swscale: support gray to 9bit and 10bit formats

With the input of Kostya and Ronald.

diff --git a/libswscale/swscale.c b/libswscale/swscale.c
index 3f54e4dc558081a3e8a4ef5be7d1aed1a1a98fa4..c1920de0a6420ee78e4d66940cdc7c45876c4f72 100644 (file)
--- a/libswscale/swscale.c
+++ b/libswscale/swscale.c
@@ -61,6 +61,28 @@ static av_always_inline void fillPlane(uint8_t *plane, int stride, int width,
     }
 }
 
+static void fill_plane9or10(uint8_t *plane, int stride, int width,
+                            int height, int y, uint8_t val,
+                            const int dst_depth, const int big_endian)
+{
+    int i, j;
+    uint16_t *dst = (uint16_t *) (plane + stride * y);
+#define FILL8TO9_OR_10(wfunc) \
+    for (i = 0; i < height; i++) { \
+        for (j = 0; j < width; j++) { \
+            wfunc(&dst[j], (val << (dst_depth - 8)) |  \
+                               (val >> (16 - dst_depth))); \
+        } \
+        dst += stride / 2; \
+    }
+    if (big_endian) {
+        FILL8TO9_OR_10(AV_WB16);
+    } else {
+        FILL8TO9_OR_10(AV_WL16);
+    }
+}
+
+
 static void hScale16To19_c(SwsContext *c, int16_t *_dst, int dstW,
                            const uint8_t *_src, const int16_t *filter,
                            const int32_t *filterPos, int filterSize)
@@ -658,8 +680,20 @@ static int swScale(SwsContext *c, const uint8_t *src[],
         }
     }
 
-    if (isPlanar(dstFormat) && isALPHA(dstFormat) && !alpPixBuf)
-        fillPlane(dst[3], dstStride[3], dstW, dstY - lastDstY, lastDstY, 255);
+    if (isPlanar(dstFormat) && isALPHA(dstFormat) && !alpPixBuf) {
+        int length = dstW;
+        int height = dstY - lastDstY;
+        if (is16BPS(c->dstFormat))
+            length *= 2;
+
+        if (is9_OR_10BPS(dstFormat)) {
+            const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(dstFormat);
+            fill_plane9or10(dst[3], dstStride[3], length, height, lastDstY,
+                            255, desc->comp[3].depth_minus1 + 1,
+                            isBE(dstFormat));
+        } else
+            fillPlane(dst[3], dstStride[3], length, height, lastDstY, 255);
+    }
 
 #if HAVE_MMXEXT_INLINE
     if (av_get_cpu_flags() & AV_CPU_FLAG_MMXEXT)

diff --git a/libswscale/swscale_unscaled.c b/libswscale/swscale_unscaled.c
index 5efc647b08f0ec047d11f86e3124acce8259a83c..9b919f8aa49856612bec7824eb4aac5e812cebb4 100644 (file)
--- a/libswscale/swscale_unscaled.c
+++ b/libswscale/swscale_unscaled.c
@@ -98,6 +98,27 @@ static void fillPlane(uint8_t *plane, int stride, int width, int height, int y,
     }
 }
 
+static void fill_plane9or10(uint8_t *plane, int stride, int width,
+                            int height, int y, uint8_t val,
+                            const int dst_depth, const int big_endian)
+{
+    int i, j;
+    uint16_t *dst = (uint16_t *) (plane + stride * y);
+#define FILL8TO9_OR_10(wfunc) \
+    for (i = 0; i < height; i++) { \
+        for (j = 0; j < width; j++) { \
+            wfunc(&dst[j], (val << (dst_depth - 8)) |  \
+                               (val >> (16 - dst_depth))); \
+        } \
+        dst += stride / 2; \
+    }
+    if (big_endian) {
+        FILL8TO9_OR_10(AV_WB16);
+    } else {
+        FILL8TO9_OR_10(AV_WL16);
+    }
+}
+
 static void copyPlane(const uint8_t *src, int srcStride,
                       int srcSliceY, int srcSliceH, int width,
                       uint8_t *dst, int dstStride)
@@ -677,10 +698,17 @@ static int planarCopyWrapper(SwsContext *c, const uint8_t *src[],
         // ignore palette for GRAY8
         if (plane == 1 && !dst[2]) continue;
         if (!src[plane] || (plane == 1 && !src[2])) {
+            int val = (plane == 3) ? 255 : 128;
             if (is16BPS(c->dstFormat))
                 length *= 2;
-            fillPlane(dst[plane], dstStride[plane], length, height, y,
-                      (plane == 3) ? 255 : 128);
+            if (is9_OR_10BPS(c->dstFormat)) {
+                fill_plane9or10(dst[plane], dstStride[plane],
+                                length, height, y, val,
+                                desc_dst->comp[plane].depth_minus1 + 1,
+                                isBE(c->dstFormat));
+            } else
+                fillPlane(dst[plane], dstStride[plane], length, height, y,
+                          val);
         } else {
             if (is9_OR_10BPS(c->srcFormat)) {
                 const int src_depth = desc_src->comp[plane].depth_minus1 + 1;