use strict;
use warnings;

while (my $line = <DATA>) {
  chomp $line;

  # store tokens other than separators
  my @aTokens;

  # state: are we inside or outside of a parenthesized token?
  my $bParen;
  my $sInParens='';

  while ($line =~ /("[^"]+"|\(|\)|[^)\s]+|\s+)/g) {
    my $sToken = $1;
    if ($sToken eq '(') {
      #starting a parenthesized token
      $bParen=1;
    } elsif ($sToken eq ')') {
      #ending a parenthesized token: add it to the list
      $bParen=0;
      push @aTokens, "($sInParens)";
      $sInParens='';
    } elsif ($bParen) {
      # in the middle of a parenthesized token
      $sInParens .= $sToken;
    } elsif ($sToken =~ /^\S/) {
      # not a parenthesized token
      # either a quoted or unquoted non-whitespace token
      # add it to the list
      push @aTokens, $sToken;
    }
  }
  local $"='> <';
  printf "input : %s\n%s", "<$line>", "tokens: <@aTokens>";
}

__DATA__
xxx "()" ("charset" "ISO-8859-1") (")") "xxx"

##</code><code>##

use strict;
use warnings;

while (my $line = <DATA>) {
  chomp $line;
  my @aTokens;
  my $sInParens='';
  my $iParenCount;

  while ($line =~ /("[^"]+"|\(|\)|[^)\s]*|\s+)/g) {
    my $sToken = $1;
    if ($sToken eq '(') {
      if ($iParenCount) {
        $sInParens .= $sToken;
      }
      $iParenCount++;
    } elsif ($sToken eq ')') {
      $iParenCount--;
      if ($iParenCount) {
        $sInParens .= $sToken;
      } else {
        push @aTokens, "($sInParens)";
        $sInParens='';
      }
    } elsif ($iParenCount) {
      $sInParens .= $sToken;
    } elsif ($sToken =~ /^\S/) {
      push @aTokens, $sToken;
    }
  }
  local $"='> <';
  print "paren count: $iParenCount\n";
  printf "input : %s\n%s", "<$line>", "tokens: <@aTokens>\n";
}

__DATA__
xxx "()" ("charset" "ISO-8859-1") (")") "xxx" ((a)(b)(c)) yyy