#pragma once
// pitch_shift — a PURE, per-voice, duration-preserving pitch shifter: the S16 "Preserve"
// engine's DSP core. Time-domain overlap-add (OLA) with two half-window-offset read taps
// crossfaded to hide the ring-wrap seam. Source is consumed 1:1 and output produced 1:1
// (duration held); only the PITCH changes — an octave up plays the same wall-clock length
// as the root note, unlike the Varispeed `readPos_ += ratio_` resample path.
//
// WHY A HAND-ROLLED PURE MODULE, NOT WDL (S16-F2, decided at build). The spec's lean was
// route (a) `WDL_SimplePitchShifter`. But its include chain
// (simple_pitchshift.h -> queue.h -> heapbuf.h -> wdltypes.h) does `#ifdef _WIN32 ->
// #include <windows.h>` unconditionally, which CANNOT enter the pure sampler_core module
// (CLAUDE.md load-bearing split: NO vendor/host/SDK types; sampler_core_tests links neither
// SDK and compiles outside the DAW). So the Preserve DSP lands as route (b): a house-native
// pure module alongside peaks / wav_trim, CTest-testable, RT-disciplined. Same
// PitchEngine::Preserve contract behind the seam — if WDL is ever preferred it swaps in at
// the SHELL, never in the pure core.
//
// PURE MODULE: NO VST3, NO REAPER, NO SWELL, NO vendor/ includes. Standard library only.
// Shares the `AudioSample` float alias from peaks (the one house precedent — sampler_core /
// wav_trim do the same).
//
// RT DISCIPLINE (S16 hard constraint). `configure()` sizes the ring ONCE (off the audio
// thread, at voice allocation). `warm()` pre-fills the ring with silence so steady-state
// latency is reached before the first real sample (no cold-start click). `process()` does
// NO allocation and NO locks — it reads/writes the pre-sized ring only. All state is plain
// value fields, so a voice owning one by value costs a fixed ring buffer per channel.

#include <cstddef>
#include <cstdint>
#include <vector>

#include "peaks.h"  // AudioSample (float)

namespace reasampler {

// A per-channel time-domain OLA pitch shifter. One instance transposes ONE channel; a stereo
// voice owns two (or a stereo-aware wrapper) — the algorithm is per-sample and channel-count
// agnostic, matching the S7 "one read head, per-channel value" idiom of the core.
//
// The default-constructed shifter is INERT: with no configure() it passes input through
// unchanged (shift ratio 1.0, empty ring), so a Varispeed voice that never touches it is
// byte-identical to the pre-S16 engine.
class PitchShifter {
public:
    // Size the delay ring for `windowFrames` (the OLA grain length) and prepare the two
    // read taps a half-window apart. `windowFrames` <= 1 degrades to pass-through (no ring),
    // so a degenerate configure never divides by zero or wraps a zero span. Called OFF the
    // audio thread (allocates). Resets all running state. A larger window = smoother on large
    // transpositions but more latency; the shell picks it from the Preserve quality setting.
    void configure(std::int64_t windowFrames);

    // Pre-fill the ring with silence (one full window of zero writes) so the read taps reach
    // steady state before the first real sample. Removes the cold-start seam (the S16 "onset
    // click absent" requirement) — call once at voice allocation after configure(). No-op when
    // unconfigured (pass-through needs no warm-up).
    void warm();

    // The pitch shift ratio: 2^((note - root)/12) plus any per-frame pitch-envelope bias.
    // 1.0 = no shift (pass-through-equivalent output). Set per frame is fine (cheap); the tap
    // advance simply uses the current value. Values <= 0 are ignored (kept at the last valid
    // ratio) so a bad input never runs the taps backward or stalls them.
    void setShiftRatio(double ratio);

    // Transform ONE input frame into ONE output frame (duration-preserving: 1 in, 1 out).
    // RT-safe: reads/writes the pre-sized ring only, no allocation, no lock. When unconfigured
    // (window <= 1) returns `in` unchanged (pass-through). Otherwise writes `in` at the write
    // head, reads the two half-window-offset taps advancing at the shift ratio, crossfades
    // them by the write-head-relative distance (equal-power), and advances both heads by one.
    AudioSample process(AudioSample in);

    // Reset running state to a freshly-warmed-equivalent silence (ring zeroed, heads re-seeded)
    // WITHOUT reallocating — for voice reuse without a re-configure. Keeps the current window.
    void reset();

    // True once configure() sized a real ring (window > 1). A pass-through shifter is false.
    bool configured() const { return window_ > 1; }

    std::int64_t window() const { return window_; }

private:
    std::vector<AudioSample> ring_;  // delay line, length `window_` (channel-local)
    std::int64_t window_ = 0;        // OLA grain length in frames; <= 1 = pass-through
    std::int64_t writePos_ = 0;      // integer write head into the ring (source rate)
    double readPos_ = 0.0;           // fractional read head (advances at shift ratio)
    double ratio_ = 1.0;             // current shift ratio (>0)
};

}  // namespace reasampler