123 lines
6.9 KiB
C++
123 lines
6.9 KiB
C++
#pragma once
|
|
// peaks — waveform min/max envelope (thumbnail) computation from raw interleaved
|
|
// PCM. We compute our own thumbnails from the captured file rather than depending
|
|
// on REAPER's peak API: we own the file format, so this is simpler, testable, and
|
|
// dependency-free. A future bank panel (M5) calls this at whatever bin resolution
|
|
// the panel width dictates and draws one min/max envelope per channel.
|
|
//
|
|
// PURE MODULE (CLAUDE.md §load-bearing split): NO REAPER types, NO SWELL, NO
|
|
// vendor/ includes. Standard library only. Builds and unit-tests without REAPER.
|
|
|
|
#include <cstddef>
|
|
#include <vector>
|
|
|
|
namespace reasampler {
|
|
|
|
// Canonical in-memory audio-sample type. `float` is REAPER's native audio buffer
|
|
// format (its render/PCM_source callbacks hand back interleaved 32-bit float), so
|
|
// peaks consumes that directly with no lossy conversion. If a capture ever lands
|
|
// as a different depth, the caller converts to float at the boundary — the
|
|
// thumbnail core stays single-typed.
|
|
//
|
|
// NAMED AudioSample, not `Sample`: `reasampler::Sample` is already bank_model's
|
|
// metadata struct. A `using Sample = float` here would collide at namespace scope
|
|
// wherever both headers are visible (the bank_panel module includes both). The
|
|
// audio-domain name also reads more precisely — this is one PCM sample value.
|
|
using AudioSample = float;
|
|
|
|
// One bin of a channel's envelope: the extremes of every sample that fell in it.
|
|
// min <= max always. For an empty bin (more bins than frames), both are 0.
|
|
struct MinMax {
|
|
AudioSample min = 0.0f;
|
|
AudioSample max = 0.0f;
|
|
|
|
bool operator==(const MinMax& o) const { return min == o.min && max == o.max; }
|
|
};
|
|
|
|
// One channel's envelope: exactly `binCount` bins, in time order.
|
|
using ChannelEnvelope = std::vector<MinMax>;
|
|
|
|
// Per-channel envelopes: outer index is channel (channelCount entries, order
|
|
// preserved — never mixed or folded), inner is that channel's bins.
|
|
using Envelope = std::vector<ChannelEnvelope>;
|
|
|
|
// Computes a per-channel min/max envelope from interleaved PCM.
|
|
//
|
|
// interleaved frame-interleaved samples: [f0c0, f0c1, ..., f1c0, f1c1, ...].
|
|
// Size must be >= frameCount * channelCount; extra is ignored.
|
|
// channelCount channels per frame (the stride). Each channel is enveloped
|
|
// INDEPENDENTLY — no averaging, no stereo fold (precision
|
|
// invariant: channel count preserved).
|
|
// frameCount frames (samples-per-channel) to consider.
|
|
// binCount requested bins per channel. Honored exactly for any frameCount.
|
|
//
|
|
// Frame->bin partition: frames are split into `binCount` contiguous spans as
|
|
// evenly as possible; when frameCount does not divide evenly, the remainder is
|
|
// spread one-frame-per-bin across the earliest bins (ceil/floor split), so the
|
|
// tail is never dropped and no bin reads out of bounds. When binCount > frameCount
|
|
// the trailing empty bins are {0, 0}.
|
|
//
|
|
// Defined behavior for degenerate input (no UB, no throw):
|
|
// binCount == 0 -> per channel: an empty bin vector.
|
|
// channelCount == 0 -> an empty envelope (no channels).
|
|
// frameCount == 0 -> per channel: binCount bins, all {0, 0}.
|
|
Envelope computeEnvelope(const std::vector<AudioSample>& interleaved,
|
|
std::size_t channelCount,
|
|
std::size_t frameCount,
|
|
std::size_t binCount);
|
|
|
|
// The merged min/max for display column `col` (0-based, of `columnCount` total columns)
|
|
// of a pre-computed per-bin ChannelEnvelope: the true extremes of every bin that projects
|
|
// to that column. This is the display-side collapse of an envelope computed at HIGHER
|
|
// resolution than the drawn width (oversampled bins -> per-pixel-column min/max), so a
|
|
// steep transient whose adjacent bins hold disjoint spans (e.g. {0.9,1.0} then
|
|
// {-1.0,-0.9}) renders as one gap-free vertical span instead of two separated dots.
|
|
//
|
|
// Bin->column mapping mirrors computeEnvelope's half-open partition:
|
|
// column col owns bins [col*nbins/columnCount, (col+1)*nbins/columnCount).
|
|
// When that range is empty (more columns than bins), the enclosing bin
|
|
// (col*nbins/columnCount) fills the column — so no column is left empty and no bin is
|
|
// ever dropped. columnCount <= 0 or bins.empty() returns {0, 0}; `col` is clamped to
|
|
// [0, columnCount-1]. Pure.
|
|
MinMax columnMinMax(const ChannelEnvelope& bins, int columnCount, int col);
|
|
|
|
// Sentinel returned by lastFrameAboveThreshold when NO frame in the scanned range
|
|
// peaks above the threshold (pure silence at that level). SIZE_MAX is unambiguous:
|
|
// no valid frame index can equal it (a real index is < frameCount <= SIZE_MAX for
|
|
// any allocatable buffer), so the caller tests `== kNoFrameAboveThreshold` cleanly.
|
|
inline constexpr std::size_t kNoFrameAboveThreshold =
|
|
static_cast<std::size_t>(-1);
|
|
|
|
// Scans interleaved PCM BACKWARD for the last frame whose per-frame peak (the max
|
|
// absolute value across all channels of that frame — NO stereo fold, just the
|
|
// loudest channel that frame) exceeds `linearThreshold`, returning that frame index.
|
|
// Returns kNoFrameAboveThreshold if no frame exceeds it (or on degenerate input).
|
|
//
|
|
// This is the boundary primitive behind the realtime tail's decay-scan trim
|
|
// (docs/product/capture-tail.md §The realtime path): the recorded tail window is
|
|
// scanned back from the end for the last frame still above -72 dB, and the file is
|
|
// truncated one frame past it. Deliberately a separate primitive from
|
|
// computeEnvelope — that answers "the min/max envelope over bins" (a thumbnail),
|
|
// this answers "the last frame above a level" (a boundary). Bending the bin-oriented
|
|
// envelope to a frame-exact boundary question is a worse fit (spec §option a).
|
|
//
|
|
// interleaved frame-interleaved samples: [f0c0, f0c1, ..., f1c0, f1c1, ...].
|
|
// Must hold >= frameCount * channelCount; extra is ignored, and a
|
|
// short buffer is clamped to what it actually holds (no OOB read).
|
|
// channelCount channels per frame (the stride). The per-frame test is the max
|
|
// |sample| over these channels — the frame is "above" if its
|
|
// loudest channel is above the threshold.
|
|
// frameCount frames to consider (the scan starts at the last of these).
|
|
// linearThreshold the comparison level as a LINEAR amplitude ratio (e.g. the
|
|
// -72 dB ratio from render_settings::autoTrimEndRatio), NOT dB.
|
|
// A frame counts as above when its peak is STRICTLY > this.
|
|
//
|
|
// Pure, stdlib-only, unit-tested (a synthetic decaying ramp, silence, all-above,
|
|
// and degenerate inputs) so the trim boundary math is locked outside the DAW.
|
|
std::size_t lastFrameAboveThreshold(const std::vector<AudioSample>& interleaved,
|
|
std::size_t channelCount,
|
|
std::size_t frameCount,
|
|
AudioSample linearThreshold);
|
|
|
|
} // namespace reasampler
|