summaryrefslogtreecommitdiffstats
path: root/libswscale/swscale_unscaled.c
diff options
context:
space:
mode:
Diffstat (limited to 'libswscale/swscale_unscaled.c')
-rw-r--r--libswscale/swscale_unscaled.c572
1 files changed, 337 insertions, 235 deletions
diff --git a/libswscale/swscale_unscaled.c b/libswscale/swscale_unscaled.c
index 595edf8..9180f2e 100644
--- a/libswscale/swscale_unscaled.c
+++ b/libswscale/swscale_unscaled.c
@@ -1,20 +1,20 @@
/*
- * Copyright (C) 2001-2003 Michael Niedermayer <michaelni@gmx.at>
+ * Copyright (C) 2001-2011 Michael Niedermayer <michaelni@gmx.at>
*
- * This file is part of Libav.
+ * This file is part of FFmpeg.
*
- * Libav is free software; you can redistribute it and/or
+ * FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
- * Libav is distributed in the hope that it will be useful,
+ * FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
- * License along with Libav; if not, write to the Free Software
+ * License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
@@ -23,7 +23,6 @@
#include <math.h>
#include <stdio.h>
#include "config.h"
-#include <assert.h>
#include "swscale.h"
#include "swscale_internal.h"
#include "rgb2rgb.h"
@@ -33,48 +32,7 @@
#include "libavutil/mathematics.h"
#include "libavutil/bswap.h"
#include "libavutil/pixdesc.h"
-
-DECLARE_ALIGNED(8, const uint8_t, dither_8x8_1)[8][8] = {
- { 0, 1, 0, 1, 0, 1, 0, 1,},
- { 1, 0, 1, 0, 1, 0, 1, 0,},
- { 0, 1, 0, 1, 0, 1, 0, 1,},
- { 1, 0, 1, 0, 1, 0, 1, 0,},
- { 0, 1, 0, 1, 0, 1, 0, 1,},
- { 1, 0, 1, 0, 1, 0, 1, 0,},
- { 0, 1, 0, 1, 0, 1, 0, 1,},
- { 1, 0, 1, 0, 1, 0, 1, 0,},
-};
-DECLARE_ALIGNED(8, const uint8_t, dither_8x8_3)[8][8] = {
- { 1, 2, 1, 2, 1, 2, 1, 2,},
- { 3, 0, 3, 0, 3, 0, 3, 0,},
- { 1, 2, 1, 2, 1, 2, 1, 2,},
- { 3, 0, 3, 0, 3, 0, 3, 0,},
- { 1, 2, 1, 2, 1, 2, 1, 2,},
- { 3, 0, 3, 0, 3, 0, 3, 0,},
- { 1, 2, 1, 2, 1, 2, 1, 2,},
- { 3, 0, 3, 0, 3, 0, 3, 0,},
-};
-DECLARE_ALIGNED(8, const uint8_t, dither_8x8_64)[8][8] = {
- { 18, 34, 30, 46, 17, 33, 29, 45,},
- { 50, 2, 62, 14, 49, 1, 61, 13,},
- { 26, 42, 22, 38, 25, 41, 21, 37,},
- { 58, 10, 54, 6, 57, 9, 53, 5,},
- { 16, 32, 28, 44, 19, 35, 31, 47,},
- { 48, 0, 60, 12, 51, 3, 63, 15,},
- { 24, 40, 20, 36, 27, 43, 23, 39,},
- { 56, 8, 52, 4, 59, 11, 55, 7,},
-};
-extern const uint8_t dither_8x8_128[8][8];
-DECLARE_ALIGNED(8, const uint8_t, dither_8x8_256)[8][8] = {
- { 72, 136, 120, 184, 68, 132, 116, 180,},
- { 200, 8, 248, 56, 196, 4, 244, 52,},
- { 104, 168, 88, 152, 100, 164, 84, 148,},
- { 232, 40, 216, 24, 228, 36, 212, 20,},
- { 64, 128, 102, 176, 76, 140, 124, 188,},
- { 192, 0, 240, 48, 204, 12, 252, 60,},
- { 96, 160, 80, 144, 108, 172, 92, 156,},
- { 224, 32, 208, 16, 236, 44, 220, 28,},
-};
+#include "libavutil/avassert.h"
#define RGB2YUV_SHIFT 15
#define BY ( (int) (0.114 * 219 / 255 * (1 << RGB2YUV_SHIFT) + 0.5))
@@ -87,6 +45,102 @@ DECLARE_ALIGNED(8, const uint8_t, dither_8x8_256)[8][8] = {
#define RV ( (int) (0.500 * 224 / 255 * (1 << RGB2YUV_SHIFT) + 0.5))
#define RU (-(int) (0.169 * 224 / 255 * (1 << RGB2YUV_SHIFT) + 0.5))
+DECLARE_ALIGNED(8, const uint8_t, dithers)[8][8][8]={
+{
+ { 0, 1, 0, 1, 0, 1, 0, 1,},
+ { 1, 0, 1, 0, 1, 0, 1, 0,},
+ { 0, 1, 0, 1, 0, 1, 0, 1,},
+ { 1, 0, 1, 0, 1, 0, 1, 0,},
+ { 0, 1, 0, 1, 0, 1, 0, 1,},
+ { 1, 0, 1, 0, 1, 0, 1, 0,},
+ { 0, 1, 0, 1, 0, 1, 0, 1,},
+ { 1, 0, 1, 0, 1, 0, 1, 0,},
+},{
+ { 1, 2, 1, 2, 1, 2, 1, 2,},
+ { 3, 0, 3, 0, 3, 0, 3, 0,},
+ { 1, 2, 1, 2, 1, 2, 1, 2,},
+ { 3, 0, 3, 0, 3, 0, 3, 0,},
+ { 1, 2, 1, 2, 1, 2, 1, 2,},
+ { 3, 0, 3, 0, 3, 0, 3, 0,},
+ { 1, 2, 1, 2, 1, 2, 1, 2,},
+ { 3, 0, 3, 0, 3, 0, 3, 0,},
+},{
+ { 2, 4, 3, 5, 2, 4, 3, 5,},
+ { 6, 0, 7, 1, 6, 0, 7, 1,},
+ { 3, 5, 2, 4, 3, 5, 2, 4,},
+ { 7, 1, 6, 0, 7, 1, 6, 0,},
+ { 2, 4, 3, 5, 2, 4, 3, 5,},
+ { 6, 0, 7, 1, 6, 0, 7, 1,},
+ { 3, 5, 2, 4, 3, 5, 2, 4,},
+ { 7, 1, 6, 0, 7, 1, 6, 0,},
+},{
+ { 4, 8, 7, 11, 4, 8, 7, 11,},
+ { 12, 0, 15, 3, 12, 0, 15, 3,},
+ { 6, 10, 5, 9, 6, 10, 5, 9,},
+ { 14, 2, 13, 1, 14, 2, 13, 1,},
+ { 4, 8, 7, 11, 4, 8, 7, 11,},
+ { 12, 0, 15, 3, 12, 0, 15, 3,},
+ { 6, 10, 5, 9, 6, 10, 5, 9,},
+ { 14, 2, 13, 1, 14, 2, 13, 1,},
+},{
+ { 9, 17, 15, 23, 8, 16, 14, 22,},
+ { 25, 1, 31, 7, 24, 0, 30, 6,},
+ { 13, 21, 11, 19, 12, 20, 10, 18,},
+ { 29, 5, 27, 3, 28, 4, 26, 2,},
+ { 8, 16, 14, 22, 9, 17, 15, 23,},
+ { 24, 0, 30, 6, 25, 1, 31, 7,},
+ { 12, 20, 10, 18, 13, 21, 11, 19,},
+ { 28, 4, 26, 2, 29, 5, 27, 3,},
+},{
+ { 18, 34, 30, 46, 17, 33, 29, 45,},
+ { 50, 2, 62, 14, 49, 1, 61, 13,},
+ { 26, 42, 22, 38, 25, 41, 21, 37,},
+ { 58, 10, 54, 6, 57, 9, 53, 5,},
+ { 16, 32, 28, 44, 19, 35, 31, 47,},
+ { 48, 0, 60, 12, 51, 3, 63, 15,},
+ { 24, 40, 20, 36, 27, 43, 23, 39,},
+ { 56, 8, 52, 4, 59, 11, 55, 7,},
+},{
+ { 18, 34, 30, 46, 17, 33, 29, 45,},
+ { 50, 2, 62, 14, 49, 1, 61, 13,},
+ { 26, 42, 22, 38, 25, 41, 21, 37,},
+ { 58, 10, 54, 6, 57, 9, 53, 5,},
+ { 16, 32, 28, 44, 19, 35, 31, 47,},
+ { 48, 0, 60, 12, 51, 3, 63, 15,},
+ { 24, 40, 20, 36, 27, 43, 23, 39,},
+ { 56, 8, 52, 4, 59, 11, 55, 7,},
+},{
+ { 36, 68, 60, 92, 34, 66, 58, 90,},
+ { 100, 4,124, 28, 98, 2,122, 26,},
+ { 52, 84, 44, 76, 50, 82, 42, 74,},
+ { 116, 20,108, 12,114, 18,106, 10,},
+ { 32, 64, 56, 88, 38, 70, 62, 94,},
+ { 96, 0,120, 24,102, 6,126, 30,},
+ { 48, 80, 40, 72, 54, 86, 46, 78,},
+ { 112, 16,104, 8,118, 22,110, 14,},
+}};
+
+static const uint8_t flat64[8]={64,64,64,64,64,64,64,64};
+
+const uint16_t dither_scale[15][16]={
+{ 2, 3, 3, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,},
+{ 2, 3, 7, 7, 13, 13, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25,},
+{ 3, 3, 4, 15, 15, 29, 57, 57, 57, 113, 113, 113, 113, 113, 113, 113,},
+{ 3, 4, 4, 5, 31, 31, 61, 121, 241, 241, 241, 241, 481, 481, 481, 481,},
+{ 3, 4, 5, 5, 6, 63, 63, 125, 249, 497, 993, 993, 993, 993, 993, 1985,},
+{ 3, 5, 6, 6, 6, 7, 127, 127, 253, 505, 1009, 2017, 4033, 4033, 4033, 4033,},
+{ 3, 5, 6, 7, 7, 7, 8, 255, 255, 509, 1017, 2033, 4065, 8129,16257,16257,},
+{ 3, 5, 6, 8, 8, 8, 8, 9, 511, 511, 1021, 2041, 4081, 8161,16321,32641,},
+{ 3, 5, 7, 8, 9, 9, 9, 9, 10, 1023, 1023, 2045, 4089, 8177,16353,32705,},
+{ 3, 5, 7, 8, 10, 10, 10, 10, 10, 11, 2047, 2047, 4093, 8185,16369,32737,},
+{ 3, 5, 7, 8, 10, 11, 11, 11, 11, 11, 12, 4095, 4095, 8189,16377,32753,},
+{ 3, 5, 7, 9, 10, 12, 12, 12, 12, 12, 12, 13, 8191, 8191,16381,32761,},
+{ 3, 5, 7, 9, 10, 12, 13, 13, 13, 13, 13, 13, 14,16383,16383,32765,},
+{ 3, 5, 7, 9, 10, 12, 14, 14, 14, 14, 14, 14, 14, 15,32767,32767,},
+{ 3, 5, 7, 9, 11, 12, 14, 15, 15, 15, 15, 15, 15, 15, 16,65535,},
+};
+
+
static void fillPlane(uint8_t *plane, int stride, int width, int height, int y,
uint8_t val)
{
@@ -98,6 +152,20 @@ static void fillPlane(uint8_t *plane, int stride, int width, int height, int y,
}
}
+static void fillPlane16(uint8_t *plane, int stride, int width, int height, int y,
+ int alpha, int bits)
+{
+ int i, j;
+ uint8_t *ptr = plane + stride * y;
+ int v = alpha ? -1 : (1<<bits);
+ for (i = 0; i < height; i++) {
+ for (j = 0; j < width; j++) {
+ AV_WN16(ptr+2*j, v);
+ }
+ ptr += stride;
+ }
+}
+
static void copyPlane(const uint8_t *src, int srcStride,
int srcSliceY, int srcSliceH, int width,
uint8_t *dst, int dstStride)
@@ -310,7 +378,7 @@ static int palToRgbWrapper(SwsContext *c, const uint8_t *src[], int srcStride[],
uint8_t *dstPtr = dst[0] + dstStride[0] * srcSliceY;
const uint8_t *srcPtr = src[0];
- if (srcFormat == PIX_FMT_Y400A) {
+ if (srcFormat == PIX_FMT_GRAY8A) {
switch (dstFormat) {
case PIX_FMT_RGB32 : conv = gray8aToPacked32; break;
case PIX_FMT_BGR32 : conv = gray8aToPacked32; break;
@@ -332,7 +400,7 @@ static int palToRgbWrapper(SwsContext *c, const uint8_t *src[], int srcStride[],
if (!conv)
av_log(c, AV_LOG_ERROR, "internal error %s -> %s converter\n",
- sws_format_name(srcFormat), sws_format_name(dstFormat));
+ av_get_pix_fmt_name(srcFormat), av_get_pix_fmt_name(dstFormat));
else {
for (i = 0; i < srcSliceH; i++) {
conv(srcPtr, dstPtr, c->srcW, (uint8_t *) c->pal_rgb);
@@ -453,6 +521,20 @@ static int planarRgbToRgbWrapper(SwsContext *c, const uint8_t *src[],
|| (x) == PIX_FMT_ABGR \
)
+#define isRGBA64(x) ( \
+ (x) == PIX_FMT_RGBA64LE \
+ || (x) == PIX_FMT_RGBA64BE \
+ || (x) == PIX_FMT_BGRA64LE \
+ || (x) == PIX_FMT_BGRA64BE \
+ )
+
+#define isRGB48(x) ( \
+ (x) == PIX_FMT_RGB48LE \
+ || (x) == PIX_FMT_RGB48BE \
+ || (x) == PIX_FMT_BGR48LE \
+ || (x) == PIX_FMT_BGR48BE \
+ )
+
/* {RGB,BGR}{15,16,24,32,32_1} -> {RGB,BGR}{15,16,24,32} */
typedef void (* rgbConvFn) (const uint8_t *, uint8_t *, int);
static rgbConvFn findRgbConvFn(SwsContext *c)
@@ -467,10 +549,6 @@ static rgbConvFn findRgbConvFn(SwsContext *c)
(((bpp + 7) >> 3) == 2 && \
(!(av_pix_fmt_descriptors[fmt].flags & PIX_FMT_BE) != !HAVE_BIGENDIAN))
- /* if this is non-native rgb444/555/565, don't handle it here. */
- if (IS_NOT_NE(srcId, srcFormat) || IS_NOT_NE(dstId, dstFormat))
- return NULL;
-
#define CONV_IS(src, dst) (srcFormat == PIX_FMT_##src && dstFormat == PIX_FMT_##dst)
if (isRGBA32(srcFormat) && isRGBA32(dstFormat)) {
@@ -486,6 +564,32 @@ static rgbConvFn findRgbConvFn(SwsContext *c)
|| CONV_IS(RGBA, BGRA)) conv = shuffle_bytes_2103;
else if (CONV_IS(BGRA, ABGR)
|| CONV_IS(RGBA, ARGB)) conv = shuffle_bytes_3012;
+ } else if (isRGB48(srcFormat) && isRGB48(dstFormat)) {
+ if (CONV_IS(RGB48LE, BGR48LE)
+ || CONV_IS(BGR48LE, RGB48LE)
+ || CONV_IS(RGB48BE, BGR48BE)
+ || CONV_IS(BGR48BE, RGB48BE)) conv = rgb48tobgr48_nobswap;
+ else if (CONV_IS(RGB48LE, BGR48BE)
+ || CONV_IS(BGR48LE, RGB48BE)
+ || CONV_IS(RGB48BE, BGR48LE)
+ || CONV_IS(BGR48BE, RGB48LE)) conv = rgb48tobgr48_bswap;
+ } else if (isRGBA64(srcFormat) && isRGB48(dstFormat)) {
+ if (CONV_IS(RGBA64LE, BGR48LE)
+ || CONV_IS(BGRA64LE, RGB48LE)
+ || CONV_IS(RGBA64BE, BGR48BE)
+ || CONV_IS(BGRA64BE, RGB48BE)) conv = rgb64tobgr48_nobswap;
+ else if (CONV_IS(RGBA64LE, BGR48BE)
+ || CONV_IS(BGRA64LE, RGB48BE)
+ || CONV_IS(RGBA64BE, BGR48LE)
+ || CONV_IS(BGRA64BE, RGB48LE)) conv = rgb64tobgr48_bswap;
+ else if (CONV_IS(RGBA64LE, RGB48LE)
+ || CONV_IS(BGRA64LE, BGR48LE)
+ || CONV_IS(RGBA64BE, RGB48BE)
+ || CONV_IS(BGRA64BE, BGR48BE)) conv = rgb64to48_nobswap;
+ else if (CONV_IS(RGBA64LE, RGB48BE)
+ || CONV_IS(BGRA64LE, BGR48BE)
+ || CONV_IS(RGBA64BE, RGB48LE)
+ || CONV_IS(BGRA64BE, BGR48LE)) conv = rgb64to48_bswap;
} else
/* BGR -> BGR */
if ((isBGRinInt(srcFormat) && isBGRinInt(dstFormat)) ||
@@ -544,10 +648,13 @@ static int rgbToRgbWrapper(SwsContext *c, const uint8_t *src[], int srcStride[],
if (!conv) {
av_log(c, AV_LOG_ERROR, "internal error %s -> %s converter\n",
- sws_format_name(srcFormat), sws_format_name(dstFormat));
+ av_get_pix_fmt_name(srcFormat), av_get_pix_fmt_name(dstFormat));
} else {
const uint8_t *srcPtr = src[0];
uint8_t *dstPtr = dst[0];
+ int src_bswap = IS_NOT_NE(c->srcFormatBpp, srcFormat);
+ int dst_bswap = IS_NOT_NE(c->dstFormatBpp, dstFormat);
+
if ((srcFormat == PIX_FMT_RGB32_1 || srcFormat == PIX_FMT_BGR32_1) &&
!isRGBA32(dstFormat))
srcPtr += ALT32_CORR;
@@ -557,15 +664,23 @@ static int rgbToRgbWrapper(SwsContext *c, const uint8_t *src[], int srcStride[],
dstPtr += ALT32_CORR;
if (dstStride[0] * srcBpp == srcStride[0] * dstBpp && srcStride[0] > 0 &&
- !(srcStride[0] % srcBpp))
+ !(srcStride[0] % srcBpp) && !dst_bswap && !src_bswap)
conv(srcPtr, dstPtr + dstStride[0] * srcSliceY,
srcSliceH * srcStride[0]);
else {
- int i;
+ int i, j;
dstPtr += dstStride[0] * srcSliceY;
for (i = 0; i < srcSliceH; i++) {
- conv(srcPtr, dstPtr, c->srcW * srcBpp);
+ if(src_bswap) {
+ for(j=0; j<c->srcW; j++)
+ ((uint16_t*)c->formatConvBuffer)[j] = av_bswap16(((uint16_t*)srcPtr)[j]);
+ conv(c->formatConvBuffer, dstPtr, c->srcW * srcBpp);
+ }else
+ conv(srcPtr, dstPtr, c->srcW * srcBpp);
+ if(dst_bswap)
+ for(j=0; j<c->srcW; j++)
+ ((uint16_t*)dstPtr)[j] = av_bswap16(((uint16_t*)dstPtr)[j]);
srcPtr += srcStride[0];
dstPtr += dstStride[0];
}
@@ -623,7 +738,7 @@ static int packedCopyWrapper(SwsContext *c, const uint8_t *src[],
while (length + c->srcW <= FFABS(dstStride[0]) &&
length + c->srcW <= FFABS(srcStride[0]))
length += c->srcW;
- assert(length != 0);
+ av_assert1(length != 0);
for (i = 0; i < srcSliceH; i++) {
memcpy(dstPtr, srcPtr, length);
@@ -634,25 +749,25 @@ static int packedCopyWrapper(SwsContext *c, const uint8_t *src[],
return srcSliceH;
}
-#define clip9(x) av_clip_uintp2(x, 9)
-#define clip10(x) av_clip_uintp2(x, 10)
-#define DITHER_COPY(dst, dstStride, wfunc, src, srcStride, rfunc, dithers, shift, clip) \
- for (i = 0; i < height; i++) { \
- const uint8_t *dither = dithers[i & 7]; \
- for (j = 0; j < length - 7; j += 8) { \
- wfunc(&dst[j + 0], clip((rfunc(&src[j + 0]) + dither[0]) >> shift)); \
- wfunc(&dst[j + 1], clip((rfunc(&src[j + 1]) + dither[1]) >> shift)); \
- wfunc(&dst[j + 2], clip((rfunc(&src[j + 2]) + dither[2]) >> shift)); \
- wfunc(&dst[j + 3], clip((rfunc(&src[j + 3]) + dither[3]) >> shift)); \
- wfunc(&dst[j + 4], clip((rfunc(&src[j + 4]) + dither[4]) >> shift)); \
- wfunc(&dst[j + 5], clip((rfunc(&src[j + 5]) + dither[5]) >> shift)); \
- wfunc(&dst[j + 6], clip((rfunc(&src[j + 6]) + dither[6]) >> shift)); \
- wfunc(&dst[j + 7], clip((rfunc(&src[j + 7]) + dither[7]) >> shift)); \
- } \
- for (; j < length; j++) \
- wfunc(&dst[j], (rfunc(&src[j]) + dither[j & 7]) >> shift); \
- dst += dstStride; \
- src += srcStride; \
+#define DITHER_COPY(dst, dstStride, src, srcStride, bswap, dbswap)\
+ uint16_t scale= dither_scale[dst_depth-1][src_depth-1];\
+ int shift= src_depth-dst_depth + dither_scale[src_depth-2][dst_depth-1];\
+ for (i = 0; i < height; i++) {\
+ const uint8_t *dither= dithers[src_depth-9][i&7];\
+ for (j = 0; j < length-7; j+=8){\
+ dst[j+0] = dbswap((bswap(src[j+0]) + dither[0])*scale>>shift);\
+ dst[j+1] = dbswap((bswap(src[j+1]) + dither[1])*scale>>shift);\
+ dst[j+2] = dbswap((bswap(src[j+2]) + dither[2])*scale>>shift);\
+ dst[j+3] = dbswap((bswap(src[j+3]) + dither[3])*scale>>shift);\
+ dst[j+4] = dbswap((bswap(src[j+4]) + dither[4])*scale>>shift);\
+ dst[j+5] = dbswap((bswap(src[j+5]) + dither[5])*scale>>shift);\
+ dst[j+6] = dbswap((bswap(src[j+6]) + dither[6])*scale>>shift);\
+ dst[j+7] = dbswap((bswap(src[j+7]) + dither[7])*scale>>shift);\
+ }\
+ for (; j < length; j++)\
+ dst[j] = dbswap((bswap(src[j]) + dither[j&7])*scale>>shift);\
+ dst += dstStride;\
+ src += srcStride;\
}
static int planarCopyWrapper(SwsContext *c, const uint8_t *src[],
@@ -666,162 +781,126 @@ static int planarCopyWrapper(SwsContext *c, const uint8_t *src[],
int height = (plane == 0 || plane == 3) ? srcSliceH: -((-srcSliceH) >> c->chrDstVSubSample);
const uint8_t *srcPtr = src[plane];
uint8_t *dstPtr = dst[plane] + dstStride[plane] * y;
+ int shiftonly= plane==1 || plane==2 || (!c->srcRange && plane==0);
if (!dst[plane])
continue;
// ignore palette for GRAY8
if (plane == 1 && !dst[2]) continue;
if (!src[plane] || (plane == 1 && !src[2])) {
- if (is16BPS(c->dstFormat))
- length *= 2;
- fillPlane(dst[plane], dstStride[plane], length, height, y,
- (plane == 3) ? 255 : 128);
+ if (is16BPS(c->dstFormat) || isNBPS(c->dstFormat)) {
+ fillPlane16(dst[plane], dstStride[plane], length, height, y,
+ plane == 3, av_pix_fmt_descriptors[c->dstFormat].comp[plane].depth_minus1);
+ } else {
+ fillPlane(dst[plane], dstStride[plane], length, height, y,
+ (plane == 3) ? 255 : 128);
+ }
} else {
- if (is9_OR_10BPS(c->srcFormat)) {
+ if(isNBPS(c->srcFormat) || isNBPS(c->dstFormat)
+ || (is16BPS(c->srcFormat) != is16BPS(c->dstFormat))
+ ) {
const int src_depth = av_pix_fmt_descriptors[c->srcFormat].comp[plane].depth_minus1 + 1;
const int dst_depth = av_pix_fmt_descriptors[c->dstFormat].comp[plane].depth_minus1 + 1;
const uint16_t *srcPtr2 = (const uint16_t *) srcPtr;
+ uint16_t *dstPtr2 = (uint16_t*)dstPtr;
- if (is16BPS(c->dstFormat)) {
- uint16_t *dstPtr2 = (uint16_t *) dstPtr;
-#define COPY9_OR_10TO16(rfunc, wfunc) \
- for (i = 0; i < height; i++) { \
- for (j = 0; j < length; j++) { \
- int srcpx = rfunc(&srcPtr2[j]); \
- wfunc(&dstPtr2[j], (srcpx << (16 - src_depth)) | (srcpx >> (2 * src_depth - 16))); \
- } \
- dstPtr2 += dstStride[plane] / 2; \
- srcPtr2 += srcStride[plane] / 2; \
+ if (dst_depth == 8) {
+ if(isBE(c->srcFormat) == HAVE_BIGENDIAN){
+ DITHER_COPY(dstPtr, dstStride[plane], srcPtr2, srcStride[plane]/2, , )
+ } else {
+ DITHER_COPY(dstPtr, dstStride[plane], srcPtr2, srcStride[plane]/2, av_bswap16, )
}
- if (isBE(c->dstFormat)) {
- if (isBE(c->srcFormat)) {
- COPY9_OR_10TO16(AV_RB16, AV_WB16);
- } else {
- COPY9_OR_10TO16(AV_RL16, AV_WB16);
+ } else if (src_depth == 8) {
+ for (i = 0; i < height; i++) {
+ #define COPY816(w)\
+ if(shiftonly){\
+ for (j = 0; j < length; j++)\
+ w(&dstPtr2[j], srcPtr[j]<<(dst_depth-8));\
+ }else{\
+ for (j = 0; j < length; j++)\
+ w(&dstPtr2[j], (srcPtr[j]<<(dst_depth-8)) |\
+ (srcPtr[j]>>(2*8-dst_depth)));\
}
- } else {
- if (isBE(c->srcFormat)) {
- COPY9_OR_10TO16(AV_RB16, AV_WL16);
+ if(isBE(c->dstFormat)){
+ COPY816(AV_WB16)
} else {
- COPY9_OR_10TO16(AV_RL16, AV_WL16);
+ COPY816(AV_WL16)
}
+ dstPtr2 += dstStride[plane]/2;
+ srcPtr += srcStride[plane];
}
- } else if (is9_OR_10BPS(c->dstFormat)) {
- uint16_t *dstPtr2 = (uint16_t *) dstPtr;
-#define COPY9_OR_10TO9_OR_10(loop) \
- for (i = 0; i < height; i++) { \
- for (j = 0; j < length; j++) { \
- loop; \
- } \
- dstPtr2 += dstStride[plane] / 2; \
- srcPtr2 += srcStride[plane] / 2; \
- }
-#define COPY9_OR_10TO9_OR_10_2(rfunc, wfunc) \
- if (dst_depth > src_depth) { \
- COPY9_OR_10TO9_OR_10(int srcpx = rfunc(&srcPtr2[j]); \
- wfunc(&dstPtr2[j], (srcpx << 1) | (srcpx >> 9))); \
- } else if (dst_depth < src_depth) { \
- DITHER_COPY(dstPtr2, dstStride[plane] / 2, wfunc, \
- srcPtr2, srcStride[plane] / 2, rfunc, \
- dither_8x8_1, 1, clip9); \
- } else { \
- COPY9_OR_10TO9_OR_10(wfunc(&dstPtr2[j], rfunc(&srcPtr2[j]))); \
- }
- if (isBE(c->dstFormat)) {
- if (isBE(c->srcFormat)) {
- COPY9_OR_10TO9_OR_10_2(AV_RB16, AV_WB16);
- } else {
- COPY9_OR_10TO9_OR_10_2(AV_RL16, AV_WB16);
+ } else if (src_depth <= dst_depth) {
+ int orig_length = length;
+ for (i = 0; i < height; i++) {
+ if(isBE(c->srcFormat) == HAVE_BIGENDIAN &&
+ isBE(c->dstFormat) == HAVE_BIGENDIAN &&
+ shiftonly) {
+ unsigned shift = dst_depth - src_depth;
+ length = orig_length;
+#if HAVE_FAST_64BIT
+#define FAST_COPY_UP(shift) \
+ for (j = 0; j < length - 3; j += 4) { \
+ uint64_t v = AV_RN64A(srcPtr2 + j); \
+ AV_WN64A(dstPtr2 + j, v << shift); \
+ } \
+ length &= 3;
+#else
+#define FAST_COPY_UP(shift) \
+ for (j = 0; j < length - 1; j += 2) { \
+ uint32_t v = AV_RN32A(srcPtr2 + j); \
+ AV_WN32A(dstPtr2 + j, v << shift); \
+ } \
+ length &= 1;
+#endif
+ switch (shift)
+ {
+ case 6: FAST_COPY_UP(6); break;
+ case 7: FAST_COPY_UP(7); break;
+ }
}
- } else {
- if (isBE(c->srcFormat)) {
- COPY9_OR_10TO9_OR_10_2(AV_RB16, AV_WL16);
+#define COPY_UP(r,w) \
+ if(shiftonly){\
+ for (j = 0; j < length; j++){ \
+ unsigned int v= r(&srcPtr2[j]);\
+ w(&dstPtr2[j], v<<(dst_depth-src_depth));\
+ }\
+ }else{\
+ for (j = 0; j < length; j++){ \
+ unsigned int v= r(&srcPtr2[j]);\
+ w(&dstPtr2[j], (v<<(dst_depth-src_depth)) | \
+ (v>>(2*src_depth-dst_depth)));\
+ }\
+ }
+ if(isBE(c->srcFormat)){
+ if(isBE(c->dstFormat)){
+ COPY_UP(AV_RB16, AV_WB16)
+ } else {
+ COPY_UP(AV_RB16, AV_WL16)
+ }
} else {
- COPY9_OR_10TO9_OR_10_2(AV_RL16, AV_WL16);
+ if(isBE(c->dstFormat)){
+ COPY_UP(AV_RL16, AV_WB16)
+ } else {
+ COPY_UP(AV_RL16, AV_WL16)
+ }
}
+ dstPtr2 += dstStride[plane]/2;
+ srcPtr2 += srcStride[plane]/2;
}
} else {
-#define W8(a, b) { *(a) = (b); }
-#define COPY9_OR_10TO8(rfunc) \
- if (src_depth == 9) { \
- DITHER_COPY(dstPtr, dstStride[plane], W8, \
- srcPtr2, srcStride[plane] / 2, rfunc, \
- dither_8x8_1, 1, av_clip_uint8); \
- } else { \
- DITHER_COPY(dstPtr, dstStride[plane], W8, \
- srcPtr2, srcStride[plane] / 2, rfunc, \
- dither_8x8_3, 2, av_clip_uint8); \
- }
- if (isBE(c->srcFormat)) {
- COPY9_OR_10TO8(AV_RB16);
- } else {
- COPY9_OR_10TO8(AV_RL16);
- }
- }
- } else if (is9_OR_10BPS(c->dstFormat)) {
- const int dst_depth = av_pix_fmt_descriptors[c->dstFormat].comp[plane].depth_minus1 + 1;
- uint16_t *dstPtr2 = (uint16_t *) dstPtr;
-
- if (is16BPS(c->srcFormat)) {
- const uint16_t *srcPtr2 = (const uint16_t *) srcPtr;
-#define COPY16TO9_OR_10(rfunc, wfunc) \
- if (dst_depth == 9) { \
- DITHER_COPY(dstPtr2, dstStride[plane] / 2, wfunc, \
- srcPtr2, srcStride[plane] / 2, rfunc, \
- dither_8x8_128, 7, clip9); \
- } else { \
- DITHER_COPY(dstPtr2, dstStride[plane] / 2, wfunc, \
- srcPtr2, srcStride[plane] / 2, rfunc, \
- dither_8x8_64, 6, clip10); \
- }
- if (isBE(c->dstFormat)) {
- if (isBE(c->srcFormat)) {
- COPY16TO9_OR_10(AV_RB16, AV_WB16);
+ if(isBE(c->srcFormat) == HAVE_BIGENDIAN){
+ if(isBE(c->dstFormat) == HAVE_BIGENDIAN){
+ DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, , )
} else {
- COPY16TO9_OR_10(AV_RL16, AV_WB16);
+ DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, , av_bswap16)
}
- } else {
- if (isBE(c->srcFormat)) {
- COPY16TO9_OR_10(AV_RB16, AV_WL16);
+ }else{
+ if(isBE(c->dstFormat) == HAVE_BIGENDIAN){
+ DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, av_bswap16, )
} else {
- COPY16TO9_OR_10(AV_RL16, AV_WL16);
+ DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, av_bswap16, av_bswap16)
}
}
- } else /* 8bit */ {
-#define COPY8TO9_OR_10(wfunc) \
- for (i = 0; i < height; i++) { \
- for (j = 0; j < length; j++) { \
- const int srcpx = srcPtr[j]; \
- wfunc(&dstPtr2[j], (srcpx << (dst_depth - 8)) | (srcpx >> (16 - dst_depth))); \
- } \
- dstPtr2 += dstStride[plane] / 2; \
- srcPtr += srcStride[plane]; \
- }
- if (isBE(c->dstFormat)) {
- COPY8TO9_OR_10(AV_WB16);
- } else {
- COPY8TO9_OR_10(AV_WL16);
- }
- }
- } else if (is16BPS(c->srcFormat) && !is16BPS(c->dstFormat)) {
- const uint16_t *srcPtr2 = (const uint16_t *) srcPtr;
-#define COPY16TO8(rfunc) \
- DITHER_COPY(dstPtr, dstStride[plane], W8, \
- srcPtr2, srcStride[plane] / 2, rfunc, \
- dither_8x8_256, 8, av_clip_uint8);
- if (isBE(c->srcFormat)) {
- COPY16TO8(AV_RB16);
- } else {
- COPY16TO8(AV_RL16);
- }
- } else if (!is16BPS(c->srcFormat) && is16BPS(c->dstFormat)) {
- for (i = 0; i < height; i++) {
- for (j = 0; j < length; j++) {
- dstPtr[ j << 1 ] = srcPtr[j];
- dstPtr[(j << 1) + 1] = srcPtr[j];
- }
- srcPtr += srcStride[plane];
- dstPtr += dstStride[plane];
}
} else if (is16BPS(c->srcFormat) && is16BPS(c->dstFormat) &&
isBE(c->srcFormat) != isBE(c->dstFormat)) {
@@ -899,28 +978,32 @@ void ff_get_unscaled_swscale(SwsContext *c)
&& (!needsDither || (c->flags&(SWS_FAST_BILINEAR|SWS_POINT))))
c->swScale= rgbToRgbWrapper;
- if (isPlanarRGB(srcFormat) && isPackedRGB(dstFormat))
+#define isByteRGB(f) (\
+ f == PIX_FMT_RGB32 ||\
+ f == PIX_FMT_RGB32_1 ||\
+ f == PIX_FMT_RGB24 ||\
+ f == PIX_FMT_BGR32 ||\
+ f == PIX_FMT_BGR32_1 ||\
+ f == PIX_FMT_BGR24)
+
+ if (isAnyRGB(srcFormat) && isPlanar(srcFormat) && isByteRGB(dstFormat))
c->swScale = planarRgbToRgbWrapper;
/* bswap 16 bits per pixel/component packed formats */
if (IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, PIX_FMT_BGR444) ||
IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, PIX_FMT_BGR48) ||
+ IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, PIX_FMT_BGRA64) ||
IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, PIX_FMT_BGR555) ||
IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, PIX_FMT_BGR565) ||
IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, PIX_FMT_GRAY16) ||
IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, PIX_FMT_RGB444) ||
IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, PIX_FMT_RGB48) ||
+ IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, PIX_FMT_RGBA64) ||
IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, PIX_FMT_RGB555) ||
IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, PIX_FMT_RGB565))
c->swScale = packed_16bpc_bswap;
- if ((usePal(srcFormat) && (
- dstFormat == PIX_FMT_RGB32 ||
- dstFormat == PIX_FMT_RGB32_1 ||
- dstFormat == PIX_FMT_RGB24 ||
- dstFormat == PIX_FMT_BGR32 ||
- dstFormat == PIX_FMT_BGR32_1 ||
- dstFormat == PIX_FMT_BGR24)))
+ if (usePal(srcFormat) && isByteRGB(dstFormat))
c->swScale = palToRgbWrapper;
if (srcFormat == PIX_FMT_YUV422P) {
@@ -951,13 +1034,14 @@ void ff_get_unscaled_swscale(SwsContext *c)
if (srcFormat == PIX_FMT_UYVY422 && dstFormat == PIX_FMT_YUV422P)
c->swScale = uyvyToYuv422Wrapper;
+#define isPlanarGray(x) (isGray(x) && (x) != PIX_FMT_GRAY8A)
/* simple copy */
if ( srcFormat == dstFormat ||
(srcFormat == PIX_FMT_YUVA420P && dstFormat == PIX_FMT_YUV420P) ||
(srcFormat == PIX_FMT_YUV420P && dstFormat == PIX_FMT_YUVA420P) ||
- (isPlanarYUV(srcFormat) && isGray(dstFormat)) ||
- (isPlanarYUV(dstFormat) && isGray(srcFormat)) ||
- (isGray(dstFormat) && isGray(srcFormat)) ||
+ (isPlanarYUV(srcFormat) && isPlanarGray(dstFormat)) ||
+ (isPlanarYUV(dstFormat) && isPlanarGray(srcFormat)) ||
+ (isPlanarGray(dstFormat) && isPlanarGray(srcFormat)) ||
(isPlanarYUV(srcFormat) && isPlanarYUV(dstFormat) &&
c->chrDstHSubSample == c->chrSrcHSubSample &&
c->chrDstVSubSample == c->chrSrcVSubSample &&
@@ -988,7 +1072,7 @@ static void reset_ptr(const uint8_t *src[], int format)
}
}
-static int check_image_pointers(uint8_t *data[4], enum PixelFormat pix_fmt,
+static int check_image_pointers(const uint8_t * const data[4], enum PixelFormat pix_fmt,
const int linesizes[4])
{
const AVPixFmtDescriptor *desc = &av_pix_fmt_descriptors[pix_fmt];
@@ -1013,9 +1097,10 @@ int attribute_align_arg sws_scale(struct SwsContext *c,
int srcSliceH, uint8_t *const dst[],
const int dstStride[])
{
- int i;
+ int i, ret;
const uint8_t *src2[4] = { srcSlice[0], srcSlice[1], srcSlice[2], srcSlice[3] };
uint8_t *dst2[4] = { dst[0], dst[1], dst[2], dst[3] };
+ uint8_t *rgb0_tmp = NULL;
// do not mess up sliceDir if we have a "trailing" 0-size slice
if (srcSliceH == 0)
@@ -1025,7 +1110,7 @@ int attribute_align_arg sws_scale(struct SwsContext *c,
av_log(c, AV_LOG_ERROR, "bad src image pointers\n");
return 0;
}
- if (!check_image_pointers(dst, c->dstFormat, dstStride)) {
+ if (!check_image_pointers((const uint8_t* const*)dst, c->dstFormat, dstStride)) {
av_log(c, AV_LOG_ERROR, "bad dst image pointers\n");
return 0;
}
@@ -1040,9 +1125,10 @@ int attribute_align_arg sws_scale(struct SwsContext *c,
if (usePal(c->srcFormat)) {
for (i = 0; i < 256; i++) {
- int p, r, g, b, y, u, v;
+ int p, r, g, b, y, u, v, a = 0xff;
if (c->srcFormat == PIX_FMT_PAL8) {
p = ((const uint32_t *)(srcSlice[1]))[i];
+ a = (p >> 24) & 0xFF;
r = (p >> 16) & 0xFF;
g = (p >> 8) & 0xFF;
b = p & 0xFF;
@@ -1058,11 +1144,10 @@ int attribute_align_arg sws_scale(struct SwsContext *c,
r = ( i >> 3 ) * 255;
g = ((i >> 1) & 3) * 85;
b = ( i & 1) * 255;
- } else if (c->srcFormat == PIX_FMT_GRAY8 ||
- c->srcFormat == PIX_FMT_Y400A) {
+ } else if (c->srcFormat == PIX_FMT_GRAY8 || c->srcFormat == PIX_FMT_GRAY8A) {
r = g = b = i;
} else {
- assert(c->srcFormat == PIX_FMT_BGR4_BYTE);
+ av_assert1(c->srcFormat == PIX_FMT_BGR4_BYTE);
b = ( i >> 3 ) * 255;
g = ((i >> 1) & 3) * 85;
r = ( i & 1) * 255;
@@ -1070,37 +1155,51 @@ int attribute_align_arg sws_scale(struct SwsContext *c,
y = av_clip_uint8((RY * r + GY * g + BY * b + ( 33 << (RGB2YUV_SHIFT - 1))) >> RGB2YUV_SHIFT);
u = av_clip_uint8((RU * r + GU * g + BU * b + (257 << (RGB2YUV_SHIFT - 1))) >> RGB2YUV_SHIFT);
v = av_clip_uint8((RV * r + GV * g + BV * b + (257 << (RGB2YUV_SHIFT - 1))) >> RGB2YUV_SHIFT);
- c->pal_yuv[i] = y + (u << 8) + (v << 16);
+ c->pal_yuv[i]= y + (u<<8) + (v<<16) + (a<<24);
switch (c->dstFormat) {
case PIX_FMT_BGR32:
#if !HAVE_BIGENDIAN
case PIX_FMT_RGB24:
#endif
- c->pal_rgb[i] = r + (g << 8) + (b << 16);
+ c->pal_rgb[i]= r + (g<<8) + (b<<16) + (a<<24);
break;
case PIX_FMT_BGR32_1:
#if HAVE_BIGENDIAN
case PIX_FMT_BGR24:
#endif
- c->pal_rgb[i] = (r + (g << 8) + (b << 16)) << 8;
+ c->pal_rgb[i]= a + (r<<8) + (g<<16) + (b<<24);
break;
case PIX_FMT_RGB32_1:
#if HAVE_BIGENDIAN
case PIX_FMT_RGB24:
#endif
- c->pal_rgb[i] = (b + (g << 8) + (r << 16)) << 8;
+ c->pal_rgb[i]= a + (b<<8) + (g<<16) + (r<<24);
break;
case PIX_FMT_RGB32:
#if !HAVE_BIGENDIAN
case PIX_FMT_BGR24:
#endif
default:
- c->pal_rgb[i] = b + (g << 8) + (r << 16);
+ c->pal_rgb[i]= b + (g<<8) + (r<<16) + (a<<24);
}
}
}
+ if (c->src0Alpha && !c->dst0Alpha && isALPHA(c->dstFormat)) {
+ uint8_t *base;
+ int x,y;
+ rgb0_tmp = av_malloc(FFABS(srcStride[0]) * srcSliceH + 32);
+ base = srcStride[0] < 0 ? rgb0_tmp - srcStride[0] * (srcSliceH-1) : rgb0_tmp;
+ for (y=0; y<srcSliceH; y++){
+ memcpy(base + srcStride[0]*y, src2[0] + srcStride[0]*y, 4*c->srcW);
+ for (x=c->src0Alpha-1; x<4*c->srcW; x+=4) {
+ base[ srcStride[0]*y + x] = 0xFF;
+ }
+ }
+ src2[0] = base;
+ }
+
// copy strides, so they can safely be modified
if (c->sliceDir == 1) {
// slices go from top to bottom
@@ -1110,13 +1209,13 @@ int attribute_align_arg sws_scale(struct SwsContext *c,
dstStride[3] };
reset_ptr(src2, c->srcFormat);
- reset_ptr((const uint8_t **) dst2, c->dstFormat);
+ reset_ptr((void*)dst2, c->dstFormat);
/* reset slice direction at end of frame */
if (srcSliceY + srcSliceH == c->srcH)
c->sliceDir = 0;
- return c->swScale(c, src2, srcStride2, srcSliceY, srcSliceH, dst2,
+ ret = c->swScale(c, src2, srcStride2, srcSliceY, srcSliceH, dst2,
dstStride2);
} else {
// slices go from bottom to top => we flip the image internally
@@ -1136,15 +1235,18 @@ int attribute_align_arg sws_scale(struct SwsContext *c,
dst2[3] += ( c->dstH - 1) * dstStride[3];
reset_ptr(src2, c->srcFormat);
- reset_ptr((const uint8_t **) dst2, c->dstFormat);
+ reset_ptr((void*)dst2, c->dstFormat);
/* reset slice direction at end of frame */
if (!srcSliceY)
c->sliceDir = 0;
- return c->swScale(c, src2, srcStride2, c->srcH-srcSliceY-srcSliceH,
+ ret = c->swScale(c, src2, srcStride2, c->srcH-srcSliceY-srcSliceH,
srcSliceH, dst2, dstStride2);
}
+
+ av_free(rgb0_tmp);
+ return ret;
}
/* Convert the palette to the same packed 32-bit format as the palette */
OpenPOWER on IntegriCloud