// This file is part of OpenCV project.
// It is subject to the license terms in the LICENSE file found in the top-level directory
// of this distribution and at http://opencv.org/license.html

#include "precomp.hpp"
#include "bufferpool.impl.hpp"

namespace cv {

void MatAllocator::map(UMatData*, int) const
{
}

void MatAllocator::unmap(UMatData* u) const
{
    if(u->urefcount == 0 && u->refcount == 0)
    {
        deallocate(u);
    }
}

void MatAllocator::download(UMatData* u, void* dstptr,
         int dims, const size_t sz[],
         const size_t srcofs[], const size_t srcstep[],
         const size_t dststep[]) const
{
    if(!u)
        return;
    int isz[CV_MAX_DIM];
    uchar* srcptr = u->data;
    for( int i = 0; i < dims; i++ )
    {
        CV_Assert( sz[i] <= (size_t)INT_MAX );
        if( sz[i] == 0 )
            return;
        if( srcofs )
            srcptr += srcofs[i]*(i <= dims-2 ? srcstep[i] : 1);
        isz[i] = (int)sz[i];
    }

    Mat src(dims, isz, CV_8U, srcptr, srcstep);
    Mat dst(dims, isz, CV_8U, dstptr, dststep);

    const Mat* arrays[] = { &src, &dst };
    uchar* ptrs[2];
    NAryMatIterator it(arrays, ptrs, 2);
    size_t planesz = it.size;

    for( size_t j = 0; j < it.nplanes; j++, ++it )
        memcpy(ptrs[1], ptrs[0], planesz);
}


void MatAllocator::upload(UMatData* u, const void* srcptr, int dims, const size_t sz[],
                    const size_t dstofs[], const size_t dststep[],
                    const size_t srcstep[]) const
{
    if(!u)
        return;
    int isz[CV_MAX_DIM];
    uchar* dstptr = u->data;
    for( int i = 0; i < dims; i++ )
    {
        CV_Assert( sz[i] <= (size_t)INT_MAX );
        if( sz[i] == 0 )
            return;
        if( dstofs )
            dstptr += dstofs[i]*(i <= dims-2 ? dststep[i] : 1);
        isz[i] = (int)sz[i];
    }

    Mat src(dims, isz, CV_8U, (void*)srcptr, srcstep);
    Mat dst(dims, isz, CV_8U, dstptr, dststep);

    const Mat* arrays[] = { &src, &dst };
    uchar* ptrs[2];
    NAryMatIterator it(arrays, ptrs, 2);
    size_t planesz = it.size;

    for( size_t j = 0; j < it.nplanes; j++, ++it )
        memcpy(ptrs[1], ptrs[0], planesz);
}

void MatAllocator::copy(UMatData* usrc, UMatData* udst, int dims, const size_t sz[],
                  const size_t srcofs[], const size_t srcstep[],
                  const size_t dstofs[], const size_t dststep[], bool /*sync*/) const
{
    CV_INSTRUMENT_REGION()

    if(!usrc || !udst)
        return;
    int isz[CV_MAX_DIM];
    uchar* srcptr = usrc->data;
    uchar* dstptr = udst->data;
    for( int i = 0; i < dims; i++ )
    {
        CV_Assert( sz[i] <= (size_t)INT_MAX );
        if( sz[i] == 0 )
            return;
        if( srcofs )
            srcptr += srcofs[i]*(i <= dims-2 ? srcstep[i] : 1);
        if( dstofs )
            dstptr += dstofs[i]*(i <= dims-2 ? dststep[i] : 1);
        isz[i] = (int)sz[i];
    }

    Mat src(dims, isz, CV_8U, srcptr, srcstep);
    Mat dst(dims, isz, CV_8U, dstptr, dststep);

    const Mat* arrays[] = { &src, &dst };
    uchar* ptrs[2];
    NAryMatIterator it(arrays, ptrs, 2);
    size_t planesz = it.size;

    for( size_t j = 0; j < it.nplanes; j++, ++it )
        memcpy(ptrs[1], ptrs[0], planesz);
}

BufferPoolController* MatAllocator::getBufferPoolController(const char* id) const
{
    (void)id;
    static DummyBufferPoolController dummy;
    return &dummy;
}

class StdMatAllocator CV_FINAL : public MatAllocator
{
public:
    UMatData* allocate(int dims, const int* sizes, int type,
                       void* data0, size_t* step, int /*flags*/, UMatUsageFlags /*usageFlags*/) const CV_OVERRIDE
    {
        size_t total = CV_ELEM_SIZE(type);
        for( int i = dims-1; i >= 0; i-- )
        {
            if( step )
            {
                if( data0 && step[i] != CV_AUTOSTEP )
                {
                    CV_Assert(total <= step[i]);
                    total = step[i];
                }
                else
                    step[i] = total;
            }
            total *= sizes[i];
        }
        uchar* data = data0 ? (uchar*)data0 : (uchar*)fastMalloc(total);
        UMatData* u = new UMatData(this);
        u->data = u->origdata = data;
        u->size = total;
        if(data0)
            u->flags |= UMatData::USER_ALLOCATED;

        return u;
    }

    bool allocate(UMatData* u, int /*accessFlags*/, UMatUsageFlags /*usageFlags*/) const CV_OVERRIDE
    {
        if(!u) return false;
        return true;
    }

    void deallocate(UMatData* u) const CV_OVERRIDE
    {
        if(!u)
            return;

        CV_Assert(u->urefcount == 0);
        CV_Assert(u->refcount == 0);
        if( !(u->flags & UMatData::USER_ALLOCATED) )
        {
            fastFree(u->origdata);
            u->origdata = 0;
        }
        delete u;
    }
};

namespace
{
    MatAllocator* volatile g_matAllocator = NULL;
}

MatAllocator* Mat::getDefaultAllocator()
{
    if (g_matAllocator == NULL)
    {
        cv::AutoLock lock(cv::getInitializationMutex());
        if (g_matAllocator == NULL)
        {
            g_matAllocator = getStdAllocator();
        }
    }
    return g_matAllocator;
}
void Mat::setDefaultAllocator(MatAllocator* allocator)
{
    g_matAllocator = allocator;
}
MatAllocator* Mat::getStdAllocator()
{
    CV_SINGLETON_LAZY_INIT(MatAllocator, new StdMatAllocator())
}

//==================================================================================================

void setSize( Mat& m, int _dims, const int* _sz, const size_t* _steps, bool autoSteps)
{
    CV_Assert( 0 <= _dims && _dims <= CV_MAX_DIM );
    if( m.dims != _dims )
    {
        if( m.step.p != m.step.buf )
        {
            fastFree(m.step.p);
            m.step.p = m.step.buf;
            m.size.p = &m.rows;
        }
        if( _dims > 2 )
        {
            m.step.p = (size_t*)fastMalloc(_dims*sizeof(m.step.p[0]) + (_dims+1)*sizeof(m.size.p[0]));
            m.size.p = (int*)(m.step.p + _dims) + 1;
            m.size.p[-1] = _dims;
            m.rows = m.cols = -1;
        }
    }

    m.dims = _dims;
    if( !_sz )
        return;

    size_t esz = CV_ELEM_SIZE(m.flags), esz1 = CV_ELEM_SIZE1(m.flags), total = esz;
    for( int i = _dims-1; i >= 0; i-- )
    {
        int s = _sz[i];
        CV_Assert( s >= 0 );
        m.size.p[i] = s;

        if( _steps )
        {
            if (_steps[i] % esz1 != 0)
            {
                CV_Error(Error::BadStep, "Step must be a multiple of esz1");
            }

            m.step.p[i] = i < _dims-1 ? _steps[i] : esz;
        }
        else if( autoSteps )
        {
            m.step.p[i] = total;
            int64 total1 = (int64)total*s;
            if( (uint64)total1 != (size_t)total1 )
                CV_Error( CV_StsOutOfRange, "The total matrix size does not fit to \"size_t\" type" );
            total = (size_t)total1;
        }
    }

    if( _dims == 1 )
    {
        m.dims = 2;
        m.cols = 1;
        m.step[1] = esz;
    }
}

int updateContinuityFlag(int flags, int dims, const int* size, const size_t* step)
{
    int i, j;
    for( i = 0; i < dims; i++ )
    {
        if( size[i] > 1 )
            break;
    }

    uint64 t = (uint64)size[std::min(i, dims-1)]*CV_MAT_CN(flags);
    for( j = dims-1; j > i; j-- )
    {
        t *= size[j];
        if( step[j]*size[j] < step[j-1] )
            break;
    }

    if( j <= i && t == (uint64)(int)t )
        return flags | Mat::CONTINUOUS_FLAG;
    return flags & ~Mat::CONTINUOUS_FLAG;
}

void Mat::updateContinuityFlag()
{
    flags = cv::updateContinuityFlag(flags, dims, size.p, step.p);
}

void finalizeHdr(Mat& m)
{
    m.updateContinuityFlag();
    int d = m.dims;
    if( d > 2 )
        m.rows = m.cols = -1;
    if(m.u)
        m.datastart = m.data = m.u->data;
    if( m.data )
    {
        m.datalimit = m.datastart + m.size[0]*m.step[0];
        if( m.size[0] > 0 )
        {
            m.dataend = m.ptr() + m.size[d-1]*m.step[d-1];
            for( int i = 0; i < d-1; i++ )
                m.dataend += (m.size[i] - 1)*m.step[i];
        }
        else
            m.dataend = m.datalimit;
    }
    else
        m.dataend = m.datalimit = 0;
}

//==================================================================================================

void Mat::create(int d, const int* _sizes, int _type)
{
    int i;
    CV_Assert(0 <= d && d <= CV_MAX_DIM && _sizes);
    _type = CV_MAT_TYPE(_type);

    if( data && (d == dims || (d == 1 && dims <= 2)) && _type == type() )
    {
        if( d == 2 && rows == _sizes[0] && cols == _sizes[1] )
            return;
        for( i = 0; i < d; i++ )
            if( size[i] != _sizes[i] )
                break;
        if( i == d && (d > 1 || size[1] == 1))
            return;
    }

    int _sizes_backup[CV_MAX_DIM]; // #5991
    if (_sizes == (this->size.p))
    {
        for(i = 0; i < d; i++ )
            _sizes_backup[i] = _sizes[i];
        _sizes = _sizes_backup;
    }

    release();
    if( d == 0 )
        return;
    flags = (_type & CV_MAT_TYPE_MASK) | MAGIC_VAL;
    setSize(*this, d, _sizes, 0, true);

    if( total() > 0 )
    {
        MatAllocator *a = allocator, *a0 = getDefaultAllocator();
#ifdef HAVE_TGPU
        if( !a || a == tegra::getAllocator() )
            a = tegra::getAllocator(d, _sizes, _type);
#endif
        if(!a)
            a = a0;
        CV_TRY
        {
            u = a->allocate(dims, size, _type, 0, step.p, 0, USAGE_DEFAULT);
            CV_Assert(u != 0);
        }
        CV_CATCH_ALL
        {
            if(a != a0)
                u = a0->allocate(dims, size, _type, 0, step.p, 0, USAGE_DEFAULT);
            CV_Assert(u != 0);
        }
        CV_Assert( step[dims-1] == (size_t)CV_ELEM_SIZE(flags) );
    }

    addref();
    finalizeHdr(*this);
}

void Mat::create(const std::vector<int>& _sizes, int _type)
{
    create((int)_sizes.size(), _sizes.data(), _type);
}

void Mat::copySize(const Mat& m)
{
    setSize(*this, m.dims, 0, 0);
    for( int i = 0; i < dims; i++ )
    {
        size[i] = m.size[i];
        step[i] = m.step[i];
    }
}

void Mat::deallocate()
{
    if(u)
    {
        UMatData* u_ = u;
        u = NULL;
        (u_->currAllocator ? u_->currAllocator : allocator ? allocator : getDefaultAllocator())->unmap(u_);
    }
}

Mat::Mat(const Mat& m, const Range& _rowRange, const Range& _colRange)
    : flags(MAGIC_VAL), dims(0), rows(0), cols(0), data(0), datastart(0), dataend(0),
      datalimit(0), allocator(0), u(0), size(&rows)
{
    CV_Assert( m.dims >= 2 );
    if( m.dims > 2 )
    {
        AutoBuffer<Range> rs(m.dims);
        rs[0] = _rowRange;
        rs[1] = _colRange;
        for( int i = 2; i < m.dims; i++ )
            rs[i] = Range::all();
        *this = m(rs.data());
        return;
    }

    *this = m;
    CV_TRY
    {
        if( _rowRange != Range::all() && _rowRange != Range(0,rows) )
        {
            CV_Assert( 0 <= _rowRange.start && _rowRange.start <= _rowRange.end
                       && _rowRange.end <= m.rows );
            rows = _rowRange.size();
            data += step*_rowRange.start;
            flags |= SUBMATRIX_FLAG;
        }

        if( _colRange != Range::all() && _colRange != Range(0,cols) )
        {
            CV_Assert( 0 <= _colRange.start && _colRange.start <= _colRange.end
                       && _colRange.end <= m.cols );
            cols = _colRange.size();
            data += _colRange.start*elemSize();
            flags |= SUBMATRIX_FLAG;
        }
    }
    CV_CATCH_ALL
    {
        release();
        CV_RETHROW();
    }

    updateContinuityFlag();

    if( rows <= 0 || cols <= 0 )
    {
        release();
        rows = cols = 0;
    }
}


Mat::Mat(const Mat& m, const Rect& roi)
    : flags(m.flags), dims(2), rows(roi.height), cols(roi.width),
    data(m.data + roi.y*m.step[0]),
    datastart(m.datastart), dataend(m.dataend), datalimit(m.datalimit),
    allocator(m.allocator), u(m.u), size(&rows)
{
    CV_Assert( m.dims <= 2 );

    size_t esz = CV_ELEM_SIZE(flags);
    data += roi.x*esz;
    CV_Assert( 0 <= roi.x && 0 <= roi.width && roi.x + roi.width <= m.cols &&
              0 <= roi.y && 0 <= roi.height && roi.y + roi.height <= m.rows );
    if( u )
        CV_XADD(&u->refcount, 1);
    if( roi.width < m.cols || roi.height < m.rows )
        flags |= SUBMATRIX_FLAG;

    step[0] = m.step[0]; step[1] = esz;
    updateContinuityFlag();

    if( rows <= 0 || cols <= 0 )
    {
        release();
        rows = cols = 0;
    }
}


Mat::Mat(int _dims, const int* _sizes, int _type, void* _data, const size_t* _steps)
    : flags(MAGIC_VAL), dims(0), rows(0), cols(0), data(0), datastart(0), dataend(0),
      datalimit(0), allocator(0), u(0), size(&rows)
{
    flags |= CV_MAT_TYPE(_type);
    datastart = data = (uchar*)_data;
    setSize(*this, _dims, _sizes, _steps, true);
    finalizeHdr(*this);
}


Mat::Mat(const std::vector<int>& _sizes, int _type, void* _data, const size_t* _steps)
    : flags(MAGIC_VAL), dims(0), rows(0), cols(0), data(0), datastart(0), dataend(0),
      datalimit(0), allocator(0), u(0), size(&rows)
{
    flags |= CV_MAT_TYPE(_type);
    datastart = data = (uchar*)_data;
    setSize(*this, (int)_sizes.size(), _sizes.data(), _steps, true);
    finalizeHdr(*this);
}


Mat::Mat(const Mat& m, const Range* ranges)
    : flags(MAGIC_VAL), dims(0), rows(0), cols(0), data(0), datastart(0), dataend(0),
      datalimit(0), allocator(0), u(0), size(&rows)
{
    int d = m.dims;

    CV_Assert(ranges);
    for( int i = 0; i < d; i++ )
    {
        Range r = ranges[i];
        CV_Assert( r == Range::all() || (0 <= r.start && r.start < r.end && r.end <= m.size[i]) );
    }
    *this = m;
    for( int i = 0; i < d; i++ )
    {
        Range r = ranges[i];
        if( r != Range::all() && r != Range(0, size.p[i]))
        {
            size.p[i] = r.end - r.start;
            data += r.start*step.p[i];
            flags |= SUBMATRIX_FLAG;
        }
    }
    updateContinuityFlag();
}

Mat::Mat(const Mat& m, const std::vector<Range>& ranges)
    : flags(MAGIC_VAL), dims(0), rows(0), cols(0), data(0), datastart(0), dataend(0),
    datalimit(0), allocator(0), u(0), size(&rows)
{
    int d = m.dims;

    CV_Assert((int)ranges.size() == d);
    for (int i = 0; i < d; i++)
    {
        Range r = ranges[i];
        CV_Assert(r == Range::all() || (0 <= r.start && r.start < r.end && r.end <= m.size[i]));
    }
    *this = m;
    for (int i = 0; i < d; i++)
    {
        Range r = ranges[i];
        if (r != Range::all() && r != Range(0, size.p[i]))
        {
            size.p[i] = r.end - r.start;
            data += r.start*step.p[i];
            flags |= SUBMATRIX_FLAG;
        }
    }
    updateContinuityFlag();
}


Mat Mat::diag(int d) const
{
    CV_Assert( dims <= 2 );
    Mat m = *this;
    size_t esz = elemSize();
    int len;

    if( d >= 0 )
    {
        len = std::min(cols - d, rows);
        m.data += esz*d;
    }
    else
    {
        len = std::min(rows + d, cols);
        m.data -= step[0]*d;
    }
    CV_DbgAssert( len > 0 );

    m.size[0] = m.rows = len;
    m.size[1] = m.cols = 1;
    m.step[0] += (len > 1 ? esz : 0);

    m.updateContinuityFlag();

    if( size() != Size(1,1) )
        m.flags |= SUBMATRIX_FLAG;

    return m;
}


void Mat::pop_back(size_t nelems)
{
    CV_Assert( nelems <= (size_t)size.p[0] );

    if( isSubmatrix() )
        *this = rowRange(0, size.p[0] - (int)nelems);
    else
    {
        size.p[0] -= (int)nelems;
        dataend -= nelems*step.p[0];
    }
}


void Mat::push_back_(const void* elem)
{
    size_t r = size.p[0];
    if( isSubmatrix() || dataend + step.p[0] > datalimit )
        reserve( std::max(r + 1, (r*3+1)/2) );

    size_t esz = elemSize();
    memcpy(data + r*step.p[0], elem, esz);
    size.p[0] = int(r + 1);
    dataend += step.p[0];
    uint64 tsz = size.p[0];
    for( int i = 1; i < dims; i++ )
        tsz *= size.p[i];
    if( esz < step.p[0] || tsz != (uint64)(int)tsz )
        flags &= ~CONTINUOUS_FLAG;
}


void Mat::reserve(size_t nelems)
{
    const size_t MIN_SIZE = 64;

    CV_Assert( (int)nelems >= 0 );
    if( !isSubmatrix() && data + step.p[0]*nelems <= datalimit )
        return;

    int r = size.p[0];

    if( (size_t)r >= nelems )
        return;

    size.p[0] = std::max((int)nelems, 1);
    size_t newsize = total()*elemSize();

    if( newsize < MIN_SIZE )
        size.p[0] = (int)((MIN_SIZE + newsize - 1)*nelems/newsize);

    Mat m(dims, size.p, type());
    size.p[0] = r;
    if( r > 0 )
    {
        Mat mpart = m.rowRange(0, r);
        copyTo(mpart);
    }

    *this = m;
    size.p[0] = r;
    dataend = data + step.p[0]*r;
}


void Mat::reserveBuffer(size_t nbytes)
{
    size_t esz = 1;
    int mtype = CV_8UC1;
    if (!empty())
    {
        if (!isSubmatrix() && data + nbytes <= dataend)//Should it be datalimit?
            return;
        esz = elemSize();
        mtype = type();
    }

    size_t nelems = (nbytes - 1) / esz + 1;

#if SIZE_MAX > UINT_MAX
    CV_Assert(nelems <= size_t(INT_MAX)*size_t(INT_MAX));
    int newrows = nelems > size_t(INT_MAX) ? nelems > 0x400*size_t(INT_MAX) ? nelems > 0x100000 * size_t(INT_MAX) ? nelems > 0x40000000 * size_t(INT_MAX) ?
                  size_t(INT_MAX) : 0x40000000 : 0x100000 : 0x400 : 1;
#else
    int newrows = nelems > size_t(INT_MAX) ? 2 : 1;
#endif
    int newcols = (int)((nelems - 1) / newrows + 1);

    create(newrows, newcols, mtype);
}


void Mat::resize(size_t nelems)
{
    int saveRows = size.p[0];
    if( saveRows == (int)nelems )
        return;
    CV_Assert( (int)nelems >= 0 );

    if( isSubmatrix() || data + step.p[0]*nelems > datalimit )
        reserve(nelems);

    size.p[0] = (int)nelems;
    dataend += (size.p[0] - saveRows)*step.p[0];

    //updateContinuityFlag(*this);
}


void Mat::resize(size_t nelems, const Scalar& s)
{
    int saveRows = size.p[0];
    resize(nelems);

    if( size.p[0] > saveRows )
    {
        Mat part = rowRange(saveRows, size.p[0]);
        part = s;
    }
}

void Mat::push_back(const Mat& elems)
{
    size_t r = size.p[0];
    size_t delta = elems.size.p[0];
    if( delta == 0 )
        return;
    if( this == &elems )
    {
        Mat tmp = elems;
        push_back(tmp);
        return;
    }
    if( !data )
    {
        *this = elems.clone();
        return;
    }

    size.p[0] = elems.size.p[0];
    bool eq = size == elems.size;
    size.p[0] = int(r);
    if( !eq )
        CV_Error(CV_StsUnmatchedSizes, "Pushed vector length is not equal to matrix row length");
    if( type() != elems.type() )
        CV_Error(CV_StsUnmatchedFormats, "Pushed vector type is not the same as matrix type");

    if( isSubmatrix() || dataend + step.p[0]*delta > datalimit )
        reserve( std::max(r + delta, (r*3+1)/2) );

    size.p[0] += int(delta);
    dataend += step.p[0]*delta;

    //updateContinuityFlag(*this);

    if( isContinuous() && elems.isContinuous() )
        memcpy(data + r*step.p[0], elems.data, elems.total()*elems.elemSize());
    else
    {
        Mat part = rowRange(int(r), int(r + delta));
        elems.copyTo(part);
    }
}


void Mat::locateROI( Size& wholeSize, Point& ofs ) const
{
    CV_Assert( dims <= 2 && step[0] > 0 );
    size_t esz = elemSize(), minstep;
    ptrdiff_t delta1 = data - datastart, delta2 = dataend - datastart;

    if( delta1 == 0 )
        ofs.x = ofs.y = 0;
    else
    {
        ofs.y = (int)(delta1/step[0]);
        ofs.x = (int)((delta1 - step[0]*ofs.y)/esz);
        CV_DbgAssert( data == datastart + ofs.y*step[0] + ofs.x*esz );
    }
    minstep = (ofs.x + cols)*esz;
    wholeSize.height = (int)((delta2 - minstep)/step[0] + 1);
    wholeSize.height = std::max(wholeSize.height, ofs.y + rows);
    wholeSize.width = (int)((delta2 - step*(wholeSize.height-1))/esz);
    wholeSize.width = std::max(wholeSize.width, ofs.x + cols);
}

Mat& Mat::adjustROI( int dtop, int dbottom, int dleft, int dright )
{
    CV_Assert( dims <= 2 && step[0] > 0 );
    Size wholeSize; Point ofs;
    size_t esz = elemSize();
    locateROI( wholeSize, ofs );
    int row1 = std::min(std::max(ofs.y - dtop, 0), wholeSize.height), row2 = std::max(0, std::min(ofs.y + rows + dbottom, wholeSize.height));
    int col1 = std::min(std::max(ofs.x - dleft, 0), wholeSize.width), col2 = std::max(0, std::min(ofs.x + cols + dright, wholeSize.width));
    if(row1 > row2)
        std::swap(row1, row2);
    if(col1 > col2)
        std::swap(col1, col2);

    data += (row1 - ofs.y)*step + (col1 - ofs.x)*esz;
    rows = row2 - row1; cols = col2 - col1;
    size.p[0] = rows; size.p[1] = cols;
    updateContinuityFlag();
    return *this;
}

Mat Mat::reshape(int new_cn, int new_rows) const
{
    int cn = channels();
    Mat hdr = *this;

    if( dims > 2 )
    {
        if( new_rows == 0 && new_cn != 0 && size[dims-1]*cn % new_cn == 0 )
        {
            hdr.flags = (hdr.flags & ~CV_MAT_CN_MASK) | ((new_cn-1) << CV_CN_SHIFT);
            hdr.step[dims-1] = CV_ELEM_SIZE(hdr.flags);
            hdr.size[dims-1] = hdr.size[dims-1]*cn / new_cn;
            return hdr;
        }
        if( new_rows > 0 )
        {
            int sz[] = { new_rows, (int)(total()/new_rows) };
            return reshape(new_cn, 2, sz);
        }
    }

    CV_Assert( dims <= 2 );

    if( new_cn == 0 )
        new_cn = cn;

    int total_width = cols * cn;

    if( (new_cn > total_width || total_width % new_cn != 0) && new_rows == 0 )
        new_rows = rows * total_width / new_cn;

    if( new_rows != 0 && new_rows != rows )
    {
        int total_size = total_width * rows;
        if( !isContinuous() )
            CV_Error( CV_BadStep,
            "The matrix is not continuous, thus its number of rows can not be changed" );

        if( (unsigned)new_rows > (unsigned)total_size )
            CV_Error( CV_StsOutOfRange, "Bad new number of rows" );

        total_width = total_size / new_rows;

        if( total_width * new_rows != total_size )
            CV_Error( CV_StsBadArg, "The total number of matrix elements "
                                    "is not divisible by the new number of rows" );

        hdr.rows = new_rows;
        hdr.step[0] = total_width * elemSize1();
    }

    int new_width = total_width / new_cn;

    if( new_width * new_cn != total_width )
        CV_Error( CV_BadNumChannels,
        "The total width is not divisible by the new number of channels" );

    hdr.cols = new_width;
    hdr.flags = (hdr.flags & ~CV_MAT_CN_MASK) | ((new_cn-1) << CV_CN_SHIFT);
    hdr.step[1] = CV_ELEM_SIZE(hdr.flags);
    return hdr;
}

Mat Mat::reshape(int _cn, int _newndims, const int* _newsz) const
{
    if(_newndims == dims)
    {
        if(_newsz == 0)
            return reshape(_cn);
        if(_newndims == 2)
            return reshape(_cn, _newsz[0]);
    }

    if (isContinuous())
    {
        CV_Assert(_cn >= 0 && _newndims > 0 && _newndims <= CV_MAX_DIM && _newsz);

        if (_cn == 0)
            _cn = this->channels();
        else
            CV_Assert(_cn <= CV_CN_MAX);

        size_t total_elem1_ref = this->total() * this->channels();
        size_t total_elem1 = _cn;

        AutoBuffer<int, 4> newsz_buf( (size_t)_newndims );

        for (int i = 0; i < _newndims; i++)
        {
            CV_Assert(_newsz[i] >= 0);

            if (_newsz[i] > 0)
                newsz_buf[i] = _newsz[i];
            else if (i < dims)
                newsz_buf[i] = this->size[i];
            else
                CV_Error(CV_StsOutOfRange, "Copy dimension (which has zero size) is not present in source matrix");

            total_elem1 *= (size_t)newsz_buf[i];
        }

        if (total_elem1 != total_elem1_ref)
            CV_Error(CV_StsUnmatchedSizes, "Requested and source matrices have different count of elements");

        Mat hdr = *this;
        hdr.flags = (hdr.flags & ~CV_MAT_CN_MASK) | ((_cn-1) << CV_CN_SHIFT);
        setSize(hdr, _newndims, newsz_buf.data(), NULL, true);

        return hdr;
    }

    CV_Error(CV_StsNotImplemented, "Reshaping of n-dimensional non-continuous matrices is not supported yet");
    // TBD
}

Mat Mat::reshape(int _cn, const std::vector<int>& _newshape) const
{
    if(_newshape.empty())
    {
        CV_Assert(empty());
        return *this;
    }

    return reshape(_cn, (int)_newshape.size(), &_newshape[0]);
}

Mat Mat::diag(const Mat& d)
{
    CV_Assert( d.cols == 1 || d.rows == 1 );
    int len = d.rows + d.cols - 1;
    Mat m(len, len, d.type(), Scalar(0));
    Mat md = m.diag();
    if( d.cols == 1 )
        d.copyTo(md);
    else
        transpose(d, md);
    return m;
}

int Mat::checkVector(int _elemChannels, int _depth, bool _requireContinuous) const
{
    return data && (depth() == _depth || _depth <= 0) &&
        (isContinuous() || !_requireContinuous) &&
        ((dims == 2 && (((rows == 1 || cols == 1) && channels() == _elemChannels) ||
                        (cols == _elemChannels && channels() == 1))) ||
        (dims == 3 && channels() == 1 && size.p[2] == _elemChannels && (size.p[0] == 1 || size.p[1] == 1) &&
         (isContinuous() || step.p[1] == step.p[2]*size.p[2])))
    ? (int)(total()*channels()/_elemChannels) : -1;
}

} // cv::