Merge branch 'fix/movie-misclassified-as-show'

2 files changed, 63 insertions, 0 deletions

diff --git a/packages/meshbay-node/tests/test_enrich.py b/packages/meshbay-node/tests/test_enrich.py
index 4b957cd..a35c713 100644
--- a/packages/meshbay-node/tests/test_enrich.py
+++ b/packages/meshbay-node/tests/test_enrich.py
@@ -373,3 +373,44 @@ async def test_enricher_reads_a_three_digit_episode_number_correctly(tmp_path, m
 
     assert fields["season"] == 6
     assert fields["episode"] == 100
+
+
+@pytestmark_ffmpeg
+@pytest.mark.asyncio
+async def test_a_movie_with_a_mangled_quality_tag_is_not_shelved_as_a_series(
+        tmp_path, media_cache):
+    """
+    Found live 2026-08-29: a standalone film whose "1080p" tag was
+    truncated to "108" in the filename makes guessit invent S01E08, so
+    enrich (flat library, no season ancestor) filed it as a nonexistent
+    series. A real flat-dumped episode carries an explicit SxxExx / 1x08 /
+    "Episode N" marker; a movie has a "(2017)"-style year and none.
+    """
+    clip = tmp_path / "Some.Film.2017.MULTI.108.grp.mkv"
+    _make_clip(clip)
+    entry = IndexEntry(id="fid-trunc", name=clip.name, path=clip.name,
+                        size=clip.stat().st_size, type="video", added_at=0)
+
+    enricher = Enricher(media_cache)
+    _, fields = await _run(enricher, entry, clip)
+
+    assert fields.get("season") is None and fields.get("episode") is None, (
+        "a movie with a mangled quality tag must not become a series")
+    assert fields["display_title"]
+
+
+@pytestmark_ffmpeg
+@pytest.mark.asyncio
+async def test_a_flat_episode_with_a_real_marker_stays_a_show_even_with_a_year(
+        tmp_path, media_cache):
+    """The guard must not misfire: a genuine flat-dumped episode that also
+    carries a year has an explicit SxxExx marker and stays a show."""
+    clip = tmp_path / "Some.Show.2022.S01E02.1080p.WEB.mkv"
+    _make_clip(clip)
+    entry = IndexEntry(id="fid-marker", name=clip.name, path=clip.name,
+                        size=clip.stat().st_size, type="video", added_at=0)
+
+    enricher = Enricher(media_cache)
+    _, fields = await _run(enricher, entry, clip)
+
+    assert fields["season"] == 1 and fields["episode"] == 2
diff --git a/packages/meshbay-node/tests/test_title_parse.py b/packages/meshbay-node/tests/test_title_parse.py
index ac4d434..045635f 100644
--- a/packages/meshbay-node/tests/test_title_parse.py
+++ b/packages/meshbay-node/tests/test_title_parse.py
@@ -7,6 +7,7 @@ is a manual acceptance step (§11), not something this repo's corpus holds.
 from meshbay_node.indexer.title_parse import (
     ParsedName,
     clean_query,
+    has_episode_marker,
     leading_episode_number,
     naive_title,
     parse_episode_filename,
@@ -113,6 +114,27 @@ def test_clean_query_despaces_a_folder_name_without_eating_the_last_word():
     assert naive_title("Some.Show.Name") != "Some Show Name"  # the trap it avoids
 
 
+# ── §10.1/V14: telling a real episode marker from a mangled number ──────────
+
+def test_has_episode_marker_accepts_real_markers():
+    for name in ["Some.Show.S01E08.mkv", "some.show.s1.e8.mkv",
+                 "Some Show 1x08.mkv", "Some Show 01x08.mkv",
+                 "Some Show Episode 8.mkv", "Some Show ep08.mkv",
+                 "Some Show ep.8.mkv", "Some Show Season 1.mkv",
+                 "Une Serie Saison 3.mkv"]:
+        assert has_episode_marker(name), name
+
+
+def test_has_episode_marker_rejects_bare_numbers_and_ordinary_words():
+    # "1080p" truncated to "108", "1280" left in, a year, plain words that
+    # merely contain "ep" — none of these are episode markers.
+    for name in ["Some.Film.2017.MULTI.108.grp.mkv",
+                 "Some.Flick.2013.1280.x264-grp.mkv",
+                 "Some Movie 2017.mkv", "The Dark Knight.mkv",
+                 "Sleep 8.mkv", "Deep 8 mm.mkv", "Ocean's 11.mkv"]:
+        assert not has_episode_marker(name), name
+
+
 # ── bug 2026-08-29: guessit peels "Volume N" off the title ─────────────────
 
 def test_movie_volume_number_is_folded_back_into_the_title():