histsdk/scripts/decode-rename-capture.py

"""Decode the RenameTags WCF request/response (HCAL R1.10).

Reads the chained WriteMessage+ReadMessage capture produced by scripts/Capture-RenameTags.ps1
and locates the rename exchange. Rename maps to the generic job framework:

  StJb (StartJob): WriteMessage carries op "StJb" + a string handle + the rename jobBuffer
                   (the (old,new) name pairs). ReadMessage carries the returned jobId string.
  GtJb (GetJobStatus): WriteMessage carries op "GtJb" + handle + jobId. ReadMessage carries
                   the job-status buffer.

We flag bodies by the StJb/GtJb op and by the sandbox names, then dump the buffers so the
jobBuffer layout (batch count + old/new UTF-16 framing) can be read off directly.

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-rename"
CAP = CAPDIR / "rename-capture-latest.ndjson"

# Sandbox names used by the default capture run (not secret).
FROM = "RetestSdkWriteRenameSrc"
TO = "RetestSdkWriteRenameDst"
OP_STJB = b"StJb"
OP_GTJB = b"GtJb"


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-RenameTags.ps1 first.")
        return 1

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

    from_u16, to_u16 = FROM.encode("utf-16-le"), TO.encode("utf-16-le")
    from_a, to_a = FROM.encode("ascii"), TO.encode("ascii")

    print(f"== {len(records)} MDAS bodies captured ==")
    for idx, rec in enumerate(records):
        body = base64.b64decode(rec["Base64"])
        flags = []
        if OP_STJB in body:
            flags.append("StJb")
        if OP_GTJB in body:
            flags.append("GtJb")
        if from_u16 in body or from_a in body:
            flags.append("FROM")
        if to_u16 in body or to_a in body:
            flags.append("TO")
        print(f"  [{idx:02d}] {rec.get('Phase'):26s} len={len(body):5d}  {','.join(flags)}")

    def find(predicate):
        hits = []
        for idx, rec in enumerate(records):
            body = base64.b64decode(rec["Base64"])
            if predicate(rec, body):
                hits.append((idx, rec, body))
        return hits

    print("\n== StJb request(s): WriteMessage bodies tagged StJb ==")
    for idx, rec, body in find(lambda r, b: r.get("Phase") == "WCF.WriteMessage.Body" and OP_STJB in b):
        hexdump(f"[{idx}] StJb 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()

    print("\n== StJb / GtJb response(s) + GtJb request(s) ==")
    for idx, rec, body in find(lambda r, b: (OP_STJB in b or OP_GTJB in b) and r.get("Phase") == "WCF.ReadMessage.Body"):
        hexdump(f"[{idx}] {rec.get('Phase')}", body)
        print("  strings:", [s for _, s in ascii_strings(body)][:16])
        print()

    return 0


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