This package is a high-performance, in-memory B-tree for Go that implements an ordered set/map with efficient insert, delete, and range iteration. It’s parameterized by tree degree so callers can tune cache behavior and memory overhead for their workload. Instead of relying on Go’s built-in maps—which are hash-based and unordered—btree preserves sorted order and provides rich traversal APIs like ascending, descending, and range scans. The implementation favors minimal allocations and locality, making it attractive for indexing, query engines, and caches that need predictable iteration costs. A simple Item interface with a Less method defines ordering, keeping the API small and flexible for custom types. The library includes benchmarks and optional freelists so users can trade memory reuse for speed in hot paths.
Features
- Ordered set/map semantics with fast range iteration
- Efficient insert, delete, get, and replace operations
- Tunable node degree to balance speed and memory locality
- Ascend/Descend and range-bounded traversal callbacks
- Minimal allocations with optional freelist reuse
- Small, idiomatic API using a Less interface for custom ordering