Even though we use PackratParsers, we've observed exponential parsing time on one of our bit more complicated inputs. It turned out that strange entries get into PackratReader cache; it contained more than one entry for seemingly equal (Parser,Position) pairs.

We've fixed this with a workaround which implements equals method in the OffsetPosition case class so that it does not compare CharSequences. Another working option which seems to be more safe is to compare toString representations of the CharSequences, but that introduces quite significant performance penalty.