From 5a642a992f331ae136b79550059a64595a421599 Mon Sep 17 00:00:00 2001 From: xufuji456 Date: Tue, 12 Jul 2022 13:44:40 +0800 Subject: [PATCH] Feature: transcode media file --- app/CMakeLists.txt | 1 + app/src/main/cpp/media_transcode.cpp | 616 ++++++++++++++++++ .../java/com/frank/ffmpeg/VideoPlayer.java | 2 + 3 files changed, 619 insertions(+) create mode 100644 app/src/main/cpp/media_transcode.cpp diff --git a/app/CMakeLists.txt b/app/CMakeLists.txt index 9e879c1..7adc98e 100644 --- a/app/CMakeLists.txt +++ b/app/CMakeLists.txt @@ -43,6 +43,7 @@ add_library( # Sets the name of the library. src/main/cpp/metadata/metadata_util.c src/main/cpp/metadata/ffmpeg_media_retriever.c src/main/cpp/yuv/yuv_converter.cpp + src/main/cpp/media_transcode.cpp ) add_library( ffmpeg diff --git a/app/src/main/cpp/media_transcode.cpp b/app/src/main/cpp/media_transcode.cpp new file mode 100644 index 0000000..c1574b5 --- /dev/null +++ b/app/src/main/cpp/media_transcode.cpp @@ -0,0 +1,616 @@ +// +// Created by xu fulong on 2022/7/11. +// + +#include + +#ifdef __cplusplus +extern "C" { +#endif +#include +#include +#include +#include +#include +#include +#ifdef __cplusplus +} +#endif + +#include "ffmpeg_jni_define.h" + +#define ALOGE(Format, ...) LOGE("Transcde", Format, ##__VA_ARGS__) + +static AVFormatContext *ifmt_ctx; +static AVFormatContext *ofmt_ctx; +typedef struct FilteringContext { + AVFilterContext *buffersink_ctx; + AVFilterContext *buffersrc_ctx; + AVFilterGraph *filter_graph; +} FilteringContext; +static FilteringContext *filter_ctx; + +typedef struct StreamContext { + AVCodecContext *dec_ctx; + AVCodecContext *enc_ctx; +} StreamContext; +static StreamContext *stream_ctx; + +static int open_input_file(const char *filename) +{ + int ret; + unsigned int i; + ifmt_ctx = nullptr; + + if ((ret = avformat_open_input(&ifmt_ctx, filename, nullptr, nullptr)) < 0) { + ALOGE("Cannot open input file\n"); + return ret; + } + + if ((ret = avformat_find_stream_info(ifmt_ctx, nullptr)) < 0) { + ALOGE("Cannot find stream information\n"); + return ret; + } + + stream_ctx = static_cast(av_mallocz_array(ifmt_ctx->nb_streams, + sizeof(*stream_ctx))); + if (!stream_ctx) + return AVERROR(ENOMEM); + + for (i = 0; i < ifmt_ctx->nb_streams; i++) { + AVStream *stream = ifmt_ctx->streams[i]; + AVCodec *dec = avcodec_find_decoder(stream->codecpar->codec_id); + AVCodecContext *codec_ctx; + if (!dec) { + ALOGE("Failed to find decoder for stream #%u\n", i); + return AVERROR_DECODER_NOT_FOUND; + } + codec_ctx = avcodec_alloc_context3(dec); + if (!codec_ctx) { + ALOGE("Failed to allocate the decoder context for stream #%u\n", i); + return AVERROR(ENOMEM); + } + ret = avcodec_parameters_to_context(codec_ctx, stream->codecpar); + if (ret < 0) { + ALOGE("Failed to copy decoder parameters to input decoder context " + "for stream #%u\n", i); + return ret; + } + /* Reencode video & audio and remux subtitles etc. */ + if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO + || codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) { + if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) + codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, stream, nullptr); + /* Open decoder */ + ret = avcodec_open2(codec_ctx, dec, nullptr); + if (ret < 0) { + ALOGE("Failed to open decoder for stream #%u\n", i); + return ret; + } + } + stream_ctx[i].dec_ctx = codec_ctx; + } + + av_dump_format(ifmt_ctx, 0, filename, 0); + return 0; +} + +static int open_output_file(const char *filename) +{ + AVStream *out_stream; + AVStream *in_stream; + AVCodecContext *dec_ctx, *enc_ctx; + AVCodec *encoder; + int ret; + unsigned int i; + + ofmt_ctx = nullptr; + avformat_alloc_output_context2(&ofmt_ctx, nullptr, nullptr, filename); + if (!ofmt_ctx) { + ALOGE("Could not create output context\n"); + return AVERROR_UNKNOWN; + } + + for (i = 0; i < ifmt_ctx->nb_streams; i++) { + out_stream = avformat_new_stream(ofmt_ctx, nullptr); + if (!out_stream) { + ALOGE("Failed allocating output stream\n"); + return AVERROR_UNKNOWN; + } + + in_stream = ifmt_ctx->streams[i]; + dec_ctx = stream_ctx[i].dec_ctx; + + if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO + || dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) { + /* in this example, we choose transcoding to same codec */ + encoder = avcodec_find_encoder(dec_ctx->codec_id); + if (!encoder) { + ALOGE("Necessary encoder not found\n"); + return AVERROR_INVALIDDATA; + } + enc_ctx = avcodec_alloc_context3(encoder); + if (!enc_ctx) { + ALOGE("Failed to allocate the encoder context\n"); + return AVERROR(ENOMEM); + } + + /* In this example, we transcode to same properties (picture size, + * sample rate etc.). These properties can be changed for output + * streams easily using filters */ + if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) { + enc_ctx->height = dec_ctx->height; + enc_ctx->width = dec_ctx->width; + enc_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio; + /* take first format from list of supported formats */ + if (encoder->pix_fmts) + enc_ctx->pix_fmt = encoder->pix_fmts[0]; + else + enc_ctx->pix_fmt = dec_ctx->pix_fmt; + /* video time_base can be set to whatever is handy and supported by encoder */ + enc_ctx->time_base = av_inv_q(dec_ctx->framerate); + } else { + enc_ctx->sample_rate = dec_ctx->sample_rate; + enc_ctx->channel_layout = dec_ctx->channel_layout; + enc_ctx->channels = av_get_channel_layout_nb_channels(enc_ctx->channel_layout); + /* take first format from list of supported formats */ + enc_ctx->sample_fmt = encoder->sample_fmts[0]; + enc_ctx->time_base = (AVRational){1, enc_ctx->sample_rate}; + } + + if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER) + enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER; + + /* Third parameter can be used to pass settings to encoder */ + ret = avcodec_open2(enc_ctx, encoder, nullptr); + if (ret < 0) { + ALOGE("Cannot open video encoder for stream #%u\n", i); + return ret; + } + ret = avcodec_parameters_from_context(out_stream->codecpar, enc_ctx); + if (ret < 0) { + ALOGE("Failed to copy encoder parameters to output stream #%u\n", i); + return ret; + } + + out_stream->time_base = enc_ctx->time_base; + stream_ctx[i].enc_ctx = enc_ctx; + } else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) { + ALOGE("Elementary stream #%d is of unknown type, cannot proceed\n", i); + return AVERROR_INVALIDDATA; + } else { + /* if this stream must be remuxed */ + ret = avcodec_parameters_copy(out_stream->codecpar, in_stream->codecpar); + if (ret < 0) { + ALOGE("Copying parameters for stream #%u failed\n", i); + return ret; + } + out_stream->time_base = in_stream->time_base; + } + + } + av_dump_format(ofmt_ctx, 0, filename, 1); + + if (!(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) { + ret = avio_open(&ofmt_ctx->pb, filename, AVIO_FLAG_WRITE); + if (ret < 0) { + ALOGE("Could not open output file '%s'", filename); + return ret; + } + } + + /* init muxer, write output file header */ + ret = avformat_write_header(ofmt_ctx, nullptr); + if (ret < 0) { + ALOGE("Error occurred when opening output file\n"); + return ret; + } + + return 0; +} + +static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx, + AVCodecContext *enc_ctx, const char *filter_spec) +{ + char args[512]; + int ret; + const AVFilter *buffersrc; + const AVFilter *buffersink; + AVFilterContext *buffersrc_ctx = nullptr; + AVFilterContext *buffersink_ctx = nullptr; + AVFilterInOut *outputs = avfilter_inout_alloc(); + AVFilterInOut *inputs = avfilter_inout_alloc(); + AVFilterGraph *filter_graph = avfilter_graph_alloc(); + + if (!outputs || !inputs || !filter_graph) { + ret = AVERROR(ENOMEM); + goto end; + } + + if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) { + buffersrc = avfilter_get_by_name("buffer"); + buffersink = avfilter_get_by_name("buffersink"); + if (!buffersrc || !buffersink) { + ALOGE("filtering source or sink element not found\n"); + ret = AVERROR_UNKNOWN; + goto end; + } + + snprintf(args, sizeof(args), + "video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d", + dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt, + dec_ctx->time_base.num, dec_ctx->time_base.den, + dec_ctx->sample_aspect_ratio.num, + dec_ctx->sample_aspect_ratio.den); + + ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in", + args, nullptr, filter_graph); + if (ret < 0) { + ALOGE("Cannot create buffer source\n"); + goto end; + } + + ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out", + nullptr, nullptr, filter_graph); + if (ret < 0) { + ALOGE("Cannot create buffer sink\n"); + goto end; + } + + ret = av_opt_set_bin(buffersink_ctx, "pix_fmts", + (uint8_t*)&enc_ctx->pix_fmt, sizeof(enc_ctx->pix_fmt), + AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + ALOGE( "Cannot set output pixel format\n"); + goto end; + } + } else if (dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) { + buffersrc = avfilter_get_by_name("abuffer"); + buffersink = avfilter_get_by_name("abuffersink"); + if (!buffersrc || !buffersink) { + ALOGE( "filtering source or sink element not found\n"); + ret = AVERROR_UNKNOWN; + goto end; + } + + if (!dec_ctx->channel_layout) + dec_ctx->channel_layout = + av_get_default_channel_layout(dec_ctx->channels); + snprintf(args, sizeof(args), + "time_base=%d/%d:sample_rate=%d:sample_fmt=%s:channel_layout=0x%" PRIx64, + dec_ctx->time_base.num, dec_ctx->time_base.den, dec_ctx->sample_rate, + av_get_sample_fmt_name(dec_ctx->sample_fmt), + dec_ctx->channel_layout); + ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in", + args, nullptr, filter_graph); + if (ret < 0) { + ALOGE("Cannot create audio buffer source\n"); + goto end; + } + + ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out", + nullptr, nullptr, filter_graph); + if (ret < 0) { + ALOGE("Cannot create audio buffer sink\n"); + goto end; + } + + ret = av_opt_set_bin(buffersink_ctx, "sample_fmts", + (uint8_t*)&enc_ctx->sample_fmt, sizeof(enc_ctx->sample_fmt), + AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + ALOGE("Cannot set output sample format\n"); + goto end; + } + + ret = av_opt_set_bin(buffersink_ctx, "channel_layouts", + (uint8_t*)&enc_ctx->channel_layout, + sizeof(enc_ctx->channel_layout), AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + ALOGE("Cannot set output channel layout\n"); + goto end; + } + + ret = av_opt_set_bin(buffersink_ctx, "sample_rates", + (uint8_t*)&enc_ctx->sample_rate, sizeof(enc_ctx->sample_rate), + AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + ALOGE("Cannot set output sample rate\n"); + goto end; + } + } else { + ret = AVERROR_UNKNOWN; + goto end; + } + + /* Endpoints for the filter graph. */ + outputs->name = av_strdup("in"); + outputs->filter_ctx = buffersrc_ctx; + outputs->pad_idx = 0; + outputs->next = nullptr; + + inputs->name = av_strdup("out"); + inputs->filter_ctx = buffersink_ctx; + inputs->pad_idx = 0; + inputs->next = nullptr; + + if (!outputs->name || !inputs->name) { + ret = AVERROR(ENOMEM); + goto end; + } + + if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec, + &inputs, &outputs, nullptr)) < 0) + goto end; + + if ((ret = avfilter_graph_config(filter_graph, nullptr)) < 0) + goto end; + + /* Fill FilteringContext */ + fctx->filter_graph = filter_graph; + fctx->buffersrc_ctx = buffersrc_ctx; + fctx->buffersink_ctx = buffersink_ctx; + +end: + avfilter_inout_free(&inputs); + avfilter_inout_free(&outputs); + + return ret; +} + +static int init_filters() +{ + const char *filter_spec; + unsigned int i; + int ret; + filter_ctx = static_cast(av_malloc_array(ifmt_ctx->nb_streams, + sizeof(*filter_ctx))); + if (!filter_ctx) + return AVERROR(ENOMEM); + + for (i = 0; i < ifmt_ctx->nb_streams; i++) { + filter_ctx[i].buffersrc_ctx = nullptr; + filter_ctx[i].buffersink_ctx = nullptr; + filter_ctx[i].filter_graph = nullptr; + if (!(ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO + || ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO)) + continue; + + + if (ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO) + filter_spec = "null"; + else + filter_spec = "anull"; + ret = init_filter(&filter_ctx[i], stream_ctx[i].dec_ctx, + stream_ctx[i].enc_ctx, filter_spec); + if (ret) + return ret; + } + return 0; +} + +static int encode_write_frame(AVFrame *filt_frame, unsigned int stream_index, int *got_frame) { + int ret; + int got_frame_local; + AVPacket enc_pkt; + int (*enc_func)(AVCodecContext *, AVPacket *, const AVFrame *, int *) = + (ifmt_ctx->streams[stream_index]->codecpar->codec_type == + AVMEDIA_TYPE_VIDEO) ? avcodec_encode_video2 : avcodec_encode_audio2; + + if (!got_frame) + got_frame = &got_frame_local; + + ALOGE("Encoding frame\n"); + /* encode filtered frame */ + enc_pkt.data = nullptr; + enc_pkt.size = 0; + av_init_packet(&enc_pkt); + ret = enc_func(stream_ctx[stream_index].enc_ctx, &enc_pkt, + filt_frame, got_frame); + av_frame_free(&filt_frame); + if (ret < 0) + return ret; + if (!(*got_frame)) + return 0; + + /* prepare packet for muxing */ + enc_pkt.stream_index = stream_index; + av_packet_rescale_ts(&enc_pkt, + stream_ctx[stream_index].enc_ctx->time_base, + ofmt_ctx->streams[stream_index]->time_base); + + ALOGE("Muxing frame\n"); + /* mux encoded frame */ + ret = av_interleaved_write_frame(ofmt_ctx, &enc_pkt); + return ret; +} + +static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index) +{ + int ret; + AVFrame *filt_frame; + + ALOGE("Pushing decoded frame to filters\n"); + /* push the decoded frame into the filtergraph */ + ret = av_buffersrc_add_frame_flags(filter_ctx[stream_index].buffersrc_ctx, + frame, 0); + if (ret < 0) { + ALOGE("Error while feeding the filtergraph\n"); + return ret; + } + + /* pull filtered frames from the filtergraph */ + while (1) { + filt_frame = av_frame_alloc(); + if (!filt_frame) { + ret = AVERROR(ENOMEM); + break; + } + ALOGE("Pulling filtered frame from filters\n"); + ret = av_buffersink_get_frame(filter_ctx[stream_index].buffersink_ctx, + filt_frame); + if (ret < 0) { + /* if no more frames for output - returns AVERROR(EAGAIN) + * if flushed and no more frames for output - returns AVERROR_EOF + * rewrite retcode to 0 to show it as normal procedure completion + */ + if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) + ret = 0; + av_frame_free(&filt_frame); + break; + } + + filt_frame->pict_type = AV_PICTURE_TYPE_NONE; + ret = encode_write_frame(filt_frame, stream_index, nullptr); + if (ret < 0) + break; + } + + return ret; +} + +static int flush_encoder(unsigned int stream_index) +{ + int ret; + int got_frame; + + if (!(stream_ctx[stream_index].enc_ctx->codec->capabilities & + AV_CODEC_CAP_DELAY)) + return 0; + + while (1) { + ALOGE("Flushing stream #%u encoder\n", stream_index); + ret = encode_write_frame(nullptr, stream_index, &got_frame); + if (ret < 0) + break; + if (!got_frame) + return 0; + } + return ret; +} + +int transcode(const char *input_file, const char *output_file) +{ + int ret; + AVPacket packet = { .data = nullptr, .size = 0 }; + AVFrame *frame = nullptr; + enum AVMediaType type; + unsigned int stream_index; + unsigned int i; + int got_frame; + int (*dec_func)(AVCodecContext *, AVFrame *, int *, const AVPacket *); + + if ((ret = open_input_file(input_file)) < 0) + goto end; + if ((ret = open_output_file(output_file)) < 0) + goto end; + if ((ret = init_filters()) < 0) + goto end; + + /* read all packets */ + while (1) { + if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0) + break; + stream_index = packet.stream_index; + type = ifmt_ctx->streams[packet.stream_index]->codecpar->codec_type; + ALOGE("Demuxer gave frame of stream_index %u\n", + stream_index); + + if (filter_ctx[stream_index].filter_graph) { + ALOGE("Going to re-encode&filter the frame\n"); + frame = av_frame_alloc(); + if (!frame) { + ret = AVERROR(ENOMEM); + break; + } + av_packet_rescale_ts(&packet, + ifmt_ctx->streams[stream_index]->time_base, + stream_ctx[stream_index].dec_ctx->time_base); + dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 : avcodec_decode_audio4; + ret = dec_func(stream_ctx[stream_index].dec_ctx, frame, + &got_frame, &packet); + if (ret < 0) { + av_frame_free(&frame); + ALOGE("Decoding failed\n"); + break; + } + + if (got_frame) { + frame->pts = frame->best_effort_timestamp; + ret = filter_encode_write_frame(frame, stream_index); + av_frame_free(&frame); + if (ret < 0) + goto end; + } else { + av_frame_free(&frame); + } + } else { + /* remux this frame without re-encoding */ + av_packet_rescale_ts(&packet, + ifmt_ctx->streams[stream_index]->time_base, + ofmt_ctx->streams[stream_index]->time_base); + + ret = av_interleaved_write_frame(ofmt_ctx, &packet); + if (ret < 0) + goto end; + } + av_packet_unref(&packet); + } + + /* flush filters and encoders */ + for (i = 0; i < ifmt_ctx->nb_streams; i++) { + /* flush filter */ + if (!filter_ctx[i].filter_graph) + continue; + ret = filter_encode_write_frame(nullptr, i); + if (ret < 0) { + ALOGE("Flushing filter failed\n"); + goto end; + } + + /* flush encoder */ + ret = flush_encoder(i); + if (ret < 0) { + ALOGE("Flushing encoder failed\n"); + goto end; + } + } + + av_write_trailer(ofmt_ctx); +end: + av_packet_unref(&packet); + av_frame_free(&frame); + for (i = 0; i < ifmt_ctx->nb_streams; i++) { + avcodec_free_context(&stream_ctx[i].dec_ctx); + if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && stream_ctx[i].enc_ctx) + avcodec_free_context(&stream_ctx[i].enc_ctx); + if (filter_ctx && filter_ctx[i].filter_graph) + avfilter_graph_free(&filter_ctx[i].filter_graph); + } + av_free(filter_ctx); + av_free(stream_ctx); + avformat_close_input(&ifmt_ctx); + if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) + avio_closep(&ofmt_ctx->pb); + avformat_free_context(ofmt_ctx); + + if (ret < 0) + ALOGE("Error occurred: %s\n", av_err2str(ret)); + + return ret ? 1 : 0; +} + +#ifdef __cplusplus +extern "C" { +#endif +VIDEO_PLAYER_FUNC(int, executeTranscode, jstring inputFile, jstring outputFile) { + const char *input_file = env->GetStringUTFChars(inputFile, JNI_FALSE); + const char *output_file = env->GetStringUTFChars(outputFile, JNI_FALSE); + int ret = transcode(input_file, output_file); + env->ReleaseStringUTFChars(inputFile, input_file); + env->ReleaseStringUTFChars(outputFile, output_file); + return ret; +} +#ifdef __cplusplus +} +#endif diff --git a/app/src/main/java/com/frank/ffmpeg/VideoPlayer.java b/app/src/main/java/com/frank/ffmpeg/VideoPlayer.java index 68c1f1f..b7a8fbd 100644 --- a/app/src/main/java/com/frank/ffmpeg/VideoPlayer.java +++ b/app/src/main/java/com/frank/ffmpeg/VideoPlayer.java @@ -26,6 +26,8 @@ public class VideoPlayer { public native void playAudio(boolean play); + public native int executeTranscode(String inputFile, String outputFile); + /** * Create an AudioTrack instance for JNI calling *