CM93 MySQL importer validated baseline

src/cm93db/scanner.py

@@ -0,0 +1,59 @@
+from __future__ import annotations
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Iterable
+
+SCALE_NATIVE = {
+    "Z": 20_000_000,
+    "A": 3_000_000,
+    "B": 1_000_000,
+    "C": 200_000,
+    "D": 100_000,
+    "E": 50_000,
+    "F": 20_000,
+    "G": 7_500,
+}
+
+@dataclass(frozen=True)
+class CellFile:
+    path: Path
+    relative_path: Path
+    scale_code: str
+    native_scale: int
+
+@dataclass(frozen=True)
+class ScanResult:
+    root: Path
+    cells: tuple[CellFile, ...]
+    object_dictionary: Path | None
+    attribute_dictionary: Path | None
+
+def _find_case_insensitive(root: Path, names: set[str]) -> Path | None:
+    lowers = {n.lower() for n in names}
+    for p in root.rglob("*"):
+        if p.is_file() and p.name.lower() in lowers:
+            return p
+    return None
+
+def scan_cm93(root: Path) -> ScanResult:
+    root = root.resolve()
+    if not root.exists():
+        raise FileNotFoundError(root)
+    cells = []
+    for p in root.rglob("*"):
+        if not p.is_file():
+            continue
+        ext = p.suffix.upper().lstrip(".")
+        if ext in SCALE_NATIVE:
+            cells.append(
+                CellFile(
+                    path=p,
+                    relative_path=p.relative_to(root),
+                    scale_code=ext,
+                    native_scale=SCALE_NATIVE[ext],
+                )
+            )
+    cells.sort(key=lambda c: (c.scale_code, str(c.relative_path).lower()))
+    obj = _find_case_insensitive(root, {"CM93OBJ.DIC"})
+    attr = _find_case_insensitive(root, {"ATTRLUT.DIC", "CM93ATTR.DIC"})
+    return ScanResult(root, tuple(cells), obj, attr)