Implements the content-derived spectral-peak signature from JRay-public-server/SPEC.md §3 so a truth file is self-identifying: 120 s window centred on the media midpoint, mono at 11025 Hz, 4096/1024 Hann STFT, 32 log-spaced bins over 300-3000 Hz, one byte per frame (5-bit peak band + 2-bit energy class), base64, `v1:` prefix. Audio decode is a second stream from the FFmpeg libraries the pipeline already links for video; libswresample is added to the existing ffmpeg_libs interface target. The FFT is written out rather than pulled from a library for the same reason the plugin vendors one: the output has to be bit-identical across two languages, so a dependency whose version could change the numerics is a liability. The server spec fixes the geometry but not enough to reproduce a byte stream — Hann periodicity, band aggregation, the energy-class definition, tie-breaking and the base64 alphabet are all unconstrained by it. Those are pinned in audio_signature.hpp and mirrored in the golden fixture, so the plugin can be implemented from the fixture alone. IR-005: tests/fixtures/audio/ carries a deterministic 120 s tone (FLAC — lossless, so identical PCM to the WAV make_fixture.py emits, and 3.5x smaller in git) plus the signature it must produce, the decoded-PCM checksum and the full parameter contract. That directory is the artefact shared with the plugin repo; the PCM checksum is separate from the signature so a codec-level difference is distinguishable from a DSP one. IR-007: media under 120 s emits no signature. Same for a file with no audio stream or one that will not open — UR-9 is an enhancement and must never be able to break a fetch. Verified against an independent Python reference implementation: same bytes. All 32 bands and all 4 energy classes appear in the golden vector, and the window-centring test wraps the fixture in 90 s of silence either side and requires the golden value back. Not wired into the truth-file output yet — that is the schema_version bump under IR-002/IR-003 and is deliberately out of scope here. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
360 lines
16 KiB
C++
360 lines
16 KiB
C++
// Unit tests for the JRay v1 audio signature (src/audio_signature.*).
|
|
//
|
|
/// TRACES: UT-101, UT-102, UT-103, UT-104 | IR-004, IR-005, IR-007, IR-008
|
|
//
|
|
// The headline test is the golden vector: a deterministic tone fixture checked
|
|
// into tests/fixtures/audio/ together with the signature it must produce. That
|
|
// fixture is the artefact shared with the jRay plugin repo, and it is what
|
|
// makes "both producers agree bit-for-bit" a checked claim rather than an
|
|
// assertion (IR-005).
|
|
//
|
|
// GPU-free, model-free, no network. Pure CPU DSP plus an FFmpeg decode of a
|
|
// 585 KB file — which is precisely why this is the right cross-repo check: it
|
|
// runs anywhere, including the N100 CI host.
|
|
#include <catch2/catch_test_macros.hpp>
|
|
#include <catch2/matchers/catch_matchers_floating_point.hpp>
|
|
|
|
#include "audio_signature.hpp"
|
|
|
|
#include <nlohmann/json.hpp>
|
|
|
|
#include <cmath>
|
|
#include <cstdint>
|
|
#include <filesystem>
|
|
#include <fstream>
|
|
#include <stdexcept>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
using namespace sae::audio;
|
|
namespace fs = std::filesystem;
|
|
|
|
namespace {
|
|
|
|
const std::string kFixtureDir = SAE_TEST_FIXTURES_DIR "/audio";
|
|
const std::string kGoldenPath = kFixtureDir + "/jray_audio_v1_golden.json";
|
|
const std::string kMediaPath = kFixtureDir + "/jray_audio_v1_tone.flac";
|
|
|
|
const nlohmann::json& golden() {
|
|
static const nlohmann::json j = [] {
|
|
std::ifstream in(kGoldenPath);
|
|
if (!in.good())
|
|
throw std::runtime_error("golden fixture not found: " + kGoldenPath);
|
|
nlohmann::json parsed;
|
|
in >> parsed;
|
|
return parsed;
|
|
}();
|
|
return j;
|
|
}
|
|
|
|
std::uint64_t hex64(const std::string& s) {
|
|
return std::stoull(s, nullptr, 16);
|
|
}
|
|
|
|
// The fixture is 120 s of audio: decoding and signing it is the expensive part
|
|
// of this file, so both results are computed once and shared. Every test below
|
|
// still asserts against the on-disk golden values, not against each other.
|
|
const std::optional<std::vector<float>>& fixture_window() {
|
|
static const std::optional<std::vector<float>> w = decode_centre_window(kMediaPath);
|
|
return w;
|
|
}
|
|
|
|
const std::optional<std::string>& fixture_signature() {
|
|
static const std::optional<std::string> s = compute_signature(kMediaPath);
|
|
return s;
|
|
}
|
|
|
|
// ── Minimal WAV writer, so the short-media and resample cases need no fixture ─
|
|
// 16-bit PCM, interleaved.
|
|
struct TempWav {
|
|
fs::path path;
|
|
explicit TempWav(const std::string& name)
|
|
: path(fs::temp_directory_path() / ("sae_audio_test_" + name + ".wav")) {}
|
|
~TempWav() { std::error_code ec; fs::remove(path, ec); }
|
|
|
|
void write(const std::vector<std::int16_t>& samples, int rate, int channels) const {
|
|
const std::uint32_t bytes = static_cast<std::uint32_t>(samples.size() * 2);
|
|
const std::uint32_t byte_rate = static_cast<std::uint32_t>(rate * channels * 2);
|
|
std::ofstream out(path, std::ios::binary);
|
|
auto u32 = [&](std::uint32_t v) { out.write(reinterpret_cast<const char*>(&v), 4); };
|
|
auto u16 = [&](std::uint16_t v) { out.write(reinterpret_cast<const char*>(&v), 2); };
|
|
out.write("RIFF", 4); u32(36 + bytes); out.write("WAVE", 4);
|
|
out.write("fmt ", 4); u32(16); u16(1); u16(static_cast<std::uint16_t>(channels));
|
|
u32(static_cast<std::uint32_t>(rate)); u32(byte_rate);
|
|
u16(static_cast<std::uint16_t>(channels * 2)); u16(16);
|
|
out.write("data", 4); u32(bytes);
|
|
out.write(reinterpret_cast<const char*>(samples.data()), bytes);
|
|
}
|
|
};
|
|
|
|
// A plain 1 kHz tone, mono, at the signature's own rate.
|
|
std::vector<std::int16_t> tone(double seconds, int rate = kSampleRate) {
|
|
const std::size_t n = static_cast<std::size_t>(std::llround(seconds * rate));
|
|
std::vector<std::int16_t> s(n);
|
|
for (std::size_t i = 0; i < n; ++i)
|
|
s[i] = static_cast<std::int16_t>(std::llround(
|
|
20000.0 * std::sin(2.0 * 3.14159265358979323846 * 1000.0 * double(i) / rate)));
|
|
return s;
|
|
}
|
|
|
|
std::vector<std::uint8_t> base64_decode(const std::string& in) {
|
|
auto val = [](char c) -> int {
|
|
if (c >= 'A' && c <= 'Z') return c - 'A';
|
|
if (c >= 'a' && c <= 'z') return c - 'a' + 26;
|
|
if (c >= '0' && c <= '9') return c - '0' + 52;
|
|
if (c == '+') return 62;
|
|
if (c == '/') return 63;
|
|
return -1;
|
|
};
|
|
std::vector<std::uint8_t> out;
|
|
std::uint32_t acc = 0;
|
|
int bits = 0;
|
|
for (char c : in) {
|
|
const int v = val(c);
|
|
if (v < 0) continue; // '=' padding
|
|
acc = (acc << 6) | static_cast<std::uint32_t>(v);
|
|
bits += 6;
|
|
if (bits >= 8) {
|
|
bits -= 8;
|
|
out.push_back(static_cast<std::uint8_t>((acc >> bits) & 0xFF));
|
|
}
|
|
}
|
|
return out;
|
|
}
|
|
|
|
} // namespace
|
|
|
|
// ── UT-101 — the golden vector ──────────────────────────────────────────────
|
|
|
|
/// TRACES: UT-101 | IR-004, IR-005, IR-008
|
|
TEST_CASE("signature of the golden fixture matches the recorded value exactly",
|
|
"[audio_signature][golden]") {
|
|
REQUIRE(fs::exists(kMediaPath));
|
|
const std::optional<std::string>& sig = fixture_signature();
|
|
REQUIRE(sig.has_value());
|
|
CHECK(*sig == golden()["signature"].get<std::string>());
|
|
}
|
|
|
|
/// TRACES: UT-101 | IR-005
|
|
TEST_CASE("decoded centre window matches the recorded PCM checksum",
|
|
"[audio_signature][golden]") {
|
|
// Checked separately from the signature so a codec-level difference is
|
|
// distinguishable from a DSP-level one: if this passes and the signature
|
|
// test fails, the DSP diverged; if this fails, the decode did.
|
|
const std::optional<std::vector<float>>& mono = fixture_window();
|
|
REQUIRE(mono.has_value());
|
|
CHECK(mono->size() == golden()["decoded_window"]["samples"].get<std::size_t>());
|
|
CHECK(fnv1a64(mono->data(), mono->size() * sizeof(float)) ==
|
|
hex64(golden()["decoded_window"]["f32le_fnv1a64"].get<std::string>()));
|
|
}
|
|
|
|
/// TRACES: UT-101 | IR-004
|
|
TEST_CASE("log-spaced band table matches the recorded one", "[audio_signature][golden]") {
|
|
// The band->FFT-bin table is the part of the construction most likely to
|
|
// drift between two implementations, so it is pinned independently of the
|
|
// signature it produces.
|
|
const auto& tbl = band_fft_bins();
|
|
const auto& want = golden()["band_fft_bins"];
|
|
REQUIRE(want.size() == tbl.size());
|
|
for (std::size_t b = 0; b < tbl.size(); ++b) {
|
|
CHECK(tbl[b].first == want[b][0].get<int>());
|
|
CHECK(tbl[b].second == want[b][1].get<int>());
|
|
CHECK(tbl[b].second > tbl[b].first); // no empty band
|
|
if (b) CHECK(tbl[b].first == tbl[b - 1].second); // contiguous, no overlap
|
|
}
|
|
}
|
|
|
|
/// TRACES: UT-101 | IR-004, IR-008
|
|
TEST_CASE("signature is well-formed: v1 prefix, 1288 frames, structural bytes",
|
|
"[audio_signature][golden]") {
|
|
const std::optional<std::string>& sig = fixture_signature();
|
|
REQUIRE(sig.has_value());
|
|
|
|
// IR-008 — the signature carries its own version, separate from
|
|
// schema_version, so a future DSP change is detectable rather than silently
|
|
// producing non-matching signatures.
|
|
REQUIRE(sig->rfind(kVersionPrefix, 0) == 0);
|
|
|
|
const std::vector<std::uint8_t> bytes = base64_decode(sig->substr(3));
|
|
CHECK(bytes.size() == kExpectedFrames);
|
|
CHECK(bytes.size() == golden()["frame_count"].get<std::size_t>());
|
|
|
|
// The server validates this structure on upload (server SPEC §3): each byte
|
|
// is a 5-bit band index plus a 2-bit energy class, so bit 7 is always clear
|
|
// and arbitrary bytes are invalid. That is what keeps the field from being
|
|
// a payload channel.
|
|
bool bands_seen[kNumBands] = {};
|
|
bool classes_seen[4] = {};
|
|
for (std::uint8_t b : bytes) {
|
|
REQUIRE((b & 0x80) == 0);
|
|
bands_seen[(b >> 2) & 0x1F] = true;
|
|
classes_seen[b & 0x03] = true;
|
|
}
|
|
// The fixture is built to exercise the whole output alphabet — if it ever
|
|
// stops doing so, the golden vector has become a weaker check than it looks.
|
|
for (bool seen : bands_seen) CHECK(seen);
|
|
for (bool seen : classes_seen) CHECK(seen);
|
|
}
|
|
|
|
// ── UT-102 — IR-007, media shorter than the window ──────────────────────────
|
|
|
|
/// TRACES: UT-102 | IR-007
|
|
TEST_CASE("media shorter than 120 s emits no signature", "[audio_signature][short]") {
|
|
// The window runtime/2 ± 60 s underflows, so there is no signature and no
|
|
// sync offset downstream. Both producers must apply the identical rule or
|
|
// they diverge on exactly the short items most likely to be misidentified.
|
|
SECTION("30 s") {
|
|
TempWav w("short30");
|
|
w.write(tone(30.0), kSampleRate, 1);
|
|
CHECK_FALSE(compute_signature(w.path.string()).has_value());
|
|
CHECK_FALSE(decode_centre_window(w.path.string()).has_value());
|
|
}
|
|
SECTION("just under the boundary") {
|
|
TempWav w("short11999");
|
|
w.write(tone(119.99), kSampleRate, 1);
|
|
CHECK_FALSE(compute_signature(w.path.string()).has_value());
|
|
}
|
|
}
|
|
|
|
/// TRACES: UT-102 | IR-007
|
|
TEST_CASE("media of exactly 120 s emits a full-length signature",
|
|
"[audio_signature][short]") {
|
|
TempWav w("exact120");
|
|
w.write(tone(120.0), kSampleRate, 1);
|
|
const std::optional<std::string> sig = compute_signature(w.path.string());
|
|
REQUIRE(sig.has_value());
|
|
CHECK(base64_decode(sig->substr(3)).size() == kExpectedFrames);
|
|
}
|
|
|
|
/// TRACES: UT-102 | IR-007
|
|
TEST_CASE("unreadable media degrades to no signature rather than failing",
|
|
"[audio_signature][short]") {
|
|
// UR-9 is an enhancement and must never be able to break a fetch.
|
|
CHECK_FALSE(compute_signature("/nonexistent/definitely-not-here.mkv").has_value());
|
|
}
|
|
|
|
/// TRACES: UT-102 | IR-004
|
|
TEST_CASE("the window is taken from the centre, not the head",
|
|
"[audio_signature][centre]") {
|
|
// Sampling from the centre is the whole reason the construction avoids the
|
|
// head and tail (logos, cold opens, credits), so it needs its own check:
|
|
// wrap the fixture's own 120 s in 90 s of silence either side and the
|
|
// signature of the 300 s file must be the golden value, byte for byte.
|
|
// Nothing else pins the seek offset — a head-anchored window would pass
|
|
// every other test in this file.
|
|
const std::optional<std::vector<float>>& mono = fixture_window();
|
|
REQUIRE(mono.has_value());
|
|
|
|
const std::size_t pad = 90 * kSampleRate;
|
|
std::vector<std::int16_t> padded(pad * 2 + mono->size(), 0);
|
|
for (std::size_t i = 0; i < mono->size(); ++i)
|
|
padded[pad + i] = static_cast<std::int16_t>(std::llround(double((*mono)[i]) * 32768.0));
|
|
|
|
TempWav w("centred300");
|
|
w.write(padded, kSampleRate, 1);
|
|
|
|
const std::optional<std::string> sig = compute_signature(w.path.string());
|
|
REQUIRE(sig.has_value());
|
|
CHECK(*sig == golden()["signature"].get<std::string>());
|
|
}
|
|
|
|
// ── UT-103 — downmix and resample ───────────────────────────────────────────
|
|
|
|
/// TRACES: UT-103 | IR-004
|
|
TEST_CASE("stereo, non-native sample rate yields the same peak-bin sequence",
|
|
"[audio_signature][resample]") {
|
|
// The golden fixture is already mono at 11025 Hz so the golden vector does
|
|
// not depend on the resampler's version. This case exercises the path that
|
|
// real media takes — downmix plus resample — by rebuilding the fixture's own
|
|
// audio as 22050 Hz stereo and checking the peak bins survive it.
|
|
const std::optional<std::vector<float>>& mono = fixture_window();
|
|
REQUIRE(mono.has_value());
|
|
|
|
std::vector<std::int16_t> stereo;
|
|
stereo.reserve(mono->size() * 4);
|
|
for (float f : *mono) {
|
|
const auto s = static_cast<std::int16_t>(std::llround(double(f) * 32768.0));
|
|
stereo.push_back(s); stereo.push_back(s); // sample 1, L/R
|
|
stereo.push_back(s); stereo.push_back(s); // sample 2 (zero-order hold)
|
|
}
|
|
TempWav w("stereo22050");
|
|
w.write(stereo, 2 * kSampleRate, 2);
|
|
|
|
const std::optional<std::string> sig = compute_signature(w.path.string());
|
|
REQUIRE(sig.has_value());
|
|
|
|
const std::vector<std::uint8_t> got = base64_decode(sig->substr(3));
|
|
const std::vector<std::uint8_t> want =
|
|
base64_decode(golden()["signature"].get<std::string>().substr(3));
|
|
REQUIRE(got.size() == want.size());
|
|
|
|
std::size_t agree = 0;
|
|
for (std::size_t i = 0; i < got.size(); ++i)
|
|
agree += ((got[i] >> 2) == (want[i] >> 2)) ? 1 : 0;
|
|
// The server treats ≥ 0.85 as the `audio` match tier; this path scores 1.0
|
|
// in practice, and the margin is left for libswresample version drift.
|
|
CHECK(double(agree) / double(got.size()) >= 0.85);
|
|
}
|
|
|
|
// ── UT-104 — the pure DSP surface ───────────────────────────────────────────
|
|
|
|
/// TRACES: UT-104 | IR-004
|
|
TEST_CASE("pack_frames uses whole frames only", "[audio_signature][dsp]") {
|
|
CHECK(pack_frames(std::vector<float>(kFrameSize - 1, 0.f)).empty());
|
|
CHECK(pack_frames(std::vector<float>(kFrameSize, 0.f)).size() == 1);
|
|
CHECK(pack_frames(std::vector<float>(kFrameSize + kHopSize - 1, 0.f)).size() == 1);
|
|
CHECK(pack_frames(std::vector<float>(kFrameSize + kHopSize, 0.f)).size() == 2);
|
|
// The full 120 s window is 1288 frames — asserted as a constant rather than
|
|
// by running the DSP over 1.3 M zeros, which is the same claim for free.
|
|
CHECK(kWindowSamples == 1323000u);
|
|
CHECK(kExpectedFrames == 1288u);
|
|
CHECK_FALSE(signature_from_mono(std::vector<float>(kFrameSize - 1, 0.f)).has_value());
|
|
}
|
|
|
|
/// TRACES: UT-104 | IR-004
|
|
TEST_CASE("a pure tone lands in the band that contains it", "[audio_signature][dsp]") {
|
|
// 1000 Hz sits in log-band floor(32 * log10(1000/300)) = 16.
|
|
const int expect = static_cast<int>(std::floor(
|
|
kNumBands * std::log10(1000.0 / kBandLoHz) / std::log10(kBandHiHz / kBandLoHz)));
|
|
std::vector<float> mono(kWindowSamples / 100);
|
|
for (std::size_t i = 0; i < mono.size(); ++i)
|
|
mono[i] = static_cast<float>(0.5 * std::sin(
|
|
2.0 * 3.14159265358979323846 * 1000.0 * double(i) / kSampleRate));
|
|
const std::vector<std::uint8_t> packed = pack_frames(mono);
|
|
REQUIRE_FALSE(packed.empty());
|
|
for (std::uint8_t b : packed) CHECK(((b >> 2) & 0x1F) == expect);
|
|
}
|
|
|
|
/// TRACES: UT-104 | IR-004
|
|
TEST_CASE("signature is invariant to overall gain", "[audio_signature][dsp]") {
|
|
// Loudness normalisation between two releases of the same cut must not
|
|
// change the signature — that is why the energy class is relative.
|
|
std::vector<float> a(kWindowSamples / 50);
|
|
for (std::size_t i = 0; i < a.size(); ++i) {
|
|
const double t = double(i) / kSampleRate;
|
|
a[i] = static_cast<float>(0.4 * std::sin(2.0 * 3.14159265358979323846 * 640.0 * t) +
|
|
0.2 * std::sin(2.0 * 3.14159265358979323846 * 1900.0 * t) *
|
|
std::sin(2.0 * 3.14159265358979323846 * 0.7 * t));
|
|
}
|
|
std::vector<float> b(a.size());
|
|
for (std::size_t i = 0; i < a.size(); ++i) b[i] = a[i] * 0.25f;
|
|
CHECK(pack_frames(a) == pack_frames(b));
|
|
}
|
|
|
|
/// TRACES: UT-104 | IR-004
|
|
TEST_CASE("base64 encoder matches the standard alphabet and padding",
|
|
"[audio_signature][dsp]") {
|
|
auto enc = [](const std::string& s) {
|
|
return base64_encode(reinterpret_cast<const std::uint8_t*>(s.data()), s.size());
|
|
};
|
|
CHECK(enc("") == "");
|
|
CHECK(enc("f") == "Zg==");
|
|
CHECK(enc("fo") == "Zm8=");
|
|
CHECK(enc("foo") == "Zm9v");
|
|
CHECK(enc("foob") == "Zm9vYg==");
|
|
CHECK(enc("fooba") == "Zm9vYmE=");
|
|
CHECK(enc("foobar") == "Zm9vYmFy");
|
|
const std::uint8_t all[] = {0xFB, 0xFF, 0xBF}; // exercises '+' and '/'
|
|
CHECK(base64_encode(all, 3) == "+/+/");
|
|
}
|