#!perl -w

#
# Parse an mbox file (Thunderbird et al) and extract email addresses (and names, if any)
# Generate a CSV file suitable for import into Thunderbird's Address Book
# Written because /somebody/ deleted the address book :D
# bjp 2008-12-21
#

use strict;

my %owner;

# below line not split in actual code
my $col_line = <<'EOL';
First Name,Last Name,Display Name,Nickname,Primary Email,Secondary Email,
Work Phone,Home Phone,Fax Number,Pager Number,Mobile Number,Home Address,
Home Address 2,Home City,Home State,Home ZipCode,Home Country,Work Address,Work Address 2,
Work City,Work State,Work ZipCode,Work Country,Job Title,Department,Organization,Web Page 1,
Web Page 2,Birth Year,Birth Month,Birth Day,Custom 1,Custom 2,Custom 3,Custom 4,Notes,
EOL

my $input_mbox = $ARGV[0] || die "Usage: $0 <mbox file>\n";
my $to_buf     = '';
my $within_to  = 0;

open( my $fh, '<', $input_mbox ) or die "open: $!\n";
while (<$fh>) {
    chomp;
    if (/^From:/) {
        s/^From://;
        s/^\s+//;
        parse_save_addrs($_);
    }

    if ( /^[-a-z]+:/i && $within_to ) {
        $within_to = 0;
    }
    if ( /^To:/ || $within_to ) {
        $within_to = 1;
        s/^To://;
        s/^\s+//;
        $to_buf .= $_;

    }
    if ( !$within_to && length $to_buf ) {
        $to_buf =~ s/\r\n|\n//g;

        #print "to_buf: $to_buf\n\n";
        parse_save_addrs($to_buf);
        $to_buf = '';
    }
}

print $col_line;
for ( sort keys %owner ) {
    print ",,$owner{$_},,$_,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,\n";
}

sub strip_lt_white {
    my ($str) = @_;
    $str =~ s/^\s+//;
    $str =~ s/\s+$//;
    $str;
}

sub parse_save_addrs {
    my ($addrs) = @_;
    my @list = split /,|;/, $addrs;
    for my $entry (@list) {
        $entry =~ s/^\s+//;
        $entry =~ s/\s+$//;
        if ($entry =~ /
			(?:        
				(?:['"]*)   # optional quotes
				([^<'"]*)   # anything up to end quotes or email delim
				(?:['"]*)   # optional quotes
				\s*         # optional whitespace
				<(.+)>      # email in lt-gt delimiters
			)
			|
			([._a-z0-9]+\@[.-a-z0-9]+)

			/xi
            )
        {

            #no warnings;
            #print "1=[$1] 2=[$2] 3=[$3]\n";

            my $name  = $1 || '';
            my $email = $2 || $3;

            # skip junk
            next if $email =~ /<|>|=/
                 || $email =~ /mailto:/i;
            $name  = strip_lt_white($name);
            $email = strip_lt_white($email);
            $owner{$email} ||= $name;

            #print "name=[$name], email=[$email]\n";
        }
        else {
            print STDERR "Entry parse failed: $entry\n";
        }

        # print "$entry\n";
    }
}