my $sentence_rx = qr{ (?: (?<= ^ ) | (?<= \s ) ) # after start-of-string or # whitespace \p{Lu} # capital letter .*? # a bunch of anything (?<= \S ) # that ends in non- # whitespace (?) { say "NEW PARAGRAPH"; my $count = 0; while ($paragraph =~ /($sentence_rx)/g) { printf "\tgot sentence %d: <%s>\n", ++$count, $1; } }