//! Look-ahead brickwall peak limiter (base-rate).
//!
//! Guarantees the output never exceeds the ceiling. A short fixed look-ahead lets the gain ramp
//! down *before* a peak reaches the output (click-free), driven by a **sliding maximum** over the
//! look-ahead window so the reduction is fully in place in time. A final clamp at the ceiling is
//! the hard guarantee against any residual from smoothing lag or float error.
//!
//! Detection is stereo-linked (one gain for all channels). This stage limits **sample** peaks at
//! the base rate; true-peak (inter-sample) limiting via oversampling is a later addition.

use super::oversampler::Oversampler;

const MAX_CHANNELS: usize = 2;
/// Fixed look-ahead — also this stage's constant latency contribution.
const LOOKAHEAD_MS: f32 = 1.5;
/// Near-instant attack; the look-ahead gives it time to act before the peak arrives.
const ATTACK_MS: f32 = 0.05;
/// The 4× true-peak detector can still under-read by a few tenths of a dB near Nyquist, so we
/// target a hair below the ceiling to keep the actual inter-sample peak under it.
const TRUE_PEAK_MARGIN_DB: f32 = 0.3;

fn time_to_coef(time_ms: f32, sample_rate: f32) -> f32 {
    if time_ms <= 0.0 {
        0.0
    } else {
        (-1.0 / (time_ms * 0.001 * sample_rate)).exp()
    }
}

pub struct Limiter {
    /// Per-channel audio delay ring.
    delay: Vec<Vec<f32>>,
    /// Linked `|x|` history, same length as the delay ring (for the sliding maximum).
    peaks: Vec<f32>,
    capacity: usize,
    write_pos: usize,
    fixed_delay: usize,
    /// Current smoothed gain (<= 1).
    gain: f32,
    attack_coef: f32,
    /// 4× interpolator for true-peak (inter-sample) detection.
    oversampler: Oversampler,
}

impl Default for Limiter {
    fn default() -> Self {
        Self {
            delay: Vec::new(),
            peaks: Vec::new(),
            capacity: 0,
            write_pos: 0,
            fixed_delay: 0,
            gain: 1.0,
            attack_coef: 0.0,
            oversampler: Oversampler::new(),
        }
    }
}

impl Limiter {
    pub fn new() -> Self {
        Self::default()
    }

    /// Allocate buffers. Call from `initialize()` (allocation allowed).
    pub fn prepare(&mut self, sample_rate: f32, num_channels: usize) {
        self.fixed_delay = (LOOKAHEAD_MS * 0.001 * sample_rate).ceil() as usize;
        self.capacity = self.fixed_delay + 1;
        self.attack_coef = time_to_coef(ATTACK_MS, sample_rate);
        let channels = num_channels.clamp(1, MAX_CHANNELS);
        self.delay = vec![vec![0.0; self.capacity]; channels];
        self.peaks = vec![0.0; self.capacity];
        self.oversampler.prepare(channels);
        self.reset();
    }

    pub fn reset(&mut self) {
        for ch in &mut self.delay {
            ch.iter_mut().for_each(|s| *s = 0.0);
        }
        self.peaks.iter_mut().for_each(|p| *p = 0.0);
        self.oversampler.reset();
        self.write_pos = 0;
        self.gain = 1.0;
    }

    /// Constant reported latency (the fixed look-ahead delay).
    pub fn latency(&self) -> u32 {
        self.fixed_delay as u32
    }

    /// Current limiter gain reduction in dB (>= 0). `gain` is linear (<= 1); expressed here as a
    /// positive dB amount for the ceiling lamp / metering.
    pub fn gain_reduction_db(&self) -> f32 {
        -20.0 * self.gain.max(1e-9).log10()
    }

    /// Limit one frame in place: `input[ch]` -> `output[ch]`.
    ///
    /// `ceiling` is linear gain (e.g. `util::db_to_gain(ceiling_db)`); `release_coef` comes from a
    /// release time. Output is guaranteed `|y| <= ceiling`.
    pub fn process(&mut self, input: &[f32], output: &mut [f32], ceiling: f32, release_coef: f32) {
        let n = input.len().min(self.delay.len());

        // Detector = max of the sample peak and the 4× true-peak (inter-sample) estimate.
        let mut sample_peak = 0.0f32;
        for &x in &input[..n] {
            sample_peak = sample_peak.max(x.abs());
        }
        let peak = sample_peak.max(self.oversampler.max_true_peak(&input[..n]));

        // Target a hair below the ceiling so the (slightly under-read) true peak stays under it.
        let target_ceiling = ceiling * 10.0f32.powf(-TRUE_PEAK_MARGIN_DB / 20.0);

        // Write into the ring.
        for ch in 0..n {
            self.delay[ch][self.write_pos] = input[ch];
        }
        self.peaks[self.write_pos] = peak;

        // Sliding maximum over the look-ahead window (= the whole ring). Because the oldest sample
        // (the one we output now) is in this window, `ceiling / window_max` applied to it can never
        // exceed the ceiling, and the gain has pre-dropped for any louder sample still to come.
        let mut window_max = 0.0f32;
        for &p in &self.peaks {
            window_max = window_max.max(p);
        }
        let target = if window_max > target_ceiling {
            target_ceiling / window_max
        } else {
            1.0
        };

        // Decoupled smoothing: fast attack down, slow release up.
        self.gain = if target < self.gain {
            self.attack_coef * self.gain + (1.0 - self.attack_coef) * target
        } else {
            release_coef * self.gain + (1.0 - release_coef) * target
        };

        // Output the delayed sample, clamped to the ceiling as the hard guarantee.
        let out_pos = (self.write_pos + 1) % self.capacity; // oldest sample = fixed_delay ago
        for ch in 0..n {
            output[ch] = (self.delay[ch][out_pos] * self.gain).clamp(-ceiling, ceiling);
        }

        self.write_pos = (self.write_pos + 1) % self.capacity;
    }
}

#[cfg(test)]
mod tests {
    use super::*;
    use std::f32::consts::TAU;

    const SR: f32 = 48_000.0;

    fn release() -> f32 {
        time_to_coef(50.0, SR)
    }

    #[test]
    fn never_exceeds_ceiling_on_spikes() {
        // Mostly silence with occasional large spikes — output must never exceed the ceiling.
        let mut lim = Limiter::new();
        lim.prepare(SR, 1);
        let ceiling = 1.0;
        let mut out = [0.0f32];
        for i in 0..10_000 {
            let x = if i % 500 == 0 { 5.0 } else { 0.01 };
            lim.process(&[x], &mut out, ceiling, release());
            assert!(out[0].abs() <= ceiling + 1e-6, "overshoot at {i}: {}", out[0]);
        }
    }

    #[test]
    fn limits_loud_sine_to_ceiling() {
        // A sine well above the ceiling settles to ~ceiling, not silenced.
        let mut lim = Limiter::new();
        lim.prepare(SR, 1);
        let ceiling = 1.0;
        let (amp, freq) = (2.0f32, 1_000.0);
        let mut out = [0.0f32];
        let mut max_tail = 0.0f32;
        let total = SR as usize;
        for i in 0..total {
            let x = amp * (TAU * freq * i as f32 / SR).sin();
            lim.process(&[x], &mut out, ceiling, release());
            if i >= total - 4_800 {
                max_tail = max_tail.max(out[0].abs());
            }
        }
        assert!(max_tail <= ceiling + 1e-6, "exceeded ceiling: {max_tail}");
        assert!(max_tail > 0.9, "over-attenuated: {max_tail}");
    }

    #[test]
    fn transparent_below_ceiling() {
        // A signal under the ceiling passes through unattenuated (just delayed).
        let mut lim = Limiter::new();
        lim.prepare(SR, 1);
        let ceiling = 1.0;
        let (amp, freq) = (0.5f32, 1_000.0);
        let mut out = [0.0f32];
        let mut max_tail = 0.0f32;
        let total = SR as usize / 2;
        for i in 0..total {
            let x = amp * (TAU * freq * i as f32 / SR).sin();
            lim.process(&[x], &mut out, ceiling, release());
            if i >= total - 4_800 {
                max_tail = max_tail.max(out[0].abs());
            }
        }
        assert!((max_tail - amp).abs() < 1e-3, "not transparent: {max_tail}");
    }

    #[test]
    fn latency_is_the_lookahead() {
        let mut lim = Limiter::new();
        lim.prepare(SR, 1);
        let expected = (LOOKAHEAD_MS * 0.001 * SR).ceil() as u32;
        assert_eq!(lim.latency(), expected);
        assert!(expected > 0);
    }
}