core: rework code locality

- to reduce binaries size of FFmpeg Windows wrapper
- MinGW linker doesn't support -ffunction-sections (used for FFmpeg Windows wrapper)
- move code to improve locality with its used dependencies
- move UMat::dot() to matmul.dispatch.cpp (Mat::dot() is already there)
- move UMat::inv() to lapack.cpp
- move UMat::mul() to arithm.cpp
- move UMat:eye() to matrix_operations.cpp (near setIdentity() implementation)
- move normalize(): convert_scale.cpp => norm.cpp
- move convertAndUnrollScalar(): arithm.cpp => copy.cpp
- move scalarToRawData(): array.cpp => copy.cpp
- move transpose(): matrix_operations.cpp => matrix_transform.cpp
- move flip(), rotate(): copy.cpp => matrix_transform.cpp (rotate90 uses flip and transpose)
- add 'OPENCV_CORE_EXCLUDE_C_API' CMake variable to exclude compilation of C-API functions from the core module
- matrix_wrap.cpp: add compile-time checks for CUDA/OpenGL calls
- the steps above allow to reduce FFmpeg wrapper size for ~1.5Mb (initial size of OpenCV part is about 3Mb)

modules/core/src/matrix_c.cpp

@@ -6,6 +6,7 @@
 #include "opencv2/core/mat.hpp"
 #include "opencv2/core/types_c.h"
 
+#ifndef OPENCV_EXCLUDE_C_API
 // glue
 
 CvMatND cvMatND(const cv::Mat& m)
@@ -360,7 +361,6 @@ cvSort( const CvArr* _src, CvArr* _dst, CvArr* _idx, int flags )
     }
 }
 
-
 CV_IMPL int
 cvKMeans2( const CvArr* _samples, int cluster_count, CvArr* _labels,
            CvTermCriteria termcrit, int attempts, CvRNG*,
@@ -389,3 +389,5 @@ cvKMeans2( const CvArr* _samples, int cluster_count, CvArr* _labels,
         *_compactness = compactness;
     return 1;
 }
+
+#endif  // OPENCV_EXCLUDE_C_API