swscale_unscaled.c 78.9 KB
Newer Older
1
/*
2
 * Copyright (C) 2001-2011 Michael Niedermayer <michaelni@gmx.at>
3
 *
4
 * This file is part of FFmpeg.
5
 *
6
 * FFmpeg is free software; you can redistribute it and/or
7 8 9 10
 * 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.
 *
11
 * FFmpeg is distributed in the hope that it will be useful,
12 13 14 15 16
 * 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
17
 * License along with FFmpeg; if not, write to the Free Software
18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#include <inttypes.h>
#include <string.h>
#include <math.h>
#include <stdio.h>
#include "config.h"
#include "swscale.h"
#include "swscale_internal.h"
#include "rgb2rgb.h"
#include "libavutil/intreadwrite.h"
#include "libavutil/cpu.h"
#include "libavutil/avutil.h"
#include "libavutil/mathematics.h"
#include "libavutil/bswap.h"
#include "libavutil/pixdesc.h"
35
#include "libavutil/avassert.h"
36
#include "libavutil/avconfig.h"
37

38
DECLARE_ALIGNED(8, static const uint8_t, dithers)[8][8][8]={
39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112
{
  {   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,},
}};

113
static const uint16_t dither_scale[15][16]={
114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131
{    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,},
};


132 133
static void fillPlane(uint8_t *plane, int stride, int width, int height, int y,
                      uint8_t val)
134 135
{
    int i;
136 137
    uint8_t *ptr = plane + stride * y;
    for (i = 0; i < height; i++) {
138 139 140 141 142 143 144 145 146 147 148 149 150 151
        memset(ptr, val, width);
        ptr += stride;
    }
}

static void copyPlane(const uint8_t *src, int srcStride,
                      int srcSliceY, int srcSliceH, int width,
                      uint8_t *dst, int dstStride)
{
    dst += dstStride * srcSliceY;
    if (dstStride == srcStride && srcStride > 0) {
        memcpy(dst, src, srcSliceH * dstStride);
    } else {
        int i;
152
        for (i = 0; i < srcSliceH; i++) {
153 154 155 156 157 158 159
            memcpy(dst, src, width);
            src += srcStride;
            dst += dstStride;
        }
    }
}

160 161 162 163
static int planarToNv12Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY,
                               int srcSliceH, uint8_t *dstParam[],
                               int dstStride[])
164
{
165
    uint8_t *dst = dstParam[1] + dstStride[1] * srcSliceY / 2;
166 167 168 169

    copyPlane(src[0], srcStride[0], srcSliceY, srcSliceH, c->srcW,
              dstParam[0], dstStride[0]);

170
    if (c->dstFormat == AV_PIX_FMT_NV12)
171
        interleaveBytes(src[1], src[2], dst, c->srcW / 2, srcSliceH / 2,
172
                        srcStride[1], srcStride[2], dstStride[1]);
173
    else
174
        interleaveBytes(src[2], src[1], dst, c->srcW / 2, srcSliceH / 2,
175
                        srcStride[2], srcStride[1], dstStride[1]);
176 177 178 179

    return srcSliceH;
}

180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
static int nv12ToPlanarWrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY,
                               int srcSliceH, uint8_t *dstParam[],
                               int dstStride[])
{
    uint8_t *dst1 = dstParam[1] + dstStride[1] * srcSliceY / 2;
    uint8_t *dst2 = dstParam[2] + dstStride[2] * srcSliceY / 2;

    copyPlane(src[0], srcStride[0], srcSliceY, srcSliceH, c->srcW,
              dstParam[0], dstStride[0]);

    if (c->srcFormat == AV_PIX_FMT_NV12)
        deinterleaveBytes(src[1], dst1, dst2,c->srcW / 2, srcSliceH / 2,
                          srcStride[1], dstStride[1], dstStride[2]);
    else
        deinterleaveBytes(src[1], dst2, dst1, c->srcW / 2, srcSliceH / 2,
                          srcStride[1], dstStride[2], dstStride[1]);

    return srcSliceH;
}

201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
static int planarToP010Wrapper(SwsContext *c, const uint8_t *src8[],
                               int srcStride[], int srcSliceY,
                               int srcSliceH, uint8_t *dstParam8[],
                               int dstStride[])
{
    const uint16_t **src = (const uint16_t**)src8;
    uint16_t *dstY = (uint16_t*)(dstParam8[0] + dstStride[0] * srcSliceY);
    uint16_t *dstUV = (uint16_t*)(dstParam8[1] + dstStride[1] * srcSliceY / 2);
    int x, y;

    av_assert0(!(srcStride[0] % 2 || srcStride[1] % 2 || srcStride[2] % 2 ||
                 dstStride[0] % 2 || dstStride[1] % 2));

    for (y = 0; y < srcSliceH; y++) {
        uint16_t *tdstY = dstY;
        const uint16_t *tsrc0 = src[0];
        for (x = c->srcW; x > 0; x--) {
            *tdstY++ = *tsrc0++ << 6;
        }
        src[0] += srcStride[0] / 2;
        dstY += dstStride[0] / 2;

        if (!(y & 1)) {
            uint16_t *tdstUV = dstUV;
            const uint16_t *tsrc1 = src[1];
            const uint16_t *tsrc2 = src[2];
            for (x = c->srcW / 2; x > 0; x--) {
                *tdstUV++ = *tsrc1++ << 6;
                *tdstUV++ = *tsrc2++ << 6;
            }
            src[1] += srcStride[1] / 2;
            src[2] += srcStride[2] / 2;
            dstUV += dstStride[1] / 2;
        }
    }

    return srcSliceH;
}

240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
#if AV_HAVE_BIGENDIAN
#define output_pixel(p, v) do { \
        uint16_t *pp = (p); \
        AV_WL16(pp, (v)); \
    } while(0)
#else
#define output_pixel(p, v) (*p) = (v)
#endif

static int planar8ToP01xleWrapper(SwsContext *c, const uint8_t *src[],
                                  int srcStride[], int srcSliceY,
                                  int srcSliceH, uint8_t *dstParam8[],
                                  int dstStride[])
{
    uint16_t *dstY = (uint16_t*)(dstParam8[0] + dstStride[0] * srcSliceY);
    uint16_t *dstUV = (uint16_t*)(dstParam8[1] + dstStride[1] * srcSliceY / 2);
    int x, y, t;

    av_assert0(!(dstStride[0] % 2 || dstStride[1] % 2));

    for (y = 0; y < srcSliceH; y++) {
        uint16_t *tdstY = dstY;
        const uint8_t *tsrc0 = src[0];
        for (x = c->srcW; x > 0; x--) {
            t = *tsrc0++;
            output_pixel(tdstY++, t | (t << 8));
        }
        src[0] += srcStride[0];
        dstY += dstStride[0] / 2;

        if (!(y & 1)) {
            uint16_t *tdstUV = dstUV;
            const uint8_t *tsrc1 = src[1];
            const uint8_t *tsrc2 = src[2];
            for (x = c->srcW / 2; x > 0; x--) {
                t = *tsrc1++;
                output_pixel(tdstUV++, t | (t << 8));
                t = *tsrc2++;
                output_pixel(tdstUV++, t | (t << 8));
            }
            src[1] += srcStride[1];
            src[2] += srcStride[2];
            dstUV += dstStride[1] / 2;
        }
    }

    return srcSliceH;
}

#undef output_pixel

291 292 293
static int planarToYuy2Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
294
{
295
    uint8_t *dst = dstParam[0] + dstStride[0] * srcSliceY;
296

297 298
    yv12toyuy2(src[0], src[1], src[2], dst, c->srcW, srcSliceH, srcStride[0],
               srcStride[1], dstStride[0]);
299 300 301 302

    return srcSliceH;
}

303 304 305
static int planarToUyvyWrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
306
{
307
    uint8_t *dst = dstParam[0] + dstStride[0] * srcSliceY;
308

309 310
    yv12touyvy(src[0], src[1], src[2], dst, c->srcW, srcSliceH, srcStride[0],
               srcStride[1], dstStride[0]);
311 312 313 314

    return srcSliceH;
}

315 316 317
static int yuv422pToYuy2Wrapper(SwsContext *c, const uint8_t *src[],
                                int srcStride[], int srcSliceY, int srcSliceH,
                                uint8_t *dstParam[], int dstStride[])
318
{
319
    uint8_t *dst = dstParam[0] + dstStride[0] * srcSliceY;
320

321 322
    yuv422ptoyuy2(src[0], src[1], src[2], dst, c->srcW, srcSliceH, srcStride[0],
                  srcStride[1], dstStride[0]);
323 324 325 326

    return srcSliceH;
}

327 328 329
static int yuv422pToUyvyWrapper(SwsContext *c, const uint8_t *src[],
                                int srcStride[], int srcSliceY, int srcSliceH,
                                uint8_t *dstParam[], int dstStride[])
330
{
331
    uint8_t *dst = dstParam[0] + dstStride[0] * srcSliceY;
332

333 334
    yuv422ptouyvy(src[0], src[1], src[2], dst, c->srcW, srcSliceH, srcStride[0],
                  srcStride[1], dstStride[0]);
335 336 337 338

    return srcSliceH;
}

339 340 341
static int yuyvToYuv420Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
342
{
343 344 345
    uint8_t *ydst = dstParam[0] + dstStride[0] * srcSliceY;
    uint8_t *udst = dstParam[1] + dstStride[1] * srcSliceY / 2;
    uint8_t *vdst = dstParam[2] + dstStride[2] * srcSliceY / 2;
346

347 348
    yuyvtoyuv420(ydst, udst, vdst, src[0], c->srcW, srcSliceH, dstStride[0],
                 dstStride[1], srcStride[0]);
349 350 351 352 353 354 355

    if (dstParam[3])
        fillPlane(dstParam[3], dstStride[3], c->srcW, srcSliceH, srcSliceY, 255);

    return srcSliceH;
}

356 357 358
static int yuyvToYuv422Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
359
{
360 361 362
    uint8_t *ydst = dstParam[0] + dstStride[0] * srcSliceY;
    uint8_t *udst = dstParam[1] + dstStride[1] * srcSliceY;
    uint8_t *vdst = dstParam[2] + dstStride[2] * srcSliceY;
363

364 365
    yuyvtoyuv422(ydst, udst, vdst, src[0], c->srcW, srcSliceH, dstStride[0],
                 dstStride[1], srcStride[0]);
366 367 368 369

    return srcSliceH;
}

370 371 372
static int uyvyToYuv420Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
373
{
374 375 376
    uint8_t *ydst = dstParam[0] + dstStride[0] * srcSliceY;
    uint8_t *udst = dstParam[1] + dstStride[1] * srcSliceY / 2;
    uint8_t *vdst = dstParam[2] + dstStride[2] * srcSliceY / 2;
377

378 379
    uyvytoyuv420(ydst, udst, vdst, src[0], c->srcW, srcSliceH, dstStride[0],
                 dstStride[1], srcStride[0]);
380 381 382 383 384 385 386

    if (dstParam[3])
        fillPlane(dstParam[3], dstStride[3], c->srcW, srcSliceH, srcSliceY, 255);

    return srcSliceH;
}

387 388 389
static int uyvyToYuv422Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
390
{
391 392 393
    uint8_t *ydst = dstParam[0] + dstStride[0] * srcSliceY;
    uint8_t *udst = dstParam[1] + dstStride[1] * srcSliceY;
    uint8_t *vdst = dstParam[2] + dstStride[2] * srcSliceY;
394

395 396
    uyvytoyuv422(ydst, udst, vdst, src[0], c->srcW, srcSliceH, dstStride[0],
                 dstStride[1], srcStride[0]);
397 398 399 400

    return srcSliceH;
}

401 402
static void gray8aToPacked32(const uint8_t *src, uint8_t *dst, int num_pixels,
                             const uint8_t *palette)
403 404
{
    int i;
405 406
    for (i = 0; i < num_pixels; i++)
        ((uint32_t *) dst)[i] = ((const uint32_t *) palette)[src[i << 1]] | (src[(i << 1) + 1] << 24);
407 408
}

409 410
static void gray8aToPacked32_1(const uint8_t *src, uint8_t *dst, int num_pixels,
                               const uint8_t *palette)
411 412 413
{
    int i;

414 415
    for (i = 0; i < num_pixels; i++)
        ((uint32_t *) dst)[i] = ((const uint32_t *) palette)[src[i << 1]] | src[(i << 1) + 1];
416 417
}

418 419
static void gray8aToPacked24(const uint8_t *src, uint8_t *dst, int num_pixels,
                             const uint8_t *palette)
420 421 422
{
    int i;

423
    for (i = 0; i < num_pixels; i++) {
424
        //FIXME slow?
425 426 427 428
        dst[0] = palette[src[i << 1] * 4 + 0];
        dst[1] = palette[src[i << 1] * 4 + 1];
        dst[2] = palette[src[i << 1] * 4 + 2];
        dst += 3;
429 430 431
    }
}

432
static int packed_16bpc_bswap(SwsContext *c, const uint8_t *src[],
433
                              int srcStride[], int srcSliceY, int srcSliceH,
434
                              uint8_t *dst[], int dstStride[])
435
{
436 437 438
    int i, j, p;

    for (p = 0; p < 4; p++) {
439 440
        int srcstr = srcStride[p] / 2;
        int dststr = dstStride[p] / 2;
441 442
        uint16_t       *dstPtr =       (uint16_t *) dst[p];
        const uint16_t *srcPtr = (const uint16_t *) src[p];
443
        int min_stride         = FFMIN(FFABS(srcstr), FFABS(dststr));
444 445
        if(!dstPtr || !srcPtr)
            continue;
446
        dstPtr += (srcSliceY >> c->chrDstVSubSample) * dststr;
447 448 449 450 451 452
        for (i = 0; i < (srcSliceH >> c->chrDstVSubSample); i++) {
            for (j = 0; j < min_stride; j++) {
                dstPtr[j] = av_bswap16(srcPtr[j]);
            }
            srcPtr += srcstr;
            dstPtr += dststr;
453 454 455 456 457 458
        }
    }

    return srcSliceH;
}

459 460 461
static int palToRgbWrapper(SwsContext *c, const uint8_t *src[], int srcStride[],
                           int srcSliceY, int srcSliceH, uint8_t *dst[],
                           int dstStride[])
462
{
463 464
    const enum AVPixelFormat srcFormat = c->srcFormat;
    const enum AVPixelFormat dstFormat = c->dstFormat;
465
    void (*conv)(const uint8_t *src, uint8_t *dst, int num_pixels,
466
                 const uint8_t *palette) = NULL;
467
    int i;
468 469
    uint8_t *dstPtr = dst[0] + dstStride[0] * srcSliceY;
    const uint8_t *srcPtr = src[0];
470

471
    if (srcFormat == AV_PIX_FMT_YA8) {
472
        switch (dstFormat) {
473 474 475 476 477 478
        case AV_PIX_FMT_RGB32  : conv = gray8aToPacked32; break;
        case AV_PIX_FMT_BGR32  : conv = gray8aToPacked32; break;
        case AV_PIX_FMT_BGR32_1: conv = gray8aToPacked32_1; break;
        case AV_PIX_FMT_RGB32_1: conv = gray8aToPacked32_1; break;
        case AV_PIX_FMT_RGB24  : conv = gray8aToPacked24; break;
        case AV_PIX_FMT_BGR24  : conv = gray8aToPacked24; break;
479 480 481
        }
    } else if (usePal(srcFormat)) {
        switch (dstFormat) {
482 483 484 485 486 487
        case AV_PIX_FMT_RGB32  : conv = sws_convertPalette8ToPacked32; break;
        case AV_PIX_FMT_BGR32  : conv = sws_convertPalette8ToPacked32; break;
        case AV_PIX_FMT_BGR32_1: conv = sws_convertPalette8ToPacked32; break;
        case AV_PIX_FMT_RGB32_1: conv = sws_convertPalette8ToPacked32; break;
        case AV_PIX_FMT_RGB24  : conv = sws_convertPalette8ToPacked24; break;
        case AV_PIX_FMT_BGR24  : conv = sws_convertPalette8ToPacked24; break;
488 489 490 491 492
        }
    }

    if (!conv)
        av_log(c, AV_LOG_ERROR, "internal error %s -> %s converter\n",
493
               av_get_pix_fmt_name(srcFormat), av_get_pix_fmt_name(dstFormat));
494
    else {
495
        for (i = 0; i < srcSliceH; i++) {
496
            conv(srcPtr, dstPtr, c->srcW, (uint8_t *) c->pal_rgb);
497 498
            srcPtr += srcStride[0];
            dstPtr += dstStride[0];
499 500 501 502 503 504
        }
    }

    return srcSliceH;
}

505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648
static void packed16togbra16(const uint8_t *src, int srcStride,
                             uint16_t *dst[], int dstStride[], int srcSliceH,
                             int src_alpha, int swap, int shift, int width)
{
    int x, h, i;
    int dst_alpha = dst[3] != NULL;
    for (h = 0; h < srcSliceH; h++) {
        uint16_t *src_line = (uint16_t *)(src + srcStride * h);
        switch (swap) {
        case 3:
            if (src_alpha && dst_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                    dst[1][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                    dst[2][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                    dst[3][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                }
            } else if (dst_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                    dst[1][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                    dst[2][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                    dst[3][x] = 0xFFFF;
                }
            } else if (src_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                    dst[1][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                    dst[2][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                    src_line++;
                }
            } else {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                    dst[1][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                    dst[2][x] = av_bswap16(av_bswap16(*src_line++) >> shift);
                }
            }
            break;
        case 2:
            if (src_alpha && dst_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(*src_line++ >> shift);
                    dst[1][x] = av_bswap16(*src_line++ >> shift);
                    dst[2][x] = av_bswap16(*src_line++ >> shift);
                    dst[3][x] = av_bswap16(*src_line++ >> shift);
                }
            } else if (dst_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(*src_line++ >> shift);
                    dst[1][x] = av_bswap16(*src_line++ >> shift);
                    dst[2][x] = av_bswap16(*src_line++ >> shift);
                    dst[3][x] = 0xFFFF;
                }
            } else if (src_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(*src_line++ >> shift);
                    dst[1][x] = av_bswap16(*src_line++ >> shift);
                    dst[2][x] = av_bswap16(*src_line++ >> shift);
                    src_line++;
                }
            } else {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(*src_line++ >> shift);
                    dst[1][x] = av_bswap16(*src_line++ >> shift);
                    dst[2][x] = av_bswap16(*src_line++ >> shift);
                }
            }
            break;
        case 1:
            if (src_alpha && dst_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(*src_line++) >> shift;
                    dst[1][x] = av_bswap16(*src_line++) >> shift;
                    dst[2][x] = av_bswap16(*src_line++) >> shift;
                    dst[3][x] = av_bswap16(*src_line++) >> shift;
                }
            } else if (dst_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(*src_line++) >> shift;
                    dst[1][x] = av_bswap16(*src_line++) >> shift;
                    dst[2][x] = av_bswap16(*src_line++) >> shift;
                    dst[3][x] = 0xFFFF;
                }
            } else if (src_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(*src_line++) >> shift;
                    dst[1][x] = av_bswap16(*src_line++) >> shift;
                    dst[2][x] = av_bswap16(*src_line++) >> shift;
                    src_line++;
                }
            } else {
                for (x = 0; x < width; x++) {
                    dst[0][x] = av_bswap16(*src_line++) >> shift;
                    dst[1][x] = av_bswap16(*src_line++) >> shift;
                    dst[2][x] = av_bswap16(*src_line++) >> shift;
                }
            }
            break;
        default:
            if (src_alpha && dst_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = *src_line++ >> shift;
                    dst[1][x] = *src_line++ >> shift;
                    dst[2][x] = *src_line++ >> shift;
                    dst[3][x] = *src_line++ >> shift;
                }
            } else if (dst_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = *src_line++ >> shift;
                    dst[1][x] = *src_line++ >> shift;
                    dst[2][x] = *src_line++ >> shift;
                    dst[3][x] = 0xFFFF;
                }
            } else if (src_alpha) {
                for (x = 0; x < width; x++) {
                    dst[0][x] = *src_line++ >> shift;
                    dst[1][x] = *src_line++ >> shift;
                    dst[2][x] = *src_line++ >> shift;
                    src_line++;
                }
            } else {
                for (x = 0; x < width; x++) {
                    dst[0][x] = *src_line++ >> shift;
                    dst[1][x] = *src_line++ >> shift;
                    dst[2][x] = *src_line++ >> shift;
                }
            }
        }
        for (i = 0; i < 4; i++)
            dst[i] += dstStride[i] >> 1;
    }
}

static int Rgb16ToPlanarRgb16Wrapper(SwsContext *c, const uint8_t *src[],
                                     int srcStride[], int srcSliceY, int srcSliceH,
                                     uint8_t *dst[], int dstStride[])
{
    uint16_t *dst2013[] = { (uint16_t *)dst[2], (uint16_t *)dst[0], (uint16_t *)dst[1], (uint16_t *)dst[3] };
    uint16_t *dst1023[] = { (uint16_t *)dst[1], (uint16_t *)dst[0], (uint16_t *)dst[2], (uint16_t *)dst[3] };
    int stride2013[] = { dstStride[2], dstStride[0], dstStride[1], dstStride[3] };
    int stride1023[] = { dstStride[1], dstStride[0], dstStride[2], dstStride[3] };
    const AVPixFmtDescriptor *src_format = av_pix_fmt_desc_get(c->srcFormat);
    const AVPixFmtDescriptor *dst_format = av_pix_fmt_desc_get(c->dstFormat);
649
    int bpc = dst_format->comp[0].depth;
650 651
    int alpha = src_format->flags & AV_PIX_FMT_FLAG_ALPHA;
    int swap = 0;
652 653
    int i;

654 655 656 657 658 659 660 661 662 663 664 665 666
    if ( HAVE_BIGENDIAN && !(src_format->flags & AV_PIX_FMT_FLAG_BE) ||
        !HAVE_BIGENDIAN &&   src_format->flags & AV_PIX_FMT_FLAG_BE)
        swap++;
    if ( HAVE_BIGENDIAN && !(dst_format->flags & AV_PIX_FMT_FLAG_BE) ||
        !HAVE_BIGENDIAN &&   dst_format->flags & AV_PIX_FMT_FLAG_BE)
        swap += 2;

    if ((dst_format->flags & (AV_PIX_FMT_FLAG_PLANAR | AV_PIX_FMT_FLAG_RGB)) !=
        (AV_PIX_FMT_FLAG_PLANAR | AV_PIX_FMT_FLAG_RGB) || bpc < 9) {
        av_log(c, AV_LOG_ERROR, "unsupported conversion to planar RGB %s -> %s\n",
               src_format->name, dst_format->name);
        return srcSliceH;
    }
667 668 669 670 671 672

    for(i=0; i<4; i++) {
        dst2013[i] += stride2013[i] * srcSliceY / 2;
        dst1023[i] += stride1023[i] * srcSliceY / 2;
    }

673 674 675 676 677
    switch (c->srcFormat) {
    case AV_PIX_FMT_RGB48LE:
    case AV_PIX_FMT_RGB48BE:
    case AV_PIX_FMT_RGBA64LE:
    case AV_PIX_FMT_RGBA64BE:
678
        packed16togbra16(src[0], srcStride[0],
679 680 681 682 683 684 685
                         dst2013, stride2013, srcSliceH, alpha, swap,
                         16 - bpc, c->srcW);
        break;
    case AV_PIX_FMT_BGR48LE:
    case AV_PIX_FMT_BGR48BE:
    case AV_PIX_FMT_BGRA64LE:
    case AV_PIX_FMT_BGRA64BE:
686
        packed16togbra16(src[0], srcStride[0],
687 688 689 690 691 692 693 694 695 696 697 698
                         dst1023, stride1023, srcSliceH, alpha, swap,
                         16 - bpc, c->srcW);
        break;
    default:
        av_log(c, AV_LOG_ERROR,
               "unsupported conversion to planar RGB %s -> %s\n",
               src_format->name, dst_format->name);
    }

    return srcSliceH;
}

699 700 701 702 703
static void gbr16ptopacked16(const uint16_t *src[], int srcStride[],
                             uint8_t *dst, int dstStride, int srcSliceH,
                             int alpha, int swap, int bpp, int width)
{
    int x, h, i;
704
    int src_alpha = src[3] != NULL;
705 706 707 708 709 710 711
    int scale_high = 16 - bpp, scale_low = (bpp - 8) * 2;
    for (h = 0; h < srcSliceH; h++) {
        uint16_t *dest = (uint16_t *)(dst + dstStride * h);
        uint16_t component;

        switch(swap) {
        case 3:
712
            if (alpha && !src_alpha) {
713 714 715 716 717 718 719 720 721
                for (x = 0; x < width; x++) {
                    component = av_bswap16(src[0][x]);
                    *dest++ = av_bswap16(component << scale_high | component >> scale_low);
                    component = av_bswap16(src[1][x]);
                    *dest++ = av_bswap16(component << scale_high | component >> scale_low);
                    component = av_bswap16(src[2][x]);
                    *dest++ = av_bswap16(component << scale_high | component >> scale_low);
                    *dest++ = 0xffff;
                }
722 723 724 725 726 727 728 729 730 731 732
            } else if (alpha && src_alpha) {
                for (x = 0; x < width; x++) {
                    component = av_bswap16(src[0][x]);
                    *dest++ = av_bswap16(component << scale_high | component >> scale_low);
                    component = av_bswap16(src[1][x]);
                    *dest++ = av_bswap16(component << scale_high | component >> scale_low);
                    component = av_bswap16(src[2][x]);
                    *dest++ = av_bswap16(component << scale_high | component >> scale_low);
                    component = av_bswap16(src[3][x]);
                    *dest++ = av_bswap16(component << scale_high | component >> scale_low);
                }
733 734 735 736 737 738 739 740 741 742 743 744
            } else {
                for (x = 0; x < width; x++) {
                    component = av_bswap16(src[0][x]);
                    *dest++ = av_bswap16(component << scale_high | component >> scale_low);
                    component = av_bswap16(src[1][x]);
                    *dest++ = av_bswap16(component << scale_high | component >> scale_low);
                    component = av_bswap16(src[2][x]);
                    *dest++ = av_bswap16(component << scale_high | component >> scale_low);
                }
            }
            break;
        case 2:
745
            if (alpha && !src_alpha) {
746 747 748 749 750 751
                for (x = 0; x < width; x++) {
                    *dest++ = av_bswap16(src[0][x] << scale_high | src[0][x] >> scale_low);
                    *dest++ = av_bswap16(src[1][x] << scale_high | src[1][x] >> scale_low);
                    *dest++ = av_bswap16(src[2][x] << scale_high | src[2][x] >> scale_low);
                    *dest++ = 0xffff;
                }
752 753 754 755 756 757 758
            } else if (alpha && src_alpha) {
                for (x = 0; x < width; x++) {
                    *dest++ = av_bswap16(src[0][x] << scale_high | src[0][x] >> scale_low);
                    *dest++ = av_bswap16(src[1][x] << scale_high | src[1][x] >> scale_low);
                    *dest++ = av_bswap16(src[2][x] << scale_high | src[2][x] >> scale_low);
                    *dest++ = av_bswap16(src[3][x] << scale_high | src[3][x] >> scale_low);
                }
759 760 761 762 763 764 765 766 767
            } else {
                for (x = 0; x < width; x++) {
                    *dest++ = av_bswap16(src[0][x] << scale_high | src[0][x] >> scale_low);
                    *dest++ = av_bswap16(src[1][x] << scale_high | src[1][x] >> scale_low);
                    *dest++ = av_bswap16(src[2][x] << scale_high | src[2][x] >> scale_low);
                }
            }
            break;
        case 1:
768
            if (alpha && !src_alpha) {
769 770 771 772 773 774
                for (x = 0; x < width; x++) {
                    *dest++ = av_bswap16(src[0][x]) << scale_high | av_bswap16(src[0][x]) >> scale_low;
                    *dest++ = av_bswap16(src[1][x]) << scale_high | av_bswap16(src[1][x]) >> scale_low;
                    *dest++ = av_bswap16(src[2][x]) << scale_high | av_bswap16(src[2][x]) >> scale_low;
                    *dest++ = 0xffff;
                }
775 776 777 778 779 780 781
            } else if (alpha && src_alpha) {
                for (x = 0; x < width; x++) {
                    *dest++ = av_bswap16(src[0][x]) << scale_high | av_bswap16(src[0][x]) >> scale_low;
                    *dest++ = av_bswap16(src[1][x]) << scale_high | av_bswap16(src[1][x]) >> scale_low;
                    *dest++ = av_bswap16(src[2][x]) << scale_high | av_bswap16(src[2][x]) >> scale_low;
                    *dest++ = av_bswap16(src[3][x]) << scale_high | av_bswap16(src[3][x]) >> scale_low;
                }
782 783 784 785 786 787 788 789 790
            } else {
                for (x = 0; x < width; x++) {
                    *dest++ = av_bswap16(src[0][x]) << scale_high | av_bswap16(src[0][x]) >> scale_low;
                    *dest++ = av_bswap16(src[1][x]) << scale_high | av_bswap16(src[1][x]) >> scale_low;
                    *dest++ = av_bswap16(src[2][x]) << scale_high | av_bswap16(src[2][x]) >> scale_low;
                }
            }
            break;
        default:
791
            if (alpha && !src_alpha) {
792 793 794 795 796 797
                for (x = 0; x < width; x++) {
                    *dest++ = src[0][x] << scale_high | src[0][x] >> scale_low;
                    *dest++ = src[1][x] << scale_high | src[1][x] >> scale_low;
                    *dest++ = src[2][x] << scale_high | src[2][x] >> scale_low;
                    *dest++ = 0xffff;
                }
798 799 800 801 802 803 804
            } else if (alpha && src_alpha) {
                for (x = 0; x < width; x++) {
                    *dest++ = src[0][x] << scale_high | src[0][x] >> scale_low;
                    *dest++ = src[1][x] << scale_high | src[1][x] >> scale_low;
                    *dest++ = src[2][x] << scale_high | src[2][x] >> scale_low;
                    *dest++ = src[3][x] << scale_high | src[3][x] >> scale_low;
                }
805 806 807 808 809 810 811 812
            } else {
                for (x = 0; x < width; x++) {
                    *dest++ = src[0][x] << scale_high | src[0][x] >> scale_low;
                    *dest++ = src[1][x] << scale_high | src[1][x] >> scale_low;
                    *dest++ = src[2][x] << scale_high | src[2][x] >> scale_low;
                }
            }
        }
813
        for (i = 0; i < 3 + src_alpha; i++)
814 815 816 817 818 819 820 821
            src[i] += srcStride[i] >> 1;
    }
}

static int planarRgb16ToRgb16Wrapper(SwsContext *c, const uint8_t *src[],
                                     int srcStride[], int srcSliceY, int srcSliceH,
                                     uint8_t *dst[], int dstStride[])
{
822 823 824 825
    const uint16_t *src102[] = { (uint16_t *)src[1], (uint16_t *)src[0], (uint16_t *)src[2], (uint16_t *)src[3] };
    const uint16_t *src201[] = { (uint16_t *)src[2], (uint16_t *)src[0], (uint16_t *)src[1], (uint16_t *)src[3] };
    int stride102[] = { srcStride[1], srcStride[0], srcStride[2], srcStride[3] };
    int stride201[] = { srcStride[2], srcStride[0], srcStride[1], srcStride[3] };
826 827
    const AVPixFmtDescriptor *src_format = av_pix_fmt_desc_get(c->srcFormat);
    const AVPixFmtDescriptor *dst_format = av_pix_fmt_desc_get(c->dstFormat);
828
    int bits_per_sample = src_format->comp[0].depth;
829 830 831 832 833 834 835 836
    int swap = 0;
    if ( HAVE_BIGENDIAN && !(src_format->flags & AV_PIX_FMT_FLAG_BE) ||
        !HAVE_BIGENDIAN &&   src_format->flags & AV_PIX_FMT_FLAG_BE)
        swap++;
    if ( HAVE_BIGENDIAN && !(dst_format->flags & AV_PIX_FMT_FLAG_BE) ||
        !HAVE_BIGENDIAN &&   dst_format->flags & AV_PIX_FMT_FLAG_BE)
        swap += 2;

837
    if ((src_format->flags & (AV_PIX_FMT_FLAG_PLANAR | AV_PIX_FMT_FLAG_RGB)) !=
838 839
        (AV_PIX_FMT_FLAG_PLANAR | AV_PIX_FMT_FLAG_RGB) ||
        bits_per_sample <= 8) {
840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877
        av_log(c, AV_LOG_ERROR, "unsupported planar RGB conversion %s -> %s\n",
               src_format->name, dst_format->name);
        return srcSliceH;
    }
    switch (c->dstFormat) {
    case AV_PIX_FMT_BGR48LE:
    case AV_PIX_FMT_BGR48BE:
        gbr16ptopacked16(src102, stride102,
                         dst[0] + srcSliceY * dstStride[0], dstStride[0],
                         srcSliceH, 0, swap, bits_per_sample, c->srcW);
        break;
    case AV_PIX_FMT_RGB48LE:
    case AV_PIX_FMT_RGB48BE:
        gbr16ptopacked16(src201, stride201,
                         dst[0] + srcSliceY * dstStride[0], dstStride[0],
                         srcSliceH, 0, swap, bits_per_sample, c->srcW);
        break;
    case AV_PIX_FMT_RGBA64LE:
    case AV_PIX_FMT_RGBA64BE:
         gbr16ptopacked16(src201, stride201,
                          dst[0] + srcSliceY * dstStride[0], dstStride[0],
                          srcSliceH, 1, swap, bits_per_sample, c->srcW);
        break;
    case AV_PIX_FMT_BGRA64LE:
    case AV_PIX_FMT_BGRA64BE:
        gbr16ptopacked16(src102, stride102,
                         dst[0] + srcSliceY * dstStride[0], dstStride[0],
                         srcSliceH, 1, swap, bits_per_sample, c->srcW);
        break;
    default:
        av_log(c, AV_LOG_ERROR,
               "unsupported planar RGB conversion %s -> %s\n",
               src_format->name, dst_format->name);
    }

    return srcSliceH;
}

878 879 880
static void gbr24ptopacked24(const uint8_t *src[], int srcStride[],
                             uint8_t *dst, int dstStride, int srcSliceH,
                             int width)
881 882 883 884 885 886 887 888 889 890 891 892 893 894 895
{
    int x, h, i;
    for (h = 0; h < srcSliceH; h++) {
        uint8_t *dest = dst + dstStride * h;
        for (x = 0; x < width; x++) {
            *dest++ = src[0][x];
            *dest++ = src[1][x];
            *dest++ = src[2][x];
        }

        for (i = 0; i < 3; i++)
            src[i] += srcStride[i];
    }
}

896 897 898
static void gbr24ptopacked32(const uint8_t *src[], int srcStride[],
                             uint8_t *dst, int dstStride, int srcSliceH,
                             int alpha_first, int width)
899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924
{
    int x, h, i;
    for (h = 0; h < srcSliceH; h++) {
        uint8_t *dest = dst + dstStride * h;

        if (alpha_first) {
            for (x = 0; x < width; x++) {
                *dest++ = 0xff;
                *dest++ = src[0][x];
                *dest++ = src[1][x];
                *dest++ = src[2][x];
            }
        } else {
            for (x = 0; x < width; x++) {
                *dest++ = src[0][x];
                *dest++ = src[1][x];
                *dest++ = src[2][x];
                *dest++ = 0xff;
            }
        }

        for (i = 0; i < 3; i++)
            src[i] += srcStride[i];
    }
}

925 926 927
static int planarRgbToRgbWrapper(SwsContext *c, const uint8_t *src[],
                                 int srcStride[], int srcSliceY, int srcSliceH,
                                 uint8_t *dst[], int dstStride[])
928 929
{
    int alpha_first = 0;
930 931 932 933 934
    const uint8_t *src102[] = { src[1], src[0], src[2] };
    const uint8_t *src201[] = { src[2], src[0], src[1] };
    int stride102[] = { srcStride[1], srcStride[0], srcStride[2] };
    int stride201[] = { srcStride[2], srcStride[0], srcStride[1] };

935
    if (c->srcFormat != AV_PIX_FMT_GBRP) {
936
        av_log(c, AV_LOG_ERROR, "unsupported planar RGB conversion %s -> %s\n",
937 938
               av_get_pix_fmt_name(c->srcFormat),
               av_get_pix_fmt_name(c->dstFormat));
939 940 941 942
        return srcSliceH;
    }

    switch (c->dstFormat) {
943
    case AV_PIX_FMT_BGR24:
944
        gbr24ptopacked24(src102, stride102,
945 946 947 948
                         dst[0] + srcSliceY * dstStride[0], dstStride[0],
                         srcSliceH, c->srcW);
        break;

949
    case AV_PIX_FMT_RGB24:
950
        gbr24ptopacked24(src201, stride201,
951 952 953 954
                         dst[0] + srcSliceY * dstStride[0], dstStride[0],
                         srcSliceH, c->srcW);
        break;

955
    case AV_PIX_FMT_ARGB:
956
        alpha_first = 1;
957
    case AV_PIX_FMT_RGBA:
958
        gbr24ptopacked32(src201, stride201,
959 960 961 962
                         dst[0] + srcSliceY * dstStride[0], dstStride[0],
                         srcSliceH, alpha_first, c->srcW);
        break;

963
    case AV_PIX_FMT_ABGR:
964
        alpha_first = 1;
965
    case AV_PIX_FMT_BGRA:
966
        gbr24ptopacked32(src102, stride102,
967 968 969 970 971 972 973 974 975
                         dst[0] + srcSliceY * dstStride[0], dstStride[0],
                         srcSliceH, alpha_first, c->srcW);
        break;

    default:
        av_log(c, AV_LOG_ERROR,
               "unsupported planar RGB conversion %s -> %s\n",
               av_get_pix_fmt_name(c->srcFormat),
               av_get_pix_fmt_name(c->dstFormat));
976 977 978 979 980
    }

    return srcSliceH;
}

981 982 983
static int planarRgbToplanarRgbWrapper(SwsContext *c,
                                       const uint8_t *src[], int srcStride[],
                                       int srcSliceY, int srcSliceH,
984 985 986 987 988 989 990 991 992 993 994 995 996 997
                                       uint8_t *dst[], int dstStride[])
{
    copyPlane(src[0], srcStride[0], srcSliceY, srcSliceH, c->srcW,
              dst[0], dstStride[0]);
    copyPlane(src[1], srcStride[1], srcSliceY, srcSliceH, c->srcW,
              dst[1], dstStride[1]);
    copyPlane(src[2], srcStride[2], srcSliceY, srcSliceH, c->srcW,
              dst[2], dstStride[2]);
    if (dst[3])
        fillPlane(dst[3], dstStride[3], c->srcW, srcSliceH, srcSliceY, 255);

    return srcSliceH;
}

998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041
static void packedtogbr24p(const uint8_t *src, int srcStride,
                           uint8_t *dst[], int dstStride[], int srcSliceH,
                           int alpha_first, int inc_size, int width)
{
    uint8_t *dest[3];
    int x, h;

    dest[0] = dst[0];
    dest[1] = dst[1];
    dest[2] = dst[2];

    if (alpha_first)
        src++;

    for (h = 0; h < srcSliceH; h++) {
        for (x = 0; x < width; x++) {
            dest[0][x] = src[0];
            dest[1][x] = src[1];
            dest[2][x] = src[2];

            src += inc_size;
        }
        src     += srcStride - width * inc_size;
        dest[0] += dstStride[0];
        dest[1] += dstStride[1];
        dest[2] += dstStride[2];
    }
}

static int rgbToPlanarRgbWrapper(SwsContext *c, const uint8_t *src[],
                                 int srcStride[], int srcSliceY, int srcSliceH,
                                 uint8_t *dst[], int dstStride[])
{
    int alpha_first = 0;
    int stride102[] = { dstStride[1], dstStride[0], dstStride[2] };
    int stride201[] = { dstStride[2], dstStride[0], dstStride[1] };
    uint8_t *dst102[] = { dst[1] + srcSliceY * dstStride[1],
                          dst[0] + srcSliceY * dstStride[0],
                          dst[2] + srcSliceY * dstStride[2] };
    uint8_t *dst201[] = { dst[2] + srcSliceY * dstStride[2],
                          dst[0] + srcSliceY * dstStride[0],
                          dst[1] + srcSliceY * dstStride[1] };

    switch (c->srcFormat) {
1042
    case AV_PIX_FMT_RGB24:
1043 1044 1045
        packedtogbr24p((const uint8_t *) src[0], srcStride[0], dst201,
                       stride201, srcSliceH, alpha_first, 3, c->srcW);
        break;
1046
    case AV_PIX_FMT_BGR24:
1047 1048 1049
        packedtogbr24p((const uint8_t *) src[0], srcStride[0], dst102,
                       stride102, srcSliceH, alpha_first, 3, c->srcW);
        break;
1050
    case AV_PIX_FMT_ARGB:
1051
        alpha_first = 1;
1052
    case AV_PIX_FMT_RGBA:
1053 1054 1055
        packedtogbr24p((const uint8_t *) src[0], srcStride[0], dst201,
                       stride201, srcSliceH, alpha_first, 4, c->srcW);
        break;
1056
    case AV_PIX_FMT_ABGR:
1057
        alpha_first = 1;
1058
    case AV_PIX_FMT_BGRA:
1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071
        packedtogbr24p((const uint8_t *) src[0], srcStride[0], dst102,
                       stride102, srcSliceH, alpha_first, 4, c->srcW);
        break;
    default:
        av_log(c, AV_LOG_ERROR,
               "unsupported planar RGB conversion %s -> %s\n",
               av_get_pix_fmt_name(c->srcFormat),
               av_get_pix_fmt_name(c->dstFormat));
    }

    return srcSliceH;
}

1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134
#define BAYER_GBRG
#define BAYER_8
#define BAYER_RENAME(x) bayer_gbrg8_to_##x
#include "bayer_template.c"

#define BAYER_GBRG
#define BAYER_16LE
#define BAYER_RENAME(x) bayer_gbrg16le_to_##x
#include "bayer_template.c"

#define BAYER_GBRG
#define BAYER_16BE
#define BAYER_RENAME(x) bayer_gbrg16be_to_##x
#include "bayer_template.c"

#define BAYER_GRBG
#define BAYER_8
#define BAYER_RENAME(x) bayer_grbg8_to_##x
#include "bayer_template.c"

#define BAYER_GRBG
#define BAYER_16LE
#define BAYER_RENAME(x) bayer_grbg16le_to_##x
#include "bayer_template.c"

#define BAYER_GRBG
#define BAYER_16BE
#define BAYER_RENAME(x) bayer_grbg16be_to_##x
#include "bayer_template.c"

#define BAYER_BGGR
#define BAYER_8
#define BAYER_RENAME(x) bayer_bggr8_to_##x
#include "bayer_template.c"

#define BAYER_BGGR
#define BAYER_16LE
#define BAYER_RENAME(x) bayer_bggr16le_to_##x
#include "bayer_template.c"

#define BAYER_BGGR
#define BAYER_16BE
#define BAYER_RENAME(x) bayer_bggr16be_to_##x
#include "bayer_template.c"

#define BAYER_RGGB
#define BAYER_8
#define BAYER_RENAME(x) bayer_rggb8_to_##x
#include "bayer_template.c"

#define BAYER_RGGB
#define BAYER_16LE
#define BAYER_RENAME(x) bayer_rggb16le_to_##x
#include "bayer_template.c"

#define BAYER_RGGB
#define BAYER_16BE
#define BAYER_RENAME(x) bayer_rggb16be_to_##x
#include "bayer_template.c"

static int bayer_to_rgb24_wrapper(SwsContext *c, const uint8_t* src[], int srcStride[], int srcSliceY,
                                  int srcSliceH, uint8_t* dst[], int dstStride[])
{
1135
    uint8_t *dstPtr= dst[0] + srcSliceY * dstStride[0];
1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161
    const uint8_t *srcPtr= src[0];
    int i;
    void (*copy)       (const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int width);
    void (*interpolate)(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int width);

    switch(c->srcFormat) {
#define CASE(pixfmt, prefix) \
    case pixfmt: copy        = bayer_##prefix##_to_rgb24_copy; \
                 interpolate = bayer_##prefix##_to_rgb24_interpolate; \
                 break;
    CASE(AV_PIX_FMT_BAYER_BGGR8,    bggr8)
    CASE(AV_PIX_FMT_BAYER_BGGR16LE, bggr16le)
    CASE(AV_PIX_FMT_BAYER_BGGR16BE, bggr16be)
    CASE(AV_PIX_FMT_BAYER_RGGB8,    rggb8)
    CASE(AV_PIX_FMT_BAYER_RGGB16LE, rggb16le)
    CASE(AV_PIX_FMT_BAYER_RGGB16BE, rggb16be)
    CASE(AV_PIX_FMT_BAYER_GBRG8,    gbrg8)
    CASE(AV_PIX_FMT_BAYER_GBRG16LE, gbrg16le)
    CASE(AV_PIX_FMT_BAYER_GBRG16BE, gbrg16be)
    CASE(AV_PIX_FMT_BAYER_GRBG8,    grbg8)
    CASE(AV_PIX_FMT_BAYER_GRBG16LE, grbg16le)
    CASE(AV_PIX_FMT_BAYER_GRBG16BE, grbg16be)
#undef CASE
    default: return 0;
    }

1162 1163
    av_assert0(srcSliceH > 1);

1164 1165 1166 1167 1168 1169 1170 1171 1172 1173
    copy(srcPtr, srcStride[0], dstPtr, dstStride[0], c->srcW);
    srcPtr += 2 * srcStride[0];
    dstPtr += 2 * dstStride[0];

    for (i = 2; i < srcSliceH - 2; i += 2) {
        interpolate(srcPtr, srcStride[0], dstPtr, dstStride[0], c->srcW);
        srcPtr += 2 * srcStride[0];
        dstPtr += 2 * dstStride[0];
    }

1174 1175 1176 1177
    if (i + 1 == srcSliceH) {
        copy(srcPtr, -srcStride[0], dstPtr, -dstStride[0], c->srcW);
    } else if (i < srcSliceH)
        copy(srcPtr, srcStride[0], dstPtr, dstStride[0], c->srcW);
1178 1179 1180 1181 1182 1183 1184
    return srcSliceH;
}

static int bayer_to_yv12_wrapper(SwsContext *c, const uint8_t* src[], int srcStride[], int srcSliceY,
                                 int srcSliceH, uint8_t* dst[], int dstStride[])
{
    const uint8_t *srcPtr= src[0];
1185 1186 1187
    uint8_t *dstY= dst[0] + srcSliceY * dstStride[0];
    uint8_t *dstU= dst[1] + srcSliceY * dstStride[1] / 2;
    uint8_t *dstV= dst[2] + srcSliceY * dstStride[2] / 2;
1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212
    int i;
    void (*copy)       (const uint8_t *src, int src_stride, uint8_t *dstY, uint8_t *dstU, uint8_t *dstV, int luma_stride, int width, int32_t *rgb2yuv);
    void (*interpolate)(const uint8_t *src, int src_stride, uint8_t *dstY, uint8_t *dstU, uint8_t *dstV, int luma_stride, int width, int32_t *rgb2yuv);

    switch(c->srcFormat) {
#define CASE(pixfmt, prefix) \
    case pixfmt: copy        = bayer_##prefix##_to_yv12_copy; \
                 interpolate = bayer_##prefix##_to_yv12_interpolate; \
                 break;
    CASE(AV_PIX_FMT_BAYER_BGGR8,    bggr8)
    CASE(AV_PIX_FMT_BAYER_BGGR16LE, bggr16le)
    CASE(AV_PIX_FMT_BAYER_BGGR16BE, bggr16be)
    CASE(AV_PIX_FMT_BAYER_RGGB8,    rggb8)
    CASE(AV_PIX_FMT_BAYER_RGGB16LE, rggb16le)
    CASE(AV_PIX_FMT_BAYER_RGGB16BE, rggb16be)
    CASE(AV_PIX_FMT_BAYER_GBRG8,    gbrg8)
    CASE(AV_PIX_FMT_BAYER_GBRG16LE, gbrg16le)
    CASE(AV_PIX_FMT_BAYER_GBRG16BE, gbrg16be)
    CASE(AV_PIX_FMT_BAYER_GRBG8,    grbg8)
    CASE(AV_PIX_FMT_BAYER_GRBG16LE, grbg16le)
    CASE(AV_PIX_FMT_BAYER_GRBG16BE, grbg16be)
#undef CASE
    default: return 0;
    }

1213 1214
    av_assert0(srcSliceH > 1);

1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228
    copy(srcPtr, srcStride[0], dstY, dstU, dstV, dstStride[0], c->srcW, c->input_rgb2yuv_table);
    srcPtr += 2 * srcStride[0];
    dstY   += 2 * dstStride[0];
    dstU   +=     dstStride[1];
    dstV   +=     dstStride[1];

    for (i = 2; i < srcSliceH - 2; i += 2) {
        interpolate(srcPtr, srcStride[0], dstY, dstU, dstV, dstStride[0], c->srcW, c->input_rgb2yuv_table);
        srcPtr += 2 * srcStride[0];
        dstY   += 2 * dstStride[0];
        dstU   +=     dstStride[1];
        dstV   +=     dstStride[1];
    }

1229 1230 1231 1232
    if (i + 1 == srcSliceH) {
        copy(srcPtr, -srcStride[0], dstY, dstU, dstV, -dstStride[0], c->srcW, c->input_rgb2yuv_table);
    } else if (i < srcSliceH)
        copy(srcPtr, srcStride[0], dstY, dstU, dstV, dstStride[0], c->srcW, c->input_rgb2yuv_table);
1233 1234 1235
    return srcSliceH;
}

1236
#define isRGBA32(x) (            \
1237 1238 1239 1240
           (x) == AV_PIX_FMT_ARGB   \
        || (x) == AV_PIX_FMT_RGBA   \
        || (x) == AV_PIX_FMT_BGRA   \
        || (x) == AV_PIX_FMT_ABGR   \
1241 1242
        )

1243
#define isRGBA64(x) (                \
1244 1245 1246 1247
           (x) == AV_PIX_FMT_RGBA64LE   \
        || (x) == AV_PIX_FMT_RGBA64BE   \
        || (x) == AV_PIX_FMT_BGRA64LE   \
        || (x) == AV_PIX_FMT_BGRA64BE   \
1248 1249
        )

1250
#define isRGB48(x) (                \
1251 1252 1253 1254
           (x) == AV_PIX_FMT_RGB48LE   \
        || (x) == AV_PIX_FMT_RGB48BE   \
        || (x) == AV_PIX_FMT_BGR48LE   \
        || (x) == AV_PIX_FMT_BGR48BE   \
1255 1256
        )

1257
/* {RGB,BGR}{15,16,24,32,32_1} -> {RGB,BGR}{15,16,24,32} */
1258 1259
typedef void (* rgbConvFn) (const uint8_t *, uint8_t *, int);
static rgbConvFn findRgbConvFn(SwsContext *c)
1260
{
1261 1262
    const enum AVPixelFormat srcFormat = c->srcFormat;
    const enum AVPixelFormat dstFormat = c->dstFormat;
1263 1264
    const int srcId = c->srcFormatBpp;
    const int dstId = c->dstFormatBpp;
1265 1266
    rgbConvFn conv = NULL;

1267
#define IS_NOT_NE(bpp, desc) \
1268
    (((bpp + 7) >> 3) == 2 && \
1269
     (!(desc->flags & AV_PIX_FMT_FLAG_BE) != !HAVE_BIGENDIAN))
1270

1271
#define CONV_IS(src, dst) (srcFormat == AV_PIX_FMT_##src && dstFormat == AV_PIX_FMT_##dst)
1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285

    if (isRGBA32(srcFormat) && isRGBA32(dstFormat)) {
        if (     CONV_IS(ABGR, RGBA)
              || CONV_IS(ARGB, BGRA)
              || CONV_IS(BGRA, ARGB)
              || CONV_IS(RGBA, ABGR)) conv = shuffle_bytes_3210;
        else if (CONV_IS(ABGR, ARGB)
              || CONV_IS(ARGB, ABGR)) conv = shuffle_bytes_0321;
        else if (CONV_IS(ABGR, BGRA)
              || CONV_IS(ARGB, RGBA)) conv = shuffle_bytes_1230;
        else if (CONV_IS(BGRA, RGBA)
              || CONV_IS(RGBA, BGRA)) conv = shuffle_bytes_2103;
        else if (CONV_IS(BGRA, ABGR)
              || CONV_IS(RGBA, ARGB)) conv = shuffle_bytes_3012;
1286 1287 1288 1289
    } else if (isRGB48(srcFormat) && isRGB48(dstFormat)) {
        if      (CONV_IS(RGB48LE, BGR48LE)
              || CONV_IS(BGR48LE, RGB48LE)
              || CONV_IS(RGB48BE, BGR48BE)
1290
              || CONV_IS(BGR48BE, RGB48BE)) conv = rgb48tobgr48_nobswap;
1291 1292 1293
        else if (CONV_IS(RGB48LE, BGR48BE)
              || CONV_IS(BGR48LE, RGB48BE)
              || CONV_IS(RGB48BE, BGR48LE)
1294
              || CONV_IS(BGR48BE, RGB48LE)) conv = rgb48tobgr48_bswap;
1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311
    } else if (isRGB48(srcFormat) && isRGBA64(dstFormat)) {
        if      (CONV_IS(RGB48LE, BGRA64LE)
              || CONV_IS(BGR48LE, RGBA64LE)
              || CONV_IS(RGB48BE, BGRA64BE)
              || CONV_IS(BGR48BE, RGBA64BE)) conv = rgb48tobgr64_nobswap;
        else if (CONV_IS(RGB48LE, BGRA64BE)
              || CONV_IS(BGR48LE, RGBA64BE)
              || CONV_IS(RGB48BE, BGRA64LE)
              || CONV_IS(BGR48BE, RGBA64LE)) conv = rgb48tobgr64_bswap;
        if      (CONV_IS(RGB48LE, RGBA64LE)
              || CONV_IS(BGR48LE, BGRA64LE)
              || CONV_IS(RGB48BE, RGBA64BE)
              || CONV_IS(BGR48BE, BGRA64BE)) conv = rgb48to64_nobswap;
        else if (CONV_IS(RGB48LE, RGBA64BE)
              || CONV_IS(BGR48LE, BGRA64BE)
              || CONV_IS(RGB48BE, RGBA64LE)
              || CONV_IS(BGR48BE, BGRA64LE)) conv = rgb48to64_bswap;
1312 1313 1314 1315 1316 1317 1318 1319 1320
    } 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;
1321 1322 1323 1324 1325 1326 1327 1328
        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;
1329 1330
    } else
    /* BGR -> BGR */
1331 1332
    if ((isBGRinInt(srcFormat) && isBGRinInt(dstFormat)) ||
        (isRGBinInt(srcFormat) && isRGBinInt(dstFormat))) {
1333
        switch (srcId | (dstId << 16)) {
Paul B Mahol's avatar
Paul B Mahol committed
1334
        case 0x000F000C: conv = rgb12to15; break;
1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346
        case 0x000F0010: conv = rgb16to15; break;
        case 0x000F0018: conv = rgb24to15; break;
        case 0x000F0020: conv = rgb32to15; break;
        case 0x0010000F: conv = rgb15to16; break;
        case 0x00100018: conv = rgb24to16; break;
        case 0x00100020: conv = rgb32to16; break;
        case 0x0018000F: conv = rgb15to24; break;
        case 0x00180010: conv = rgb16to24; break;
        case 0x00180020: conv = rgb32to24; break;
        case 0x0020000F: conv = rgb15to32; break;
        case 0x00200010: conv = rgb16to32; break;
        case 0x00200018: conv = rgb24to32; break;
1347
        }
1348 1349
    } else if ((isBGRinInt(srcFormat) && isRGBinInt(dstFormat)) ||
               (isRGBinInt(srcFormat) && isBGRinInt(dstFormat))) {
1350
        switch (srcId | (dstId << 16)) {
Paul B Mahol's avatar
Paul B Mahol committed
1351
        case 0x000C000C: conv = rgb12tobgr12; break;
1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366
        case 0x000F000F: conv = rgb15tobgr15; break;
        case 0x000F0010: conv = rgb16tobgr15; break;
        case 0x000F0018: conv = rgb24tobgr15; break;
        case 0x000F0020: conv = rgb32tobgr15; break;
        case 0x0010000F: conv = rgb15tobgr16; break;
        case 0x00100010: conv = rgb16tobgr16; break;
        case 0x00100018: conv = rgb24tobgr16; break;
        case 0x00100020: conv = rgb32tobgr16; break;
        case 0x0018000F: conv = rgb15tobgr24; break;
        case 0x00180010: conv = rgb16tobgr24; break;
        case 0x00180018: conv = rgb24tobgr24; break;
        case 0x00180020: conv = rgb32tobgr24; break;
        case 0x0020000F: conv = rgb15tobgr32; break;
        case 0x00200010: conv = rgb16tobgr32; break;
        case 0x00200018: conv = rgb24tobgr32; break;
1367 1368 1369
        }
    }

1370 1371 1372
    if ((dstFormat == AV_PIX_FMT_RGB32_1 || dstFormat == AV_PIX_FMT_BGR32_1) && !isRGBA32(srcFormat) && ALT32_CORR<0)
        return NULL;

1373 1374 1375 1376 1377
    // Maintain symmetry between endianness
    if (c->flags & SWS_BITEXACT)
        if ((dstFormat == AV_PIX_FMT_RGB32   || dstFormat == AV_PIX_FMT_BGR32  ) && !isRGBA32(srcFormat) && ALT32_CORR>0)
            return NULL;

1378 1379 1380 1381 1382 1383 1384 1385 1386
    return conv;
}

/* {RGB,BGR}{15,16,24,32,32_1} -> {RGB,BGR}{15,16,24,32} */
static int rgbToRgbWrapper(SwsContext *c, const uint8_t *src[], int srcStride[],
                           int srcSliceY, int srcSliceH, uint8_t *dst[],
                           int dstStride[])

{
1387 1388
    const enum AVPixelFormat srcFormat = c->srcFormat;
    const enum AVPixelFormat dstFormat = c->dstFormat;
1389 1390
    const AVPixFmtDescriptor *desc_src = av_pix_fmt_desc_get(c->srcFormat);
    const AVPixFmtDescriptor *desc_dst = av_pix_fmt_desc_get(c->dstFormat);
1391 1392 1393 1394
    const int srcBpp = (c->srcFormatBpp + 7) >> 3;
    const int dstBpp = (c->dstFormatBpp + 7) >> 3;
    rgbConvFn conv = findRgbConvFn(c);

1395 1396
    if (!conv) {
        av_log(c, AV_LOG_ERROR, "internal error %s -> %s converter\n",
1397
               av_get_pix_fmt_name(srcFormat), av_get_pix_fmt_name(dstFormat));
1398
    } else {
1399 1400
        const uint8_t *srcPtr = src[0];
              uint8_t *dstPtr = dst[0];
1401 1402
        int src_bswap = IS_NOT_NE(c->srcFormatBpp, desc_src);
        int dst_bswap = IS_NOT_NE(c->dstFormatBpp, desc_dst);
1403

1404
        if ((srcFormat == AV_PIX_FMT_RGB32_1 || srcFormat == AV_PIX_FMT_BGR32_1) &&
1405
            !isRGBA32(dstFormat))
1406 1407
            srcPtr += ALT32_CORR;

1408
        if ((dstFormat == AV_PIX_FMT_RGB32_1 || dstFormat == AV_PIX_FMT_BGR32_1) &&
1409 1410 1411 1412 1413
            !isRGBA32(srcFormat)) {
            int i;
            av_assert0(ALT32_CORR == 1);
            for (i = 0; i < srcSliceH; i++)
                dstPtr[dstStride[0] * (srcSliceY + i)] = 255;
1414
            dstPtr += ALT32_CORR;
1415
        }
1416

1417
        if (dstStride[0] * srcBpp == srcStride[0] * dstBpp && srcStride[0] > 0 &&
1418
            !(srcStride[0] % srcBpp) && !dst_bswap && !src_bswap)
1419
            conv(srcPtr, dstPtr + dstStride[0] * srcSliceY,
1420
                 (srcSliceH - 1) * srcStride[0] + c->srcW * srcBpp);
1421
        else {
1422
            int i, j;
1423
            dstPtr += dstStride[0] * srcSliceY;
1424

1425
            for (i = 0; i < srcSliceH; i++) {
1426 1427 1428 1429 1430 1431 1432 1433 1434
                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]);
1435 1436
                srcPtr += srcStride[0];
                dstPtr += dstStride[0];
1437 1438 1439 1440 1441 1442
            }
        }
    }
    return srcSliceH;
}

1443 1444 1445
static int bgr24ToYv12Wrapper(SwsContext *c, const uint8_t *src[],
                              int srcStride[], int srcSliceY, int srcSliceH,
                              uint8_t *dst[], int dstStride[])
1446
{
1447
    ff_rgb24toyv12(
1448
        src[0],
1449 1450 1451
        dst[0] +  srcSliceY       * dstStride[0],
        dst[1] + (srcSliceY >> 1) * dstStride[1],
        dst[2] + (srcSliceY >> 1) * dstStride[2],
1452
        c->srcW, srcSliceH,
1453 1454
        dstStride[0], dstStride[1], srcStride[0],
        c->input_rgb2yuv_table);
1455 1456 1457 1458 1459
    if (dst[3])
        fillPlane(dst[3], dstStride[3], c->srcW, srcSliceH, srcSliceY, 255);
    return srcSliceH;
}

1460 1461 1462
static int yvu9ToYv12Wrapper(SwsContext *c, const uint8_t *src[],
                             int srcStride[], int srcSliceY, int srcSliceH,
                             uint8_t *dst[], int dstStride[])
1463 1464 1465 1466
{
    copyPlane(src[0], srcStride[0], srcSliceY, srcSliceH, c->srcW,
              dst[0], dstStride[0]);

1467
    planar2x(src[1], dst[1] + dstStride[1] * (srcSliceY >> 1), c->chrSrcW,
1468
             srcSliceH >> 2, srcStride[1], dstStride[1]);
1469
    planar2x(src[2], dst[2] + dstStride[2] * (srcSliceY >> 1), c->chrSrcW,
1470 1471 1472 1473 1474 1475 1476
             srcSliceH >> 2, srcStride[2], dstStride[2]);
    if (dst[3])
        fillPlane(dst[3], dstStride[3], c->srcW, srcSliceH, srcSliceY, 255);
    return srcSliceH;
}

/* unscaled copy like stuff (assumes nearly identical formats) */
1477 1478 1479
static int packedCopyWrapper(SwsContext *c, const uint8_t *src[],
                             int srcStride[], int srcSliceY, int srcSliceH,
                             uint8_t *dst[], int dstStride[])
1480
{
1481 1482
    if (dstStride[0] == srcStride[0] && srcStride[0] > 0)
        memcpy(dst[0] + dstStride[0] * srcSliceY, src[0], srcSliceH * dstStride[0]);
1483 1484
    else {
        int i;
1485 1486 1487
        const uint8_t *srcPtr = src[0];
        uint8_t *dstPtr = dst[0] + dstStride[0] * srcSliceY;
        int length = 0;
1488 1489

        /* universal length finder */
1490 1491 1492
        while (length + c->srcW <= FFABS(dstStride[0]) &&
               length + c->srcW <= FFABS(srcStride[0]))
            length += c->srcW;
1493
        av_assert1(length != 0);
1494

1495
        for (i = 0; i < srcSliceH; i++) {
1496
            memcpy(dstPtr, srcPtr, length);
1497 1498
            srcPtr += srcStride[0];
            dstPtr += dstStride[0];
1499 1500 1501 1502 1503
        }
    }
    return srcSliceH;
}

1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524
#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;\
    }

1525 1526 1527
static int planarCopyWrapper(SwsContext *c, const uint8_t *src[],
                             int srcStride[], int srcSliceY, int srcSliceH,
                             uint8_t *dst[], int dstStride[])
1528
{
1529 1530
    const AVPixFmtDescriptor *desc_src = av_pix_fmt_desc_get(c->srcFormat);
    const AVPixFmtDescriptor *desc_dst = av_pix_fmt_desc_get(c->dstFormat);
1531
    int plane, i, j;
1532
    for (plane = 0; plane < 4; plane++) {
1533 1534 1535
        int length = (plane == 0 || plane == 3) ? c->srcW  : AV_CEIL_RSHIFT(c->srcW,   c->chrDstHSubSample);
        int y =      (plane == 0 || plane == 3) ? srcSliceY: AV_CEIL_RSHIFT(srcSliceY, c->chrDstVSubSample);
        int height = (plane == 0 || plane == 3) ? srcSliceH: AV_CEIL_RSHIFT(srcSliceH, c->chrDstVSubSample);
1536 1537
        const uint8_t *srcPtr = src[plane];
        uint8_t *dstPtr = dst[plane] + dstStride[plane] * y;
1538
        int shiftonly = plane == 1 || plane == 2 || (!c->srcRange && plane == 0);
1539

1540 1541
        if (!dst[plane])
            continue;
1542 1543 1544
        // ignore palette for GRAY8
        if (plane == 1 && !dst[2]) continue;
        if (!src[plane] || (plane == 1 && !src[2])) {
1545 1546
            if (is16BPS(c->dstFormat) || isNBPS(c->dstFormat)) {
                fillPlane16(dst[plane], dstStride[plane], length, height, y,
1547
                        plane == 3, desc_dst->comp[plane].depth,
1548
                        isBE(c->dstFormat));
1549 1550 1551 1552
            } else {
                fillPlane(dst[plane], dstStride[plane], length, height, y,
                        (plane == 3) ? 255 : 128);
            }
1553
        } else {
1554 1555 1556
            if(isNBPS(c->srcFormat) || isNBPS(c->dstFormat)
               || (is16BPS(c->srcFormat) != is16BPS(c->dstFormat))
            ) {
1557 1558
                const int src_depth = desc_src->comp[plane].depth;
                const int dst_depth = desc_dst->comp[plane].depth;
1559
                const uint16_t *srcPtr2 = (const uint16_t *) srcPtr;
1560
                uint16_t *dstPtr2 = (uint16_t*)dstPtr;
1561

1562 1563 1564
                if (dst_depth == 8) {
                    if(isBE(c->srcFormat) == HAVE_BIGENDIAN){
                        DITHER_COPY(dstPtr, dstStride[plane], srcPtr2, srcStride[plane]/2, , )
1565
                    } else {
1566
                        DITHER_COPY(dstPtr, dstStride[plane], srcPtr2, srcStride[plane]/2, av_bswap16, )
1567
                    }
1568 1569
                } else if (src_depth == 8) {
                    for (i = 0; i < height; i++) {
1570
                        #define COPY816(w)\
1571
                        if (shiftonly) {\
1572 1573
                            for (j = 0; j < length; j++)\
                                w(&dstPtr2[j], srcPtr[j]<<(dst_depth-8));\
1574
                        } else {\
1575 1576 1577 1578
                            for (j = 0; j < length; j++)\
                                w(&dstPtr2[j], (srcPtr[j]<<(dst_depth-8)) |\
                                               (srcPtr[j]>>(2*8-dst_depth)));\
                        }
1579
                        if(isBE(c->dstFormat)){
1580
                            COPY816(AV_WB16)
1581
                        } else {
1582
                            COPY816(AV_WL16)
1583
                        }
1584 1585 1586 1587 1588
                        dstPtr2 += dstStride[plane]/2;
                        srcPtr  += srcStride[plane];
                    }
                } else if (src_depth <= dst_depth) {
                    for (i = 0; i < height; i++) {
1589
                        j = 0;
1590 1591 1592 1593 1594 1595
                        if(isBE(c->srcFormat) == HAVE_BIGENDIAN &&
                           isBE(c->dstFormat) == HAVE_BIGENDIAN &&
                           shiftonly) {
                             unsigned shift = dst_depth - src_depth;
#if HAVE_FAST_64BIT
#define FAST_COPY_UP(shift) \
1596
    for (; j < length - 3; j += 4) { \
1597 1598
        uint64_t v = AV_RN64A(srcPtr2 + j); \
        AV_WN64A(dstPtr2 + j, v << shift); \
1599
    }
1600 1601
#else
#define FAST_COPY_UP(shift) \
1602
    for (; j < length - 1; j += 2) { \
1603 1604
        uint32_t v = AV_RN32A(srcPtr2 + j); \
        AV_WN32A(dstPtr2 + j, v << shift); \
1605
    }
1606 1607 1608 1609 1610 1611 1612
#endif
                             switch (shift)
                             {
                             case 6: FAST_COPY_UP(6); break;
                             case 7: FAST_COPY_UP(7); break;
                             }
                        }
1613
#define COPY_UP(r,w) \
1614
    if(shiftonly){\
1615
        for (; j < length; j++){ \
1616 1617 1618 1619
            unsigned int v= r(&srcPtr2[j]);\
            w(&dstPtr2[j], v<<(dst_depth-src_depth));\
        }\
    }else{\
1620
        for (; j < length; j++){ \
1621 1622 1623 1624
            unsigned int v= r(&srcPtr2[j]);\
            w(&dstPtr2[j], (v<<(dst_depth-src_depth)) | \
                        (v>>(2*src_depth-dst_depth)));\
        }\
1625 1626 1627 1628 1629 1630 1631
    }
                        if(isBE(c->srcFormat)){
                            if(isBE(c->dstFormat)){
                                COPY_UP(AV_RB16, AV_WB16)
                            } else {
                                COPY_UP(AV_RB16, AV_WL16)
                            }
1632
                        } else {
1633 1634 1635 1636 1637
                            if(isBE(c->dstFormat)){
                                COPY_UP(AV_RL16, AV_WB16)
                            } else {
                                COPY_UP(AV_RL16, AV_WL16)
                            }
1638
                        }
1639 1640
                        dstPtr2 += dstStride[plane]/2;
                        srcPtr2 += srcStride[plane]/2;
1641 1642
                    }
                } else {
1643 1644 1645
                    if(isBE(c->srcFormat) == HAVE_BIGENDIAN){
                        if(isBE(c->dstFormat) == HAVE_BIGENDIAN){
                            DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, , )
1646
                        } else {
1647
                            DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, , av_bswap16)
1648
                        }
1649 1650 1651
                    }else{
                        if(isBE(c->dstFormat) == HAVE_BIGENDIAN){
                            DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, av_bswap16, )
1652
                        } else {
1653
                            DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, av_bswap16, av_bswap16)
1654 1655 1656
                        }
                    }
                }
1657 1658 1659 1660 1661 1662 1663 1664
            } else if (is16BPS(c->srcFormat) && is16BPS(c->dstFormat) &&
                      isBE(c->srcFormat) != isBE(c->dstFormat)) {

                for (i = 0; i < height; i++) {
                    for (j = 0; j < length; j++)
                        ((uint16_t *) dstPtr)[j] = av_bswap16(((const uint16_t *) srcPtr)[j]);
                    srcPtr += srcStride[plane];
                    dstPtr += dstStride[plane];
1665 1666 1667
                }
            } else if (dstStride[plane] == srcStride[plane] &&
                       srcStride[plane] > 0 && srcStride[plane] == length) {
1668 1669
                memcpy(dst[plane] + dstStride[plane] * y, src[plane],
                       height * dstStride[plane]);
1670
            } else {
1671 1672
                if (is16BPS(c->srcFormat) && is16BPS(c->dstFormat))
                    length *= 2;
1673
                else if (desc_src->comp[0].depth == 1)
1674
                    length >>= 3; // monowhite/black
1675
                for (i = 0; i < height; i++) {
1676
                    memcpy(dstPtr, srcPtr, length);
1677 1678
                    srcPtr += srcStride[plane];
                    dstPtr += dstStride[plane];
1679 1680 1681 1682 1683 1684 1685
                }
            }
        }
    }
    return srcSliceH;
}

1686 1687 1688 1689 1690 1691

#define IS_DIFFERENT_ENDIANESS(src_fmt, dst_fmt, pix_fmt)          \
    ((src_fmt == pix_fmt ## BE && dst_fmt == pix_fmt ## LE) ||     \
     (src_fmt == pix_fmt ## LE && dst_fmt == pix_fmt ## BE))


1692 1693
void ff_get_unscaled_swscale(SwsContext *c)
{
1694 1695
    const enum AVPixelFormat srcFormat = c->srcFormat;
    const enum AVPixelFormat dstFormat = c->dstFormat;
1696 1697 1698 1699
    const int flags = c->flags;
    const int dstH = c->dstH;
    int needsDither;

1700 1701 1702
    needsDither = isAnyRGB(dstFormat) &&
            c->dstFormatBpp < 24 &&
           (c->dstFormatBpp < c->srcFormatBpp || (!isAnyRGB(srcFormat)));
1703 1704

    /* yv12_to_nv12 */
1705 1706
    if ((srcFormat == AV_PIX_FMT_YUV420P || srcFormat == AV_PIX_FMT_YUVA420P) &&
        (dstFormat == AV_PIX_FMT_NV12 || dstFormat == AV_PIX_FMT_NV21)) {
1707
        c->swscale = planarToNv12Wrapper;
1708
    }
1709 1710 1711 1712 1713
    /* nv12_to_yv12 */
    if (dstFormat == AV_PIX_FMT_YUV420P &&
        (srcFormat == AV_PIX_FMT_NV12 || srcFormat == AV_PIX_FMT_NV21)) {
        c->swscale = nv12ToPlanarWrapper;
    }
1714
    /* yuv2bgr */
1715 1716
    if ((srcFormat == AV_PIX_FMT_YUV420P || srcFormat == AV_PIX_FMT_YUV422P ||
         srcFormat == AV_PIX_FMT_YUVA420P) && isAnyRGB(dstFormat) &&
1717
        !(flags & SWS_ACCURATE_RND) && (c->dither == SWS_DITHER_BAYER || c->dither == SWS_DITHER_AUTO) && !(dstH & 1)) {
1718
        c->swscale = ff_yuv2rgb_get_func_ptr(c);
1719
    }
1720 1721 1722 1723 1724
    /* yuv420p10_to_p010 */
    if ((srcFormat == AV_PIX_FMT_YUV420P10 || srcFormat == AV_PIX_FMT_YUVA420P10) &&
        dstFormat == AV_PIX_FMT_P010) {
        c->swscale = planarToP010Wrapper;
    }
1725 1726 1727 1728 1729
    /* yuv420p_to_p010le */
    if ((srcFormat == AV_PIX_FMT_YUV420P || srcFormat == AV_PIX_FMT_YUVA420P) &&
        dstFormat == AV_PIX_FMT_P010LE) {
        c->swscale = planar8ToP01xleWrapper;
    }
1730

1731
    if (srcFormat == AV_PIX_FMT_YUV410P && !(dstH & 3) &&
1732
        (dstFormat == AV_PIX_FMT_YUV420P || dstFormat == AV_PIX_FMT_YUVA420P) &&
1733
        !(flags & SWS_BITEXACT)) {
1734
        c->swscale = yvu9ToYv12Wrapper;
1735 1736 1737
    }

    /* bgr24toYV12 */
1738 1739
    if (srcFormat == AV_PIX_FMT_BGR24 &&
        (dstFormat == AV_PIX_FMT_YUV420P || dstFormat == AV_PIX_FMT_YUVA420P) &&
1740
        !(flags & SWS_ACCURATE_RND))
1741
        c->swscale = bgr24ToYv12Wrapper;
1742 1743

    /* RGB/BGR -> RGB/BGR (no dither needed forms) */
1744
    if (isAnyRGB(srcFormat) && isAnyRGB(dstFormat) && findRgbConvFn(c)
1745
        && (!needsDither || (c->flags&(SWS_FAST_BILINEAR|SWS_POINT))))
1746
        c->swscale = rgbToRgbWrapper;
1747

1748
    /* RGB to planar RGB */
1749 1750
    if ((srcFormat == AV_PIX_FMT_GBRP && dstFormat == AV_PIX_FMT_GBRAP) ||
        (srcFormat == AV_PIX_FMT_GBRAP && dstFormat == AV_PIX_FMT_GBRP))
1751
        c->swscale = planarRgbToplanarRgbWrapper;
1752

1753 1754 1755 1756 1757 1758
#define isByteRGB(f) (             \
        f == AV_PIX_FMT_RGB32   || \
        f == AV_PIX_FMT_RGB32_1 || \
        f == AV_PIX_FMT_RGB24   || \
        f == AV_PIX_FMT_BGR32   || \
        f == AV_PIX_FMT_BGR32_1 || \
1759
        f == AV_PIX_FMT_BGR24)
1760

1761
    if (srcFormat == AV_PIX_FMT_GBRP && isPlanar(srcFormat) && isByteRGB(dstFormat))
1762
        c->swscale = planarRgbToRgbWrapper;
1763

1764 1765 1766 1767 1768 1769 1770 1771 1772
    if ((srcFormat == AV_PIX_FMT_RGB48LE  || srcFormat == AV_PIX_FMT_RGB48BE  ||
         srcFormat == AV_PIX_FMT_BGR48LE  || srcFormat == AV_PIX_FMT_BGR48BE  ||
         srcFormat == AV_PIX_FMT_RGBA64LE || srcFormat == AV_PIX_FMT_RGBA64BE ||
         srcFormat == AV_PIX_FMT_BGRA64LE || srcFormat == AV_PIX_FMT_BGRA64BE) &&
        (dstFormat == AV_PIX_FMT_GBRP9LE  || dstFormat == AV_PIX_FMT_GBRP9BE  ||
         dstFormat == AV_PIX_FMT_GBRP10LE || dstFormat == AV_PIX_FMT_GBRP10BE ||
         dstFormat == AV_PIX_FMT_GBRP12LE || dstFormat == AV_PIX_FMT_GBRP12BE ||
         dstFormat == AV_PIX_FMT_GBRP14LE || dstFormat == AV_PIX_FMT_GBRP14BE ||
         dstFormat == AV_PIX_FMT_GBRP16LE || dstFormat == AV_PIX_FMT_GBRP16BE ||
1773
         dstFormat == AV_PIX_FMT_GBRAP12LE || dstFormat == AV_PIX_FMT_GBRAP12BE ||
1774 1775 1776
         dstFormat == AV_PIX_FMT_GBRAP16LE || dstFormat == AV_PIX_FMT_GBRAP16BE ))
        c->swscale = Rgb16ToPlanarRgb16Wrapper;

1777 1778 1779 1780
    if ((srcFormat == AV_PIX_FMT_GBRP9LE  || srcFormat == AV_PIX_FMT_GBRP9BE  ||
         srcFormat == AV_PIX_FMT_GBRP16LE || srcFormat == AV_PIX_FMT_GBRP16BE ||
         srcFormat == AV_PIX_FMT_GBRP10LE || srcFormat == AV_PIX_FMT_GBRP10BE ||
         srcFormat == AV_PIX_FMT_GBRP12LE || srcFormat == AV_PIX_FMT_GBRP12BE ||
1781
         srcFormat == AV_PIX_FMT_GBRP14LE || srcFormat == AV_PIX_FMT_GBRP14BE ||
1782
         srcFormat == AV_PIX_FMT_GBRAP12LE || srcFormat == AV_PIX_FMT_GBRAP12BE ||
1783
         srcFormat == AV_PIX_FMT_GBRAP16LE || srcFormat == AV_PIX_FMT_GBRAP16BE) &&
1784 1785 1786 1787
        (dstFormat == AV_PIX_FMT_RGB48LE  || dstFormat == AV_PIX_FMT_RGB48BE  ||
         dstFormat == AV_PIX_FMT_BGR48LE  || dstFormat == AV_PIX_FMT_BGR48BE  ||
         dstFormat == AV_PIX_FMT_RGBA64LE || dstFormat == AV_PIX_FMT_RGBA64BE ||
         dstFormat == AV_PIX_FMT_BGRA64LE || dstFormat == AV_PIX_FMT_BGRA64BE))
1788
        c->swscale = planarRgb16ToRgb16Wrapper;
1789

1790
    if (av_pix_fmt_desc_get(srcFormat)->comp[0].depth == 8 &&
1791
        isPackedRGB(srcFormat) && dstFormat == AV_PIX_FMT_GBRP)
1792
        c->swscale = rgbToPlanarRgbWrapper;
1793

1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804
    if (isBayer(srcFormat)) {
        if (dstFormat == AV_PIX_FMT_RGB24)
            c->swscale = bayer_to_rgb24_wrapper;
        else if (dstFormat == AV_PIX_FMT_YUV420P)
            c->swscale = bayer_to_yv12_wrapper;
        else if (!isBayer(dstFormat)) {
            av_log(c, AV_LOG_ERROR, "unsupported bayer conversion\n");
            av_assert0(0);
        }
    }

1805
    /* bswap 16 bits per pixel/component packed formats */
1806 1807 1808 1809 1810
    if (IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BAYER_BGGR16) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BAYER_RGGB16) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BAYER_GBRG16) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BAYER_GRBG16) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BGR444) ||
1811
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BGR48)  ||
1812
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BGRA64) ||
1813 1814
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BGR555) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BGR565) ||
1815
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BGRA64) ||
1816
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GRAY9)  ||
1817
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GRAY10) ||
Luca Barbato's avatar
Luca Barbato committed
1818
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GRAY12) ||
1819
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GRAY16) ||
1820
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YA16)   ||
1821
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_AYUV64) ||
1822 1823 1824 1825 1826
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GBRP9)  ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GBRP10) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GBRP12) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GBRP14) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GBRP16) ||
1827
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GBRAP12) ||
1828
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GBRAP16) ||
1829 1830
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGB444) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGB48)  ||
1831
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGBA64) ||
1832
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGB555) ||
1833
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGB565) ||
1834
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGBA64) ||
1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_XYZ12)  ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV420P9)  ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV420P10) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV420P12) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV420P14) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV420P16) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV422P9)  ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV422P10) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV422P12) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV422P14) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV422P16) ||
1846 1847
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV440P10) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV440P12) ||
1848 1849 1850 1851 1852
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV444P9)  ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV444P10) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV444P12) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV444P14) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YUV444P16))
1853
        c->swscale = packed_16bpc_bswap;
1854

1855
    if (usePal(srcFormat) && isByteRGB(dstFormat))
1856
        c->swscale = palToRgbWrapper;
1857

1858 1859
    if (srcFormat == AV_PIX_FMT_YUV422P) {
        if (dstFormat == AV_PIX_FMT_YUYV422)
1860
            c->swscale = yuv422pToYuy2Wrapper;
1861
        else if (dstFormat == AV_PIX_FMT_UYVY422)
1862
            c->swscale = yuv422pToUyvyWrapper;
1863 1864 1865 1866 1867
    }

    /* LQ converters if -sws 0 or -sws 4*/
    if (c->flags&(SWS_FAST_BILINEAR|SWS_POINT)) {
        /* yv12_to_yuy2 */
1868 1869
        if (srcFormat == AV_PIX_FMT_YUV420P || srcFormat == AV_PIX_FMT_YUVA420P) {
            if (dstFormat == AV_PIX_FMT_YUYV422)
1870
                c->swscale = planarToYuy2Wrapper;
1871
            else if (dstFormat == AV_PIX_FMT_UYVY422)
1872
                c->swscale = planarToUyvyWrapper;
1873 1874
        }
    }
1875 1876
    if (srcFormat == AV_PIX_FMT_YUYV422 &&
       (dstFormat == AV_PIX_FMT_YUV420P || dstFormat == AV_PIX_FMT_YUVA420P))
1877
        c->swscale = yuyvToYuv420Wrapper;
1878 1879
    if (srcFormat == AV_PIX_FMT_UYVY422 &&
       (dstFormat == AV_PIX_FMT_YUV420P || dstFormat == AV_PIX_FMT_YUVA420P))
1880
        c->swscale = uyvyToYuv420Wrapper;
1881
    if (srcFormat == AV_PIX_FMT_YUYV422 && dstFormat == AV_PIX_FMT_YUV422P)
1882
        c->swscale = yuyvToYuv422Wrapper;
1883
    if (srcFormat == AV_PIX_FMT_UYVY422 && dstFormat == AV_PIX_FMT_YUV422P)
1884
        c->swscale = uyvyToYuv422Wrapper;
1885

1886
#define isPlanarGray(x) (isGray(x) && (x) != AV_PIX_FMT_YA8 && (x) != AV_PIX_FMT_YA16LE && (x) != AV_PIX_FMT_YA16BE)
1887
    /* simple copy */
1888
    if ( srcFormat == dstFormat ||
1889 1890
        (srcFormat == AV_PIX_FMT_YUVA420P && dstFormat == AV_PIX_FMT_YUV420P) ||
        (srcFormat == AV_PIX_FMT_YUV420P && dstFormat == AV_PIX_FMT_YUVA420P) ||
1891 1892 1893
        (isPlanarYUV(srcFormat) && isPlanarGray(dstFormat)) ||
        (isPlanarYUV(dstFormat) && isPlanarGray(srcFormat)) ||
        (isPlanarGray(dstFormat) && isPlanarGray(srcFormat)) ||
1894 1895 1896
        (isPlanarYUV(srcFormat) && isPlanarYUV(dstFormat) &&
         c->chrDstHSubSample == c->chrSrcHSubSample &&
         c->chrDstVSubSample == c->chrSrcVSubSample &&
1897
         dstFormat != AV_PIX_FMT_NV12 && dstFormat != AV_PIX_FMT_NV21 &&
1898
         dstFormat != AV_PIX_FMT_P010LE && dstFormat != AV_PIX_FMT_P010BE &&
1899
         dstFormat != AV_PIX_FMT_P016LE && dstFormat != AV_PIX_FMT_P016BE &&
1900
         srcFormat != AV_PIX_FMT_NV12 && srcFormat != AV_PIX_FMT_NV21 &&
1901 1902
         srcFormat != AV_PIX_FMT_P010LE && srcFormat != AV_PIX_FMT_P010BE &&
         srcFormat != AV_PIX_FMT_P016LE && srcFormat != AV_PIX_FMT_P016BE))
1903 1904
    {
        if (isPacked(c->srcFormat))
1905
            c->swscale = packedCopyWrapper;
1906
        else /* Planar YUV or gray */
1907
            c->swscale = planarCopyWrapper;
1908 1909
    }

1910
    if (ARCH_PPC)
1911
        ff_get_unscaled_swscale_ppc(c);
1912 1913
     if (ARCH_ARM)
         ff_get_unscaled_swscale_arm(c);
1914 1915
    if (ARCH_AARCH64)
        ff_get_unscaled_swscale_aarch64(c);
1916 1917 1918
}

/* Convert the palette to the same packed 32-bit format as the palette */
1919 1920
void sws_convertPalette8ToPacked32(const uint8_t *src, uint8_t *dst,
                                   int num_pixels, const uint8_t *palette)
1921 1922 1923
{
    int i;

1924
    for (i = 0; i < num_pixels; i++)
1925 1926 1927 1928
        ((uint32_t *) dst)[i] = ((const uint32_t *) palette)[src[i]];
}

/* Palette format: ABCD -> dst format: ABC */
1929 1930
void sws_convertPalette8ToPacked24(const uint8_t *src, uint8_t *dst,
                                   int num_pixels, const uint8_t *palette)
1931 1932 1933
{
    int i;

1934
    for (i = 0; i < num_pixels; i++) {
1935
        //FIXME slow?
1936 1937 1938 1939
        dst[0] = palette[src[i] * 4 + 0];
        dst[1] = palette[src[i] * 4 + 1];
        dst[2] = palette[src[i] * 4 + 2];
        dst += 3;
1940 1941
    }
}