text_similarity.rs

 1mod occurrences;
 2mod sliding_window;
 3mod source;
 4
 5pub use occurrences::*;
 6pub use sliding_window::*;
 7pub use source::*;
 8
 9// Variants to consider trying:
10//
11// * Also include unsplit identifier (or a hash of its hashes), so that full identifier matches get
12// a higher score.
13//
14// * Inclusion of both unmodified and lowercased identifier parts, so that case matches get a higher
15// score.
16//
17//     - If this is implemented then SmallOccurrenceSet::from_hashes should do some eager deduping based
18//     on last added.