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.
This commit is contained in:
@@ -30,7 +30,7 @@ from app.models import (
|
||||
Video,
|
||||
VideoState,
|
||||
)
|
||||
from app.utils import iso, to_tsquery_str
|
||||
from app.utils import iso, like_escape, to_tsquery_str
|
||||
|
||||
|
||||
def _channel_url(channel_id: str, handle: str | None) -> str:
|
||||
@@ -272,8 +272,9 @@ def filtered_query(
|
||||
# `unaccent(channels.title) ILIKE '%q%'` straight into the per-video predicate defeated the
|
||||
# search_vector GIN — the planner detoasted every non-matching tsvector to test the `@@`
|
||||
# (~2.6s/search on the prod-sized set); channel_id.in_(...) keeps the GIN as a BitmapOr branch
|
||||
# (PERF-12). Empty match -> false() so the OR collapses to the text match alone.
|
||||
like = func.unaccent(f"%{q}%")
|
||||
# (PERF-12). Empty match -> false() so the OR collapses to the text match alone. The query
|
||||
# is a literal inside the pattern: `_` in `my_channel` is not a wildcard.
|
||||
like = func.unaccent(f"%{like_escape(q)}%")
|
||||
matching_channel_ids = (
|
||||
db.execute(select(Channel.id).where(func.unaccent(Channel.title).ilike(like)))
|
||||
.scalars()
|
||||
|
||||
@@ -298,10 +298,6 @@ class LibraryFilters:
|
||||
}
|
||||
|
||||
|
||||
def like_escape(s: str) -> str:
|
||||
return s.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
|
||||
|
||||
|
||||
# --- Watch-state scope (shared by the /library grid AND the /facets aggregation) ---------------
|
||||
#
|
||||
# The `show` scope (all | watched | in_progress | unwatched) filters the browse result by per-user
|
||||
|
||||
@@ -24,7 +24,8 @@ from app.plex import sync as plex_sync
|
||||
from app.plex.cards import movie_card, show_card
|
||||
from app.plex.client import PlexClient, PlexError, PlexNotConfigured
|
||||
from app.plex.lookups import by_rating_key
|
||||
from app.plex.query import content_libs, like_escape, runtime_by_key, top_art_keys
|
||||
from app.plex.query import content_libs, runtime_by_key, top_art_keys
|
||||
from app.utils import like_escape
|
||||
|
||||
# The most-restrictive → least ordering used to pick a collection's effective content rating from its
|
||||
# members (Plex shows one cert on the collection; we don't store it, so derive it).
|
||||
|
||||
@@ -38,6 +38,7 @@ from app.models import (
|
||||
VideoState,
|
||||
)
|
||||
from app.feedquery import feed_columns, serialize
|
||||
from app.utils import like_escape
|
||||
from app.sync.subscriptions import apply_channel_details
|
||||
from app.sync.videos import insert_stubs, apply_video_details, parse_dt
|
||||
from app.youtube import search_scrape
|
||||
@@ -224,6 +225,25 @@ def _new_first(db: Session, user: User, ids: list[str]) -> list[str]:
|
||||
return [i for i in ids if i not in have] + [i for i in ids if i in have]
|
||||
|
||||
|
||||
def _fold_term(db: Session, video_ids: list[str], term: str) -> None:
|
||||
"""Append `term` to each video's space-joined `search_terms`, unless it is already one of them.
|
||||
|
||||
"Already one of them" is a whole-term match, as a literal: a substring test skipped `cat` on a
|
||||
video already found for `category`, and an unescaped one read the `_` in `my_channel` as a
|
||||
wildcard — either way the term was never folded in, and local search lost that relevance."""
|
||||
padded = func.concat(" ", func.coalesce(Video.search_terms, ""), " ")
|
||||
db.execute(
|
||||
update(Video)
|
||||
.where(Video.id.in_(video_ids))
|
||||
.where(padded.notilike(f"% {like_escape(term)} %"))
|
||||
.values(
|
||||
search_terms=func.trim(
|
||||
func.coalesce(Video.search_terms, "").op("||")(" ").op("||")(term)
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@router.get("/youtube")
|
||||
def search_youtube(
|
||||
q: str | None = None,
|
||||
@@ -364,16 +384,7 @@ def search_youtube(
|
||||
.values([{"user_id": user.id, "video_id": vid} for vid in ordered])
|
||||
.on_conflict_do_nothing(index_elements=["user_id", "video_id"])
|
||||
)
|
||||
db.execute(
|
||||
update(Video)
|
||||
.where(Video.id.in_(ordered))
|
||||
.where(func.coalesce(Video.search_terms, "").notilike(f"%{term}%"))
|
||||
.values(
|
||||
search_terms=func.trim(
|
||||
func.coalesce(Video.search_terms, "").op("||")(" ").op("||")(term)
|
||||
)
|
||||
)
|
||||
)
|
||||
_fold_term(db, ordered, term)
|
||||
db.commit()
|
||||
|
||||
ordered = _new_first(db, user, ordered)
|
||||
|
||||
@@ -73,6 +73,14 @@ def to_tsquery_str(q: str) -> str | None:
|
||||
return " & ".join(tokens)
|
||||
|
||||
|
||||
def like_escape(s: str) -> str:
|
||||
"""`s` as a LITERAL inside a LIKE/ILIKE pattern: `%` and `_` are wildcards there, and `\\` is
|
||||
Postgres's default escape character, so all three are escaped. Every pattern built from text a
|
||||
person typed goes through this — unescaped, a search for `100%` or `my_channel` matches rows it
|
||||
should not."""
|
||||
return s.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
|
||||
|
||||
|
||||
def normalize_description(text: str | None) -> str | None:
|
||||
"""Strip whitespace-only lines from a CHANNEL description before storing. YouTube channel
|
||||
descriptions pad their contact/link blocks with runs of blank lines; keeping them wastes storage,
|
||||
|
||||
Reference in New Issue
Block a user