Good! I got always fascinated by non-boolean indexing (probabilistic instead).
I've remember having implemented an OOP indexed version of U.C. Berkeley's Cheshire-II in 2007 with Dolphin Smalltalk.
I was using BTrees tho, hence O(log N). The non-boolean part was in the values of the keys which were probability of good match against your search target.
I've remember having implemented an OOP indexed version of U.C. Berkeley's Cheshire-II in 2007 with Dolphin Smalltalk.
I was using BTrees tho, hence O(log N). The non-boolean part was in the values of the keys which were probability of good match against your search target.