Initial public release

scripts/archive_technical_projects.py

@@ -0,0 +1,117 @@
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+import re
+import sys
+from dataclasses import dataclass
+from uuid import UUID
+
+from sqlalchemy.orm import Session
+
+# Direct execution from /app/scripts must resolve the repository's backend
+# package before similarly named installed packages.
+ROOT = Path(__file__).resolve().parents[1]
+BACKEND_ROOT = ROOT / "backend" if (ROOT / "backend" / "app").is_dir() else ROOT
+if str(BACKEND_ROOT) not in sys.path:
+    sys.path.insert(0, str(BACKEND_ROOT))
+
+from app.db.session import SessionLocal  # noqa: E402 - imported after backend path bootstrap
+from app.models import Project  # noqa: E402 - imported after backend path bootstrap
+
+
+CANONICAL_PROJECT_NAMES = frozenset(
+    {
+        "Kempen Regional Workbench",
+        "Mol Municipality Workbench",
+    }
+)
+
+TECHNICAL_PROJECT_PATTERNS = (
+    re.compile(r"^GeoIntel Detection Quality Matrix", re.IGNORECASE),
+    re.compile(r"^GeoIntel hard-negative", re.IGNORECASE),
+    re.compile(r"^GeoIntel Detection Calibration", re.IGNORECASE),
+    re.compile(r"^GeoIntel Real Data Validation", re.IGNORECASE),
+    re.compile(r"^GeoIntel Operational YOLO .* Smoke", re.IGNORECASE),
+    re.compile(r"^GeoIntel Demo - Building QA$", re.IGNORECASE),
+    re.compile(r"^GeoIntel training", re.IGNORECASE),
+    re.compile(r"^Mol Building QA", re.IGNORECASE),
+)
+
+
+@dataclass(frozen=True)
+class ArchivePlan:
+    project_ids: tuple[UUID, ...]
+    names: tuple[str, ...]
+
+    @property
+    def count(self) -> int:
+        return len(self.project_ids)
+
+
+def is_technical_project_name(name: str) -> bool:
+    normalized = name.strip()
+    if normalized in CANONICAL_PROJECT_NAMES:
+        return False
+    return any(pattern.search(normalized) for pattern in TECHNICAL_PROJECT_PATTERNS)
+
+
+def build_archive_plan(db: Session) -> ArchivePlan:
+    rows = (
+        db.query(Project)
+        .filter(Project.status == "active")
+        .order_by(Project.created_at.asc())
+        .all()
+    )
+    selected = [row for row in rows if is_technical_project_name(row.name)]
+    return ArchivePlan(
+        project_ids=tuple(row.id for row in selected),
+        names=tuple(row.name for row in selected),
+    )
+
+
+def apply_archive_plan(db: Session, plan: ArchivePlan) -> int:
+    if not plan.project_ids:
+        return 0
+    updated = (
+        db.query(Project)
+        .filter(Project.id.in_(plan.project_ids), Project.status == "active")
+        .update({Project.status: "archived"}, synchronize_session=False)
+    )
+    db.commit()
+    return int(updated)
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(
+        description=(
+            "Archive allowlisted GeoIntel operator and benchmark projects. "
+            "Dry-run is the default; pass --apply to persist status changes."
+        )
+    )
+    parser.add_argument("--apply", action="store_true", help="Persist status='archived'.")
+    parser.add_argument(
+        "--show-names",
+        action="store_true",
+        help="Include every matched project name in the JSON output.",
+    )
+    args = parser.parse_args()
+
+    with SessionLocal() as db:
+        plan = build_archive_plan(db)
+        archived_count = apply_archive_plan(db, plan) if args.apply else 0
+        payload = {
+            "mode": "apply" if args.apply else "dry-run",
+            "matched_count": plan.count,
+            "archived_count": archived_count,
+            "canonical_projects_preserved": sorted(CANONICAL_PROJECT_NAMES),
+        }
+        if args.show_names:
+            payload["matched_names"] = list(plan.names)
+        print(json.dumps(payload, indent=2))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())