Deblock::deblockCU()

/* Deblocking filter process in CU-based (the same function as conventional's)
 * param Edge the direction of the edge in block boundary (horizonta/vertical), which is added newly 
	基于CU进行环路滤波：

	过程：
		1.递归找到每个CU，基于CU进行进行环路滤波
		2.确定滤波边界，设置边界强度
			1.默认给CU内部的PU边界设置block strength = 1
			2.默认给CU内部的TU边界递归设置block strength = 2
			3.默认给CU边界但非帧边界设置block strength = 2，帧边界block strength = 0
			4.对于非0的8x8block，获取其boundary strength，并将其赋值给block strength
		3.进行边界滤波
 */
void Deblock::deblockCU(const CUData* cu, const CUGeom& cuGeom, const int32_t dir, uint8_t blockStrength[])
{
    uint32_t absPartIdx = cuGeom.absPartIdx;
    uint32_t depth = cuGeom.depth;
    if (cu->m_predMode[absPartIdx] == MODE_NONE)
        return;

	// 若当前cuGeom.depth深度没有达到之前分析的最优深度m_cuDepth[absPartIdx]，则递归
    if (cu->m_cuDepth[absPartIdx] > depth)
    {
		// 拆分当前CU
        for (uint32_t subPartIdx = 0; subPartIdx < 4; subPartIdx++)
        {
			// 得到subCU的几何形状
            const CUGeom& childGeom = *(&cuGeom + cuGeom.childOffset + subPartIdx);
			// 若当前subCU呈现出来，则递归deblock
            if (childGeom.flags & CUGeom::PRESENT)
                deblockCU(cu, childGeom, dir, blockStrength);
        }
        return;
    }

	/*	确定滤波边界	*/
	// CU的4x4block个数
    uint32_t numUnits = 1 << (cuGeom.log2CUSize - LOG2_UNIT_SIZE);
	// PU边界给1
    setEdgefilterPU(cu, absPartIdx, dir, blockStrength, numUnits);
	// 递归对TU边界给2
    setEdgefilterTU(cu, absPartIdx, 0, dir, blockStrength);
	// CU边界给2，图像边界给0
    setEdgefilterMultiple(absPartIdx, dir, 0, bsCuEdge(cu, absPartIdx, dir), blockStrength, numUnits);

	/* 获取边界强度	*/
	// CU的4x4block个数
	uint32_t numParts = cuGeom.numPartitions;
	// 遍历当前CU的每个4x4block
    for (uint32_t partIdx = absPartIdx; partIdx < absPartIdx + numParts; partIdx++)
    {
		// 因为这里遍历单位4x4block，而滤波边界单位为8x8block，
		// 所以bsCheck过滤掉非8x8block边界
        uint32_t bsCheck = !(partIdx & (1 << dir));

		// 若是8x8边界，且blockStrength非0，则获取获取边界强度
        if (bsCheck && blockStrength[partIdx])
            blockStrength[partIdx] = getBoundaryStrength(cu, dir, partIdx, blockStrength);
    }

	/* 执行环路滤波 */
	// 最小环路滤波执行单位DEBLOCK_SMALLEST_BLOCK = 8x8中，有partIdxIncr块4x4block，
	// 遍历时计数器增长单位为partIdxIncr
    const uint32_t partIdxIncr = DEBLOCK_SMALLEST_BLOCK >> LOG2_UNIT_SIZE;
    uint32_t shiftFactor = (dir == EDGE_VER) ? cu->m_hChromaShift : cu->m_vChromaShift;
    uint32_t chromaMask = ((DEBLOCK_SMALLEST_BLOCK << shiftFactor) >> LOG2_UNIT_SIZE) - 1;
    uint32_t e0 = (dir == EDGE_VER ? g_zscanToPelX[absPartIdx] : g_zscanToPelY[absPartIdx]) >> LOG2_UNIT_SIZE;
    
	// 以8x8block为单位遍历进行边界滤波
    for (uint32_t e = 0; e < numUnits; e += partIdxIncr)
    {
		// 进行luma环路滤波
        edgeFilterLuma(cu, absPartIdx, depth, dir, e, blockStrength);
		// 进行chroma环路滤波
        if (!((e0 + e) & chromaMask) && cu->m_chromaFormat != X265_CSP_I400)
            edgeFilterChroma(cu, absPartIdx, depth, dir, e, blockStrength);
    }
}