Files
FacereDataset/tools/epro2/std/__main__.py
Knowit d11ca1d3be tools/epro2/std: fetch + decrypt Pro 2.x encrypted-external blobs
Pro 2.x stores some doc payloads (notably Taishan's PCB) externally at
modules.lceda.cn keyed by dataStrId, AES-256-GCM encrypted with the
iv/key fields stored alongside. Same crypto pattern as Pro 3.x EPRO2:
last 16 bytes are the GCM auth tag, rest is gzip(plaintext-op-stream).
The CDN doesn't require auth.

  - pro2_writer.fetch_encrypted_plaintext(): fetch + decrypt + gunzip,
    cache result at source/<uuid>.decrypted.txt so re-runs skip the
    network round-trip. Heavy imports (httpx, pycryptodome) are
    deferred to call-time so the pure-replay path doesn't pay for them.
  - pro2_writer.split_plaintext_by_doctype(): walk the multi-doc
    plaintext (Pro 2.x bundles N FOOTPRINTs + 1 PCB into one blob), yield
    (label, sub_text) per inner doc. Label = HEAD.uuid if present, else
    fallback `<kind>_<idx>`.
  - __main__._convert_pro2_encrypted(): for each sub-doc, write a
    synthetic inline-Pro-2.x JSON next to the original and re-route
    through write_pro2_doc — re-uses BBox / layers / objects-extraction
    instead of duplicating the logic. Output filename
    `<parent_uuid>__<sub_label>.json` makes the parent association
    visible.

Smoke (Taishan): 28 inline SCHs → 55 total. Decrypts:
  - one PCB blob (3.4 MB plaintext, 20267-object PCB + 25 FOOTPRINT
    sub-docs of 130-580 objects each)
  - one SCH-typed encrypted doc (1 sub-SCH of 891 objects)

86 unit tests still pass; new fetch/decrypt path is covered manually
via the smoke test rather than mocking httpx + AES.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-29 02:07:40 +08:00

292 lines
11 KiB
Python

"""CLI: dump EPRO2 docs to Std-shaped JSON files for downstream consumers.
The output is "Option 2" per the downstream colleague's spec: Std envelope
with a raw EPRO2 ``objects: {id: payload}`` dict in place of the usual
``shape[]`` tilde-string array. Their ~100-LoC adapter walks ``objects``
and dispatches by ``_type`` to build real Std shapes — see
``docs/sources/epro2_to_std_mapping.md`` for the OPTYPE → Std verb table.
Usage:
uv run python -m tools.epro2.std <project_dir> --all-pcb --out <dir>
uv run python -m tools.epro2.std <project_dir> --all-sch --out <dir>
uv run python -m tools.epro2.std <project_dir> --all --out <dir>
Output: flat ``<doc_uuid>.json`` per doc — mirrors Std's own data layout
so a downstream pipeline that already iterates ``source/*.json`` works
unchanged.
"""
from __future__ import annotations
import argparse
import json
import sys
from pathlib import Path
from ..replay import Project, replay_project
from .pcb_writer import write_pcb_std
from .pro2_writer import (
fetch_encrypted_plaintext,
split_plaintext_by_doctype,
write_pro2_doc,
)
from .sch_writer import write_sch_std
def _detect_pro2(project_dir: Path) -> tuple[bool, str]:
"""Return ``(is_pro2, editor_version)`` from manifest.json.
Pro 2.x and Pro 3.x EPRO2 share the manifest filename + per-doc-uuid
layout, but Pro 2.x sets ``editor_version`` to a 2.x string like
``"2.1.40"`` and stores documents as ``<uuid>.json`` (vs Pro 3.x's
``<uuid>.epro2``). The cheap test is just to read the editor_version
string — falls through to the existing EPRO2 path on any mismatch.
"""
mani_path = project_dir / "source" / "manifest.json"
if not mani_path.exists():
return (False, "")
try:
m = json.loads(mani_path.read_text(encoding="utf-8"))
except json.JSONDecodeError:
return (False, "")
ev = str(m.get("editor_version") or "")
return (ev.startswith("2."), ev)
def _dump(payload: dict, out_path: Path, project_uuid: str) -> None:
payload["result"]["puuid"] = project_uuid or ""
out_path.write_text(
json.dumps(payload, ensure_ascii=False, separators=(",", ":")),
encoding="utf-8",
)
def _convert_pcbs(proj: Project, out_dir: Path) -> int:
uuids = [u for u, d in proj.documents.items() if d.doc_type == "PCB"]
if not uuids:
return 0
print(f"PCB: dumping {len(uuids)} doc(s) → {out_dir}")
for u in uuids:
try:
payload = write_pcb_std(proj.documents[u])
except Exception as e: # noqa: BLE001
print(f" FAIL {u[:12]}: {e}", file=sys.stderr)
continue
_dump(payload, out_dir / f"{u}.json", proj.project_uuid or "")
s = getattr(write_pcb_std, "last_stats", None)
if s:
print(
f" {u[:12]}.json: objects={s.objects} layers={s.layers_emitted} "
f"BBox=({s.bbox_x:g},{s.bbox_y:g},{s.bbox_w:g},{s.bbox_h:g})"
)
return len(uuids)
def _convert_schs(proj: Project, out_dir: Path) -> int:
uuids = [u for u, d in proj.documents.items() if d.doc_type == "SCH_PAGE"]
if not uuids:
return 0
print(f"SCH: dumping {len(uuids)} doc(s) → {out_dir}")
for u in uuids:
try:
payload = write_sch_std(proj.documents[u])
except Exception as e: # noqa: BLE001
print(f" FAIL {u[:12]}: {e}", file=sys.stderr)
continue
_dump(payload, out_dir / f"{u}.json", proj.project_uuid or "")
s = getattr(write_sch_std, "last_stats", None)
if s:
print(
f" {u[:12]}.json: objects={s.objects} "
f"BBox=({s.bbox_x:g},{s.bbox_y:g},{s.bbox_w:g},{s.bbox_h:g})"
)
return len(uuids)
def _convert_pro2_encrypted(
json_path: Path, out_dir: Path,
project_uuid: str, editor_version: str, parent_uuid: str,
) -> int:
"""Try fetch + AES-256-GCM decrypt + gunzip the encrypted-external
blob, then split by DOCTYPE boundary into per-sub-doc JSONs.
Pro 2.x bundles N FOOTPRINTs + 1 PCB (or N SYMBOLs + 1 SCH) into one
blob; we emit each as a separate file named
``<parent_uuid>__<sub_label>.json`` so the parent association is
visible in the filename without colliding with other sources.
"""
plain = fetch_encrypted_plaintext(json_path)
if plain is None:
return 0
n = 0
for sub_label, sub_text in split_plaintext_by_doctype(plain):
# Re-route the inline path: build a synthetic Pro 2.x doc shape
# in a temp file so write_pro2_doc + its caching behave normally.
synth = {
"uuid": f"{parent_uuid}__{sub_label}",
"title": sub_label,
"docType": _doctype_from_first_line(sub_text),
"dataStr": sub_text,
}
# Write the synthetic JSON next to the original, with a name
# that won't collide with manifest entries.
synth_path = json_path.parent / f".synth__{parent_uuid}__{sub_label}.json"
synth_path.write_text(json.dumps(synth, ensure_ascii=False), encoding="utf-8")
try:
payload = write_pro2_doc(
synth_path, project_uuid=project_uuid,
editor_version_hint=editor_version,
)
finally:
synth_path.unlink(missing_ok=True)
if payload is None:
continue
out_name = f"{parent_uuid}__{sub_label}.json"
(out_dir / out_name).write_text(
json.dumps(payload, ensure_ascii=False, separators=(",", ":")),
encoding="utf-8",
)
s = getattr(write_pro2_doc, "last_stats", None)
if s:
print(
f" {parent_uuid[:12]}__{sub_label}: docType={synth['docType']} "
f"objects={s.objects}"
)
n += 1
return n
def _doctype_from_first_line(text: str) -> int:
"""Read the leading ``["DOCTYPE","KIND","x.y"]`` line and return the
Std docType code (1=SCH, 2=SYMBOL, 3=PCB, 4=FOOTPRINT, 5=DEVICE)."""
for line in text.splitlines():
line = line.strip()
if not line:
continue
try:
arr = json.loads(line)
except json.JSONDecodeError:
continue
if not (isinstance(arr, list) and arr and arr[0] == "DOCTYPE"):
continue
kind = arr[1] if len(arr) > 1 else ""
return {
"SCH": 1, "SYMBOL": 2, "PCB": 3, "FOOTPRINT": 4, "DEVICE": 5,
}.get(kind, 0)
return 0
def _convert_pro2(project_dir: Path, out_dir: Path,
editor_version: str, want_pcb: bool, want_sch: bool) -> int:
"""Pro 2.x path — read each <uuid>.json directly (no EPRO2 replay)
and run pro2_writer. The manifest tells us per-doc docType so we
can route to PCB/SCH filters without parsing dataStr first."""
mani_path = project_dir / "source" / "manifest.json"
m = json.loads(mani_path.read_text(encoding="utf-8"))
project_uuid = m.get("project_uuid") or project_dir.name
skipped_encrypted = 0
n = 0
print(f"Pro 2.x project (editor {editor_version}) → {out_dir}")
for entry in m["documents"]:
dt = entry.get("docType")
if dt == 3 and not want_pcb:
continue
if dt == 1 and not want_sch:
continue
if dt not in (1, 3):
continue
path = project_dir / entry["path"]
try:
payload = write_pro2_doc(
path, project_uuid=project_uuid, editor_version_hint=editor_version,
)
except Exception as e: # noqa: BLE001
print(f" FAIL {entry['doc_uuid'][:12]}: {e}", file=sys.stderr)
continue
if payload is None:
stats = getattr(write_pro2_doc, "last_stats", None)
if stats and stats.skipped_encrypted:
# Try fetching + decrypting from modules.lceda.cn. The blob
# bundles N FOOTPRINTs/SYMBOLs + 1 parent PCB/SCH; we emit
# one JSON per sub-doc.
m_n = _convert_pro2_encrypted(
path, out_dir, project_uuid, editor_version,
parent_uuid=entry["doc_uuid"],
)
if m_n > 0:
print(
f" decrypted {entry['doc_uuid'][:12]}: "
f"{m_n} sub-doc(s) emitted"
)
n += m_n
else:
print(
f" SKIP {entry['doc_uuid'][:12]}: encrypted-external "
f"and fetch/decrypt failed."
)
skipped_encrypted += 1
continue
out_path = out_dir / f"{entry['doc_uuid']}.json"
out_path.write_text(
json.dumps(payload, ensure_ascii=False, separators=(",", ":")),
encoding="utf-8",
)
s = getattr(write_pro2_doc, "last_stats", None)
if s:
print(
f" {entry['doc_uuid'][:12]}.json: docType={dt} "
f"objects={s.objects} BBox=({s.bbox_x:g},{s.bbox_y:g},"
f"{s.bbox_w:g},{s.bbox_h:g})"
)
n += 1
if skipped_encrypted:
print(
f" ({skipped_encrypted} encrypted-external doc(s) skipped — "
f"the source/<uuid>.json files still hold the dataStrId/iv/key "
f"so a future fetch+decrypt pass can recover them.)"
)
return n
def main(argv: list[str] | None = None) -> int:
ap = argparse.ArgumentParser(description="EPRO2 / Pro 2.x → EasyEDA Std-shaped JSON dump")
ap.add_argument("project_dir", type=Path)
g = ap.add_mutually_exclusive_group(required=True)
g.add_argument("--all-pcb", action="store_true", help="dump every PCB doc")
g.add_argument("--all-sch", action="store_true", help="dump every SCH_PAGE doc")
g.add_argument("--all", action="store_true", help="dump both PCB and SCH_PAGE docs")
ap.add_argument("--out", type=Path, default=Path("data/processed/std_json"))
args = ap.parse_args(argv)
args.out.mkdir(parents=True, exist_ok=True)
is_pro2, editor_version = _detect_pro2(args.project_dir)
if is_pro2:
n = _convert_pro2(
args.project_dir, args.out, editor_version,
want_pcb=args.all_pcb or args.all,
want_sch=args.all_sch or args.all,
)
if n == 0:
print("nothing to dump (no Pro 2.x SCH/PCB docs survived)", file=sys.stderr)
return 1
return 0
# Pro 3.x EPRO2 path — full replay then per-doc dump.
proj = replay_project(args.project_dir)
n = 0
if args.all_pcb or args.all:
n += _convert_pcbs(proj, args.out)
if args.all_sch or args.all:
n += _convert_schs(proj, args.out)
if n == 0:
print("nothing to dump (no PCB / SCH_PAGE docs found)", file=sys.stderr)
return 1
return 0
if __name__ == "__main__":
raise SystemExit(main())