Files
mxaccess/analysis/scripts/summarize_dcerpc.py
T
Joseph Doherty fe2a6db786
rust / build / test / clippy / fmt (push) Has been cancelled
Initial project state: .NET reference, design, Rust port (M0+M1), evidence
Layout:
- src/                    .NET 10 x64 reference: MxNativeCodec, MxNativeClient,
                          MxAsbClient, probes, tests, harnesses. Executable spec.
- design/                 Architectural plan for the Rust port (M0–M6), error
                          model, protocol invariants, risks (R1–R16), adversarial
                          review log (review.md).
- rust/                   Rust workspace. M0 skeleton + M1 codec parity.
                          mxaccess-codec: 215 unit tests + 2 cross-implementation
                          parity tests (byte-identical against .NET reference).
                          Other crates are M0 stubs awaiting M2+.
- captures/               Frida + netsh + pcap evidence per CLAUDE.md
                          ("captures are evidence, not throwaway logs").
- analysis/               Decompiled C# (frida/proxy/decompiled-*),
                          Ghidra exports for native DLLs (`exports/` only —
                          working state at `projects/` and AVEVA's input
                          binaries at `input/` are gitignored).
- docs/                   Reverse-engineering reference docs.
- tools/                  Setup-LiveProbeEnv.ps1 (Infisical credential fetcher),
                          Compute-Crc.ps1 (.NET parity helper).
- .github/workflows/      Rust CI: fmt + build + test + clippy on Windows.
- LICENSE                 MIT (Joseph Doherty, 2026).

Verified:
- cargo test --workspace → 217 passed (215 unit + 2 .NET parity), 0 failed
- cargo clippy --workspace -- -D warnings → clean
- cargo fmt --all -- --check → clean
- cargo publish --dry-run -p mxaccess-codec → packages cleanly

Excluded from history (see .gitignore):
- **/bin, **/obj, **/target — build artifacts
- analysis/ghidra/projects/ — Ghidra working state (regenerable)
- analysis/ghidra/input/ — AVEVA proprietary DLLs (vendor IP)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 06:21:00 -04:00

75 lines
2.2 KiB
Python

from __future__ import annotations
import argparse
import csv
from collections import Counter
from pathlib import Path
HEADER = [
"capture",
"stream",
"packet_type",
"context_id",
"opnum",
"count",
"frag_lengths",
]
def summarize(path: Path) -> list[list[str]]:
rows: list[list[str]] = []
counts: Counter[tuple[str, str, str, str]] = Counter()
lengths: dict[tuple[str, str, str, str], Counter[str]] = {}
with path.open("r", encoding="utf-8-sig", newline="") as handle:
reader = csv.reader(handle, delimiter="\t")
for fields in reader:
if len(fields) < 10:
continue
stream = fields[2]
packet_type = fields[3]
context_id = fields[5]
opnum = fields[6]
frag_len = fields[8]
key = (stream, packet_type, context_id, opnum)
counts[key] += 1
lengths.setdefault(key, Counter())[frag_len] += 1
for key, count in sorted(counts.items(), key=lambda item: (-item[1], item[0])):
stream, packet_type, context_id, opnum = key
frag_lengths = ",".join(
f"{length}:{length_count}"
for length, length_count in sorted(lengths[key].items(), key=lambda item: (item[0], item[1]))
)
rows.append([path.parent.name, stream, packet_type, context_id, opnum, str(count), frag_lengths])
return rows
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument("dcerpc_tsv", type=Path, nargs="+")
parser.add_argument("--out", type=Path)
args = parser.parse_args()
output_rows = [HEADER]
for path in args.dcerpc_tsv:
output_rows.extend(summarize(path))
if args.out:
args.out.parent.mkdir(parents=True, exist_ok=True)
with args.out.open("w", encoding="utf-8", newline="") as handle:
writer = csv.writer(handle, delimiter="\t", lineterminator="\n")
writer.writerows(output_rows)
else:
writer = csv.writer(__import__("sys").stdout, delimiter="\t", lineterminator="\n")
writer.writerows(output_rows)
return 0
if __name__ == "__main__":
raise SystemExit(main())