swscale: Add GBRAP10 output

[ffmpeg] / libswscale / output.c

diff --git a/libswscale/output.c b/libswscale/output.c
index de40e4b33ebbd998fec16ccbaf78f8d1de3364d1..b0d33b18ec91e09aa1d6b0cc3332d6c574a005bb 100644 (file)
--- a/libswscale/output.c
+++ b/libswscale/output.c
@@ -311,6 +311,98 @@ static void yuv2nv12cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterS
         }
 }
 
+
+#define output_pixel(pos, val) \
+    if (big_endian) { \
+        AV_WB16(pos, av_clip_uintp2(val >> shift, 10) << 6); \
+    } else { \
+        AV_WL16(pos, av_clip_uintp2(val >> shift, 10) << 6); \
+    }
+
+static void yuv2p010l1_c(const int16_t *src,
+                         uint16_t *dest, int dstW,
+                         int big_endian)
+{
+    int i;
+    int shift = 5;
+
+    for (i = 0; i < dstW; i++) {
+        int val = src[i] + (1 << (shift - 1));
+        output_pixel(&dest[i], val);
+    }
+}
+
+static void yuv2p010lX_c(const int16_t *filter, int filterSize,
+                         const int16_t **src, uint16_t *dest, int dstW,
+                         int big_endian)
+{
+    int i, j;
+    int shift = 17;
+
+    for (i = 0; i < dstW; i++) {
+        int val = 1 << (shift - 1);
+
+        for (j = 0; j < filterSize; j++)
+            val += src[j][i] * filter[j];
+
+        output_pixel(&dest[i], val);
+    }
+}
+
+static void yuv2p010cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterSize,
+                         const int16_t **chrUSrc, const int16_t **chrVSrc,
+                         uint8_t *dest8, int chrDstW)
+{
+    uint16_t *dest = (uint16_t*)dest8;
+    int shift = 17;
+    int big_endian = c->dstFormat == AV_PIX_FMT_P010BE;
+    int i, j;
+
+    for (i = 0; i < chrDstW; i++) {
+        int u = 1 << (shift - 1);
+        int v = 1 << (shift - 1);
+
+        for (j = 0; j < chrFilterSize; j++) {
+            u += chrUSrc[j][i] * chrFilter[j];
+            v += chrVSrc[j][i] * chrFilter[j];
+        }
+
+        output_pixel(&dest[2*i]  , u);
+        output_pixel(&dest[2*i+1], v);
+    }
+}
+
+static void yuv2p010l1_LE_c(const int16_t *src,
+                            uint8_t *dest, int dstW,
+                            const uint8_t *dither, int offset)
+{
+    yuv2p010l1_c(src, (uint16_t*)dest, dstW, 0);
+}
+
+static void yuv2p010l1_BE_c(const int16_t *src,
+                            uint8_t *dest, int dstW,
+                            const uint8_t *dither, int offset)
+{
+    yuv2p010l1_c(src, (uint16_t*)dest, dstW, 1);
+}
+
+static void yuv2p010lX_LE_c(const int16_t *filter, int filterSize,
+                            const int16_t **src, uint8_t *dest, int dstW,
+                            const uint8_t *dither, int offset)
+{
+    yuv2p010lX_c(filter, filterSize, src, (uint16_t*)dest, dstW, 0);
+}
+
+static void yuv2p010lX_BE_c(const int16_t *filter, int filterSize,
+                            const int16_t **src, uint8_t *dest, int dstW,
+                            const uint8_t *dither, int offset)
+{
+    yuv2p010lX_c(filter, filterSize, src, (uint16_t*)dest, dstW, 1);
+}
+
+#undef output_pixel
+
+
 #define accumulate_bit(acc, val) \
     acc <<= 1; \
     acc |= (val) >= 234
@@ -1887,15 +1979,13 @@ yuv2gbrp_full_X_c(SwsContext *c, const int16_t *lumFilter,
             for (j = 0; j < lumFilterSize; j++)
                 A += alpSrc[j][i] * lumFilter[j];
 
-            A >>= 19;
-
-            if (A & 0x100)
-                A = av_clip_uint8(A);
+            if (A & 0xF8000000)
+                A =  av_clip_uintp2(A, 27);
         }
 
         Y -= c->yuv2rgb_y_offset;
         Y *= c->yuv2rgb_y_coeff;
-        Y += 1 << 21;
+        Y += 1 << (SH-1);
         R = Y + V * c->yuv2rgb_v2r_coeff;
         G = Y + V * c->yuv2rgb_v2g_coeff + U * c->yuv2rgb_u2g_coeff;
         B = Y +                            U * c->yuv2rgb_u2b_coeff;
@@ -1911,13 +2001,13 @@ yuv2gbrp_full_X_c(SwsContext *c, const int16_t *lumFilter,
             dest16[1][i] = B >> SH;
             dest16[2][i] = R >> SH;
             if (hasAlpha)
-                dest16[3][i] = A;
+                dest16[3][i] = A >> (SH - 3);
         } else {
             dest[0][i] = G >> 22;
             dest[1][i] = B >> 22;
             dest[2][i] = R >> 22;
             if (hasAlpha)
-                dest[3][i] = A;
+                dest[3][i] = A >> 19;
         }
     }
     if (SH != 22 && (!isBE(c->dstFormat)) != (!HAVE_BIGENDIAN)) {
@@ -2085,10 +2175,14 @@ av_cold void ff_sws_init_output_funcs(SwsContext *c,
     enum AVPixelFormat dstFormat = c->dstFormat;
     const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(dstFormat);
 
-    if (is16BPS(dstFormat)) {
+    if (dstFormat == AV_PIX_FMT_P010LE || dstFormat == AV_PIX_FMT_P010BE) {
+        *yuv2plane1 = isBE(dstFormat) ? yuv2p010l1_BE_c : yuv2p010l1_LE_c;
+        *yuv2planeX = isBE(dstFormat) ? yuv2p010lX_BE_c : yuv2p010lX_LE_c;
+        *yuv2nv12cX = yuv2p010cX_c;
+    } else if (is16BPS(dstFormat)) {
         *yuv2planeX = isBE(dstFormat) ? yuv2planeX_16BE_c  : yuv2planeX_16LE_c;
         *yuv2plane1 = isBE(dstFormat) ? yuv2plane1_16BE_c  : yuv2plane1_16LE_c;
-    } else if (is9_OR_10BPS(dstFormat)) {
+    } else if (isNBPS(dstFormat)) {
         if (desc->comp[0].depth == 9) {
             *yuv2planeX = isBE(dstFormat) ? yuv2planeX_9BE_c  : yuv2planeX_9LE_c;
             *yuv2plane1 = isBE(dstFormat) ? yuv2plane1_9BE_c  : yuv2plane1_9LE_c;
@@ -2311,6 +2405,10 @@ av_cold void ff_sws_init_output_funcs(SwsContext *c,
         case AV_PIX_FMT_GBRP16BE:
         case AV_PIX_FMT_GBRP16LE:
         case AV_PIX_FMT_GBRAP:
+        case AV_PIX_FMT_GBRAP10BE:
+        case AV_PIX_FMT_GBRAP10LE:
+        case AV_PIX_FMT_GBRAP12BE:
+        case AV_PIX_FMT_GBRAP12LE:
             *yuv2anyX = yuv2gbrp_full_X_c;
             break;
         }