+
Skip to content

Compiler warning in pixel.hpp #688

@jsenn

Description

@jsenn

Actual behavior

I get the following compiler warnings from pixel.hpp when using some gil functions:

3>  C:\Colony\VS2015\x64\boost_1_72_0\boost\gil\pixel.hpp(214,31): warning C4244: 'argument': conversion from 'const Channel' to 'BaseChannelValue', possible loss of data
3>          with
3>          [
3>              Channel=int
3>          ]
3>          and
3>          [
3>              BaseChannelValue=float
3>          ]
3>  C:\Colony\VS2015\x64\boost_1_72_0\boost\gil\pixel.hpp(158): note: see reference to function template instantiation 'void boost::gil::pixel<boost::gil::float32_t,boost::gil::gray_layout_t>::assign<Pixel>(const Channel &,std::false_type)' being compiled
3>          with
3>          [
3>              Pixel=int,
3>              Channel=int
3>          ]
3>  C:\Colony\VS2015\x64\boost_1_72_0\boost\gil\pixel.hpp(158): note: see reference to function template instantiation 'void boost::gil::pixel<boost::gil::float32_t,boost::gil::gray_layout_t>::assign<Pixel>(const Channel &,std::false_type)' being compiled
3>          with
3>          [
3>              Pixel=int,
3>              Channel=int
3>          ]
3>  C:\Colony\VS2015\x64\boost_1_72_0\boost\gil\image_processing\numeric.hpp(68): note: see reference to function template instantiation 'boost::gil::pixel<boost::gil::float32_t,boost::gil::gray_layout_t> &boost::gil::pixel<boost::gil::float32_t,boost::gil::gray_layout_t>::operator =<int>(const Pixel &)' being compiled
3>          with
3>          [
3>              Pixel=int
3>          ]
3>  C:\Colony\VS2015\x64\boost_1_72_0\boost\gil\image_processing\numeric.hpp(68): note: see reference to function template instantiation 'boost::gil::pixel<boost::gil::float32_t,boost::gil::gray_layout_t> &boost::gil::pixel<boost::gil::float32_t,boost::gil::gray_layout_t>::operator =<int>(const Pixel &)' being compiled
3>          with
3>          [
3>              Pixel=int
3>          ]

This is in the grayscale pixel assign function, where it's assigning the int channel value directly to the float grayscale value without an explicit cast. Since not every int has a representation as a float, this is a loss of data, hence the warning. I guess the fix would be to add an explicit static_cast<> in there like the following?

    template <typename Channel>
    void assign(Channel const& channel, std::false_type)
    {
        check_gray();
        gil::at_c<0>(*this) = static_cast<channel_t::base_channel_t>( channel );
    }

Expected behavior

No warning

C++ Minimal Working Example

#include <stdexcept>
#include <boost/gil.hpp>
#include <boost/gil/io/write_view.hpp>
#include <boost/gil/extension/io/png.hpp>

int main()
{
	int width = 640;
	int height = 480;
	unsigned char* pImageData = new unsigned char[width*height*4];
	boost::gil::rgba8c_view_t imageView = boost::gil::interleaved_view( width, height, ( const boost::gil::rgba8c_pixel_t* )pImageData, width * 4 );
	try
	{
		boost::gil::write_view( "test.png", imageView, boost::gil::png_tag{});
	}
	catch ( ... )
	{
		return false;
	}
}

Environment

Compiled in Visual Studio 2019 using MSVC with language standard set to latest (C++20).

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

      点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载