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;
}
static int ff_filter_frame_framed(AVFilterLink *link, AVFrame *frame)
{
int (*filter_frame)(AVFilterLink *, AVFrame *);
AVFilterContext *dstctx = link->dst;
AVFilterPad *dst = link->dstpad;
AVFrame *out;
int ret;
AVFilterCommand *cmd= link->dst->command_queue;
int64_t pts;
if (link->closed) {
av_frame_free(&frame);
return AVERROR_EOF;
}
if (!(filter_frame = dst->filter_frame))
filter_frame = default_filter_frame;
/* copy the frame if needed */
if (dst->needs_writable && !av_frame_is_writable(frame)) {
av_log(link->dst, AV_LOG_DEBUG, "Copying data in avfilter.\n");
/* Maybe use ff_copy_buffer_ref instead? */
switch (link->type) {
case AVMEDIA_TYPE_VIDEO:
out = ff_get_video_buffer(link, link->w, link->h);
break;
case AVMEDIA_TYPE_AUDIO:
out = ff_get_audio_buffer(link, frame->nb_samples);
break;
default:
return AVERROR(EINVAL);
}
if (!out) {
av_frame_free(&frame);
return AVERROR(ENOMEM);
}
av_frame_copy_props(out, frame);
switch (link->type) {
case AVMEDIA_TYPE_VIDEO:
av_image_copy(out->data, out->linesize, (const uint8_t **)frame->data, frame->linesize,
frame->format, frame->width, frame->height);
break;
case AVMEDIA_TYPE_AUDIO:
av_samples_copy(out->extended_data, frame->extended_data,
0, 0, frame->nb_samples,
av_get_channel_layout_nb_channels(frame->channel_layout),
frame->format);
break;
default:
return AVERROR(EINVAL);
}
av_frame_free(&frame);
} else
out = frame;
while(cmd && cmd->time <= out->pts * av_q2d(link->time_base)) {
av_log(link->dst, AV_LOG_DEBUG,
"Processing command time:%f command:%s arg:%s\n",
cmd->time, cmd->command, cmd->arg);
avfilter_process_command(link->dst, cmd->command, cmd->arg, 0, 0, cmd->flags);
ff_command_queue_pop(link->dst);
cmd= link->dst->command_queue;
}
pts = out->pts;
if (dstctx->enable_str) {
int64_t pos = av_frame_get_pkt_pos(out);
dstctx->var_values[VAR_N] = link->frame_count;
dstctx->var_values[VAR_T] = pts == AV_NOPTS_VALUE ? NAN : pts * av_q2d(link->time_base);
dstctx->var_values[VAR_POS] = pos == -1 ? NAN : pos;
dstctx->is_disabled = !av_expr_eval(dstctx->enable, dstctx->var_values, NULL);
if (dstctx->is_disabled &&
(dstctx->filter->flags & AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC))
filter_frame = default_filter_frame;
}
ret = filter_frame(link, out);
link->frame_count++;
link->frame_requested = 0;
ff_update_link_current_pts(link, pts);
return ret;
}
int av_frame_ref(AVFrame *dst, const AVFrame *src)
{
int i, ret = 0;
dst->format = src->format;
dst->width = src->width;
dst->height = src->height;
dst->channel_layout = src->channel_layout;
dst->nb_samples = src->nb_samples;
ret = av_frame_copy_props(dst, src);
if (ret < 0)
return ret;
/* duplicate the frame data if it's not refcounted */
if (!src->buf[0]) {
ret = av_frame_get_buffer(dst, 32);
if (ret < 0)
return ret;
if (src->nb_samples) {
int ch = av_get_channel_layout_nb_channels(src->channel_layout);
av_samples_copy(dst->extended_data, src->extended_data, 0, 0,
dst->nb_samples, ch, dst->format);
} else {
av_image_copy(dst->data, dst->linesize, src->data, src->linesize,
dst->format, dst->width, dst->height);
}
return 0;
}
/* ref the buffers */
for (i = 0; i < FF_ARRAY_ELEMS(src->buf) && src->buf[i]; i++) {
dst->buf[i] = av_buffer_ref(src->buf[i]);
if (!dst->buf[i]) {
ret = AVERROR(ENOMEM);
goto fail;
}
}
if (src->extended_buf) {
dst->extended_buf = av_mallocz(sizeof(*dst->extended_buf) *
src->nb_extended_buf);
if (!dst->extended_buf) {
ret = AVERROR(ENOMEM);
goto fail;
}
dst->nb_extended_buf = src->nb_extended_buf;
for (i = 0; i < src->nb_extended_buf; i++) {
dst->extended_buf[i] = av_buffer_ref(src->extended_buf[i]);
if (!dst->extended_buf[i]) {
ret = AVERROR(ENOMEM);
goto fail;
}
}
}
/* duplicate extended data */
if (src->extended_data != src->data) {
int ch = av_get_channel_layout_nb_channels(src->channel_layout);
if (!ch) {
ret = AVERROR(EINVAL);
goto fail;
}
dst->extended_data = av_malloc(sizeof(*dst->extended_data) * ch);
if (!dst->extended_data) {
ret = AVERROR(ENOMEM);
goto fail;
}
memcpy(dst->extended_data, src->extended_data, sizeof(*src->extended_data) * ch);
} else
dst->extended_data = dst->data;
memcpy(dst->data, src->data, sizeof(src->data));
memcpy(dst->linesize, src->linesize, sizeof(src->linesize));
return 0;
fail:
av_frame_unref(dst);
return ret;
}
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
{
int (*filter_frame)(AVFilterLink *, AVFrame *);
AVFilterPad *dst = link->dstpad;
AVFrame *out = NULL;
int ret;
FF_DPRINTF_START(NULL, filter_frame);
ff_dlog_link(NULL, link, 1);
if (!(filter_frame = dst->filter_frame))
filter_frame = default_filter_frame;
/* copy the frame if needed */
if (dst->needs_writable && !av_frame_is_writable(frame)) {
av_log(link->dst, AV_LOG_DEBUG, "Copying data in avfilter.\n");
switch (link->type) {
case AVMEDIA_TYPE_VIDEO:
out = ff_get_video_buffer(link, link->w, link->h);
break;
case AVMEDIA_TYPE_AUDIO:
out = ff_get_audio_buffer(link, frame->nb_samples);
break;
default:
ret = AVERROR(EINVAL);
goto fail;
}
if (!out) {
ret = AVERROR(ENOMEM);
goto fail;
}
ret = av_frame_copy_props(out, frame);
if (ret < 0)
goto fail;
switch (link->type) {
case AVMEDIA_TYPE_VIDEO:
av_image_copy(out->data, out->linesize, frame->data, frame->linesize,
frame->format, frame->width, frame->height);
break;
case AVMEDIA_TYPE_AUDIO:
av_samples_copy(out->extended_data, frame->extended_data,
0, 0, frame->nb_samples,
av_get_channel_layout_nb_channels(frame->channel_layout),
frame->format);
break;
default:
ret = AVERROR(EINVAL);
goto fail;
}
av_frame_free(&frame);
} else
out = frame;
return filter_frame(link, out);
fail:
av_frame_free(&out);
av_frame_free(&frame);
return ret;
}
static int videotoolbox_retrieve_data(AVCodecContext *s, AVFrame *frame)
{
InputStream *ist = s->opaque;
VTContext *vt = ist->hwaccel_ctx;
CVPixelBufferRef pixbuf = (CVPixelBufferRef)frame->data[3];
OSType pixel_format = CVPixelBufferGetPixelFormatType(pixbuf);
CVReturn err;
uint8_t *data[4] = { 0 };
int linesize[4] = { 0 };
int planes, ret, i;
char codec_str[32];
av_frame_unref(vt->tmp_frame);
switch (pixel_format) {
case kCVPixelFormatType_420YpCbCr8Planar: vt->tmp_frame->format = AV_PIX_FMT_YUV420P; break;
case kCVPixelFormatType_422YpCbCr8: vt->tmp_frame->format = AV_PIX_FMT_UYVY422; break;
case kCVPixelFormatType_32BGRA: vt->tmp_frame->format = AV_PIX_FMT_BGRA; break;
#ifdef kCFCoreFoundationVersionNumber10_7
case kCVPixelFormatType_420YpCbCr8BiPlanarVideoRange: vt->tmp_frame->format = AV_PIX_FMT_NV12; break;
#endif
default:
av_get_codec_tag_string(codec_str, sizeof(codec_str), s->codec_tag);
av_log(NULL, AV_LOG_ERROR,
"%s: Unsupported pixel format: %s\n", codec_str, videotoolbox_pixfmt);
return AVERROR(ENOSYS);
}
vt->tmp_frame->width = frame->width;
vt->tmp_frame->height = frame->height;
ret = av_frame_get_buffer(vt->tmp_frame, 32);
if (ret < 0)
return ret;
err = CVPixelBufferLockBaseAddress(pixbuf, kCVPixelBufferLock_ReadOnly);
if (err != kCVReturnSuccess) {
av_log(NULL, AV_LOG_ERROR, "Error locking the pixel buffer.\n");
return AVERROR_UNKNOWN;
}
if (CVPixelBufferIsPlanar(pixbuf)) {
planes = CVPixelBufferGetPlaneCount(pixbuf);
for (i = 0; i < planes; i++) {
data[i] = CVPixelBufferGetBaseAddressOfPlane(pixbuf, i);
linesize[i] = CVPixelBufferGetBytesPerRowOfPlane(pixbuf, i);
}
} else {
data[0] = CVPixelBufferGetBaseAddress(pixbuf);
linesize[0] = CVPixelBufferGetBytesPerRow(pixbuf);
}
av_image_copy(vt->tmp_frame->data, vt->tmp_frame->linesize,
(const uint8_t **)data, linesize, vt->tmp_frame->format,
frame->width, frame->height);
ret = av_frame_copy_props(vt->tmp_frame, frame);
CVPixelBufferUnlockBaseAddress(pixbuf, kCVPixelBufferLock_ReadOnly);
if (ret < 0)
return ret;
av_frame_unref(frame);
av_frame_move_ref(frame, vt->tmp_frame);
return 0;
}
static int libkvazaar_encode(AVCodecContext *avctx,
AVPacket *avpkt,
const AVFrame *frame,
int *got_packet_ptr)
{
int retval = 0;
kvz_picture *img_in = NULL;
kvz_data_chunk *data_out = NULL;
uint32_t len_out = 0;
kvz_picture *recon_pic = NULL;
kvz_frame_info frame_info;
LibkvazaarContext *ctx = avctx->priv_data;
*got_packet_ptr = 0;
if (frame) {
if (frame->width != ctx->config->width ||
frame->height != ctx->config->height) {
av_log(avctx, AV_LOG_ERROR,
"Changing video dimensions during encoding is not supported. "
"(changed from %dx%d to %dx%d)\n",
ctx->config->width, ctx->config->height,
frame->width, frame->height);
retval = AVERROR_INVALIDDATA;
goto done;
}
if (frame->format != avctx->pix_fmt) {
av_log(avctx, AV_LOG_ERROR,
"Changing pixel format during encoding is not supported. "
"(changed from %s to %s)\n",
av_get_pix_fmt_name(avctx->pix_fmt),
av_get_pix_fmt_name(frame->format));
retval = AVERROR_INVALIDDATA;
goto done;
}
// Allocate input picture for kvazaar.
img_in = ctx->api->picture_alloc(frame->width, frame->height);
if (!img_in) {
av_log(avctx, AV_LOG_ERROR, "Failed to allocate picture.\n");
retval = AVERROR(ENOMEM);
goto done;
}
// Copy pixels from frame to img_in.
{
int dst_linesizes[4] = {
frame->width,
frame->width / 2,
frame->width / 2,
0
};
av_image_copy(img_in->data, dst_linesizes,
frame->data, frame->linesize,
frame->format, frame->width, frame->height);
}
img_in->pts = frame->pts;
}
if (!ctx->api->encoder_encode(ctx->encoder, img_in,
&data_out, &len_out,
&recon_pic, NULL,
&frame_info)) {
av_log(avctx, AV_LOG_ERROR, "Failed to encode frame.\n");
retval = AVERROR_EXTERNAL;
goto done;
}
if (data_out) {
kvz_data_chunk *chunk = NULL;
uint64_t written = 0;
retval = ff_alloc_packet(avpkt, len_out);
if (retval < 0) {
av_log(avctx, AV_LOG_ERROR, "Failed to allocate output packet.\n");
goto done;
}
for (chunk = data_out; chunk != NULL; chunk = chunk->next) {
av_assert0(written + chunk->len <= len_out);
memcpy(avpkt->data + written, chunk->data, chunk->len);
written += chunk->len;
}
*got_packet_ptr = 1;
ctx->api->chunk_free(data_out);
data_out = NULL;
avpkt->pts = recon_pic->pts;
avpkt->dts = recon_pic->dts;
avpkt->flags = 0;
// IRAP VCL NAL unit types span the range
// [BLA_W_LP (16), RSV_IRAP_VCL23 (23)].
if (frame_info.nal_unit_type >= KVZ_NAL_BLA_W_LP &&
frame_info.nal_unit_type <= KVZ_NAL_RSV_IRAP_VCL23) {
avpkt->flags |= AV_PKT_FLAG_KEY;
}
}
done:
ctx->api->picture_free(img_in);
ctx->api->picture_free(recon_pic);
ctx->api->chunk_free(data_out);
return retval;
}
