histsdk/scripts/decode-del-tep-capture.py

"""Decode the DeleteTagExtendedProperties (DelTep) WCF inBuff (HCAL R1.11 delete half).

Reads the Run-B capture produced by scripts/Capture-DeleteTagExtendedProperties.ps1 and dumps the
DelTep WriteMessage body so the delete-request framing (tag name + property names + the
delete-from-server flag) can be read off and compared to the AddTEx serializer.

Output is diagnostic. Sanitize before copying into docs/.
"""
import base64
import json
import sys
from pathlib import Path

REPO_ROOT = Path(__file__).resolve().parent.parent
CAPDIR = REPO_ROOT / "artifacts" / "reverse-engineering" / "instrumented-wcf-del-tep"
CAP = CAPDIR / "del-tep-capture-latest.ndjson"

TAG = "RetestSdkWriteDelTepSdk"
PROP = "SdkDelProp"
OP_DEL = b"DelTep"
OP_GET = b"GetTepByNm"


def hexdump(label, buf, base=0):
    print(f"=== {label}: {len(buf)} bytes ===")
    for off in range(0, len(buf), 16):
        c = buf[off:off + 16]
        hp = " ".join(f"{x:02X}" for x in c)
        ap = "".join(chr(x) if 32 <= x < 127 else "." for x in c)
        print(f"  {base + off:04X}  {hp:<48}  |{ap}|")
    print()


def ascii_strings(buf, minlen=3):
    out, cur, start = [], [], 0
    for i, x in enumerate(buf):
        if 32 <= x < 127:
            if not cur:
                start = i
            cur.append(chr(x))
        else:
            if len(cur) >= minlen:
                out.append((start, "".join(cur)))
            cur = []
    if len(cur) >= minlen:
        out.append((start, "".join(cur)))
    return out


def u16_strings(buf, minlen=3):
    out, i = [], 0
    while i < len(buf) - 1:
        j, chars = i, []
        while j < len(buf) - 1 and 32 <= buf[j] < 127 and buf[j + 1] == 0:
            chars.append(chr(buf[j]))
            j += 2
        if len(chars) >= minlen:
            out.append((i, "".join(chars)))
            i = j
        else:
            i += 1
    return out


def main() -> int:
    if not CAP.exists():
        print(f"Missing capture: {CAP}\nRun scripts/Capture-DeleteTagExtendedProperties.ps1 first.")
        return 1

    records = []
    for line in CAP.open(encoding="utf-8-sig"):
        if line.strip():
            records.append(json.loads(line))

    print(f"== {len(records)} MDAS bodies captured (Run B) ==")
    for idx, rec in enumerate(records):
        body = base64.b64decode(rec["Base64"])
        flags = []
        if OP_DEL in body:
            flags.append("DelTep")
        if OP_GET in body:
            flags.append("GetTepByNm")
        if TAG.encode("ascii") in body or TAG.encode("utf-16-le") in body:
            flags.append("TAG")
        if PROP.encode("ascii") in body or PROP.encode("utf-16-le") in body:
            flags.append("PROP")
        print(f"  [{idx:02d}] {rec.get('Phase'):26s} len={len(body):5d}  {','.join(flags)}")

    print("\n== DelTep request(s) ==")
    for idx, rec in enumerate(records):
        body = base64.b64decode(rec["Base64"])
        if rec.get("Phase") == "WCF.WriteMessage.Body" and OP_DEL in body:
            hexdump(f"[{idx}] DelTep WriteMessage", body)
            print("  UTF-16 strings:")
            for off, s in u16_strings(body):
                print(f"    0x{off:04X} {s!r}")
            print("  ASCII strings:")
            for off, s in ascii_strings(body):
                print(f"    0x{off:04X} {s!r}")
            print()
    return 0


if __name__ == "__main__":
    sys.exit(main())