Bump ruff line-length to 120 and reformat

Rejoins lines that only wrapped because they exceeded the old 88-char
limit; ruff check and the full test suite (725 passed) are unaffected.

scripts/bump_dataset_version.py

@@ -82,9 +82,7 @@ def _max_index(parent: Path, pattern: re.Pattern) -> int:
 
 def _git_user_name() -> str | None:
     try:
-        out = subprocess.run(
-            ["git", "config", "user.name"], capture_output=True, text=True, timeout=2
-        )
+        out = subprocess.run(["git", "config", "user.name"], capture_output=True, text=True, timeout=2)
     except (OSError, subprocess.SubprocessError):
         # OSError (e.g. git not on PATH) and subprocess.SubprocessError
         # (e.g. TimeoutExpired) are unrelated hierarchies — TimeoutExpired
@@ -142,9 +140,7 @@ def plan_bump_schema(
     raw_gen_dir = root / "raw" / kind / gen_tag
     processed_gen_dir = root / "processed" / kind / gen_tag
     if not raw_gen_dir.is_dir() and not processed_gen_dir.is_dir():
-        raise SystemExit(
-            f"error: {gen_tag} doesn't exist yet for kind={kind} — run bump-gen first"
-        )
+        raise SystemExit(f"error: {gen_tag} doesn't exist yet for kind={kind} — run bump-gen first")
     if target is not None:
         if not SCHEMA_RE.match(target):
             raise SystemExit(f"error: --to must look like 'schemaN', got {target!r}")
@@ -154,9 +150,7 @@ def plan_bump_schema(
         schema_tag = f"schema{next_schema}"
     new_dirs = [processed_gen_dir / schema_tag]
     by_suffix = f" ({by})" if by else ""
-    log_line = (
-        f"- `{gen_tag}`/`{schema_tag}` (kind={kind}) — {date} — {reason}{by_suffix}"
-    )
+    log_line = f"- `{gen_tag}`/`{schema_tag}` (kind={kind}) — {date} — {reason}{by_suffix}"
     return new_dirs, log_line
 
 
@@ -212,9 +206,7 @@ def _manifest_referenced_files(pools_root: Path) -> set[Path]:
     return referenced
 
 
-def _referenced_root_count(
-    raw_gen_dir: Path, processed_gen_dir: Path
-) -> tuple[int, int]:
+def _referenced_root_count(raw_gen_dir: Path, processed_gen_dir: Path) -> tuple[int, int]:
     """(total .root files, count with a same-named .parquet under any schema) for one gen."""
     if not raw_gen_dir.is_dir():
         return 0, 0
@@ -243,9 +235,7 @@ def _referenced_root_count(
     return total, referenced
 
 
-def _referenced_parquet_count(
-    schema_dir: Path, manifest_referenced: set[Path]
-) -> tuple[int, int]:
+def _referenced_parquet_count(schema_dir: Path, manifest_referenced: set[Path]) -> tuple[int, int]:
     """(total .parquet files, count listed in at least one manifest) for one schema dir."""
     if not schema_dir.is_dir():
         return 0, 0
@@ -342,11 +332,7 @@ def print_status(root: Path) -> None:
     grand_files = 0
     for kind_dir in sorted(p for p in raw_root.iterdir() if p.is_dir()):
         kind = kind_dir.name
-        gens = sorted(
-            int(m.group(1))
-            for m in (GEN_RE.match(p.name) for p in kind_dir.iterdir() if p.is_dir())
-            if m
-        )
+        gens = sorted(int(m.group(1)) for m in (GEN_RE.match(p.name) for p in kind_dir.iterdir() if p.is_dir()) if m)
         print(_colorize(f"{kind}/", "kind"))
         kind_total = 0
         kind_files = 0
@@ -359,25 +345,18 @@ def print_status(root: Path) -> None:
             schemas = sorted(
                 int(m.group(1))
                 for m in (
-                    SCHEMA_RE.match(p.name)
-                    for p in (schema_dir.iterdir() if schema_dir.is_dir() else [])
-                    if p.is_dir()
+                    SCHEMA_RE.match(p.name) for p in (schema_dir.iterdir() if schema_dir.is_dir() else []) if p.is_dir()
                 )
                 if m
             )
             schema_sizes = {s: _du(schema_dir / f"schema{s}") for s in schemas}
             schema_counts = {
-                s: _referenced_parquet_count(
-                    schema_dir / f"schema{s}", manifest_referenced
-                )
-                for s in schemas
+                s: _referenced_parquet_count(schema_dir / f"schema{s}", manifest_referenced) for s in schemas
             }
             processed_size = sum(schema_sizes.values())
             processed_files = sum(c[0] for c in schema_counts.values())
             processed_referenced = sum(c[1] for c in schema_counts.values())
-            raw_files, raw_referenced = _referenced_root_count(
-                raw_gen_dir, processed_gen_dir
-            )
+            raw_files, raw_referenced = _referenced_root_count(raw_gen_dir, processed_gen_dir)
             gen_total = raw_size + processed_size
             gen_files = raw_files + processed_files
             kind_total += gen_total
@@ -425,9 +404,7 @@ def print_status(root: Path) -> None:
                         print(_reason_line(schema_reason, indent=4))
             else:
                 print(_colorize("      (none)", "schema"))
-        print(
-            _row(f"{kind} total", kind_total, indent=1, level="gen", count=kind_files)
-        )
+        print(_row(f"{kind} total", kind_total, indent=1, level="gen", count=kind_files))
         print()
         grand_total += kind_total
         grand_files += kind_files
@@ -526,13 +503,8 @@ def plan_update_manifest(
     return result, missing
 
 
-def apply_update_manifest(
-    manifest_path: Path, lines: list[tuple[str, str | None]]
-) -> None:
-    out = [
-        replacement if replacement is not None else original
-        for original, replacement in lines
-    ]
+def apply_update_manifest(manifest_path: Path, lines: list[tuple[str, str | None]]) -> None:
+    out = [replacement if replacement is not None else original for original, replacement in lines]
     manifest_path.write_text("\n".join(out) + "\n")
 
 
@@ -552,9 +524,7 @@ def _resolve_manifest_files(manifest_path: Path) -> list[Path]:
     return files
 
 
-def plan_create_manifest(
-    output_path: Path, parquet_files: list[Path]
-) -> tuple[list[str], list[Path], list[Path]]:
+def plan_create_manifest(output_path: Path, parquet_files: list[Path]) -> tuple[list[str], list[Path], list[Path]]:
     """Return (relative_lines, missing_files, resolved_abs_paths)."""
     manifest_dir = output_path.resolve().parent
     lines: list[str] = []
@@ -569,9 +539,7 @@ def plan_create_manifest(
     return lines, missing, resolved
 
 
-def check_holdout_overlap(
-    output_path: Path, resolved_new_files: list[Path]
-) -> list[tuple[str, Path]]:
+def check_holdout_overlap(output_path: Path, resolved_new_files: list[Path]) -> list[tuple[str, Path]]:
     """Return (other_manifest_name, file) pairs where new files clash with existing manifests.
 
     The check is triggered when output_path is (or will be) holdout.manifest, or when a
@@ -641,9 +609,7 @@ def _run_bump(
     if gen is None:
         new_dirs, log_line = plan_bump_gen(root_path, kind, reason, by, date, to)
     else:
-        new_dirs, log_line = plan_bump_schema(
-            root_path, kind, gen, reason, by, date, to
-        )
+        new_dirs, log_line = plan_bump_schema(root_path, kind, gen, reason, by, date, to)
 
     print(f"=== {'EXECUTING' if execute else 'DRY RUN'} ===")
     print("new directories:")