perf(search): a one- or two-letter last word is matched whole, not as a prefix

A 1-2 letter prefix matched most of the library and ts_rank scored every
match: "m" took ~4-8 s on prod against ~150 ms now. The prefix match
starts at three characters (MIN_PREFIX_LEN); shared by the YouTube feed
and the Plex library search.

backend/app/utils.py

@@ -60,16 +60,24 @@ def now_utc() -> datetime:
     return datetime.now(timezone.utc)
 
 
+# The shortest last word that is prefix-matched. A 1–2 letter prefix matches a large share of the
+# library and ts_rank then scores every match: "m" took ~5–8 s on prod against ~100 ms for a whole
+# word (E31 S4e). A shorter last word is matched whole instead ("tv", "4k" still find themselves).
+MIN_PREFIX_LEN = 3
+
+
 def to_tsquery_str(q: str) -> str | None:
     """Turn free-text into a to_tsquery() string: word runs ANDed together, the LAST word
-    prefix-matched (`:*`) for as-you-type search — e.g. "ti amo magyar" → "ti & amo & magyar:*".
+    prefix-matched (`:*`) for as-you-type search — e.g. "ti amo magyar" → "ti & amo & magyar:*" —
+    once it has MIN_PREFIX_LEN characters ("ti amo m" → "ti & amo & m").
     Only `\\w` runs containing an alphanumeric are kept, so no tsquery operators can leak in
     (the string is built from sanitised tokens, never the raw query). Shared by the YouTube feed
     search and the Plex library search, hence this neutral home rather than either domain module."""
     tokens = [t for t in re.findall(r"\w+", q, flags=re.UNICODE) if any(c.isalnum() for c in t)]
     if not tokens:
         return None
-    tokens[-1] = tokens[-1] + ":*"
+    if len(tokens[-1]) >= MIN_PREFIX_LEN:
+        tokens[-1] = tokens[-1] + ":*"
     return " & ".join(tokens)
 
 

backend/tests/test_utils.py

@@ -1,8 +1,8 @@
-"""iso(): the single date/datetime→JSON serializer the routes share (R6 S1a)."""
+"""iso(): the single date/datetime→JSON serializer the routes share (R6 S1a); to_tsquery_str()."""
 
 from datetime import date, datetime, timezone
 
-from app.utils import iso, normalize_description
+from app.utils import iso, normalize_description, to_tsquery_str
 
 
 def test_none_maps_to_none():
@@ -56,3 +56,19 @@ def test_normalize_description_single_line_unchanged():
 def test_normalize_description_folds_crlf_line_endings():
     # splitlines() folds CR/CRLF to \n — a documented, benign line-ending normalization.
     assert normalize_description("a\r\nb\r\n\r\nc") == "a\nb\nc"
+
+
+def test_tsquery_prefix_matches_a_last_word_of_three_or_more():
+    assert to_tsquery_str("ti amo magyar") == "ti & amo & magyar:*"
+    assert to_tsquery_str("min") == "min:*"
+
+
+def test_tsquery_matches_a_short_last_word_whole():
+    # A 1-2 letter prefix made ts_rank score most of the library (5-8 s on prod, E31 S4e).
+    assert to_tsquery_str("m") == "m"
+    assert to_tsquery_str("minecraft 4k") == "minecraft & 4k"
+    assert to_tsquery_str("ti amo m") == "ti & amo & m"
+
+
+def test_tsquery_without_a_word_is_none():
+    assert to_tsquery_str("?! --") is None