Premiers éléments de l'étude

lib/rebrickable/enrich_sets.py

@@ -0,0 +1,86 @@
+"""Enrichissement des sets LEGO avec des métadonnées Rebrickable et personnelles."""
+
+import csv
+from pathlib import Path
+from typing import Iterable, Set
+
+from lib.filesystem import ensure_parent_dir
+
+REBRICKABLE_SET_BASE_URL = "https://rebrickable.com/sets/"
+
+
+def extract_set_id(set_num: str) -> str:
+    """Extrait l'identifiant LEGO (partie avant la révision) depuis set_num."""
+    return set_num.split("-", 1)[0]
+
+
+def build_rebrickable_set_url(set_num: str) -> str:
+    """Construit l'URL publique Rebrickable d'un set."""
+    return f"{REBRICKABLE_SET_BASE_URL}{set_num}"
+
+
+def parse_set_collection_root(raw_value: str) -> Path | None:
+    """Prépare le chemin de collection, ou None si aucune collection n'est fournie."""
+    cleaned = raw_value.strip()
+    if not cleaned:
+        print("La variable MY_SETS est vide, aucun set en collection.")
+        return None
+    return Path(cleaned)
+
+
+def load_owned_set_ids(collection_root: Path) -> Set[str]:
+    """Retourne l'ensemble des identifiants de sets présents dans un dossier de collection."""
+    if not collection_root.exists():
+        print(f"Le dossier {collection_root} n'existe pas, aucun set en collection.")
+        return set()
+    if not collection_root.is_dir():
+        print(f"Le chemin {collection_root} n'est pas un dossier, aucun set en collection.")
+        return set()
+    entries = [path for path in collection_root.iterdir() if path.is_dir()]
+    if not entries:
+        print(f"Le dossier {collection_root} est vide, aucun set en collection.")
+        return set()
+    return {entry.name for entry in entries}
+
+
+def enrich_sets(
+    source_path: Path,
+    destination_path: Path,
+    owned_set_ids: Iterable[str],
+) -> None:
+    """Ajoute les colonnes set_id, rebrickable_url et in_collection au catalogue filtré."""
+    ensure_parent_dir(destination_path)
+    owned_lookup = set(owned_set_ids)
+    with source_path.open() as source_file, destination_path.open("w", newline="") as target_file:
+        reader = csv.DictReader(source_file)
+        fieldnames = reader.fieldnames + ["set_id", "rebrickable_url", "in_collection"]
+        writer = csv.DictWriter(target_file, fieldnames=fieldnames)
+        writer.writeheader()
+        for row in reader:
+            set_id = extract_set_id(row["set_num"])
+            writer.writerow(
+                {
+                    **row,
+                    "set_id": set_id,
+                    "rebrickable_url": build_rebrickable_set_url(row["set_num"]),
+                    "in_collection": str(set_id in owned_lookup).lower(),
+                }
+            )
+
+
+def write_missing_sets_markdown(enriched_path: Path, destination_path: Path) -> None:
+    """Génère un tableau Markdown listant les sets non possédés."""
+    with enriched_path.open() as source_file:
+        reader = csv.DictReader(source_file)
+        rows = [
+            row
+            for row in reader
+            if row["in_collection"] == "false"
+        ]
+    ensure_parent_dir(destination_path)
+    with destination_path.open("w") as target_file:
+        target_file.write("| set_id | year | name |\n")
+        target_file.write("| --- | --- | --- |\n")
+        for row in rows:
+            link = f"[{row['set_id']}]({row['rebrickable_url']})"
+            target_file.write(f"| {link} | {row['year']} | {row['name']} |\n")