersink_ctx = NULL;
filter_ctx[i].filter_graph = NULL;
if (!(ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO
|| ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO))
continue;
if (ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO)
filter_spec = "null"; /* passthrough (dummy) filter for video */
else
filter_spec = "anull"; /* passthrough (dummy) filter for audio */
ret = init_filter(&filter_ctx[i], ifmt_ctx->streams[i]->codec,
ofmt_ctx->streams[i]->codec, filter_spec);
if (ret)
return ret;
}
return 0;
}
static int encode_write_frame(AVFrame *filt_frame, unsigned int stream_index, int *got_frame) {
int ret;
int got_frame_local;
AVPacket enc_pkt;
int(*enc_func)(AVCodecContext *, AVPacket *, const AVFrame *, int *) =
(ifmt_ctx->streams[stream_index]->codec->codec_type ==
AVMEDIA_TYPE_VIDEO) ? avcodec_encode_video2 : avcodec_encode_audio2;
if (!got_frame)
got_frame = &got_frame_local;
av_log(NULL, AV_LOG_INFO, "Encoding frame\n");
/* encode filtered frame */
enc_pkt.data = NULL;
enc_pkt.size = 0;
av_init_packet(&enc_pkt);
ret = enc_func(ofmt_ctx->streams[stream_index]->codec, &enc_pkt,
filt_frame, got_frame);
av_frame_free(&filt_frame);
if (ret < 0)
return ret;
if (!(*got_frame))
return 0;
/* prepare packet for muxing */
enc_pkt.stream_index = stream_index;
av_packet_rescale_ts(&enc_pkt,
ofmt_ctx->streams[stream_index]->codec->time_base,
ofmt_ctx->streams[stream_index]->time_base);
av_log(NULL, AV_LOG_DEBUG, "Muxing frame\n");
/* mux encoded frame */
ret = av_interleaved_write_frame(ofmt_ctx, &enc_pkt);
return ret;
}
for (int i = 0; i < merged_info2.size(); i++) {
if (readfile(merged_info2[i].c_str(), 1) < 0) {
printf("open file: %s error", merged_info2[i].c_str());
return -2;
static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index)
{
int ret;
AVFrame *filt_frame;
av_log(NULL, AV_LOG_INFO, "Pushing decoded frame to filters\n");
/* push the decoded frame into the filtergraph */
ret = av_buffersrc_add_frame_flags(filter_ctx[stream_index].buffersrc_ctx,
frame, 0);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n");
return ret;
}
/* pull filtered frames from the filtergraph */
while (1) {
filt_frame = av_frame_alloc();
if (!filt_frame) {
ret = AVERROR(ENOMEM);
break;
}
av_log(NULL, AV_LOG_INFO, "Pulling filtered frame from filters\n");
ret = av_buffersink_get_frame(filter_ctx[stream_index].buffersink_ctx,
filt_frame);
if (ret < 0) {
/* if no more frames for output - returns AVERROR(EAGAIN)
* if flushed and no more frames for output - returns AVERROR_EOF
* rewrite retcode to 0 to show it as normal procedure completion
*/
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
ret = 0;
av_frame_free(&filt_frame);
break;
}
#if 0
get_outinfo_file_name(argv[1], argv[2]);
#else
get_outinfo_file_name(argv[1]);
#endif
filt_frame->pict_type = AV_PICTURE_TYPE_NONE;
ret = encode_write_frame(filt_frame, stream_index, NULL);
if (ret < 0)
break;
}
process_merged_files_to_pip_files();
return ret;
}
if (!keep_tmp_files && bmerge_files) {
removefiles(all_input_files_for_pip);
removefiles(merged_info1);
removefiles(merged_info2);
}
static int flush_encoder(unsigned int stream_index)
{
int ret;
int got_frame;
if (!(ofmt_ctx->streams[stream_index]->codec->codec->capabilities &
CODEC_CAP_DELAY))
return 0;
while (1) {
av_log(NULL, AV_LOG_INFO, "Flushing stream #%u encoder\n", stream_index);
ret = encode_write_frame(NULL, stream_index, &got_frame);
if (ret < 0)
break;
if (!got_frame)
return 0;
}
return ret;
}
int transcode(int argc, char *argv[]){
int ret;
AVPacket packet;
AVFrame *frame = NULL;
enum AVMediaType type;
unsigned int stream_index;
unsigned int i;
int got_frame;
int(*dec_func)(AVCodecContext *, AVFrame *, int *, const AVPacket *);
memset(&packet, 0, sizeof(AVPacket));
if (argc != 3) {
av_log(NULL, AV_LOG_ERROR, "Usage: %s <input file> <output file>\n", argv[0]);
return 1;
}
av_register_all();
avfilter_register_all();
if ((ret = open_input_file(argv[1])) < 0)
goto end;
if ((ret = open_output_file(argv[2])) < 0)
goto end;
if ((ret = init_filters()) < 0)
goto end;
/* read all packets */
while (1) {
if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0)
break;
stream_index = packet.stream_index;
type = ifmt_ctx->streams[packet.stream_index]->codec->codec_type;
av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n",
stream_index);
if (filter_ctx[stream_index].filter_graph) {
av_log(NULL, AV_LOG_DEBUG, "Going to reencode&filter the frame\n");
frame = av_frame_alloc();
if (!frame) {
ret = AVERROR(ENOMEM);
break;
}
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
ifmt_ctx->streams[stream_index]->codec->time_base);
dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 :
avcodec_decode_audio4;
ret = dec_func(ifmt_ctx->streams[stream_index]->codec, frame,
&got_frame, &packet);
if (ret < 0) {
av_frame_free(&frame);
av_log(NULL, AV_LOG_ERROR, "Decoding failed\n");
break;
}
if (got_frame) {
frame->pts = av_frame_get_best_effort_timestamp(frame);
ret = filter_encode_write_frame(frame, stream_index);
av_frame_free(&frame);
if (ret < 0)
goto end;
}
else {
av_frame_free(&frame);
}
}
else {
/* remux this frame without reencoding */
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
ofmt_ctx->streams[stream_index]->time_base);
ret = av_interleaved_write_frame(ofmt_ctx, &packet);
if (ret < 0)
goto end;
}
av_packet_unref(&packet);
}
/* flush filters and encoders */
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
/* flush filter */
if (!filter_ctx[i].filter_graph)
continue;
ret = filter_encode_write_frame(NULL, i);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing filter failed\n");
goto end;
}
/* flush encoder */
ret = flush_encoder(i);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing encoder failed\n");
goto end;
}
}
av_write_trailer(ofmt_ctx);
end:
av_packet_unref(&packet);
av_frame_free(&frame);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
avcodec_close(ifmt_ctx->streams[i]->codec);
if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && ofmt_ctx->streams[i]->codec)
avcodec_close(ofmt_ctx->streams[i]->codec);
if (filter_ctx && filter_ctx[i].filter_graph)
avfilter_graph_free(&filter_ctx[i].filter_graph);
}
av_free(filter_ctx);
avformat_close_input(&ifmt_ctx);
if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE))
avio_closep(&ofmt_ctx->pb);
avformat_free_context(ofmt_ctx);
//if (ret < 0)
// av_log(NULL, AV_LOG_ERROR, "Error occurred: %s\n", av_err2str(ret));
return ret ? 1 : 0;
}
... ...
... ... @@ -53,10 +53,12 @@
<WarningLevel>Level3</WarningLevel>
<Optimization>Disabled</Optimization>
<PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;_LIB;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<AdditionalIncludeDirectories>..\..\liveAssistant\third-lib\ffmpeg\include</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<GenerateDebugInformation>true</GenerateDebugInformation>
<AdditionalLibraryDirectories>..\..\liveAssistant\third-lib\ffmpeg\lib;</AdditionalLibraryDirectories>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
... ...