Ajoute le graphique variations vs total par personnage

lib/rebrickable/minifig_characters.py

@@ -34,6 +34,41 @@ def aggregate_by_character(rows: Iterable[dict]) -> List[dict]:
     return aggregates
 
 
+def aggregate_variations_and_totals(
+    rows: Iterable[dict],
+    excluded_characters: Sequence[str] | None = None,
+) -> List[dict]:
+    """Compte les variations uniques et le total de minifigs par personnage."""
+    excluded = set(excluded_characters or [])
+    variations: Dict[str, set] = defaultdict(set)
+    totals: Dict[str, int] = defaultdict(int)
+    genders: Dict[str, str] = {}
+    for row in rows:
+        character = row["known_character"].strip()
+        fig_num = row["fig_num"].strip()
+        gender = row.get("gender", "").strip()
+        if character == "" or fig_num == "":
+            continue
+        if character in excluded:
+            continue
+        variations[character].add(fig_num)
+        totals[character] += 1
+        if character not in genders:
+            genders[character] = gender
+    aggregates: List[dict] = []
+    for character, fig_nums in variations.items():
+        aggregates.append(
+            {
+                "known_character": character,
+                "gender": genders.get(character, ""),
+                "variation_count": len(fig_nums),
+                "total_minifigs": totals.get(character, 0),
+            }
+        )
+    aggregates.sort(key=lambda r: (-r["total_minifigs"], -r["variation_count"], r["known_character"]))
+    return aggregates
+
+
 def aggregate_by_gender(rows: Iterable[dict]) -> List[dict]:
     """Compte les minifigs distinctes par genre (fig_num unique)."""
     genders_by_fig: Dict[str, str] = {}
@@ -78,6 +113,17 @@ def write_gender_counts(path: Path, rows: Sequence[dict]) -> None:
             writer.writerow(row)
 
 
+def write_character_variations_totals(path: Path, rows: Sequence[dict]) -> None:
+    """Écrit le CSV comparant variations et total par personnage."""
+    ensure_parent_dir(path)
+    fieldnames = ["known_character", "gender", "variation_count", "total_minifigs"]
+    with path.open("w", newline="") as csv_file:
+        writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
+        writer.writeheader()
+        for row in rows:
+            writer.writerow(row)
+
+
 def load_sets_enriched(path: Path) -> Dict[str, str]:
     """Indexe les années par set_num."""
     lookup: Dict[str, str] = {}