Skip to content

Pages Query: use $text search or prefix search #2415

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tw4l merged 4 commits into from
Feb 20, 2025
Merged

Pages Query: use $text search or prefix search #2415

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f0a884e
try $text for title, $gte for urls
ikreymer Feb 20, 2025
b2f343f
Adjust test
tw4l Feb 20, 2025
f5cd451
Call lower correctly
tw4l Feb 20, 2025
7f0457b
Remove commented out code
tw4l Feb 20, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 17 additions & 5 deletions backend/btrixcloud/pages.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,7 @@ async def init_index(self):
("ts", pymongo.ASCENDING),
]
)
await self.pages.create_index([("title", "text")])

async def set_ops(self, background_job_ops: BackgroundJobOps):
"""Set ops classes as needed"""
Expand Down Expand Up @@ -759,12 +760,14 @@ async def list_replay_query_pages(
if org:
query["oid"] = org.id

is_text_search = False
if search:
search_regex = re.escape(urllib.parse.unquote(search))
query["$or"] = [
{"url": {"$regex": search_regex, "$options": "i"}},
{"title": {"$regex": search_regex, "$options": "i"}},
]
search = urllib.parse.unquote(search)
if search.startswith("http:") or search.startswith("https:"):
query["url"] = {"$gte": search}
else:
query["$text"] = {"$search": search}
is_text_search = True

elif url_prefix:
url_prefix = urllib.parse.unquote(url_prefix)
Expand Down Expand Up @@ -805,6 +808,15 @@ async def list_replay_query_pages(
raise HTTPException(status_code=400, detail="invalid_sort_direction")

aggregate.extend([{"$sort": {sort_by: sort_direction}}])
elif search:
if is_text_search:
aggregate.extend(
[
{"$sort": {"score": {"$meta": "textScore"}}},
]
)
else:
aggregate.extend([{"$sort": {"url": 1}}])
else:
# default sort: seeds first, then by timestamp
aggregate.extend([{"$sort": {"isSeed": -1, "ts": 1}}])
Expand Down
7 changes: 4 additions & 3 deletions backend/test/test_collections.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -643,12 +643,13 @@ def test_list_pages_in_collection(crawler_auth_headers, default_org_id):
coll_page_ts = coll_page["ts"]
coll_page_title = coll_page["title"]

# Test search filter
partial_title = coll_page_title[:5]
# Test search filter, make sure text search isn't case sensitive
partial_title = "Archiving"
partial_title_lower = partial_title.lower()
partial_url = coll_page_url[:8]

r = requests.get(
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}/pages?search={partial_title}",
f"{API_PREFIX}/orgs/{default_org_id}/collections/{_coll_id}/pages?search={partial_title_lower}",
headers=crawler_auth_headers,
)
assert r.status_code == 200
Expand Down
Loading