Corrige l'alias Franklin Webb et régénère les frises

lib/rebrickable/minifig_character_sets.py

@@ -0,0 +1,95 @@
+"""Liste les sets contenant chaque personnage connu."""
+
+import csv
+from pathlib import Path
+from typing import Dict, Iterable, List, Sequence
+
+from lib.filesystem import ensure_parent_dir
+from lib.rebrickable.stats import read_rows
+
+
+def load_minifigs_by_set(path: Path) -> List[dict]:
+    """Charge le CSV minifigs_by_set."""
+    return read_rows(path)
+
+
+def load_sets(path: Path) -> Dict[str, dict]:
+    """Indexe les sets enrichis par set_num."""
+    lookup: Dict[str, dict] = {}
+    for row in read_rows(path):
+        lookup[row["set_num"]] = row
+    return lookup
+
+
+def build_character_sets(
+    minifigs_rows: Iterable[dict],
+    sets_lookup: Dict[str, dict],
+    excluded_characters: Sequence[str] | None = None,
+) -> List[dict]:
+    """Associe chaque personnage connu aux sets où il apparaît (hors figurants)."""
+    excluded = set(excluded_characters or [])
+    seen: set[tuple[str, str, str]] = set()
+    character_sets: List[dict] = []
+    for row in minifigs_rows:
+        character = row["known_character"].strip()
+        fig_num = row["fig_num"].strip()
+        if character == "" or fig_num == "":
+            continue
+        if character in excluded:
+            continue
+        set_row = sets_lookup[row["set_num"]]
+        key = (character, row["set_num"], fig_num)
+        if key in seen:
+            continue
+        character_sets.append(
+            {
+                "known_character": character,
+                "set_num": row["set_num"],
+                "set_id": set_row["set_id"],
+                "year": set_row["year"],
+                "fig_num": fig_num,
+            }
+        )
+        seen.add(key)
+    character_sets.sort(key=lambda row: (row["known_character"], int(row["year"]), row["set_num"], row["fig_num"]))
+    return character_sets
+
+
+def write_character_sets(destination_path: Path, rows: Sequence[dict]) -> None:
+    """Écrit le CSV listant les sets par personnage."""
+    ensure_parent_dir(destination_path)
+    fieldnames = ["known_character", "set_num", "set_id", "year", "fig_num"]
+    with destination_path.open("w", newline="") as csv_file:
+        writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
+        writer.writeheader()
+        for row in rows:
+            writer.writerow(row)
+
+
+def group_by_character(rows: Iterable[dict]) -> Dict[str, List[dict]]:
+    """Regroupe les lignes par personnage pour la génération des frises."""
+    grouped: Dict[str, List[dict]] = {}
+    for row in rows:
+        character = row["known_character"]
+        entries = grouped.get(character)
+        if entries is None:
+            entries = []
+            grouped[character] = entries
+        entries.append(row)
+    for character, entries in grouped.items():
+        entries.sort(key=lambda row: (int(row["year"]), row["set_num"], row["fig_num"]))
+    return grouped
+
+
+def load_missing_minifigs(path: Path) -> set[str]:
+    """Charge les ressources minifigs introuvables consignées dans le log de téléchargement."""
+    missing: set[str] = set()
+    with path.open() as csv_file:
+        reader = csv.DictReader(csv_file)
+        for row in reader:
+            if row["status"] != "missing":
+                continue
+            if not row["path"].endswith("minifig.jpg"):
+                continue
+            missing.add(row["path"])
+    return missing