wip: estado de trabajo pendiente antes de la vista grid (suite 230 verde)

tests/test_extract.py

@@ -0,0 +1,154 @@
+"""Tests for per-language subtitle selection and dict-typed ``Config.languages``.
+
+These tests are pure: no network, no yt-dlp, no DB.  They cover the policy
+logic that decides which subtitle track to pick for a given
+``info`` dict produced by yt-dlp, plus the legacy/back-compat shims that
+let older YAML configs still load.
+"""
+from __future__ import annotations
+
+import pytest
+
+from yt_scraper.config import Config, parse_languages
+from yt_scraper.extract import pick_subtitle
+
+
+# ---------- fixtures ----------
+
+def _track(ext: str = "json3", url: str = "u") -> dict:
+    return {"ext": ext, "url": url}
+
+
+def _info(manual: dict | None = None, auto: dict | None = None) -> dict:
+    return {"subtitles": manual or {}, "automatic_captions": auto or {}}
+
+
+# ---------- pick_subtitle: mixed per-language mode ----------
+
+def test_mixed_manual_and_auto_per_language() -> None:
+    """`es: auto` only takes auto; iterating `es` first means it wins.
+
+    With ``{"es": "auto", "en": "manual"}`` the iteration matches `es`
+    against the auto dict and picks the auto track; for `en` only the
+    manual dict is consulted and the manual track is returned.  The two
+    policies do NOT cross-pollinate between languages.
+    """
+    info = _info(
+        manual={"en": [_track(url="man-en")]},
+        auto={"en": [_track(url="auto-en")], "es": [_track(url="auto-es")]},
+    )
+    pick = pick_subtitle(info, {"es": "auto", "en": "manual"}, prefer_manual=True)
+    assert pick is not None
+    assert pick.lang == "es"
+    assert pick.source == "auto"
+
+
+def test_manual_only_skips_auto_even_when_present() -> None:
+    info = _info(manual={}, auto={"es": [_track(url="auto")]})
+    pick = pick_subtitle(info, {"es": "manual"}, prefer_manual=True)
+    assert pick is None
+
+
+def test_auto_only_skips_manual_even_when_present() -> None:
+    info = _info(manual={"es": [_track(url="man")]}, auto={})
+    pick = pick_subtitle(info, {"es": "auto"}, prefer_manual=True)
+    assert pick is None
+
+
+def test_any_defer_to_prefer_manual_default_true() -> None:
+    """`any` honours the legacy prefer_manual=True default."""
+    info = _info(
+        manual={"es": [_track(url="man")]},
+        auto={"es": [_track(url="auto")]},
+    )
+    pick = pick_subtitle(info, {"es": "any"}, prefer_manual=True)
+    assert pick is not None
+    assert pick.source == "manual"
+
+
+def test_any_defer_to_prefer_manual_default_false() -> None:
+    info = _info(
+        manual={"es": [_track(url="man")]},
+        auto={"es": [_track(url="auto")]},
+    )
+    pick = pick_subtitle(info, {"es": "any"}, prefer_manual=False)
+    assert pick is not None
+    assert pick.source == "auto"
+
+
+def test_picks_best_format_within_track() -> None:
+    info = _info(manual={"en": [_track(ext="ttml", url="t"), _track(ext="json3", url="j")]})
+    pick = pick_subtitle(info, {"en": "manual"}, prefer_manual=True)
+    assert pick.url == "j"
+
+
+# ---------- language normalisation ----------
+
+def test_language_base_match() -> None:
+    """`es-419` preference matches the `es` caption track."""
+    info = _info(manual={"es": [_track(url="u")]})
+    pick = pick_subtitle(info, {"es-419": "manual"}, prefer_manual=True)
+    assert pick is not None
+    assert pick.lang == "es"
+
+
+# ---------- legacy list input ----------
+
+def test_legacy_list_input_uses_prefer_manual() -> None:
+    info = _info(
+        manual={"es": [_track(url="m")]},
+        auto={"es": [_track(url="a")]},
+    )
+    pick = pick_subtitle(info, ["es"], prefer_manual=True)
+    assert pick.source == "manual"
+    pick = pick_subtitle(info, ["es"], prefer_manual=False)
+    assert pick.source == "auto"
+
+
+def test_unknown_mode_falls_back_to_any() -> None:
+    info = _info(manual={"es": [_track()]}, auto={"es": [_track()]})
+    pick = pick_subtitle(info, {"es": "garbage"}, prefer_manual=True)
+    assert pick is not None
+    assert pick.source == "manual"
+
+
+# ---------- parse_languages config helper ----------
+
+def test_parse_languages_dict_pass_through() -> None:
+    assert parse_languages({"en": "manual", "es": "auto"}, True) == {
+        "en": "manual", "es": "auto",
+    }
+
+
+def test_parse_languages_dict_unknown_mode_to_any() -> None:
+    assert parse_languages({"en": "garbage"}, True) == {"en": "any"}
+
+
+def test_parse_languages_legacy_list_to_manual_by_default() -> None:
+    assert parse_languages(["es", "en"], prefer_manual=True) == {
+        "es": "manual", "en": "manual",
+    }
+
+
+def test_parse_languages_legacy_list_to_auto_when_prefer_manual_false() -> None:
+    assert parse_languages(["es", "en"], prefer_manual=False) == {
+        "es": "auto", "en": "auto",
+    }
+
+
+def test_parse_languages_none_returns_empty() -> None:
+    assert parse_languages(None, True) == {}
+
+
+# ---------- Config dataclass default shape ----------
+
+def test_config_languages_defaults_to_dict() -> None:
+    cfg = Config()
+    assert isinstance(cfg.languages, dict)
+    # "any", not "manual": the default must not exclude auto-generated captions.
+    assert cfg.languages == {"es": "any", "en": "any"}
+
+
+def test_config_prefer_manual_defaults_true() -> None:
+    cfg = Config()
+    assert cfg.prefer_manual is True