static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt, const char *tag)
{
AVRational *time_base = &fmt_ctx->streams[pkt->stream_index]->time_base;
printf("%s: pts:%s pts_time:%s dts:%s dts_time:%s duration:%s duration_time:%s stream_index:%d\n",
tag,
av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, time_base),
av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, time_base),
av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, time_base),
pkt->stream_index);
}
static void check_black_end(AVFilterContext *ctx)
{
BlackDetectContext *blackdetect = ctx->priv;
AVFilterLink *inlink = ctx->inputs[0];
if ((blackdetect->black_end - blackdetect->black_start) >= blackdetect->black_min_duration) {
av_log(blackdetect, AV_LOG_INFO,
"black_start:%s black_end:%s black_duration:%s\n",
av_ts2timestr(blackdetect->black_start, &inlink->time_base),
av_ts2timestr(blackdetect->black_end, &inlink->time_base),
av_ts2timestr(blackdetect->black_end - blackdetect->black_start, &inlink->time_base));
}
}
static av_always_inline void update(SilenceDetectContext *s, AVFrame *insamples,
int is_silence, int64_t nb_samples_notify,
AVRational time_base)
{
#ifdef IDE_COMPILE
char tmp__0[32] = {0};
char *tmp;
#endif
if (is_silence) {
if (!s->start) {
s->nb_null_samples++;
if (s->nb_null_samples >= nb_samples_notify) {
s->start = insamples->pts - (int64_t)(s->duration / av_q2d(time_base) + .5);
#ifdef IDE_COMPILE
tmp = av_ts_make_time_string(tmp__0, s->start, &time_base);
av_dict_set(&insamples->metadata, "lavfi.silence_start",
tmp, 0);
#else
av_dict_set(&insamples->metadata, "lavfi.silence_start",
av_ts2timestr(s->start, &time_base), 0);
#endif
av_log(s, AV_LOG_INFO, "silence_start: %s\n",
get_metadata_val(insamples, "lavfi.silence_start"));
}
}
} else {
if (s->start) {
#ifdef IDE_COMPILE
tmp = av_ts_make_time_string(tmp__0, insamples->pts, &time_base);
av_dict_set(&insamples->metadata, "lavfi.silence_end",
tmp, 0);
tmp = av_ts_make_time_string(tmp__0, insamples->pts - s->start, &time_base);
av_dict_set(&insamples->metadata, "lavfi.silence_duration",
tmp, 0);
#else
av_dict_set(&insamples->metadata, "lavfi.silence_end",
av_ts2timestr(insamples->pts, &time_base), 0);
av_dict_set(&insamples->metadata, "lavfi.silence_duration",
av_ts2timestr(insamples->pts - s->start, &time_base), 0);
#endif
av_log(s, AV_LOG_INFO,
"silence_end: %s | silence_duration: %s\n",
get_metadata_val(insamples, "lavfi.silence_end"),
get_metadata_val(insamples, "lavfi.silence_duration"));
}
s->nb_null_samples = s->start = 0;
}
}
static void end_frame(AVFilterLink *inlink)
{
AVFilterContext *ctx = inlink->dst;
BBoxContext *bbox = ctx->priv;
AVFilterBufferRef *picref = inlink->cur_buf;
FFBoundingBox box;
int has_bbox, w, h;
has_bbox =
ff_calculate_bounding_box(&box,
picref->data[0], picref->linesize[0],
inlink->w, inlink->h, 16);
w = box.x2 - box.x1 + 1;
h = box.y2 - box.y1 + 1;
av_log(ctx, AV_LOG_INFO,
"n:%d pts:%s pts_time:%s", bbox->frame,
av_ts2str(picref->pts), av_ts2timestr(picref->pts, &inlink->time_base));
if (has_bbox) {
av_log(ctx, AV_LOG_INFO,
"x1:%d x2:%d y1:%d y2:%d w:%d h:%d"
" crop=%d:%d:%d:%d drawbox=%d:%d:%d:%d",
box.x1, box.x2, box.y1, box.y2, w, h,
w, h, box.x1, box.y1, /* crop params */
box.x1, box.y1, w, h); /* drawbox params */
}
av_log(ctx, AV_LOG_INFO, "\n");
bbox->frame++;
avfilter_end_frame(inlink->dst->outputs[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 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,
pix_fmt, width, height);
/* write to rawvideo file */
fwrite(video_dst_data[0], 1, video_dst_bufsize, video_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)
// if (*got_frame)
// av_frame_unref(frame);
return decoded;
}
// TODO: document metadata
static int filter_frame(AVFilterLink *inlink, AVFrame *picref)
{
AVFilterContext *ctx = inlink->dst;
BlackDetectContext *blackdetect = ctx->priv;
double picture_black_ratio = 0;
const uint8_t *p = picref->data[0];
int x, i;
for (i = 0; i < inlink->h; i++) {
for (x = 0; x < inlink->w; x++)
blackdetect->nb_black_pixels += p[x] <= blackdetect->pixel_black_th_i;
p += picref->linesize[0];
}
picture_black_ratio = (double)blackdetect->nb_black_pixels / (inlink->w * inlink->h);
av_log(ctx, AV_LOG_DEBUG,
"frame:%"PRId64" picture_black_ratio:%f pts:%s t:%s type:%c\n",
inlink->frame_count_out, picture_black_ratio,
av_ts2str(picref->pts), av_ts2timestr(picref->pts, &inlink->time_base),
av_get_picture_type_char(picref->pict_type));
if (picture_black_ratio >= blackdetect->picture_black_ratio_th) {
if (!blackdetect->black_started) {
/* black starts here */
blackdetect->black_started = 1;
blackdetect->black_start = picref->pts;
av_dict_set(&picref->metadata, "lavfi.black_start",
av_ts2timestr(blackdetect->black_start, &inlink->time_base), 0);
}
} else if (blackdetect->black_started) {
/* black ends here */
blackdetect->black_started = 0;
blackdetect->black_end = picref->pts;
check_black_end(ctx);
av_dict_set(&picref->metadata, "lavfi.black_end",
av_ts2timestr(blackdetect->black_end, &inlink->time_base), 0);
}
blackdetect->last_picref_pts = picref->pts;
blackdetect->nb_black_pixels = 0;
return ff_filter_frame(inlink->dst->outputs[0], picref);
}
static int filter_frame(AVFilterLink *inlink, AVFrame *buf)
{
AVFilterContext *ctx = inlink->dst;
AShowInfoContext *s = ctx->priv;
char chlayout_str[128];
uint32_t checksum = 0;
int channels = av_get_channel_layout_nb_channels(buf->channel_layout);
int planar = av_sample_fmt_is_planar(buf->format);
int block_align = av_get_bytes_per_sample(buf->format) * (planar ? 1 : channels);
int data_size = buf->nb_samples * block_align;
int planes = planar ? channels : 1;
int i;
void *tmp_ptr = av_realloc(s->plane_checksums, channels * sizeof(*s->plane_checksums));
if (!tmp_ptr)
return AVERROR(ENOMEM);
s->plane_checksums = tmp_ptr;
for (i = 0; i < planes; i++) {
uint8_t *data = buf->extended_data[i];
s->plane_checksums[i] = av_adler32_update(0, data, data_size);
checksum = i ? av_adler32_update(checksum, data, data_size) :
s->plane_checksums[0];
}
av_get_channel_layout_string(chlayout_str, sizeof(chlayout_str), -1,
buf->channel_layout);
av_log(ctx, AV_LOG_INFO,
"n:%"PRId64" pts:%s pts_time:%s pos:%"PRId64" "
"fmt:%s channels:%d chlayout:%s rate:%d nb_samples:%d "
"checksum:%08X ",
inlink->frame_count,
av_ts2str(buf->pts), av_ts2timestr(buf->pts, &inlink->time_base),
av_frame_get_pkt_pos(buf),
av_get_sample_fmt_name(buf->format), av_frame_get_channels(buf), chlayout_str,
buf->sample_rate, buf->nb_samples,
checksum);
av_log(ctx, AV_LOG_INFO, "plane_checksums: [ ");
for (i = 0; i < planes; i++)
av_log(ctx, AV_LOG_INFO, "%08X ", s->plane_checksums[i]);
av_log(ctx, AV_LOG_INFO, "]\n");
return ff_filter_frame(inlink->dst->outputs[0], buf);
}
static int end_frame(AVFilterLink *inlink)
{
AVFilterContext *ctx = inlink->dst;
ShowInfoContext *showinfo = ctx->priv;
AVFilterBufferRef *picref = inlink->cur_buf;
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);
uint32_t plane_checksum[4] = {0}, checksum = 0;
int i, plane, vsub = desc->log2_chroma_h;
for (plane = 0; picref->data[plane] && plane < 4; plane++) {
int64_t linesize = av_image_get_linesize(picref->format, picref->video->w, plane);
uint8_t *data = picref->data[plane];
int h = plane == 1 || plane == 2 ? inlink->h >> vsub : inlink->h;
if (linesize < 0)
return linesize;
for (i = 0; i < h; i++) {
plane_checksum[plane] = av_adler32_update(plane_checksum[plane], data, linesize);
checksum = av_adler32_update(checksum, data, linesize);
data += picref->linesize[plane];
}
}
av_log(ctx, AV_LOG_INFO,
"n:%d pts:%s pts_time:%s pos:%"PRId64" "
"fmt:%s sar:%d/%d s:%dx%d i:%c iskey:%d type:%c "
"checksum:%08X plane_checksum:[%08X",
showinfo->frame,
av_ts2str(picref->pts), av_ts2timestr(picref->pts, &inlink->time_base), picref->pos,
desc->name,
picref->video->sample_aspect_ratio.num, picref->video->sample_aspect_ratio.den,
picref->video->w, picref->video->h,
!picref->video->interlaced ? 'P' : /* Progressive */
picref->video->top_field_first ? 'T' : 'B', /* Top / Bottom */
picref->video->key_frame,
av_get_picture_type_char(picref->video->pict_type),
checksum, plane_checksum[0]);
for (plane = 1; picref->data[plane] && plane < 4; plane++)
av_log(ctx, AV_LOG_INFO, " %08X", plane_checksum[plane]);
av_log(ctx, AV_LOG_INFO, "]\n");
showinfo->frame++;
return ff_end_frame(inlink->dst->outputs[0]);
}
static void filter_samples(AVFilterLink *inlink, AVFilterBufferRef *samplesref)
{
AVFilterContext *ctx = inlink->dst;
ShowInfoContext *showinfo = ctx->priv;
uint32_t plane_checksum[8] = {0}, checksum = 0;
char chlayout_str[128];
int plane;
int linesize =
samplesref->audio->nb_samples *
av_get_bytes_per_sample(samplesref->format);
if (!av_sample_fmt_is_planar(samplesref->format))
linesize *= av_get_channel_layout_nb_channels(samplesref->audio->channel_layout);
for (plane = 0; samplesref->data[plane] && plane < 8; plane++) {
uint8_t *data = samplesref->data[plane];
plane_checksum[plane] = av_adler32_update(plane_checksum[plane],
data, linesize);
checksum = av_adler32_update(checksum, data, linesize);
}
av_get_channel_layout_string(chlayout_str, sizeof(chlayout_str), -1,
samplesref->audio->channel_layout);
av_log(ctx, AV_LOG_INFO,
"n:%d pts:%s pts_time:%s pos:%"PRId64" "
"fmt:%s chlayout:%s nb_samples:%d rate:%d "
"checksum:%08X plane_checksum[%08X",
showinfo->frame,
av_ts2str(samplesref->pts), av_ts2timestr(samplesref->pts, &inlink->time_base),
samplesref->pos,
av_get_sample_fmt_name(samplesref->format),
chlayout_str,
samplesref->audio->nb_samples,
samplesref->audio->sample_rate,
checksum,
plane_checksum[0]);
for (plane = 1; samplesref->data[plane] && plane < 8; plane++)
av_log(ctx, AV_LOG_INFO, " %08X", plane_checksum[plane]);
av_log(ctx, AV_LOG_INFO, "]\n");
showinfo->frame++;
ff_filter_samples(inlink->dst->outputs[0], samplesref);
}
static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
{
AVFilterContext *ctx = inlink->dst;
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);
uint32_t plane_checksum[4] = {0}, checksum = 0;
int i, plane, vsub = desc->log2_chroma_h;
for (plane = 0; plane < 4 && frame->data[plane] && frame->linesize[plane]; plane++) {
int64_t linesize = av_image_get_linesize(frame->format, frame->width, plane);
uint8_t *data = frame->data[plane];
int h = plane == 1 || plane == 2 ? FF_CEIL_RSHIFT(inlink->h, vsub) : inlink->h;
if (linesize < 0)
return linesize;
for (i = 0; i < h; i++) {
plane_checksum[plane] = av_adler32_update(plane_checksum[plane], data, linesize);
checksum = av_adler32_update(checksum, data, linesize);
data += frame->linesize[plane];
}
}
av_log(ctx, AV_LOG_INFO,
"n:%"PRId64" pts:%s pts_time:%s pos:%"PRId64" "
"fmt:%s sar:%d/%d s:%dx%d i:%c iskey:%d type:%c "
"checksum:%08X plane_checksum:[%08X",
inlink->frame_count,
av_ts2str(frame->pts), av_ts2timestr(frame->pts, &inlink->time_base), av_frame_get_pkt_pos(frame),
desc->name,
frame->sample_aspect_ratio.num, frame->sample_aspect_ratio.den,
frame->width, frame->height,
!frame->interlaced_frame ? 'P' : /* Progressive */
frame->top_field_first ? 'T' : 'B', /* Top / Bottom */
frame->key_frame,
av_get_picture_type_char(frame->pict_type),
checksum, plane_checksum[0]);
for (plane = 1; plane < 4 && frame->data[plane] && frame->linesize[plane]; plane++)
av_log(ctx, AV_LOG_INFO, " %08X", plane_checksum[plane]);
av_log(ctx, AV_LOG_INFO, "]\n");
return ff_filter_frame(inlink->dst->outputs[0], frame);
}
static int config_input(AVFilterLink *inlink)
{
AVFilterContext *ctx = inlink->dst;
BlackDetectContext *blackdetect = ctx->priv;
blackdetect->black_min_duration =
blackdetect->black_min_duration_time / av_q2d(inlink->time_base);
blackdetect->pixel_black_th_i = ff_fmt_is_in(inlink->format, yuvj_formats) ?
// luminance_minimum_value + pixel_black_th * luminance_range_size
blackdetect->pixel_black_th * 255 :
16 + blackdetect->pixel_black_th * (235 - 16);
av_log(blackdetect, AV_LOG_VERBOSE,
"black_min_duration:%s pixel_black_th:%f pixel_black_th_i:%d picture_black_ratio_th:%f\n",
av_ts2timestr(blackdetect->black_min_duration, &inlink->time_base),
blackdetect->pixel_black_th, blackdetect->pixel_black_th_i,
blackdetect->picture_black_ratio_th);
return 0;
}
static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
{
AVFilterContext *ctx = inlink->dst;
BBoxContext *bbox = ctx->priv;
FFBoundingBox box;
int has_bbox, w, h;
has_bbox =
ff_calculate_bounding_box(&box,
frame->data[0], frame->linesize[0],
inlink->w, inlink->h, bbox->min_val);
w = box.x2 - box.x1 + 1;
h = box.y2 - box.y1 + 1;
av_log(ctx, AV_LOG_INFO,
"n:%"PRId64" pts:%s pts_time:%s", inlink->frame_count_out,
av_ts2str(frame->pts), av_ts2timestr(frame->pts, &inlink->time_base));
if (has_bbox) {
AVDictionary **metadata = &frame->metadata;
SET_META("lavfi.bbox.x1", box.x1)
SET_META("lavfi.bbox.x2", box.x2)
SET_META("lavfi.bbox.y1", box.y1)
SET_META("lavfi.bbox.y2", box.y2)
SET_META("lavfi.bbox.w", w)
SET_META("lavfi.bbox.h", h)
av_log(ctx, AV_LOG_INFO,
" x1:%d x2:%d y1:%d y2:%d w:%d h:%d"
" crop=%d:%d:%d:%d drawbox=%d:%d:%d:%d",
box.x1, box.x2, box.y1, box.y2, w, h,
w, h, box.x1, box.y1, /* crop params */
box.x1, box.y1, w, h); /* drawbox params */
}
av_log(ctx, AV_LOG_INFO, "\n");
return ff_filter_frame(inlink->dst->outputs[0], frame);
}
static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
{
AVFilterContext *ctx = inlink->dst;
AVFilterLink *outlink = ctx->outputs[0];
MetadataContext *s = ctx->priv;
AVDictionary *metadata = av_frame_get_metadata(frame);
AVDictionaryEntry *e;
if (!metadata)
return ff_filter_frame(outlink, frame);
e = av_dict_get(metadata, !s->key ? "" : s->key, NULL,
!s->key ? AV_DICT_IGNORE_SUFFIX: 0);
switch (s->mode) {
case METADATA_SELECT:
if (!s->value && e && e->value) {
return ff_filter_frame(outlink, frame);
} else if (s->value && e && e->value &&
s->compare(s, e->value, s->value)) {
return ff_filter_frame(outlink, frame);
}
break;
case METADATA_ADD:
if (e && e->value) {
;
} else {
av_dict_set(&metadata, s->key, s->value, 0);
}
return ff_filter_frame(outlink, frame);
break;
case METADATA_MODIFY:
if (e && e->value) {
av_dict_set(&metadata, s->key, s->value, 0);
}
return ff_filter_frame(outlink, frame);
break;
case METADATA_PRINT:
if (!s->key && e) {
s->print(ctx, "frame:%-4"PRId64" pts:%-7s pts_time:%-7s\n",
inlink->frame_count, av_ts2str(frame->pts), av_ts2timestr(frame->pts, &inlink->time_base));
s->print(ctx, "%s=%s\n", e->key, e->value);
while ((e = av_dict_get(metadata, "", e, AV_DICT_IGNORE_SUFFIX)) != NULL) {
s->print(ctx, "%s=%s\n", e->key, e->value);
}
} else if (e && e->value && (!s->value || (e->value && s->compare(s, e->value, s->value)))) {
s->print(ctx, "frame:%-4"PRId64" pts:%-7s pts_time:%-7s\n",
inlink->frame_count, av_ts2str(frame->pts), av_ts2timestr(frame->pts, &inlink->time_base));
s->print(ctx, "%s=%s\n", s->key, e->value);
}
return ff_filter_frame(outlink, frame);
break;
case METADATA_DELETE:
if (e && e->value && s->value && s->compare(s, e->value, s->value)) {
av_dict_set(&metadata, s->key, NULL, 0);
} else if (e && e->value) {
av_dict_set(&metadata, s->key, NULL, 0);
}
return ff_filter_frame(outlink, frame);
break;
default:
av_assert0(0);
};
av_frame_free(&frame);
return 0;
}
static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
{
AVFilterContext *ctx = inlink->dst;
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);
uint32_t plane_checksum[4] = {0}, checksum = 0;
int i, plane, vsub = desc->log2_chroma_h;
for (plane = 0; plane < 4 && frame->data[plane] && frame->linesize[plane]; plane++) {
int64_t linesize = av_image_get_linesize(frame->format, frame->width, plane);
uint8_t *data = frame->data[plane];
int h = plane == 1 || plane == 2 ? FF_CEIL_RSHIFT(inlink->h, vsub) : inlink->h;
if (linesize < 0)
return linesize;
for (i = 0; i < h; i++) {
plane_checksum[plane] = av_adler32_update(plane_checksum[plane], data, linesize);
checksum = av_adler32_update(checksum, data, linesize);
data += frame->linesize[plane];
}
}
av_log(ctx, AV_LOG_INFO,
"n:%"PRId64" pts:%s pts_time:%s pos:%"PRId64" "
"fmt:%s sar:%d/%d s:%dx%d i:%c iskey:%d type:%c "
"checksum:%08"PRIX32" plane_checksum:[%08"PRIX32,
inlink->frame_count,
av_ts2str(frame->pts), av_ts2timestr(frame->pts, &inlink->time_base), av_frame_get_pkt_pos(frame),
desc->name,
frame->sample_aspect_ratio.num, frame->sample_aspect_ratio.den,
frame->width, frame->height,
!frame->interlaced_frame ? 'P' : /* Progressive */
frame->top_field_first ? 'T' : 'B', /* Top / Bottom */
frame->key_frame,
av_get_picture_type_char(frame->pict_type),
checksum, plane_checksum[0]);
for (plane = 1; plane < 4 && frame->data[plane] && frame->linesize[plane]; plane++)
av_log(ctx, AV_LOG_INFO, " %08"PRIX32, plane_checksum[plane]);
av_log(ctx, AV_LOG_INFO, "]\n");
for (i = 0; i < frame->nb_side_data; i++) {
AVFrameSideData *sd = frame->side_data[i];
av_log(ctx, AV_LOG_INFO, " side data - ");
switch (sd->type) {
case AV_FRAME_DATA_PANSCAN:
av_log(ctx, AV_LOG_INFO, "pan/scan");
break;
case AV_FRAME_DATA_A53_CC:
av_log(ctx, AV_LOG_INFO, "A/53 closed captions (%d bytes)", sd->size);
break;
case AV_FRAME_DATA_STEREO3D:
dump_stereo3d(ctx, sd);
break;
default:
av_log(ctx, AV_LOG_WARNING, "unknown side data type %d (%d bytes)",
sd->type, sd->size);
break;
}
av_log(ctx, AV_LOG_INFO, "\n");
}
return ff_filter_frame(inlink->dst->outputs[0], frame);
}
static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
{
AVFilterContext *ctx = inlink->dst;
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);
uint32_t plane_checksum[4] = {0}, checksum = 0;
int64_t sum[4] = {0}, sum2[4] = {0};
int32_t pixelcount[4] = {0};
int i, plane, vsub = desc->log2_chroma_h;
#ifdef IDE_COMPILE
char tmp1[32] = {0};
char tmp2[32] = {0};
#endif
for (plane = 0; plane < 4 && frame->data[plane] && frame->linesize[plane]; plane++) {
int64_t linesize = av_image_get_linesize(frame->format, frame->width, plane);
uint8_t *data = frame->data[plane];
int h = plane == 1 || plane == 2 ? FF_CEIL_RSHIFT(inlink->h, vsub) : inlink->h;
if (linesize < 0)
return linesize;
for (i = 0; i < h; i++) {
plane_checksum[plane] = av_adler32_update(plane_checksum[plane], data, linesize);
checksum = av_adler32_update(checksum, data, linesize);
update_sample_stats(data, linesize, sum+plane, sum2+plane);
pixelcount[plane] += linesize;
data += frame->linesize[plane];
}
}
#ifdef IDE_COMPILE
av_log(ctx, AV_LOG_INFO,
"n:%"PRId64" pts:%s pts_time:%s pos:%"PRId64" "
"fmt:%s sar:%d/%d s:%dx%d i:%c iskey:%d type:%c "
"checksum:%08"PRIX32" plane_checksum:[%08"PRIX32,
inlink->frame_count,
av_ts_make_string(tmp1, frame->pts), av_ts_make_time_string(tmp2, frame->pts, &inlink->time_base), av_frame_get_pkt_pos(frame),
desc->name,
frame->sample_aspect_ratio.num, frame->sample_aspect_ratio.den,
frame->width, frame->height,
!frame->interlaced_frame ? 'P' : /* Progressive */
frame->top_field_first ? 'T' : 'B', /* Top / Bottom */
frame->key_frame,
av_get_picture_type_char(frame->pict_type),
checksum, plane_checksum[0]);
#else
av_log(ctx, AV_LOG_INFO,
"n:%"PRId64" pts:%s pts_time:%s pos:%"PRId64" "
"fmt:%s sar:%d/%d s:%dx%d i:%c iskey:%d type:%c "
"checksum:%08"PRIX32" plane_checksum:[%08"PRIX32,
inlink->frame_count,
av_ts2str(frame->pts), av_ts2timestr(frame->pts, &inlink->time_base), av_frame_get_pkt_pos(frame),
desc->name,
frame->sample_aspect_ratio.num, frame->sample_aspect_ratio.den,
frame->width, frame->height,
!frame->interlaced_frame ? 'P' : /* Progressive */
frame->top_field_first ? 'T' : 'B', /* Top / Bottom */
frame->key_frame,
av_get_picture_type_char(frame->pict_type),
checksum, plane_checksum[0]);
#endif
for (plane = 1; plane < 4 && frame->data[plane] && frame->linesize[plane]; plane++)
av_log(ctx, AV_LOG_INFO, " %08"PRIX32, plane_checksum[plane]);
av_log(ctx, AV_LOG_INFO, "] mean:[");
for (plane = 0; plane < 4 && frame->data[plane] && frame->linesize[plane]; plane++)
av_log(ctx, AV_LOG_INFO, "%"PRId64" ", (sum[plane] + pixelcount[plane]/2) / pixelcount[plane]);
av_log(ctx, AV_LOG_INFO, "\b] stdev:[");
for (plane = 0; plane < 4 && frame->data[plane] && frame->linesize[plane]; plane++)
av_log(ctx, AV_LOG_INFO, "%3.1f ",
sqrt((sum2[plane] - sum[plane]*(double)sum[plane]/pixelcount[plane])/pixelcount[plane]));
av_log(ctx, AV_LOG_INFO, "\b]\n");
for (i = 0; i < frame->nb_side_data; i++) {
AVFrameSideData *sd = frame->side_data[i];
av_log(ctx, AV_LOG_INFO, " side data - ");
switch (sd->type) {
case AV_FRAME_DATA_PANSCAN:
av_log(ctx, AV_LOG_INFO, "pan/scan");
break;
case AV_FRAME_DATA_A53_CC:
av_log(ctx, AV_LOG_INFO, "A/53 closed captions (%d bytes)", sd->size);
break;
case AV_FRAME_DATA_STEREO3D:
dump_stereo3d(ctx, sd);
break;
case AV_FRAME_DATA_DISPLAYMATRIX:
av_log(ctx, AV_LOG_INFO, "displaymatrix: rotation of %.2f degrees",
av_display_rotation_get((int32_t *)sd->data));
break;
case AV_FRAME_DATA_AFD:
av_log(ctx, AV_LOG_INFO, "afd: value of %"PRIu8, sd->data[0]);
break;
default:
av_log(ctx, AV_LOG_WARNING, "unknown side data type %d (%d bytes)",
sd->type, sd->size);
break;
}
av_log(ctx, AV_LOG_INFO, "\n");
}
return ff_filter_frame(inlink->dst->outputs[0], frame);
}
/*
* Return
* - 0 -- one packet was read and processed
* - AVERROR(EAGAIN) -- no packets were available for selected file,
* this function should be called again
* - AVERROR_EOF -- this function should not be called again
*/
static int process_input(int file_index)
{
InputFile *ifile = input_files[file_index];
AVFormatContext *is;
InputStream *ist;
AVPacket pkt;
int ret, i, j;
is = ifile->ctx;
// ****<< Capture a frame: audio/video/subtitle
ret = get_input_packet(ifile, &pkt); // ****<< Call stack: av_read_frame() --> read_frame_internal() --> ff_read_packet() --> s->iformat->read_packet(s, pkt); --> dshow_read_frame();
if (ret == AVERROR(EAGAIN)) {
ifile->eagain = 1;
return ret;
}
if (ret < 0) {
if (ret != AVERROR_EOF) {
print_error(is->filename, ret);
if (exit_on_error)
exit_program(1);
}
ifile->eof_reached = 1;
for (i = 0; i < ifile->nb_streams; i++) {
ist = input_streams[ifile->ist_index + i];
if (ist->decoding_needed)
output_packet(ist, NULL);
/* mark all outputs that don't go through lavfi as finished */
for (j = 0; j < nb_output_streams; j++) {
OutputStream *ost = output_streams[j];
if (ost->source_index == ifile->ist_index + i &&
(ost->stream_copy || ost->enc->type == AVMEDIA_TYPE_SUBTITLE))
close_output_stream(ost);
}
}
return AVERROR(EAGAIN);
}
reset_eagain();
if (do_pkt_dump) {
av_pkt_dump_log2(NULL, AV_LOG_DEBUG, &pkt, do_hex_dump,
is->streams[pkt.stream_index]);
}
/* the following test is needed in case new streams appear
dynamically in stream : we ignore them */
if (pkt.stream_index >= ifile->nb_streams) {
report_new_stream(file_index, &pkt);
goto discard_packet;
}
ist = input_streams[ifile->ist_index + pkt.stream_index];
ist->data_size += pkt.size;
ist->nb_packets++;
if (ist->discard)
goto discard_packet;
if (debug_ts) {
av_log(NULL, AV_LOG_INFO, "demuxer -> ist_index:%d type:%s "
"next_dts:%s next_dts_time:%s next_pts:%s next_pts_time:%s pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s off:%s off_time:%s\n",
ifile->ist_index + pkt.stream_index, av_get_media_type_string(ist->dec_ctx->codec_type),
av_ts2str(ist->next_dts), av_ts2timestr(ist->next_dts, &AV_TIME_BASE_Q),
av_ts2str(ist->next_pts), av_ts2timestr(ist->next_pts, &AV_TIME_BASE_Q),
av_ts2str(pkt.pts), av_ts2timestr(pkt.pts, &ist->st->time_base),
av_ts2str(pkt.dts), av_ts2timestr(pkt.dts, &ist->st->time_base),
av_ts2str(input_files[ist->file_index]->ts_offset),
av_ts2timestr(input_files[ist->file_index]->ts_offset, &AV_TIME_BASE_Q));
}
if(!ist->wrap_correction_done && is->start_time != AV_NOPTS_VALUE && ist->st->pts_wrap_bits < 64) {
int64_t stime, stime2;
// Correcting starttime based on the enabled streams
// FIXME this ideally should be done before the first use of starttime but we do not know which are the enabled streams at that point.
// so we instead do it here as part of discontinuity handling
if ( ist->next_dts == AV_NOPTS_VALUE
&& ifile->ts_offset == -is->start_time
&& (is->iformat->flags & AVFMT_TS_DISCONT)) {
int64_t new_start_time = INT64_MAX;
for (i=0; i<is->nb_streams; i++) {
AVStream *st = is->streams[i];
if(st->discard == AVDISCARD_ALL || st->start_time == AV_NOPTS_VALUE)
continue;
new_start_time = FFMIN(new_start_time, av_rescale_q(st->start_time, st->time_base, AV_TIME_BASE_Q));
}
if (new_start_time > is->start_time) {
av_log(is, AV_LOG_VERBOSE, "Correcting start time by %"PRId64"\n", new_start_time - is->start_time);
ifile->ts_offset = -new_start_time;
}
}
stime = av_rescale_q(is->start_time, AV_TIME_BASE_Q, ist->st->time_base);
stime2= stime + (1ULL<<ist->st->pts_wrap_bits);
ist->wrap_correction_done = 1;
if(stime2 > stime && pkt.dts != AV_NOPTS_VALUE && pkt.dts > stime + (1LL<<(ist->st->pts_wrap_bits-1))) {
pkt.dts -= 1ULL<<ist->st->pts_wrap_bits;
ist->wrap_correction_done = 0;
}
if(stime2 > stime && pkt.pts != AV_NOPTS_VALUE && pkt.pts > stime + (1LL<<(ist->st->pts_wrap_bits-1))) {
pkt.pts -= 1ULL<<ist->st->pts_wrap_bits;
ist->wrap_correction_done = 0;
}
}
/* add the stream-global side data to the first packet */
if (ist->nb_packets == 1)
if (ist->st->nb_side_data)
av_packet_split_side_data(&pkt);
for (i = 0; i < ist->st->nb_side_data; i++) {
AVPacketSideData *src_sd = &ist->st->side_data[i];
uint8_t *dst_data;
if (av_packet_get_side_data(&pkt, src_sd->type, NULL))
continue;
dst_data = av_packet_new_side_data(&pkt, src_sd->type, src_sd->size);
if (!dst_data)
exit_program(1);
memcpy(dst_data, src_sd->data, src_sd->size);
}
// ****<< pkt.pts: 采集时间戳(以毫秒为单位; 一般为系统时间)
// ****<< ts_offset: 起始时间戳(以毫秒为单位; 一般为第一帧采集时间戳的相反数)
// ****<< 最终.pts: 相对时间戳(以毫秒为单位; 从第一帧到现在的相对时间)
if (pkt.dts != AV_NOPTS_VALUE)
pkt.dts += av_rescale_q(ifile->ts_offset, AV_TIME_BASE_Q, ist->st->time_base);
if (pkt.pts != AV_NOPTS_VALUE)
pkt.pts += av_rescale_q(ifile->ts_offset, AV_TIME_BASE_Q, ist->st->time_base);
if (pkt.pts != AV_NOPTS_VALUE)
pkt.pts *= ist->ts_scale;
if (pkt.dts != AV_NOPTS_VALUE)
pkt.dts *= ist->ts_scale;
if (pkt.dts != AV_NOPTS_VALUE && ist->next_dts == AV_NOPTS_VALUE && !copy_ts
&& (is->iformat->flags & AVFMT_TS_DISCONT) && ifile->last_ts != AV_NOPTS_VALUE) {
int64_t pkt_dts = av_rescale_q(pkt.dts, ist->st->time_base, AV_TIME_BASE_Q);
int64_t delta = pkt_dts - ifile->last_ts;
if(delta < -1LL*dts_delta_threshold*AV_TIME_BASE ||
(delta > 1LL*dts_delta_threshold*AV_TIME_BASE &&
ist->dec_ctx->codec_type != AVMEDIA_TYPE_SUBTITLE)) {
ifile->ts_offset -= delta;
av_log(NULL, AV_LOG_DEBUG,
"Inter stream timestamp discontinuity %"PRId64", new offset= %"PRId64"\n",
delta, ifile->ts_offset);
pkt.dts -= av_rescale_q(delta, AV_TIME_BASE_Q, ist->st->time_base);
if (pkt.pts != AV_NOPTS_VALUE)
pkt.pts -= av_rescale_q(delta, AV_TIME_BASE_Q, ist->st->time_base);
}
}
if (pkt.dts != AV_NOPTS_VALUE && ist->next_dts != AV_NOPTS_VALUE &&
!copy_ts) {
int64_t pkt_dts = av_rescale_q(pkt.dts, ist->st->time_base, AV_TIME_BASE_Q);
int64_t delta = pkt_dts - ist->next_dts;
if (is->iformat->flags & AVFMT_TS_DISCONT) {
if (delta < -1LL*dts_delta_threshold*AV_TIME_BASE ||
(delta > 1LL*dts_delta_threshold*AV_TIME_BASE &&
ist->dec_ctx->codec_type != AVMEDIA_TYPE_SUBTITLE) ||
pkt_dts + AV_TIME_BASE/10 < FFMAX(ist->pts, ist->dts)) {
ifile->ts_offset -= delta;
av_log(NULL, AV_LOG_DEBUG,
"timestamp discontinuity %"PRId64", new offset= %"PRId64"\n",
delta, ifile->ts_offset);
pkt.dts -= av_rescale_q(delta, AV_TIME_BASE_Q, ist->st->time_base);
if (pkt.pts != AV_NOPTS_VALUE)
pkt.pts -= av_rescale_q(delta, AV_TIME_BASE_Q, ist->st->time_base);
}
} else {
if ( delta < -1LL*dts_error_threshold*AV_TIME_BASE ||
(delta > 1LL*dts_error_threshold*AV_TIME_BASE && ist->dec_ctx->codec_type != AVMEDIA_TYPE_SUBTITLE)) {
av_log(NULL, AV_LOG_WARNING, "DTS %"PRId64", next:%"PRId64" st:%d invalid dropping\n", pkt.dts, ist->next_dts, pkt.stream_index);
pkt.dts = AV_NOPTS_VALUE;
}
if (pkt.pts != AV_NOPTS_VALUE) {
int64_t pkt_pts = av_rescale_q(pkt.pts, ist->st->time_base, AV_TIME_BASE_Q);
delta = pkt_pts - ist->next_dts;
if ( delta < -1LL*dts_error_threshold*AV_TIME_BASE ||
(delta > 1LL*dts_error_threshold*AV_TIME_BASE && ist->dec_ctx->codec_type != AVMEDIA_TYPE_SUBTITLE)) {
av_log(NULL, AV_LOG_WARNING, "PTS %"PRId64", next:%"PRId64" invalid dropping st:%d\n", pkt.pts, ist->next_dts, pkt.stream_index);
pkt.pts = AV_NOPTS_VALUE;
}
}
}
}
if (pkt.dts != AV_NOPTS_VALUE)
ifile->last_ts = av_rescale_q(pkt.dts, ist->st->time_base, AV_TIME_BASE_Q);
if (debug_ts) {
av_log(NULL, AV_LOG_INFO, "demuxer+ffmpeg -> ist_index:%d type:%s pkt_pts:%s pkt_pts_time:%s pkt_dts:%s pkt_dts_time:%s off:%s off_time:%s\n",
ifile->ist_index + pkt.stream_index, av_get_media_type_string(ist->dec_ctx->codec_type),
av_ts2str(pkt.pts), av_ts2timestr(pkt.pts, &ist->st->time_base),
av_ts2str(pkt.dts), av_ts2timestr(pkt.dts, &ist->st->time_base),
av_ts2str(input_files[ist->file_index]->ts_offset),
av_ts2timestr(input_files[ist->file_index]->ts_offset, &AV_TIME_BASE_Q));
}
sub2video_heartbeat(ist, pkt.pts);
ret = output_packet(ist, &pkt); // ****<< see output_packet.c
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while decoding stream #%d:%d: %s\n",
ist->file_index, ist->st->index, av_err2str(ret));
if (exit_on_error)
exit_program(1);
}
discard_packet:
av_free_packet(&pkt);
return 0;
}
static int decode_packet(int *got_frame, int cached)
{
int ret = 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;
}
if (*got_frame) {
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));
ret = av_samples_alloc(audio_dst_data, &audio_dst_linesize, frame->channels,
frame->nb_samples, frame->format, 1);
if (ret < 0) {
fprintf(stderr, "Could not allocate audio buffer\n");
return AVERROR(ENOMEM);
}
/* TODO: extend return code of the av_samples_* functions so that this call is not needed */
audio_dst_bufsize =
av_samples_get_buffer_size(NULL, frame->channels,
frame->nb_samples, frame->format, 1);
/* copy audio data to destination buffer:
* this is required since rawaudio expects non aligned data */
av_samples_copy(audio_dst_data, frame->data, 0, 0,
frame->nb_samples, frame->channels, frame->format);
/* write to rawaudio file */
fwrite(audio_dst_data[0], 1, audio_dst_bufsize, audio_dst_file);
av_freep(&audio_dst_data[0]);
}
}
return ret;
}
/**
* Decode a frame to a packet, run the result through SwrContext, if desired, encode it via an appropriate
* encoder, and write the results to the Java-side native buffer.
*
* @param aio FFAudio context
* @param cached true or false
* @return number of bytes placed into java buffer or a negative value, if something went wrong
*/
static int decode_packet(FFAudioIO *aio, int cached) {
int res = 0;
uint8_t **resample_buf = NULL;
jobject byte_buffer = NULL;
uint8_t *javaBuffer = NULL;
uint32_t out_buf_size = 0;
int out_buf_samples = 0;
int64_t out_channel_count;
int64_t out_sample_rate;
int flush = aio->got_frame;
enum AVSampleFormat out;
int bytesConsumed = 0;
init_ids(aio->env, aio->java_instance);
av_opt_get_int(aio->swr_context, "out_channel_count", 0, &out_channel_count);
av_opt_get_int(aio->swr_context, "out_sample_rate", 0, &out_sample_rate);
av_opt_get_sample_fmt(aio->swr_context, "out_sample_fmt", 0, &out);
resample_buf = av_mallocz(sizeof(uint8_t *) * 1); // one plane!
// make sure we really have an audio packet
if (aio->decode_packet.stream_index == aio->stream_index) {
// decode frame
// got_frame indicates whether we got a frame
bytesConsumed = avcodec_decode_audio4(aio->decode_context, aio->decode_frame, &aio->got_frame, &aio->decode_packet);
if (bytesConsumed < 0) {
throwUnsupportedAudioFileExceptionIfError(aio->env, bytesConsumed, "Failed to decode audio frame.");
return bytesConsumed;
}
if (aio->got_frame) {
aio->decoded_samples += aio->decode_frame->nb_samples;
out_buf_samples = aio->decode_frame->nb_samples;
#ifdef DEBUG
fprintf(stderr, "samples%s n:%" PRIu64 " nb_samples:%d pts:%s\n",
cached ? "(cached)" : "",
aio->decoded_samples, aio->decode_frame->nb_samples,
av_ts2timestr(aio->decode_frame->pts, &aio->decode_context->time_base));
#endif
// adjust out sample number for a different sample rate
// this is an estimate!!
out_buf_samples = av_rescale_rnd(
swr_get_delay(aio->swr_context, aio->stream->codecpar->sample_rate) + aio->decode_frame->nb_samples,
out_sample_rate,
aio->stream->codecpar->sample_rate,
AV_ROUND_UP
);
// allocate new aio->audio_data buffers
res = av_samples_alloc(aio->audio_data, NULL, av_frame_get_channels(aio->decode_frame),
aio->decode_frame->nb_samples, aio->decode_frame->format, 1);
if (res < 0) {
throwIOExceptionIfError(aio->env, res, "Could not allocate audio buffer.");
return AVERROR(ENOMEM);
}
// copy audio data to aio->audio_data
av_samples_copy(aio->audio_data, aio->decode_frame->data, 0, 0,
aio->decode_frame->nb_samples, av_frame_get_channels(aio->decode_frame), aio->decode_frame->format);
res = resample(aio, resample_buf, out_buf_samples, (const uint8_t **)aio->audio_data, aio->decode_frame->nb_samples);
if (res < 0) goto bail;
else out_buf_samples = res;
} else if (flush && swr_get_delay(aio->swr_context, aio->stream->codecpar->sample_rate)) {
res = resample(aio, resample_buf, swr_get_delay(aio->swr_context, aio->stream->codecpar->sample_rate), NULL, 0);
if (res < 0) goto bail;
else out_buf_samples = res;
} else {
#ifdef DEBUG
fprintf(stderr, "Got no frame.\n");
#endif
}
if (out_buf_samples > 0) {
res = av_samples_get_buffer_size(NULL, (int)out_channel_count, out_buf_samples, out, 1);
if (res < 0) goto bail;
else out_buf_size = res;
// ensure native buffer capacity
if (aio->java_buffer_capacity < out_buf_size) {
aio->java_buffer_capacity = (*aio->env)->CallIntMethod(aio->env, aio->java_instance, setNativeBufferCapacity_MID, (jint)out_buf_size);
}
// get java-managed byte buffer reference
byte_buffer = (*aio->env)->GetObjectField(aio->env, aio->java_instance, nativeBuffer_FID);
if (!byte_buffer) {
res = -1;
throwIOExceptionIfError(aio->env, 1, "Failed to get native buffer.");
goto bail;
}
// we have some samples, let's copy them to the java buffer, using the desired encoding
javaBuffer = (uint8_t *)(*aio->env)->GetDirectBufferAddress(aio->env, byte_buffer);
if (!javaBuffer) {
throwIOExceptionIfError(aio->env, 1, "Failed to get address for native buffer.");
goto bail;
}
if (aio->encode_context) {
aio->encode_frame->nb_samples = out_buf_samples;
res = encode_buffer(aio, resample_buf[0], out_buf_size, javaBuffer);
if (res < 0) {
out_buf_size = 0;
goto bail;
}
out_buf_size = res;
} else {
memcpy(javaBuffer, resample_buf[0], out_buf_size);
}
// we already wrote to the buffer, now we still need to
// set new bytebuffer limit and position to 0.
(*aio->env)->CallObjectMethod(aio->env, byte_buffer, rewind_MID);
(*aio->env)->CallObjectMethod(aio->env, byte_buffer, limit_MID, out_buf_size);
}
}
aio->resampled_samples += out_buf_size;
bail:
if (resample_buf) {
if (resample_buf[0]) av_freep(&resample_buf[0]);
av_free(resample_buf);
}
if (aio->audio_data[0]) av_freep(&aio->audio_data[0]);
return res;
}
int main(int argc, char **argv)
{
int opt, ret, stream, flags;
const char *filename;
AVFormatContext *avf = NULL;
int64_t min_ts, max_ts, ts;
AVPacket packet;
while ((opt = getopt(argc, argv, "h")) != -1) {
switch (opt) {
case 'h':
usage(0);
default:
usage(1);
}
}
argc -= optind;
argv += optind;
if (!argc)
usage(1);
filename = *argv;
argv++;
argc--;
av_register_all();
if ((ret = avformat_open_input(&avf, filename, NULL, NULL)) < 0) {
fprintf(stderr, "%s: %s\n", filename, av_err2str(ret));
return 1;
}
if ((ret = avformat_find_stream_info(avf, NULL)) < 0) {
fprintf(stderr, "%s: could not find codec parameters: %s\n", filename,
av_err2str(ret));
return 1;
}
for (; argc; argc--, argv++) {
if (!strcmp(*argv, "read")) {
ret = av_read_frame(avf, &packet);
if (ret < 0) {
printf("read: %d (%s)\n", ret, av_err2str(ret));
} else {
AVRational *tb = &avf->streams[packet.stream_index]->time_base;
printf("read: %d size=%d stream=%d dts=%s (%s) pts=%s (%s)\n",
ret, packet.size, packet.stream_index,
av_ts2str(packet.dts), av_ts2timestr(packet.dts, tb),
av_ts2str(packet.pts), av_ts2timestr(packet.pts, tb));
av_packet_unref(&packet);
}
} else if (sscanf(*argv, "seek:%i:%"SCNi64":%"SCNi64":%"SCNi64":%i",
&stream, &min_ts, &ts, &max_ts, &flags) == 5) {
ret = avformat_seek_file(avf, stream, min_ts, ts, max_ts, flags);
printf("seek: %d (%s)\n", ret, av_err2str(ret));
} else {
fprintf(stderr, "'%s': unknown command\n", *argv);
return 1;
}
}
avformat_close_input(&avf);
return 0;
}
static int decode_packet(AVCodecContext *dec_ctx, FILE *dst_file, AVFrame *frame, int *got_frame, int *frame_count, AVPacket *pkt)
{
int ret = -1;
*got_frame = 0;
AVSubtitle sub;
unsigned i, j, k, l;
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
ret = 0;
/* decode video frame */
ret = avcodec_decode_video2(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) {
fprintf(stderr, "Error: input video width/height/format 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),
dec_ctx->width, dec_ctx->height,
av_get_pix_fmt_name(dec_ctx->pix_fmt));
return -1;
}
printf("video_frame n:%d coded_n:%d pts:%s\n",
*frame_count, frame->coded_picture_number,
av_ts2timestr(frame->pts, &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,
pix_fmt, width, height);
*frame_count += 1;
/* write to rawvideo file */
fwrite(video_dst_data[0], 1, video_dst_bufsize, dst_file);
}
} else if (dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
ret = 0;
/* decode audio frame */
ret = avcodec_decode_audio4(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. */
ret = FFMIN(ret, pkt->size);
if (*got_frame) {
size_t unpadded_linesize = frame->nb_samples * av_get_bytes_per_sample(frame->format);
printf("audio_frame n:%d nb_samples:%d pts:%s\n",
*frame_count, frame->nb_samples,
av_ts2timestr(frame->pts, &dec_ctx->time_base));
*frame_count += 1;
/* 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, dst_file);
}
} else if (dec_ctx->codec_type == AVMEDIA_TYPE_SUBTITLE) {
ret = 0;
/* decode video frame */
ret = avcodec_decode_subtitle2(dec_ctx, &sub, got_frame, pkt);
if (ret < 0) {
fprintf(stderr, "Error decoding subtitle (%s)\n", av_err2str(ret));
return ret;
}
if (*got_frame) {
printf("subtitle n:%d format:%u pts:%s start_time:%u end_time:%u num_recs:%u\n",
*frame_count, sub.format,
av_ts2timestr(sub.pts, &dec_ctx->time_base),
sub.start_display_time, sub.end_display_time, sub.num_rects);
*frame_count += 1;
/* write to text file */
for (i = 0; i < sub.num_rects; i += 1) {
fprintf(dst_file, "x:%d y:%d w:%d h:%d nb_colors:%d flags:%x linesizes:%d,%d,%d,%d,%d,%d,%d,%d\n"
"text:%s\nass:%s\n",
sub.rects[i]->x, sub.rects[i]->y, sub.rects[i]->w, sub.rects[i]->h,
sub.rects[i]->nb_colors, sub.rects[i]->flags,
sub.rects[i]->pict.linesize[0], sub.rects[i]->pict.linesize[1],
sub.rects[i]->pict.linesize[2], sub.rects[i]->pict.linesize[3],
sub.rects[i]->pict.linesize[4], sub.rects[i]->pict.linesize[5],
sub.rects[i]->pict.linesize[6], sub.rects[i]->pict.linesize[7],
sub.rects[i]->text, sub.rects[i]->ass);
for (j = 0; j < AV_NUM_DATA_POINTERS; j += 1) {
if (sub.rects[i]->pict.linesize[j]) {
fprintf(dst_file, "data:%d\n", j);
for (k = 0; k < sub.rects[i]->h; k += 1) {
for (l = 0; l < sub.rects[i]->w; l += 1) {
fprintf(dst_file, "%x", sub.rects[i]->pict.data[j][l + k * sub.rects[i]->pict.linesize[j]]);
}
fprintf(dst_file, "\n");
}
}
}
}
avsubtitle_free(&sub);
}
}
/* de-reference the frame, which is not used anymore */
if (*got_frame)
av_frame_unref(frame);
return ret;
}
static int filter_frame(AVFilterLink *inlink, AVFrame *buf)
{
AVFilterContext *ctx = inlink->dst;
AShowInfoContext *s = ctx->priv;
char chlayout_str[128];
uint32_t checksum = 0;
int channels = inlink->channels;
int planar = av_sample_fmt_is_planar(buf->format);
int block_align = av_get_bytes_per_sample(buf->format) * (planar ? 1 : channels);
int data_size = buf->nb_samples * block_align;
int planes = planar ? channels : 1;
int i;
void *tmp_ptr = av_realloc_array(s->plane_checksums, channels, sizeof(*s->plane_checksums));
if (!tmp_ptr)
return AVERROR(ENOMEM);
s->plane_checksums = tmp_ptr;
for (i = 0; i < planes; i++) {
uint8_t *data = buf->extended_data[i];
s->plane_checksums[i] = av_adler32_update(0, data, data_size);
checksum = i ? av_adler32_update(checksum, data, data_size) :
s->plane_checksums[0];
}
av_get_channel_layout_string(chlayout_str, sizeof(chlayout_str), -1,
buf->channel_layout);
av_log(ctx, AV_LOG_INFO,
"n:%"PRId64" pts:%s pts_time:%s pos:%"PRId64" "
"fmt:%s channels:%d chlayout:%s rate:%d nb_samples:%d "
"checksum:%08"PRIX32" ",
inlink->frame_count_out,
av_ts2str(buf->pts), av_ts2timestr(buf->pts, &inlink->time_base),
av_frame_get_pkt_pos(buf),
av_get_sample_fmt_name(buf->format), av_frame_get_channels(buf), chlayout_str,
buf->sample_rate, buf->nb_samples,
checksum);
av_log(ctx, AV_LOG_INFO, "plane_checksums: [ ");
for (i = 0; i < planes; i++)
av_log(ctx, AV_LOG_INFO, "%08"PRIX32" ", s->plane_checksums[i]);
av_log(ctx, AV_LOG_INFO, "]\n");
for (i = 0; i < buf->nb_side_data; i++) {
AVFrameSideData *sd = buf->side_data[i];
av_log(ctx, AV_LOG_INFO, " side data - ");
switch (sd->type) {
case AV_FRAME_DATA_MATRIXENCODING: dump_matrixenc (ctx, sd); break;
case AV_FRAME_DATA_DOWNMIX_INFO: dump_downmix (ctx, sd); break;
case AV_FRAME_DATA_REPLAYGAIN: dump_replaygain(ctx, sd); break;
case AV_FRAME_DATA_AUDIO_SERVICE_TYPE: dump_audio_service_type(ctx, sd); break;
default: dump_unknown (ctx, sd); break;
}
av_log(ctx, AV_LOG_INFO, "\n");
}
return ff_filter_frame(inlink->dst->outputs[0], buf);
}
static int decode_packet(int *got_frame, int cached)
{
int ret = 0;
int decoded = pkt.size;
*got_frame = 0;
//avpicture_fill(h264_frame, (uint8_t*)yuv_buff, PIX_FMT_YUV420P, frame->width*SCALE_MULTIPLE, frame->height*SCALE_MULTIPLE);
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 pts:%s\n",
cached ? "(cached)" : "",
video_frame_count++, frame->coded_picture_number,
av_ts2timestr(frame->pts, &video_dec_ctx->time_base));
/*scale yuv*/
/* 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);
/* convert to destination format */
sws_scale(sws_ctx, (const uint8_t * const*)video_dst_data,
video_dst_linesize, 0, height, scale_video_dst_data , scale_video_dst_linesize);
/*encode yuv to h264*/
encode2file();
/* write to rawvideo file */
//fwrite(video_dst_data[0], 1, video_dst_bufsize, video_dst_file);
fwrite(scale_video_dst_data[0], 1, scale_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;
}
