fix: improve perf of count with smarter handling of half-open range

[sstadick]

The BITS paper uses fully inclusive ranges. When this was written I'm not sure I understood that. To get things to match the naive version of count (find -> count) I had a while loop in the bits count method to advance the cursor past the matched start/stop index.

This change was found while porting mojo-lapper and removes the while loop. It also has a more effecient branchless binary search.

Benchmarks for count improve 24-30% (see PR).

Bakeoff/rust-lapper: count with 100% hit rate                                                                             
                        time:   [14.742 us 14.773 us 14.811 us]
                        change: [-24.448% -24.164% -23.869%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 18 outliers among 100 measurements (18.00%)
  18 (18.00%) high severe
Bakeoff/rust-lapper: count with below 100% hit rate                                                                             
                        time:   [2.1958 us 2.2019 us 2.2076 us]
                        change: [-30.391% -29.790% -29.274%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 6 outliers among 100 measurements (6.00%)
  6 (6.00%) low mild                                                                                                                                              
Benchmarking Bakeoff/rust-lapper: count with below 100% hit rate - chromosome spanning interval: Collecting 100 samples in estimated 5.0080 s (2.3M ite                                                                                                                                                       Bakeoff/rust-lapper: count with below 100% hit rate - chromosome spanning interval                        
                        time:   [2.1989 us 2.2070 us 2.2148 us]
                        change: [-32.616% -30.807% -29.536%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 6 outliers among 100 measurements (6.00%)
  5 (5.00%) low mild
  1 (1.00%) high severe

[Copilot]

Pull Request Overview

This PR refactors the interval counting logic to remove an extra cursor-advancing loop, replaces the traditional binary search with a branchless version, and bumps the crate version to 1.2.0.

• Remove mutable top binding and simplify stack handling
• Introduce branchless bsearch_seq, eliminate inclusive-range loop in count
• Bump rust-lapper version from 1.1.0 to 1.2.0

Reviewed Changes

Copilot reviewed 2 out of 3 changed files in this pull request and generated no comments.

File	Description
src/lib.rs	Simplified stack pop, replaced binary search with branchless variant, adjusted half-open logic in count, and left a debug println! in tests
Cargo.toml	Updated package version to 1.2.0

Comments suppressed due to low confidence (3)

src/lib.rs:431

• [nitpick] The variable name cursor is ambiguous in the context of a search index; consider renaming to something like index or position, and likewise rename length to remaining or span for clarity.

        let mut cursor = 0;

src/lib.rs:587

• [nitpick] It would be helpful to add unit tests targeting edge cases around the start + one::<I>() adjustment to ensure the half-open interval logic remains correct under all boundary conditions.

        let first = Self::bsearch_seq(start + one::<I>(), &self.stops);

src/lib.rs:1009

• This debug println! in the test appears to be leftover and will clutter test output; consider removing it.

        println!("{:?}",lapper);