That will only handle that one character. The problem is there are other characters that are modified as well. After my previous post the other day, I ended up going and making a much more verbose version of that script. Now the bad characters can be referred to by name. Plus I added a silly way of making it display the identity of characters to make it easier to find more that need to be fixed.

#!/usr/bin/perl -n

#use strict;
#use warnings;
use charnames ();
use encoding "utf8";

$|++;

my $chars = {
    'HYPHEN'                      => '-',    #  \x{2010}
    'MINUS SIGN'                  => '-',    #  \x{2212}
    'FIGURE DASH'                 => '-',    #  \x{2012}
    'RIGHT SINGLE QUOTATION MARK' => "'",    #  \x{2212}
    'BOX DRAWINGS LIGHT VERTICAL' => '|',    #  \x{2502}
};

# If the first character is an equal sign, skip it and
# display the identity of each remaining characters.
#
if (/^=/) {
    for my $index ( 1 .. length($_) - 1 ) {

        my $char = substr( $_, $index++, 1 );

        print $char . " "
                    . sprintf( "\\x{%04X}", ord($char) )
                    . "\" = '"
                    . charnames::viacode( ord($char) ) 
                    . "'\n" ;

    }

} else {

    for my $cname ( keys %$chars ) {

        my $char = chr( charnames::vianame($cname) );
        s/$char/$chars->{$cname}/g;

    }

    print;

}
[download]