in Extended/libwebp/src/dec/vp8_dec.c [513:602]
static int ParseResiduals(VP8Decoder* const dec,
VP8MB* const mb, VP8BitReader* const token_br) {
const VP8BandProbas* (* const bands)[16 + 1] = dec->proba_.bands_ptr_;
const VP8BandProbas* const * ac_proba;
VP8MBData* const block = dec->mb_data_ + dec->mb_x_;
const VP8QuantMatrix* const q = &dec->dqm_[block->segment_];
int16_t* dst = block->coeffs_;
VP8MB* const left_mb = dec->mb_info_ - 1;
uint8_t tnz, lnz;
uint32_t non_zero_y = 0;
uint32_t non_zero_uv = 0;
int x, y, ch;
uint32_t out_t_nz, out_l_nz;
int first;
memset(dst, 0, 384 * sizeof(*dst));
if (!block->is_i4x4_) { // parse DC
int16_t dc[16] = { 0 };
const int ctx = mb->nz_dc_ + left_mb->nz_dc_;
const int nz = GetCoeffs(token_br, bands[1], ctx, q->y2_mat_, 0, dc);
mb->nz_dc_ = left_mb->nz_dc_ = (nz > 0);
if (nz > 1) { // more than just the DC -> perform the full transform
VP8TransformWHT(dc, dst);
} else { // only DC is non-zero -> inlined simplified transform
int i;
const int dc0 = (dc[0] + 3) >> 3;
for (i = 0; i < 16 * 16; i += 16) dst[i] = dc0;
}
first = 1;
ac_proba = bands[0];
} else {
first = 0;
ac_proba = bands[3];
}
tnz = mb->nz_ & 0x0f;
lnz = left_mb->nz_ & 0x0f;
for (y = 0; y < 4; ++y) {
int l = lnz & 1;
uint32_t nz_coeffs = 0;
for (x = 0; x < 4; ++x) {
const int ctx = l + (tnz & 1);
const int nz = GetCoeffs(token_br, ac_proba, ctx, q->y1_mat_, first, dst);
l = (nz > first);
tnz = (tnz >> 1) | (l << 7);
nz_coeffs = NzCodeBits(nz_coeffs, nz, dst[0] != 0);
dst += 16;
}
tnz >>= 4;
lnz = (lnz >> 1) | (l << 7);
non_zero_y = (non_zero_y << 8) | nz_coeffs;
}
out_t_nz = tnz;
out_l_nz = lnz >> 4;
for (ch = 0; ch < 4; ch += 2) {
uint32_t nz_coeffs = 0;
tnz = mb->nz_ >> (4 + ch);
lnz = left_mb->nz_ >> (4 + ch);
for (y = 0; y < 2; ++y) {
int l = lnz & 1;
for (x = 0; x < 2; ++x) {
const int ctx = l + (tnz & 1);
const int nz = GetCoeffs(token_br, bands[2], ctx, q->uv_mat_, 0, dst);
l = (nz > 0);
tnz = (tnz >> 1) | (l << 3);
nz_coeffs = NzCodeBits(nz_coeffs, nz, dst[0] != 0);
dst += 16;
}
tnz >>= 2;
lnz = (lnz >> 1) | (l << 5);
}
// Note: we don't really need the per-4x4 details for U/V blocks.
non_zero_uv |= nz_coeffs << (4 * ch);
out_t_nz |= (tnz << 4) << ch;
out_l_nz |= (lnz & 0xf0) << ch;
}
mb->nz_ = out_t_nz;
left_mb->nz_ = out_l_nz;
block->non_zero_y_ = non_zero_y;
block->non_zero_uv_ = non_zero_uv;
// We look at the mode-code of each block and check if some blocks have less
// than three non-zero coeffs (code < 2). This is to avoid dithering flat and
// empty blocks.
block->dither_ = (non_zero_uv & 0xaaaa) ? 0 : q->dither_;
return !(non_zero_y | non_zero_uv); // will be used for further optimization
}