R help - Apr 2006 - Error in readChar(): invalid UTF-8 input

I have R code to read a binary header file, consisting of several 
readBin() and readChar() statements.  I am currently using version R-2.2.1 
(on x86_64, RH EL4) and have received the following error

        Error in readChar(fid, n = 1) : invalid UTF-8 input in readChar()

This is strange because (a) I was able to read in this file successfully 
in previous versions of R (circa 2005) and (b) it doesn't fail all the 
time; i.e., other readChar() statements work.

When I access the header file using a different piece of software, it 
gives the value "-1" for the field. 

What's going on?

cheers...

Brandon


	[[alternative HTML version deleted]]

On 4/27/2006 1:21 PM, Brandon.J.Whitcher at gsk.com
wrote:
> I have R code to read a binary header file, consisting of several 
> readBin() and readChar() statements.  I am currently using version R-2.2.1 
> (on x86_64, RH EL4) and have received the following error
> 
>         Error in readChar(fid, n = 1) : invalid UTF-8 input in readChar()
> 
> This is strange because (a) I was able to read in this file successfully 
> in previous versions of R (circa 2005) and (b) it doesn't fail all the 
> time; i.e., other readChar() statements work.
> 
> When I access the header file using a different piece of software, it 
> gives the value "-1" for the field. 
> 
> What's going on?
Probably the older versions of R were not trying to interpret the field 
as UTF-8:  that's locale-dependent, and a relatively recent addition. 
Not all byte sequences are legal UTF-8 encodings, and it sounds as 
though R is trying to tell you that yours is not.

To say more than this would require lots more information from you, for 
example a reproducible example.  Can you write the same bytes that are 
in that field into a file by themselves, and read that file?  Can you 
read the file using the current version of R (2.3.0)?  What about on 
other platforms?

Duncan Murdoch