Rend le téléchargement des ressources plus patient et cache

tests/test_resources.py

@@ -0,0 +1,108 @@
+"""Tests des outils de téléchargement de ressources."""
+
+from pathlib import Path
+
+from lib.rebrickable.resources import (
+    add_part_img_urls,
+    build_download_plan,
+    build_part_img_lookup,
+    download_resources,
+    sanitize_name,
+    write_minifigs_by_set_with_images,
+)
+from lib.filesystem import ensure_parent_dir
+from lib.rebrickable.stats import read_rows
+
+
+def test_build_part_img_lookup_calls_fetcher_once_per_part() -> None:
+    """Construit un index en appelant le fetcher sur les références uniques."""
+    calls: list[str] = []
+
+    def fetcher(part_num: str) -> str:
+        calls.append(part_num)
+        return f"url-{part_num}"
+
+    lookup = build_part_img_lookup(["p1", "p2", "p1"], fetcher, delay_seconds=0)
+
+    assert lookup == {"p1": "url-p1", "p2": "url-p2"}
+    assert calls == ["p1", "p2"]
+
+
+def test_add_part_img_urls_and_write(tmp_path: Path) -> None:
+    """Ajoute les URLs de tête et réécrit minifigs_by_set."""
+    rows = [
+        {"set_num": "123-1", "part_num": "p1", "known_character": "Alice", "fig_num": "f1", "gender": "female"},
+    ]
+    lookup = {"p1": "http://img/p1.jpg"}
+
+    enriched = add_part_img_urls(rows, lookup)
+    destination = tmp_path / "minifigs_by_set.csv"
+    write_minifigs_by_set_with_images(destination, enriched)
+
+    assert read_rows(destination) == [
+        {
+            "set_num": "123-1",
+            "part_num": "p1",
+            "known_character": "Alice",
+            "fig_num": "f1",
+            "gender": "female",
+            "part_img_url": "http://img/p1.jpg",
+        }
+    ]
+
+
+def test_build_download_plan_and_download(tmp_path: Path) -> None:
+    """Construit le plan et télécharge les binaires via un downloader stub."""
+    sets_rows = [
+        {"set_num": "123-1", "set_id": "123", "img_url": "http://set.img", "name": "A", "year": "2020"},
+    ]
+    minifigs_rows = [
+        {"set_num": "123-1", "part_num": "p1", "known_character": "Bob", "fig_num": "fig-1", "gender": "male", "part_img_url": "http://head.img"}
+    ]
+    minifigs_catalog = {"fig-1": {"img_url": "http://fig.img"}}
+    base_dir = tmp_path / "resources"
+
+    plan = build_download_plan(sets_rows, minifigs_rows, minifigs_catalog, base_dir)
+    downloaded: list[tuple[str, Path]] = []
+
+    def downloader(url: str, path: Path) -> bool:
+        downloaded.append((url, path))
+        path.parent.mkdir(parents=True, exist_ok=True)
+        path.write_bytes(b"data")
+        return True
+
+    download_resources(plan, downloader, delay_seconds=0, log_path=tmp_path / "log.csv")
+
+    assert downloaded == [
+        ("http://set.img", base_dir / "123" / "set.jpg"),
+        ("http://fig.img", base_dir / "123" / "Bob" / "minifig.jpg"),
+        ("http://head.img", base_dir / "123" / "Bob" / "head.jpg"),
+    ]
+    assert (base_dir / "123" / "Bob" / "head.jpg").exists()
+
+
+def test_download_resources_duplicates_from_cache(tmp_path: Path) -> None:
+    """Duplique les fichiers déjà téléchargés pour d'autres sets."""
+    plan = [
+        {"url": "http://same.img", "path": tmp_path / "resources" / "111" / "set.jpg"},
+        {"url": "http://same.img", "path": tmp_path / "resources" / "222" / "set.jpg"},
+    ]
+    downloads: list[tuple[str, Path]] = []
+
+    def downloader(url: str, path: Path) -> bool:
+        downloads.append((url, path))
+        ensure_parent_dir(path)
+        path.write_bytes(b"img")
+        return True
+
+    download_resources(plan, downloader, delay_seconds=0, log_path=tmp_path / "log.csv")
+
+    assert downloads == [("http://same.img", tmp_path / "resources" / "111" / "set.jpg")]
+    assert (tmp_path / "resources" / "222" / "set.jpg").exists()
+
+
+def test_sanitize_name_handles_special_chars() -> None:
+    """Nettoie les noms en enlevant les caractères spéciaux."""
+    assert sanitize_name("Owen Grady") == "Owen_Grady"
+    assert sanitize_name("Kayla-Watts!") == "Kayla_Watts"
+    assert sanitize_name("") == "Unknown"