diff options
Diffstat (limited to 'doc/examples')
-rw-r--r-- | doc/examples/Makefile | 46 | ||||
-rw-r--r-- | doc/examples/README | 23 | ||||
-rw-r--r-- | doc/examples/avio_dir_cmd.c | 180 | ||||
-rw-r--r-- | doc/examples/avio_reading.c | 134 | ||||
-rw-r--r-- | doc/examples/decoding_encoding.c (renamed from doc/examples/avcodec.c) | 350 | ||||
-rw-r--r-- | doc/examples/demuxing_decoding.c | 383 | ||||
-rw-r--r-- | doc/examples/extract_mvs.c | 185 | ||||
-rw-r--r-- | doc/examples/filter_audio.c | 8 | ||||
-rw-r--r-- | doc/examples/filtering_audio.c | 295 | ||||
-rw-r--r-- | doc/examples/filtering_video.c | 280 | ||||
-rw-r--r-- | doc/examples/http_multiclient.c | 155 | ||||
-rw-r--r-- | doc/examples/metadata.c | 4 | ||||
-rw-r--r-- | doc/examples/muxing.c (renamed from doc/examples/output.c) | 466 | ||||
-rw-r--r-- | doc/examples/remuxing.c | 165 | ||||
-rw-r--r-- | doc/examples/resampling_audio.c | 214 | ||||
-rw-r--r-- | doc/examples/scaling_video.c | 140 | ||||
-rw-r--r-- | doc/examples/transcode_aac.c | 103 | ||||
-rw-r--r-- | doc/examples/transcoding.c | 582 |
18 files changed, 3274 insertions, 439 deletions
diff --git a/doc/examples/Makefile b/doc/examples/Makefile new file mode 100644 index 0000000000..af3815995a --- /dev/null +++ b/doc/examples/Makefile @@ -0,0 +1,46 @@ +# use pkg-config for getting CFLAGS and LDLIBS +FFMPEG_LIBS= libavdevice \ + libavformat \ + libavfilter \ + libavcodec \ + libswresample \ + libswscale \ + libavutil \ + +CFLAGS += -Wall -g +CFLAGS := $(shell pkg-config --cflags $(FFMPEG_LIBS)) $(CFLAGS) +LDLIBS := $(shell pkg-config --libs $(FFMPEG_LIBS)) $(LDLIBS) + +EXAMPLES= avio_dir_cmd \ + avio_reading \ + decoding_encoding \ + demuxing_decoding \ + extract_mvs \ + filtering_video \ + filtering_audio \ + http_multiclient \ + metadata \ + muxing \ + remuxing \ + resampling_audio \ + scaling_video \ + transcode_aac \ + transcoding \ + +OBJS=$(addsuffix .o,$(EXAMPLES)) + +# the following examples make explicit use of the math library +avcodec: LDLIBS += -lm +decoding_encoding: LDLIBS += -lm +muxing: LDLIBS += -lm +resampling_audio: LDLIBS += -lm + +.phony: all clean-test clean + +all: $(OBJS) $(EXAMPLES) + +clean-test: + $(RM) test*.pgm test.h264 test.mp2 test.sw test.mpg + +clean: clean-test + $(RM) $(EXAMPLES) $(OBJS) diff --git a/doc/examples/README b/doc/examples/README new file mode 100644 index 0000000000..c1ce619d35 --- /dev/null +++ b/doc/examples/README @@ -0,0 +1,23 @@ +FFmpeg examples README +---------------------- + +Both following use cases rely on pkg-config and make, thus make sure +that you have them installed and working on your system. + + +Method 1: build the installed examples in a generic read/write user directory + +Copy to a read/write user directory and just use "make", it will link +to the libraries on your system, assuming the PKG_CONFIG_PATH is +correctly configured. + +Method 2: build the examples in-tree + +Assuming you are in the source FFmpeg checkout directory, you need to build +FFmpeg (no need to make install in any prefix). Then just run "make examples". +This will build the examples using the FFmpeg build system. You can clean those +examples using "make examplesclean" + +If you want to try the dedicated Makefile examples (to emulate the first +method), go into doc/examples and run a command such as +PKG_CONFIG_PATH=pc-uninstalled make. diff --git a/doc/examples/avio_dir_cmd.c b/doc/examples/avio_dir_cmd.c new file mode 100644 index 0000000000..50c435cf8f --- /dev/null +++ b/doc/examples/avio_dir_cmd.c @@ -0,0 +1,180 @@ +/* + * Copyright (c) 2014 Lukasz Marek + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include <libavcodec/avcodec.h> +#include <libavformat/avformat.h> +#include <libavformat/avio.h> + +static const char *type_string(int type) +{ + switch (type) { + case AVIO_ENTRY_DIRECTORY: + return "<DIR>"; + case AVIO_ENTRY_FILE: + return "<FILE>"; + case AVIO_ENTRY_BLOCK_DEVICE: + return "<BLOCK DEVICE>"; + case AVIO_ENTRY_CHARACTER_DEVICE: + return "<CHARACTER DEVICE>"; + case AVIO_ENTRY_NAMED_PIPE: + return "<PIPE>"; + case AVIO_ENTRY_SYMBOLIC_LINK: + return "<LINK>"; + case AVIO_ENTRY_SOCKET: + return "<SOCKET>"; + case AVIO_ENTRY_SERVER: + return "<SERVER>"; + case AVIO_ENTRY_SHARE: + return "<SHARE>"; + case AVIO_ENTRY_WORKGROUP: + return "<WORKGROUP>"; + case AVIO_ENTRY_UNKNOWN: + default: + break; + } + return "<UNKNOWN>"; +} + +static int list_op(const char *input_dir) +{ + AVIODirEntry *entry = NULL; + AVIODirContext *ctx = NULL; + int cnt, ret; + char filemode[4], uid_and_gid[20]; + + if ((ret = avio_open_dir(&ctx, input_dir, NULL)) < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot open directory: %s.\n", av_err2str(ret)); + goto fail; + } + + cnt = 0; + for (;;) { + if ((ret = avio_read_dir(ctx, &entry)) < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot list directory: %s.\n", av_err2str(ret)); + goto fail; + } + if (!entry) + break; + if (entry->filemode == -1) { + snprintf(filemode, 4, "???"); + } else { + snprintf(filemode, 4, "%3"PRIo64, entry->filemode); + } + snprintf(uid_and_gid, 20, "%"PRId64"(%"PRId64")", entry->user_id, entry->group_id); + if (cnt == 0) + av_log(NULL, AV_LOG_INFO, "%-9s %12s %30s %10s %s %16s %16s %16s\n", + "TYPE", "SIZE", "NAME", "UID(GID)", "UGO", "MODIFIED", + "ACCESSED", "STATUS_CHANGED"); + av_log(NULL, AV_LOG_INFO, "%-9s %12"PRId64" %30s %10s %s %16"PRId64" %16"PRId64" %16"PRId64"\n", + type_string(entry->type), + entry->size, + entry->name, + uid_and_gid, + filemode, + entry->modification_timestamp, + entry->access_timestamp, + entry->status_change_timestamp); + avio_free_directory_entry(&entry); + cnt++; + }; + + fail: + avio_close_dir(&ctx); + return ret; +} + +static int del_op(const char *url) +{ + int ret = avpriv_io_delete(url); + if (ret < 0) + av_log(NULL, AV_LOG_ERROR, "Cannot delete '%s': %s.\n", url, av_err2str(ret)); + return ret; +} + +static int move_op(const char *src, const char *dst) +{ + int ret = avpriv_io_move(src, dst); + if (ret < 0) + av_log(NULL, AV_LOG_ERROR, "Cannot move '%s' into '%s': %s.\n", src, dst, av_err2str(ret)); + return ret; +} + + +static void usage(const char *program_name) +{ + fprintf(stderr, "usage: %s OPERATION entry1 [entry2]\n" + "API example program to show how to manipulate resources " + "accessed through AVIOContext.\n" + "OPERATIONS:\n" + "list list content of the directory\n" + "move rename content in directory\n" + "del delete content in directory\n", + program_name); +} + +int main(int argc, char *argv[]) +{ + const char *op = NULL; + int ret; + + av_log_set_level(AV_LOG_DEBUG); + + if (argc < 2) { + usage(argv[0]); + return 1; + } + + /* register codecs and formats and other lavf/lavc components*/ + av_register_all(); + avformat_network_init(); + + op = argv[1]; + if (strcmp(op, "list") == 0) { + if (argc < 3) { + av_log(NULL, AV_LOG_INFO, "Missing argument for list operation.\n"); + ret = AVERROR(EINVAL); + } else { + ret = list_op(argv[2]); + } + } else if (strcmp(op, "del") == 0) { + if (argc < 3) { + av_log(NULL, AV_LOG_INFO, "Missing argument for del operation.\n"); + ret = AVERROR(EINVAL); + } else { + ret = del_op(argv[2]); + } + } else if (strcmp(op, "move") == 0) { + if (argc < 4) { + av_log(NULL, AV_LOG_INFO, "Missing argument for move operation.\n"); + ret = AVERROR(EINVAL); + } else { + ret = move_op(argv[2], argv[3]); + } + } else { + av_log(NULL, AV_LOG_INFO, "Invalid operation %s\n", op); + ret = AVERROR(EINVAL); + } + + avformat_network_deinit(); + + return ret < 0 ? 1 : 0; +} diff --git a/doc/examples/avio_reading.c b/doc/examples/avio_reading.c new file mode 100644 index 0000000000..02474e907a --- /dev/null +++ b/doc/examples/avio_reading.c @@ -0,0 +1,134 @@ +/* + * Copyright (c) 2014 Stefano Sabatini + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +/** + * @file + * libavformat AVIOContext API example. + * + * Make libavformat demuxer access media content through a custom + * AVIOContext read callback. + * @example avio_reading.c + */ + +#include <libavcodec/avcodec.h> +#include <libavformat/avformat.h> +#include <libavformat/avio.h> +#include <libavutil/file.h> + +struct buffer_data { + uint8_t *ptr; + size_t size; ///< size left in the buffer +}; + +static int read_packet(void *opaque, uint8_t *buf, int buf_size) +{ + struct buffer_data *bd = (struct buffer_data *)opaque; + buf_size = FFMIN(buf_size, bd->size); + + printf("ptr:%p size:%zu\n", bd->ptr, bd->size); + + /* copy internal buffer data to buf */ + memcpy(buf, bd->ptr, buf_size); + bd->ptr += buf_size; + bd->size -= buf_size; + + return buf_size; +} + +int main(int argc, char *argv[]) +{ + AVFormatContext *fmt_ctx = NULL; + AVIOContext *avio_ctx = NULL; + uint8_t *buffer = NULL, *avio_ctx_buffer = NULL; + size_t buffer_size, avio_ctx_buffer_size = 4096; + char *input_filename = NULL; + int ret = 0; + struct buffer_data bd = { 0 }; + + if (argc != 2) { + fprintf(stderr, "usage: %s input_file\n" + "API example program to show how to read from a custom buffer " + "accessed through AVIOContext.\n", argv[0]); + return 1; + } + input_filename = argv[1]; + + /* register codecs and formats and other lavf/lavc components*/ + av_register_all(); + + /* slurp file content into buffer */ + ret = av_file_map(input_filename, &buffer, &buffer_size, 0, NULL); + if (ret < 0) + goto end; + + /* fill opaque structure used by the AVIOContext read callback */ + bd.ptr = buffer; + bd.size = buffer_size; + + if (!(fmt_ctx = avformat_alloc_context())) { + ret = AVERROR(ENOMEM); + goto end; + } + + avio_ctx_buffer = av_malloc(avio_ctx_buffer_size); + if (!avio_ctx_buffer) { + ret = AVERROR(ENOMEM); + goto end; + } + avio_ctx = avio_alloc_context(avio_ctx_buffer, avio_ctx_buffer_size, + 0, &bd, &read_packet, NULL, NULL); + if (!avio_ctx) { + ret = AVERROR(ENOMEM); + goto end; + } + fmt_ctx->pb = avio_ctx; + + ret = avformat_open_input(&fmt_ctx, NULL, NULL, NULL); + if (ret < 0) { + fprintf(stderr, "Could not open input\n"); + goto end; + } + + ret = avformat_find_stream_info(fmt_ctx, NULL); + if (ret < 0) { + fprintf(stderr, "Could not find stream information\n"); + goto end; + } + + av_dump_format(fmt_ctx, 0, input_filename, 0); + +end: + avformat_close_input(&fmt_ctx); + /* note: the internal buffer could have changed, and be != avio_ctx_buffer */ + if (avio_ctx) { + av_freep(&avio_ctx->buffer); + av_freep(&avio_ctx); + } + av_file_unmap(buffer, buffer_size); + + if (ret < 0) { + fprintf(stderr, "Error occurred: %s\n", av_err2str(ret)); + return 1; + } + + return 0; +} diff --git a/doc/examples/avcodec.c b/doc/examples/decoding_encoding.c index df0af4b1ea..06a98a630e 100644 --- a/doc/examples/avcodec.c +++ b/doc/examples/decoding_encoding.c @@ -1,47 +1,44 @@ /* - * copyright (c) 2001 Fabrice Bellard + * Copyright (c) 2001 Fabrice Bellard * - * This file is part of Libav. + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: * - * Libav is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. * - * Libav is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with Libav; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. */ /** * @file * libavcodec API use example. * - * @example avcodec.c - * Note that this library only handles codecs (mpeg, mpeg4, etc...), - * not file formats (avi, vob, etc...). See library 'libavformat' for the + * @example decoding_encoding.c + * Note that libavcodec only handles codecs (mpeg, mpeg4, etc...), + * not file formats (avi, vob, mp4, mov, mkv, mxf, flv, mpegts, mpegps, etc...). See library 'libavformat' for the * format handling */ -#include <stdlib.h> -#include <stdio.h> -#include <string.h> - -#ifdef HAVE_AV_CONFIG_H -#undef HAVE_AV_CONFIG_H -#endif +#include <math.h> -#include "libavcodec/avcodec.h" -#include "libavutil/channel_layout.h" -#include "libavutil/common.h" -#include "libavutil/imgutils.h" -#include "libavutil/mathematics.h" -#include "libavutil/samplefmt.h" +#include <libavutil/opt.h> +#include <libavcodec/avcodec.h> +#include <libavutil/channel_layout.h> +#include <libavutil/common.h> +#include <libavutil/imgutils.h> +#include <libavutil/mathematics.h> +#include <libavutil/samplefmt.h> #define INBUF_SIZE 4096 #define AUDIO_INBUF_SIZE 20480 @@ -115,16 +112,20 @@ static void audio_encode_example(const char *filename) uint16_t *samples; float t, tincr; - printf("Audio encoding\n"); + printf("Encode audio file %s\n", filename); /* find the MP2 encoder */ codec = avcodec_find_encoder(AV_CODEC_ID_MP2); if (!codec) { - fprintf(stderr, "codec not found\n"); + fprintf(stderr, "Codec not found\n"); exit(1); } c = avcodec_alloc_context3(codec); + if (!c) { + fprintf(stderr, "Could not allocate audio codec context\n"); + exit(1); + } /* put sample parameters */ c->bit_rate = 64000; @@ -132,7 +133,7 @@ static void audio_encode_example(const char *filename) /* check that the encoder supports s16 pcm input */ c->sample_fmt = AV_SAMPLE_FMT_S16; if (!check_sample_fmt(codec, c->sample_fmt)) { - fprintf(stderr, "encoder does not support %s", + fprintf(stderr, "Encoder does not support sample format %s", av_get_sample_fmt_name(c->sample_fmt)); exit(1); } @@ -144,20 +145,20 @@ static void audio_encode_example(const char *filename) /* open it */ if (avcodec_open2(c, codec, NULL) < 0) { - fprintf(stderr, "could not open codec\n"); + fprintf(stderr, "Could not open codec\n"); exit(1); } f = fopen(filename, "wb"); if (!f) { - fprintf(stderr, "could not open %s\n", filename); + fprintf(stderr, "Could not open %s\n", filename); exit(1); } /* frame containing input raw audio */ frame = av_frame_alloc(); if (!frame) { - fprintf(stderr, "could not allocate audio frame\n"); + fprintf(stderr, "Could not allocate audio frame\n"); exit(1); } @@ -169,9 +170,13 @@ static void audio_encode_example(const char *filename) * we calculate the size of the samples buffer in bytes */ buffer_size = av_samples_get_buffer_size(NULL, c->channels, c->frame_size, c->sample_fmt, 0); + if (buffer_size < 0) { + fprintf(stderr, "Could not get sample buffer size\n"); + exit(1); + } samples = av_malloc(buffer_size); if (!samples) { - fprintf(stderr, "could not allocate %d bytes for samples buffer\n", + fprintf(stderr, "Could not allocate %d bytes for samples buffer\n", buffer_size); exit(1); } @@ -179,14 +184,14 @@ static void audio_encode_example(const char *filename) ret = avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt, (const uint8_t*)samples, buffer_size, 0); if (ret < 0) { - fprintf(stderr, "could not setup audio frame\n"); + fprintf(stderr, "Could not setup audio frame\n"); exit(1); } /* encode a single tone sound */ t = 0; tincr = 2 * M_PI * 440.0 / c->sample_rate; - for(i=0;i<200;i++) { + for (i = 0; i < 200; i++) { av_init_packet(&pkt); pkt.data = NULL; // packet data will be allocated by the encoder pkt.size = 0; @@ -201,9 +206,23 @@ static void audio_encode_example(const char *filename) /* encode the samples */ ret = avcodec_encode_audio2(c, &pkt, frame, &got_output); if (ret < 0) { - fprintf(stderr, "error encoding audio frame\n"); + fprintf(stderr, "Error encoding audio frame\n"); + exit(1); + } + if (got_output) { + fwrite(pkt.data, 1, pkt.size, f); + av_packet_unref(&pkt); + } + } + + /* get the delayed frames */ + for (got_output = 1; got_output; i++) { + ret = avcodec_encode_audio2(c, &pkt, NULL, &got_output); + if (ret < 0) { + fprintf(stderr, "Error encoding frame\n"); exit(1); } + if (got_output) { fwrite(pkt.data, 1, pkt.size, f); av_packet_unref(&pkt); @@ -232,26 +251,30 @@ static void audio_decode_example(const char *outfilename, const char *filename) av_init_packet(&avpkt); - printf("Audio decoding\n"); + printf("Decode audio file %s to %s\n", filename, outfilename); /* find the mpeg audio decoder */ codec = avcodec_find_decoder(AV_CODEC_ID_MP2); if (!codec) { - fprintf(stderr, "codec not found\n"); + fprintf(stderr, "Codec not found\n"); exit(1); } c = avcodec_alloc_context3(codec); + if (!c) { + fprintf(stderr, "Could not allocate audio codec context\n"); + exit(1); + } /* open it */ if (avcodec_open2(c, codec, NULL) < 0) { - fprintf(stderr, "could not open codec\n"); + fprintf(stderr, "Could not open codec\n"); exit(1); } f = fopen(filename, "rb"); if (!f) { - fprintf(stderr, "could not open %s\n", filename); + fprintf(stderr, "Could not open %s\n", filename); exit(1); } outfile = fopen(outfilename, "wb"); @@ -265,11 +288,12 @@ static void audio_decode_example(const char *outfilename, const char *filename) avpkt.size = fread(inbuf, 1, AUDIO_INBUF_SIZE, f); while (avpkt.size > 0) { + int i, ch; int got_frame = 0; if (!decoded_frame) { if (!(decoded_frame = av_frame_alloc())) { - fprintf(stderr, "out of memory\n"); + fprintf(stderr, "Could not allocate audio frame\n"); exit(1); } } @@ -281,13 +305,20 @@ static void audio_decode_example(const char *outfilename, const char *filename) } if (got_frame) { /* if a frame has been decoded, output it */ - int data_size = av_samples_get_buffer_size(NULL, c->channels, - decoded_frame->nb_samples, - c->sample_fmt, 1); - fwrite(decoded_frame->data[0], 1, data_size, outfile); + int data_size = av_get_bytes_per_sample(c->sample_fmt); + if (data_size < 0) { + /* This should not occur, checking just for paranoia */ + fprintf(stderr, "Failed to calculate data size\n"); + exit(1); + } + for (i=0; i<decoded_frame->nb_samples; i++) + for (ch=0; ch<c->channels; ch++) + fwrite(decoded_frame->data[ch] + data_size*i, 1, data_size, outfile); } avpkt.size -= len; avpkt.data += len; + avpkt.dts = + avpkt.pts = AV_NOPTS_VALUE; if (avpkt.size < AUDIO_REFILL_THRESH) { /* Refill the input buffer, to avoid trying to decode * incomplete frames. Instead of this, one could also use @@ -313,27 +344,30 @@ static void audio_decode_example(const char *outfilename, const char *filename) /* * Video encoding example */ -static void video_encode_example(const char *filename) +static void video_encode_example(const char *filename, int codec_id) { AVCodec *codec; AVCodecContext *c= NULL; int i, ret, x, y, got_output; FILE *f; - AVFrame *picture; + AVFrame *frame; AVPacket pkt; uint8_t endcode[] = { 0, 0, 1, 0xb7 }; - printf("Video encoding\n"); + printf("Encode video file %s\n", filename); /* find the mpeg1 video encoder */ - codec = avcodec_find_encoder(AV_CODEC_ID_MPEG1VIDEO); + codec = avcodec_find_encoder(codec_id); if (!codec) { - fprintf(stderr, "codec not found\n"); + fprintf(stderr, "Codec not found\n"); exit(1); } c = avcodec_alloc_context3(codec); - picture = av_frame_alloc(); + if (!c) { + fprintf(stderr, "Could not allocate video codec context\n"); + exit(1); + } /* put sample parameters */ c->bit_rate = 400000; @@ -341,35 +375,52 @@ static void video_encode_example(const char *filename) c->width = 352; c->height = 288; /* frames per second */ - c->time_base= (AVRational){1,25}; - c->gop_size = 10; /* emit one intra frame every ten frames */ - c->max_b_frames=1; + c->time_base = (AVRational){1,25}; + /* emit one intra frame every ten frames + * check frame pict_type before passing frame + * to encoder, if frame->pict_type is AV_PICTURE_TYPE_I + * then gop_size is ignored and the output of encoder + * will always be I frame irrespective to gop_size + */ + c->gop_size = 10; + c->max_b_frames = 1; c->pix_fmt = AV_PIX_FMT_YUV420P; + if (codec_id == AV_CODEC_ID_H264) + av_opt_set(c->priv_data, "preset", "slow", 0); + /* open it */ if (avcodec_open2(c, codec, NULL) < 0) { - fprintf(stderr, "could not open codec\n"); + fprintf(stderr, "Could not open codec\n"); exit(1); } f = fopen(filename, "wb"); if (!f) { - fprintf(stderr, "could not open %s\n", filename); + fprintf(stderr, "Could not open %s\n", filename); + exit(1); + } + + frame = av_frame_alloc(); + if (!frame) { + fprintf(stderr, "Could not allocate video frame\n"); exit(1); } + frame->format = c->pix_fmt; + frame->width = c->width; + frame->height = c->height; - ret = av_image_alloc(picture->data, picture->linesize, c->width, c->height, + /* the image can be allocated by any means and av_image_alloc() is + * just the most convenient way if av_malloc() is to be used */ + ret = av_image_alloc(frame->data, frame->linesize, c->width, c->height, c->pix_fmt, 32); if (ret < 0) { - fprintf(stderr, "could not alloc raw picture buffer\n"); + fprintf(stderr, "Could not allocate raw picture buffer\n"); exit(1); } - picture->format = c->pix_fmt; - picture->width = c->width; - picture->height = c->height; /* encode 1 second of video */ - for(i=0;i<25;i++) { + for (i = 0; i < 25; i++) { av_init_packet(&pkt); pkt.data = NULL; // packet data will be allocated by the encoder pkt.size = 0; @@ -377,31 +428,31 @@ static void video_encode_example(const char *filename) fflush(stdout); /* prepare a dummy image */ /* Y */ - for(y=0;y<c->height;y++) { - for(x=0;x<c->width;x++) { - picture->data[0][y * picture->linesize[0] + x] = x + y + i * 3; + for (y = 0; y < c->height; y++) { + for (x = 0; x < c->width; x++) { + frame->data[0][y * frame->linesize[0] + x] = x + y + i * 3; } } /* Cb and Cr */ - for(y=0;y<c->height/2;y++) { - for(x=0;x<c->width/2;x++) { - picture->data[1][y * picture->linesize[1] + x] = 128 + y + i * 2; - picture->data[2][y * picture->linesize[2] + x] = 64 + x + i * 5; + for (y = 0; y < c->height/2; y++) { + for (x = 0; x < c->width/2; x++) { + frame->data[1][y * frame->linesize[1] + x] = 128 + y + i * 2; + frame->data[2][y * frame->linesize[2] + x] = 64 + x + i * 5; } } - picture->pts = i; + frame->pts = i; /* encode the image */ - ret = avcodec_encode_video2(c, &pkt, picture, &got_output); + ret = avcodec_encode_video2(c, &pkt, frame, &got_output); if (ret < 0) { - fprintf(stderr, "error encoding frame\n"); + fprintf(stderr, "Error encoding frame\n"); exit(1); } if (got_output) { - printf("encoding frame %3d (size=%5d)\n", i, pkt.size); + printf("Write frame %3d (size=%5d)\n", i, pkt.size); fwrite(pkt.data, 1, pkt.size, f); av_packet_unref(&pkt); } @@ -413,12 +464,12 @@ static void video_encode_example(const char *filename) ret = avcodec_encode_video2(c, &pkt, NULL, &got_output); if (ret < 0) { - fprintf(stderr, "error encoding frame\n"); + fprintf(stderr, "Error encoding frame\n"); exit(1); } if (got_output) { - printf("encoding frame %3d (size=%5d)\n", i, pkt.size); + printf("Write frame %3d (size=%5d)\n", i, pkt.size); fwrite(pkt.data, 1, pkt.size, f); av_packet_unref(&pkt); } @@ -430,8 +481,8 @@ static void video_encode_example(const char *filename) avcodec_close(c); av_free(c); - av_freep(&picture->data[0]); - av_frame_free(&picture); + av_freep(&frame->data[0]); + av_frame_free(&frame); printf("\n"); } @@ -445,22 +496,49 @@ static void pgm_save(unsigned char *buf, int wrap, int xsize, int ysize, FILE *f; int i; - f=fopen(filename,"w"); - fprintf(f,"P5\n%d %d\n%d\n",xsize,ysize,255); - for(i=0;i<ysize;i++) - fwrite(buf + i * wrap,1,xsize,f); + f = fopen(filename,"w"); + fprintf(f, "P5\n%d %d\n%d\n", xsize, ysize, 255); + for (i = 0; i < ysize; i++) + fwrite(buf + i * wrap, 1, xsize, f); fclose(f); } +static int decode_write_frame(const char *outfilename, AVCodecContext *avctx, + AVFrame *frame, int *frame_count, AVPacket *pkt, int last) +{ + int len, got_frame; + char buf[1024]; + + len = avcodec_decode_video2(avctx, frame, &got_frame, pkt); + if (len < 0) { + fprintf(stderr, "Error while decoding frame %d\n", *frame_count); + return len; + } + if (got_frame) { + printf("Saving %sframe %3d\n", last ? "last " : "", *frame_count); + fflush(stdout); + + /* the picture is allocated by the decoder, no need to free it */ + snprintf(buf, sizeof(buf), outfilename, *frame_count); + pgm_save(frame->data[0], frame->linesize[0], + frame->width, frame->height, buf); + (*frame_count)++; + } + if (pkt->data) { + pkt->size -= len; + pkt->data += len; + } + return 0; +} + static void video_decode_example(const char *outfilename, const char *filename) { AVCodec *codec; AVCodecContext *c= NULL; - int frame, got_picture, len; + int frame_count; FILE *f; - AVFrame *picture; + AVFrame *frame; uint8_t inbuf[INBUF_SIZE + AV_INPUT_BUFFER_PADDING_SIZE]; - char buf[1024]; AVPacket avpkt; av_init_packet(&avpkt); @@ -468,17 +546,20 @@ static void video_decode_example(const char *outfilename, const char *filename) /* set end of buffer to 0 (this ensures that no overreading happens for damaged mpeg streams) */ memset(inbuf + INBUF_SIZE, 0, AV_INPUT_BUFFER_PADDING_SIZE); - printf("Video decoding\n"); + printf("Decode video file %s to %s\n", filename, outfilename); /* find the mpeg1 video decoder */ codec = avcodec_find_decoder(AV_CODEC_ID_MPEG1VIDEO); if (!codec) { - fprintf(stderr, "codec not found\n"); + fprintf(stderr, "Codec not found\n"); exit(1); } c = avcodec_alloc_context3(codec); - picture = av_frame_alloc(); + if (!c) { + fprintf(stderr, "Could not allocate video codec context\n"); + exit(1); + } if (codec->capabilities & AV_CODEC_CAP_TRUNCATED) c->flags |= AV_CODEC_FLAG_TRUNCATED; // we do not send complete frames @@ -489,20 +570,24 @@ static void video_decode_example(const char *outfilename, const char *filename) /* open it */ if (avcodec_open2(c, codec, NULL) < 0) { - fprintf(stderr, "could not open codec\n"); + fprintf(stderr, "Could not open codec\n"); exit(1); } - /* the codec gives us the frame size, in samples */ - f = fopen(filename, "rb"); if (!f) { - fprintf(stderr, "could not open %s\n", filename); + fprintf(stderr, "Could not open %s\n", filename); exit(1); } - frame = 0; - for(;;) { + frame = av_frame_alloc(); + if (!frame) { + fprintf(stderr, "Could not allocate video frame\n"); + exit(1); + } + + frame_count = 0; + for (;;) { avpkt.size = fread(inbuf, 1, INBUF_SIZE, f); if (avpkt.size == 0) break; @@ -523,26 +608,9 @@ static void video_decode_example(const char *outfilename, const char *filename) /* here, we use a stream based decoder (mpeg1video), so we feed decoder and see if it could decode a frame */ avpkt.data = inbuf; - while (avpkt.size > 0) { - len = avcodec_decode_video2(c, picture, &got_picture, &avpkt); - if (len < 0) { - fprintf(stderr, "Error while decoding frame %d\n", frame); + while (avpkt.size > 0) + if (decode_write_frame(outfilename, c, frame, &frame_count, &avpkt, 0) < 0) exit(1); - } - if (got_picture) { - printf("saving frame %3d\n", frame); - fflush(stdout); - - /* the picture is allocated by the decoder. no need to - free it */ - snprintf(buf, sizeof(buf), outfilename, frame); - pgm_save(picture->data[0], picture->linesize[0], - c->width, c->height, buf); - frame++; - } - avpkt.size -= len; - avpkt.data += len; - } } /* some codecs, such as MPEG, transmit the I and P frame with a @@ -550,46 +618,48 @@ static void video_decode_example(const char *outfilename, const char *filename) chance to get the last frame of the video */ avpkt.data = NULL; avpkt.size = 0; - len = avcodec_decode_video2(c, picture, &got_picture, &avpkt); - if (got_picture) { - printf("saving last frame %3d\n", frame); - fflush(stdout); - - /* the picture is allocated by the decoder. no need to - free it */ - snprintf(buf, sizeof(buf), outfilename, frame); - pgm_save(picture->data[0], picture->linesize[0], - c->width, c->height, buf); - frame++; - } + decode_write_frame(outfilename, c, frame, &frame_count, &avpkt, 1); fclose(f); avcodec_close(c); av_free(c); - av_frame_free(&picture); + av_frame_free(&frame); printf("\n"); } int main(int argc, char **argv) { - const char *filename; + const char *output_type; /* register all the codecs */ avcodec_register_all(); - if (argc <= 1) { - audio_encode_example("/tmp/test.mp2"); - audio_decode_example("/tmp/test.sw", "/tmp/test.mp2"); - - video_encode_example("/tmp/test.mpg"); - filename = "/tmp/test.mpg"; + if (argc < 2) { + printf("usage: %s output_type\n" + "API example program to decode/encode a media stream with libavcodec.\n" + "This program generates a synthetic stream and encodes it to a file\n" + "named test.h264, test.mp2 or test.mpg depending on output_type.\n" + "The encoded stream is then decoded and written to a raw data output.\n" + "output_type must be chosen between 'h264', 'mp2', 'mpg'.\n", + argv[0]); + return 1; + } + output_type = argv[1]; + + if (!strcmp(output_type, "h264")) { + video_encode_example("test.h264", AV_CODEC_ID_H264); + } else if (!strcmp(output_type, "mp2")) { + audio_encode_example("test.mp2"); + audio_decode_example("test.pcm", "test.mp2"); + } else if (!strcmp(output_type, "mpg")) { + video_encode_example("test.mpg", AV_CODEC_ID_MPEG1VIDEO); + video_decode_example("test%02d.pgm", "test.mpg"); } else { - filename = argv[1]; + fprintf(stderr, "Invalid output type '%s', choose between 'h264', 'mp2', or 'mpg'\n", + output_type); + return 1; } - // audio_decode_example("/tmp/test.sw", filename); - video_decode_example("/tmp/test%d.pgm", filename); - return 0; } diff --git a/doc/examples/demuxing_decoding.c b/doc/examples/demuxing_decoding.c new file mode 100644 index 0000000000..59e0ccc986 --- /dev/null +++ b/doc/examples/demuxing_decoding.c @@ -0,0 +1,383 @@ +/* + * Copyright (c) 2012 Stefano Sabatini + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +/** + * @file + * Demuxing and decoding example. + * + * Show how to use the libavformat and libavcodec API to demux and + * decode audio and video data. + * @example demuxing_decoding.c + */ + +#include <libavutil/imgutils.h> +#include <libavutil/samplefmt.h> +#include <libavutil/timestamp.h> +#include <libavformat/avformat.h> + +static AVFormatContext *fmt_ctx = NULL; +static AVCodecContext *video_dec_ctx = NULL, *audio_dec_ctx; +static int width, height; +static enum AVPixelFormat pix_fmt; +static AVStream *video_stream = NULL, *audio_stream = NULL; +static const char *src_filename = NULL; +static const char *video_dst_filename = NULL; +static const char *audio_dst_filename = NULL; +static FILE *video_dst_file = NULL; +static FILE *audio_dst_file = NULL; + +static uint8_t *video_dst_data[4] = {NULL}; +static int video_dst_linesize[4]; +static int video_dst_bufsize; + +static int video_stream_idx = -1, audio_stream_idx = -1; +static AVFrame *frame = NULL; +static AVPacket pkt; +static int video_frame_count = 0; +static int audio_frame_count = 0; + +/* Enable or disable frame reference counting. You are not supposed to support + * both paths in your application but pick the one most appropriate to your + * needs. Look for the use of refcount in this example to see what are the + * differences of API usage between them. */ +static int refcount = 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); + } + } 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 open_codec_context(int *stream_idx, + AVFormatContext *fmt_ctx, enum AVMediaType type) +{ + int ret, stream_index; + AVStream *st; + AVCodecContext *dec_ctx = NULL; + AVCodec *dec = NULL; + AVDictionary *opts = NULL; + + ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0); + if (ret < 0) { + fprintf(stderr, "Could not find %s stream in input file '%s'\n", + av_get_media_type_string(type), src_filename); + return ret; + } else { + stream_index = ret; + st = fmt_ctx->streams[stream_index]; + + /* find decoder for the stream */ + dec_ctx = st->codec; + dec = avcodec_find_decoder(dec_ctx->codec_id); + if (!dec) { + fprintf(stderr, "Failed to find %s codec\n", + av_get_media_type_string(type)); + return AVERROR(EINVAL); + } + + /* Init the decoders, with or without reference counting */ + av_dict_set(&opts, "refcounted_frames", refcount ? "1" : "0", 0); + if ((ret = avcodec_open2(dec_ctx, dec, &opts)) < 0) { + fprintf(stderr, "Failed to open %s codec\n", + av_get_media_type_string(type)); + return ret; + } + *stream_idx = stream_index; + } + + return 0; +} + +static int get_format_from_sample_fmt(const char **fmt, + enum AVSampleFormat sample_fmt) +{ + int i; + struct sample_fmt_entry { + enum AVSampleFormat sample_fmt; const char *fmt_be, *fmt_le; + } sample_fmt_entries[] = { + { AV_SAMPLE_FMT_U8, "u8", "u8" }, + { AV_SAMPLE_FMT_S16, "s16be", "s16le" }, + { AV_SAMPLE_FMT_S32, "s32be", "s32le" }, + { AV_SAMPLE_FMT_FLT, "f32be", "f32le" }, + { AV_SAMPLE_FMT_DBL, "f64be", "f64le" }, + }; + *fmt = NULL; + + for (i = 0; i < FF_ARRAY_ELEMS(sample_fmt_entries); i++) { + struct sample_fmt_entry *entry = &sample_fmt_entries[i]; + if (sample_fmt == entry->sample_fmt) { + *fmt = AV_NE(entry->fmt_be, entry->fmt_le); + return 0; + } + } + + fprintf(stderr, + "sample format %s is not supported as output format\n", + av_get_sample_fmt_name(sample_fmt)); + return -1; +} + +int main (int argc, char **argv) +{ + int ret = 0, got_frame; + + if (argc != 4 && argc != 5) { + fprintf(stderr, "usage: %s [-refcount] input_file video_output_file audio_output_file\n" + "API example program to show how to read frames from an input file.\n" + "This program reads frames from a file, decodes them, and writes decoded\n" + "video frames to a rawvideo file named video_output_file, and decoded\n" + "audio frames to a rawaudio file named audio_output_file.\n\n" + "If the -refcount option is specified, the program use the\n" + "reference counting frame system which allows keeping a copy of\n" + "the data for longer than one decode call.\n" + "\n", argv[0]); + exit(1); + } + if (argc == 5 && !strcmp(argv[1], "-refcount")) { + refcount = 1; + argv++; + } + src_filename = argv[1]; + video_dst_filename = argv[2]; + audio_dst_filename = argv[3]; + + /* register all formats and codecs */ + av_register_all(); + + /* open input file, and allocate format context */ + if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) { + fprintf(stderr, "Could not open source file %s\n", src_filename); + exit(1); + } + + /* retrieve stream information */ + if (avformat_find_stream_info(fmt_ctx, NULL) < 0) { + fprintf(stderr, "Could not find stream information\n"); + exit(1); + } + + if (open_codec_context(&video_stream_idx, fmt_ctx, AVMEDIA_TYPE_VIDEO) >= 0) { + video_stream = fmt_ctx->streams[video_stream_idx]; + video_dec_ctx = video_stream->codec; + + video_dst_file = fopen(video_dst_filename, "wb"); + if (!video_dst_file) { + fprintf(stderr, "Could not open destination file %s\n", video_dst_filename); + ret = 1; + goto end; + } + + /* allocate image where the decoded image will be put */ + width = video_dec_ctx->width; + height = video_dec_ctx->height; + pix_fmt = video_dec_ctx->pix_fmt; + ret = av_image_alloc(video_dst_data, video_dst_linesize, + width, height, pix_fmt, 1); + if (ret < 0) { + fprintf(stderr, "Could not allocate raw video buffer\n"); + goto end; + } + video_dst_bufsize = ret; + } + + if (open_codec_context(&audio_stream_idx, fmt_ctx, AVMEDIA_TYPE_AUDIO) >= 0) { + audio_stream = fmt_ctx->streams[audio_stream_idx]; + audio_dec_ctx = audio_stream->codec; + audio_dst_file = fopen(audio_dst_filename, "wb"); + if (!audio_dst_file) { + fprintf(stderr, "Could not open destination file %s\n", audio_dst_filename); + ret = 1; + goto end; + } + } + + /* dump input information to stderr */ + av_dump_format(fmt_ctx, 0, src_filename, 0); + + if (!audio_stream && !video_stream) { + fprintf(stderr, "Could not find audio or video stream in the input, aborting\n"); + ret = 1; + goto end; + } + + frame = av_frame_alloc(); + if (!frame) { + fprintf(stderr, "Could not allocate frame\n"); + ret = AVERROR(ENOMEM); + goto end; + } + + /* initialize packet, set data to NULL, let the demuxer fill it */ + av_init_packet(&pkt); + pkt.data = NULL; + pkt.size = 0; + + if (video_stream) + printf("Demuxing video from file '%s' into '%s'\n", src_filename, video_dst_filename); + if (audio_stream) + printf("Demuxing audio from file '%s' into '%s'\n", src_filename, audio_dst_filename); + + /* read frames from the file */ + while (av_read_frame(fmt_ctx, &pkt) >= 0) { + AVPacket orig_pkt = pkt; + do { + ret = decode_packet(&got_frame, 0); + if (ret < 0) + break; + pkt.data += ret; + pkt.size -= ret; + } while (pkt.size > 0); + av_packet_unref(&orig_pkt); + } + + /* flush cached frames */ + pkt.data = NULL; + pkt.size = 0; + do { + decode_packet(&got_frame, 1); + } while (got_frame); + + printf("Demuxing succeeded.\n"); + + if (video_stream) { + printf("Play the output video file with the command:\n" + "ffplay -f rawvideo -pix_fmt %s -video_size %dx%d %s\n", + av_get_pix_fmt_name(pix_fmt), width, height, + video_dst_filename); + } + + if (audio_stream) { + enum AVSampleFormat sfmt = audio_dec_ctx->sample_fmt; + int n_channels = audio_dec_ctx->channels; + const char *fmt; + + if (av_sample_fmt_is_planar(sfmt)) { + const char *packed = av_get_sample_fmt_name(sfmt); + printf("Warning: the sample format the decoder produced is planar " + "(%s). This example will output the first channel only.\n", + packed ? packed : "?"); + sfmt = av_get_packed_sample_fmt(sfmt); + n_channels = 1; + } + + if ((ret = get_format_from_sample_fmt(&fmt, sfmt)) < 0) + goto end; + + printf("Play the output audio file with the command:\n" + "ffplay -f %s -ac %d -ar %d %s\n", + fmt, n_channels, audio_dec_ctx->sample_rate, + audio_dst_filename); + } + +end: + avcodec_close(video_dec_ctx); + avcodec_close(audio_dec_ctx); + avformat_close_input(&fmt_ctx); + if (video_dst_file) + fclose(video_dst_file); + if (audio_dst_file) + fclose(audio_dst_file); + av_frame_free(&frame); + av_free(video_dst_data[0]); + + return ret < 0; +} diff --git a/doc/examples/extract_mvs.c b/doc/examples/extract_mvs.c new file mode 100644 index 0000000000..975189c77d --- /dev/null +++ b/doc/examples/extract_mvs.c @@ -0,0 +1,185 @@ +/* + * Copyright (c) 2012 Stefano Sabatini + * Copyright (c) 2014 Clément Bœsch + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include <libavutil/motion_vector.h> +#include <libavformat/avformat.h> + +static AVFormatContext *fmt_ctx = NULL; +static AVCodecContext *video_dec_ctx = NULL; +static AVStream *video_stream = NULL; +static const char *src_filename = NULL; + +static int video_stream_idx = -1; +static AVFrame *frame = NULL; +static AVPacket pkt; +static int video_frame_count = 0; + +static int decode_packet(int *got_frame, int cached) +{ + int decoded = pkt.size; + + *got_frame = 0; + + if (pkt.stream_index == video_stream_idx) { + int 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) { + int i; + AVFrameSideData *sd; + + video_frame_count++; + sd = av_frame_get_side_data(frame, AV_FRAME_DATA_MOTION_VECTORS); + if (sd) { + const AVMotionVector *mvs = (const AVMotionVector *)sd->data; + for (i = 0; i < sd->size / sizeof(*mvs); i++) { + const AVMotionVector *mv = &mvs[i]; + printf("%d,%2d,%2d,%2d,%4d,%4d,%4d,%4d,0x%"PRIx64"\n", + video_frame_count, mv->source, + mv->w, mv->h, mv->src_x, mv->src_y, + mv->dst_x, mv->dst_y, mv->flags); + } + } + } + } + + return decoded; +} + +static int open_codec_context(int *stream_idx, + AVFormatContext *fmt_ctx, enum AVMediaType type) +{ + int ret; + AVStream *st; + AVCodecContext *dec_ctx = NULL; + AVCodec *dec = NULL; + AVDictionary *opts = NULL; + + ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0); + if (ret < 0) { + fprintf(stderr, "Could not find %s stream in input file '%s'\n", + av_get_media_type_string(type), src_filename); + return ret; + } else { + *stream_idx = ret; + st = fmt_ctx->streams[*stream_idx]; + + /* find decoder for the stream */ + dec_ctx = st->codec; + dec = avcodec_find_decoder(dec_ctx->codec_id); + if (!dec) { + fprintf(stderr, "Failed to find %s codec\n", + av_get_media_type_string(type)); + return AVERROR(EINVAL); + } + + /* Init the video decoder */ + av_dict_set(&opts, "flags2", "+export_mvs", 0); + if ((ret = avcodec_open2(dec_ctx, dec, &opts)) < 0) { + fprintf(stderr, "Failed to open %s codec\n", + av_get_media_type_string(type)); + return ret; + } + } + + return 0; +} + +int main(int argc, char **argv) +{ + int ret = 0, got_frame; + + if (argc != 2) { + fprintf(stderr, "Usage: %s <video>\n", argv[0]); + exit(1); + } + src_filename = argv[1]; + + av_register_all(); + + if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) { + fprintf(stderr, "Could not open source file %s\n", src_filename); + exit(1); + } + + if (avformat_find_stream_info(fmt_ctx, NULL) < 0) { + fprintf(stderr, "Could not find stream information\n"); + exit(1); + } + + if (open_codec_context(&video_stream_idx, fmt_ctx, AVMEDIA_TYPE_VIDEO) >= 0) { + video_stream = fmt_ctx->streams[video_stream_idx]; + video_dec_ctx = video_stream->codec; + } + + av_dump_format(fmt_ctx, 0, src_filename, 0); + + if (!video_stream) { + fprintf(stderr, "Could not find video stream in the input, aborting\n"); + ret = 1; + goto end; + } + + frame = av_frame_alloc(); + if (!frame) { + fprintf(stderr, "Could not allocate frame\n"); + ret = AVERROR(ENOMEM); + goto end; + } + + printf("framenum,source,blockw,blockh,srcx,srcy,dstx,dsty,flags\n"); + + /* initialize packet, set data to NULL, let the demuxer fill it */ + av_init_packet(&pkt); + pkt.data = NULL; + pkt.size = 0; + + /* read frames from the file */ + while (av_read_frame(fmt_ctx, &pkt) >= 0) { + AVPacket orig_pkt = pkt; + do { + ret = decode_packet(&got_frame, 0); + if (ret < 0) + break; + pkt.data += ret; + pkt.size -= ret; + } while (pkt.size > 0); + av_packet_unref(&orig_pkt); + } + + /* flush cached frames */ + pkt.data = NULL; + pkt.size = 0; + do { + decode_packet(&got_frame, 1); + } while (got_frame); + +end: + avcodec_close(video_dec_ctx); + avformat_close_input(&fmt_ctx); + av_frame_free(&frame); + return ret < 0; +} diff --git a/doc/examples/filter_audio.c b/doc/examples/filter_audio.c index 60fe107dda..01761dcee4 100644 --- a/doc/examples/filter_audio.c +++ b/doc/examples/filter_audio.c @@ -1,20 +1,20 @@ /* * copyright (c) 2013 Andrew Kelley * - * This file is part of Libav. + * This file is part of FFmpeg. * - * Libav is free software; you can redistribute it and/or + * FFmpeg is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * - * Libav is distributed in the hope that it will be useful, + * FFmpeg is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with Libav; if not, write to the Free Software + * License along with FFmpeg; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA */ diff --git a/doc/examples/filtering_audio.c b/doc/examples/filtering_audio.c new file mode 100644 index 0000000000..6bb24a431d --- /dev/null +++ b/doc/examples/filtering_audio.c @@ -0,0 +1,295 @@ +/* + * Copyright (c) 2010 Nicolas George + * Copyright (c) 2011 Stefano Sabatini + * Copyright (c) 2012 Clément Bœsch + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +/** + * @file + * API example for audio decoding and filtering + * @example filtering_audio.c + */ + +#include <unistd.h> + +#include <libavcodec/avcodec.h> +#include <libavformat/avformat.h> +#include <libavfilter/avfiltergraph.h> +#include <libavfilter/buffersink.h> +#include <libavfilter/buffersrc.h> +#include <libavutil/opt.h> + +static const char *filter_descr = "aresample=8000,aformat=sample_fmts=s16:channel_layouts=mono"; +static const char *player = "ffplay -f s16le -ar 8000 -ac 1 -"; + +static AVFormatContext *fmt_ctx; +static AVCodecContext *dec_ctx; +AVFilterContext *buffersink_ctx; +AVFilterContext *buffersrc_ctx; +AVFilterGraph *filter_graph; +static int audio_stream_index = -1; + +static int open_input_file(const char *filename) +{ + int ret; + AVCodec *dec; + + if ((ret = avformat_open_input(&fmt_ctx, filename, NULL, NULL)) < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n"); + return ret; + } + + if ((ret = avformat_find_stream_info(fmt_ctx, NULL)) < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n"); + return ret; + } + + /* select the audio stream */ + ret = av_find_best_stream(fmt_ctx, AVMEDIA_TYPE_AUDIO, -1, -1, &dec, 0); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot find an audio stream in the input file\n"); + return ret; + } + audio_stream_index = ret; + dec_ctx = fmt_ctx->streams[audio_stream_index]->codec; + av_opt_set_int(dec_ctx, "refcounted_frames", 1, 0); + + /* init the audio decoder */ + if ((ret = avcodec_open2(dec_ctx, dec, NULL)) < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot open audio decoder\n"); + return ret; + } + + return 0; +} + +static int init_filters(const char *filters_descr) +{ + char args[512]; + int ret = 0; + AVFilter *abuffersrc = avfilter_get_by_name("abuffer"); + AVFilter *abuffersink = avfilter_get_by_name("abuffersink"); + AVFilterInOut *outputs = avfilter_inout_alloc(); + AVFilterInOut *inputs = avfilter_inout_alloc(); + static const enum AVSampleFormat out_sample_fmts[] = { AV_SAMPLE_FMT_S16, -1 }; + static const int64_t out_channel_layouts[] = { AV_CH_LAYOUT_MONO, -1 }; + static const int out_sample_rates[] = { 8000, -1 }; + const AVFilterLink *outlink; + AVRational time_base = fmt_ctx->streams[audio_stream_index]->time_base; + + filter_graph = avfilter_graph_alloc(); + if (!outputs || !inputs || !filter_graph) { + ret = AVERROR(ENOMEM); + goto end; + } + + /* buffer audio source: the decoded frames from the decoder will be inserted here. */ + 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, + time_base.num, 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, abuffersrc, "in", + args, NULL, filter_graph); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer source\n"); + goto end; + } + + /* buffer audio sink: to terminate the filter chain. */ + ret = avfilter_graph_create_filter(&buffersink_ctx, abuffersink, "out", + NULL, NULL, filter_graph); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer sink\n"); + goto end; + } + + ret = av_opt_set_int_list(buffersink_ctx, "sample_fmts", out_sample_fmts, -1, + AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot set output sample format\n"); + goto end; + } + + ret = av_opt_set_int_list(buffersink_ctx, "channel_layouts", out_channel_layouts, -1, + AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot set output channel layout\n"); + goto end; + } + + ret = av_opt_set_int_list(buffersink_ctx, "sample_rates", out_sample_rates, -1, + AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot set output sample rate\n"); + goto end; + } + + /* + * Set the endpoints for the filter graph. The filter_graph will + * be linked to the graph described by filters_descr. + */ + + /* + * The buffer source output must be connected to the input pad of + * the first filter described by filters_descr; since the first + * filter input label is not specified, it is set to "in" by + * default. + */ + outputs->name = av_strdup("in"); + outputs->filter_ctx = buffersrc_ctx; + outputs->pad_idx = 0; + outputs->next = NULL; + + /* + * The buffer sink input must be connected to the output pad of + * the last filter described by filters_descr; since the last + * filter output label is not specified, it is set to "out" by + * default. + */ + inputs->name = av_strdup("out"); + inputs->filter_ctx = buffersink_ctx; + inputs->pad_idx = 0; + inputs->next = NULL; + + if ((ret = avfilter_graph_parse_ptr(filter_graph, filters_descr, + &inputs, &outputs, NULL)) < 0) + goto end; + + if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0) + goto end; + + /* Print summary of the sink buffer + * Note: args buffer is reused to store channel layout string */ + outlink = buffersink_ctx->inputs[0]; + av_get_channel_layout_string(args, sizeof(args), -1, outlink->channel_layout); + av_log(NULL, AV_LOG_INFO, "Output: srate:%dHz fmt:%s chlayout:%s\n", + (int)outlink->sample_rate, + (char *)av_x_if_null(av_get_sample_fmt_name(outlink->format), "?"), + args); + +end: + avfilter_inout_free(&inputs); + avfilter_inout_free(&outputs); + + return ret; +} + +static void print_frame(const AVFrame *frame) +{ + const int n = frame->nb_samples * av_get_channel_layout_nb_channels(av_frame_get_channel_layout(frame)); + const uint16_t *p = (uint16_t*)frame->data[0]; + const uint16_t *p_end = p + n; + + while (p < p_end) { + fputc(*p & 0xff, stdout); + fputc(*p>>8 & 0xff, stdout); + p++; + } + fflush(stdout); +} + +int main(int argc, char **argv) +{ + int ret; + AVPacket packet0, packet; + AVFrame *frame = av_frame_alloc(); + AVFrame *filt_frame = av_frame_alloc(); + int got_frame; + + if (!frame || !filt_frame) { + perror("Could not allocate frame"); + exit(1); + } + if (argc != 2) { + fprintf(stderr, "Usage: %s file | %s\n", argv[0], player); + exit(1); + } + + av_register_all(); + avfilter_register_all(); + + if ((ret = open_input_file(argv[1])) < 0) + goto end; + if ((ret = init_filters(filter_descr)) < 0) + goto end; + + /* read all packets */ + packet0.data = NULL; + packet.data = NULL; + while (1) { + if (!packet0.data) { + if ((ret = av_read_frame(fmt_ctx, &packet)) < 0) + break; + packet0 = packet; + } + + if (packet.stream_index == audio_stream_index) { + got_frame = 0; + ret = avcodec_decode_audio4(dec_ctx, frame, &got_frame, &packet); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Error decoding audio\n"); + continue; + } + packet.size -= ret; + packet.data += ret; + + if (got_frame) { + /* push the audio data from decoded frame into the filtergraph */ + if (av_buffersrc_add_frame_flags(buffersrc_ctx, frame, 0) < 0) { + av_log(NULL, AV_LOG_ERROR, "Error while feeding the audio filtergraph\n"); + break; + } + + /* pull filtered audio from the filtergraph */ + while (1) { + ret = av_buffersink_get_frame(buffersink_ctx, filt_frame); + if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) + break; + if (ret < 0) + goto end; + print_frame(filt_frame); + av_frame_unref(filt_frame); + } + } + + if (packet.size <= 0) + av_packet_unref(&packet0); + } else { + /* discard non-wanted packets */ + av_packet_unref(&packet0); + } + } +end: + avfilter_graph_free(&filter_graph); + avcodec_close(dec_ctx); + avformat_close_input(&fmt_ctx); + av_frame_free(&frame); + av_frame_free(&filt_frame); + + if (ret < 0 && ret != AVERROR_EOF) { + fprintf(stderr, "Error occurred: %s\n", av_err2str(ret)); + exit(1); + } + + exit(0); +} diff --git a/doc/examples/filtering_video.c b/doc/examples/filtering_video.c new file mode 100644 index 0000000000..3dabf13b10 --- /dev/null +++ b/doc/examples/filtering_video.c @@ -0,0 +1,280 @@ +/* + * Copyright (c) 2010 Nicolas George + * Copyright (c) 2011 Stefano Sabatini + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +/** + * @file + * API example for decoding and filtering + * @example filtering_video.c + */ + +#define _XOPEN_SOURCE 600 /* for usleep */ +#include <unistd.h> + +#include <libavcodec/avcodec.h> +#include <libavformat/avformat.h> +#include <libavfilter/avfiltergraph.h> +#include <libavfilter/buffersink.h> +#include <libavfilter/buffersrc.h> +#include <libavutil/opt.h> + +const char *filter_descr = "scale=78:24,transpose=cclock"; +/* other way: + scale=78:24 [scl]; [scl] transpose=cclock // assumes "[in]" and "[out]" to be input output pads respectively + */ + +static AVFormatContext *fmt_ctx; +static AVCodecContext *dec_ctx; +AVFilterContext *buffersink_ctx; +AVFilterContext *buffersrc_ctx; +AVFilterGraph *filter_graph; +static int video_stream_index = -1; +static int64_t last_pts = AV_NOPTS_VALUE; + +static int open_input_file(const char *filename) +{ + int ret; + AVCodec *dec; + + if ((ret = avformat_open_input(&fmt_ctx, filename, NULL, NULL)) < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n"); + return ret; + } + + if ((ret = avformat_find_stream_info(fmt_ctx, NULL)) < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n"); + return ret; + } + + /* select the video stream */ + ret = av_find_best_stream(fmt_ctx, AVMEDIA_TYPE_VIDEO, -1, -1, &dec, 0); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot find a video stream in the input file\n"); + return ret; + } + video_stream_index = ret; + dec_ctx = fmt_ctx->streams[video_stream_index]->codec; + av_opt_set_int(dec_ctx, "refcounted_frames", 1, 0); + + /* init the video decoder */ + if ((ret = avcodec_open2(dec_ctx, dec, NULL)) < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot open video decoder\n"); + return ret; + } + + return 0; +} + +static int init_filters(const char *filters_descr) +{ + char args[512]; + int ret = 0; + AVFilter *buffersrc = avfilter_get_by_name("buffer"); + AVFilter *buffersink = avfilter_get_by_name("buffersink"); + AVFilterInOut *outputs = avfilter_inout_alloc(); + AVFilterInOut *inputs = avfilter_inout_alloc(); + AVRational time_base = fmt_ctx->streams[video_stream_index]->time_base; + enum AVPixelFormat pix_fmts[] = { AV_PIX_FMT_GRAY8, AV_PIX_FMT_NONE }; + + filter_graph = avfilter_graph_alloc(); + if (!outputs || !inputs || !filter_graph) { + ret = AVERROR(ENOMEM); + goto end; + } + + /* buffer video source: the decoded frames from the decoder will be inserted here. */ + 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, + time_base.num, time_base.den, + dec_ctx->sample_aspect_ratio.num, dec_ctx->sample_aspect_ratio.den); + + ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in", + args, NULL, filter_graph); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot create buffer source\n"); + goto end; + } + + /* buffer video sink: to terminate the filter chain. */ + ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out", + NULL, NULL, filter_graph); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot create buffer sink\n"); + goto end; + } + + ret = av_opt_set_int_list(buffersink_ctx, "pix_fmts", pix_fmts, + AV_PIX_FMT_NONE, AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n"); + goto end; + } + + /* + * Set the endpoints for the filter graph. The filter_graph will + * be linked to the graph described by filters_descr. + */ + + /* + * The buffer source output must be connected to the input pad of + * the first filter described by filters_descr; since the first + * filter input label is not specified, it is set to "in" by + * default. + */ + outputs->name = av_strdup("in"); + outputs->filter_ctx = buffersrc_ctx; + outputs->pad_idx = 0; + outputs->next = NULL; + + /* + * The buffer sink input must be connected to the output pad of + * the last filter described by filters_descr; since the last + * filter output label is not specified, it is set to "out" by + * default. + */ + inputs->name = av_strdup("out"); + inputs->filter_ctx = buffersink_ctx; + inputs->pad_idx = 0; + inputs->next = NULL; + + if ((ret = avfilter_graph_parse_ptr(filter_graph, filters_descr, + &inputs, &outputs, NULL)) < 0) + goto end; + + if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0) + goto end; + +end: + avfilter_inout_free(&inputs); + avfilter_inout_free(&outputs); + + return ret; +} + +static void display_frame(const AVFrame *frame, AVRational time_base) +{ + int x, y; + uint8_t *p0, *p; + int64_t delay; + + if (frame->pts != AV_NOPTS_VALUE) { + if (last_pts != AV_NOPTS_VALUE) { + /* sleep roughly the right amount of time; + * usleep is in microseconds, just like AV_TIME_BASE. */ + delay = av_rescale_q(frame->pts - last_pts, + time_base, AV_TIME_BASE_Q); + if (delay > 0 && delay < 1000000) + usleep(delay); + } + last_pts = frame->pts; + } + + /* Trivial ASCII grayscale display. */ + p0 = frame->data[0]; + puts("\033c"); + for (y = 0; y < frame->height; y++) { + p = p0; + for (x = 0; x < frame->width; x++) + putchar(" .-+#"[*(p++) / 52]); + putchar('\n'); + p0 += frame->linesize[0]; + } + fflush(stdout); +} + +int main(int argc, char **argv) +{ + int ret; + AVPacket packet; + AVFrame *frame = av_frame_alloc(); + AVFrame *filt_frame = av_frame_alloc(); + int got_frame; + + if (!frame || !filt_frame) { + perror("Could not allocate frame"); + exit(1); + } + if (argc != 2) { + fprintf(stderr, "Usage: %s file\n", argv[0]); + exit(1); + } + + av_register_all(); + avfilter_register_all(); + + if ((ret = open_input_file(argv[1])) < 0) + goto end; + if ((ret = init_filters(filter_descr)) < 0) + goto end; + + /* read all packets */ + while (1) { + if ((ret = av_read_frame(fmt_ctx, &packet)) < 0) + break; + + if (packet.stream_index == video_stream_index) { + got_frame = 0; + ret = avcodec_decode_video2(dec_ctx, frame, &got_frame, &packet); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Error decoding video\n"); + break; + } + + if (got_frame) { + frame->pts = av_frame_get_best_effort_timestamp(frame); + + /* push the decoded frame into the filtergraph */ + if (av_buffersrc_add_frame_flags(buffersrc_ctx, frame, AV_BUFFERSRC_FLAG_KEEP_REF) < 0) { + av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n"); + break; + } + + /* pull filtered frames from the filtergraph */ + while (1) { + ret = av_buffersink_get_frame(buffersink_ctx, filt_frame); + if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) + break; + if (ret < 0) + goto end; + display_frame(filt_frame, buffersink_ctx->inputs[0]->time_base); + av_frame_unref(filt_frame); + } + av_frame_unref(frame); + } + } + av_packet_unref(&packet); + } +end: + avfilter_graph_free(&filter_graph); + avcodec_close(dec_ctx); + avformat_close_input(&fmt_ctx); + av_frame_free(&frame); + av_frame_free(&filt_frame); + + if (ret < 0 && ret != AVERROR_EOF) { + fprintf(stderr, "Error occurred: %s\n", av_err2str(ret)); + exit(1); + } + + exit(0); +} diff --git a/doc/examples/http_multiclient.c b/doc/examples/http_multiclient.c new file mode 100644 index 0000000000..b9a306d835 --- /dev/null +++ b/doc/examples/http_multiclient.c @@ -0,0 +1,155 @@ +/* + * Copyright (c) 2015 Stephan Holljes + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +/** + * @file + * libavformat multi-client network API usage example. + * + * @example http_multiclient.c + * This example will serve a file without decoding or demuxing it over http. + * Multiple clients can connect and will receive the same file. + */ + +#include <libavformat/avformat.h> +#include <libavutil/opt.h> +#include <unistd.h> + +void process_client(AVIOContext *client, const char *in_uri) +{ + AVIOContext *input = NULL; + uint8_t buf[1024]; + int ret, n, reply_code; + char *resource = NULL; + while ((ret = avio_handshake(client)) > 0) { + av_opt_get(client, "resource", AV_OPT_SEARCH_CHILDREN, &resource); + // check for strlen(resource) is necessary, because av_opt_get() + // may return empty string. + if (resource && strlen(resource)) + break; + } + if (ret < 0) + goto end; + av_log(client, AV_LOG_TRACE, "resource=%p\n", resource); + if (resource && resource[0] == '/' && !strcmp((resource + 1), in_uri)) { + reply_code = 200; + } else { + reply_code = AVERROR_HTTP_NOT_FOUND; + } + if ((ret = av_opt_set_int(client, "reply_code", reply_code, AV_OPT_SEARCH_CHILDREN)) < 0) { + av_log(client, AV_LOG_ERROR, "Failed to set reply_code: %s.\n", av_err2str(ret)); + goto end; + } + av_log(client, AV_LOG_TRACE, "Set reply code to %d\n", reply_code); + + while ((ret = avio_handshake(client)) > 0); + + if (ret < 0) + goto end; + + fprintf(stderr, "Handshake performed.\n"); + if (reply_code != 200) + goto end; + fprintf(stderr, "Opening input file.\n"); + if ((ret = avio_open2(&input, in_uri, AVIO_FLAG_READ, NULL, NULL)) < 0) { + av_log(input, AV_LOG_ERROR, "Failed to open input: %s: %s.\n", in_uri, + av_err2str(ret)); + goto end; + } + for(;;) { + n = avio_read(input, buf, sizeof(buf)); + if (n < 0) { + if (n == AVERROR_EOF) + break; + av_log(input, AV_LOG_ERROR, "Error reading from input: %s.\n", + av_err2str(n)); + break; + } + avio_write(client, buf, n); + avio_flush(client); + } +end: + fprintf(stderr, "Flushing client\n"); + avio_flush(client); + fprintf(stderr, "Closing client\n"); + avio_close(client); + fprintf(stderr, "Closing input\n"); + avio_close(input); +} + +int main(int argc, char **argv) +{ + av_log_set_level(AV_LOG_TRACE); + AVDictionary *options = NULL; + AVIOContext *client = NULL, *server = NULL; + const char *in_uri, *out_uri; + int ret, pid; + if (argc < 3) { + printf("usage: %s input http://hostname[:port]\n" + "API example program to serve http to multiple clients.\n" + "\n", argv[0]); + return 1; + } + + in_uri = argv[1]; + out_uri = argv[2]; + + av_register_all(); + avformat_network_init(); + + if ((ret = av_dict_set(&options, "listen", "2", 0)) < 0) { + fprintf(stderr, "Failed to set listen mode for server: %s\n", av_err2str(ret)); + return ret; + } + if ((ret = avio_open2(&server, out_uri, AVIO_FLAG_WRITE, NULL, &options)) < 0) { + fprintf(stderr, "Failed to open server: %s\n", av_err2str(ret)); + return ret; + } + fprintf(stderr, "Entering main loop.\n"); + for(;;) { + if ((ret = avio_accept(server, &client)) < 0) + goto end; + fprintf(stderr, "Accepted client, forking process.\n"); + // XXX: Since we don't reap our children and don't ignore signals + // this produces zombie processes. + pid = fork(); + if (pid < 0) { + perror("Fork failed"); + ret = AVERROR(errno); + goto end; + } + if (pid == 0) { + fprintf(stderr, "In child.\n"); + process_client(client, in_uri); + avio_close(server); + exit(0); + } + if (pid > 0) + avio_close(client); + } +end: + avio_close(server); + if (ret < 0 && ret != AVERROR_EOF) { + fprintf(stderr, "Some errors occurred: %s\n", av_err2str(ret)); + return 1; + } + return 0; +} diff --git a/doc/examples/metadata.c b/doc/examples/metadata.c index f4c6eee9c3..f73c267369 100644 --- a/doc/examples/metadata.c +++ b/doc/examples/metadata.c @@ -22,8 +22,8 @@ /** * @file - * @example metadata.c * Shows how the metadata API can be used in application programs. + * @example metadata.c */ #include <stdio.h> @@ -51,6 +51,6 @@ int main (int argc, char **argv) while ((tag = av_dict_get(fmt_ctx->metadata, "", tag, AV_DICT_IGNORE_SUFFIX))) printf("%s=%s\n", tag->key, tag->value); - avformat_free_context(fmt_ctx); + avformat_close_input(&fmt_ctx); return 0; } diff --git a/doc/examples/output.c b/doc/examples/muxing.c index cc2cbb1bae..2fbc89bb02 100644 --- a/doc/examples/output.c +++ b/doc/examples/muxing.c @@ -24,9 +24,9 @@ * @file * libavformat API example. * - * @example output.c * Output a media file in any supported libavformat format. The default * codecs are used. + * @example muxing.c */ #include <stdlib.h> @@ -34,17 +34,17 @@ #include <string.h> #include <math.h> -#include "libavutil/channel_layout.h" -#include "libavutil/mathematics.h" -#include "libavutil/opt.h" -#include "libavformat/avformat.h" -#include "libavresample/avresample.h" -#include "libswscale/swscale.h" +#include <libavutil/avassert.h> +#include <libavutil/channel_layout.h> +#include <libavutil/opt.h> +#include <libavutil/mathematics.h> +#include <libavutil/timestamp.h> +#include <libavformat/avformat.h> +#include <libswscale/swscale.h> +#include <libswresample/swresample.h> -/* 5 seconds stream duration */ -#define STREAM_DURATION 5.0 +#define STREAM_DURATION 10.0 #define STREAM_FRAME_RATE 25 /* 25 images/s */ -#define STREAM_NB_FRAMES ((int)(STREAM_DURATION * STREAM_FRAME_RATE)) #define STREAM_PIX_FMT AV_PIX_FMT_YUV420P /* default pix_fmt */ #define SCALE_FLAGS SWS_BICUBIC @@ -56,6 +56,7 @@ typedef struct OutputStream { /* pts of the next frame that will be generated */ int64_t next_pts; + int samples_count; AVFrame *frame; AVFrame *tmp_frame; @@ -63,80 +64,126 @@ typedef struct OutputStream { float t, tincr, tincr2; struct SwsContext *sws_ctx; - AVAudioResampleContext *avr; + struct SwrContext *swr_ctx; } OutputStream; -/**************************************************************/ -/* audio output */ +static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt) +{ + AVRational *time_base = &fmt_ctx->streams[pkt->stream_index]->time_base; -/* - * add an audio output stream - */ -static void add_audio_stream(OutputStream *ost, AVFormatContext *oc, - enum AVCodecID codec_id) + printf("pts:%s pts_time:%s dts:%s dts_time:%s duration:%s duration_time:%s stream_index:%d\n", + 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 int write_frame(AVFormatContext *fmt_ctx, const AVRational *time_base, AVStream *st, AVPacket *pkt) +{ + /* rescale output packet timestamp values from codec to stream timebase */ + av_packet_rescale_ts(pkt, *time_base, st->time_base); + pkt->stream_index = st->index; + + /* Write the compressed frame to the media file. */ + log_packet(fmt_ctx, pkt); + return av_interleaved_write_frame(fmt_ctx, pkt); +} + +/* Add an output stream. */ +static void add_stream(OutputStream *ost, AVFormatContext *oc, + AVCodec **codec, + enum AVCodecID codec_id) { AVCodecContext *c; - AVCodec *codec; - int ret; + int i; - /* find the audio encoder */ - codec = avcodec_find_encoder(codec_id); - if (!codec) { - fprintf(stderr, "codec not found\n"); + /* find the encoder */ + *codec = avcodec_find_encoder(codec_id); + if (!(*codec)) { + fprintf(stderr, "Could not find encoder for '%s'\n", + avcodec_get_name(codec_id)); exit(1); } ost->st = avformat_new_stream(oc, NULL); if (!ost->st) { - fprintf(stderr, "Could not alloc stream\n"); + fprintf(stderr, "Could not allocate stream\n"); exit(1); } - - c = avcodec_alloc_context3(codec); + ost->st->id = oc->nb_streams-1; + c = avcodec_alloc_context3(*codec); if (!c) { fprintf(stderr, "Could not alloc an encoding context\n"); exit(1); } ost->enc = c; - /* put sample parameters */ - c->sample_fmt = codec->sample_fmts ? codec->sample_fmts[0] : AV_SAMPLE_FMT_S16; - c->sample_rate = codec->supported_samplerates ? codec->supported_samplerates[0] : 44100; - c->channel_layout = codec->channel_layouts ? codec->channel_layouts[0] : AV_CH_LAYOUT_STEREO; - c->channels = av_get_channel_layout_nb_channels(c->channel_layout); - c->bit_rate = 64000; + switch ((*codec)->type) { + case AVMEDIA_TYPE_AUDIO: + c->sample_fmt = (*codec)->sample_fmts ? + (*codec)->sample_fmts[0] : AV_SAMPLE_FMT_FLTP; + c->bit_rate = 64000; + c->sample_rate = 44100; + if ((*codec)->supported_samplerates) { + c->sample_rate = (*codec)->supported_samplerates[0]; + for (i = 0; (*codec)->supported_samplerates[i]; i++) { + if ((*codec)->supported_samplerates[i] == 44100) + c->sample_rate = 44100; + } + } + c->channels = av_get_channel_layout_nb_channels(c->channel_layout); + c->channel_layout = AV_CH_LAYOUT_STEREO; + if ((*codec)->channel_layouts) { + c->channel_layout = (*codec)->channel_layouts[0]; + for (i = 0; (*codec)->channel_layouts[i]; i++) { + if ((*codec)->channel_layouts[i] == AV_CH_LAYOUT_STEREO) + c->channel_layout = AV_CH_LAYOUT_STEREO; + } + } + c->channels = av_get_channel_layout_nb_channels(c->channel_layout); + ost->st->time_base = (AVRational){ 1, c->sample_rate }; + break; + + case AVMEDIA_TYPE_VIDEO: + c->codec_id = codec_id; + + c->bit_rate = 400000; + /* Resolution must be a multiple of two. */ + c->width = 352; + c->height = 288; + /* timebase: This is the fundamental unit of time (in seconds) in terms + * of which frame timestamps are represented. For fixed-fps content, + * timebase should be 1/framerate and timestamp increments should be + * identical to 1. */ + ost->st->time_base = (AVRational){ 1, STREAM_FRAME_RATE }; + c->time_base = ost->st->time_base; + + c->gop_size = 12; /* emit one intra frame every twelve frames at most */ + c->pix_fmt = STREAM_PIX_FMT; + if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO) { + /* just for testing, we also add B frames */ + c->max_b_frames = 2; + } + if (c->codec_id == AV_CODEC_ID_MPEG1VIDEO) { + /* Needed to avoid using macroblocks in which some coeffs overflow. + * This does not happen with normal video, it just happens here as + * the motion of the chroma plane does not match the luma plane. */ + c->mb_decision = 2; + } + break; - ost->st->time_base = (AVRational){ 1, c->sample_rate }; + default: + break; + } - // some formats want stream headers to be separate + /* Some formats want stream headers to be separate. */ if (oc->oformat->flags & AVFMT_GLOBALHEADER) c->flags |= AV_CODEC_FLAG_GLOBAL_HEADER; - - /* initialize sample format conversion; - * to simplify the code, we always pass the data through lavr, even - * if the encoder supports the generated format directly -- the price is - * some extra data copying; - */ - ost->avr = avresample_alloc_context(); - if (!ost->avr) { - fprintf(stderr, "Error allocating the resampling context\n"); - exit(1); - } - - av_opt_set_int(ost->avr, "in_sample_fmt", AV_SAMPLE_FMT_S16, 0); - av_opt_set_int(ost->avr, "in_sample_rate", 44100, 0); - av_opt_set_int(ost->avr, "in_channel_layout", AV_CH_LAYOUT_STEREO, 0); - av_opt_set_int(ost->avr, "out_sample_fmt", c->sample_fmt, 0); - av_opt_set_int(ost->avr, "out_sample_rate", c->sample_rate, 0); - av_opt_set_int(ost->avr, "out_channel_layout", c->channel_layout, 0); - - ret = avresample_open(ost->avr); - if (ret < 0) { - fprintf(stderr, "Error opening the resampling context\n"); - exit(1); - } } +/**************************************************************/ +/* audio output */ + static AVFrame *alloc_audio_frame(enum AVSampleFormat sample_fmt, uint64_t channel_layout, int sample_rate, int nb_samples) @@ -165,16 +212,21 @@ static AVFrame *alloc_audio_frame(enum AVSampleFormat sample_fmt, return frame; } -static void open_audio(AVFormatContext *oc, OutputStream *ost) +static void open_audio(AVFormatContext *oc, AVCodec *codec, OutputStream *ost, AVDictionary *opt_arg) { AVCodecContext *c; - int nb_samples, ret; + int nb_samples; + int ret; + AVDictionary *opt = NULL; c = ost->enc; /* open it */ - if (avcodec_open2(c, NULL, NULL) < 0) { - fprintf(stderr, "could not open codec\n"); + av_dict_copy(&opt, opt_arg, 0); + ret = avcodec_open2(c, codec, &opt); + av_dict_free(&opt); + if (ret < 0) { + fprintf(stderr, "Could not open audio codec: %s\n", av_err2str(ret)); exit(1); } @@ -191,8 +243,8 @@ static void open_audio(AVFormatContext *oc, OutputStream *ost) ost->frame = alloc_audio_frame(c->sample_fmt, c->channel_layout, c->sample_rate, nb_samples); - ost->tmp_frame = alloc_audio_frame(AV_SAMPLE_FMT_S16, AV_CH_LAYOUT_STEREO, - 44100, nb_samples); + ost->tmp_frame = alloc_audio_frame(AV_SAMPLE_FMT_S16, c->channel_layout, + c->sample_rate, nb_samples); /* copy the stream parameters to the muxer */ ret = avcodec_parameters_from_context(ost->st->codecpar, c); @@ -200,6 +252,27 @@ static void open_audio(AVFormatContext *oc, OutputStream *ost) fprintf(stderr, "Could not copy the stream parameters\n"); exit(1); } + + /* create resampler context */ + ost->swr_ctx = swr_alloc(); + if (!ost->swr_ctx) { + fprintf(stderr, "Could not allocate resampler context\n"); + exit(1); + } + + /* set options */ + av_opt_set_int (ost->swr_ctx, "in_channel_count", c->channels, 0); + av_opt_set_int (ost->swr_ctx, "in_sample_rate", c->sample_rate, 0); + av_opt_set_sample_fmt(ost->swr_ctx, "in_sample_fmt", AV_SAMPLE_FMT_S16, 0); + av_opt_set_int (ost->swr_ctx, "out_channel_count", c->channels, 0); + av_opt_set_int (ost->swr_ctx, "out_sample_rate", c->sample_rate, 0); + av_opt_set_sample_fmt(ost->swr_ctx, "out_sample_fmt", c->sample_fmt, 0); + + /* initialize the resampling context */ + if ((ret = swr_init(ost->swr_ctx)) < 0) { + fprintf(stderr, "Failed to initialize the resampling context\n"); + exit(1); + } } /* Prepare a 16 bit dummy audio frame of 'frame_size' samples and @@ -215,8 +288,7 @@ static AVFrame *get_audio_frame(OutputStream *ost) STREAM_DURATION, (AVRational){ 1, 1 }) >= 0) return NULL; - - for (j = 0; j < frame->nb_samples; j++) { + for (j = 0; j <frame->nb_samples; j++) { v = (int)(sin(ost->t) * 10000); for (i = 0; i < ost->enc->channels; i++) *q++ = v; @@ -224,62 +296,37 @@ static AVFrame *get_audio_frame(OutputStream *ost) ost->tincr += ost->tincr2; } - return frame; -} + frame->pts = ost->next_pts; + ost->next_pts += frame->nb_samples; -/* if a frame is provided, send it to the encoder, otherwise flush the encoder; - * return 1 when encoding is finished, 0 otherwise - */ -static int encode_audio_frame(AVFormatContext *oc, OutputStream *ost, - AVFrame *frame) -{ - AVPacket pkt = { 0 }; // data and size must be 0; - int got_packet; - - av_init_packet(&pkt); - avcodec_encode_audio2(ost->enc, &pkt, frame, &got_packet); - - if (got_packet) { - pkt.stream_index = ost->st->index; - - av_packet_rescale_ts(&pkt, ost->enc->time_base, ost->st->time_base); - - /* Write the compressed frame to the media file. */ - if (av_interleaved_write_frame(oc, &pkt) != 0) { - fprintf(stderr, "Error while writing audio frame\n"); - exit(1); - } - } - - return (frame || got_packet) ? 0 : 1; + return frame; } /* * encode one audio frame and send it to the muxer * return 1 when encoding is finished, 0 otherwise */ -static int process_audio_stream(AVFormatContext *oc, OutputStream *ost) +static int write_audio_frame(AVFormatContext *oc, OutputStream *ost) { + AVCodecContext *c; + AVPacket pkt = { 0 }; // data and size must be 0; AVFrame *frame; - int got_output = 0; int ret; + int got_packet; + int dst_nb_samples; + + av_init_packet(&pkt); + c = ost->enc; frame = get_audio_frame(ost); - got_output |= !!frame; - /* feed the data to lavr */ if (frame) { - ret = avresample_convert(ost->avr, NULL, 0, 0, - frame->extended_data, frame->linesize[0], - frame->nb_samples); - if (ret < 0) { - fprintf(stderr, "Error feeding audio data to the resampler\n"); - exit(1); - } - } + /* convert samples from native format to destination codec format, using the resampler */ + /* compute destination number of samples */ + dst_nb_samples = av_rescale_rnd(swr_get_delay(ost->swr_ctx, c->sample_rate) + frame->nb_samples, + c->sample_rate, c->sample_rate, AV_ROUND_UP); + av_assert0(dst_nb_samples == frame->nb_samples); - while ((frame && avresample_available(ost->avr) >= ost->frame->nb_samples) || - (!frame && avresample_get_out_samples(ost->avr, 0))) { /* when we pass a frame to the encoder, it may keep a reference to it * internally; * make sure we do not overwrite it here @@ -288,97 +335,41 @@ static int process_audio_stream(AVFormatContext *oc, OutputStream *ost) if (ret < 0) exit(1); - /* the difference between the two avresample calls here is that the - * first one just reads the already converted data that is buffered in - * the lavr output buffer, while the second one also flushes the - * resampler */ - if (frame) { - ret = avresample_read(ost->avr, ost->frame->extended_data, - ost->frame->nb_samples); - } else { - ret = avresample_convert(ost->avr, ost->frame->extended_data, - ost->frame->linesize[0], ost->frame->nb_samples, - NULL, 0, 0); - } + /* convert to destination format */ + ret = swr_convert(ost->swr_ctx, + ost->frame->data, dst_nb_samples, + (const uint8_t **)frame->data, frame->nb_samples); + if (ret < 0) { + fprintf(stderr, "Error while converting\n"); + exit(1); + } + frame = ost->frame; + + frame->pts = av_rescale_q(ost->samples_count, (AVRational){1, c->sample_rate}, c->time_base); + ost->samples_count += dst_nb_samples; + } + + ret = avcodec_encode_audio2(c, &pkt, frame, &got_packet); + if (ret < 0) { + fprintf(stderr, "Error encoding audio frame: %s\n", av_err2str(ret)); + exit(1); + } + if (got_packet) { + ret = write_frame(oc, &c->time_base, ost->st, &pkt); if (ret < 0) { - fprintf(stderr, "Error while resampling\n"); - exit(1); - } else if (frame && ret != ost->frame->nb_samples) { - fprintf(stderr, "Too few samples returned from lavr\n"); + fprintf(stderr, "Error while writing audio frame: %s\n", + av_err2str(ret)); exit(1); } - - ost->frame->nb_samples = ret; - - ost->frame->pts = ost->next_pts; - ost->next_pts += ost->frame->nb_samples; - - got_output |= encode_audio_frame(oc, ost, ret ? ost->frame : NULL); } - return !got_output; + return (frame || got_packet) ? 0 : 1; } /**************************************************************/ /* video output */ -/* Add a video output stream. */ -static void add_video_stream(OutputStream *ost, AVFormatContext *oc, - enum AVCodecID codec_id) -{ - AVCodecContext *c; - AVCodec *codec; - - /* find the video encoder */ - codec = avcodec_find_encoder(codec_id); - if (!codec) { - fprintf(stderr, "codec not found\n"); - exit(1); - } - - ost->st = avformat_new_stream(oc, NULL); - if (!ost->st) { - fprintf(stderr, "Could not alloc stream\n"); - exit(1); - } - - c = avcodec_alloc_context3(codec); - if (!c) { - fprintf(stderr, "Could not alloc an encoding context\n"); - exit(1); - } - ost->enc = c; - - /* Put sample parameters. */ - c->bit_rate = 400000; - /* Resolution must be a multiple of two. */ - c->width = 352; - c->height = 288; - /* timebase: This is the fundamental unit of time (in seconds) in terms - * of which frame timestamps are represented. For fixed-fps content, - * timebase should be 1/framerate and timestamp increments should be - * identical to 1. */ - ost->st->time_base = (AVRational){ 1, STREAM_FRAME_RATE }; - c->time_base = ost->st->time_base; - - c->gop_size = 12; /* emit one intra frame every twelve frames at most */ - c->pix_fmt = STREAM_PIX_FMT; - if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO) { - /* just for testing, we also add B frames */ - c->max_b_frames = 2; - } - if (c->codec_id == AV_CODEC_ID_MPEG1VIDEO) { - /* Needed to avoid using macroblocks in which some coeffs overflow. - * This does not happen with normal video, it just happens here as - * the motion of the chroma plane does not match the luma plane. */ - c->mb_decision = 2; - } - /* Some formats want stream headers to be separate. */ - if (oc->oformat->flags & AVFMT_GLOBALHEADER) - c->flags |= AV_CODEC_FLAG_GLOBAL_HEADER; -} - static AVFrame *alloc_picture(enum AVPixelFormat pix_fmt, int width, int height) { AVFrame *picture; @@ -402,23 +393,26 @@ static AVFrame *alloc_picture(enum AVPixelFormat pix_fmt, int width, int height) return picture; } -static void open_video(AVFormatContext *oc, OutputStream *ost) +static void open_video(AVFormatContext *oc, AVCodec *codec, OutputStream *ost, AVDictionary *opt_arg) { - AVCodecContext *c; int ret; + AVCodecContext *c = ost->enc; + AVDictionary *opt = NULL; - c = ost->enc; + av_dict_copy(&opt, opt_arg, 0); /* open the codec */ - if (avcodec_open2(c, NULL, NULL) < 0) { - fprintf(stderr, "could not open codec\n"); + ret = avcodec_open2(c, codec, &opt); + av_dict_free(&opt); + if (ret < 0) { + fprintf(stderr, "Could not open video codec: %s\n", av_err2str(ret)); exit(1); } - /* Allocate the encoded raw picture. */ + /* allocate and init a re-usable frame */ ost->frame = alloc_picture(c->pix_fmt, c->width, c->height); if (!ost->frame) { - fprintf(stderr, "Could not allocate picture\n"); + fprintf(stderr, "Could not allocate video frame\n"); exit(1); } @@ -492,12 +486,13 @@ static AVFrame *get_video_frame(OutputStream *ost) SCALE_FLAGS, NULL, NULL, NULL); if (!ost->sws_ctx) { fprintf(stderr, - "Cannot initialize the conversion context\n"); + "Could not initialize the conversion context\n"); exit(1); } } fill_yuv_image(ost->tmp_frame, ost->next_pts, c->width, c->height); - sws_scale(ost->sws_ctx, ost->tmp_frame->data, ost->tmp_frame->linesize, + sws_scale(ost->sws_ctx, + (const uint8_t * const *)ost->tmp_frame->data, ost->tmp_frame->linesize, 0, c->height, ost->frame->data, ost->frame->linesize); } else { fill_yuv_image(ost->frame, ost->next_pts, c->width, c->height); @@ -517,8 +512,8 @@ static int write_video_frame(AVFormatContext *oc, OutputStream *ost) int ret; AVCodecContext *c; AVFrame *frame; - AVPacket pkt = { 0 }; int got_packet = 0; + AVPacket pkt = { 0 }; c = ost->enc; @@ -529,20 +524,18 @@ static int write_video_frame(AVFormatContext *oc, OutputStream *ost) /* encode the image */ ret = avcodec_encode_video2(c, &pkt, frame, &got_packet); if (ret < 0) { - fprintf(stderr, "Error encoding a video frame\n"); + fprintf(stderr, "Error encoding video frame: %s\n", av_err2str(ret)); exit(1); } if (got_packet) { - av_packet_rescale_ts(&pkt, c->time_base, ost->st->time_base); - pkt.stream_index = ost->st->index; - - /* Write the compressed frame to the media file. */ - ret = av_interleaved_write_frame(oc, &pkt); + ret = write_frame(oc, &c->time_base, ost->st, &pkt); + } else { + ret = 0; } - if (ret != 0) { - fprintf(stderr, "Error while writing video frame\n"); + if (ret < 0) { + fprintf(stderr, "Error while writing video frame: %s\n", av_err2str(ret)); exit(1); } @@ -555,7 +548,7 @@ static void close_stream(AVFormatContext *oc, OutputStream *ost) av_frame_free(&ost->frame); av_frame_free(&ost->tmp_frame); sws_freeContext(ost->sws_ctx); - avresample_free(&ost->avr); + swr_free(&ost->swr_ctx); } /**************************************************************/ @@ -567,52 +560,51 @@ int main(int argc, char **argv) const char *filename; AVOutputFormat *fmt; AVFormatContext *oc; + AVCodec *audio_codec, *video_codec; + int ret; int have_video = 0, have_audio = 0; int encode_video = 0, encode_audio = 0; + AVDictionary *opt = NULL; /* Initialize libavcodec, and register all codecs and formats. */ av_register_all(); - if (argc != 2) { + if (argc < 2) { printf("usage: %s output_file\n" "API example program to output a media file with libavformat.\n" + "This program generates a synthetic audio and video stream, encodes and\n" + "muxes them into a file named output_file.\n" "The output format is automatically guessed according to the file extension.\n" - "Raw images can also be output by using '%%d' in the filename\n" + "Raw images can also be output by using '%%d' in the filename.\n" "\n", argv[0]); return 1; } filename = argv[1]; + if (argc > 3 && !strcmp(argv[2], "-flags")) { + av_dict_set(&opt, argv[2]+1, argv[3], 0); + } - /* Autodetect the output format from the name. default is MPEG. */ - fmt = av_guess_format(NULL, filename, NULL); - if (!fmt) { + /* allocate the output media context */ + avformat_alloc_output_context2(&oc, NULL, NULL, filename); + if (!oc) { printf("Could not deduce output format from file extension: using MPEG.\n"); - fmt = av_guess_format("mpeg", NULL, NULL); + avformat_alloc_output_context2(&oc, NULL, "mpeg", filename); } - if (!fmt) { - fprintf(stderr, "Could not find suitable output format\n"); + if (!oc) return 1; - } - /* Allocate the output media context. */ - oc = avformat_alloc_context(); - if (!oc) { - fprintf(stderr, "Memory error\n"); - return 1; - } - oc->oformat = fmt; - snprintf(oc->filename, sizeof(oc->filename), "%s", filename); + fmt = oc->oformat; /* Add the audio and video streams using the default format codecs * and initialize the codecs. */ if (fmt->video_codec != AV_CODEC_ID_NONE) { - add_video_stream(&video_st, oc, fmt->video_codec); + add_stream(&video_st, oc, &video_codec, fmt->video_codec); have_video = 1; encode_video = 1; } if (fmt->audio_codec != AV_CODEC_ID_NONE) { - add_audio_stream(&audio_st, oc, fmt->audio_codec); + add_stream(&audio_st, oc, &audio_codec, fmt->audio_codec); have_audio = 1; encode_audio = 1; } @@ -620,22 +612,30 @@ int main(int argc, char **argv) /* Now that all the parameters are set, we can open the audio and * video codecs and allocate the necessary encode buffers. */ if (have_video) - open_video(oc, &video_st); + open_video(oc, video_codec, &video_st, opt); + if (have_audio) - open_audio(oc, &audio_st); + open_audio(oc, audio_codec, &audio_st, opt); av_dump_format(oc, 0, filename, 1); /* open the output file, if needed */ if (!(fmt->flags & AVFMT_NOFILE)) { - if (avio_open(&oc->pb, filename, AVIO_FLAG_WRITE) < 0) { - fprintf(stderr, "Could not open '%s'\n", filename); + ret = avio_open(&oc->pb, filename, AVIO_FLAG_WRITE); + if (ret < 0) { + fprintf(stderr, "Could not open '%s': %s\n", filename, + av_err2str(ret)); return 1; } } /* Write the stream header, if any. */ - avformat_write_header(oc, NULL); + ret = avformat_write_header(oc, &opt); + if (ret < 0) { + fprintf(stderr, "Error occurred when opening output file: %s\n", + av_err2str(ret)); + return 1; + } while (encode_video || encode_audio) { /* select the stream to encode */ @@ -644,7 +644,7 @@ int main(int argc, char **argv) audio_st.next_pts, audio_st.enc->time_base) <= 0)) { encode_video = !write_video_frame(oc, &video_st); } else { - encode_audio = !process_audio_stream(oc, &audio_st); + encode_audio = !write_audio_frame(oc, &audio_st); } } @@ -662,7 +662,7 @@ int main(int argc, char **argv) if (!(fmt->flags & AVFMT_NOFILE)) /* Close the output file. */ - avio_close(oc->pb); + avio_closep(&oc->pb); /* free the stream */ avformat_free_context(oc); diff --git a/doc/examples/remuxing.c b/doc/examples/remuxing.c new file mode 100644 index 0000000000..65437d9abd --- /dev/null +++ b/doc/examples/remuxing.c @@ -0,0 +1,165 @@ +/* + * Copyright (c) 2013 Stefano Sabatini + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +/** + * @file + * libavformat/libavcodec demuxing and muxing API example. + * + * Remux streams from one container format to another. + * @example remuxing.c + */ + +#include <libavutil/timestamp.h> +#include <libavformat/avformat.h> + +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); +} + +int main(int argc, char **argv) +{ + AVOutputFormat *ofmt = NULL; + AVFormatContext *ifmt_ctx = NULL, *ofmt_ctx = NULL; + AVPacket pkt; + const char *in_filename, *out_filename; + int ret, i; + + if (argc < 3) { + printf("usage: %s input output\n" + "API example program to remux a media file with libavformat and libavcodec.\n" + "The output format is guessed according to the file extension.\n" + "\n", argv[0]); + return 1; + } + + in_filename = argv[1]; + out_filename = argv[2]; + + av_register_all(); + + if ((ret = avformat_open_input(&ifmt_ctx, in_filename, 0, 0)) < 0) { + fprintf(stderr, "Could not open input file '%s'", in_filename); + goto end; + } + + if ((ret = avformat_find_stream_info(ifmt_ctx, 0)) < 0) { + fprintf(stderr, "Failed to retrieve input stream information"); + goto end; + } + + av_dump_format(ifmt_ctx, 0, in_filename, 0); + + avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, out_filename); + if (!ofmt_ctx) { + fprintf(stderr, "Could not create output context\n"); + ret = AVERROR_UNKNOWN; + goto end; + } + + ofmt = ofmt_ctx->oformat; + + for (i = 0; i < ifmt_ctx->nb_streams; i++) { + AVStream *in_stream = ifmt_ctx->streams[i]; + AVStream *out_stream = avformat_new_stream(ofmt_ctx, in_stream->codec->codec); + if (!out_stream) { + fprintf(stderr, "Failed allocating output stream\n"); + ret = AVERROR_UNKNOWN; + goto end; + } + + ret = avcodec_copy_context(out_stream->codec, in_stream->codec); + if (ret < 0) { + fprintf(stderr, "Failed to copy context from input to output stream codec context\n"); + goto end; + } + out_stream->codec->codec_tag = 0; + if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER) + out_stream->codec->flags |= AV_CODEC_FLAG_GLOBAL_HEADER; + } + av_dump_format(ofmt_ctx, 0, out_filename, 1); + + if (!(ofmt->flags & AVFMT_NOFILE)) { + ret = avio_open(&ofmt_ctx->pb, out_filename, AVIO_FLAG_WRITE); + if (ret < 0) { + fprintf(stderr, "Could not open output file '%s'", out_filename); + goto end; + } + } + + ret = avformat_write_header(ofmt_ctx, NULL); + if (ret < 0) { + fprintf(stderr, "Error occurred when opening output file\n"); + goto end; + } + + while (1) { + AVStream *in_stream, *out_stream; + + ret = av_read_frame(ifmt_ctx, &pkt); + if (ret < 0) + break; + + in_stream = ifmt_ctx->streams[pkt.stream_index]; + out_stream = ofmt_ctx->streams[pkt.stream_index]; + + log_packet(ifmt_ctx, &pkt, "in"); + + /* copy packet */ + pkt.pts = av_rescale_q_rnd(pkt.pts, in_stream->time_base, out_stream->time_base, AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX); + pkt.dts = av_rescale_q_rnd(pkt.dts, in_stream->time_base, out_stream->time_base, AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX); + pkt.duration = av_rescale_q(pkt.duration, in_stream->time_base, out_stream->time_base); + pkt.pos = -1; + log_packet(ofmt_ctx, &pkt, "out"); + + ret = av_interleaved_write_frame(ofmt_ctx, &pkt); + if (ret < 0) { + fprintf(stderr, "Error muxing packet\n"); + break; + } + av_packet_unref(&pkt); + } + + av_write_trailer(ofmt_ctx); +end: + + avformat_close_input(&ifmt_ctx); + + /* close output */ + if (ofmt_ctx && !(ofmt->flags & AVFMT_NOFILE)) + avio_closep(&ofmt_ctx->pb); + avformat_free_context(ofmt_ctx); + + if (ret < 0 && ret != AVERROR_EOF) { + fprintf(stderr, "Error occurred: %s\n", av_err2str(ret)); + return 1; + } + + return 0; +} diff --git a/doc/examples/resampling_audio.c b/doc/examples/resampling_audio.c new file mode 100644 index 0000000000..f35e7e1779 --- /dev/null +++ b/doc/examples/resampling_audio.c @@ -0,0 +1,214 @@ +/* + * Copyright (c) 2012 Stefano Sabatini + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +/** + * @example resampling_audio.c + * libswresample API use example. + */ + +#include <libavutil/opt.h> +#include <libavutil/channel_layout.h> +#include <libavutil/samplefmt.h> +#include <libswresample/swresample.h> + +static int get_format_from_sample_fmt(const char **fmt, + enum AVSampleFormat sample_fmt) +{ + int i; + struct sample_fmt_entry { + enum AVSampleFormat sample_fmt; const char *fmt_be, *fmt_le; + } sample_fmt_entries[] = { + { AV_SAMPLE_FMT_U8, "u8", "u8" }, + { AV_SAMPLE_FMT_S16, "s16be", "s16le" }, + { AV_SAMPLE_FMT_S32, "s32be", "s32le" }, + { AV_SAMPLE_FMT_FLT, "f32be", "f32le" }, + { AV_SAMPLE_FMT_DBL, "f64be", "f64le" }, + }; + *fmt = NULL; + + for (i = 0; i < FF_ARRAY_ELEMS(sample_fmt_entries); i++) { + struct sample_fmt_entry *entry = &sample_fmt_entries[i]; + if (sample_fmt == entry->sample_fmt) { + *fmt = AV_NE(entry->fmt_be, entry->fmt_le); + return 0; + } + } + + fprintf(stderr, + "Sample format %s not supported as output format\n", + av_get_sample_fmt_name(sample_fmt)); + return AVERROR(EINVAL); +} + +/** + * Fill dst buffer with nb_samples, generated starting from t. + */ +static void fill_samples(double *dst, int nb_samples, int nb_channels, int sample_rate, double *t) +{ + int i, j; + double tincr = 1.0 / sample_rate, *dstp = dst; + const double c = 2 * M_PI * 440.0; + + /* generate sin tone with 440Hz frequency and duplicated channels */ + for (i = 0; i < nb_samples; i++) { + *dstp = sin(c * *t); + for (j = 1; j < nb_channels; j++) + dstp[j] = dstp[0]; + dstp += nb_channels; + *t += tincr; + } +} + +int main(int argc, char **argv) +{ + int64_t src_ch_layout = AV_CH_LAYOUT_STEREO, dst_ch_layout = AV_CH_LAYOUT_SURROUND; + int src_rate = 48000, dst_rate = 44100; + uint8_t **src_data = NULL, **dst_data = NULL; + int src_nb_channels = 0, dst_nb_channels = 0; + int src_linesize, dst_linesize; + int src_nb_samples = 1024, dst_nb_samples, max_dst_nb_samples; + enum AVSampleFormat src_sample_fmt = AV_SAMPLE_FMT_DBL, dst_sample_fmt = AV_SAMPLE_FMT_S16; + const char *dst_filename = NULL; + FILE *dst_file; + int dst_bufsize; + const char *fmt; + struct SwrContext *swr_ctx; + double t; + int ret; + + if (argc != 2) { + fprintf(stderr, "Usage: %s output_file\n" + "API example program to show how to resample an audio stream with libswresample.\n" + "This program generates a series of audio frames, resamples them to a specified " + "output format and rate and saves them to an output file named output_file.\n", + argv[0]); + exit(1); + } + dst_filename = argv[1]; + + dst_file = fopen(dst_filename, "wb"); + if (!dst_file) { + fprintf(stderr, "Could not open destination file %s\n", dst_filename); + exit(1); + } + + /* create resampler context */ + swr_ctx = swr_alloc(); + if (!swr_ctx) { + fprintf(stderr, "Could not allocate resampler context\n"); + ret = AVERROR(ENOMEM); + goto end; + } + + /* set options */ + av_opt_set_int(swr_ctx, "in_channel_layout", src_ch_layout, 0); + av_opt_set_int(swr_ctx, "in_sample_rate", src_rate, 0); + av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", src_sample_fmt, 0); + + av_opt_set_int(swr_ctx, "out_channel_layout", dst_ch_layout, 0); + av_opt_set_int(swr_ctx, "out_sample_rate", dst_rate, 0); + av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", dst_sample_fmt, 0); + + /* initialize the resampling context */ + if ((ret = swr_init(swr_ctx)) < 0) { + fprintf(stderr, "Failed to initialize the resampling context\n"); + goto end; + } + + /* allocate source and destination samples buffers */ + + src_nb_channels = av_get_channel_layout_nb_channels(src_ch_layout); + ret = av_samples_alloc_array_and_samples(&src_data, &src_linesize, src_nb_channels, + src_nb_samples, src_sample_fmt, 0); + if (ret < 0) { + fprintf(stderr, "Could not allocate source samples\n"); + goto end; + } + + /* compute the number of converted samples: buffering is avoided + * ensuring that the output buffer will contain at least all the + * converted input samples */ + max_dst_nb_samples = dst_nb_samples = + av_rescale_rnd(src_nb_samples, dst_rate, src_rate, AV_ROUND_UP); + + /* buffer is going to be directly written to a rawaudio file, no alignment */ + dst_nb_channels = av_get_channel_layout_nb_channels(dst_ch_layout); + ret = av_samples_alloc_array_and_samples(&dst_data, &dst_linesize, dst_nb_channels, + dst_nb_samples, dst_sample_fmt, 0); + if (ret < 0) { + fprintf(stderr, "Could not allocate destination samples\n"); + goto end; + } + + t = 0; + do { + /* generate synthetic audio */ + fill_samples((double *)src_data[0], src_nb_samples, src_nb_channels, src_rate, &t); + + /* compute destination number of samples */ + dst_nb_samples = av_rescale_rnd(swr_get_delay(swr_ctx, src_rate) + + src_nb_samples, dst_rate, src_rate, AV_ROUND_UP); + if (dst_nb_samples > max_dst_nb_samples) { + av_freep(&dst_data[0]); + ret = av_samples_alloc(dst_data, &dst_linesize, dst_nb_channels, + dst_nb_samples, dst_sample_fmt, 1); + if (ret < 0) + break; + max_dst_nb_samples = dst_nb_samples; + } + + /* convert to destination format */ + ret = swr_convert(swr_ctx, dst_data, dst_nb_samples, (const uint8_t **)src_data, src_nb_samples); + if (ret < 0) { + fprintf(stderr, "Error while converting\n"); + goto end; + } + dst_bufsize = av_samples_get_buffer_size(&dst_linesize, dst_nb_channels, + ret, dst_sample_fmt, 1); + if (dst_bufsize < 0) { + fprintf(stderr, "Could not get sample buffer size\n"); + goto end; + } + printf("t:%f in:%d out:%d\n", t, src_nb_samples, ret); + fwrite(dst_data[0], 1, dst_bufsize, dst_file); + } while (t < 10); + + if ((ret = get_format_from_sample_fmt(&fmt, dst_sample_fmt)) < 0) + goto end; + fprintf(stderr, "Resampling succeeded. Play the output file with the command:\n" + "ffplay -f %s -channel_layout %"PRId64" -channels %d -ar %d %s\n", + fmt, dst_ch_layout, dst_nb_channels, dst_rate, dst_filename); + +end: + fclose(dst_file); + + if (src_data) + av_freep(&src_data[0]); + av_freep(&src_data); + + if (dst_data) + av_freep(&dst_data[0]); + av_freep(&dst_data); + + swr_free(&swr_ctx); + return ret < 0; +} diff --git a/doc/examples/scaling_video.c b/doc/examples/scaling_video.c new file mode 100644 index 0000000000..587f3abe4f --- /dev/null +++ b/doc/examples/scaling_video.c @@ -0,0 +1,140 @@ +/* + * Copyright (c) 2012 Stefano Sabatini + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +/** + * @file + * libswscale API use example. + * @example scaling_video.c + */ + +#include <libavutil/imgutils.h> +#include <libavutil/parseutils.h> +#include <libswscale/swscale.h> + +static void fill_yuv_image(uint8_t *data[4], int linesize[4], + int width, int height, int frame_index) +{ + int x, y; + + /* Y */ + for (y = 0; y < height; y++) + for (x = 0; x < width; x++) + data[0][y * linesize[0] + x] = x + y + frame_index * 3; + + /* Cb and Cr */ + for (y = 0; y < height / 2; y++) { + for (x = 0; x < width / 2; x++) { + data[1][y * linesize[1] + x] = 128 + y + frame_index * 2; + data[2][y * linesize[2] + x] = 64 + x + frame_index * 5; + } + } +} + +int main(int argc, char **argv) +{ + uint8_t *src_data[4], *dst_data[4]; + int src_linesize[4], dst_linesize[4]; + int src_w = 320, src_h = 240, dst_w, dst_h; + enum AVPixelFormat src_pix_fmt = AV_PIX_FMT_YUV420P, dst_pix_fmt = AV_PIX_FMT_RGB24; + const char *dst_size = NULL; + const char *dst_filename = NULL; + FILE *dst_file; + int dst_bufsize; + struct SwsContext *sws_ctx; + int i, ret; + + if (argc != 3) { + fprintf(stderr, "Usage: %s output_file output_size\n" + "API example program to show how to scale an image with libswscale.\n" + "This program generates a series of pictures, rescales them to the given " + "output_size and saves them to an output file named output_file\n." + "\n", argv[0]); + exit(1); + } + dst_filename = argv[1]; + dst_size = argv[2]; + + if (av_parse_video_size(&dst_w, &dst_h, dst_size) < 0) { + fprintf(stderr, + "Invalid size '%s', must be in the form WxH or a valid size abbreviation\n", + dst_size); + exit(1); + } + + dst_file = fopen(dst_filename, "wb"); + if (!dst_file) { + fprintf(stderr, "Could not open destination file %s\n", dst_filename); + exit(1); + } + + /* create scaling context */ + sws_ctx = sws_getContext(src_w, src_h, src_pix_fmt, + dst_w, dst_h, dst_pix_fmt, + SWS_BILINEAR, NULL, NULL, NULL); + if (!sws_ctx) { + fprintf(stderr, + "Impossible to create scale context for the conversion " + "fmt:%s s:%dx%d -> fmt:%s s:%dx%d\n", + av_get_pix_fmt_name(src_pix_fmt), src_w, src_h, + av_get_pix_fmt_name(dst_pix_fmt), dst_w, dst_h); + ret = AVERROR(EINVAL); + goto end; + } + + /* allocate source and destination image buffers */ + if ((ret = av_image_alloc(src_data, src_linesize, + src_w, src_h, src_pix_fmt, 16)) < 0) { + fprintf(stderr, "Could not allocate source image\n"); + goto end; + } + + /* buffer is going to be written to rawvideo file, no alignment */ + if ((ret = av_image_alloc(dst_data, dst_linesize, + dst_w, dst_h, dst_pix_fmt, 1)) < 0) { + fprintf(stderr, "Could not allocate destination image\n"); + goto end; + } + dst_bufsize = ret; + + for (i = 0; i < 100; i++) { + /* generate synthetic video */ + fill_yuv_image(src_data, src_linesize, src_w, src_h, i); + + /* convert to destination format */ + sws_scale(sws_ctx, (const uint8_t * const*)src_data, + src_linesize, 0, src_h, dst_data, dst_linesize); + + /* write scaled image to file */ + fwrite(dst_data[0], 1, dst_bufsize, dst_file); + } + + fprintf(stderr, "Scaling succeeded. Play the output file with the command:\n" + "ffplay -f rawvideo -pix_fmt %s -video_size %dx%d %s\n", + av_get_pix_fmt_name(dst_pix_fmt), dst_w, dst_h, dst_filename); + +end: + fclose(dst_file); + av_freep(&src_data[0]); + av_freep(&dst_data[0]); + sws_freeContext(sws_ctx); + return ret < 0; +} diff --git a/doc/examples/transcode_aac.c b/doc/examples/transcode_aac.c index 3eebfb9d02..486e54c281 100644 --- a/doc/examples/transcode_aac.c +++ b/doc/examples/transcode_aac.c @@ -1,18 +1,18 @@ /* - * This file is part of Libav. + * This file is part of FFmpeg. * - * Libav is free software; you can redistribute it and/or + * FFmpeg is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * - * Libav is distributed in the hope that it will be useful, + * FFmpeg is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with Libav; if not, write to the Free Software + * License along with FFmpeg; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA */ @@ -21,7 +21,7 @@ * simple audio converter * * @example transcode_aac.c - * Convert an input audio file to AAC in an MP4 container using Libav. + * Convert an input audio file to AAC in an MP4 container using FFmpeg. * @author Andreas Unterweger (dustsigns@gmail.com) */ @@ -33,11 +33,12 @@ #include "libavcodec/avcodec.h" #include "libavutil/audio_fifo.h" +#include "libavutil/avassert.h" #include "libavutil/avstring.h" #include "libavutil/frame.h" #include "libavutil/opt.h" -#include "libavresample/avresample.h" +#include "libswresample/swresample.h" /** The output bit rate in kbit/s */ #define OUTPUT_BIT_RATE 96000 @@ -49,7 +50,7 @@ * @param error Error code to be converted * @return Corresponding error text (not thread-safe) */ -static char *const get_error_text(const int error) +static const char *get_error_text(const int error) { static char error_buffer[255]; av_strerror(error, error_buffer, sizeof(error_buffer)); @@ -203,7 +204,7 @@ static int open_output_file(const char *filename, return 0; cleanup: - avio_close((*output_format_context)->pb); + avio_closep(&(*output_format_context)->pb); avformat_free_context(*output_format_context); *output_format_context = NULL; return error < 0 ? error : AVERROR_EXIT; @@ -231,52 +232,46 @@ static int init_input_frame(AVFrame **frame) /** * Initialize the audio resampler based on the input and output codec settings. * If the input and output sample formats differ, a conversion is required - * libavresample takes care of this, but requires initialization. + * libswresample takes care of this, but requires initialization. */ static int init_resampler(AVCodecContext *input_codec_context, AVCodecContext *output_codec_context, - AVAudioResampleContext **resample_context) + SwrContext **resample_context) { - /** - * Only initialize the resampler if it is necessary, i.e., - * if and only if the sample formats differ. - */ - if (input_codec_context->sample_fmt != output_codec_context->sample_fmt || - input_codec_context->channels != output_codec_context->channels) { int error; - /** Create a resampler context for the conversion. */ - if (!(*resample_context = avresample_alloc_context())) { - fprintf(stderr, "Could not allocate resample context\n"); - return AVERROR(ENOMEM); - } - /** + * Create a resampler context for the conversion. * Set the conversion parameters. * Default channel layouts based on the number of channels * are assumed for simplicity (they are sometimes not detected * properly by the demuxer and/or decoder). */ - av_opt_set_int(*resample_context, "in_channel_layout", - av_get_default_channel_layout(input_codec_context->channels), 0); - av_opt_set_int(*resample_context, "out_channel_layout", - av_get_default_channel_layout(output_codec_context->channels), 0); - av_opt_set_int(*resample_context, "in_sample_rate", - input_codec_context->sample_rate, 0); - av_opt_set_int(*resample_context, "out_sample_rate", - output_codec_context->sample_rate, 0); - av_opt_set_int(*resample_context, "in_sample_fmt", - input_codec_context->sample_fmt, 0); - av_opt_set_int(*resample_context, "out_sample_fmt", - output_codec_context->sample_fmt, 0); + *resample_context = swr_alloc_set_opts(NULL, + av_get_default_channel_layout(output_codec_context->channels), + output_codec_context->sample_fmt, + output_codec_context->sample_rate, + av_get_default_channel_layout(input_codec_context->channels), + input_codec_context->sample_fmt, + input_codec_context->sample_rate, + 0, NULL); + if (!*resample_context) { + fprintf(stderr, "Could not allocate resample context\n"); + return AVERROR(ENOMEM); + } + /** + * Perform a sanity check so that the number of converted samples is + * not greater than the number of samples to be converted. + * If the sample rates differ, this case has to be handled differently + */ + av_assert0(output_codec_context->sample_rate == input_codec_context->sample_rate); /** Open the resampler with the specified parameters. */ - if ((error = avresample_open(*resample_context)) < 0) { + if ((error = swr_init(*resample_context)) < 0) { fprintf(stderr, "Could not open resample context\n"); - avresample_free(resample_context); + swr_free(resample_context); return error; } - } return 0; } @@ -317,7 +312,7 @@ static int decode_audio_frame(AVFrame *frame, /** Read one audio frame from the input file into a temporary packet. */ if ((error = av_read_frame(input_format_context, &input_packet)) < 0) { - /** If we are the the end of the file, flush the decoder below. */ + /** If we are at the end of the file, flush the decoder below. */ if (error == AVERROR_EOF) *finished = 1; else { @@ -396,30 +391,21 @@ static int init_converted_samples(uint8_t ***converted_input_samples, * The conversion happens on a per-frame basis, the size of which is specified * by frame_size. */ -static int convert_samples(uint8_t **input_data, +static int convert_samples(const uint8_t **input_data, uint8_t **converted_data, const int frame_size, - AVAudioResampleContext *resample_context) + SwrContext *resample_context) { int error; /** Convert the samples using the resampler. */ - if ((error = avresample_convert(resample_context, converted_data, 0, - frame_size, input_data, 0, frame_size)) < 0) { + if ((error = swr_convert(resample_context, + converted_data, frame_size, + input_data , frame_size)) < 0) { fprintf(stderr, "Could not convert input samples (error '%s')\n", get_error_text(error)); return error; } - /** - * Perform a sanity check so that the number of converted samples is - * not greater than the number of samples to be converted. - * If the sample rates differ, this case has to be handled differently - */ - if (avresample_available(resample_context)) { - fprintf(stderr, "Converted samples left over\n"); - return AVERROR_EXIT; - } - return 0; } @@ -456,7 +442,7 @@ static int read_decode_convert_and_store(AVAudioFifo *fifo, AVFormatContext *input_format_context, AVCodecContext *input_codec_context, AVCodecContext *output_codec_context, - AVAudioResampleContext *resampler_context, + SwrContext *resampler_context, int *finished) { /** Temporary storage of the input samples of the frame read from the file. */ @@ -493,7 +479,7 @@ static int read_decode_convert_and_store(AVAudioFifo *fifo, * Convert the input samples to the desired output sample format. * This requires a temporary storage provided by converted_input_samples. */ - if (convert_samples(input_frame->extended_data, converted_input_samples, + if (convert_samples((const uint8_t**)input_frame->extended_data, converted_input_samples, input_frame->nb_samples, resampler_context)) goto cleanup; @@ -664,7 +650,7 @@ int main(int argc, char **argv) { AVFormatContext *input_format_context = NULL, *output_format_context = NULL; AVCodecContext *input_codec_context = NULL, *output_codec_context = NULL; - AVAudioResampleContext *resample_context = NULL; + SwrContext *resample_context = NULL; AVAudioFifo *fifo = NULL; int ret = AVERROR_EXIT; @@ -768,14 +754,11 @@ int main(int argc, char **argv) cleanup: if (fifo) av_audio_fifo_free(fifo); - if (resample_context) { - avresample_close(resample_context); - avresample_free(&resample_context); - } + swr_free(&resample_context); if (output_codec_context) avcodec_close(output_codec_context); if (output_format_context) { - avio_close(output_format_context->pb); + avio_closep(&output_format_context->pb); avformat_free_context(output_format_context); } if (input_codec_context) diff --git a/doc/examples/transcoding.c b/doc/examples/transcoding.c new file mode 100644 index 0000000000..d5d410b168 --- /dev/null +++ b/doc/examples/transcoding.c @@ -0,0 +1,582 @@ +/* + * Copyright (c) 2010 Nicolas George + * Copyright (c) 2011 Stefano Sabatini + * Copyright (c) 2014 Andrey Utkin + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +/** + * @file + * API example for demuxing, decoding, filtering, encoding and muxing + * @example transcoding.c + */ + +#include <libavcodec/avcodec.h> +#include <libavformat/avformat.h> +#include <libavfilter/avfiltergraph.h> +#include <libavfilter/buffersink.h> +#include <libavfilter/buffersrc.h> +#include <libavutil/opt.h> +#include <libavutil/pixdesc.h> + +static AVFormatContext *ifmt_ctx; +static AVFormatContext *ofmt_ctx; +typedef struct FilteringContext { + AVFilterContext *buffersink_ctx; + AVFilterContext *buffersrc_ctx; + AVFilterGraph *filter_graph; +} FilteringContext; +static FilteringContext *filter_ctx; + +static int open_input_file(const char *filename) +{ + int ret; + unsigned int i; + + ifmt_ctx = NULL; + if ((ret = avformat_open_input(&ifmt_ctx, filename, NULL, NULL)) < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n"); + return ret; + } + + if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n"); + return ret; + } + + for (i = 0; i < ifmt_ctx->nb_streams; i++) { + AVStream *stream; + AVCodecContext *codec_ctx; + stream = ifmt_ctx->streams[i]; + codec_ctx = stream->codec; + /* Reencode video & audio and remux subtitles etc. */ + if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO + || codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) { + /* Open decoder */ + ret = avcodec_open2(codec_ctx, + avcodec_find_decoder(codec_ctx->codec_id), NULL); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i); + return ret; + } + } + } + + av_dump_format(ifmt_ctx, 0, filename, 0); + return 0; +} + +static int open_output_file(const char *filename) +{ + AVStream *out_stream; + AVStream *in_stream; + AVCodecContext *dec_ctx, *enc_ctx; + AVCodec *encoder; + int ret; + unsigned int i; + + ofmt_ctx = NULL; + avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, filename); + if (!ofmt_ctx) { + av_log(NULL, AV_LOG_ERROR, "Could not create output context\n"); + return AVERROR_UNKNOWN; + } + + + for (i = 0; i < ifmt_ctx->nb_streams; i++) { + out_stream = avformat_new_stream(ofmt_ctx, NULL); + if (!out_stream) { + av_log(NULL, AV_LOG_ERROR, "Failed allocating output stream\n"); + return AVERROR_UNKNOWN; + } + + in_stream = ifmt_ctx->streams[i]; + dec_ctx = in_stream->codec; + enc_ctx = out_stream->codec; + + if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO + || dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) { + /* in this example, we choose transcoding to same codec */ + encoder = avcodec_find_encoder(dec_ctx->codec_id); + if (!encoder) { + av_log(NULL, AV_LOG_FATAL, "Necessary encoder not found\n"); + return AVERROR_INVALIDDATA; + } + + /* In this example, we transcode to same properties (picture size, + * sample rate etc.). These properties can be changed for output + * streams easily using filters */ + if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) { + enc_ctx->height = dec_ctx->height; + enc_ctx->width = dec_ctx->width; + enc_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio; + /* take first format from list of supported formats */ + enc_ctx->pix_fmt = encoder->pix_fmts[0]; + /* video time_base can be set to whatever is handy and supported by encoder */ + enc_ctx->time_base = dec_ctx->time_base; + } else { + enc_ctx->sample_rate = dec_ctx->sample_rate; + enc_ctx->channel_layout = dec_ctx->channel_layout; + enc_ctx->channels = av_get_channel_layout_nb_channels(enc_ctx->channel_layout); + /* take first format from list of supported formats */ + enc_ctx->sample_fmt = encoder->sample_fmts[0]; + enc_ctx->time_base = (AVRational){1, enc_ctx->sample_rate}; + } + + /* Third parameter can be used to pass settings to encoder */ + ret = avcodec_open2(enc_ctx, encoder, NULL); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot open video encoder for stream #%u\n", i); + return ret; + } + } else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) { + av_log(NULL, AV_LOG_FATAL, "Elementary stream #%d is of unknown type, cannot proceed\n", i); + return AVERROR_INVALIDDATA; + } else { + /* if this stream must be remuxed */ + ret = avcodec_copy_context(ofmt_ctx->streams[i]->codec, + ifmt_ctx->streams[i]->codec); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Copying stream context failed\n"); + return ret; + } + } + + if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER) + enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER; + + } + av_dump_format(ofmt_ctx, 0, filename, 1); + + if (!(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) { + ret = avio_open(&ofmt_ctx->pb, filename, AVIO_FLAG_WRITE); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Could not open output file '%s'", filename); + return ret; + } + } + + /* init muxer, write output file header */ + ret = avformat_write_header(ofmt_ctx, NULL); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Error occurred when opening output file\n"); + return ret; + } + + return 0; +} + +static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx, + AVCodecContext *enc_ctx, const char *filter_spec) +{ + char args[512]; + int ret = 0; + AVFilter *buffersrc = NULL; + AVFilter *buffersink = NULL; + AVFilterContext *buffersrc_ctx = NULL; + AVFilterContext *buffersink_ctx = NULL; + AVFilterInOut *outputs = avfilter_inout_alloc(); + AVFilterInOut *inputs = avfilter_inout_alloc(); + AVFilterGraph *filter_graph = avfilter_graph_alloc(); + + if (!outputs || !inputs || !filter_graph) { + ret = AVERROR(ENOMEM); + goto end; + } + + if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) { + buffersrc = avfilter_get_by_name("buffer"); + buffersink = avfilter_get_by_name("buffersink"); + if (!buffersrc || !buffersink) { + av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n"); + ret = AVERROR_UNKNOWN; + goto end; + } + + snprintf(args, sizeof(args), + "video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d", + dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt, + dec_ctx->time_base.num, dec_ctx->time_base.den, + dec_ctx->sample_aspect_ratio.num, + dec_ctx->sample_aspect_ratio.den); + + ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in", + args, NULL, filter_graph); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot create buffer source\n"); + goto end; + } + + ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out", + NULL, NULL, filter_graph); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot create buffer sink\n"); + goto end; + } + + ret = av_opt_set_bin(buffersink_ctx, "pix_fmts", + (uint8_t*)&enc_ctx->pix_fmt, sizeof(enc_ctx->pix_fmt), + AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n"); + goto end; + } + } else if (dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) { + buffersrc = avfilter_get_by_name("abuffer"); + buffersink = avfilter_get_by_name("abuffersink"); + if (!buffersrc || !buffersink) { + av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n"); + ret = AVERROR_UNKNOWN; + goto end; + } + + if (!dec_ctx->channel_layout) + dec_ctx->channel_layout = + av_get_default_channel_layout(dec_ctx->channels); + 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, NULL, filter_graph); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer source\n"); + goto end; + } + + ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out", + NULL, NULL, filter_graph); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer sink\n"); + goto end; + } + + ret = av_opt_set_bin(buffersink_ctx, "sample_fmts", + (uint8_t*)&enc_ctx->sample_fmt, sizeof(enc_ctx->sample_fmt), + AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot set output sample format\n"); + goto end; + } + + ret = av_opt_set_bin(buffersink_ctx, "channel_layouts", + (uint8_t*)&enc_ctx->channel_layout, + sizeof(enc_ctx->channel_layout), AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot set output channel layout\n"); + goto end; + } + + ret = av_opt_set_bin(buffersink_ctx, "sample_rates", + (uint8_t*)&enc_ctx->sample_rate, sizeof(enc_ctx->sample_rate), + AV_OPT_SEARCH_CHILDREN); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Cannot set output sample rate\n"); + goto end; + } + } else { + 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 = NULL; + + inputs->name = av_strdup("out"); + inputs->filter_ctx = buffersink_ctx; + inputs->pad_idx = 0; + inputs->next = NULL; + + if (!outputs->name || !inputs->name) { + ret = AVERROR(ENOMEM); + goto end; + } + + if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec, + &inputs, &outputs, NULL)) < 0) + goto end; + + if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0) + goto end; + + /* Fill FilteringContext */ + fctx->buffersrc_ctx = buffersrc_ctx; + fctx->buffersink_ctx = buffersink_ctx; + fctx->filter_graph = filter_graph; + +end: + avfilter_inout_free(&inputs); + avfilter_inout_free(&outputs); + + return ret; +} + +static int init_filters(void) +{ + const char *filter_spec; + unsigned int i; + int ret; + filter_ctx = av_malloc_array(ifmt_ctx->nb_streams, sizeof(*filter_ctx)); + if (!filter_ctx) + return AVERROR(ENOMEM); + + for (i = 0; i < ifmt_ctx->nb_streams; i++) { + filter_ctx[i].buffersrc_ctx = NULL; + filter_ctx[i].buffersink_ctx = NULL; + filter_ctx[i].filter_graph = NULL; + if (!(ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO + || ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO)) + continue; + + + if (ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO) + filter_spec = "null"; /* passthrough (dummy) filter for video */ + else + filter_spec = "anull"; /* passthrough (dummy) filter for audio */ + ret = init_filter(&filter_ctx[i], ifmt_ctx->streams[i]->codec, + ofmt_ctx->streams[i]->codec, filter_spec); + if (ret) + return ret; + } + return 0; +} + +static int encode_write_frame(AVFrame *filt_frame, unsigned int stream_index, int *got_frame) { + int ret; + int got_frame_local; + AVPacket enc_pkt; + int (*enc_func)(AVCodecContext *, AVPacket *, const AVFrame *, int *) = + (ifmt_ctx->streams[stream_index]->codec->codec_type == + AVMEDIA_TYPE_VIDEO) ? avcodec_encode_video2 : avcodec_encode_audio2; + + if (!got_frame) + got_frame = &got_frame_local; + + av_log(NULL, AV_LOG_INFO, "Encoding frame\n"); + /* encode filtered frame */ + enc_pkt.data = NULL; + enc_pkt.size = 0; + av_init_packet(&enc_pkt); + ret = enc_func(ofmt_ctx->streams[stream_index]->codec, &enc_pkt, + filt_frame, got_frame); + av_frame_free(&filt_frame); + if (ret < 0) + return ret; + if (!(*got_frame)) + return 0; + + /* prepare packet for muxing */ + enc_pkt.stream_index = stream_index; + av_packet_rescale_ts(&enc_pkt, + ofmt_ctx->streams[stream_index]->codec->time_base, + ofmt_ctx->streams[stream_index]->time_base); + + av_log(NULL, AV_LOG_DEBUG, "Muxing frame\n"); + /* mux encoded frame */ + ret = av_interleaved_write_frame(ofmt_ctx, &enc_pkt); + return ret; +} + +static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index) +{ + int ret; + AVFrame *filt_frame; + + av_log(NULL, AV_LOG_INFO, "Pushing decoded frame to filters\n"); + /* push the decoded frame into the filtergraph */ + ret = av_buffersrc_add_frame_flags(filter_ctx[stream_index].buffersrc_ctx, + frame, 0); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n"); + return ret; + } + + /* pull filtered frames from the filtergraph */ + while (1) { + filt_frame = av_frame_alloc(); + if (!filt_frame) { + ret = AVERROR(ENOMEM); + break; + } + av_log(NULL, AV_LOG_INFO, "Pulling filtered frame from filters\n"); + ret = av_buffersink_get_frame(filter_ctx[stream_index].buffersink_ctx, + filt_frame); + if (ret < 0) { + /* if no more frames for output - returns AVERROR(EAGAIN) + * if flushed and no more frames for output - returns AVERROR_EOF + * rewrite retcode to 0 to show it as normal procedure completion + */ + if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) + ret = 0; + av_frame_free(&filt_frame); + break; + } + + filt_frame->pict_type = AV_PICTURE_TYPE_NONE; + ret = encode_write_frame(filt_frame, stream_index, NULL); + if (ret < 0) + break; + } + + return ret; +} + +static int flush_encoder(unsigned int stream_index) +{ + int ret; + int got_frame; + + if (!(ofmt_ctx->streams[stream_index]->codec->codec->capabilities & + AV_CODEC_CAP_DELAY)) + return 0; + + while (1) { + av_log(NULL, AV_LOG_INFO, "Flushing stream #%u encoder\n", stream_index); + ret = encode_write_frame(NULL, stream_index, &got_frame); + if (ret < 0) + break; + if (!got_frame) + return 0; + } + return ret; +} + +int main(int argc, char **argv) +{ + int ret; + AVPacket packet = { .data = NULL, .size = 0 }; + AVFrame *frame = NULL; + enum AVMediaType type; + unsigned int stream_index; + unsigned int i; + int got_frame; + int (*dec_func)(AVCodecContext *, AVFrame *, int *, const AVPacket *); + + if (argc != 3) { + av_log(NULL, AV_LOG_ERROR, "Usage: %s <input file> <output file>\n", argv[0]); + return 1; + } + + av_register_all(); + avfilter_register_all(); + + if ((ret = open_input_file(argv[1])) < 0) + goto end; + if ((ret = open_output_file(argv[2])) < 0) + goto end; + if ((ret = init_filters()) < 0) + goto end; + + /* read all packets */ + while (1) { + if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0) + break; + stream_index = packet.stream_index; + type = ifmt_ctx->streams[packet.stream_index]->codec->codec_type; + av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n", + stream_index); + + if (filter_ctx[stream_index].filter_graph) { + av_log(NULL, AV_LOG_DEBUG, "Going to reencode&filter the frame\n"); + frame = av_frame_alloc(); + if (!frame) { + ret = AVERROR(ENOMEM); + break; + } + av_packet_rescale_ts(&packet, + ifmt_ctx->streams[stream_index]->time_base, + ifmt_ctx->streams[stream_index]->codec->time_base); + dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 : + avcodec_decode_audio4; + ret = dec_func(ifmt_ctx->streams[stream_index]->codec, frame, + &got_frame, &packet); + if (ret < 0) { + av_frame_free(&frame); + av_log(NULL, AV_LOG_ERROR, "Decoding failed\n"); + break; + } + + if (got_frame) { + frame->pts = av_frame_get_best_effort_timestamp(frame); + ret = filter_encode_write_frame(frame, stream_index); + av_frame_free(&frame); + if (ret < 0) + goto end; + } else { + av_frame_free(&frame); + } + } else { + /* remux this frame without reencoding */ + av_packet_rescale_ts(&packet, + ifmt_ctx->streams[stream_index]->time_base, + ofmt_ctx->streams[stream_index]->time_base); + + ret = av_interleaved_write_frame(ofmt_ctx, &packet); + if (ret < 0) + goto end; + } + av_packet_unref(&packet); + } + + /* flush filters and encoders */ + for (i = 0; i < ifmt_ctx->nb_streams; i++) { + /* flush filter */ + if (!filter_ctx[i].filter_graph) + continue; + ret = filter_encode_write_frame(NULL, i); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Flushing filter failed\n"); + goto end; + } + + /* flush encoder */ + ret = flush_encoder(i); + if (ret < 0) { + av_log(NULL, AV_LOG_ERROR, "Flushing encoder failed\n"); + goto end; + } + } + + av_write_trailer(ofmt_ctx); +end: + av_packet_unref(&packet); + av_frame_free(&frame); + for (i = 0; i < ifmt_ctx->nb_streams; i++) { + avcodec_close(ifmt_ctx->streams[i]->codec); + if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && ofmt_ctx->streams[i]->codec) + avcodec_close(ofmt_ctx->streams[i]->codec); + if (filter_ctx && filter_ctx[i].filter_graph) + avfilter_graph_free(&filter_ctx[i].filter_graph); + } + av_free(filter_ctx); + avformat_close_input(&ifmt_ctx); + if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) + avio_closep(&ofmt_ctx->pb); + avformat_free_context(ofmt_ctx); + + if (ret < 0) + av_log(NULL, AV_LOG_ERROR, "Error occurred: %s\n", av_err2str(ret)); + + return ret ? 1 : 0; +} |