use strict;
use warnings 'all';

# The phrase we are testing
$_ = '"this is a     phrase" +one -two .three, "another" phrase "unbalalanced bit, ""remove';
print $_,"\n";

my (@phrases,@terms);

# Grab the chunks and stick into our arrays
while(m/\G("[^"]*"|[^"]+|"[^"]*)/gc)
{
	my $p = $1;
	next unless defined($p);
	if($p =~ m/"$/)
	{
		push @phrases,cleanup('phrase',$p);
	}
	else
	{
		push @terms,cleanup('term',$p);
	}
}

# Display the phrases and terms
foreach (@phrases)
{
	print 'phrase: ',$_,"\n";
}

foreach (@terms)
{
	print 'term: \'',$_,"'\n";
}

#
# Sub cleanup
#
# Removes quotes and multiple spaces. In the case of a
# term it also removes all punctuation (other than a + or a -)
# and splits on spaces.
#

sub cleanup
{
	my $context = shift;
	return unless defined $context;
	
	if($context eq 'phrase')
	{
		$_[0] =~ s/"+//g;
		$_[0] =~ s/\s+/ /g;
		return $_[0];
	}
	else
	{
		$_[0] =~ s/"//g;
		$_[0] =~ s/[^\w\d\+\-]+/ /g;
		$_[0] =~ s/^\s+//g;	
		return split(/\s+/,$_[0]);
	}
}