From 26cc9333c76062224326ba6521ffbf84c430da51 Mon Sep 17 00:00:00 2001
From: Brad Stein <Brad.Stein@gmail.com>
Date: Sun, 19 Apr 2026 15:04:48 -0300
Subject: [PATCH] ci(ariadne): restore LOC checker with tracked waivers

---
 Jenkinsfile                 |  2 +-
 ci/loc_hygiene_waivers.tsv  | 15 +++++++
 scripts/check_file_sizes.py | 85 +++++++++++++++++++++++++++++++++++++
 3 files changed, 101 insertions(+), 1 deletion(-)
 create mode 100644 ci/loc_hygiene_waivers.tsv
 create mode 100644 scripts/check_file_sizes.py

diff --git a/Jenkinsfile b/Jenkinsfile
index 5d25e32..a358bf7 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -173,7 +173,7 @@ mkdir -p build
 set +e
 python -m pip install --no-cache-dir -r requirements.txt -r requirements-dev.txt \
   && python -m ruff check ariadne scripts --select PLR \
-  && python scripts/check_file_sizes.py --roots ariadne scripts testing --max-lines 500 --waivers ci/loc_hygiene_waivers.tsv \
+  && python scripts/check_file_sizes.py --roots ariadne scripts tests --max-lines 500 --waivers ci/loc_hygiene_waivers.tsv \
   && python -m slipcover \
     --json \
     --out "${COVERAGE_JSON}" \
diff --git a/ci/loc_hygiene_waivers.tsv b/ci/loc_hygiene_waivers.tsv
new file mode 100644
index 0000000..d090ebb
--- /dev/null
+++ b/ci/loc_hygiene_waivers.tsv
@@ -0,0 +1,15 @@
+# path	reason
+ariadne/services/cluster_state.py	split planned; service orchestration decomposition tracked in hygiene backlog
+ariadne/app.py	split planned; Flask app bootstrap/routes currently co-located
+ariadne/services/comms.py	split planned; comms adapters still consolidated
+ariadne/manager/provisioning.py	split planned; provisioning flow modules pending extraction
+ariadne/services/nextcloud.py	split planned; provider methods pending partition
+ariadne/services/firefly.py	split planned; provider methods pending partition
+ariadne/settings.py	split planned; settings schema + helpers pending split
+ariadne/services/jenkins_workspace_cleanup.py	split planned; job orchestration pending extraction
+ariadne/services/wger.py	split planned; provider methods pending partition
+ariadne/services/vault.py	split planned; auth + data access helpers pending split
+tests/test_provisioning.py	test module split planned; broad provisioning coverage retained meanwhile
+tests/test_services.py	test module split planned; broad service contract coverage retained meanwhile
+tests/test_app.py	test module split planned; API coverage retained meanwhile
+tests/test_keycloak_admin.py	test module split planned; identity admin coverage retained meanwhile
diff --git a/scripts/check_file_sizes.py b/scripts/check_file_sizes.py
new file mode 100644
index 0000000..b339608
--- /dev/null
+++ b/scripts/check_file_sizes.py
@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+"""Fail when source files exceed a configured line-count threshold."""
+
+from __future__ import annotations
+
+import argparse
+from pathlib import Path
+
+
+DEFAULT_SKIP_PARTS = {
+    ".git",
+    ".venv",
+    "venv",
+    "build",
+    "dist",
+    "node_modules",
+    "__pycache__",
+    ".pytest_cache",
+}
+SOURCE_SUFFIXES = {".py", ".sh", ".json", ".yaml", ".yml"}
+
+
+def _read_waivers(path: Path) -> set[str]:
+    if not path.exists():
+        return set()
+    waived: set[str] = set()
+    for line in path.read_text(encoding="utf-8").splitlines():
+        row = line.strip()
+        if not row or row.startswith("#"):
+            continue
+        waived.add(row.split("\t", 1)[0].strip())
+    return waived
+
+
+def _iter_files(root: Path) -> list[Path]:
+    if not root.exists():
+        return []
+    files: list[Path] = []
+    for path in root.rglob("*"):
+        if not path.is_file():
+            continue
+        if any(part in DEFAULT_SKIP_PARTS for part in path.parts):
+            continue
+        if path.suffix.lower() not in SOURCE_SUFFIXES and path.name != "Jenkinsfile":
+            continue
+        files.append(path)
+    return files
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--roots", nargs="+", required=True)
+    parser.add_argument("--max-lines", type=int, default=500)
+    parser.add_argument("--waivers", default="ci/loc_hygiene_waivers.tsv")
+    args = parser.parse_args()
+
+    repo_root = Path.cwd().resolve()
+    waived = _read_waivers(repo_root / args.waivers)
+
+    offenders: list[tuple[int, str]] = []
+    for root_name in args.roots:
+        for path in _iter_files(repo_root / root_name):
+            rel = path.relative_to(repo_root).as_posix()
+            if rel in waived:
+                continue
+            try:
+                line_count = sum(1 for _ in path.open("r", encoding="utf-8", errors="ignore"))
+            except OSError:
+                continue
+            if line_count > args.max_lines:
+                offenders.append((line_count, rel))
+
+    if not offenders:
+        print(f"[loc] ok: no files exceed {args.max_lines} lines")
+        return 0
+
+    offenders.sort(reverse=True)
+    print(f"[loc] failed: {len(offenders)} file(s) exceed {args.max_lines} lines")
+    for lines, rel in offenders:
+        print(f" - {rel}: {lines} lines")
+    return 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())