series 4 codec work, inital decode success

2026-05-29 06:33:06 +00:00
parent 1bccc44b88
commit 9b71ead44b
20 changed files with 1578 additions and 76 deletions
@@ -0,0 +1,89 @@
+"""Reconnaissance helpers for cracking the Thor IDFW binary."""
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+REPO = Path(__file__).resolve().parents[1]
+sys.path.insert(0, str(REPO))
+
+TARGET = REPO / "tests/fixtures/THORDATA_example/THORDATA_example/UPMC Presby/UM11719/UM11719_20231219162723.IDFW"
+TXT = REPO / "tests/fixtures/THORDATA_example/THORDATA_example/UPMC Presby/UM11719/TXT/UM11719_20231219162723.IDFW.txt"
+
+
+def hex_at(buf: bytes, off: int, n: int = 32) -> str:
+    chunk = buf[off : off + n]
+    hexs = " ".join(f"{b:02x}" for b in chunk)
+    asc = "".join(chr(b) if 32 <= b < 127 else "." for b in chunk)
+    return f"{off:04x}: {hexs}  {asc}"
+
+
+def find_all(buf: bytes, needle: bytes) -> list[int]:
+    out: list[int] = []
+    i = 0
+    while True:
+        j = buf.find(needle, i)
+        if j < 0:
+            break
+        out.append(j)
+        i = j + 1
+    return out
+
+
+def load_sidecar_samples(path: Path) -> dict[str, list[float]]:
+    """Parse the txt sample table — Tran/Vert/Long/MicL."""
+    out = {"Tran": [], "Vert": [], "Long": [], "MicL": []}
+    in_block = False
+    for line in path.read_text(errors="replace").splitlines():
+        if not in_block:
+            if line.strip() == "Waveform Data Channels":
+                in_block = True
+            continue
+        if line.startswith("Waveform Data USB Channels"):
+            break
+        parts = line.split("\t")
+        # First row is the header "\tTran\tVert\tLong\tMicL"
+        if len(parts) >= 5 and parts[1] == "Tran":
+            continue
+        if len(parts) < 5:
+            continue
+        try:
+            out["Tran"].append(float(parts[1]))
+            out["Vert"].append(float(parts[2]))
+            out["Long"].append(float(parts[3]))
+            out["MicL"].append(float(parts[4]))
+        except ValueError:
+            continue
+    return out
+
+
+def main():
+    buf = TARGET.read_bytes()
+    samples = load_sidecar_samples(TXT)
+    print(f"file size: {len(buf)} bytes")
+    print(f"sample rows: Tran={len(samples['Tran'])} Vert={len(samples['Vert'])} Long={len(samples['Long'])} MicL={len(samples['MicL'])}")
+    print(f"first 6 Tran samples: {samples['Tran'][:6]}")
+    print(f"first 6 Vert samples: {samples['Vert'][:6]}")
+    print(f"first 6 Long samples: {samples['Long'][:6]}")
+    print(f"first 6 MicL samples: {samples['MicL'][:6]}")
+
+    print()
+    print("=== BW magic '00 02 00' positions ===")
+    hits = find_all(buf, b"\x00\x02\x00")
+    print(f"{len(hits)} hits")
+    for h in hits[:20]:
+        print(hex_at(buf, h, 24))
+
+    print()
+    print("=== '40 02' segment-header positions ===")
+    hits = find_all(buf, b"\x40\x02")
+    print(f"{len(hits)} hits")
+    for h in hits:
+        ctx_pre = buf[max(0, h - 4): h].hex()
+        ctx_post = buf[h: h + 20].hex()
+        # Show byte preceding to help identify real headers vs casual occurrences
+        print(f"  0x{h:04x}  pre={ctx_pre}  post={ctx_post}")
+
+
+if __name__ == "__main__":
+    main()