wmv2.c

来自「君正早期ucos系统(只有早期的才不没有打包成库),MPLAYER,文件系统,图」· C语言 代码 · 共 1,478 行 · 第 1/4 页

        cbp = code & 0x3f;
    } else {
        s->mb_intra = 1;
        code = get_vlc2(&s->gb, ff_msmp4_mb_i_vlc.table, MB_INTRA_VLC_BITS, 2);
        if (code < 0){
            av_log(s->avctx, AV_LOG_ERROR, "II-cbp illegal at %d %d\n", s->mb_x, s->mb_y);
            return -1;
        }
        /* predict coded block pattern */
        cbp = 0;
        for(i=0;i<6;i++) {
            int val = ((code >> (5 - i)) & 1);
            if (i < 4) {
                int pred = coded_block_pred(s, i, &coded_val);
                val = val ^ pred;
                *coded_val = val;
            }
            cbp |= val << (5 - i);
        }
    }

    if (!s->mb_intra) {
        int mx, my;
//printf("P at %d %d\n", s->mb_x, s->mb_y);
        wmv2_pred_motion(w, &mx, &my);

        if(cbp){
            s->dsp.clear_blocks(s->block[0]);
            if(s->per_mb_rl_table){
                s->rl_table_index = decode012(&s->gb);
                s->rl_chroma_table_index = s->rl_table_index;
            }

            if(w->abt_flag && w->per_mb_abt){
                w->per_block_abt= get_bits1(&s->gb);
                if(!w->per_block_abt)
                    w->abt_type= decode012(&s->gb);
            }else
                w->per_block_abt=0;
        }

        if (wmv2_decode_motion(w, &mx, &my) < 0)
            return -1;

        s->mv_dir = MV_DIR_FORWARD;
        s->mv_type = MV_TYPE_16X16;
        s->mv[0][0][0] = mx;
        s->mv[0][0][1] = my;

        for (i = 0; i < 6; i++) {
            if (wmv2_decode_inter_block(w, block[i], i, (cbp >> (5 - i)) & 1) < 0)
            {
                av_log(s->avctx, AV_LOG_ERROR, "\nerror while decoding inter block: %d x %d (%d)\n", s->mb_x, s->mb_y, i);
                return -1;
            }
        }
    } else {
//if(s->pict_type==P_TYPE)
//   printf("%d%d ", s->inter_intra_pred, cbp);
//printf("I at %d %d %d %06X\n", s->mb_x, s->mb_y, ((cbp&3)? 1 : 0) +((cbp&0x3C)? 2 : 0), show_bits(&s->gb, 24));
        s->ac_pred = get_bits1(&s->gb);
        if(s->inter_intra_pred){
            s->h263_aic_dir= get_vlc2(&s->gb, inter_intra_vlc.table, INTER_INTRA_VLC_BITS, 1);
//            printf("%d%d %d %d/", s->ac_pred, s->h263_aic_dir, s->mb_x, s->mb_y);
        }
        if(s->per_mb_rl_table && cbp){
            s->rl_table_index = decode012(&s->gb);
            s->rl_chroma_table_index = s->rl_table_index;
        }

        s->dsp.clear_blocks(s->block[0]);
        for (i = 0; i < 6; i++) {
            if (msmpeg4_decode_block(s, block[i], i, (cbp >> (5 - i)) & 1, NULL) < 0)
            {
                av_log(s->avctx, AV_LOG_ERROR, "\nerror while decoding intra block: %d x %d (%d)\n", s->mb_x, s->mb_y, i);
                return -1;
            }
        }
    }

    return 0;
}

static int wmv2_decode_init(AVCodecContext *avctx){
    Wmv2Context * const w= avctx->priv_data;

    if(ff_h263_decode_init(avctx) < 0)
        return -1;

    wmv2_common_init(w);

    return 0;
}

#ifdef CONFIG_WMV2_DECODER
AVCodec wmv2_decoder = {
    "wmv2",
    CODEC_TYPE_VIDEO,
    CODEC_ID_WMV2,
    sizeof(Wmv2Context),
    wmv2_decode_init,
    NULL,
    ff_h263_decode_end,
    ff_h263_decode_frame,
    CODEC_CAP_DRAW_HORIZ_BAND | CODEC_CAP_DR1,
};
#endif

#ifdef CONFIG_WMV2_ENCODER
AVCodec wmv2_encoder = {
    "wmv2",
    CODEC_TYPE_VIDEO,
    CODEC_ID_WMV2,
    sizeof(Wmv2Context),
    wmv2_encode_init,
    MPV_encode_picture,
    MPV_encode_end,
    .pix_fmts= (enum PixelFormat[]){PIX_FMT_YUV420P, -1},
};
#endif


#ifdef USE_16M_SDRAM

#include "avcodec.h"
#include "dsputil.h"
#include "simple_idct.h"

//#ifdef JZ4740_MXU_OPT
//#include "jzmedia.h"
//Q15 Constant Data
//#define  WM44  0x5A825A82   //(W4,W4)
//#define  WM26  0x764230FC   //(W2,W6)
//#define  WM13  0x7D8A6A6E   //(W1,W3)
//#define  WM57  0x471D18F9   //(W5,W7)

#if 0
#define W1 2841 /* 2048*sqrt (2)*cos (1*pi/16) */
#define W2 2676 /* 2048*sqrt (2)*cos (2*pi/16) */
#define W3 2408 /* 2048*sqrt (2)*cos (3*pi/16) */
#define W4 2048 /* 2048*sqrt (2)*cos (4*pi/16) */
#define W5 1609 /* 2048*sqrt (2)*cos (5*pi/16) */
#define W6 1108 /* 2048*sqrt (2)*cos (6*pi/16) */
#define W7 565  /* 2048*sqrt (2)*cos (7*pi/16) */
#define ROW_SHIFT 8
#define COL_SHIFT 17
#else
#define W1  22725  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
#define W2  21407  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
#define W3  19266  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
#define W4  16383  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
#define W5  12873  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
#define W6  8867   //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
#define W7  4520   //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
#define ROW_SHIFT 11
#define COL_SHIFT 20 // 6
#endif

#if defined(ARCH_POWERPC_405)
/* signed 16x16 -> 32 multiply add accumulate */
#define MAC16(rt, ra, rb) \
    asm ("maclhw %0, %2, %3" : "=r" (rt) : "0" (rt), "r" (ra), "r" (rb));

/* signed 16x16 -> 32 multiply */
#define MUL16(rt, ra, rb) \
    asm ("mullhw %0, %1, %2" : "=r" (rt) : "r" (ra), "r" (rb));

#else

/* signed 16x16 -> 32 multiply add accumulate */
#define MAC16(rt, ra, rb) rt += (ra) * (rb)

/* signed 16x16 -> 32 multiply */
#define MUL16(rt, ra, rb) rt = (ra) * (rb)

#endif

static inline void idctRowCondDC (DCTELEM * row)
{
        int a0, a1, a2, a3, b0, b1, b2, b3;
#ifdef HAVE_FAST_64BIT
        uint64_t temp;
#else
        uint32_t temp;
#endif

#ifdef HAVE_FAST_64BIT
#ifdef WORDS_BIGENDIAN
#define ROW0_MASK 0xffff000000000000LL
#else
#define ROW0_MASK 0xffffLL
#endif
        if(sizeof(DCTELEM)==2){
            if ( ((((uint64_t *)row)[0] & ~ROW0_MASK) |
                  ((uint64_t *)row)[1]) == 0) {
                temp = (row[0] << 3) & 0xffff;
                temp += temp << 16;
                temp += temp << 32;
                ((uint64_t *)row)[0] = temp;
                ((uint64_t *)row)[1] = temp;
                return;
            }
        }else{
            if (!(row[1]|row[2]|row[3]|row[4]|row[5]|row[6]|row[7])) {
                row[0]=row[1]=row[2]=row[3]=row[4]=row[5]=row[6]=row[7]= row[0] << 3;
                return;
            }
        }
#else
        if(sizeof(DCTELEM)==2){
            if (!(((uint32_t*)row)[1] |
                  ((uint32_t*)row)[2] |
                  ((uint32_t*)row)[3] |
                  row[1])) {
                temp = (row[0] << 3) & 0xffff;
                temp += temp << 16;
                ((uint32_t*)row)[0]=((uint32_t*)row)[1] =
                ((uint32_t*)row)[2]=((uint32_t*)row)[3] = temp;
                return;
            }
        }else{
            if (!(row[1]|row[2]|row[3]|row[4]|row[5]|row[6]|row[7])) {
                row[0]=row[1]=row[2]=row[3]=row[4]=row[5]=row[6]=row[7]= row[0] << 3;
                return;
            }
        }
#endif

        a0 = (W4 * row[0]) + (1 << (ROW_SHIFT - 1));
        a1 = a0;
        a2 = a0;
        a3 = a0;

        /* no need to optimize : gcc does it */
        a0 += W2 * row[2];
        a1 += W6 * row[2];
        a2 -= W6 * row[2];
        a3 -= W2 * row[2];

        MUL16(b0, W1, row[1]);
        MAC16(b0, W3, row[3]);
        MUL16(b1, W3, row[1]);
        MAC16(b1, -W7, row[3]);
        MUL16(b2, W5, row[1]);
        MAC16(b2, -W1, row[3]);
        MUL16(b3, W7, row[1]);
        MAC16(b3, -W5, row[3]);

#ifdef HAVE_FAST_64BIT
        temp = ((uint64_t*)row)[1];
#else
        temp = ((uint32_t*)row)[2] | ((uint32_t*)row)[3];
#endif
        if (temp != 0) {
            a0 += W4*row[4] + W6*row[6];
            a1 += - W4*row[4] - W2*row[6];
            a2 += - W4*row[4] + W2*row[6];
            a3 += W4*row[4] - W6*row[6];

            MAC16(b0, W5, row[5]);
            MAC16(b0, W7, row[7]);

            MAC16(b1, -W1, row[5]);
            MAC16(b1, -W5, row[7]);

            MAC16(b2, W7, row[5]);
            MAC16(b2, W3, row[7]);

            MAC16(b3, W3, row[5]);
            MAC16(b3, -W1, row[7]);
        }

        row[0] = (a0 + b0) >> ROW_SHIFT;
        row[7] = (a0 - b0) >> ROW_SHIFT;
        row[1] = (a1 + b1) >> ROW_SHIFT;
        row[6] = (a1 - b1) >> ROW_SHIFT;
        row[2] = (a2 + b2) >> ROW_SHIFT;
        row[5] = (a2 - b2) >> ROW_SHIFT;
        row[3] = (a3 + b3) >> ROW_SHIFT;
        row[4] = (a3 - b3) >> ROW_SHIFT;
}

static inline void idctSparseColAdd (uint8_t *dest, int line_size,
                                     DCTELEM * col)
{
        int a0, a1, a2, a3, b0, b1, b2, b3;
        uint8_t *cm = ff_cropTbl + MAX_NEG_CROP;

        /* XXX: I did that only to give same values as previous code */
        a0 = W4 * (col[8*0] + ((1<<(COL_SHIFT-1))/W4));
        a1 = a0;
        a2 = a0;
        a3 = a0;

        a0 +=  + W2*col[8*2];
        a1 +=  + W6*col[8*2];
        a2 +=  - W6*col[8*2];
        a3 +=  - W2*col[8*2];

        MUL16(b0, W1, col[8*1]);
        MUL16(b1, W3, col[8*1]);
        MUL16(b2, W5, col[8*1]);
        MUL16(b3, W7, col[8*1]);

        MAC16(b0, + W3, col[8*3]);
        MAC16(b1, - W7, col[8*3]);
        MAC16(b2, - W1, col[8*3]);
        MAC16(b3, - W5, col[8*3]);

        if(col[8*4]){
            a0 += + W4*col[8*4];
            a1 += - W4*col[8*4];
            a2 += - W4*col[8*4];
            a3 += + W4*col[8*4];
        }

        if (col[8*5]) {
            MAC16(b0, + W5, col[8*5]);
            MAC16(b1, - W1, col[8*5]);
            MAC16(b2, + W7, col[8*5]);
            MAC16(b3, + W3, col[8*5]);
        }

        if(col[8*6]){
            a0 += + W6*col[8*6];
            a1 += - W2*col[8*6];
            a2 += + W2*col[8*6];
            a3 += - W6*col[8*6];
        }

        if (col[8*7]) {
            MAC16(b0, + W7, col[8*7]);
            MAC16(b1, - W5, col[8*7]);
            MAC16(b2, + W3, col[8*7]);
            MAC16(b3, - W1, col[8*7]);
        }

        dest[0] = cm[dest[0] + ((a0 + b0) >> COL_SHIFT)];
        dest += line_size;
        dest[0] = cm[dest[0] + ((a1 + b1) >> COL_SHIFT)];
        dest += line_size;
        dest[0] = cm[dest[0] + ((a2 + b2) >> COL_SHIFT)];
        dest += line_size;
        dest[0] = cm[dest[0] + ((a3 + b3) >> COL_SHIFT)];
        dest += line_size;
        dest[0] = cm[dest[0] + ((a3 - b3) >> COL_SHIFT)];
        dest += line_size;
        dest[0] = cm[dest[0] + ((a2 - b2) >> COL_SHIFT)];
        dest += line_size;
        dest[0] = cm[dest[0] + ((a1 - b1) >> COL_SHIFT)];
        dest += line_size;
        dest[0] = cm[dest[0] + ((a0 - b0) >> COL_SHIFT)];
}

/* 8x4 & 4x8 WMV2 IDCT */
#undef CN_SHIFT
#undef C_SHIFT
#undef C_FIX
#undef C1
#undef C2
#define CN_SHIFT 12
#define C_FIX(x) ((int)((x) * 1.414213562 * (1 << CN_SHIFT) + 0.5))
#define C1 C_FIX(0.6532814824)
#define C2 C_FIX(0.2705980501)
#define C3 C_FIX(0.5)
#define C_SHIFT (4+1+12)
static inline void idct4col_add(uint8_t *dest, int line_size, const DCTELEM *col)
{
    int c0, c1, c2, c3, a0, a1, a2, a3;