Color-code dwarf status output by tree level

Each row (kind header, gen, raw/processed, schema, root totals) gets a
distinct ANSI color so the hierarchy is easier to scan. Disabled when
stdout isn't a TTY or NO_COLOR is set.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

scripts/bump_dataset_version.py

@@ -20,11 +20,33 @@ import datetime as dt
 import os
 import re
 import subprocess
+import sys
 from pathlib import Path
 
 GEN_RE = re.compile(r"^gen(\d+)$")
 SCHEMA_RE = re.compile(r"^schema(\d+)$")
 
+# One color per tree level in `dwarf status` output, so the eye can jump
+# straight to e.g. "all the schema rows" or "all the totals".
+_LEVEL_COLORS = {
+    "kind": "\033[1;36m",  # bold cyan — top-level kind/ header
+    "gen": "\033[1;33m",  # bold yellow — genN row + kind total
+    "bucket": "\033[34m",  # blue — raw/processed subtotals
+    "schema": "\033[32m",  # green — schemaN rows
+    "root": "\033[1;35m",  # bold magenta — derived/, pools/, grand total
+}
+_RESET = "\033[0m"
+
+
+def _use_color() -> bool:
+    return sys.stdout.isatty() and os.environ.get("NO_COLOR") is None
+
+
+def _colorize(text: str, level: str) -> str:
+    if not _use_color():
+        return text
+    return f"{_LEVEL_COLORS[level]}{text}{_RESET}"
+
 
 def _find_component_idx(abs_path: Path, pattern: re.Pattern) -> int | None:
     """Return the index of the first path component matching *pattern*, or None."""
@@ -147,11 +169,12 @@ def _human_size(n: int) -> str:
 _ROW_WIDTH = 48
 
 
-def _row(label: str, size_bytes: int, indent: int = 0) -> str:
+def _row(label: str, size_bytes: int, indent: int = 0, level: str | None = None) -> 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
+    row = text + " " * pad + size_str
+    return _colorize(row, level) if level else row
 
 
 def print_status(root: Path) -> None:
@@ -167,7 +190,7 @@ 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}/")
+        print(_colorize(f"{kind}/", "kind"))
         kind_total = 0
         for gen in gens:
             gen_tag = f"gen{gen}"
@@ -187,25 +210,25 @@ def print_status(root: Path) -> None:
             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))
+            print(_row(gen_tag, gen_total, indent=1, level="gen"))
+            print(_row("raw", raw_size, indent=2, level="bucket"))
+            print(_row("processed", processed_size, indent=2, level="bucket"))
             if schemas:
                 for s in schemas:
-                    print(_row(f"schema{s}", schema_sizes[s], indent=3))
+                    print(_row(f"schema{s}", schema_sizes[s], indent=3, level="schema"))
             else:
-                print("      (none)")
-        print(_row(f"{kind} total", kind_total, indent=1))
+                print(_colorize("      (none)", "schema"))
+        print(_row(f"{kind} total", kind_total, indent=1, level="gen"))
         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("derived/", derived_size, level="root"))
+    print(_row("pools/", pools_size, level="root"))
     print("-" * _ROW_WIDTH)
-    print(_row("grand total", grand_total))
+    print(_row("grand total", grand_total, level="root"))
 
 
 # ---------------------------------------------------------------------------