fix(search): typed text is a literal in every LIKE pattern

The feed's channel-name match and the live search's term fold built their LIKE pattern from the typed text as it was, so `_` and `%` acted as wildcards: `build_log` also matched `buildXlog`. The term fold also tested a substring, so a term already present inside a longer word (`cat` in `category`) was never folded into search_terms. It now compares whole terms, escaped. `like_escape` moves from the Plex query module to `app.utils`, beside `to_tsquery_str`, and every pattern built from typed text goes through it.
2026-09-19 01:33:32 +02:00
parent 59fd068711
commit 66dbd0af81
6 changed files with 116 additions and 18 deletions
@@ -0,0 +1,81 @@
+"""What a person types is a literal inside a LIKE pattern, never a wildcard (DB-lane).
+
+`%` and `_` are LIKE wildcards. The feed's channel-name match and the live search's term fold both
+built their pattern from the typed text as it was, so `my_channel` also matched `myXchannel`, and a
+term already present as part of a longer word was never folded in.
+"""
+
+from datetime import datetime, timezone
+
+from sqlalchemy import select
+
+from app.models import Channel, Subscription, Video
+from app.routes.search import _fold_term
+
+
+def _video(vid: str, ch: str, title: str, search_terms: str | None = None) -> Video:
+    return Video(
+        id=vid,
+        channel_id=ch,
+        published_at=datetime(2024, 1, 1, tzinfo=timezone.utc),
+        title=title,
+        is_short=False,
+        live_status="none",
+        via_search=False,
+        via_explore=False,
+        search_terms=search_terms,
+    )
+
+
+def test_an_underscore_in_a_feed_search_matches_only_itself(db, as_user, make_user):
+    user = make_user()
+    db.add_all(
+        [
+            Channel(id="UCunder", title="build_log daily", subscriber_count=1),
+            Channel(id="UClookalike", title="buildXlog daily", subscriber_count=1),
+        ]
+    )
+    db.add_all(
+        [
+            Subscription(user_id=user.id, channel_id=ch, priority=0, hidden=False)
+            for ch in ("UCunder", "UClookalike")
+        ]
+    )
+    db.add_all(
+        [
+            _video("vidUnder", "UCunder", "Nothing in common"),
+            _video("vidLook", "UClookalike", "Nothing in common either"),
+        ]
+    )
+    db.commit()
+
+    resp = as_user(user).get("/api/feed?q=build_log&show=all&limit=50")
+
+    assert resp.status_code == 200, resp.text
+    assert {it["id"] for it in resp.json()["items"]} == {"vidUnder"}
+
+
+def test_a_term_is_folded_in_unless_it_is_already_a_whole_term(db):
+    db.add(Channel(id="UCfold", title="Fold", subscriber_count=1))
+    db.add_all(
+        [
+            _video("vidWord", "UCfold", "a", search_terms="category"),
+            _video("vidWild", "UCfold", "b", search_terms="catXdog"),
+            _video("vidHas", "UCfold", "c", search_terms="old cat_dog new"),
+            _video("vidNone", "UCfold", "d"),
+        ]
+    )
+    db.commit()
+
+    _fold_term(db, ["vidWord", "vidWild", "vidHas", "vidNone"], "cat")
+    _fold_term(db, ["vidWild", "vidHas"], "cat_dog")
+    db.commit()
+    db.expire_all()
+
+    terms = dict(db.execute(select(Video.id, Video.search_terms)).all())
+    assert terms == {
+        "vidWord": "category cat",
+        "vidWild": "catXdog cat cat_dog",
+        "vidHas": "old cat_dog new cat",
+        "vidNone": "cat",
+    }