[FFmpeg-devel] [PATCH 2/2] doc/examples: add audio decoding/filtering example.
Nicolas George
nicolas.george at normalesup.org
Mon Feb 20 18:45:27 CET 2012
Le duodi 2 ventôse, an CCXX, Clément Bœsch a écrit :
> doc/examples/Makefile | 2 +-
> doc/examples/filtering-audio.c | 244 ++++++++++++++++++++++++++++++++++++++++
> 2 files changed, 245 insertions(+), 1 deletions(-)
> create mode 100644 doc/examples/filtering-audio.c
Good idea.
>
> diff --git a/doc/examples/Makefile b/doc/examples/Makefile
> index b4d299f..135fa95 100644
> --- a/doc/examples/Makefile
> +++ b/doc/examples/Makefile
> @@ -3,7 +3,7 @@ FFMPEG_LIBS=libavdevice libavformat libavfilter libavcodec libswscale libavutil
> CFLAGS+=-Wall $(shell pkg-config --cflags $(FFMPEG_LIBS))
> LDFLAGS+=$(shell pkg-config --libs $(FFMPEG_LIBS))
>
> -EXAMPLES=decoding_encoding filtering metadata muxing
> +EXAMPLES=decoding_encoding filtering filtering-audio metadata muxing
Aren't we being inconsistent with dashes and underscores?
>
> OBJS=$(addsuffix .o,$(EXAMPLES))
>
> diff --git a/doc/examples/filtering-audio.c b/doc/examples/filtering-audio.c
> new file mode 100644
> index 0000000..738b186
> --- /dev/null
> +++ b/doc/examples/filtering-audio.c
> @@ -0,0 +1,244 @@
> +/*
> + * 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
> + */
> +
> +#include <unistd.h>
> +
> +#include <libavcodec/avcodec.h>
> +#include <libavformat/avformat.h>
> +#include <libavfilter/asrc_abuffer.h>
> +#include <libavfilter/avfiltergraph.h>
> +#include <libavfilter/avcodec.h>
> +#include <libavfilter/buffersink.h>
> +
> +const char *filter_descr = "aresample=8000,aconvert=s16:mono";
> +const char *player = "ffplay -f s16le -ar 8000 -ac 1 -i /dev/stdin";
For ffplay, I believe "-" works too, and may be more portable. And the -i is
not necessary.
> +
> +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 a audio stream in the input file\n");
> + return ret;
> + }
> + audio_stream_index = ret;
> + dec_ctx = fmt_ctx->streams[audio_stream_index]->codec;
> +
> + /* 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;
> + AVFilter *buffersrc = avfilter_get_by_name("abuffer");
> + AVFilter *buffersink = avfilter_get_by_name("abuffersink");
> + AVFilterInOut *outputs = avfilter_inout_alloc();
> + AVFilterInOut *inputs = avfilter_inout_alloc();
> + const enum AVSampleFormat sample_fmts[] = { AV_SAMPLE_FMT_S16, -1 };
> + const int packing_fmts[] = { AVFILTER_PACKED, -1 };
> + const int64_t *chlayouts = avfilter_all_channel_layouts;
> + AVABufferSinkParams *abuffersink_params;
Some of the variables use the exact name "abuffer...", some use only
"buffer", this is slightly inconsistent.
> + const AVFilterLink *outlink;
> +
> + filter_graph = avfilter_graph_alloc();
> +
> + /* 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), "%d:%d:0x%"PRIx64":packed",
> + dec_ctx->sample_rate, 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");
> + return ret;
> + }
> +
> + /* buffer audio sink: to terminate the filter chain. */
> + abuffersink_params = av_abuffersink_params_alloc();
> + abuffersink_params->sample_fmts = sample_fmts;
> + abuffersink_params->channel_layouts = chlayouts;
> + abuffersink_params->packing_fmts = packing_fmts;
> + ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
> + NULL, abuffersink_params, filter_graph);
As a matter of curiosity, is there a reason to use a string argument for
abuffersrc and a structured parameter for abuffersink?
> + if (ret < 0) {
> + av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer sink\n");
> + return ret;
> + }
> +
> + /* 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 ((ret = avfilter_graph_parse(filter_graph, filter_descr,
> + &inputs, &outputs, NULL)) < 0)
> + return ret;
> +
> + if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
> + return ret;
> +
> + outlink = buffersink_ctx->inputs[0];
> + // abuse args buffer to store channel layout string
"reuse", maybe? And while I am nitpicking, the comment style is
inconsistent.
> + 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);
> +
> + return 0;
> +}
> +
> +static void print_samplesref(AVFilterBufferRef *samplesref)
> +{
> + const AVFilterBufferRefAudioProps *props = samplesref->audio;
> + const int n = props->nb_samples * av_get_channel_layout_nb_channels(props->channel_layout);
> + const uint16_t *p = (uint16_t*)samplesref->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 packet;
> + AVFrame frame;
> + int got_frame;
> +
> + if (argc != 2) {
> + fprintf(stderr, "Usage: %s file | %s\n", argv[0], player);
> + exit(1);
> + }
> +
> + avcodec_register_all();
> + 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) {
> + AVFilterBufferRef *samplesref;
> + if ((ret = av_read_frame(fmt_ctx, &packet)) < 0)
> + break;
> +
> + if (packet.stream_index == audio_stream_index) {
> + avcodec_get_frame_defaults(&frame);
> + got_frame = 0;
> + ret = avcodec_decode_audio4(dec_ctx, &frame, &got_frame, &packet);
> + av_free_packet(&packet);
> + if (ret < 0) {
> + av_log(NULL, AV_LOG_ERROR, "Error decoding audio\n");
> + break;
> + }
> +
> + if (got_frame) {
> + const int bps = av_get_bytes_per_sample(dec_ctx->sample_fmt);
> + const int decoded_data_size = frame.nb_samples * dec_ctx->channels * bps;
> +
> + /* push the audio data from decoded frame into the filtergraph */
> + if (av_asrc_buffer_add_buffer(buffersrc_ctx,
> + frame.data[0],
> + decoded_data_size,
> + dec_ctx->sample_rate,
> + dec_ctx->sample_fmt,
> + dec_ctx->channel_layout,
> + 0, frame.pts, 0) < 0) {
> + av_log(NULL, AV_LOG_ERROR, "Error while feeding the audio filtergraph\n");
> + exit(1);
Is there a reason to use exit here while the other places use break or goto?
> + }
> +
> + /* pull filtered pictures from the filtergraph */
> + while (avfilter_poll_frame(buffersink_ctx->inputs[0])) {
> + av_buffersink_get_buffer_ref(buffersink_ctx, &samplesref, 0);
> + if (samplesref) {
> + print_samplesref(samplesref);
> + avfilter_unref_buffer(samplesref);
> + }
> + }
> + }
> + }
> + }
> +end:
> + avfilter_graph_free(&filter_graph);
> + if (dec_ctx)
> + avcodec_close(dec_ctx);
> + avformat_close_input(&fmt_ctx);
> +
> + if (ret < 0 && ret != AVERROR_EOF) {
> + char buf[1024];
> + av_strerror(ret, buf, sizeof(buf));
> + fprintf(stderr, "Error occurred: %s\n", buf);
> + exit(1);
> + }
> +
> + exit(0);
> +}
Apart from these little details, it seems really useful.
Regards,
--
Nicolas George
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 198 bytes
Desc: Digital signature
URL: <http://ffmpeg.org/pipermail/ffmpeg-devel/attachments/20120220/42c606bb/attachment.asc>
More information about the ffmpeg-devel
mailing list