Add movie-keyed pool index with multi-version movies, ČSFD title bridge, subtitles and miniDLNA library scoping

2026-09-13 17:16:48 +02:00
parent c0ad1c1553
commit c399a6aed3
26 changed files with 4635 additions and 221 deletions
@@ -0,0 +1,255 @@
+"""Tests for the lean ČSFD title-bridge scraper (`src.core.csfd`)."""
+import hashlib
+from unittest.mock import patch
+
+import pytest
+
+from src.core import csfd
+from src.core.csfd import (
+    CsfdError,
+    CsfdFilm,
+    _extract_csfd_id,
+    _is_film_href,
+    _parse_origin,
+    _parse_original_title,
+    _solve_anubis_pow,
+    clean_filename_to_query,
+    fetch_film,
+    find_csfd_url,
+    search_films,
+)
+
+# A trimmed ČSFD film page: Czech title in JSON-LD, USA origin, and a
+# ``.film-names`` list whose USA-flagged entry is the original title.
+FILM_HTML = """
+<html><head>
+<script type="application/ld+json">
+{"@context":"https://schema.org/","@type":"Movie","name":"Vykoupení z věznice Shawshank",
+ "dateCreated":"1994","duration":"PT142M"}
+</script>
+</head><body>
+<div class="film-header-name">
+  <h1>Vykoupení z věznice Shawshank</h1>
+  <ul class="film-names">
+    <li><img src="//x/us.svg" class="flag" title="USA" alt="USA"/> The Shawshank Redemption
+        <span class="normal more-name-link"><a class="more">více</a></span></li>
+    <li class="more-names hidden"><img src="//x/sk.svg" class="flag" title="Slovensko"/>
+        Vykúpenie z väznice Shawshank</li>
+  </ul>
+</div>
+<div class="origin">USA <span class="bullet"></span>
+  <span>1994 <span class="bullet"></span> </span>142 min</div>
+</body></html>
+"""
+
+# A Czech film: ČSFD omits the Czech title from ``.film-names`` (it equals the
+# <h1>) and lists only a foreign festival title — the original title must fall
+# back to the <h1>, not "Cosy Dens".
+CZECH_FILM_HTML = """
+<html><head>
+<script type="application/ld+json">
+{"@type":"Movie","name":"Pelíšky","datePublished":"1999-04-01"}
+</script>
+</head><body>
+<div class="film-header-name"><h1>Pelíšky</h1>
+  <ul class="film-names">
+    <li><img class="flag" title="angličtina"/> Cosy Dens</li>
+    <li><img class="flag" title="Slovensko"/> Pelíšky</li>
+  </ul></div>
+<div class="origin">Česko <span class="bullet"></span><span>1999</span></div>
+</body></html>
+"""
+
+# The real search page groups hits into <section> blocks; a.film-title-name also
+# matches series episodes, so search_films must scope to "Filmy" and drop the
+# two-segment episode hrefs.
+SEARCH_HTML = """
+<html><body>
+<section><div class="box-header"><h2>Filmy</h2></div>
+  <a href="/film/2294-vykoupeni-z-veznice-shawshank/prehled/" class="film-title-name">Vykoupení z věznice Shawshank</a>
+  <a href="/film/248803-film-o-filmu/prehled/" class="film-title-name">Film o filmu</a>
+</section>
+<section><div class="box-header"><h2>Seriály</h2></div>
+  <a href="/film/318290-arrow/620181-x/prehled/" class="film-title-name">Arrow - Vykoupení</a>
+</section>
+</body></html>
+"""
+
+
+class TestCleanFilenameToQuery:
+    def test_strips_release_tags_and_keeps_year(self):
+        assert clean_filename_to_query(
+            "Matrix.1999.1080p.BluRay.x264-GROUP.mkv") == "Matrix 1999"
+
+    def test_handles_spaces_and_parens_year(self):
+        assert clean_filename_to_query(
+            "Forrest Gump (1994) 2160p HDR.mkv") == "Forrest Gump 1994"
+
+    def test_no_year_no_markers(self):
+        assert clean_filename_to_query("Amelie.mkv") == "Amelie"
+
+    def test_underscores_and_resolution(self):
+        assert clean_filename_to_query("Sam_doma_720p.mkv") == "Sam doma"
+
+    def test_falls_back_to_stem_when_starting_with_marker(self):
+        assert clean_filename_to_query("1080p.mkv") == "1080p"
+
+
+class TestExtractCsfdId:
+    def test_extract_from_various_urls(self):
+        assert _extract_csfd_id(
+            "https://www.csfd.cz/film/2294-vykoupeni/prehled/") == 2294
+        assert _extract_csfd_id("/film/999/") == 999
+
+    def test_none_when_absent(self):
+        assert _extract_csfd_id("https://www.csfd.cz/") is None
+
+
+class TestAnubisPoW:
+    def test_solve_difficulty_one_gives_one_leading_zero_nibble(self):
+        hash_hex, nonce, _ = _solve_anubis_pow("abc123", difficulty=1)
+        assert hash_hex[0] == "0"
+        assert hashlib.sha256(f"abc123{nonce}".encode()).hexdigest() == hash_hex
+
+    def test_solve_difficulty_two_gives_leading_zero_byte(self):
+        hash_hex, _, _ = _solve_anubis_pow("seed", difficulty=2)
+        assert hash_hex[:2] == "00"
+
+
+class TestParseOrigin:
+    def test_country_and_year_from_bullet_format(self):
+        from bs4 import BeautifulSoup
+        soup = BeautifulSoup(FILM_HTML, "html.parser")
+        assert _parse_origin(soup) == ("USA", "1994")
+
+    def test_first_country_of_coproduction(self):
+        from bs4 import BeautifulSoup
+        html = ('<div class="origin">Francie / Německo <span class="bullet"></span>'
+                '<span>2001</span> 120 min</div>')
+        soup = BeautifulSoup(html, "html.parser")
+        assert _parse_origin(soup) == ("Francie", "2001")
+
+
+class TestParseOriginalTitle:
+    def test_picks_name_matching_origin_country(self):
+        from bs4 import BeautifulSoup
+        soup = BeautifulSoup(FILM_HTML, "html.parser")
+        assert _parse_original_title(soup, "USA") == "The Shawshank Redemption"
+
+    def test_none_without_country_match_so_caller_uses_czech_title(self):
+        # A Czech film lists only foreign/festival alt-titles here — none match
+        # the origin country, so we must NOT return one of them.
+        from bs4 import BeautifulSoup
+        html = ('<ul class="film-names">'
+                '<li><img class="flag" title="angličtina"/> Loners</li>'
+                '<li><img class="flag" title="Slovinsko"/> Samotarji</li></ul>')
+        soup = BeautifulSoup(html, "html.parser")
+        assert _parse_original_title(soup, "Česko") is None
+
+    def test_cesko_matches_ceskoslovensko_flag(self):
+        from bs4 import BeautifulSoup
+        html = ('<ul class="film-names">'
+                '<li><img class="flag" title="Československo"/> Ostře sledované vlaky</li>'
+                '</ul>')
+        soup = BeautifulSoup(html, "html.parser")
+        assert _parse_original_title(soup, "Česko") == "Ostře sledované vlaky"
+
+    def test_none_when_no_names(self):
+        from bs4 import BeautifulSoup
+        soup = BeautifulSoup("<div>x</div>", "html.parser")
+        assert _parse_original_title(soup, "USA") is None
+
+
+class TestFetchFilm:
+    def test_parses_czech_and_original_title_and_year(self):
+        class _Resp:
+            text = FILM_HTML
+
+        with patch("src.core.csfd._get_page", return_value=_Resp()):
+            film = fetch_film("https://www.csfd.cz/film/2294-x/")
+
+        assert film.czech_title == "Vykoupení z věznice Shawshank"
+        assert film.original_title == "The Shawshank Redemption"
+        assert film.year == "1994"
+        assert film.csfd_id == 2294
+        assert film.tmdb_query == ("The Shawshank Redemption", "1994")
+
+    def test_czech_film_original_title_falls_back_to_czech(self):
+        class _Resp:
+            text = CZECH_FILM_HTML
+
+        with patch("src.core.csfd._get_page", return_value=_Resp()):
+            film = fetch_film("https://www.csfd.cz/film/15387-pelisky/")
+
+        assert film.czech_title == "Pelíšky"
+        assert film.original_title == "Pelíšky"
+        assert film.year == "1999"
+        assert film.tmdb_query == ("Pelíšky", "1999")
+
+    def test_wraps_network_error_in_csfd_error(self):
+        import requests
+
+        with patch("src.core.csfd._get_page",
+                   side_effect=requests.RequestException("boom")):
+            with pytest.raises(CsfdError):
+                fetch_film("https://www.csfd.cz/film/1/")
+
+
+class TestIsFilmHref:
+    def test_accepts_single_segment_film(self):
+        assert _is_film_href("/film/2294-vykoupeni/prehled/") is True
+        assert _is_film_href("/film/2294-vykoupeni/") is True
+
+    def test_rejects_series_episode(self):
+        assert _is_film_href("/film/318290-arrow/620181-vykoupeni/prehled/") is False
+
+    def test_rejects_non_film(self):
+        assert _is_film_href("/tvurce/123-nekdo/") is False
+
+
+class TestSearchFilms:
+    def test_scopes_to_films_section_and_drops_episodes(self):
+        class _Resp:
+            text = SEARCH_HTML
+
+        with patch("src.core.csfd._get_page", return_value=_Resp()):
+            films = search_films("shawshank", limit=5)
+
+        # the Seriály-section episode link is excluded
+        assert [f.csfd_id for f in films] == [2294, 248803]
+        assert films[0].url == (
+            "https://www.csfd.cz/film/2294-vykoupeni-z-veznice-shawshank/prehled/")
+
+    def test_empty_query_returns_empty(self):
+        assert search_films("   ") == []
+
+
+class TestFindCsfdUrl:
+    def test_returns_first_hit_url(self):
+        hit = CsfdFilm(url="https://www.csfd.cz/film/2294-x/", csfd_id=2294)
+        with patch("src.core.csfd.search_films", return_value=[hit]):
+            assert find_csfd_url("shawshank 1994") == "https://www.csfd.cz/film/2294-x/"
+
+    def test_retries_without_trailing_year_when_first_query_misses(self):
+        hit = CsfdFilm(url="https://www.csfd.cz/film/221006-vratne-lahve/", csfd_id=221006)
+        calls: list[str] = []
+
+        def fake_search(query, limit=1, session=None):
+            calls.append(query)
+            return [] if query.endswith("2006") else [hit]
+
+        with patch("src.core.csfd.search_films", side_effect=fake_search):
+            assert find_csfd_url("Vratne lahve 2006") == hit.url
+        assert calls == ["Vratne lahve 2006", "Vratne lahve"]
+
+    def test_none_for_blank_query(self):
+        assert find_csfd_url("   ") is None
+
+    def test_none_when_no_results(self):
+        with patch("src.core.csfd.search_films", return_value=[]):
+            assert find_csfd_url("nic") is None
+
+
+class TestDependencies:
+    def test_dependencies_available_in_test_env(self):
+        assert csfd.dependencies_available() is True