diff mbox series

[FFmpeg-devel,v3,GSOC] avfilter: add atone filter

Message ID 20200317161927.18980-1-marshallmax1991@gmail.com
State New
Headers show
Series [FFmpeg-devel,v3,GSOC] avfilter: add atone filter
Related show

Checks

Context Check Description
andriy/ffmpeg-patchwork pending
andriy/ffmpeg-patchwork success Applied patch
andriy/ffmpeg-patchwork success Configure finished
andriy/ffmpeg-patchwork success Make finished
andriy/ffmpeg-patchwork success Make fate finished

Commit Message

Marshall Murmu March 17, 2020, 4:19 p.m. UTC
I hope this one's simple enough
---
 Changelog                |   1 +
 configure                |   4 +
 doc/filters.texi         |  29 ++++++
 libavfilter/Makefile     |   1 +
 libavfilter/allfilters.c |   1 +
 libavfilter/asrc_atone.c | 188 +++++++++++++++++++++++++++++++++++++++
 libavfilter/version.h    |   2 +-
 7 files changed, 225 insertions(+), 1 deletion(-)
 create mode 100644 libavfilter/asrc_atone.c

Comments

Paul B Mahol March 17, 2020, 5:46 p.m. UTC | #1
On 3/17/20, Marshall Murmu <marshallmax1991@gmail.com> wrote:
>  I hope this one's simple enough

It is not simple at all. How do you plan to extend it and add other
instruments and so on later?

Use some state variable, which will hold current number of samples
outputted per tone and use loops.

There is filter private context exactly for that.
diff mbox series

Patch

diff --git a/Changelog b/Changelog
index 711861bda9..7888ffc7fb 100644
--- a/Changelog
+++ b/Changelog
@@ -54,6 +54,7 @@  version <next>:
 - DERF demuxer
 - CRI HCA decoder
 - CRI HCA demuxer
+- atone filter
 
 
 version 4.2:
diff --git a/configure b/configure
index 18f2841765..b083ac6453 100755
--- a/configure
+++ b/configure
@@ -233,6 +233,7 @@  External library support:
                            and libraw1394 [no]
   --enable-libfdk-aac      enable AAC de/encoding via libfdk-aac [no]
   --enable-libflite        enable flite (voice synthesis) support via libflite [no]
+  --enable-libfluidsynth   enable fluidsynth support via libfluidsynth [no]
   --enable-libfontconfig   enable libfontconfig, useful for drawtext filter [no]
   --enable-libfreetype     enable libfreetype, needed for drawtext filter [no]
   --enable-libfribidi      enable libfribidi, improves drawtext filter [no]
@@ -1770,6 +1771,7 @@  EXTERNAL_LIBRARY_LIST="
     libdc1394
     libdrm
     libflite
+    libfluidsynth
     libfontconfig
     libfreetype
     libfribidi
@@ -3465,6 +3467,7 @@  asr_filter_deps="pocketsphinx"
 ass_filter_deps="libass"
 atempo_filter_deps="avcodec"
 atempo_filter_select="rdft"
+atone_filter_deps="libfluidsynth"
 avgblur_opencl_filter_deps="opencl"
 avgblur_vulkan_filter_deps="vulkan libglslang"
 azmq_filter_deps="libzmq"
@@ -6270,6 +6273,7 @@  enabled libfdk_aac        && { check_pkg_config libfdk_aac fdk-aac "fdk-aac/aace
                                  warn "using libfdk without pkg-config"; } }
 flite_extralibs="-lflite_cmu_time_awb -lflite_cmu_us_awb -lflite_cmu_us_kal -lflite_cmu_us_kal16 -lflite_cmu_us_rms -lflite_cmu_us_slt -lflite_usenglish -lflite_cmulex -lflite"
 enabled libflite          && require libflite "flite/flite.h" flite_init $flite_extralibs
+enabled libfluidsynth     && require_pkg_config libfluidsynth fluidsynth "fluidsynth.h" fluid_log
 enabled fontconfig        && enable libfontconfig
 enabled libfontconfig     && require_pkg_config libfontconfig fontconfig "fontconfig/fontconfig.h" FcInit
 enabled libfreetype       && require_pkg_config libfreetype freetype2 "ft2build.h FT_FREETYPE_H" FT_Init_FreeType
diff --git a/doc/filters.texi b/doc/filters.texi
index 328e984e92..918b1703f8 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -5946,6 +5946,35 @@  anullsrc=r=48000:cl=mono
 
 All the parameters need to be explicitly defined.
 
+@section atone
+
+Synthesize random notes using libfluidsynth library.
+
+To compile this filter you need to configure FFmpeg with
+@code{--enable-libfluidsynth}.
+
+The filter accepts the following options:
+
+@table @option
+@item sample_rate, r
+Set the sample rate of the synthesizer. Default value is 44100.
+
+@item nb_samples, n
+Set the number of samples per frame. Default value is 1024.
+
+@item duration, d
+Set the duration of sound generation. Default value is 10 sec.
+
+@item soundfont
+Enter the location of the soundfont. Without loading the soundfont fluidsynth won't be able to synthesize.
+
+@item mchan
+Set the MIDI channel. Default value is 0.
+
+@item seed
+Set the seed value for the PRNG
+@end table
+
 @section flite
 
 Synthesize a voice utterance using the libflite library.
diff --git a/libavfilter/Makefile b/libavfilter/Makefile
index 750412da6b..020c4553cb 100644
--- a/libavfilter/Makefile
+++ b/libavfilter/Makefile
@@ -147,6 +147,7 @@  OBJS-$(CONFIG_AEVALSRC_FILTER)               += aeval.o
 OBJS-$(CONFIG_AFIRSRC_FILTER)                += asrc_afirsrc.o
 OBJS-$(CONFIG_ANOISESRC_FILTER)              += asrc_anoisesrc.o
 OBJS-$(CONFIG_ANULLSRC_FILTER)               += asrc_anullsrc.o
+OBJS-$(CONFIG_ATONE_FILTER)                  += asrc_atone.o
 OBJS-$(CONFIG_FLITE_FILTER)                  += asrc_flite.o
 OBJS-$(CONFIG_HILBERT_FILTER)                += asrc_hilbert.o
 OBJS-$(CONFIG_SINC_FILTER)                   += asrc_sinc.o
diff --git a/libavfilter/allfilters.c b/libavfilter/allfilters.c
index 501e5d041b..d167499cf1 100644
--- a/libavfilter/allfilters.c
+++ b/libavfilter/allfilters.c
@@ -141,6 +141,7 @@  extern AVFilter ff_asrc_aevalsrc;
 extern AVFilter ff_asrc_afirsrc;
 extern AVFilter ff_asrc_anoisesrc;
 extern AVFilter ff_asrc_anullsrc;
+extern AVFilter ff_asrc_atone;
 extern AVFilter ff_asrc_flite;
 extern AVFilter ff_asrc_hilbert;
 extern AVFilter ff_asrc_sinc;
diff --git a/libavfilter/asrc_atone.c b/libavfilter/asrc_atone.c
new file mode 100644
index 0000000000..25490424e0
--- /dev/null
+++ b/libavfilter/asrc_atone.c
@@ -0,0 +1,188 @@ 
+/*
+ * This file is part of FFmpeg.
+ *
+ * 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.
+ *
+ * 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 FFmpeg; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#include <fluidsynth.h>
+#include "libavutil/avassert.h"
+#include "libavutil/opt.h"
+#include "libavutil/lfg.h"
+#include "libavutil/random_seed.h"
+#include "avfilter.h"
+#include "audio.h"
+#include "formats.h"
+#include "internal.h"
+
+typedef struct AToneContext {
+    const AVClass *class;
+    fluid_settings_t *settings;
+    fluid_synth_t *synth;
+    int soundfont_id;
+    int nb_samples;
+    int sample_rate;
+    int mchan;
+    char *soundfont;
+    int64_t pts;
+    int64_t duration;
+    int64_t interval;
+    int64_t seed;
+    AVLFG c;
+} AToneContext;
+
+#define OFFSET(x) offsetof(AToneContext, x)
+#define FLAGS AV_OPT_FLAG_AUDIO_PARAM|AV_OPT_FLAG_FILTERING_PARAM
+
+static const AVOption atone_options[] = {
+    {"sample_rate", "set sample rate",                           OFFSET(sample_rate), AV_OPT_TYPE_INT,      {.i64=44100},    1,        INT_MAX,   FLAGS},
+    {"r",           "set sample rate",                           OFFSET(sample_rate), AV_OPT_TYPE_INT,      {.i64=44100},    1,        INT_MAX,   FLAGS},
+    {"nb_samples",  "set number of samples per requested frame", OFFSET(nb_samples),  AV_OPT_TYPE_INT,      {.i64=1024},     1,        INT64_MAX, FLAGS},
+    {"n",           "set number of samples per requested frame", OFFSET(nb_samples),  AV_OPT_TYPE_INT,      {.i64=1024},     1,        INT64_MAX, FLAGS},
+    {"duration",    "set duration",                              OFFSET(duration),    AV_OPT_TYPE_DURATION, {.i64=10000000}, 0,        INT64_MAX, FLAGS},
+    {"d",           "set duration",                              OFFSET(duration),    AV_OPT_TYPE_DURATION, {.i64=10000000}, 0,        INT64_MAX, FLAGS},
+    {"soundfont",   "location of soundfont",                     OFFSET(soundfont),   AV_OPT_TYPE_STRING,   {.str=NULL},                          FLAGS},
+    {"mchan",       "set MIDI channel",                          OFFSET(mchan),       AV_OPT_TYPE_INT,      {.i64=0},        0,        15,        FLAGS},
+    {"seed",        "set random seed",                           OFFSET(seed),        AV_OPT_TYPE_INT64,    {.i64=-1},       -1,       INT64_MAX, FLAGS},
+    {"t",           "set interval between notes",                OFFSET(interval),    AV_OPT_TYPE_DURATION, {.i64=0},        0,        INT64_MAX, FLAGS},
+    { NULL }
+};
+
+AVFILTER_DEFINE_CLASS(atone);
+
+static av_cold int init(AVFilterContext *ctx)
+{
+    AToneContext *fluidsynth = ctx->priv;
+    fluidsynth->soundfont_id = -1;
+    fluidsynth->settings = new_fluid_settings();
+    if (!fluidsynth->settings) {
+        av_log(ctx, AV_LOG_ERROR, "Failed to create fluidsynth settings\n");
+        return AVERROR_EXTERNAL;
+    }
+    fluidsynth->synth = new_fluid_synth(fluidsynth->settings);
+    if (!fluidsynth->synth) {
+        av_log(ctx, AV_LOG_ERROR, "Failed to create fluidsynth synthesizer\n");
+        return AVERROR_EXTERNAL;
+    }
+    fluidsynth->soundfont_id = fluid_synth_sfload(fluidsynth->synth, fluidsynth->soundfont, 1);
+    if (fluidsynth->soundfont_id < 0) {
+        av_log(ctx, AV_LOG_ERROR, "Failed to load soundfont\n");
+        return AVERROR_EXTERNAL;
+    }
+
+    return 0;
+}
+
+static av_cold void uninit(AVFilterContext *ctx)
+{
+    AToneContext *fluidsynth = ctx->priv;
+    delete_fluid_synth(fluidsynth->synth);
+    delete_fluid_settings(fluidsynth->settings);
+}
+
+static int query_formats(AVFilterContext *ctx)
+{
+    AToneContext *fluidsynth = ctx->priv;
+    AVFilterChannelLayouts *chanlayout = NULL;
+    int64_t chanlayouts = av_get_default_channel_layout(2*fluid_synth_count_audio_channels(fluidsynth->synth));
+    AVFilterFormats *formats = NULL;
+    AVFilterFormats *sample_rate = NULL;
+    int ret;
+
+    if ((ret = ff_add_format                 (&formats    , AV_SAMPLE_FMT_FLT      )) < 0 ||
+        (ret = ff_set_common_formats         (ctx         , formats                )) < 0 ||
+        (ret = ff_add_channel_layout         (&chanlayout , chanlayouts            )) < 0 ||
+        (ret = ff_set_common_channel_layouts (ctx         , chanlayout             )) < 0 ||
+        (ret = ff_add_format                 (&sample_rate, fluidsynth->sample_rate)) < 0 ||
+        (ret = ff_set_common_samplerates     (ctx         , sample_rate            )) < 0)
+        return ret;
+    return 0;
+}
+
+static int config_output(AVFilterLink *outlink)
+{
+    AVFilterContext *ctx = outlink->src;
+    AToneContext *fluidsynth = ctx->priv;
+
+    if (fluidsynth->seed == -1)
+        fluidsynth->seed = av_get_random_seed();
+    av_lfg_init(&fluidsynth->c, fluidsynth->seed);
+
+    outlink->sample_rate = fluidsynth->sample_rate;
+    fluidsynth->duration = av_rescale(fluidsynth->duration, fluidsynth->sample_rate, AV_TIME_BASE);
+    fluidsynth->interval = av_rescale(fluidsynth->interval, fluidsynth->sample_rate, AV_TIME_BASE);
+    return 0;
+}
+
+static int request_frame(AVFilterLink *outlink)
+{
+    AVFrame *frame;
+    AToneContext *fluidsynth = outlink->src->priv;
+    int nb_samples, key;
+    int64_t off;
+
+    if (fluidsynth->duration) {
+        nb_samples = FFMIN(fluidsynth->nb_samples, fluidsynth->duration - fluidsynth->pts);
+        av_assert1(nb_samples >= 0);
+        if (!nb_samples)
+            return AVERROR_EOF;
+    }
+
+    if (!(frame = ff_get_audio_buffer(outlink, nb_samples)))
+        return AVERROR(ENOMEM);
+
+    key = av_lfg_get(&fluidsynth->c) % 128 ;
+    if (fluidsynth->interval <= nb_samples) {
+        fluid_synth_noteon(fluidsynth->synth, fluidsynth->mchan, key, 100);
+        fluid_synth_write_float(fluidsynth->synth, nb_samples, frame->data[0], 0, 2, frame->data[0], 1, 2);
+    }
+    if (nb_samples < fluidsynth->interval) {
+        off = fluidsynth->interval - (fluidsynth->pts % fluidsynth->interval);
+        if (fluidsynth->pts % fluidsynth->interval == 0) {
+            fluid_synth_noteon(fluidsynth->synth, fluidsynth->mchan, key, 100);
+            fluid_synth_write_float(fluidsynth->synth, nb_samples, frame->data[0], 0, 2, frame->data[0], 1, 2);
+        } else if (off < nb_samples) {
+            fluid_synth_write_float(fluidsynth->synth, off, frame->data[0], 0, 2, frame->data[0], 1, 2);
+            fluid_synth_noteon(fluidsynth->synth, fluidsynth->mchan, key, 100);
+            fluid_synth_write_float(fluidsynth->synth, nb_samples-off, frame->data[0], off*2, 2, frame->data[0], (off*2)+1, 2);
+        } else
+            fluid_synth_write_float(fluidsynth->synth, nb_samples, frame->data[0], 0, 2, frame->data[0], 1, 2);
+    }
+
+    frame->pts = fluidsynth->pts;
+    fluidsynth->pts += nb_samples;
+    return ff_filter_frame(outlink, frame);
+}
+
+static const AVFilterPad atone_outputs[] = {
+    {
+        .name          = "default",
+        .type          = AVMEDIA_TYPE_AUDIO,
+        .request_frame = request_frame,
+        .config_props  = config_output,
+    },
+    { NULL }
+};
+
+AVFilter ff_asrc_atone = {
+    .name          = "atone",
+    .description   = NULL_IF_CONFIG_SMALL("Synthesize tones using libfluidsynth."),
+    .query_formats = query_formats,
+    .init          = init,
+    .uninit        = uninit,
+    .priv_size     = sizeof(AToneContext),
+    .inputs        = NULL,
+    .outputs       = atone_outputs,
+    .priv_class    = &atone_class,
+};
diff --git a/libavfilter/version.h b/libavfilter/version.h
index 7b41018be7..4c4e8afe2d 100644
--- a/libavfilter/version.h
+++ b/libavfilter/version.h
@@ -30,7 +30,7 @@ 
 #include "libavutil/version.h"
 
 #define LIBAVFILTER_VERSION_MAJOR   7
-#define LIBAVFILTER_VERSION_MINOR  77
+#define LIBAVFILTER_VERSION_MINOR  78
 #define LIBAVFILTER_VERSION_MICRO 100