swscale: fix overflow in gray16 vertical scaling.

This fixes the same overflow as in the RGB48/16-bit YUV scaling;
some filters can overflow both negatively and positively (e.g.
spline/lanczos), so we bias a signed integer so it's "half signed"
and "half unsigned", and can cover overflows in both directions
while maintaining full 31-bit depth.

Signed-off-by: Mans Rullgard <mans@mansr.com>

diff --git a/libswscale/swscale.c b/libswscale/swscale.c
index 3ea3710..c9dfc8d 100644 (file)
--- a/libswscale/swscale.c
+++ b/libswscale/swscale.c
@@ -386,8 +386,8 @@ yuv2gray16_X_c_template(SwsContext *c, const int16_t *lumFilter,
 
     for (i = 0; i < (dstW >> 1); i++) {
         int j;
-        int Y1 = 1 << 14;
-        int Y2 = 1 << 14;
+        int Y1 = (1 << 14) - 0x40000000;
+        int Y2 = (1 << 14) - 0x40000000;
 
         for (j = 0; j < lumFilterSize; j++) {
             Y1 += lumSrc[j][i * 2]     * lumFilter[j];
@@ -395,12 +395,10 @@ yuv2gray16_X_c_template(SwsContext *c, const int16_t *lumFilter,
         }
         Y1 >>= 15;
         Y2 >>= 15;
-        if ((Y1 | Y2) & 0x10000) {
-            Y1 = av_clip_uint16(Y1);
-            Y2 = av_clip_uint16(Y2);
-        }
-        output_pixel(&dest[i * 2 + 0], Y1);
-        output_pixel(&dest[i * 2 + 1], Y2);
+        Y1 = av_clip_int16(Y1);
+        Y2 = av_clip_int16(Y2);
+        output_pixel(&dest[i * 2 + 0], 0x8000 + Y1);
+        output_pixel(&dest[i * 2 + 1], 0x8000 + Y2);
     }
 }