#!/usr/bin/perl
#
# [ Miguel Thu Feb 17 15:23:32 CET 2005 (@colinux) ]
#
# Finds BOM signatures and strips them from files.
#
# More info regarding BOM at http://www.unicode.org/faq/utf_bom.html
#

use strict;
use warnings;

sub remove_bom($);

if (@ARGV < 2) {
    print "removebom.pl: removes UTF Byte Order Marks from files.\n\n";
    print " Usage: removebom.pl [path] [pattern]\n\n";
    print " You must specify both a target directory to be traversed and a file pattern.\n";
    exit 1;
}

my ($dir, $patt) = ($ARGV[0], $ARGV[1]);
my @list = `find $dir -iname "*$patt"`;
my $enc;

open LOG, ">>", "/tmp/removebom.log"
    or die "Unable to open log file /tmp/removebom.log\n";

chomp @list;

print LOG "\n\n\n-------------- removebom.pl $dir $patt --------------\n\n";

foreach my $file (@list) {
    print LOG remove_bom($file);
}

close LOG;


##############################################################################
# Removes BOMs
##############################################################################
sub remove_bom($)
{
    my $fname = shift;
    my $str;
    my $enc = "No";

    open (FH, "<", $fname)
        or return "Unable to open file $fname for reading.\n";

    {
        $/ = undef;    # only in this scope.
        $str = <FH>;   # read the entire input.
    }

    close FH;



    # Remove UTF-8 Byte Order Mark
    ($str =~ s/^\xEF\xBB\xBF//) && ($enc = "UTF-8");

    # Remove UTF-16 Big Endian Byte Order Mark
    ($str =~ s/^\xFE\xFF//) && ($enc = "UTF-16BE");

    # Remove UTF-16 Little Endian Byte Order Mark
    ($str =~ s/^\xFF\x/FE/) && ($enc = "UTF-16LE");

    # Remove UTF-32 Big Endian Byte Order Mark
    ($str =~ s/^\x00\x00\xFE\xFF//) && ($enc = "UTF-32BE");

    # Remove UTF-32 Little Endian Byte Order Mark
    ($str =~ s/^\xFF\xFE\x00\x00//) && ($enc = "UTF-32LE");


    #
    # Reopen and truncate file.
    #

    open (FH, ">", $fname)
        or return "Unable to open file $fname for writing.\n";

    print FH $str;

    close FH;

    return "$enc BOM removed from $fname\n";
}