mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-02 03:06:28 +02:00
b4f5201967
If one looks at the many query_formats callbacks in existence, one will immediately recognize that there is one type of default callback for video and a slightly different default callback for audio: It is "return ff_set_common_formats_from_list(ctx, pix_fmts);" for video with a filter-specific pix_fmts list. For audio, it is the same with a filter-specific sample_fmts list together with ff_set_common_all_samplerates() and ff_set_common_all_channel_counts(). This commit allows to remove the boilerplate query_formats callbacks by replacing said callback with a union consisting the old callback and pointers for pixel and sample format arrays. For the not uncommon case in which these lists only contain a single entry (besides the sentinel) enum AVPixelFormat and enum AVSampleFormat fields are also added to the union to store them directly in the AVFilter, thereby avoiding a relocation. The state of said union will be contained in a new, dedicated AVFilter field (the nb_inputs and nb_outputs fields have been shrunk to uint8_t in order to create a hole for this new field; this is no problem, as the maximum of all the nb_inputs is four; for nb_outputs it is only two). The state's default value coincides with the earlier default of query_formats being unset, namely that the filter accepts all formats (and also sample rates and channel counts/layouts for audio) provided that these properties agree coincide for all inputs and outputs. By using different union members for audio and video filters the type-unsafety of using the same functions for audio and video lists will furthermore be more confined to formats.c than before. When the new fields are used, they will also avoid allocations: Currently something nearly equivalent to ff_default_query_formats() is called after every successful call to a query_formats callback; yet in the common case that the newly allocated AVFilterFormats are not used at all (namely if there are no free links) these newly allocated AVFilterFormats are freed again without ever being used. Filters no longer using the callback will not exhibit this any more. Reviewed-by: Paul B Mahol <onemda@gmail.com> Reviewed-by: Nicolas George <george@nsup.org> Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
322 lines
12 KiB
C
322 lines
12 KiB
C
/*
|
|
* Copyright (c) 2018 Paul B Mahol
|
|
*
|
|
* 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 "libavutil/imgutils.h"
|
|
#include "libavutil/pixdesc.h"
|
|
#include "libavutil/opt.h"
|
|
#include "avfilter.h"
|
|
#include "formats.h"
|
|
#include "internal.h"
|
|
#include "video.h"
|
|
|
|
typedef struct MaskFunContext {
|
|
const AVClass *class;
|
|
|
|
int low, high;
|
|
int planes;
|
|
int fill;
|
|
int sum;
|
|
|
|
int linesize[4];
|
|
int width[4], height[4];
|
|
int nb_planes;
|
|
int depth;
|
|
int max;
|
|
uint64_t max_sum;
|
|
|
|
AVFrame *empty;
|
|
int (*getsum)(AVFilterContext *ctx, AVFrame *out);
|
|
int (*maskfun)(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs);
|
|
} MaskFunContext;
|
|
|
|
#define OFFSET(x) offsetof(MaskFunContext, x)
|
|
#define VFT AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM|AV_OPT_FLAG_RUNTIME_PARAM
|
|
|
|
static const AVOption maskfun_options[] = {
|
|
{ "low", "set low threshold", OFFSET(low), AV_OPT_TYPE_INT, {.i64=10}, 0, UINT16_MAX, VFT },
|
|
{ "high", "set high threshold", OFFSET(high), AV_OPT_TYPE_INT, {.i64=10}, 0, UINT16_MAX, VFT },
|
|
{ "planes", "set planes", OFFSET(planes), AV_OPT_TYPE_INT, {.i64=0xF}, 0, 0xF, VFT },
|
|
{ "fill", "set fill value", OFFSET(fill), AV_OPT_TYPE_INT, {.i64=0}, 0, UINT16_MAX, VFT },
|
|
{ "sum", "set sum value", OFFSET(sum), AV_OPT_TYPE_INT, {.i64=10}, 0, UINT16_MAX, VFT },
|
|
{ NULL }
|
|
};
|
|
|
|
AVFILTER_DEFINE_CLASS(maskfun);
|
|
|
|
static int query_formats(AVFilterContext *ctx)
|
|
{
|
|
static const enum AVPixelFormat pix_fmts[] = {
|
|
AV_PIX_FMT_YUVA444P, AV_PIX_FMT_YUV444P, AV_PIX_FMT_YUV440P,
|
|
AV_PIX_FMT_YUVJ444P, AV_PIX_FMT_YUVJ440P,
|
|
AV_PIX_FMT_YUVA422P, AV_PIX_FMT_YUV422P, AV_PIX_FMT_YUVA420P, AV_PIX_FMT_YUV420P,
|
|
AV_PIX_FMT_YUVJ422P, AV_PIX_FMT_YUVJ420P,
|
|
AV_PIX_FMT_YUVJ411P, AV_PIX_FMT_YUV411P, AV_PIX_FMT_YUV410P,
|
|
AV_PIX_FMT_YUV420P9, AV_PIX_FMT_YUV422P9, AV_PIX_FMT_YUV444P9,
|
|
AV_PIX_FMT_YUV420P10, AV_PIX_FMT_YUV422P10, AV_PIX_FMT_YUV444P10,
|
|
AV_PIX_FMT_YUV420P12, AV_PIX_FMT_YUV422P12, AV_PIX_FMT_YUV444P12, AV_PIX_FMT_YUV440P12,
|
|
AV_PIX_FMT_YUV420P14, AV_PIX_FMT_YUV422P14, AV_PIX_FMT_YUV444P14,
|
|
AV_PIX_FMT_YUV420P16, AV_PIX_FMT_YUV422P16, AV_PIX_FMT_YUV444P16,
|
|
AV_PIX_FMT_YUVA420P9, AV_PIX_FMT_YUVA422P9, AV_PIX_FMT_YUVA444P9,
|
|
AV_PIX_FMT_YUVA420P10, AV_PIX_FMT_YUVA422P10, AV_PIX_FMT_YUVA444P10,
|
|
AV_PIX_FMT_YUVA420P16, AV_PIX_FMT_YUVA422P16, AV_PIX_FMT_YUVA444P16,
|
|
AV_PIX_FMT_GBRP, AV_PIX_FMT_GBRP9, AV_PIX_FMT_GBRP10,
|
|
AV_PIX_FMT_GBRP12, AV_PIX_FMT_GBRP14, AV_PIX_FMT_GBRP16,
|
|
AV_PIX_FMT_GBRAP, AV_PIX_FMT_GBRAP10, AV_PIX_FMT_GBRAP12, AV_PIX_FMT_GBRAP16,
|
|
AV_PIX_FMT_GRAY8, AV_PIX_FMT_GRAY9, AV_PIX_FMT_GRAY10, AV_PIX_FMT_GRAY12, AV_PIX_FMT_GRAY14, AV_PIX_FMT_GRAY16,
|
|
AV_PIX_FMT_NONE
|
|
};
|
|
|
|
return ff_set_common_formats_from_list(ctx, pix_fmts);
|
|
}
|
|
|
|
static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
|
|
{
|
|
AVFilterContext *ctx = inlink->dst;
|
|
MaskFunContext *s = ctx->priv;
|
|
AVFilterLink *outlink = ctx->outputs[0];
|
|
|
|
if (s->getsum(ctx, frame)) {
|
|
AVFrame *out = av_frame_clone(s->empty);
|
|
|
|
if (!out) {
|
|
av_frame_free(&frame);
|
|
return AVERROR(ENOMEM);
|
|
}
|
|
out->pts = frame->pts;
|
|
av_frame_free(&frame);
|
|
|
|
return ff_filter_frame(outlink, out);
|
|
}
|
|
|
|
ff_filter_execute(ctx, s->maskfun, frame, NULL,
|
|
FFMIN(s->height[1], ff_filter_get_nb_threads(ctx)));
|
|
|
|
return ff_filter_frame(outlink, frame);
|
|
}
|
|
|
|
#define GETSUM(name, type, div) \
|
|
static int getsum##name(AVFilterContext *ctx, AVFrame *out) \
|
|
{ \
|
|
MaskFunContext *s = ctx->priv; \
|
|
uint64_t sum = 0; \
|
|
int p; \
|
|
\
|
|
for (p = 0; p < s->nb_planes; p++) { \
|
|
const int linesize = out->linesize[p] / div; \
|
|
const int w = s->width[p]; \
|
|
const int h = s->height[p]; \
|
|
type *dst = (type *)out->data[p]; \
|
|
\
|
|
if (!((1 << p) & s->planes)) \
|
|
continue; \
|
|
\
|
|
for (int y = 0; y < h; y++) { \
|
|
for (int x = 0; x < w; x++) \
|
|
sum += dst[x]; \
|
|
if (sum >= s->max_sum) \
|
|
return 1; \
|
|
dst += linesize; \
|
|
} \
|
|
} \
|
|
\
|
|
return 0; \
|
|
}
|
|
|
|
GETSUM(8, uint8_t, 1)
|
|
GETSUM(16, uint16_t, 2)
|
|
|
|
#define MASKFUN(name, type, div) \
|
|
static int maskfun##name(AVFilterContext *ctx, void *arg, \
|
|
int jobnr, int nb_jobs) \
|
|
{ \
|
|
MaskFunContext *s = ctx->priv; \
|
|
AVFrame *out = arg; \
|
|
const int low = s->low; \
|
|
const int high = s->high; \
|
|
const int max = s->max; \
|
|
int p; \
|
|
\
|
|
for (p = 0; p < s->nb_planes; p++) { \
|
|
const int linesize = out->linesize[p] / div; \
|
|
const int w = s->width[p]; \
|
|
const int h = s->height[p]; \
|
|
const int slice_start = (h * jobnr) / nb_jobs; \
|
|
const int slice_end = (h * (jobnr+1)) / nb_jobs; \
|
|
type *dst = (type *)out->data[p] + slice_start * linesize; \
|
|
\
|
|
if (!((1 << p) & s->planes)) \
|
|
continue; \
|
|
\
|
|
for (int y = slice_start; y < slice_end; y++) { \
|
|
for (int x = 0; x < w; x++) { \
|
|
if (dst[x] <= low) \
|
|
dst[x] = 0; \
|
|
else if (dst[x] > high) \
|
|
dst[x] = max; \
|
|
} \
|
|
\
|
|
dst += linesize; \
|
|
} \
|
|
} \
|
|
\
|
|
return 0; \
|
|
}
|
|
|
|
MASKFUN(8, uint8_t, 1)
|
|
MASKFUN(16, uint16_t, 2)
|
|
|
|
static void fill_frame(AVFilterContext *ctx)
|
|
{
|
|
MaskFunContext *s = ctx->priv;
|
|
|
|
s->fill = FFMIN(s->fill, s->max);
|
|
if (s->depth == 8) {
|
|
for (int p = 0; p < s->nb_planes; p++) {
|
|
uint8_t *dst = s->empty->data[p];
|
|
|
|
for (int y = 0; y < s->height[p]; y++) {
|
|
memset(dst, s->fill, s->width[p]);
|
|
dst += s->empty->linesize[p];
|
|
}
|
|
}
|
|
} else {
|
|
for (int p = 0; p < s->nb_planes; p++) {
|
|
uint16_t *dst = (uint16_t *)s->empty->data[p];
|
|
|
|
for (int y = 0; y < s->height[p]; y++) {
|
|
for (int x = 0; x < s->width[p]; x++)
|
|
dst[x] = s->fill;
|
|
dst += s->empty->linesize[p] / 2;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
static void set_max_sum(AVFilterContext *ctx)
|
|
{
|
|
MaskFunContext *s = ctx->priv;
|
|
|
|
s->max_sum = 0;
|
|
for (int p = 0; p < s->nb_planes; p++) {
|
|
if (!((1 << p) & s->planes))
|
|
continue;
|
|
s->max_sum += (uint64_t)s->sum * s->width[p] * s->height[p];
|
|
}
|
|
}
|
|
|
|
static int config_input(AVFilterLink *inlink)
|
|
{
|
|
AVFilterContext *ctx = inlink->dst;
|
|
MaskFunContext *s = ctx->priv;
|
|
const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);
|
|
int vsub, hsub, ret;
|
|
|
|
s->nb_planes = av_pix_fmt_count_planes(inlink->format);
|
|
|
|
if ((ret = av_image_fill_linesizes(s->linesize, inlink->format, inlink->w)) < 0)
|
|
return ret;
|
|
|
|
hsub = desc->log2_chroma_w;
|
|
vsub = desc->log2_chroma_h;
|
|
s->height[1] = s->height[2] = AV_CEIL_RSHIFT(inlink->h, vsub);
|
|
s->height[0] = s->height[3] = inlink->h;
|
|
s->width[1] = s->width[2] = AV_CEIL_RSHIFT(inlink->w, hsub);
|
|
s->width[0] = s->width[3] = inlink->w;
|
|
|
|
s->depth = desc->comp[0].depth;
|
|
s->max = (1 << s->depth) - 1;
|
|
|
|
if (s->depth == 8) {
|
|
s->maskfun = maskfun8;
|
|
s->getsum = getsum8;
|
|
} else {
|
|
s->maskfun = maskfun16;
|
|
s->getsum = getsum16;
|
|
}
|
|
|
|
s->empty = ff_get_video_buffer(inlink, inlink->w, inlink->h);
|
|
if (!s->empty)
|
|
return AVERROR(ENOMEM);
|
|
|
|
fill_frame(ctx);
|
|
|
|
set_max_sum(ctx);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int process_command(AVFilterContext *ctx, const char *cmd, const char *args,
|
|
char *res, int res_len, int flags)
|
|
{
|
|
MaskFunContext *s = ctx->priv;
|
|
int fill = s->fill;
|
|
int sum = s->sum;
|
|
int ret;
|
|
|
|
ret = ff_filter_process_command(ctx, cmd, args, res, res_len, flags);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
if (sum != s->sum)
|
|
set_max_sum(ctx);
|
|
|
|
if (fill != s->fill)
|
|
fill_frame(ctx);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static av_cold void uninit(AVFilterContext *ctx)
|
|
{
|
|
MaskFunContext *s = ctx->priv;
|
|
|
|
av_frame_free(&s->empty);
|
|
}
|
|
|
|
static const AVFilterPad maskfun_inputs[] = {
|
|
{
|
|
.name = "default",
|
|
.type = AVMEDIA_TYPE_VIDEO,
|
|
.flags = AVFILTERPAD_FLAG_NEEDS_WRITABLE,
|
|
.filter_frame = filter_frame,
|
|
.config_props = config_input,
|
|
},
|
|
};
|
|
|
|
static const AVFilterPad maskfun_outputs[] = {
|
|
{
|
|
.name = "default",
|
|
.type = AVMEDIA_TYPE_VIDEO,
|
|
},
|
|
};
|
|
|
|
const AVFilter ff_vf_maskfun = {
|
|
.name = "maskfun",
|
|
.description = NULL_IF_CONFIG_SMALL("Create Mask."),
|
|
.priv_size = sizeof(MaskFunContext),
|
|
.uninit = uninit,
|
|
FILTER_INPUTS(maskfun_inputs),
|
|
FILTER_OUTPUTS(maskfun_outputs),
|
|
FILTER_QUERY_FUNC(query_formats),
|
|
.priv_class = &maskfun_class,
|
|
.flags = AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC | AVFILTER_FLAG_SLICE_THREADS,
|
|
.process_command = process_command,
|
|
};
|