use strict; use warnings; while (my $line = ) { 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