// Accepts a full path to an HTML file.
// Reads the file, detects the encoding
// and returns the text converted to Unicode.
QString HTMLEncodingResolver::ReadHTMLFile( const QString &fullfilepath )
{
QFile file( fullfilepath );
// Check if we can open the file
if ( !file.open( QFile::ReadOnly ) )
{
boost_throw( CannotOpenFile()
<< errinfo_file_fullpath( file.fileName().toStdString() )
<< errinfo_file_errorstring( file.errorString().toStdString() )
);
}
QByteArray data = file.readAll();
return Utility::ConvertLineEndings( GetCodecForHTML( data ).toUnicode( data ) );
}
// Accepts a full path to an HTML file.
// Reads the file, detects the encoding
// and returns the text converted to Unicode.
QString HTMLEncodingResolver::ReadHTMLFile(const QString &fullfilepath)
{
QFile file(fullfilepath);
// Check if we can open the file
if (!file.open(QFile::ReadOnly)) {
std::string msg = file.fileName().toStdString() + ": " + file.errorString().toStdString();
throw (CannotOpenFile(msg));
}
QByteArray data = file.readAll();
if (IsValidUtf8(data)) {
data.replace("\xC2\xA0", " ");
}
return Utility::ConvertLineEndings(GetCodecForHTML(data)->toUnicode(data));
}