# example 1: see what perl produces for "UTF-16" output:

$ perl -e 'binmode STDOUT, ":encoding(UTF-16)"; print "abc\n"' | od -txC -a
0000000    fe  ff  00  61  00  62  00  63  00  0a                        
          fe  ff nul   a nul   b nul   c nul  nl                        
0000012

# perl is well-behaved: it attaches a BOM when writing UTF-16 to a file handle

# example 1 was done on a mac powerbook (big-endian)
# ... on an intel box the output would have been:
#    ff  fe  61  00  62  00  63  00  0a  00
#    ff  fe  a  nul  b  nul  c  nul  nl nul


# example 2: see how perl reads "UTF-16" input:

$ perl -e 'binmode STDOUT, ":encoding(UTF-16)"; print "abc\n"' | 
  perl -e 'binmode STDIN, ":encoding(UTF-16)"; $_ = <>; print' | od -txC -a
0000000    61  62  63  0a                                                
           a   b   c  nl                                                
0000004

# when reading UTF-16, perl removes the BOM from input and
# converts data internally to utf8 (in this example, the
# result is just ascii, because there were no wide characters)


# example 3: what perl does when byte order is specified in the encoding:

$ perl -e 'binmode STDOUT, ":encoding(UTF-16BE)"; print "abc\n"' | od -txC -a
0000000    00  61  00  62  00  63  00  0a                                
         nul   a nul   b nul   c nul  nl                                
0000010

# when byte order is specified, perl does not write a BOM


# example 4: what perl does when reading data with no BOM:

$ perl -e 'binmode STDOUT, ":encoding(UTF-16BE)"; print "abc\n"' |
  perl -e 'binmode STDIN, ":encoding(UTF-16)"; $_ = <>; print'
UTF-16:Unrecognised BOM 61 at -e line 1.

# if the reading script set "UTF-16BE" on STDIN, to match how
# it was written, it would work correctly.


##</code><code>##

#!/usr/bin/perl

use strict;

my $encoding = 'UTF-16';

my $Usage = "Usage: $0 [-BE|-LE] file.u16\n";
if ( @ARGV and $ARGV[0] =~ /^-([BL]E)$/ ) {
    $encoding .= $1;
    shift;
}
die $Usage unless ( @ARGV == 1 and -f $ARGV[0] );

my $filename = pop @ARGV;

# if user didn't specify byte order, let's check the input file

if ( $encoding eq 'UTF-16' ) {
    my $first_short;
    open( F, "<", $filename ) or die "$filename: $!";

    my $n = sysread( F, $first_short, 2 );
    die "sysread failed on $filename" unless ( $n == 2 );

    if ( $first_short == pack( 'S', 0xfeff ) or
         $first_short == pack( 'S', 0xfffe ) {
        # it's a BOM, and using ":encoding(UTF-16)" is fine
    }
    else {
        die "$filename has no BOM; please specify byte order\n$Usage";
    }
}
close F;

open( F, "<:$encoding", $filename );

# ... and go to work...