From: Limin Wang <lance.lmwang at gmail.com>
Merge the old patch 2/3/4 into one by Carl Eugen comments:
https://patchwork.ffmpeg.org/patch/13270/
---
libavfilter/vf_overlay.c | 358 +++++++++++++++++++--------------------
1 file changed, 179 insertions(+), 179 deletions(-)
diff --git a/libavfilter/vf_overlay.c b/libavfilter/vf_overlay.c
index b468cedf2e..ba8147f579 100644
--- a/libavfilter/vf_overlay.c
+++ b/libavfilter/vf_overlay.c
@@ -441,189 +441,189 @@ static av_always_inline void blend_slice_packed_rgb(AVFilterContext *ctx,
}
}
-static av_always_inline void blend_plane(AVFilterContext *ctx,
- AVFrame *dst, const AVFrame *src,
- int src_w, int src_h,
- int dst_w, int dst_h,
- int i, int hsub, int vsub,
- int x, int y,
- int main_has_alpha,
- int dst_plane,
- int dst_offset,
- int dst_step,
- int straight,
- int yuv,
- int jobnr,
- int nb_jobs)
-{
- OverlayContext *octx = ctx->priv;
- int src_wp = AV_CEIL_RSHIFT(src_w, hsub);
- int src_hp = AV_CEIL_RSHIFT(src_h, vsub);
- int dst_wp = AV_CEIL_RSHIFT(dst_w, hsub);
- int dst_hp = AV_CEIL_RSHIFT(dst_h, vsub);
- int yp = y>>vsub;
- int xp = x>>hsub;
- uint8_t *s, *sp, *d, *dp, *dap, *a, *da, *ap;
- int jmax, j, k, kmax;
- int slice_start, slice_end;
-
- j = FFMAX(-yp, 0);
- jmax = FFMIN3(-yp + dst_hp, FFMIN(src_hp, dst_hp), yp + src_hp);
-
- slice_start = j + (jmax * jobnr) / nb_jobs;
- slice_end = j + (jmax * (jobnr+1)) / nb_jobs;
-
- sp = src->data[i] + (slice_start) * src->linesize[i];
- dp = dst->data[dst_plane]
- + (yp + slice_start) * dst->linesize[dst_plane]
- + dst_offset;
- ap = src->data[3] + (slice_start << vsub) * src->linesize[3];
- dap = dst->data[3] + ((yp + slice_start) << vsub) * dst->linesize[3];
-
- for (j = slice_start; j < slice_end; j++) {
- k = FFMAX(-xp, 0);
- d = dp + (xp+k) * dst_step;
- s = sp + k;
- a = ap + (k<<hsub);
- da = dap + ((xp+k) << hsub);
- kmax = FFMIN(-xp + dst_wp, src_wp);
-
- if (((vsub && j+1 < src_hp) || !vsub) && octx->blend_row[i]) {
- int c = octx->blend_row[i](d, da, s, a, kmax - k, src->linesize[3]);
-
- s += c;
- d += dst_step * c;
- da += (1 << hsub) * c;
- a += (1 << hsub) * c;
- k += c;
- }
- for (; k < kmax; k++) {
- int alpha_v, alpha_h, alpha;
-
- /* average alpha for color components, improve quality */
- if (hsub && vsub && j+1 < src_hp && k+1 < src_wp) {
- alpha = (a[0] + a[src->linesize[3]] +
- a[1] + a[src->linesize[3]+1]) >> 2;
- } else if (hsub || vsub) {
- alpha_h = hsub && k+1 < src_wp ?
- (a[0] + a[1]) >> 1 : a[0];
- alpha_v = vsub && j+1 < src_hp ?
- (a[0] + a[src->linesize[3]]) >> 1 : a[0];
- alpha = (alpha_v + alpha_h) >> 1;
- } else
- alpha = a[0];
- /* if the main channel has an alpha channel, alpha has to be calculated */
- /* to create an un-premultiplied (straight) alpha value */
- if (main_has_alpha && alpha != 0 && alpha != 255) {
- /* average alpha for color components, improve quality */
- uint8_t alpha_d;
- if (hsub && vsub && j+1 < src_hp && k+1 < src_wp) {
- alpha_d = (da[0] + da[dst->linesize[3]] +
- da[1] + da[dst->linesize[3]+1]) >> 2;
- } else if (hsub || vsub) {
- alpha_h = hsub && k+1 < src_wp ?
- (da[0] + da[1]) >> 1 : da[0];
- alpha_v = vsub && j+1 < src_hp ?
- (da[0] + da[dst->linesize[3]]) >> 1 : da[0];
- alpha_d = (alpha_v + alpha_h) >> 1;
- } else
- alpha_d = da[0];
- alpha = UNPREMULTIPLY_ALPHA(alpha, alpha_d);
- }
- if (straight) {
- *d = FAST_DIV255(*d * (255 - alpha) + *s * alpha);
- } else {
- if (i && yuv)
- *d = av_clip(FAST_DIV255((*d - 128) * (255 - alpha)) + *s - 128, -128, 128) + 128;
- else
- *d = FFMIN(FAST_DIV255(*d * (255 - alpha)) + *s, 255);
- }
- s++;
- d += dst_step;
- da += 1 << hsub;
- a += 1 << hsub;
- }
- dp += dst->linesize[dst_plane];
- sp += src->linesize[i];
- ap += (1 << vsub) * src->linesize[3];
- dap += (1 << vsub) * dst->linesize[3];
- }
+static av_always_inline void blend_plane(AVFilterContext *ctx, \
+ AVFrame *dst, const AVFrame *src, \
+ int src_w, int src_h, \
+ int dst_w, int dst_h, \
+ int i, int hsub, int vsub, \
+ int x, int y, \
+ int main_has_alpha, \
+ int dst_plane, \
+ int dst_offset, \
+ int dst_step, \
+ int straight, \
+ int yuv, \
+ int jobnr, \
+ int nb_jobs) \
+{ \
+ OverlayContext *octx = ctx->priv; \
+ int src_wp = AV_CEIL_RSHIFT(src_w, hsub); \
+ int src_hp = AV_CEIL_RSHIFT(src_h, vsub); \
+ int dst_wp = AV_CEIL_RSHIFT(dst_w, hsub); \
+ int dst_hp = AV_CEIL_RSHIFT(dst_h, vsub); \
+ int yp = y>>vsub; \
+ int xp = x>>hsub; \
+ uint8_t *s, *sp, *d, *dp, *dap, *a, *da, *ap; \
+ int jmax, j, k, kmax; \
+ int slice_start, slice_end; \
+ \
+ j = FFMAX(-yp, 0); \
+ jmax = FFMIN3(-yp + dst_hp, FFMIN(src_hp, dst_hp), yp + src_hp); \
+ \
+ slice_start = j + (jmax * jobnr) / nb_jobs; \
+ slice_end = j + (jmax * (jobnr+1)) / nb_jobs; \
+ \
+ sp = src->data[i] + (slice_start) * src->linesize[i]; \
+ dp = dst->data[dst_plane] \
+ + (yp + slice_start) * dst->linesize[dst_plane] \
+ + dst_offset; \
+ ap = src->data[3] + (slice_start << vsub) * src->linesize[3]; \
+ dap = dst->data[3] + ((yp + slice_start) << vsub) * dst->linesize[3]; \
+ \
+ for (j = slice_start; j < slice_end; j++) { \
+ k = FFMAX(-xp, 0); \
+ d = dp + (xp+k) * dst_step; \
+ s = sp + k; \
+ a = ap + (k<<hsub); \
+ da = dap + ((xp+k) << hsub); \
+ kmax = FFMIN(-xp + dst_wp, src_wp); \
+ \
+ if (((vsub && j+1 < src_hp) || !vsub) && octx->blend_row[i]) { \
+ int c = octx->blend_row[i](d, da, s, a, kmax - k, src->linesize[3]); \
+ \
+ s += c; \
+ d += dst_step * c; \
+ da += (1 << hsub) * c; \
+ a += (1 << hsub) * c; \
+ k += c; \
+ } \
+ for (; k < kmax; k++) { \
+ int alpha_v, alpha_h, alpha; \
+ \
+ /* average alpha for color components, improve quality */ \
+ if (hsub && vsub && j+1 < src_hp && k+1 < src_wp) { \
+ alpha = (a[0] + a[src->linesize[3]] + \
+ a[1] + a[src->linesize[3]+1]) >> 2; \
+ } else if (hsub || vsub) { \
+ alpha_h = hsub && k+1 < src_wp ? \
+ (a[0] + a[1]) >> 1 : a[0]; \
+ alpha_v = vsub && j+1 < src_hp ? \
+ (a[0] + a[src->linesize[3]]) >> 1 : a[0]; \
+ alpha = (alpha_v + alpha_h) >> 1; \
+ } else \
+ alpha = a[0]; \
+ /* if the main channel has an alpha channel, alpha has to be calculated */ \
+ /* to create an un-premultiplied (straight) alpha value */ \
+ if (main_has_alpha && alpha != 0 && alpha != 255) { \
+ /* average alpha for color components, improve quality */ \
+ uint8_t alpha_d; \
+ if (hsub && vsub && j+1 < src_hp && k+1 < src_wp) { \
+ alpha_d = (da[0] + da[dst->linesize[3]] + \
+ da[1] + da[dst->linesize[3]+1]) >> 2; \
+ } else if (hsub || vsub) { \
+ alpha_h = hsub && k+1 < src_wp ? \
+ (da[0] + da[1]) >> 1 : da[0]; \
+ alpha_v = vsub && j+1 < src_hp ? \
+ (da[0] + da[dst->linesize[3]]) >> 1 : da[0]; \
+ alpha_d = (alpha_v + alpha_h) >> 1; \
+ } else \
+ alpha_d = da[0]; \
+ alpha = UNPREMULTIPLY_ALPHA(alpha, alpha_d); \
+ } \
+ if (straight) { \
+ *d = FAST_DIV255(*d * (255 - alpha) + *s * alpha); \
+ } else { \
+ if (i && yuv) \
+ *d = av_clip(FAST_DIV255((*d - 128) * (255 - alpha)) + *s - 128, -128, 128) + 128; \
+ else \
+ *d = FFMIN(FAST_DIV255(*d * (255 - alpha)) + *s, 255); \
+ } \
+ s++; \
+ d += dst_step; \
+ da += 1 << hsub; \
+ a += 1 << hsub; \
+ } \
+ dp += dst->linesize[dst_plane]; \
+ sp += src->linesize[i]; \
+ ap += (1 << vsub) * src->linesize[3]; \
+ dap += (1 << vsub) * dst->linesize[3]; \
+ } \
}
-static inline void alpha_composite(const AVFrame *src, const AVFrame *dst,
- int src_w, int src_h,
- int dst_w, int dst_h,
- int x, int y,
- int jobnr, int nb_jobs)
-{
- uint8_t alpha; /* the amount of overlay to blend on to main */
- uint8_t *s, *sa, *d, *da;
- int i, imax, j, jmax;
- int slice_start, slice_end;
-
- imax = FFMIN(-y + dst_h, src_h);
- slice_start = (imax * jobnr) / nb_jobs;
- slice_end = ((imax * (jobnr+1)) / nb_jobs);
-
- i = FFMAX(-y, 0);
- sa = src->data[3] + (i + slice_start) * src->linesize[3];
- da = dst->data[3] + (y + i + slice_start) * dst->linesize[3];
-
- for (i = i + slice_start; i < slice_end; i++) {
- j = FFMAX(-x, 0);
- s = sa + j;
- d = da + x+j;
-
- for (jmax = FFMIN(-x + dst_w, src_w); j < jmax; j++) {
- alpha = *s;
- if (alpha != 0 && alpha != 255) {
- uint8_t alpha_d = *d;
- alpha = UNPREMULTIPLY_ALPHA(alpha, alpha_d);
- }
- switch (alpha) {
- case 0:
- break;
- case 255:
- *d = *s;
- break;
- default:
- /* apply alpha compositing: main_alpha += (1-main_alpha) * overlay_alpha */
- *d += FAST_DIV255((255 - *d) * *s);
- }
- d += 1;
- s += 1;
- }
- da += dst->linesize[3];
- sa += src->linesize[3];
- }
+static inline void alpha_composite(const AVFrame *src, const AVFrame *dst, \
+ int src_w, int src_h, \
+ int dst_w, int dst_h, \
+ int x, int y, \
+ int jobnr, int nb_jobs) \
+{ \
+ uint8_t alpha; /* the amount of overlay to blend on to main */ \
+ uint8_t *s, *sa, *d, *da; \
+ int i, imax, j, jmax; \
+ int slice_start, slice_end; \
+ \
+ imax = FFMIN(-y + dst_h, src_h); \
+ slice_start = (imax * jobnr) / nb_jobs; \
+ slice_end = ((imax * (jobnr+1)) / nb_jobs); \
+ \
+ i = FFMAX(-y, 0); \
+ sa = src->data[3] + (i + slice_start) * src->linesize[3]; \
+ da = dst->data[3] + (y + i + slice_start) * dst->linesize[3]; \
+ \
+ for (i = i + slice_start; i < slice_end; i++) { \
+ j = FFMAX(-x, 0); \
+ s = sa + j; \
+ d = da + x+j; \
+ \
+ for (jmax = FFMIN(-x + dst_w, src_w); j < jmax; j++) { \
+ alpha = *s; \
+ if (alpha != 0 && alpha != 255) { \
+ uint8_t alpha_d = *d; \
+ alpha = UNPREMULTIPLY_ALPHA(alpha, alpha_d); \
+ } \
+ switch (alpha) { \
+ case 0: \
+ break; \
+ case 255: \
+ *d = *s; \
+ break; \
+ default: \
+ /* apply alpha compositing: main_alpha += (1-main_alpha) * overlay_alpha */ \
+ *d += FAST_DIV255((255 - *d) * *s); \
+ } \
+ d += 1; \
+ s += 1; \
+ } \
+ da += dst->linesize[3]; \
+ sa += src->linesize[3]; \
+ } \
}
-static av_always_inline void blend_slice_yuv(AVFilterContext *ctx,
- AVFrame *dst, const AVFrame *src,
- int hsub, int vsub,
- int main_has_alpha,
- int x, int y,
- int is_straight,
- int jobnr, int nb_jobs)
-{
- OverlayContext *s = ctx->priv;
- const int src_w = src->width;
- const int src_h = src->height;
- const int dst_w = dst->width;
- const int dst_h = dst->height;
-
- blend_plane(ctx, dst, src, src_w, src_h, dst_w, dst_h, 0, 0, 0, x, y, main_has_alpha,
- s->main_desc->comp[0].plane, s->main_desc->comp[0].offset, s->main_desc->comp[0].step, is_straight, 1,
- jobnr, nb_jobs);
- blend_plane(ctx, dst, src, src_w, src_h, dst_w, dst_h, 1, hsub, vsub, x, y, main_has_alpha,
- s->main_desc->comp[1].plane, s->main_desc->comp[1].offset, s->main_desc->comp[1].step, is_straight, 1,
- jobnr, nb_jobs);
- blend_plane(ctx, dst, src, src_w, src_h, dst_w, dst_h, 2, hsub, vsub, x, y, main_has_alpha,
- s->main_desc->comp[2].plane, s->main_desc->comp[2].offset, s->main_desc->comp[2].step, is_straight, 1,
- jobnr, nb_jobs);
-
- if (main_has_alpha)
- alpha_composite(src, dst, src_w, src_h, dst_w, dst_h, x, y, jobnr, nb_jobs);
+static av_always_inline void blend_slice_yuv(AVFilterContext *ctx, \
+ AVFrame *dst, const AVFrame *src, \
+ int hsub, int vsub, \
+ int main_has_alpha, \
+ int x, int y, \
+ int is_straight, \
+ int jobnr, int nb_jobs) \
+{ \
+ OverlayContext *s = ctx->priv; \
+ const int src_w = src->width; \
+ const int src_h = src->height; \
+ const int dst_w = dst->width; \
+ const int dst_h = dst->height; \
+ \
+ blend_plane(ctx, dst, src, src_w, src_h, dst_w, dst_h, 0, 0, 0, x, y, main_has_alpha, \
+ s->main_desc->comp[0].plane, s->main_desc->comp[0].offset, s->main_desc->comp[0].step, is_straight, 1, \
+ jobnr, nb_jobs); \
+ blend_plane(ctx, dst, src, src_w, src_h, dst_w, dst_h, 1, hsub, vsub, x, y, main_has_alpha, \
+ s->main_desc->comp[1].plane, s->main_desc->comp[1].offset, s->main_desc->comp[1].step, is_straight, 1, \
+ jobnr, nb_jobs); \
+ blend_plane(ctx, dst, src, src_w, src_h, dst_w, dst_h, 2, hsub, vsub, x, y, main_has_alpha, \
+ s->main_desc->comp[2].plane, s->main_desc->comp[2].offset, s->main_desc->comp[2].step, is_straight, 1, \
+ jobnr, nb_jobs); \
+ \
+ if (main_has_alpha) \
+ alpha_composite(src, dst, src_w, src_h, dst_w, dst_h, x, y, jobnr, nb_jobs); \
}
static av_always_inline void blend_slice_planar_rgb(AVFilterContext *ctx,
--
2.21.0