From 71b7a310ce938f072fe20f27eeeadd40685f1ad1 Mon Sep 17 00:00:00 2001 From: Christophe Besson Date: Sat, 29 Aug 2026 14:58:30 +0200 Subject: fix(node): correct TMDB movie matching, per-file overrides, rematch A batch of wrong poster-grid matches found live on a real library (2026-08-29): a two-volume film's second part matched the first; a numbered sequel matched a same-year making-of documentary; several entries of one franchise matched a single early entry whose localized TMDB title is the franchise name; one matched nothing. One mechanism: _tmdb_search returned the first candidate query whose title-similarity ratio merely cleared 0.6, before alternative_title / the Roman-numeral variant was ever tried. Matching: - title_parse: fold guessit's volume/part number back into display_title so the parts of a multi-part film stay distinct in the query, the card and the override. - _tmdb_search: keep a strong PASS 1 fast path (ratio >= 0.85, one request), otherwise score every candidate query and pick the best. A year-exact rescue lifts a sub-0.6 top hit to the confidence floor only when TMDB's own year-filtered result lands exactly on the filename's year. No local re-ranking of any single result list; no tmdb.py change. Fix match / rematch: - _admin_exec_tmdb_override: a movie override touches its own file only (guessit gives a whole franchise one display_title); a show override still fans out. Corrected files are marked in media_cache.tmdb_override. - media_cache: tmdb_override table; clear_file_tmdb / clear_tmdb_matches drop auto-resolved matches while sparing manual corrections. - ops.rematch_video + `meshbay-node video rematch` (loopback endpoint + CLI verb): re-resolve a group's video matches after a matcher fix. file_tmdb is keyed by content hash and otherwise only pruned on deletion, so nothing dislodged a cached match before. - a rename now drops the stale auto match too (daemon _reenrich_renamed_video_entries). UI: - VideoDetailModal shows the source filename and resolved TMDB id; an unmatched poster gets a badge (3 new video.* i18n keys x 10 locales). So a wrong match can actually be identified before hitting Fix match. docs/mediacenter.md 10.1 records this and the V8-V13 follow-up backlog (show-branch ladder, year-aware _best_match, wider sequel_variants, the 0.6-0.85 extra calls, movie grid merge, per-card rematch). Co-Authored-By: Claude Sonnet 5 Claude-Session: https://claude.ai/code/session_018BMLQjqFGCize2KtNBT79v --- .../meshbay-node/tests/test_ops_rematch_video.py | 71 ++++++++++++++++++++++ 1 file changed, 71 insertions(+) create mode 100644 packages/meshbay-node/tests/test_ops_rematch_video.py (limited to 'packages/meshbay-node/tests/test_ops_rematch_video.py') diff --git a/packages/meshbay-node/tests/test_ops_rematch_video.py b/packages/meshbay-node/tests/test_ops_rematch_video.py new file mode 100644 index 0000000..f63a1a9 --- /dev/null +++ b/packages/meshbay-node/tests/test_ops_rematch_video.py @@ -0,0 +1,71 @@ +""" +Tests for ops.rematch_video — drops a group's *auto-resolved* video->TMDB +matches so they re-resolve against the current matcher (run by the operator +after a matcher/parser fix; `media_cache.file_tmdb` is keyed by content +hash and is otherwise only pruned on deletion). Manual "Fix match" +corrections are kept. +""" + +import types + +import pytest +from meshbay_node import ops +from meshbay_node.media_cache import MediaCache + +pytestmark = pytest.mark.asyncio + + +def _indexer(*entries): + return types.SimpleNamespace(index=types.SimpleNamespace(entries=list(entries))) + + +def _entry(file_id, type_="video"): + return types.SimpleNamespace(id=file_id, type=type_) + + +@pytest.fixture +async def media_cache(tmp_path): + c = MediaCache(db_path=tmp_path / "media_cache.db") + await c.open() + yield c + await c.close() + + +async def test_no_media_cache_raises(): + with pytest.raises(ops.OpError): + await ops.rematch_video({}, "g" * 32) + + +async def test_unknown_group_raises(media_cache): + with pytest.raises(ops.OpError): + await ops.rematch_video({"media_cache": media_cache, "indexers": {}}, "nope") + + +async def test_clears_auto_matches_keeps_overrides_ignores_non_video(media_cache): + await media_cache.set_file_tmdb("v-auto-1", "10", "movie") + await media_cache.set_file_tmdb("v-auto-2", "20", "movie") + await media_cache.set_file_tmdb("v-fixed", "30", "movie") + await media_cache.mark_tmdb_override("v-fixed") + await media_cache.set_file_mbid("a-track", "some-mbid") # audio, untouched + + state = { + "media_cache": media_cache, + "indexers": {"g": _indexer( + _entry("v-auto-1"), _entry("v-auto-2"), _entry("v-fixed"), + _entry("a-track", "audio"), + )}, + } + + result = await ops.rematch_video(state, "g") + + assert result == {"status": "cleared", "removed": 2, "videos": 3, "group_id": "g"} + assert await media_cache.get_file_tmdb("v-auto-1") is None + assert await media_cache.get_file_tmdb("v-auto-2") is None + assert await media_cache.get_file_tmdb("v-fixed") == ("30", "movie") + assert await media_cache.get_file_mbid("a-track") == "some-mbid" + + +async def test_group_with_no_videos_is_a_clean_noop(media_cache): + state = {"media_cache": media_cache, "indexers": {"g": _indexer()}} + result = await ops.rematch_video(state, "g") + assert result == {"status": "cleared", "removed": 0, "videos": 0, "group_id": "g"} -- cgit v1.2.3