//! Dep-free linear-interpolation resamplers for the Windows/cpal backend (W4).
//!
//! The pipeline runs internally at 48 kHz (Opus + the 20 ms frame), but a WASAPI
//! endpoint may run at a different rate (commonly 44.1 kHz) and/or a non-stereo
//! channel layout. These convert at the device boundary so such a device plays and
//! captures instead of hard-erroring (the W4 limitation in the Windows port).
//!
//! ## Where each is used
//! - [`PushResampler`] (single channel) converts **capture** from the device rate
//!   to 48 kHz on the capture drain thread — off the RT callback.
//! - [`StereoPullResampler`] converts **playback** from the internal 48 kHz stereo
//!   bus to the device rate inside the output RT callback, pulling internal frames
//!   from the ring on demand. It allocates nothing in `next`, so it is RT-safe.
//!
//! ## Quality
//! This is plain linear interpolation with no anti-aliasing filter: correct,
//! allocation-free, and adequate for speech, but it adds some aliasing when
//! downsampling. The seam is intentionally tiny so a higher-quality polyphase/FIR
//! resampler (e.g. the `rubato` crate, pending a supply-chain decision) can later
//! replace the internals without touching the cpal backend. The matching-rate /
//! matching-layout path in the backend bypasses these entirely and stays bit-exact.

/// Linear interpolation between `a` and `b` at fractional position `frac` in `[0, 1)`.
#[inline]
fn lerp(a: f32, b: f32, frac: f32) -> f32 {
    a + (b - a) * frac
}

/// Stateful single-channel **push** resampler: feed input samples at `in_rate`,
/// receive output samples at `out_rate` through an `emit` callback. It carries the
/// fractional read position and the previous input sample across calls, so feeding
/// the stream block-by-block joins seamlessly. Neither [`push`](Self::push) nor
/// [`process`](Self::process) allocates.
pub struct PushResampler {
    /// Input samples consumed per output sample (`in_rate / out_rate`).
    step: f64,
    /// Position of the next output sample, in input-sample units, measured from the
    /// index of `prev` (the most recent input). Always advanced to stay `< 1.0`
    /// after each input is consumed.
    next: f64,
    /// The previous input sample (left edge of the current interpolation segment).
    prev: f32,
    /// Whether any input has been seen yet (anchors the first output at input[0]).
    started: bool,
}

impl PushResampler {
    /// Build a resampler from `in_rate` to `out_rate` (both in Hz). Rates are
    /// clamped to `>= 1` so `step` is always finite and non-zero: a zero `step`
    /// would make [`push`](Self::push)'s `while self.next < 1.0` loop forever. The
    /// cpal backend's `resolve()` also rejects such rates up front, so this is
    /// belt-and-suspenders against a future caller (review W7).
    pub fn new(in_rate: u32, out_rate: u32) -> Self {
        Self {
            step: in_rate.max(1) as f64 / out_rate.max(1) as f64,
            next: 0.0,
            prev: 0.0,
            started: false,
        }
    }

    /// Feed one input sample; `emit` is called for each output sample produced
    /// (zero or more, depending on the rate ratio).
    pub fn push(&mut self, cur: f32, mut emit: impl FnMut(f32)) {
        if !self.started {
            // First sample: just establish the left edge. Linear interpolation
            // needs the next input as the right edge, so the first output is
            // produced on the next push. This gives exact alignment
            // (`output[k] == input[k]` at equal rates) with one input-sample of
            // latency — negligible (~20 µs at 48 kHz).
            self.started = true;
            self.prev = cur;
            self.next = 0.0;
            return;
        }
        // `prev` sits at position 0 of this segment and `cur` at position 1; emit
        // every output whose position falls in [0, 1).
        while self.next < 1.0 {
            emit(lerp(self.prev, cur, self.next as f32));
            self.next += self.step;
        }
        self.next -= 1.0;
        self.prev = cur;
    }

    /// Convenience for tests / batch callers: push a whole slice.
    pub fn process(&mut self, input: &[f32], mut emit: impl FnMut(f32)) {
        for &s in input {
            self.push(s, &mut emit);
        }
    }
}

/// Stateful stereo **pull** resampler: produce output frames at `out_rate` by
/// pulling input frames at `in_rate` from a closure on demand. Call
/// [`next`](Self::next) once per output frame; it pulls as many input frames as the
/// ratio requires and returns the interpolated `(left, right)`, or `None` when the
/// puller runs dry (an underrun). Allocates nothing, so it is safe in an RT output
/// callback.
pub struct StereoPullResampler {
    /// Input frames consumed per output frame (`in_rate / out_rate`).
    step: f64,
    /// Position of the next output frame within `[prev, cur)`, in `[0, 1)`.
    frac: f64,
    /// Left edge of the current interpolation segment.
    prev: (f32, f32),
    /// Right edge of the current interpolation segment.
    cur: (f32, f32),
    /// Whether `prev`/`cur` have been primed from the puller yet.
    primed: bool,
}

impl StereoPullResampler {
    /// Build a resampler from `in_rate` to `out_rate` (both in Hz). Rates are
    /// clamped to `>= 1` so `step` is finite and non-zero — otherwise
    /// [`next`](Self::next)'s `while self.frac >= 1.0` could spin (review W7).
    pub fn new(in_rate: u32, out_rate: u32) -> Self {
        Self {
            step: in_rate.max(1) as f64 / out_rate.max(1) as f64,
            frac: 0.0,
            prev: (0.0, 0.0),
            cur: (0.0, 0.0),
            primed: false,
        }
    }

    /// Produce the next output frame, pulling input frames via `pull` as needed.
    /// Returns `None` if `pull` returns `None` before the frame can be formed
    /// (underrun); the caller should substitute silence for that frame.
    pub fn next(&mut self, mut pull: impl FnMut() -> Option<(f32, f32)>) -> Option<(f32, f32)> {
        if !self.primed {
            // Prime both edges from two pulls so the first output frame aligns
            // exactly with the first input frame (`out[0] == in[0]` at equal
            // rates). Needs two frames available to start, which the prefilled
            // playback ring always has.
            self.prev = pull()?;
            self.cur = pull()?;
            self.primed = true;
            self.frac = 0.0;
        }
        // Advance the segment until the read position lands inside [prev, cur).
        while self.frac >= 1.0 {
            self.prev = self.cur;
            self.cur = pull()?;
            self.frac -= 1.0;
        }
        let f = self.frac as f32;
        let out = (
            lerp(self.prev.0, self.cur.0, f),
            lerp(self.prev.1, self.cur.1, f),
        );
        self.frac += self.step;
        Some(out)
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    /// Equal rates align exactly: `output[k] == input[k]`. The final input lands on
    /// the next push (one-sample streaming latency), so we get `n - 1` outputs.
    #[test]
    fn push_identity_when_rates_match() {
        let mut r = PushResampler::new(48_000, 48_000);
        let input = [0.0, 0.1, 0.2, 0.3, 0.4];
        let mut out = Vec::new();
        r.process(&input, |s| out.push(s));
        assert_eq!(out.len(), input.len() - 1);
        for (a, b) in out.iter().zip(input.iter()) {
            assert!((a - b).abs() < 1e-6, "{a} vs {b}");
        }
    }

    /// Upsampling 2x roughly doubles the output count and the midpoints interpolate.
    #[test]
    fn push_upsample_2x_interpolates_midpoints() {
        let mut r = PushResampler::new(24_000, 48_000); // step = 0.5
        let input = [0.0, 1.0, 2.0, 3.0];
        let mut out = Vec::new();
        r.process(&input, |s| out.push(s));
        // (n - 1) segments at 2 outputs each = 6.
        assert_eq!(out.len(), 6, "out {out:?}");
        // A half-step between 1.0 and 2.0 must appear near 1.5.
        assert!(
            out.iter().any(|&s| (s - 1.5).abs() < 1e-3),
            "expected a ~1.5 midpoint in {out:?}"
        );
    }

    /// Downsampling drops the rate: fewer outputs than inputs, monotonic ramp preserved.
    #[test]
    fn push_downsample_reduces_count() {
        let mut r = PushResampler::new(48_000, 44_100); // step ~1.088
        let input: Vec<f32> = (0..441).map(|i| i as f32).collect();
        let mut out = Vec::new();
        r.process(&input, |s| out.push(s));
        // 441 in @ 48k -> ~405 out @ 44.1k.
        assert!(
            (390..=410).contains(&out.len()),
            "expected ~405 outputs, got {}",
            out.len()
        );
        // Output stays within the input's value range and is non-decreasing.
        for w in out.windows(2) {
            assert!(w[1] >= w[0] - 1e-3, "ramp should not reverse: {w:?}");
        }
        assert!(*out.last().unwrap() <= 440.0 + 1e-3);
    }

    /// Pull resampler at equal rates returns each input frame in order, aligned.
    /// Two-pull priming uses one frame of lookahead, so `n` inputs yield `n - 1`
    /// outputs (the last frame emits once a successor arrives).
    #[test]
    fn pull_identity_when_rates_match() {
        let mut r = StereoPullResampler::new(48_000, 48_000);
        let frames = [(0.0, 9.0), (1.0, 8.0), (2.0, 7.0), (3.0, 6.0)];
        let mut idx = 0;
        let mut out = Vec::new();
        while let Some(f) = r.next(|| {
            let v = frames.get(idx).copied();
            idx += 1;
            v
        }) {
            out.push(f);
        }
        assert_eq!(out.len(), frames.len() - 1, "out {out:?}");
        for (got, want) in out.iter().zip(frames.iter()) {
            assert!((got.0 - want.0).abs() < 1e-6 && (got.1 - want.1).abs() < 1e-6);
        }
    }

    /// Pull resampler reports underrun (`None`) once the source is exhausted.
    #[test]
    fn pull_returns_none_on_underrun() {
        let mut r = StereoPullResampler::new(48_000, 44_100); // step ~1.088 -> pulls >1 per out
        let frames = [(0.0, 0.0), (1.0, -1.0)];
        let mut idx = 0;
        let mut pull = || {
            let v = frames.get(idx).copied();
            idx += 1;
            v
        };
        // First frame primes + emits; subsequent calls eventually exhaust the source.
        let mut produced = 0;
        let mut hit_none = false;
        for _ in 0..10 {
            if r.next(&mut pull).is_some() {
                produced += 1;
            } else {
                hit_none = true;
                break;
            }
        }
        assert!(produced >= 1, "should produce at least the primed frame");
        assert!(hit_none, "should report underrun once the puller is dry");
    }

    /// Downsampling via pull consumes more input frames than it emits output frames.
    #[test]
    fn pull_downsample_consumes_more_than_it_emits() {
        let mut r = StereoPullResampler::new(48_000, 24_000); // step = 2.0
        let input: Vec<(f32, f32)> = (0..100).map(|i| (i as f32, -(i as f32))).collect();
        let mut idx = 0;
        let mut emitted = 0;
        for _ in 0..40 {
            let f = r.next(|| {
                let v = input.get(idx).copied();
                idx += 1;
                v
            });
            if f.is_some() {
                emitted += 1;
            } else {
                break;
            }
        }
        // At step 2.0 we consume ~2 input frames per output frame.
        assert!(
            idx > emitted,
            "consumed {idx} input, emitted {emitted} output"
        );
    }

    /// A zero rate must not produce a zero `step` (which would spin `push`'s inner
    /// `while self.next < 1.0` forever). Clamping makes the call terminate (W7).
    #[test]
    fn push_zero_rate_does_not_spin() {
        let mut r = PushResampler::new(0, 48_000);
        let mut count = 0usize;
        // Feed two samples; with a clamped non-zero step this returns promptly.
        r.push(0.0, |_| count += 1);
        r.push(1.0, |_| count += 1);
        // Reaching here at all is the assertion (no hang); some output is produced.
        assert!(count >= 1);
    }

    /// A zero output rate must not make the pull resampler's segment-advance loop
    /// spin. Clamping keeps `step` finite so `next` terminates (W7).
    #[test]
    fn pull_zero_out_rate_does_not_spin() {
        let mut r = StereoPullResampler::new(48_000, 0);
        let frames = [(0.0, 0.0), (1.0, 1.0), (2.0, 2.0)];
        let mut idx = 0;
        let got = r.next(|| {
            let v = frames.get(idx).copied();
            idx += 1;
            v
        });
        // Terminates and yields the primed frame instead of hanging.
        assert!(got.is_some());
    }
}