Add disk usage summary to dwarf status

Shows per-schema, per-gen (raw/processed split), per-kind, and grand
total sizes so the dataset tree's footprint is visible at a glance.

scripts/bump_dataset_version.py

@@ -120,11 +120,46 @@ def apply_bump(root: Path, new_dirs: list[Path], log_line: str) -> None:
         f.write(log_line + "\n")
 
 
+def _du(path: Path) -> int:
+    """Total size in bytes of all regular files under *path* (0 if missing)."""
+    if not path.is_dir():
+        return 0
+    total = 0
+    for dirpath, _dirnames, filenames in os.walk(path):
+        for name in filenames:
+            fp = Path(dirpath) / name
+            try:
+                total += fp.stat().st_size
+            except OSError:
+                pass
+    return total
+
+
+def _human_size(n: int) -> str:
+    size = float(n)
+    for unit in ("B", "KB", "MB", "GB", "TB"):
+        if size < 1024 or unit == "TB":
+            return f"{size:.1f} {unit}" if unit != "B" else f"{int(size)} {unit}"
+        size /= 1024
+    return f"{size:.1f} TB"
+
+
+_ROW_WIDTH = 48
+
+
+def _row(label: str, size_bytes: int, indent: int = 0) -> str:
+    text = "  " * indent + label
+    size_str = _human_size(size_bytes)
+    pad = max(1, _ROW_WIDTH - len(text) - len(size_str))
+    return text + " " * pad + size_str
+
+
 def print_status(root: Path) -> None:
     raw_root = root / "raw"
     if not raw_root.is_dir():
         print(f"no raw/ tree found under {root}")
         return
+    grand_total = 0
     for kind_dir in sorted(p for p in raw_root.iterdir() if p.is_dir()):
         kind = kind_dir.name
         gens = sorted(
@@ -132,9 +167,11 @@ def print_status(root: Path) -> None:
             for m in (GEN_RE.match(p.name) for p in kind_dir.iterdir() if p.is_dir())
             if m
         )
-        print(f"kind={kind}")
+        print(f"{kind}/")
+        kind_total = 0
         for gen in gens:
             gen_tag = f"gen{gen}"
+            raw_size = _du(raw_root / kind / gen_tag)
             schema_dir = root / "processed" / kind / gen_tag
             schemas = sorted(
                 int(m.group(1))
@@ -145,8 +182,30 @@ def print_status(root: Path) -> None:
                 )
                 if m
             )
-            schema_str = ", ".join(f"schema{s}" for s in schemas) or "(none)"
-            print(f"  {gen_tag}: {schema_str}")
+            schema_sizes = {s: _du(schema_dir / f"schema{s}") for s in schemas}
+            processed_size = sum(schema_sizes.values())
+            gen_total = raw_size + processed_size
+            kind_total += gen_total
+
+            print(_row(gen_tag, gen_total, indent=1))
+            print(_row("raw", raw_size, indent=2))
+            print(_row("processed", processed_size, indent=2))
+            if schemas:
+                for s in schemas:
+                    print(_row(f"schema{s}", schema_sizes[s], indent=3))
+            else:
+                print("      (none)")
+        print(_row(f"{kind} total", kind_total, indent=1))
+        print()
+        grand_total += kind_total
+
+    derived_size = _du(root / "derived")
+    pools_size = _du(root / "pools")
+    grand_total += derived_size + pools_size
+    print(_row("derived/", derived_size))
+    print(_row("pools/", pools_size))
+    print("-" * _ROW_WIDTH)
+    print(_row("grand total", grand_total))
 
 
 # ---------------------------------------------------------------------------