As it stands, my project correctly uses libavcodec to decode a video, where each frame is manipulated (it doesn't matter how) and output to a new video. I've cobbled this together from examples found online, and it works. The result is a perfect .mp4 of the manipulated frames, minus the audio.
My problem is, when I try to add an audio stream to the output container, I get a crash in mux.c that I can't explain. It's in static int compute_muxer_pkt_fields(AVFormatContext *s, AVStream *st, AVPacket *pkt). Where st->internal->priv_pts->val = pkt->dts; is attempted, priv_pts is nullptr.
I don't recall the version number, but this is from a November 4, 2020 ffmpeg build from git.
My MediaContentMgr is much bigger than what I have here. I'm stripping out everything to do with the frame manipulation, so if I'm missing anything, please let me know and I'll edit.
The code that, when added, triggers the nullptr exception, is called out inline
The .h:
#ifndef _API_EXAMPLE_H
#define _API_EXAMPLE_H
#include <glad/glad.h>
#include <GLFW/glfw3.h>
#include "glm/glm.hpp"
extern "C" {
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavutil/avutil.h>
#include <libavutil/opt.h>
#include <libswscale/swscale.h>
}
#include "shader_s.h"
class MediaContainerMgr {
public:
MediaContainerMgr(const std::string& infile, const std::string& vert, const std::string& frag,
const glm::vec3* extents);
~MediaContainerMgr();
void render();
bool recording() { return m_recording; }
// Major thanks to "shi-yan" who helped make this possible:
// https://github.com/shi-yan/videosamples/blob/master/libavmp4encoding/main.cpp
bool init_video_output(const std::string& video_file_name, unsigned int width, unsigned int height);
bool output_video_frame(uint8_t* buf);
bool finalize_output();
private:
AVFormatContext* m_format_context;
AVCodec* m_video_codec;
AVCodec* m_audio_codec;
AVCodecParameters* m_video_codec_parameters;
AVCodecParameters* m_audio_codec_parameters;
AVCodecContext* m_codec_context;
AVFrame* m_frame;
AVPacket* m_packet;
uint32_t m_video_stream_index;
uint32_t m_audio_stream_index;
void init_rendering(const glm::vec3* extents);
int decode_packet();
// For writing the output video:
void free_output_assets();
bool m_recording;
AVOutputFormat* m_output_format;
AVFormatContext* m_output_format_context;
AVCodec* m_output_video_codec;
AVCodecContext* m_output_video_codec_context;
AVFrame* m_output_video_frame;
SwsContext* m_output_scale_context;
AVStream* m_output_video_stream;
AVCodec* m_output_audio_codec;
AVStream* m_output_audio_stream;
AVCodecContext* m_output_audio_codec_context;
};
#endif
And, the hellish .cpp:
#include <stdio.h>
#include <stdarg.h>
#include <stdlib.h>
#include <string.h>
#include <inttypes.h>
#include "media_container_manager.h"
MediaContainerMgr::MediaContainerMgr(const std::string& infile, const std::string& vert, const std::string& frag,
const glm::vec3* extents) :
m_video_stream_index(-1),
m_audio_stream_index(-1),
m_recording(false),
m_output_format(nullptr),
m_output_format_context(nullptr),
m_output_video_codec(nullptr),
m_output_video_codec_context(nullptr),
m_output_video_frame(nullptr),
m_output_scale_context(nullptr),
m_output_video_stream(nullptr)
{
// AVFormatContext holds header info from the format specified in the container:
m_format_context = avformat_alloc_context();
if (!m_format_context) {
throw "ERROR could not allocate memory for Format Context";
}
// open the file and read its header. Codecs are not opened here.
if (avformat_open_input(&m_format_context, infile.c_str(), NULL, NULL) != 0) {
throw "ERROR could not open input file for reading";
}
printf("format %s, duration %lldus, bit_rate %lld\n", m_format_context->iformat->name, m_format_context->duration, m_format_context->bit_rate);
//read avPackets (?) from the avFormat (?) to get stream info. This populates format_context->streams.
if (avformat_find_stream_info(m_format_context, NULL) < 0) {
throw "ERROR could not get stream info";
}
for (unsigned int i = 0; i < m_format_context->nb_streams; i++) {
AVCodecParameters* local_codec_parameters = NULL;
local_codec_parameters = m_format_context->streams[i]->codecpar;
printf("AVStream->time base before open coded %d/%d\n", m_format_context->streams[i]->time_base.num, m_format_context->streams[i]->time_base.den);
printf("AVStream->r_frame_rate before open coded %d/%d\n", m_format_context->streams[i]->r_frame_rate.num, m_format_context->streams[i]->r_frame_rate.den);
printf("AVStream->start_time %" PRId64 "\n", m_format_context->streams[i]->start_time);
printf("AVStream->duration %" PRId64 "\n", m_format_context->streams[i]->duration);
printf("duration(s): %lf\n", (float)m_format_context->streams[i]->duration / m_format_context->streams[i]->time_base.den * m_format_context->streams[i]->time_base.num);
AVCodec* local_codec = NULL;
local_codec = avcodec_find_decoder(local_codec_parameters->codec_id);
if (local_codec == NULL) {
throw "ERROR unsupported codec!";
}
if (local_codec_parameters->codec_type == AVMEDIA_TYPE_VIDEO) {
if (m_video_stream_index == -1) {
m_video_stream_index = i;
m_video_codec = local_codec;
m_video_codec_parameters = local_codec_parameters;
}
m_height = local_codec_parameters->height;
m_width = local_codec_parameters->width;
printf("Video Codec: resolution %dx%d\n", m_width, m_height);
}
else if (local_codec_parameters->codec_type == AVMEDIA_TYPE_AUDIO) {
if (m_audio_stream_index == -1) {
m_audio_stream_index = i;
m_audio_codec = local_codec;
m_audio_codec_parameters = local_codec_parameters;
}
printf("Audio Codec: %d channels, sample rate %d\n", local_codec_parameters->channels, local_codec_parameters->sample_rate);
}
printf("\tCodec %s ID %d bit_rate %lld\n", local_codec->name, local_codec->id, local_codec_parameters->bit_rate);
}
m_codec_context = avcodec_alloc_context3(m_video_codec);
if (!m_codec_context) {
throw "ERROR failed to allocate memory for AVCodecContext";
}
if (avcodec_parameters_to_context(m_codec_context, m_video_codec_parameters) < 0) {
throw "ERROR failed to copy codec params to codec context";
}
if (avcodec_open2(m_codec_context, m_video_codec, NULL) < 0) {
throw "ERROR avcodec_open2 failed to open codec";
}
m_frame = av_frame_alloc();
if (!m_frame) {
throw "ERROR failed to allocate AVFrame memory";
}
m_packet = av_packet_alloc();
if (!m_packet) {
throw "ERROR failed to allocate AVPacket memory";
}
}
MediaContainerMgr::~MediaContainerMgr() {
avformat_close_input(&m_format_context);
av_packet_free(&m_packet);
av_frame_free(&m_frame);
avcodec_free_context(&m_codec_context);
glDeleteVertexArrays(1, &m_VAO);
glDeleteBuffers(1, &m_VBO);
}
bool MediaContainerMgr::advance_frame() {
while (true) {
if (av_read_frame(m_format_context, m_packet) < 0) {
// Do we actually need to unref the packet if it failed?
av_packet_unref(m_packet);
continue;
//return false;
}
else {
if (m_packet->stream_index == m_video_stream_index) {
//printf("AVPacket->pts %" PRId64 "\n", m_packet->pts);
int response = decode_packet();
av_packet_unref(m_packet);
if (response != 0) {
continue;
//return false;
}
return true;
}
else {
printf("m_packet->stream_index: %d\n", m_packet->stream_index);
printf(" m_packet->pts: %lld\n", m_packet->pts);
printf(" mpacket->size: %d\n", m_packet->size);
if (m_recording) {
int err = 0;
//err = avcodec_send_packet(m_output_video_codec_context, m_packet);
printf(" encoding error: %d\n", err);
}
}
}
// We're done with the packet (it's been unpacked to a frame), so deallocate & reset to defaults:
/*
if (m_frame == NULL)
return false;
if (m_frame->data[0] == NULL || m_frame->data[1] == NULL || m_frame->data[2] == NULL) {
printf("WARNING: null frame data");
continue;
}
*/
}
}
int MediaContainerMgr::decode_packet() {
// Supply raw packet data as input to a decoder
// https://ffmpeg.org/doxygen/trunk/group__lavc__decoding.html#ga58bc4bf1e0ac59e27362597e467efff3
int response = avcodec_send_packet(m_codec_context, m_packet);
if (response < 0) {
char buf[256];
av_strerror(response, buf, 256);
printf("Error while receiving a frame from the decoder: %s\n", buf);
return response;
}
// Return decoded output data (into a frame) from a decoder
// https://ffmpeg.org/doxygen/trunk/group__lavc__decoding.html#ga11e6542c4e66d3028668788a1a74217c
response = avcodec_receive_frame(m_codec_context, m_frame);
if (response == AVERROR(EAGAIN) || response == AVERROR_EOF) {
return response;
} else if (response < 0) {
char buf[256];
av_strerror(response, buf, 256);
printf("Error while receiving a frame from the decoder: %s\n", buf);
return response;
} else {
printf(
"Frame %d (type=%c, size=%d bytes) pts %lld key_frame %d [DTS %d]\n",
m_codec_context->frame_number,
av_get_picture_type_char(m_frame->pict_type),
m_frame->pkt_size,
m_frame->pts,
m_frame->key_frame,
m_frame->coded_picture_number
);
}
return 0;
}
bool MediaContainerMgr::init_video_output(const std::string& video_file_name, unsigned int width, unsigned int height) {
if (m_recording)
return true;
m_recording = true;
advance_to(0L); // I've deleted the implmentation. Just seeks to beginning of vid. Works fine.
if (!(m_output_format = av_guess_format(nullptr, video_file_name.c_str(), nullptr))) {
printf("Cannot guess output format.\n");
return false;
}
int err = avformat_alloc_output_context2(&m_output_format_context, m_output_format, nullptr, video_file_name.c_str());
if (err < 0) {
printf("Failed to allocate output context.\n");
return false;
}
//TODO(P0): Break out the video and audio inits into their own methods.
m_output_video_codec = avcodec_find_encoder(m_output_format->video_codec);
if (!m_output_video_codec) {
printf("Failed to create video codec.\n");
return false;
}
m_output_video_stream = avformat_new_stream(m_output_format_context, m_output_video_codec);
if (!m_output_video_stream) {
printf("Failed to find video format.\n");
return false;
}
m_output_video_codec_context = avcodec_alloc_context3(m_output_video_codec);
if (!m_output_video_codec_context) {
printf("Failed to create video codec context.\n");
return(false);
}
m_output_video_stream->codecpar->codec_id = m_output_format->video_codec;
m_output_video_stream->codecpar->codec_type = AVMEDIA_TYPE_VIDEO;
m_output_video_stream->codecpar->width = width;
m_output_video_stream->codecpar->height = height;
m_output_video_stream->codecpar->format = AV_PIX_FMT_YUV420P;
// Use the same bit rate as the input stream.
m_output_video_stream->codecpar->bit_rate = m_format_context->streams[m_video_stream_index]->codecpar->bit_rate;
m_output_video_stream->avg_frame_rate = m_format_context->streams[m_video_stream_index]->avg_frame_rate;
avcodec_parameters_to_context(m_output_video_codec_context, m_output_video_stream->codecpar);
m_output_video_codec_context->time_base = m_format_context->streams[m_video_stream_index]->time_base;
//TODO(P1): Set these to match the input stream?
m_output_video_codec_context->max_b_frames = 2;
m_output_video_codec_context->gop_size = 12;
m_output_video_codec_context->framerate = m_format_context->streams[m_video_stream_index]->r_frame_rate;
//m_output_codec_context->refcounted_frames = 0;
if (m_output_video_stream->codecpar->codec_id == AV_CODEC_ID_H264) {
av_opt_set(m_output_video_codec_context, "preset", "ultrafast", 0);
} else if (m_output_video_stream->codecpar->codec_id == AV_CODEC_ID_H265) {
av_opt_set(m_output_video_codec_context, "preset", "ultrafast", 0);
} else {
av_opt_set_int(m_output_video_codec_context, "lossless", 1, 0);
}
avcodec_parameters_from_context(m_output_video_stream->codecpar, m_output_video_codec_context);
m_output_audio_codec = avcodec_find_encoder(m_output_format->audio_codec);
if (!m_output_audio_codec) {
printf("Failed to create audio codec.\n");
return false;
}
I've commented out all of the audio stream init beyond this next line, because this is where
the trouble begins. Creating this output stream causes the null reference I mentioned. If I
uncomment everything below here, I still get the null deref. If I comment out this line, the
deref exception vanishes. (IOW, I commented out more and more code until I found that this
was the trigger that caused the problem.)
I assume that there's something I'm doing wrong in the rest of the commented out code, that,
when fixed, will fix the nullptr and give me a working audio stream.
m_output_audio_stream = avformat_new_stream(m_output_format_context, m_output_audio_codec);
if (!m_output_audio_stream) {
printf("Failed to find audio format.\n");
return false;
}
/*
m_output_audio_codec_context = avcodec_alloc_context3(m_output_audio_codec);
if (!m_output_audio_codec_context) {
printf("Failed to create audio codec context.\n");
return(false);
}
m_output_audio_stream->codecpar->codec_id = m_output_format->audio_codec;
m_output_audio_stream->codecpar->codec_type = AVMEDIA_TYPE_AUDIO;
m_output_audio_stream->codecpar->format = m_format_context->streams[m_audio_stream_index]->codecpar->format;
m_output_audio_stream->codecpar->bit_rate = m_format_context->streams[m_audio_stream_index]->codecpar->bit_rate;
m_output_audio_stream->avg_frame_rate = m_format_context->streams[m_audio_stream_index]->avg_frame_rate;
avcodec_parameters_to_context(m_output_audio_codec_context, m_output_audio_stream->codecpar);
m_output_audio_codec_context->time_base = m_format_context->streams[m_audio_stream_index]->time_base;
*/
//TODO(P2): Free assets that have been allocated.
err = avcodec_open2(m_output_video_codec_context, m_output_video_codec, nullptr);
if (err < 0) {
printf("Failed to open codec.\n");
return false;
}
if (!(m_output_format->flags & AVFMT_NOFILE)) {
err = avio_open(&m_output_format_context->pb, video_file_name.c_str(), AVIO_FLAG_WRITE);
if (err < 0) {
printf("Failed to open output file.");
return false;
}
}
err = avformat_write_header(m_output_format_context, NULL);
if (err < 0) {
printf("Failed to write header.\n");
return false;
}
av_dump_format(m_output_format_context, 0, video_file_name.c_str(), 1);
return true;
}
//TODO(P2): make this a member. (Thanks to https://emvlo.wordpress.com/2016/03/10/sws_scale/)
void PrepareFlipFrameJ420(AVFrame* pFrame) {
for (int i = 0; i < 4; i++) {
if (i)
pFrame->data[i] += pFrame->linesize[i] * ((pFrame->height >> 1) - 1);
else
pFrame->data[i] += pFrame->linesize[i] * (pFrame->height - 1);
pFrame->linesize[i] = -pFrame->linesize[i];
}
}
This is where we take an altered frame and write it to the output container. This works fine
as long as we haven't set up an audio stream in the output container.
bool MediaContainerMgr::output_video_frame(uint8_t* buf) {
int err;
if (!m_output_video_frame) {
m_output_video_frame = av_frame_alloc();
m_output_video_frame->format = AV_PIX_FMT_YUV420P;
m_output_video_frame->width = m_output_video_codec_context->width;
m_output_video_frame->height = m_output_video_codec_context->height;
err = av_frame_get_buffer(m_output_video_frame, 32);
if (err < 0) {
printf("Failed to allocate output frame.\n");
return false;
}
}
if (!m_output_scale_context) {
m_output_scale_context = sws_getContext(m_output_video_codec_context->width, m_output_video_codec_context->height,
AV_PIX_FMT_RGB24,
m_output_video_codec_context->width, m_output_video_codec_context->height,
AV_PIX_FMT_YUV420P, SWS_BICUBIC, nullptr, nullptr, nullptr);
}
int inLinesize[1] = { 3 * m_output_video_codec_context->width };
sws_scale(m_output_scale_context, (const uint8_t* const*)&buf, inLinesize, 0, m_output_video_codec_context->height,
m_output_video_frame->data, m_output_video_frame->linesize);
PrepareFlipFrameJ420(m_output_video_frame);
//TODO(P0): Switch m_frame to be m_input_video_frame so I don't end up using the presentation timestamp from
// an audio frame if I threadify the frame reading.
m_output_video_frame->pts = m_frame->pts;
printf("Output PTS: %d, time_base: %d/%d\n", m_output_video_frame->pts,
m_output_video_codec_context->time_base.num, m_output_video_codec_context->time_base.den);
err = avcodec_send_frame(m_output_video_codec_context, m_output_video_frame);
if (err < 0) {
printf(" ERROR sending new video frame output: ");
switch (err) {
case AVERROR(EAGAIN):
printf("AVERROR(EAGAIN): %d\n", err);
break;
case AVERROR_EOF:
printf("AVERROR_EOF: %d\n", err);
break;
case AVERROR(EINVAL):
printf("AVERROR(EINVAL): %d\n", err);
break;
case AVERROR(ENOMEM):
printf("AVERROR(ENOMEM): %d\n", err);
break;
}
return false;
}
AVPacket pkt;
av_init_packet(&pkt);
pkt.data = nullptr;
pkt.size = 0;
pkt.flags |= AV_PKT_FLAG_KEY;
int ret = 0;
if ((ret = avcodec_receive_packet(m_output_video_codec_context, &pkt)) == 0) {
static int counter = 0;
printf("pkt.key: 0x%08x, pkt.size: %d, counter:\n", pkt.flags & AV_PKT_FLAG_KEY, pkt.size, counter++);
uint8_t* size = ((uint8_t*)pkt.data);
printf("sizes: %d %d %d %d %d %d %d %d %d\n", size[0], size[1], size[2], size[2], size[3], size[4], size[5], size[6], size[7]);
av_interleaved_write_frame(m_output_format_context, &pkt);
}
printf("push: %d\n", ret);
av_packet_unref(&pkt);
return true;
}
bool MediaContainerMgr::finalize_output() {
if (!m_recording)
return true;
AVPacket pkt;
av_init_packet(&pkt);
pkt.data = nullptr;
pkt.size = 0;
for (;;) {
avcodec_send_frame(m_output_video_codec_context, nullptr);
if (avcodec_receive_packet(m_output_video_codec_context, &pkt) == 0) {
av_interleaved_write_frame(m_output_format_context, &pkt);
printf("final push:\n");
} else {
break;
}
}
av_packet_unref(&pkt);
av_write_trailer(m_output_format_context);
if (!(m_output_format->flags & AVFMT_NOFILE)) {
int err = avio_close(m_output_format_context->pb);
if (err < 0) {
printf("Failed to close file. err: %d\n", err);
return false;
}
}
return true;
}
EDIT
The call stack on the crash (which I should have included in the original question):
avformat-58.dll!compute_muxer_pkt_fields(AVFormatContext * s, AVStream * st, AVPacket * pkt) Line 630 C
avformat-58.dll!write_packet_common(AVFormatContext * s, AVStream * st, AVPacket * pkt, int interleaved) Line 1122 C
avformat-58.dll!write_packets_common(AVFormatContext * s, AVPacket * pkt, int interleaved) Line 1186 C
avformat-58.dll!av_interleaved_write_frame(AVFormatContext * s, AVPacket * pkt) Line 1241 C
CamBot.exe!MediaContainerMgr::output_video_frame(unsigned char * buf) Line 553 C++
CamBot.exe!main() Line 240 C++
If I move the call to avformat_write_header so it's immediately before the audio stream initialization, I still get a crash, but in a different place. The crash happens on line 6459 of movenc.c, where we have:
/* Non-seekable output is ok if using fragmentation. If ism_lookahead
* is enabled, we don't support non-seekable output at all. */
if (!(s->pb->seekable & AVIO_SEEKABLE_NORMAL) && // CRASH IS HERE
(!(mov->flags & FF_MOV_FLAG_FRAGMENT) || mov->ism_lookahead)) {
av_log(s, AV_LOG_ERROR, "muxer does not support non seekable output\n");
return AVERROR(EINVAL);
}
The exception is a nullptr exception, where s->pb is NULL. The call stack is:
avformat-58.dll!mov_init(AVFormatContext * s) Line 6459 C
avformat-58.dll!init_muxer(AVFormatContext * s, AVDictionary * * options) Line 407 C
[Inline Frame] avformat-58.dll!avformat_init_output(AVFormatContext *) Line 489 C
avformat-58.dll!avformat_write_header(AVFormatContext * s, AVDictionary * * options) Line 512 C
CamBot.exe!MediaContainerMgr::init_video_output(const std::string & video_file_name, unsigned int width, unsigned int height) Line 424 C++
CamBot.exe!main() Line 183 C++
Please note that you should always try to provide a self-contained minimal working example to make it easier for others to help. With the actual code, the matching FFmpeg version, and an input video that triggers the segmentation fault (to be sure), the issue would be a matter of analyzing the control flow to identify why st->internal->priv_pts was not allocated. Without the full scenario, I have to report to making assumptions that may or may not correspond to your actual code.
Based on your description, I attempted to reproduce the issue by cloning https://github.com/FFmpeg/FFmpeg.git and creating a new branch from commit b52e0d95 (November 4, 2020) to approximate your FFmpeg version.
I recreated your scenario using the provided code snippets by
including the avformat_new_stream() call for the audio stream
keeping the remaining audio initialization commented out
including the original avformat_write_header() call site (unchanged order)
With that scenario, the video write with MP4 video/audio input fails in avformat_write_header():
[mp4 # 0x2b39f40] sample rate not set 0
The call stack of the error location:
#0 0x00007ffff75253d7 in raise () from /lib64/libc.so.6
#1 0x00007ffff7526ac8 in abort () from /lib64/libc.so.6
#2 0x000000000094feca in init_muxer (s=0x2b39f40, options=0x0) at libavformat/mux.c:309
#3 0x00000000009508f4 in avformat_init_output (s=0x2b39f40, options=0x0) at libavformat/mux.c:490
#4 0x0000000000950a10 in avformat_write_header (s=0x2b39f40, options=0x0) at libavformat/mux.c:514
[...]
In init_muxer(), the sample rate in the stream parameters is checked unconditionally:
case AVMEDIA_TYPE_AUDIO:
if (par->sample_rate <= 0) {
av_log(s, AV_LOG_ERROR, "sample rate not set %d\n", par->sample_rate); abort();
ret = AVERROR(EINVAL);
goto fail;
}
That condition has been in effect since 2014-06-18 at the very least (didn't go back any further) and still exists. With a version from November 2020, the check must be active and the parameter must be set accordingly.
If I uncomment the remaining audio initialization, the situation remains unchanged (as expected). So, satisfy the condition, I added the missing parameter as follows:
m_output_audio_stream->codecpar->sample_rate =
m_format_context->streams[m_audio_stream_index]->codecpar->sample_rate;
With that, the check succeeds, avformat_write_header() succeeds, and the actual video write succeeds.
As you indicated in your question, the segmentation fault is caused by st->internal->priv_pts being NULL at this location:
#0 0x00000000009516db in compute_muxer_pkt_fields (s=0x2b39f40, st=0x2b3a580, pkt=0x7fffffffe2d0) at libavformat/mux.c:632
#1 0x0000000000953128 in write_packet_common (s=0x2b39f40, st=0x2b3a580, pkt=0x7fffffffe2d0, interleaved=1) at libavformat/mux.c:1125
#2 0x0000000000953473 in write_packets_common (s=0x2b39f40, pkt=0x7fffffffe2d0, interleaved=1) at libavformat/mux.c:1188
#3 0x0000000000953634 in av_interleaved_write_frame (s=0x2b39f40, pkt=0x7fffffffe2d0) at libavformat/mux.c:1243
[...]
In the FFmpeg code base, the allocation of priv_pts is handled by init_pts() for all streams referenced by the context. init_pts() has two call sites:
libavformat/mux.c:496:
if (s->oformat->init && ret) {
if ((ret = init_pts(s)) < 0)
return ret;
return AVSTREAM_INIT_IN_INIT_OUTPUT;
}
libavformat/mux.c:530:
if (!s->internal->streams_initialized) {
if ((ret = init_pts(s)) < 0)
goto fail;
}
In both cases, the calls are triggered by avformat_write_header() (indirectly via avformat_init_output() for the first, directly for the second). According to control flow analysis, there's no success case that would leave priv_pts unallocated.
Considering a high probability that our versions of FFmpeg are compatible in terms of behavior, I have to assume that 1) the sample rate must be provided for audio streams and 1) priv_pts is always allocated by avformat_write_header() in the absence of errors. Therefore, two possible root causes come to mind:
Your stream is not an audio stream (unlikely; the type is based on the codec, which in turn is based on the output file extension - assuming mp4)
You do not call avformat_write_header() (unlikely) or do not handle the error in the caller of your C++ member function (the return value of avformat_write_header() is checked but I do not have code corresponding to the caller of the C++ member function; your actual code might differ significantly from the code provided, so it's possible and the only plausible conclusion that can be drawn from available data)
The solution: Ensure that processing does not continue if avformat_write_header() fails. By adding the audio stream, avformat_write_header() starts to fail unless you set the stream sample rate. If the error is ignored, av_interleaved_write_frame() triggers a segmentation fault by accessing the unallocated st->internal->priv_pts.
As mentioned initially, scenario is incomplete. If you do call avformat_write_header() and stop processing in case of an error (meaning you do not call av_interleaved_write_frame()), more information is needed. As it stands now, that is unlikely. For further analysis, the executable output (stdout, stderr) is required to see your traces and FFmpeg log messages. If that does not reveal new information, a self-contained minimal working example and the video input are needed to get all the full picture.
I using libzip to work with zip files and everything goes fine, until i need to read file from zip
I need to read just a whole text files, so it will be great to achieve something like PHP "file_get_contents" function.
To read file from zip there is a function "int
zip_fread(struct zip_file *file, void *buf, zip_uint64_t nbytes)".
Main problem what i don't know what size of buf must be and how many nbytes i must read (well i need to read whole file, but files have different size). I can just do a big buffer to fit them all and read all it's size, or do a while loop until fread return -1 but i don't think it's rational option.
You can try using zip_stat to get file size.
http://linux.die.net/man/3/zip_stat
I haven't used the libzip interface but from what you write it seems to look very similar to a file interface: once you got a handle to the stream you keep calling zip_fread() until this function return an error (ir, possibly, less than requested bytes). The buffer you pass in us just a reasonably size temporary buffer where the data is communicated.
Personally I would probably create a stream buffer for this so once the file in the zip archive is set up it can be read using the conventional I/O stream methods. This would look something like this:
struct zipbuf: std::streambuf {
zipbuf(???): file_(???) {}
private:
zip_file* file_;
enum { s_size = 8196 };
char buffer_[s_size];
int underflow() {
int rc(zip_fread(this->file_, this->buffer_, s_size));
this->setg(this->buffer_, this->buffer_,
this->buffer_ + std::max(0, rc));
return this->gptr() == this->egptr()
? traits_type::eof()
: traits_type::to_int_type(*this->gptr());
}
};
With this stream buffer you should be able to create an std::istream and read the file into whatever structure you need:
zipbuf buf(???);
std::istream in(&buf);
...
Obviously, this code isn't tested or compiled. However, when you replace the ??? with whatever is needed to open the zip file, I'd think this should pretty much work.
Here is a routine I wrote that extracts data from a zip-stream and prints out a line at a time. This uses zlib, not libzip, but if this code is useful to you, feel free to use it:
#
# compile with -lz option in order to link in the zlib library
#
#include <zlib.h>
#define Z_CHUNK 2097152
int unzipFile(const char *fName)
{
z_stream zStream;
char *zRemainderBuf = malloc(1);
unsigned char zInBuf[Z_CHUNK];
unsigned char zOutBuf[Z_CHUNK];
char zLineBuf[Z_CHUNK];
unsigned int zHave, zBufIdx, zBufOffset, zOutBufIdx;
int zError;
FILE *inFp = fopen(fName, "rbR");
if (!inFp) { fprintf(stderr, "could not open file: %s\n", fName); return EXIT_FAILURE; }
zStream.zalloc = Z_NULL;
zStream.zfree = Z_NULL;
zStream.opaque = Z_NULL;
zStream.avail_in = 0;
zStream.next_in = Z_NULL;
zError = inflateInit2(&zStream, (15+32)); /* cf. http://www.zlib.net/manual.html */
if (zError != Z_OK) { fprintf(stderr, "could not initialize z-stream\n"); return EXIT_FAILURE; }
*zRemainderBuf = '\0';
do {
zStream.avail_in = fread(zInBuf, 1, Z_CHUNK, inFp);
if (zStream.avail_in == 0)
break;
zStream.next_in = zInBuf;
do {
zStream.avail_out = Z_CHUNK;
zStream.next_out = zOutBuf;
zError = inflate(&zStream, Z_NO_FLUSH);
switch (zError) {
case Z_NEED_DICT: { fprintf(stderr, "Z-stream needs dictionary!\n"); return EXIT_FAILURE; }
case Z_DATA_ERROR: { fprintf(stderr, "Z-stream suffered data error!\n"); return EXIT_FAILURE; }
case Z_MEM_ERROR: { fprintf(stderr, "Z-stream suffered memory error!\n"); return EXIT_FAILURE; }
}
zHave = Z_CHUNK - zStream.avail_out;
zOutBuf[zHave] = '\0';
/* copy remainder buffer onto line buffer, if not NULL */
if (zRemainderBuf) {
strncpy(zLineBuf, zRemainderBuf, strlen(zRemainderBuf));
zBufOffset = strlen(zRemainderBuf);
}
else
zBufOffset = 0;
/* read through zOutBuf for newlines */
for (zBufIdx = zBufOffset, zOutBufIdx = 0; zOutBufIdx < zHave; zBufIdx++, zOutBufIdx++) {
zLineBuf[zBufIdx] = zOutBuf[zOutBufIdx];
if (zLineBuf[zBufIdx] == '\n') {
zLineBuf[zBufIdx] = '\0';
zBufIdx = -1;
fprintf(stdout, "%s\n", zLineBuf);
}
}
/* copy some of line buffer onto the remainder buffer, if there are remnants from the z-stream */
if (strlen(zLineBuf) > 0) {
if (strlen(zLineBuf) > strlen(zRemainderBuf)) {
/* to minimize the chance of doing another (expensive) malloc, we double the length of zRemainderBuf */
free(zRemainderBuf);
zRemainderBuf = malloc(strlen(zLineBuf) * 2);
}
strncpy(zRemainderBuf, zLineBuf, zBufIdx);
zRemainderBuf[zBufIdx] = '\0';
}
} while (zStream.avail_out == 0);
} while (zError != Z_STREAM_END);
/* close gzip stream */
zError = inflateEnd(&zStream);
if (zError != Z_OK) {
fprintf(stderr, "could not close z-stream!\n");
return EXIT_FAILURE;
}
if (zRemainderBuf)
free(zRemainderBuf);
fclose(inFp);
return EXIT_SUCCESS;
}
With any streaming you should consider the memory requirements of your app.
A good buffer size is large, but you do not want to have too much memory in use depending on your RAM usage requirements. A small buffer size will require you call your read and write operations more times which are expensive in terms of time performance. So, you need to find a buffer in the middle of those two extremes.
Typically I use a size of 4096 (4KB) which is sufficiently large for many purposes. If you want, you can go larger. But at the worst case size of 1 byte, you will be waiting a long time for you read to complete.
So to answer your question, there is no "right" size to pick. It is a choice you should make so that the speed of your app and the memory it requires are what you need.
Simply what it says on the tin
I'm loading a bitmap from a file using Bitmap::FromFile but afterwards I want to delete it from the disk.
The problem is, Bitmap::FromFile absolutely locks the file from any changes/deletion until the loaded image is unloaded
This is because I'm storing the bitmaps in a binary file, so I want to do it in this order:
1. extract the image from binary file
2. load the image
3. delete the file extracted in #1
(just some basic protection for my image resources, I just don't want them sitting in my program directory)
Bitmap::FromFile still locks the file from deletion even when cloning the loaded image from the file like in my attempt:
Bitmap* tempbmp = Bitmap::FromFile(fileanddir.c_str(),false);
Rect temprect( 0, 0, tempbmp->GetWidth(), tempbmp->GetHeight() );
// make the image to be used as a clone to the temporary
// bitmap to avoid file locking
image_to_be_used = tempbmp->Clone(temprect, PixelFormatDontCare);
// delete temporary loaded bitmap since it shouldn't be needed
delete tempbmp;
// delete the file itself, too bad the file is locked
int theresult = remove(tocharptr(fileanddir));
// returns -1, also: manually deleting at this point gives the error
// that the file is being used by another person/program
Any idea how I can load a bitmap or somehow copy it to memory so the file itself wouldn't be locked ?
(So i can delete it a moment after loading it)
You can do it this way
Gdiplus::Bitmap* LoadImageFromFileWithoutLocking(const WCHAR* fileName) {
using namespace Gdiplus;
Bitmap src( fileName );
if ( src.GetLastStatus() != Ok ) {
return 0;
}
Bitmap *dst = new Bitmap(src.GetWidth(), src.GetHeight(), PixelFormat32bppARGB);
BitmapData srcData;
BitmapData dstData;
Rect rc(0, 0, src.GetWidth(), src.GetHeight());
if (src.LockBits(& rc, ImageLockModeRead, PixelFormat32bppARGB, & srcData) == Ok)
{
if ( dst->LockBits(& rc, ImageLockModeWrite, PixelFormat32bppARGB, & dstData) == Ok ) {
uint8_t * srcBits = (uint8_t *) srcData.Scan0;
uint8_t * dstBits = (uint8_t *) dstData.Scan0;
unsigned int stride;
if (srcData.Stride > 0) {
stride = srcData.Stride;
} else {
stride = - srcData.Stride;
}
memcpy(dstBits, srcBits, src.GetHeight() * stride);
dst->UnlockBits(&dstData);
}
src.UnlockBits(&srcData);
}
return dst;
}
Take a look at Bitmap::FromStream. You should be able to use SHCreateStreamOnFileEx to open an IStream on the file. After loading your bitmap you can safely delete the stream and then the temporary file.
If the binary file is only compressed with a supported algorithm, then pass the corresponding flag to SHCreateStreamOnFileEx and have it read the archive, bypassing the extraction of the image into a temp file. Otherwise can implement the IStream interface to read the binary file and extract your image data directly.
if you interested in MFC-OLE sample:
CFile file;
CFileException fe;
CString strFileName = "C:\\yours.bmp";
if (!file.Open(strFileName, CFile::modeRead | CFile::shareDenyNone , &fe))
{
return;
}
COleStreamFile stream;
if(!stream.CreateMemoryStream(NULL))
{
return;
}
BYTE buf[1024];
int readed = 0;
do
{
readed = file.Read(buf,1024);
stream.Write(buf,readed);
}
while(readed > 0);
file.Close();
stream.SeekToBegin();
USES_CONVERSION;
m_pImage = new Gdiplus::Bitmap(stream.GetStream( ));
How to write bitmaps as frames to Ogg Theora in C\C++?
Some Examples with source would be grate!)
The entire solution is a little lengthy to post on here as a code sample, but if you download libtheora from Xiph.org, there is an example png2theora. All of the library functions I am about to mention can be found in the documentation on Xiph.org for theora and ogg.
Call th_info_init() to initialise a th_info structure, then set up you output parameters by assigning the appropriate members in that.
Use that structure in a call to th_encode_alloc() to get an encoder context
Initialise an ogg stream, with ogg_stream_init()
Initialise a blank th_comment structure using th_comment_init
Iterate through the following:
Call th_encode_flushheader with the the encoder context, the blank comment structure and an ogg_packet.
Send the resulting packet to the ogg stream with ogg_stream_packetin()
Until th_encode_flushheader returns 0 (or an error code)
Now, repeatedly call ogg_stream_pageout(), every time writing the page.header and then page.body to an output file, until it returns 0. Now call ogg_stream_flush and write the resulting page to the file.
You can now write frames to the encoder. Here is how I did it:
int theora_write_frame(int outputFd, unsigned long w, unsigned long h, unsigned char *yuv_y, unsigned char *yuv_u, unsigned char *yuv_v, int last)
{
th_ycbcr_buffer ycbcr;
ogg_packet op;
ogg_page og;
unsigned long yuv_w;
unsigned long yuv_h;
/* Must hold: yuv_w >= w */
yuv_w = (w + 15) & ~15;
/* Must hold: yuv_h >= h */
yuv_h = (h + 15) & ~15;
//Fill out the ycbcr buffer
ycbcr[0].width = yuv_w;
ycbcr[0].height = yuv_h;
ycbcr[0].stride = yuv_w;
ycbcr[1].width = yuv_w;
ycbcr[1].stride = ycbcr[1].width;
ycbcr[1].height = yuv_h;
ycbcr[2].width = ycbcr[1].width;
ycbcr[2].stride = ycbcr[1].stride;
ycbcr[2].height = ycbcr[1].height;
if(encoderInfo->pixel_fmt == TH_PF_420)
{
//Chroma is decimated by 2 in both directions
ycbcr[1].width = yuv_w >> 1;
ycbcr[2].width = yuv_w >> 1;
ycbcr[1].height = yuv_h >> 1;
ycbcr[2].height = yuv_h >> 1;
}else if(encoderInfo->pixel_fmt == TH_PF_422)
{
ycbcr[1].width = yuv_w >> 1;
ycbcr[2].width = yuv_w >> 1;
}else if(encoderInfo->pixel_fmt != TH_PF_422)
{
//Then we have an unknown pixel format
//We don't know how long the arrays are!
fprintf(stderr, "[theora_write_frame] Unknown pixel format in writeFrame!\n");
return -1;
}
ycbcr[0].data = yuv_y;
ycbcr[1].data = yuv_u;
ycbcr[2].data = yuv_v;
/* Theora is a one-frame-in,one-frame-out system; submit a frame
for compression and pull out the packet */
if(th_encode_ycbcr_in(encoderContext, ycbcr)) {
fprintf(stderr, "[theora_write_frame] Error: could not encode frame\n");
return -1;
}
if(!th_encode_packetout(encoderContext, last, &op)) {
fprintf(stderr, "[theora_write_frame] Error: could not read packets\n");
return -1;
}
ogg_stream_packetin(&theoraStreamState, &op);
ssize_t bytesWritten = 0;
int pagesOut = 0;
while(ogg_stream_pageout(&theoraStreamState, &og)) {
pagesOut ++;
bytesWritten = write(outputFd, og.header, og.header_len);
if(bytesWritten != og.header_len)
{
fprintf(stderr, "[theora_write_frame] Error: Could not write to file\n");
return -1;
}
bytesWritten = write(outputFd, og.body, og.body_len);
if(bytesWritten != og.body_len)
{
bytesWritten = fprintf(stderr, "[theora_write_frame] Error: Could not write to file\n");
return -1;
}
}
return pagesOut;
}
Where encoderInfo is the th_info structure used to initialise the encoder (static in the data section for me).
On your last frame, setting the last frame on th_encode_packetout() will make sure the stream terminates properly.
Once your done, just make sure to clean up (closing fds mainly). th_info_clear() will clear the th_info structure, and th_encode_free() will free your encoder context.
Obviously, you'll need to convert your bitmap into YUV planes before you can pass them to theora_write_frame().
Hope this is of some help. Good luck!
Here's the libtheora API and example code.
Here's a micro howto that shows how to use the theora binaries. As the encoder reads raw, uncompressed 'yuv4mpeg' data for video you could use that from your app, too by piping the video frames to the encoder.