swscale_unscaled.c 73 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

37
DECLARE_ALIGNED(8, static const uint8_t, dithers)[8][8][8]={
38 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
{
  {   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,},
}};

112
static const uint16_t dither_scale[15][16]={
113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130
{    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,},
};


131 132
static void fillPlane(uint8_t *plane, int stride, int width, int height, int y,
                      uint8_t val)
133 134
{
    int i;
135 136
    uint8_t *ptr = plane + stride * y;
    for (i = 0; i < height; i++) {
137 138 139 140 141 142 143 144 145 146 147 148 149 150
        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;
151
        for (i = 0; i < srcSliceH; i++) {
152 153 154 155 156 157 158
            memcpy(dst, src, width);
            src += srcStride;
            dst += dstStride;
        }
    }
}

159 160 161 162
static int planarToNv12Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY,
                               int srcSliceH, uint8_t *dstParam[],
                               int dstStride[])
163
{
164
    uint8_t *dst = dstParam[1] + dstStride[1] * srcSliceY / 2;
165 166 167 168

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

169
    if (c->dstFormat == AV_PIX_FMT_NV12)
170
        interleaveBytes(src[1], src[2], dst, c->srcW / 2, srcSliceH / 2,
171
                        srcStride[1], srcStride[2], dstStride[1]);
172
    else
173
        interleaveBytes(src[2], src[1], dst, c->srcW / 2, srcSliceH / 2,
174
                        srcStride[2], srcStride[1], dstStride[1]);
175 176 177 178

    return srcSliceH;
}

179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199
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;
}

200 201 202
static int planarToYuy2Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
203
{
204
    uint8_t *dst = dstParam[0] + dstStride[0] * srcSliceY;
205

206 207
    yv12toyuy2(src[0], src[1], src[2], dst, c->srcW, srcSliceH, srcStride[0],
               srcStride[1], dstStride[0]);
208 209 210 211

    return srcSliceH;
}

212 213 214
static int planarToUyvyWrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
215
{
216
    uint8_t *dst = dstParam[0] + dstStride[0] * srcSliceY;
217

218 219
    yv12touyvy(src[0], src[1], src[2], dst, c->srcW, srcSliceH, srcStride[0],
               srcStride[1], dstStride[0]);
220 221 222 223

    return srcSliceH;
}

224 225 226
static int yuv422pToYuy2Wrapper(SwsContext *c, const uint8_t *src[],
                                int srcStride[], int srcSliceY, int srcSliceH,
                                uint8_t *dstParam[], int dstStride[])
227
{
228
    uint8_t *dst = dstParam[0] + dstStride[0] * srcSliceY;
229

230 231
    yuv422ptoyuy2(src[0], src[1], src[2], dst, c->srcW, srcSliceH, srcStride[0],
                  srcStride[1], dstStride[0]);
232 233 234 235

    return srcSliceH;
}

236 237 238
static int yuv422pToUyvyWrapper(SwsContext *c, const uint8_t *src[],
                                int srcStride[], int srcSliceY, int srcSliceH,
                                uint8_t *dstParam[], int dstStride[])
239
{
240
    uint8_t *dst = dstParam[0] + dstStride[0] * srcSliceY;
241

242 243
    yuv422ptouyvy(src[0], src[1], src[2], dst, c->srcW, srcSliceH, srcStride[0],
                  srcStride[1], dstStride[0]);
244 245 246 247

    return srcSliceH;
}

248 249 250
static int yuyvToYuv420Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
251
{
252 253 254
    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;
255

256 257
    yuyvtoyuv420(ydst, udst, vdst, src[0], c->srcW, srcSliceH, dstStride[0],
                 dstStride[1], srcStride[0]);
258 259 260 261 262 263 264

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

    return srcSliceH;
}

265 266 267
static int yuyvToYuv422Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
268
{
269 270 271
    uint8_t *ydst = dstParam[0] + dstStride[0] * srcSliceY;
    uint8_t *udst = dstParam[1] + dstStride[1] * srcSliceY;
    uint8_t *vdst = dstParam[2] + dstStride[2] * srcSliceY;
272

273 274
    yuyvtoyuv422(ydst, udst, vdst, src[0], c->srcW, srcSliceH, dstStride[0],
                 dstStride[1], srcStride[0]);
275 276 277 278

    return srcSliceH;
}

279 280 281
static int uyvyToYuv420Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
282
{
283 284 285
    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;
286

287 288
    uyvytoyuv420(ydst, udst, vdst, src[0], c->srcW, srcSliceH, dstStride[0],
                 dstStride[1], srcStride[0]);
289 290 291 292 293 294 295

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

    return srcSliceH;
}

296 297 298
static int uyvyToYuv422Wrapper(SwsContext *c, const uint8_t *src[],
                               int srcStride[], int srcSliceY, int srcSliceH,
                               uint8_t *dstParam[], int dstStride[])
299
{
300 301 302
    uint8_t *ydst = dstParam[0] + dstStride[0] * srcSliceY;
    uint8_t *udst = dstParam[1] + dstStride[1] * srcSliceY;
    uint8_t *vdst = dstParam[2] + dstStride[2] * srcSliceY;
303

304 305
    uyvytoyuv422(ydst, udst, vdst, src[0], c->srcW, srcSliceH, dstStride[0],
                 dstStride[1], srcStride[0]);
306 307 308 309

    return srcSliceH;
}

310 311
static void gray8aToPacked32(const uint8_t *src, uint8_t *dst, int num_pixels,
                             const uint8_t *palette)
312 313
{
    int i;
314 315
    for (i = 0; i < num_pixels; i++)
        ((uint32_t *) dst)[i] = ((const uint32_t *) palette)[src[i << 1]] | (src[(i << 1) + 1] << 24);
316 317
}

318 319
static void gray8aToPacked32_1(const uint8_t *src, uint8_t *dst, int num_pixels,
                               const uint8_t *palette)
320 321 322
{
    int i;

323 324
    for (i = 0; i < num_pixels; i++)
        ((uint32_t *) dst)[i] = ((const uint32_t *) palette)[src[i << 1]] | src[(i << 1) + 1];
325 326
}

327 328
static void gray8aToPacked24(const uint8_t *src, uint8_t *dst, int num_pixels,
                             const uint8_t *palette)
329 330 331
{
    int i;

332
    for (i = 0; i < num_pixels; i++) {
333
        //FIXME slow?
334 335 336 337
        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;
338 339 340
    }
}

341
static int packed_16bpc_bswap(SwsContext *c, const uint8_t *src[],
342
                              int srcStride[], int srcSliceY, int srcSliceH,
343
                              uint8_t *dst[], int dstStride[])
344
{
345 346 347
    int i, j, p;

    for (p = 0; p < 4; p++) {
348 349
        int srcstr = srcStride[p] / 2;
        int dststr = dstStride[p] / 2;
350 351
        uint16_t       *dstPtr =       (uint16_t *) dst[p];
        const uint16_t *srcPtr = (const uint16_t *) src[p];
352
        int min_stride         = FFMIN(FFABS(srcstr), FFABS(dststr));
353 354 355 356 357 358 359 360
        if(!dstPtr || !srcPtr)
            continue;
        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;
361 362 363 364 365 366
        }
    }

    return srcSliceH;
}

367 368 369
static int palToRgbWrapper(SwsContext *c, const uint8_t *src[], int srcStride[],
                           int srcSliceY, int srcSliceH, uint8_t *dst[],
                           int dstStride[])
370
{
371 372
    const enum AVPixelFormat srcFormat = c->srcFormat;
    const enum AVPixelFormat dstFormat = c->dstFormat;
373
    void (*conv)(const uint8_t *src, uint8_t *dst, int num_pixels,
374
                 const uint8_t *palette) = NULL;
375
    int i;
376 377
    uint8_t *dstPtr = dst[0] + dstStride[0] * srcSliceY;
    const uint8_t *srcPtr = src[0];
378

379
    if (srcFormat == AV_PIX_FMT_YA8) {
380
        switch (dstFormat) {
381 382 383 384 385 386
        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;
387 388 389
        }
    } else if (usePal(srcFormat)) {
        switch (dstFormat) {
390 391 392 393 394 395
        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;
396 397 398 399 400
        }
    }

    if (!conv)
        av_log(c, AV_LOG_ERROR, "internal error %s -> %s converter\n",
401
               av_get_pix_fmt_name(srcFormat), av_get_pix_fmt_name(dstFormat));
402
    else {
403
        for (i = 0; i < srcSliceH; i++) {
404
            conv(srcPtr, dstPtr, c->srcW, (uint8_t *) c->pal_rgb);
405 406
            srcPtr += srcStride[0];
            dstPtr += dstStride[0];
407 408 409 410 411 412
        }
    }

    return srcSliceH;
}

413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598
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);
    int bpc = dst_format->comp[0].depth_minus1 + 1;
    int alpha = src_format->flags & AV_PIX_FMT_FLAG_ALPHA;
    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;

    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;
    }
    switch (c->srcFormat) {
    case AV_PIX_FMT_RGB48LE:
    case AV_PIX_FMT_RGB48BE:
    case AV_PIX_FMT_RGBA64LE:
    case AV_PIX_FMT_RGBA64BE:
        packed16togbra16(src[0] + srcSliceY * srcStride[0], srcStride[0],
                         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:
        packed16togbra16(src[0] + srcSliceY * srcStride[0], srcStride[0],
                         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;
}

599 600 601 602 603
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;
604
    int src_alpha = src[3] != NULL;
605 606 607 608 609 610 611
    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:
612
            if (alpha && !src_alpha) {
613 614 615 616 617 618 619 620 621
                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;
                }
622 623 624 625 626 627 628 629 630 631 632
            } 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);
                }
633 634 635 636 637 638 639 640 641 642 643 644
            } 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:
645
            if (alpha && !src_alpha) {
646 647 648 649 650 651
                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;
                }
652 653 654 655 656 657 658
            } 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);
                }
659 660 661 662 663 664 665 666 667
            } 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:
668
            if (alpha && !src_alpha) {
669 670 671 672 673 674
                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;
                }
675 676 677 678 679 680 681
            } 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;
                }
682 683 684 685 686 687 688 689 690
            } 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:
691
            if (alpha && !src_alpha) {
692 693 694 695 696 697
                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;
                }
698 699 700 701 702 703 704
            } 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;
                }
705 706 707 708 709 710 711 712
            } 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;
                }
            }
        }
713
        for (i = 0; i < 3 + src_alpha; i++)
714 715 716 717 718 719 720 721
            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[])
{
722 723 724 725
    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] };
726 727 728 729 730 731 732 733 734 735 736
    const AVPixFmtDescriptor *src_format = av_pix_fmt_desc_get(c->srcFormat);
    const AVPixFmtDescriptor *dst_format = av_pix_fmt_desc_get(c->dstFormat);
    int bits_per_sample = src_format->comp[0].depth_minus1 + 1;
    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;

737
    if ((src_format->flags & (AV_PIX_FMT_FLAG_PLANAR | AV_PIX_FMT_FLAG_RGB)) !=
738 739
        (AV_PIX_FMT_FLAG_PLANAR | AV_PIX_FMT_FLAG_RGB) ||
        bits_per_sample <= 8) {
740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777
        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;
}

778 779 780
static void gbr24ptopacked24(const uint8_t *src[], int srcStride[],
                             uint8_t *dst, int dstStride, int srcSliceH,
                             int width)
781 782 783 784 785 786 787 788 789 790 791 792 793 794 795
{
    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];
    }
}

796 797 798
static void gbr24ptopacked32(const uint8_t *src[], int srcStride[],
                             uint8_t *dst, int dstStride, int srcSliceH,
                             int alpha_first, int width)
799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824
{
    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];
    }
}

825 826 827
static int planarRgbToRgbWrapper(SwsContext *c, const uint8_t *src[],
                                 int srcStride[], int srcSliceY, int srcSliceH,
                                 uint8_t *dst[], int dstStride[])
828 829
{
    int alpha_first = 0;
830 831 832 833 834
    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] };

835
    if (c->srcFormat != AV_PIX_FMT_GBRP) {
836
        av_log(c, AV_LOG_ERROR, "unsupported planar RGB conversion %s -> %s\n",
837 838
               av_get_pix_fmt_name(c->srcFormat),
               av_get_pix_fmt_name(c->dstFormat));
839 840 841 842
        return srcSliceH;
    }

    switch (c->dstFormat) {
843
    case AV_PIX_FMT_BGR24:
844
        gbr24ptopacked24(src102, stride102,
845 846 847 848
                         dst[0] + srcSliceY * dstStride[0], dstStride[0],
                         srcSliceH, c->srcW);
        break;

849
    case AV_PIX_FMT_RGB24:
850
        gbr24ptopacked24(src201, stride201,
851 852 853 854
                         dst[0] + srcSliceY * dstStride[0], dstStride[0],
                         srcSliceH, c->srcW);
        break;

855
    case AV_PIX_FMT_ARGB:
856
        alpha_first = 1;
857
    case AV_PIX_FMT_RGBA:
858
        gbr24ptopacked32(src201, stride201,
859 860 861 862
                         dst[0] + srcSliceY * dstStride[0], dstStride[0],
                         srcSliceH, alpha_first, c->srcW);
        break;

863
    case AV_PIX_FMT_ABGR:
864
        alpha_first = 1;
865
    case AV_PIX_FMT_BGRA:
866
        gbr24ptopacked32(src102, stride102,
867 868 869 870 871 872 873 874 875
                         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));
876 877 878 879 880
    }

    return srcSliceH;
}

881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896
static int planarRgbToplanarRgbWrapper(SwsContext *c, const uint8_t *src[],
                                       int srcStride[], int srcSliceY, int srcSliceH,
                                       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;
}

897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940
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) {
941
    case AV_PIX_FMT_RGB24:
942 943 944
        packedtogbr24p((const uint8_t *) src[0], srcStride[0], dst201,
                       stride201, srcSliceH, alpha_first, 3, c->srcW);
        break;
945
    case AV_PIX_FMT_BGR24:
946 947 948
        packedtogbr24p((const uint8_t *) src[0], srcStride[0], dst102,
                       stride102, srcSliceH, alpha_first, 3, c->srcW);
        break;
949
    case AV_PIX_FMT_ARGB:
950
        alpha_first = 1;
951
    case AV_PIX_FMT_RGBA:
952 953 954
        packedtogbr24p((const uint8_t *) src[0], srcStride[0], dst201,
                       stride201, srcSliceH, alpha_first, 4, c->srcW);
        break;
955
    case AV_PIX_FMT_ABGR:
956
        alpha_first = 1;
957
    case AV_PIX_FMT_BGRA:
958 959 960 961 962 963 964 965 966 967 968 969 970
        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;
}

971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 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
#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[])
{
    uint8_t *dstPtr= dst[0];
    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;
    }

    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];
    }

    copy(srcPtr, srcStride[0], dstPtr, dstStride[0], c->srcW);
    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];
    uint8_t *dstY= dst[0];
    uint8_t *dstU= dst[1];
    uint8_t *dstV= dst[2];
    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;
    }

    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];
    }

    copy(srcPtr, srcStride[0], dstY, dstU, dstV, dstStride[0], c->srcW, c->input_rgb2yuv_table);
    return srcSliceH;
}

1125
#define isRGBA32(x) (            \
1126 1127 1128 1129
           (x) == AV_PIX_FMT_ARGB   \
        || (x) == AV_PIX_FMT_RGBA   \
        || (x) == AV_PIX_FMT_BGRA   \
        || (x) == AV_PIX_FMT_ABGR   \
1130 1131
        )

1132
#define isRGBA64(x) (                \
1133 1134 1135 1136
           (x) == AV_PIX_FMT_RGBA64LE   \
        || (x) == AV_PIX_FMT_RGBA64BE   \
        || (x) == AV_PIX_FMT_BGRA64LE   \
        || (x) == AV_PIX_FMT_BGRA64BE   \
1137 1138
        )

1139
#define isRGB48(x) (                \
1140 1141 1142 1143
           (x) == AV_PIX_FMT_RGB48LE   \
        || (x) == AV_PIX_FMT_RGB48BE   \
        || (x) == AV_PIX_FMT_BGR48LE   \
        || (x) == AV_PIX_FMT_BGR48BE   \
1144 1145
        )

1146
/* {RGB,BGR}{15,16,24,32,32_1} -> {RGB,BGR}{15,16,24,32} */
1147 1148
typedef void (* rgbConvFn) (const uint8_t *, uint8_t *, int);
static rgbConvFn findRgbConvFn(SwsContext *c)
1149
{
1150 1151
    const enum AVPixelFormat srcFormat = c->srcFormat;
    const enum AVPixelFormat dstFormat = c->dstFormat;
1152 1153
    const int srcId = c->srcFormatBpp;
    const int dstId = c->dstFormatBpp;
1154 1155
    rgbConvFn conv = NULL;

1156
#define IS_NOT_NE(bpp, desc) \
1157
    (((bpp + 7) >> 3) == 2 && \
1158
     (!(desc->flags & AV_PIX_FMT_FLAG_BE) != !HAVE_BIGENDIAN))
1159

1160
#define CONV_IS(src, dst) (srcFormat == AV_PIX_FMT_##src && dstFormat == AV_PIX_FMT_##dst)
1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174

    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;
1175 1176 1177 1178
    } else if (isRGB48(srcFormat) && isRGB48(dstFormat)) {
        if      (CONV_IS(RGB48LE, BGR48LE)
              || CONV_IS(BGR48LE, RGB48LE)
              || CONV_IS(RGB48BE, BGR48BE)
1179
              || CONV_IS(BGR48BE, RGB48BE)) conv = rgb48tobgr48_nobswap;
1180 1181 1182
        else if (CONV_IS(RGB48LE, BGR48BE)
              || CONV_IS(BGR48LE, RGB48BE)
              || CONV_IS(RGB48BE, BGR48LE)
1183
              || CONV_IS(BGR48BE, RGB48LE)) conv = rgb48tobgr48_bswap;
1184 1185 1186 1187 1188 1189 1190 1191 1192
    } 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;
1193 1194 1195 1196 1197 1198 1199 1200
        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;
1201 1202
    } else
    /* BGR -> BGR */
1203 1204
    if ((isBGRinInt(srcFormat) && isBGRinInt(dstFormat)) ||
        (isRGBinInt(srcFormat) && isRGBinInt(dstFormat))) {
1205
        switch (srcId | (dstId << 16)) {
Paul B Mahol's avatar
Paul B Mahol committed
1206
        case 0x000F000C: conv = rgb12to15; break;
1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218
        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;
1219
        }
1220 1221
    } else if ((isBGRinInt(srcFormat) && isRGBinInt(dstFormat)) ||
               (isRGBinInt(srcFormat) && isBGRinInt(dstFormat))) {
1222
        switch (srcId | (dstId << 16)) {
Paul B Mahol's avatar
Paul B Mahol committed
1223
        case 0x000C000C: conv = rgb12tobgr12; break;
1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238
        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;
1239 1240 1241
        }
    }

1242 1243 1244
    if ((dstFormat == AV_PIX_FMT_RGB32_1 || dstFormat == AV_PIX_FMT_BGR32_1) && !isRGBA32(srcFormat) && ALT32_CORR<0)
        return NULL;

1245 1246 1247 1248 1249 1250 1251 1252 1253
    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[])

{
1254 1255
    const enum AVPixelFormat srcFormat = c->srcFormat;
    const enum AVPixelFormat dstFormat = c->dstFormat;
1256 1257
    const AVPixFmtDescriptor *desc_src = av_pix_fmt_desc_get(c->srcFormat);
    const AVPixFmtDescriptor *desc_dst = av_pix_fmt_desc_get(c->dstFormat);
1258 1259 1260 1261
    const int srcBpp = (c->srcFormatBpp + 7) >> 3;
    const int dstBpp = (c->dstFormatBpp + 7) >> 3;
    rgbConvFn conv = findRgbConvFn(c);

1262 1263
    if (!conv) {
        av_log(c, AV_LOG_ERROR, "internal error %s -> %s converter\n",
1264
               av_get_pix_fmt_name(srcFormat), av_get_pix_fmt_name(dstFormat));
1265
    } else {
1266 1267
        const uint8_t *srcPtr = src[0];
              uint8_t *dstPtr = dst[0];
1268 1269
        int src_bswap = IS_NOT_NE(c->srcFormatBpp, desc_src);
        int dst_bswap = IS_NOT_NE(c->dstFormatBpp, desc_dst);
1270

1271
        if ((srcFormat == AV_PIX_FMT_RGB32_1 || srcFormat == AV_PIX_FMT_BGR32_1) &&
1272
            !isRGBA32(dstFormat))
1273 1274
            srcPtr += ALT32_CORR;

1275
        if ((dstFormat == AV_PIX_FMT_RGB32_1 || dstFormat == AV_PIX_FMT_BGR32_1) &&
1276 1277 1278 1279 1280
            !isRGBA32(srcFormat)) {
            int i;
            av_assert0(ALT32_CORR == 1);
            for (i = 0; i < srcSliceH; i++)
                dstPtr[dstStride[0] * (srcSliceY + i)] = 255;
1281
            dstPtr += ALT32_CORR;
1282
        }
1283

1284
        if (dstStride[0] * srcBpp == srcStride[0] * dstBpp && srcStride[0] > 0 &&
1285
            !(srcStride[0] % srcBpp) && !dst_bswap && !src_bswap)
1286
            conv(srcPtr, dstPtr + dstStride[0] * srcSliceY,
1287
                 (srcSliceH - 1) * srcStride[0] + c->srcW * srcBpp);
1288
        else {
1289
            int i, j;
1290
            dstPtr += dstStride[0] * srcSliceY;
1291

1292
            for (i = 0; i < srcSliceH; i++) {
1293 1294 1295 1296 1297 1298 1299 1300 1301
                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]);
1302 1303
                srcPtr += srcStride[0];
                dstPtr += dstStride[0];
1304 1305 1306 1307 1308 1309
            }
        }
    }
    return srcSliceH;
}

1310 1311 1312
static int bgr24ToYv12Wrapper(SwsContext *c, const uint8_t *src[],
                              int srcStride[], int srcSliceY, int srcSliceH,
                              uint8_t *dst[], int dstStride[])
1313
{
1314
    ff_rgb24toyv12(
1315
        src[0],
1316 1317 1318
        dst[0] +  srcSliceY       * dstStride[0],
        dst[1] + (srcSliceY >> 1) * dstStride[1],
        dst[2] + (srcSliceY >> 1) * dstStride[2],
1319
        c->srcW, srcSliceH,
1320 1321
        dstStride[0], dstStride[1], srcStride[0],
        c->input_rgb2yuv_table);
1322 1323 1324 1325 1326
    if (dst[3])
        fillPlane(dst[3], dstStride[3], c->srcW, srcSliceH, srcSliceY, 255);
    return srcSliceH;
}

1327 1328 1329
static int yvu9ToYv12Wrapper(SwsContext *c, const uint8_t *src[],
                             int srcStride[], int srcSliceY, int srcSliceH,
                             uint8_t *dst[], int dstStride[])
1330 1331 1332 1333
{
    copyPlane(src[0], srcStride[0], srcSliceY, srcSliceH, c->srcW,
              dst[0], dstStride[0]);

1334
    planar2x(src[1], dst[1] + dstStride[1] * (srcSliceY >> 1), c->chrSrcW,
1335
             srcSliceH >> 2, srcStride[1], dstStride[1]);
1336
    planar2x(src[2], dst[2] + dstStride[2] * (srcSliceY >> 1), c->chrSrcW,
1337 1338 1339 1340 1341 1342 1343
             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) */
1344 1345 1346
static int packedCopyWrapper(SwsContext *c, const uint8_t *src[],
                             int srcStride[], int srcSliceY, int srcSliceH,
                             uint8_t *dst[], int dstStride[])
1347
{
1348 1349
    if (dstStride[0] == srcStride[0] && srcStride[0] > 0)
        memcpy(dst[0] + dstStride[0] * srcSliceY, src[0], srcSliceH * dstStride[0]);
1350 1351
    else {
        int i;
1352 1353 1354
        const uint8_t *srcPtr = src[0];
        uint8_t *dstPtr = dst[0] + dstStride[0] * srcSliceY;
        int length = 0;
1355 1356

        /* universal length finder */
1357 1358 1359
        while (length + c->srcW <= FFABS(dstStride[0]) &&
               length + c->srcW <= FFABS(srcStride[0]))
            length += c->srcW;
1360
        av_assert1(length != 0);
1361

1362
        for (i = 0; i < srcSliceH; i++) {
1363
            memcpy(dstPtr, srcPtr, length);
1364 1365
            srcPtr += srcStride[0];
            dstPtr += dstStride[0];
1366 1367 1368 1369 1370
        }
    }
    return srcSliceH;
}

1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391
#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;\
    }

1392 1393 1394
static int planarCopyWrapper(SwsContext *c, const uint8_t *src[],
                             int srcStride[], int srcSliceY, int srcSliceH,
                             uint8_t *dst[], int dstStride[])
1395
{
1396 1397
    const AVPixFmtDescriptor *desc_src = av_pix_fmt_desc_get(c->srcFormat);
    const AVPixFmtDescriptor *desc_dst = av_pix_fmt_desc_get(c->dstFormat);
1398
    int plane, i, j;
1399
    for (plane = 0; plane < 4; plane++) {
1400 1401 1402
        int length = (plane == 0 || plane == 3) ? c->srcW  : FF_CEIL_RSHIFT(c->srcW,   c->chrDstHSubSample);
        int y =      (plane == 0 || plane == 3) ? srcSliceY: FF_CEIL_RSHIFT(srcSliceY, c->chrDstVSubSample);
        int height = (plane == 0 || plane == 3) ? srcSliceH: FF_CEIL_RSHIFT(srcSliceH, c->chrDstVSubSample);
1403 1404
        const uint8_t *srcPtr = src[plane];
        uint8_t *dstPtr = dst[plane] + dstStride[plane] * y;
1405
        int shiftonly= plane==1 || plane==2 || (!c->srcRange && plane==0);
1406

1407 1408
        if (!dst[plane])
            continue;
1409 1410 1411
        // ignore palette for GRAY8
        if (plane == 1 && !dst[2]) continue;
        if (!src[plane] || (plane == 1 && !src[2])) {
1412 1413
            if (is16BPS(c->dstFormat) || isNBPS(c->dstFormat)) {
                fillPlane16(dst[plane], dstStride[plane], length, height, y,
1414 1415
                        plane == 3, desc_dst->comp[plane].depth_minus1,
                        isBE(c->dstFormat));
1416 1417 1418 1419
            } else {
                fillPlane(dst[plane], dstStride[plane], length, height, y,
                        (plane == 3) ? 255 : 128);
            }
1420
        } else {
1421 1422 1423
            if(isNBPS(c->srcFormat) || isNBPS(c->dstFormat)
               || (is16BPS(c->srcFormat) != is16BPS(c->dstFormat))
            ) {
1424 1425
                const int src_depth = desc_src->comp[plane].depth_minus1 + 1;
                const int dst_depth = desc_dst->comp[plane].depth_minus1 + 1;
1426
                const uint16_t *srcPtr2 = (const uint16_t *) srcPtr;
1427
                uint16_t *dstPtr2 = (uint16_t*)dstPtr;
1428

1429 1430 1431
                if (dst_depth == 8) {
                    if(isBE(c->srcFormat) == HAVE_BIGENDIAN){
                        DITHER_COPY(dstPtr, dstStride[plane], srcPtr2, srcStride[plane]/2, , )
1432
                    } else {
1433
                        DITHER_COPY(dstPtr, dstStride[plane], srcPtr2, srcStride[plane]/2, av_bswap16, )
1434
                    }
1435 1436
                } else if (src_depth == 8) {
                    for (i = 0; i < height; i++) {
1437 1438 1439 1440 1441 1442 1443 1444 1445
                        #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)));\
                        }
1446
                        if(isBE(c->dstFormat)){
1447
                            COPY816(AV_WB16)
1448
                        } else {
1449
                            COPY816(AV_WL16)
1450
                        }
1451 1452 1453 1454 1455
                        dstPtr2 += dstStride[plane]/2;
                        srcPtr  += srcStride[plane];
                    }
                } else if (src_depth <= dst_depth) {
                    for (i = 0; i < height; i++) {
1456
                        j = 0;
1457 1458 1459 1460 1461 1462
                        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) \
1463
    for (; j < length - 3; j += 4) { \
1464 1465
        uint64_t v = AV_RN64A(srcPtr2 + j); \
        AV_WN64A(dstPtr2 + j, v << shift); \
1466
    }
1467 1468
#else
#define FAST_COPY_UP(shift) \
1469
    for (; j < length - 1; j += 2) { \
1470 1471
        uint32_t v = AV_RN32A(srcPtr2 + j); \
        AV_WN32A(dstPtr2 + j, v << shift); \
1472
    }
1473 1474 1475 1476 1477 1478 1479
#endif
                             switch (shift)
                             {
                             case 6: FAST_COPY_UP(6); break;
                             case 7: FAST_COPY_UP(7); break;
                             }
                        }
1480
#define COPY_UP(r,w) \
1481
    if(shiftonly){\
1482
        for (; j < length; j++){ \
1483 1484 1485 1486
            unsigned int v= r(&srcPtr2[j]);\
            w(&dstPtr2[j], v<<(dst_depth-src_depth));\
        }\
    }else{\
1487
        for (; j < length; j++){ \
1488 1489 1490 1491
            unsigned int v= r(&srcPtr2[j]);\
            w(&dstPtr2[j], (v<<(dst_depth-src_depth)) | \
                        (v>>(2*src_depth-dst_depth)));\
        }\
1492 1493 1494 1495 1496 1497 1498
    }
                        if(isBE(c->srcFormat)){
                            if(isBE(c->dstFormat)){
                                COPY_UP(AV_RB16, AV_WB16)
                            } else {
                                COPY_UP(AV_RB16, AV_WL16)
                            }
1499
                        } else {
1500 1501 1502 1503 1504
                            if(isBE(c->dstFormat)){
                                COPY_UP(AV_RL16, AV_WB16)
                            } else {
                                COPY_UP(AV_RL16, AV_WL16)
                            }
1505
                        }
1506 1507
                        dstPtr2 += dstStride[plane]/2;
                        srcPtr2 += srcStride[plane]/2;
1508 1509
                    }
                } else {
1510 1511 1512
                    if(isBE(c->srcFormat) == HAVE_BIGENDIAN){
                        if(isBE(c->dstFormat) == HAVE_BIGENDIAN){
                            DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, , )
1513
                        } else {
1514
                            DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, , av_bswap16)
1515
                        }
1516 1517 1518
                    }else{
                        if(isBE(c->dstFormat) == HAVE_BIGENDIAN){
                            DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, av_bswap16, )
1519
                        } else {
1520
                            DITHER_COPY(dstPtr2, dstStride[plane]/2, srcPtr2, srcStride[plane]/2, av_bswap16, av_bswap16)
1521 1522 1523
                        }
                    }
                }
1524 1525 1526 1527 1528 1529 1530 1531
            } 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];
1532 1533 1534
                }
            } else if (dstStride[plane] == srcStride[plane] &&
                       srcStride[plane] > 0 && srcStride[plane] == length) {
1535 1536
                memcpy(dst[plane] + dstStride[plane] * y, src[plane],
                       height * dstStride[plane]);
1537
            } else {
1538 1539
                if (is16BPS(c->srcFormat) && is16BPS(c->dstFormat))
                    length *= 2;
1540
                else if (!desc_src->comp[0].depth_minus1)
1541
                    length >>= 3; // monowhite/black
1542
                for (i = 0; i < height; i++) {
1543
                    memcpy(dstPtr, srcPtr, length);
1544 1545
                    srcPtr += srcStride[plane];
                    dstPtr += dstStride[plane];
1546 1547 1548 1549 1550 1551 1552
                }
            }
        }
    }
    return srcSliceH;
}

1553 1554 1555 1556 1557 1558

#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))


1559 1560
void ff_get_unscaled_swscale(SwsContext *c)
{
1561 1562
    const enum AVPixelFormat srcFormat = c->srcFormat;
    const enum AVPixelFormat dstFormat = c->dstFormat;
1563 1564 1565 1566
    const int flags = c->flags;
    const int dstH = c->dstH;
    int needsDither;

1567 1568 1569
    needsDither = isAnyRGB(dstFormat) &&
            c->dstFormatBpp < 24 &&
           (c->dstFormatBpp < c->srcFormatBpp || (!isAnyRGB(srcFormat)));
1570 1571

    /* yv12_to_nv12 */
1572 1573
    if ((srcFormat == AV_PIX_FMT_YUV420P || srcFormat == AV_PIX_FMT_YUVA420P) &&
        (dstFormat == AV_PIX_FMT_NV12 || dstFormat == AV_PIX_FMT_NV21)) {
1574
        c->swscale = planarToNv12Wrapper;
1575
    }
1576 1577 1578 1579 1580
    /* nv12_to_yv12 */
    if (dstFormat == AV_PIX_FMT_YUV420P &&
        (srcFormat == AV_PIX_FMT_NV12 || srcFormat == AV_PIX_FMT_NV21)) {
        c->swscale = nv12ToPlanarWrapper;
    }
1581
    /* yuv2bgr */
1582 1583
    if ((srcFormat == AV_PIX_FMT_YUV420P || srcFormat == AV_PIX_FMT_YUV422P ||
         srcFormat == AV_PIX_FMT_YUVA420P) && isAnyRGB(dstFormat) &&
1584
        !(flags & SWS_ACCURATE_RND) && (c->dither == SWS_DITHER_BAYER || c->dither == SWS_DITHER_AUTO) && !(dstH & 1)) {
1585
        c->swscale = ff_yuv2rgb_get_func_ptr(c);
1586 1587
    }

1588
    if (srcFormat == AV_PIX_FMT_YUV410P && !(dstH & 3) &&
1589
        (dstFormat == AV_PIX_FMT_YUV420P || dstFormat == AV_PIX_FMT_YUVA420P) &&
1590
        !(flags & SWS_BITEXACT)) {
1591
        c->swscale = yvu9ToYv12Wrapper;
1592 1593 1594
    }

    /* bgr24toYV12 */
1595 1596
    if (srcFormat == AV_PIX_FMT_BGR24 &&
        (dstFormat == AV_PIX_FMT_YUV420P || dstFormat == AV_PIX_FMT_YUVA420P) &&
1597
        !(flags & SWS_ACCURATE_RND))
1598
        c->swscale = bgr24ToYv12Wrapper;
1599 1600

    /* RGB/BGR -> RGB/BGR (no dither needed forms) */
1601
    if (isAnyRGB(srcFormat) && isAnyRGB(dstFormat) && findRgbConvFn(c)
1602
        && (!needsDither || (c->flags&(SWS_FAST_BILINEAR|SWS_POINT))))
1603
        c->swscale = rgbToRgbWrapper;
1604

1605 1606
    if ((srcFormat == AV_PIX_FMT_GBRP && dstFormat == AV_PIX_FMT_GBRAP) ||
        (srcFormat == AV_PIX_FMT_GBRAP && dstFormat == AV_PIX_FMT_GBRP))
1607
        c->swscale = planarRgbToplanarRgbWrapper;
1608

1609 1610 1611 1612 1613 1614
#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 || \
1615
        f == AV_PIX_FMT_BGR24)
1616

1617
    if (srcFormat == AV_PIX_FMT_GBRP && isPlanar(srcFormat) && isByteRGB(dstFormat))
1618
        c->swscale = planarRgbToRgbWrapper;
1619

1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631
    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 ||
         dstFormat == AV_PIX_FMT_GBRAP16LE || dstFormat == AV_PIX_FMT_GBRAP16BE ))
        c->swscale = Rgb16ToPlanarRgb16Wrapper;

1632 1633 1634 1635
    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 ||
1636 1637
         srcFormat == AV_PIX_FMT_GBRP14LE || srcFormat == AV_PIX_FMT_GBRP14BE ||
         srcFormat == AV_PIX_FMT_GBRAP16LE || srcFormat == AV_PIX_FMT_GBRAP16BE) &&
1638 1639 1640 1641
        (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))
1642
        c->swscale = planarRgb16ToRgb16Wrapper;
1643

1644 1645
    if (av_pix_fmt_desc_get(srcFormat)->comp[0].depth_minus1 == 7 &&
        isPackedRGB(srcFormat) && dstFormat == AV_PIX_FMT_GBRP)
1646
        c->swscale = rgbToPlanarRgbWrapper;
1647

1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658
    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);
        }
    }

1659
    /* bswap 16 bits per pixel/component packed formats */
1660 1661 1662 1663 1664
    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) ||
1665
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BGR48)  ||
1666
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BGRA64) ||
1667 1668
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BGR555) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BGR565) ||
1669
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_BGRA64) ||
1670
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GRAY16) ||
1671
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_YA16)   ||
1672 1673 1674 1675 1676
        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) ||
1677
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_GBRAP16) ||
1678 1679
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGB444) ||
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGB48)  ||
1680
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGBA64) ||
1681
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGB555) ||
1682
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGB565) ||
1683
        IS_DIFFERENT_ENDIANESS(srcFormat, dstFormat, AV_PIX_FMT_RGBA64) ||
1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699
        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) ||
        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))
1700
        c->swscale = packed_16bpc_bswap;
1701

1702
    if (usePal(srcFormat) && isByteRGB(dstFormat))
1703
        c->swscale = palToRgbWrapper;
1704

1705 1706
    if (srcFormat == AV_PIX_FMT_YUV422P) {
        if (dstFormat == AV_PIX_FMT_YUYV422)
1707
            c->swscale = yuv422pToYuy2Wrapper;
1708
        else if (dstFormat == AV_PIX_FMT_UYVY422)
1709
            c->swscale = yuv422pToUyvyWrapper;
1710 1711 1712 1713 1714
    }

    /* LQ converters if -sws 0 or -sws 4*/
    if (c->flags&(SWS_FAST_BILINEAR|SWS_POINT)) {
        /* yv12_to_yuy2 */
1715 1716
        if (srcFormat == AV_PIX_FMT_YUV420P || srcFormat == AV_PIX_FMT_YUVA420P) {
            if (dstFormat == AV_PIX_FMT_YUYV422)
1717
                c->swscale = planarToYuy2Wrapper;
1718
            else if (dstFormat == AV_PIX_FMT_UYVY422)
1719
                c->swscale = planarToUyvyWrapper;
1720 1721
        }
    }
1722 1723
    if (srcFormat == AV_PIX_FMT_YUYV422 &&
       (dstFormat == AV_PIX_FMT_YUV420P || dstFormat == AV_PIX_FMT_YUVA420P))
1724
        c->swscale = yuyvToYuv420Wrapper;
1725 1726
    if (srcFormat == AV_PIX_FMT_UYVY422 &&
       (dstFormat == AV_PIX_FMT_YUV420P || dstFormat == AV_PIX_FMT_YUVA420P))
1727
        c->swscale = uyvyToYuv420Wrapper;
1728
    if (srcFormat == AV_PIX_FMT_YUYV422 && dstFormat == AV_PIX_FMT_YUV422P)
1729
        c->swscale = yuyvToYuv422Wrapper;
1730
    if (srcFormat == AV_PIX_FMT_UYVY422 && dstFormat == AV_PIX_FMT_YUV422P)
1731
        c->swscale = uyvyToYuv422Wrapper;
1732

1733
#define isPlanarGray(x) (isGray(x) && (x) != AV_PIX_FMT_YA8 && (x) != AV_PIX_FMT_YA16LE && (x) != AV_PIX_FMT_YA16BE)
1734
    /* simple copy */
1735
    if ( srcFormat == dstFormat ||
1736 1737
        (srcFormat == AV_PIX_FMT_YUVA420P && dstFormat == AV_PIX_FMT_YUV420P) ||
        (srcFormat == AV_PIX_FMT_YUV420P && dstFormat == AV_PIX_FMT_YUVA420P) ||
1738 1739 1740
        (isPlanarYUV(srcFormat) && isPlanarGray(dstFormat)) ||
        (isPlanarYUV(dstFormat) && isPlanarGray(srcFormat)) ||
        (isPlanarGray(dstFormat) && isPlanarGray(srcFormat)) ||
1741 1742 1743
        (isPlanarYUV(srcFormat) && isPlanarYUV(dstFormat) &&
         c->chrDstHSubSample == c->chrSrcHSubSample &&
         c->chrDstVSubSample == c->chrSrcVSubSample &&
1744 1745
         dstFormat != AV_PIX_FMT_NV12 && dstFormat != AV_PIX_FMT_NV21 &&
         srcFormat != AV_PIX_FMT_NV12 && srcFormat != AV_PIX_FMT_NV21))
1746 1747
    {
        if (isPacked(c->srcFormat))
1748
            c->swscale = packedCopyWrapper;
1749
        else /* Planar YUV or gray */
1750
            c->swscale = planarCopyWrapper;
1751 1752
    }

1753
    if (ARCH_PPC)
1754
        ff_get_unscaled_swscale_ppc(c);
1755 1756
//     if (ARCH_ARM)
//         ff_get_unscaled_swscale_arm(c);
1757 1758 1759
}

/* Convert the palette to the same packed 32-bit format as the palette */
1760 1761
void sws_convertPalette8ToPacked32(const uint8_t *src, uint8_t *dst,
                                   int num_pixels, const uint8_t *palette)
1762 1763 1764
{
    int i;

1765
    for (i = 0; i < num_pixels; i++)
1766 1767 1768 1769
        ((uint32_t *) dst)[i] = ((const uint32_t *) palette)[src[i]];
}

/* Palette format: ABCD -> dst format: ABC */
1770 1771
void sws_convertPalette8ToPacked24(const uint8_t *src, uint8_t *dst,
                                   int num_pixels, const uint8_t *palette)
1772 1773 1774
{
    int i;

1775
    for (i = 0; i < num_pixels; i++) {
1776
        //FIXME slow?
1777 1778 1779 1780
        dst[0] = palette[src[i] * 4 + 0];
        dst[1] = palette[src[i] * 4 + 1];
        dst[2] = palette[src[i] * 4 + 2];
        dst += 3;
1781 1782
    }
}