Add test tooling: synthetic .sras generator and equivalence harness

tools/make_test_sras.py writes small v6 files with per-angle-varying geometry, distinct per-channel calibration, and deterministic waveform content (predictable FFT peak per pixel, predictable DC mean per pixel). tools/check_equivalence.py hashes DC/FFT/alignment outputs across channels, angles, bg-sub, pad factors, and thresholds. It imports from either the monolith or the split modules, so the same script captures both sides of a refactor. Hashes canonicalise to native float64 so a dtype or byte-order change that preserves values is not a false failure. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-30 23:25:45 -05:00
parent ed0eba4bae
commit 95c273dce5
3 changed files with 339 additions and 0 deletions
@@ -0,0 +1,142 @@
+#!/usr/bin/env python3
+"""Generate small synthetic .sras files for testing.
+
+Writes v6 files (per-angle geometry, ragged waveform blocks) matching
+scan_format.md, with deterministic pseudo-random waveform content so a test
+can compute expected DC/FFT images independently of the reader under test.
+
+Usage:
+    python tools/make_test_sras.py out.sras [--angles 3] [--seed 0]
+"""
+
+import argparse
+import struct
+from pathlib import Path
+
+import numpy as np
+
+HDR_FMT_V6 = ">4sBHfffffffIdBB"
+GEO_FMT_V6 = ">ffIH"
+
+# Per-angle (n_rows, n_frames) — deliberately different per angle so ragged
+# geometry handling is actually exercised.
+_GEOMETRY = [(5, 7), (4, 11), (6, 9), (3, 13), (7, 6)]
+
+_SAMPLE_RATE_HZ = 6.25e9
+_VELOCITY_MM_S = 20.0
+_LASER_FREQ_HZ = 1000.0
+_ROW_SPACING_MM = 0.05
+
+
+def _preamble(ymult_v: float, yoff_adc: float, yzero_v: float) -> bytes:
+    """A Tektronix WFMOutpre string in verbose (keyword) form — the reader
+    pulls YMULT/YOFF/YZERO out of it by name, so the keywords must be
+    present literally. YMULT/YZERO are in volts, as the scope reports them."""
+    return (
+        ":WFMOUTPRE:BYT_NR 1;BIT_NR 8;ENCDG BIN;BN_FMT RI;BYT_OR MSB;"
+        'WFID "Ch1, DC coupling";NR_PT 2500;PT_FMT Y;'
+        "XINCR 1.6000E-10;XZERO 0.0E0;XUNIT \"s\";"
+        f"YMULT {ymult_v:.6E};YOFF {yoff_adc:.6E};YZERO {yzero_v:.6E};"
+        'YUNIT "V"'
+    ).encode("utf-8")
+
+
+def build(n_angles: int, seed: int, samples_per_frame: int) -> tuple[bytes, dict]:
+    rng = np.random.default_rng(seed)
+    geom = [_GEOMETRY[a % len(_GEOMETRY)] for a in range(n_angles)]
+    n_ch = 3
+    bps = 1
+
+    angles_deg = np.linspace(0.0, 60.0, n_angles, dtype=np.float32)
+    # Distinct calibration per channel so a swapped-channel bug is visible.
+    cal = [
+        (1.5625e-3, -87.04, 0.0),
+        (2.0000e-3, -60.00, 1.0e-3),
+        (2.5000e-3, -40.00, -2.0e-3),
+    ]
+
+    out = bytearray()
+    out += struct.pack(
+        HDR_FMT_V6, b"SRAS", 6, n_angles,
+        0.0, 0.0, 1.0, 1.0, _ROW_SPACING_MM,
+        _VELOCITY_MM_S, _LASER_FREQ_HZ,
+        samples_per_frame, _SAMPLE_RATE_HZ, bps, n_ch,
+    )
+    out += angles_deg.astype(">f4").tobytes()
+
+    x_starts = []
+    for a, (n_rows, n_frames) in enumerate(geom):
+        x_start = -0.5 + 0.1 * a
+        x_starts.append(x_start)
+        out += struct.pack(GEO_FMT_V6, x_start, 1.0, n_frames, n_rows)
+
+    y_positions = []
+    for a, (n_rows, _) in enumerate(geom):
+        y = (0.2 * a + np.arange(n_rows) * _ROW_SPACING_MM).astype(np.float32)
+        y_positions.append(y)
+        out += y.astype(">f4").tobytes()
+
+    for ymult_v, yoff, yzero_v in cal:
+        p = _preamble(ymult_v, yoff, yzero_v)
+        out += struct.pack(">H", len(p)) + p
+
+    background = rng.integers(-8, 9, size=samples_per_frame, dtype=np.int8)
+    out += struct.pack(">I", samples_per_frame) + background.tobytes()
+
+    # Waveform data. CH1 gets a sinusoid at a per-pixel frequency so the FFT
+    # peak is predictable; CH3/CH4 get per-pixel DC levels so the mean is too.
+    t = np.arange(samples_per_frame)
+    waveforms = []
+    for a, (n_rows, n_frames) in enumerate(geom):
+        block = np.empty((n_rows, n_ch, n_frames, samples_per_frame), dtype=np.int8)
+        for r in range(n_rows):
+            for f in range(n_frames):
+                bin_idx = 3 + ((a + r + f) % 17)
+                phase = 2 * np.pi * bin_idx * t / samples_per_frame
+                block[r, 0, f] = np.clip(
+                    np.round(60 * np.sin(phase)), -128, 127).astype(np.int8)
+                block[r, 1, f] = np.int8((a * 7 + r * 3 + f) % 100 - 50)
+                block[r, 2, f] = np.int8((a * 5 + r * 11 + f * 2) % 120 - 60)
+        waveforms.append(block)
+        out += block.tobytes()
+
+    meta = {
+        "n_angles": n_angles,
+        "geometry": geom,
+        "angles_deg": angles_deg,
+        "x_starts": x_starts,
+        "y_positions": y_positions,
+        "cal": cal,
+        "background": background,
+        "waveforms": waveforms,
+        "samples_per_frame": samples_per_frame,
+        "sample_rate_hz": _SAMPLE_RATE_HZ,
+    }
+    return bytes(out), meta
+
+
+def write(path: Path, n_angles: int = 3, seed: int = 0,
+          samples_per_frame: int = 64) -> dict:
+    payload, meta = build(n_angles, seed, samples_per_frame)
+    path.write_bytes(payload)
+    return meta
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__)
+    p.add_argument("output")
+    p.add_argument("--angles", type=int, default=3)
+    p.add_argument("--seed", type=int, default=0)
+    p.add_argument("--spf", type=int, default=64, help="samples per frame")
+    args = p.parse_args()
+
+    out = Path(args.output)
+    meta = write(out, args.angles, args.seed, args.spf)
+    print(f"Wrote {out} ({out.stat().st_size:,} bytes)")
+    print(f"  angles   : {meta['n_angles']}")
+    print(f"  geometry : {meta['geometry']}")
+    print(f"  spf      : {meta['samples_per_frame']}")
+
+
+if __name__ == "__main__":
+    main()