sws/output: factor yuv2rgb_write_full() out

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

libswscale/output.c

@@ -1217,45 +1217,13 @@ YUV2RGBWRAPPER(yuv2rgb,,   8,    AV_PIX_FMT_RGB8,      0)
 YUV2RGBWRAPPER(yuv2rgb,,   4,    AV_PIX_FMT_RGB4,      0)
 YUV2RGBWRAPPER(yuv2rgb,,   4b,   AV_PIX_FMT_RGB4_BYTE, 0)
 
-static av_always_inline void
-yuv2rgb_full_X_c_template(SwsContext *c, const int16_t *lumFilter,
-                          const int16_t **lumSrc, int lumFilterSize,
-                          const int16_t *chrFilter, const int16_t **chrUSrc,
-                          const int16_t **chrVSrc, int chrFilterSize,
-                          const int16_t **alpSrc, uint8_t *dest,
-                          int dstW, int y, enum AVPixelFormat target, int hasAlpha)
+static av_always_inline void yuv2rgb_write_full(SwsContext *c,
+    uint8_t *dest, int i, int Y, int A, int U, int V,
+    int y, enum AVPixelFormat target, int hasAlpha, int err[4])
 {
-    int i;
-    int step = (target == AV_PIX_FMT_RGB24 || target == AV_PIX_FMT_BGR24) ? 3 : 4;
-    int err[4] = {0};
+    int R, G, B;
     int isrgb8 = target == AV_PIX_FMT_BGR8 || target == AV_PIX_FMT_RGB8;
 
-    for (i = 0; i < dstW; i++) {
-        int j;
-        int Y = 1<<9;
-        int U = (1<<9)-(128 << 19);
-        int V = (1<<9)-(128 << 19);
-        int R, G, B, A;
-
-        for (j = 0; j < lumFilterSize; j++) {
-            Y += lumSrc[j][i] * lumFilter[j];
-        }
-        for (j = 0; j < chrFilterSize; j++) {
-            U += chrUSrc[j][i] * chrFilter[j];
-            V += chrVSrc[j][i] * chrFilter[j];
-        }
-        Y >>= 10;
-        U >>= 10;
-        V >>= 10;
-        if (hasAlpha) {
-            A = 1 << 18;
-            for (j = 0; j < lumFilterSize; j++) {
-                A += alpSrc[j][i] * lumFilter[j];
-            }
-            A >>= 19;
-            if (A & 0x100)
-                A = av_clip_uint8(A);
-        }
     Y -= c->yuv2rgb_y_offset;
     Y *= c->yuv2rgb_y_coeff;
     Y += 1 << 21;
@@ -1337,9 +1305,53 @@ yuv2rgb_full_X_c_template(SwsContext *c, const int16_t *lumFilter,
             dest[0] = b + 4*g + 32*r;
         } else
             av_assert2(0);
-            step = 1;
         break;}
     }
+}
+
+static av_always_inline void
+yuv2rgb_full_X_c_template(SwsContext *c, const int16_t *lumFilter,
+                          const int16_t **lumSrc, int lumFilterSize,
+                          const int16_t *chrFilter, const int16_t **chrUSrc,
+                          const int16_t **chrVSrc, int chrFilterSize,
+                          const int16_t **alpSrc, uint8_t *dest,
+                          int dstW, int y, enum AVPixelFormat target, int hasAlpha)
+{
+    int i;
+    int step = (target == AV_PIX_FMT_RGB24 || target == AV_PIX_FMT_BGR24) ? 3 : 4;
+    int err[4] = {0};
+
+    if(   target == AV_PIX_FMT_BGR4_BYTE || target == AV_PIX_FMT_RGB4_BYTE
+       || target == AV_PIX_FMT_BGR8      || target == AV_PIX_FMT_RGB8)
+        step = 1;
+
+    for (i = 0; i < dstW; i++) {
+        int j;
+        int Y = 1<<9;
+        int U = (1<<9)-(128 << 19);
+        int V = (1<<9)-(128 << 19);
+        int A;
+
+        for (j = 0; j < lumFilterSize; j++) {
+            Y += lumSrc[j][i] * lumFilter[j];
+        }
+        for (j = 0; j < chrFilterSize; j++) {
+            U += chrUSrc[j][i] * chrFilter[j];
+            V += chrVSrc[j][i] * chrFilter[j];
+        }
+        Y >>= 10;
+        U >>= 10;
+        V >>= 10;
+        if (hasAlpha) {
+            A = 1 << 18;
+            for (j = 0; j < lumFilterSize; j++) {
+                A += alpSrc[j][i] * lumFilter[j];
+            }
+            A >>= 19;
+            if (A & 0x100)
+                A = av_clip_uint8(A);
+        }
+        yuv2rgb_write_full(c, dest, i, Y, A, U, V, y, target, hasAlpha, err);
         dest += step;
     }
     c->dither_error[0][i] = err[0];