aic.c 15.7 KB
Newer Older
1 2 3 4 5
/*
 * Apple Intermediate Codec decoder
 *
 * Copyright (c) 2013 Konstantin Shishkov
 *
6
 * This file is part of FFmpeg.
7
 *
8
 * FFmpeg is free software; you can redistribute it and/or
9 10 11 12
 * 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.
 *
13
 * FFmpeg is distributed in the hope that it will be useful,
14 15 16 17 18
 * 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
19
 * License along with FFmpeg; if not, write to the Free Software
20 21 22
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

23 24
#include <inttypes.h>

25 26 27 28 29
#include "avcodec.h"
#include "bytestream.h"
#include "internal.h"
#include "get_bits.h"
#include "golomb.h"
30
#include "idctdsp.h"
31
#include "thread.h"
32 33 34 35 36 37 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135
#include "unary.h"

#define AIC_HDR_SIZE    24
#define AIC_BAND_COEFFS (64 + 32 + 192 + 96)

enum AICBands {
    COEFF_LUMA = 0,
    COEFF_CHROMA,
    COEFF_LUMA_EXT,
    COEFF_CHROMA_EXT,
    NUM_BANDS
};

static const int aic_num_band_coeffs[NUM_BANDS] = { 64, 32, 192, 96 };

static const int aic_band_off[NUM_BANDS] = { 0, 64, 96, 288 };

static const uint8_t aic_quant_matrix[64] = {
     8, 16, 19, 22, 22, 26, 26, 27,
    16, 16, 22, 22, 26, 27, 27, 29,
    19, 22, 26, 26, 27, 29, 29, 35,
    22, 24, 27, 27, 29, 32, 34, 38,
    26, 27, 29, 29, 32, 35, 38, 46,
    27, 29, 34, 34, 35, 40, 46, 56,
    29, 34, 34, 37, 40, 48, 56, 69,
    34, 37, 38, 40, 48, 58, 69, 83,
};

static const uint8_t aic_y_scan[64] = {
     0,  4,  1,  2,  5,  8, 12,  9,
     6,  3,  7, 10, 13, 14, 11, 15,
    47, 43, 46, 45, 42, 39, 35, 38,
    41, 44, 40, 37, 34, 33, 36, 32,
    16, 20, 17, 18, 21, 24, 28, 25,
    22, 19, 23, 26, 29, 30, 27, 31,
    63, 59, 62, 61, 58, 55, 51, 54,
    57, 60, 56, 53, 50, 49, 52, 48,
};

static const uint8_t aic_y_ext_scan[192] = {
     64,  72,  65,  66,  73,  80,  88,  81,
     74,  67,  75,  82,  89,  90,  83,  91,
      0,   4,   1,   2,   5,   8,  12,   9,
      6,   3,   7,  10,  13,  14,  11,  15,
     16,  20,  17,  18,  21,  24,  28,  25,
     22,  19,  23,  26,  29,  30,  27,  31,
    155, 147, 154, 153, 146, 139, 131, 138,
    145, 152, 144, 137, 130, 129, 136, 128,
     47,  43,  46,  45,  42,  39,  35,  38,
     41,  44,  40,  37,  34,  33,  36,  32,
     63,  59,  62,  61,  58,  55,  51,  54,
     57,  60,  56,  53,  50,  49,  52,  48,
     96, 104,  97,  98, 105, 112, 120, 113,
    106,  99, 107, 114, 121, 122, 115, 123,
     68,  76,  69,  70,  77,  84,  92,  85,
     78,  71,  79,  86,  93,  94,  87,  95,
    100, 108, 101, 102, 109, 116, 124, 117,
    110, 103, 111, 118, 125, 126, 119, 127,
    187, 179, 186, 185, 178, 171, 163, 170,
    177, 184, 176, 169, 162, 161, 168, 160,
    159, 151, 158, 157, 150, 143, 135, 142,
    149, 156, 148, 141, 134, 133, 140, 132,
    191, 183, 190, 189, 182, 175, 167, 174,
    181, 188, 180, 173, 166, 165, 172, 164,
};

static const uint8_t aic_c_scan[64] = {
     0,  4,  1,  2,  5,  8, 12,  9,
     6,  3,  7, 10, 13, 14, 11, 15,
    31, 27, 30, 29, 26, 23, 19, 22,
    25, 28, 24, 21, 18, 17, 20, 16,
    32, 36, 33, 34, 37, 40, 44, 41,
    38, 35, 39, 42, 45, 46, 43, 47,
    63, 59, 62, 61, 58, 55, 51, 54,
    57, 60, 56, 53, 50, 49, 52, 48,
};

static const uint8_t aic_c_ext_scan[192] = {
     16,  24,  17,  18,  25,  32,  40,  33,
     26,  19,  27,  34,  41,  42,  35,  43,
      0,   4,   1,   2,   5,   8,  12,   9,
      6,   3,   7,  10,  13,  14,  11,  15,
     20,  28,  21,  22,  29,  36,  44,  37,
     30,  23,  31,  38,  45,  46,  39,  47,
     95,  87,  94,  93,  86,  79,  71,  78,
     85,  92,  84,  77,  70,  69,  76,  68,
     63,  59,  62,  61,  58,  55,  51,  54,
     57,  60,  56,  53,  50,  49,  52,  48,
     91,  83,  90,  89,  82,  75,  67,  74,
     81,  88,  80,  73,  66,  65,  72,  64,
    112, 120, 113, 114, 121, 128, 136, 129,
    122, 115, 123, 130, 137, 138, 131, 139,
     96, 100,  97,  98, 101, 104, 108, 105,
    102,  99, 103, 106, 109, 110, 107, 111,
    116, 124, 117, 118, 125, 132, 140, 133,
    126, 119, 127, 134, 141, 142, 135, 143,
    191, 183, 190, 189, 182, 175, 167, 174,
    181, 188, 180, 173, 166, 165, 172, 164,
    159, 155, 158, 157, 154, 151, 147, 150,
    153, 156, 152, 149, 146, 145, 148, 144,
    187, 179, 186, 185, 178, 171, 163, 170,
    177, 184, 176, 169, 162, 161, 168, 160,
};

136
static const uint8_t * const aic_scan[NUM_BANDS] = {
137 138 139 140 141 142
    aic_y_scan, aic_c_scan, aic_y_ext_scan, aic_c_ext_scan
};

typedef struct AICContext {
    AVCodecContext *avctx;
    AVFrame        *frame;
143
    IDCTDSPContext idsp;
144 145 146 147 148 149 150 151 152 153 154 155
    ScanTable      scantable;

    int            num_x_slices;
    int            slice_width;
    int            mb_width, mb_height;
    int            quant;
    int            interlaced;

    int16_t        *slice_data;
    int16_t        *data_ptr[NUM_BANDS];

    DECLARE_ALIGNED(16, int16_t, block)[64];
156
    DECLARE_ALIGNED(16, uint8_t, quant_matrix)[64];
157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175
} AICContext;

static int aic_decode_header(AICContext *ctx, const uint8_t *src, int size)
{
    uint32_t frame_size;
    int width, height;

    if (src[0] != 1) {
        av_log(ctx->avctx, AV_LOG_ERROR, "Invalid version %d\n", src[0]);
        return AVERROR_INVALIDDATA;
    }
    if (src[1] != AIC_HDR_SIZE - 2) {
        av_log(ctx->avctx, AV_LOG_ERROR, "Invalid header size %d\n", src[1]);
        return AVERROR_INVALIDDATA;
    }
    frame_size = AV_RB32(src + 2);
    width      = AV_RB16(src + 6);
    height     = AV_RB16(src + 8);
    if (frame_size > size) {
176
        av_log(ctx->avctx, AV_LOG_ERROR, "Frame size should be %"PRIu32" got %d\n",
177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202
               frame_size, size);
        return AVERROR_INVALIDDATA;
    }
    if (width != ctx->avctx->width || height != ctx->avctx->height) {
        av_log(ctx->avctx, AV_LOG_ERROR,
               "Picture dimension changed: old: %d x %d, new: %d x %d\n",
               ctx->avctx->width, ctx->avctx->height, width, height);
        return AVERROR_INVALIDDATA;
    }
    ctx->quant      = src[15];
    ctx->interlaced = ((src[16] >> 4) == 3);

    return 0;
}

#define GET_CODE(val, type, add_bits)                         \
    do {                                                      \
        if (type)                                             \
            val = get_ue_golomb(gb);                          \
        else                                                  \
            val = get_unary(gb, 1, 31);                       \
        if (add_bits)                                         \
            val = (val << add_bits) + get_bits(gb, add_bits); \
    } while (0)

static int aic_decode_coeffs(GetBitContext *gb, int16_t *dst,
203
                             int band, int slice_width, int force_chroma)
204 205 206
{
    int has_skips, coeff_type, coeff_bits, skip_type, skip_bits;
    const int num_coeffs = aic_num_band_coeffs[band];
207
    const uint8_t *scan = aic_scan[band | force_chroma];
208 209
    int mb, idx;
    unsigned val;
210 211 212 213 214 215 216 217 218 219 220 221 222

    has_skips  = get_bits1(gb);
    coeff_type = get_bits1(gb);
    coeff_bits = get_bits(gb, 3);

    if (has_skips) {
        skip_type = get_bits1(gb);
        skip_bits = get_bits(gb, 3);

        for (mb = 0; mb < slice_width; mb++) {
            idx = -1;
            do {
                GET_CODE(val, skip_type, skip_bits);
223 224
                if (val >= 0x10000)
                    return AVERROR_INVALIDDATA;
225 226 227 228 229
                idx += val + 1;
                if (idx >= num_coeffs)
                    break;
                GET_CODE(val, coeff_type, coeff_bits);
                val++;
230
                if (val >= 0x10000)
231 232 233 234 235 236 237 238 239
                    return AVERROR_INVALIDDATA;
                dst[scan[idx]] = val;
            } while (idx < num_coeffs - 1);
            dst += num_coeffs;
        }
    } else {
        for (mb = 0; mb < slice_width; mb++) {
            for (idx = 0; idx < num_coeffs; idx++) {
                GET_CODE(val, coeff_type, coeff_bits);
240
                if (val >= 0x10000)
241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291
                    return AVERROR_INVALIDDATA;
                dst[scan[idx]] = val;
            }
            dst += num_coeffs;
        }
    }
    return 0;
}

static void recombine_block(int16_t *dst, const uint8_t *scan,
                            int16_t **base, int16_t **ext)
{
    int i, j;

    for (i = 0; i < 4; i++) {
        for (j = 0; j < 4; j++)
            dst[scan[i * 8 + j]]     = (*base)[j];
        for (j = 0; j < 4; j++)
            dst[scan[i * 8 + j + 4]] = (*ext)[j];
        *base += 4;
        *ext  += 4;
    }
    for (; i < 8; i++) {
        for (j = 0; j < 8; j++)
            dst[scan[i * 8 + j]] = (*ext)[j];
        *ext  += 8;
    }
}

static void recombine_block_il(int16_t *dst, const uint8_t *scan,
                               int16_t **base, int16_t **ext,
                               int block_no)
{
    int i, j;

    if (block_no < 2) {
        for (i = 0; i < 8; i++) {
            for (j = 0; j < 4; j++)
                dst[scan[i * 8 + j]]     = (*base)[j];
            for (j = 0; j < 4; j++)
                dst[scan[i * 8 + j + 4]] = (*ext)[j];
            *base += 4;
            *ext  += 4;
        }
    } else {
        for (i = 0; i < 64; i++)
            dst[scan[i]] = (*ext)[i];
        *ext += 64;
    }
}

292
static void unquant_block(int16_t *block, int q, uint8_t *quant_matrix)
293 294 295 296 297 298 299
{
    int i;

    for (i = 0; i < 64; i++) {
        int val  = (uint16_t)block[i];
        int sign = val & 1;

300
        block[i] = (((val >> 1) ^ -sign) * q * quant_matrix[i] >> 4)
301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328
                   + sign;
    }
}

static int aic_decode_slice(AICContext *ctx, int mb_x, int mb_y,
                            const uint8_t *src, int src_size)
{
    GetBitContext gb;
    int ret, i, mb, blk;
    int slice_width = FFMIN(ctx->slice_width, ctx->mb_width - mb_x);
    uint8_t *Y, *C[2];
    uint8_t *dst;
    int16_t *base_y = ctx->data_ptr[COEFF_LUMA];
    int16_t *base_c = ctx->data_ptr[COEFF_CHROMA];
    int16_t *ext_y  = ctx->data_ptr[COEFF_LUMA_EXT];
    int16_t *ext_c  = ctx->data_ptr[COEFF_CHROMA_EXT];
    const int ystride = ctx->frame->linesize[0];

    Y = ctx->frame->data[0] + mb_x * 16 + mb_y * 16 * ystride;
    for (i = 0; i < 2; i++)
        C[i] = ctx->frame->data[i + 1] + mb_x * 8
               + mb_y * 8 * ctx->frame->linesize[i + 1];
    init_get_bits(&gb, src, src_size * 8);

    memset(ctx->slice_data, 0,
           sizeof(*ctx->slice_data) * slice_width * AIC_BAND_COEFFS);
    for (i = 0; i < NUM_BANDS; i++)
        if ((ret = aic_decode_coeffs(&gb, ctx->data_ptr[i],
329 330
                                     i, slice_width,
                                     !ctx->interlaced)) < 0)
331 332 333 334 335 336 337 338 339 340
            return ret;

    for (mb = 0; mb < slice_width; mb++) {
        for (blk = 0; blk < 4; blk++) {
            if (!ctx->interlaced)
                recombine_block(ctx->block, ctx->scantable.permutated,
                                &base_y, &ext_y);
            else
                recombine_block_il(ctx->block, ctx->scantable.permutated,
                                   &base_y, &ext_y, blk);
341
            unquant_block(ctx->block, ctx->quant, ctx->quant_matrix);
342
            ctx->idsp.idct(ctx->block);
343 344

            if (!ctx->interlaced) {
345
                dst = Y + (blk >> 1) * 8 * ystride + (blk & 1) * 8;
346
                ctx->idsp.put_signed_pixels_clamped(ctx->block, dst, ystride);
347 348
            } else {
                dst = Y + (blk & 1) * 8 + (blk >> 1) * ystride;
349 350
                ctx->idsp.put_signed_pixels_clamped(ctx->block, dst,
                                                    ystride * 2);
351 352 353 354 355 356 357
            }
        }
        Y += 16;

        for (blk = 0; blk < 2; blk++) {
            recombine_block(ctx->block, ctx->scantable.permutated,
                            &base_c, &ext_c);
358
            unquant_block(ctx->block, ctx->quant, ctx->quant_matrix);
359 360 361
            ctx->idsp.idct(ctx->block);
            ctx->idsp.put_signed_pixels_clamped(ctx->block, C[blk],
                                                ctx->frame->linesize[blk + 1]);
362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378
            C[blk] += 8;
        }
    }

    return 0;
}

static int aic_decode_frame(AVCodecContext *avctx, void *data, int *got_frame,
                            AVPacket *avpkt)
{
    AICContext *ctx    = avctx->priv_data;
    const uint8_t *buf = avpkt->data;
    int buf_size       = avpkt->size;
    GetByteContext gb;
    uint32_t off;
    int x, y, ret;
    int slice_size;
379
    ThreadFrame frame = { .f = data };
380 381 382 383 384 385 386 387 388 389 390 391

    ctx->frame            = data;
    ctx->frame->pict_type = AV_PICTURE_TYPE_I;
    ctx->frame->key_frame = 1;

    off = FFALIGN(AIC_HDR_SIZE + ctx->num_x_slices * ctx->mb_height * 2, 4);

    if (buf_size < off) {
        av_log(avctx, AV_LOG_ERROR, "Too small frame\n");
        return AVERROR_INVALIDDATA;
    }

392 393 394
    ret = aic_decode_header(ctx, buf, buf_size);
    if (ret < 0) {
        av_log(avctx, AV_LOG_ERROR, "Invalid header\n");
395
        return ret;
396
    }
397

398
    if ((ret = ff_thread_get_buffer(avctx, &frame, 0)) < 0)
399 400 401 402 403 404 405 406 407
        return ret;

    bytestream2_init(&gb, buf + AIC_HDR_SIZE,
                     ctx->num_x_slices * ctx->mb_height * 2);

    for (y = 0; y < ctx->mb_height; y++) {
        for (x = 0; x < ctx->mb_width; x += ctx->slice_width) {
            slice_size = bytestream2_get_le16(&gb) * 4;
            if (slice_size + off > buf_size || !slice_size) {
408 409
                av_log(avctx, AV_LOG_ERROR,
                       "Incorrect slice size %d at %d.%d\n", slice_size, x, y);
410 411 412
                return AVERROR_INVALIDDATA;
            }

413 414 415 416
            ret = aic_decode_slice(ctx, x, y, buf + off, slice_size);
            if (ret < 0) {
                av_log(avctx, AV_LOG_ERROR,
                       "Error decoding slice at %d.%d\n", x, y);
417
                return ret;
418
            }
419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438

            off += slice_size;
        }
    }

    *got_frame = 1;

    return avpkt->size;
}

static av_cold int aic_decode_init(AVCodecContext *avctx)
{
    AICContext *ctx = avctx->priv_data;
    int i;
    uint8_t scan[64];

    ctx->avctx = avctx;

    avctx->pix_fmt = AV_PIX_FMT_YUV420P;

439
    ff_idctdsp_init(&ctx->idsp, avctx);
440 441 442

    for (i = 0; i < 64; i++)
        scan[i] = i;
443
    ff_init_scantable(ctx->idsp.idct_permutation, &ctx->scantable, scan);
444
    for (i = 0; i < 64; i++)
445
        ctx->quant_matrix[ctx->idsp.idct_permutation[i]] = aic_quant_matrix[i];
446 447 448 449

    ctx->mb_width  = FFALIGN(avctx->width,  16) >> 4;
    ctx->mb_height = FFALIGN(avctx->height, 16) >> 4;

450 451
    ctx->num_x_slices = (ctx->mb_width + 15) >> 4;
    ctx->slice_width  = 16;
452
    for (i = 1; i < ctx->mb_width; i++) {
453
        if (!(ctx->mb_width % i) && (ctx->mb_width / i <= 32)) {
454 455 456 457 458 459
            ctx->slice_width  = ctx->mb_width / i;
            ctx->num_x_slices = i;
            break;
        }
    }

460
    ctx->slice_data = av_malloc_array(ctx->slice_width, AIC_BAND_COEFFS
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
                                * sizeof(*ctx->slice_data));
    if (!ctx->slice_data) {
        av_log(avctx, AV_LOG_ERROR, "Error allocating slice buffer\n");

        return AVERROR(ENOMEM);
    }

    for (i = 0; i < NUM_BANDS; i++)
        ctx->data_ptr[i] = ctx->slice_data + ctx->slice_width
                                             * aic_band_off[i];

    return 0;
}

static av_cold int aic_decode_close(AVCodecContext *avctx)
{
    AICContext *ctx = avctx->priv_data;

    av_freep(&ctx->slice_data);

    return 0;
}

AVCodec ff_aic_decoder = {
    .name           = "aic",
486
    .long_name      = NULL_IF_CONFIG_SMALL("Apple Intermediate Codec"),
487 488 489 490 491 492
    .type           = AVMEDIA_TYPE_VIDEO,
    .id             = AV_CODEC_ID_AIC,
    .priv_data_size = sizeof(AICContext),
    .init           = aic_decode_init,
    .close          = aic_decode_close,
    .decode         = aic_decode_frame,
493 494
    .capabilities   = AV_CODEC_CAP_DR1 | AV_CODEC_CAP_FRAME_THREADS,
    .init_thread_copy = ONLY_IF_THREADS_ENABLED(aic_decode_init),
495
    .caps_internal  = FF_CODEC_CAP_INIT_THREADSAFE,
496
};