SimurgArray/rust/simurg-core/src/lib.rs

//! Compiled kernels for SimurgArray (plan §18 P9, §19).
//!
//! Every kernel is a drop-in replacement for a pure-Python/NumPy reference in the `simurg` package and returns
//! bit-identical results (checked by `tests/unit/test_core_kernels.py`):
//!
//! * `exp`, `log10`, `log2`, `pow` — element-wise glibc libm calls with the error semantics of CPython's `math`
//!   module as used by `simurg.genotype.gencall._c_call` (NaN input returned as is, a domain error gives the
//!   canonical +NaN, `log10(0)` = −inf, overflow = +inf). The libm symbols are the ones CPython's `math` calls, so
//!   results equal the C reference implementations (gtc2vcf, MIT) that the Python port follows.
//! * `closest_binned` — the per-bin candidate scan of the vendor's binned nearest-neighbour search
//!   (`simurg.signal.normalization.fit._closest_binned`): float32 squared distances, first minimum wins.
//!
//! * `call_genotypes`, `baf_lrr` — fused per-locus GenCall calling/scoring and BAF/LRR (`gencall.rs`).
//! * `bpm_locus_entries` — the BPM LocusEntry parser (`simurg.formats.bpm._parse_locus_entries`).
//!
//! No floating-point contraction (FMA) happens: Rust never fuses `a*b+c` implicitly.

mod bpm;
mod gencall;

use numpy::{IntoPyArray, PyArray1, PyReadonlyArray1};
use pyo3::exceptions::PyValueError;
use pyo3::prelude::*;

#[link(name = "m")]
unsafe extern "C" {
    #[link_name = "exp"]
    fn c_exp(x: f64) -> f64;
    #[link_name = "log10"]
    fn c_log10(x: f64) -> f64;
    #[link_name = "log2"]
    fn c_log2(x: f64) -> f64;
    #[link_name = "pow"]
    fn c_pow(x: f64, y: f64) -> f64;
}

/// CPython's `float('nan')`.
const PY_NAN: f64 = f64::from_bits(0x7ff8_0000_0000_0000);

#[inline]
pub(crate) fn math_exp(v: f64) -> f64 {
    if v.is_nan() {
        return v;
    }
    let r = unsafe { c_exp(v) };
    if r.is_nan() { PY_NAN } else if r.is_infinite() && v.is_finite() { f64::INFINITY } else { r }
}

/// CPython `m_log10`/`m_log2` + `_c_call`: x > 0 → libm; 0 → −inf (log10) or NaN (log2); x < 0, −inf → NaN.
#[inline]
pub(crate) fn math_log(v: f64, ten: bool) -> f64 {
    if v.is_nan() {
        return v;
    }
    if v.is_infinite() {
        return if v > 0.0 { v } else { PY_NAN };
    }
    if v > 0.0 {
        return unsafe { if ten { c_log10(v) } else { c_log2(v) } };
    }
    if v == 0.0 && ten { f64::NEG_INFINITY } else { PY_NAN }
}

/// CPython `math.pow(v, e)` for a finite exponent e > 0 that is not an integer, + `_c_call`.
#[inline]
pub(crate) fn math_pow(v: f64, e: f64) -> f64 {
    if v.is_nan() {
        return v;
    }
    if v.is_infinite() {
        return f64::INFINITY;
    }
    if v == 0.0 {
        return 0.0;
    }
    let r = unsafe { c_pow(v, e) };
    if r.is_nan() { PY_NAN } else if r.is_infinite() { f64::INFINITY } else { r }
}

fn map_f64<'py>(py: Python<'py>, x: PyReadonlyArray1<'py, f64>, f: impl Fn(f64) -> f64) -> PyResult<Bound<'py, PyArray1<f64>>> {
    let s = x.as_slice()?;
    let out: Vec<f64> = s.iter().map(|&v| f(v)).collect();
    Ok(out.into_pyarray(py))
}

#[pyfunction]
fn exp<'py>(py: Python<'py>, x: PyReadonlyArray1<'py, f64>) -> PyResult<Bound<'py, PyArray1<f64>>> {
    map_f64(py, x, math_exp)
}

#[pyfunction]
fn log10<'py>(py: Python<'py>, x: PyReadonlyArray1<'py, f64>) -> PyResult<Bound<'py, PyArray1<f64>>> {
    map_f64(py, x, |v| math_log(v, true))
}

#[pyfunction]
fn log2<'py>(py: Python<'py>, x: PyReadonlyArray1<'py, f64>) -> PyResult<Bound<'py, PyArray1<f64>>> {
    map_f64(py, x, |v| math_log(v, false))
}

#[pyfunction]
fn pow<'py>(py: Python<'py>, x: PyReadonlyArray1<'py, f64>, e: f64) -> PyResult<Bound<'py, PyArray1<f64>>> {
    if !(e.is_finite() && e > 0.0 && e.fract() != 0.0) {
        return Err(PyValueError::new_err("pow kernel: exponent must be finite, positive and not an integer"));
    }
    map_f64(py, x, |v| math_pow(v, e))
}

/// For each sweep point `p` searching bin `choice[p]` (0..11 regular, 12..22 shifted; any other value: none), the
/// index of the closest candidate among `eligible[i]` with `b1[i] == choice` (regular) or `b2[i] == choice − 12`
/// (shifted), in ascending order; squared distance in float32; −1 if no candidate or the best is not < 1e20.
#[pyfunction]
#[allow(clippy::too_many_arguments)]
fn closest_binned<'py>(
    py: Python<'py>,
    raw_x: PyReadonlyArray1<'py, f32>,
    raw_y: PyReadonlyArray1<'py, f32>,
    axis_x: PyReadonlyArray1<'py, f32>,
    axis_y: PyReadonlyArray1<'py, f32>,
    choice: PyReadonlyArray1<'py, i64>,
    eligible: PyReadonlyArray1<'py, i64>,
    b1: PyReadonlyArray1<'py, i64>,
    b2: PyReadonlyArray1<'py, i64>,
) -> PyResult<Bound<'py, PyArray1<i64>>> {
    let (rx, ry) = (raw_x.as_slice()?, raw_y.as_slice()?);
    let (ax, ay, ch) = (axis_x.as_slice()?, axis_y.as_slice()?, choice.as_slice()?);
    let (el, b1, b2) = (eligible.as_slice()?, b1.as_slice()?, b2.as_slice()?);
    if ax.len() != ay.len() || ax.len() != ch.len() || el.len() != b1.len() || el.len() != b2.len() || rx.len() != ry.len() {
        return Err(PyValueError::new_err("closest_binned: length mismatch"));
    }
    let mut groups: Vec<Vec<usize>> = vec![Vec::new(); 23];
    for (i, &e) in el.iter().enumerate() {
        let e = usize::try_from(e).map_err(|_| PyValueError::new_err("closest_binned: negative index"))?;
        if e >= rx.len() {
            return Err(PyValueError::new_err("closest_binned: index out of range"));
        }
        if (0..12).contains(&b1[i]) {
            groups[b1[i] as usize].push(e);
        }
        if (0..11).contains(&b2[i]) {
            groups[12 + b2[i] as usize].push(e);
        }
    }
    let out: Vec<i64> = (0..ax.len())
        .map(|p| {
            let c = ch[p];
            if !(0..23).contains(&c) {
                return -1;
            }
            let cand = &groups[c as usize];
            let mut best_j = usize::MAX;
            let mut best = f32::INFINITY;
            for (j, &e) in cand.iter().enumerate() {
                let dx = rx[e] - ax[p];
                let dy = ry[e] - ay[p];
                let d = dx * dx + dy * dy;
                // numpy argmin: the first NaN wins, otherwise the first strict minimum
                if d.is_nan() {
                    best_j = j;
                    best = d;
                    break;
                }
                if best_j == usize::MAX || d < best {
                    best_j = j;
                    best = d;
                }
            }
            if best_j == usize::MAX || !((best as f64) < 1e20) { -1 } else { cand[best_j] as i64 }
        })
        .collect();
    Ok(out.into_pyarray(py))
}

/// Exact nearest neighbour (`simurg.signal.normalization.fit._closest_slow`): for each sweep point (x, y) the
/// index of the reference point with the smallest float32 squared distance `(x-xr)²+(y-yr)²`; first minimum wins,
/// a NaN distance wins as in `numpy.argmin`. `xref` must not be empty.
#[pyfunction]
fn closest_exact<'py>(
    py: Python<'py>,
    xref: PyReadonlyArray1<'py, f32>,
    yref: PyReadonlyArray1<'py, f32>,
    x: PyReadonlyArray1<'py, f32>,
    y: PyReadonlyArray1<'py, f32>,
) -> PyResult<Bound<'py, PyArray1<i64>>> {
    let (xr, yr, xs, ys) = (xref.as_slice()?, yref.as_slice()?, x.as_slice()?, y.as_slice()?);
    if xr.is_empty() || xr.len() != yr.len() || xs.len() != ys.len() {
        return Err(PyValueError::new_err("closest_exact: empty reference or length mismatch"));
    }
    let out: Vec<i64> = xs
        .iter()
        .zip(ys)
        .map(|(&px, &py_)| {
            let mut best_j = 0usize;
            let mut best = f32::INFINITY;
            for (j, (&rx, &ry)) in xr.iter().zip(yr).enumerate() {
                let dx = px - rx;
                let dy = py_ - ry;
                let d = dx * dx + dy * dy;
                if d.is_nan() {
                    return j as i64;
                }
                if j == 0 || d < best {
                    best_j = j;
                    best = d;
                }
            }
            best_j as i64
        })
        .collect();
    Ok(out.into_pyarray(py))
}

#[pymodule]
fn simurg_core(m: &Bound<'_, PyModule>) -> PyResult<()> {
    m.add("__version__", env!("CARGO_PKG_VERSION"))?;
    m.add_function(wrap_pyfunction!(exp, m)?)?;
    m.add_function(wrap_pyfunction!(log10, m)?)?;
    m.add_function(wrap_pyfunction!(log2, m)?)?;
    m.add_function(wrap_pyfunction!(pow, m)?)?;
    m.add_function(wrap_pyfunction!(closest_binned, m)?)?;
    m.add_function(wrap_pyfunction!(closest_exact, m)?)?;
    m.add_function(wrap_pyfunction!(bpm::bpm_locus_entries, m)?)?;
    m.add_function(wrap_pyfunction!(gencall::call_genotypes, m)?)?;
    m.add_function(wrap_pyfunction!(gencall::baf_lrr, m)?)?;
    Ok(())
}