Matrix-Mirrors/anonymousland-synapse
1
0
Fork 0
mirror of https://git.anonymousland.org/anonymousland/synapse.git synced 2024-10-01 11:49:51 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #2275 from matrix-org/erikj/tweark_user_directory_search

Browse Source 
Tweak the ranking of PG user dir search
This commit is contained in:
Erik Johnston 2017-06-13 10:58:43 +01:00 committed by GitHub
commit 90ae0cffec
1 changed files with 40 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
synapse/storage/user_directory.py
View File

@ -391,11 +391,14 @@ class UserDirectoryStore(SQLBaseStore):
] ]
} }
""" """
search_query = _parse_query(self.database_engine, search_term)
if isinstance(self.database_engine, PostgresEngine): if isinstance(self.database_engine, PostgresEngine):
full_query, exact_query, prefix_query = _parse_query_postgres(search_term)
# We order by rank and then if they have profile info # We order by rank and then if they have profile info
# The ranking algorithm is hand tweaked for "best" results. Broadly
# the idea is we give a higher weight to exact matches.
# The array of numbers are the weights for the various part of the
# search: (domain, _, display name, localpart)
sql = """ sql = """
SELECT user_id, display_name, avatar_url SELECT user_id, display_name, avatar_url
FROM user_directory_search FROM user_directory_search
@ -403,13 +406,27 @@ class UserDirectoryStore(SQLBaseStore):
INNER JOIN users_in_pubic_room USING (user_id) INNER JOIN users_in_pubic_room USING (user_id)
WHERE vector @@ to_tsquery('english', ?) WHERE vector @@ to_tsquery('english', ?)
ORDER BY ORDER BY
ts_rank_cd(vector, to_tsquery('english', ?), 1) DESC, 2 * ts_rank_cd(
'{0.1, 0.1, 0.9, 1.0}',
vector,
to_tsquery('english', ?),
8
)
+ ts_rank_cd(
'{0.1, 0.1, 0.9, 1.0}',
vector,
to_tsquery('english', ?),
8
)
DESC,
display_name IS NULL, display_name IS NULL,
avatar_url IS NULL avatar_url IS NULL
LIMIT ? LIMIT ?
""" """
args = (search_query, search_query, limit + 1,) args = (full_query, exact_query, prefix_query, limit + 1,)
elif isinstance(self.database_engine, Sqlite3Engine): elif isinstance(self.database_engine, Sqlite3Engine):
search_query = _parse_query_sqlite(search_term)
sql = """ sql = """
SELECT user_id, display_name, avatar_url SELECT user_id, display_name, avatar_url
FROM user_directory_search FROM user_directory_search
@ -439,7 +456,7 @@ class UserDirectoryStore(SQLBaseStore):
}) })
def _parse_query(database_engine, search_term): def _parse_query_sqlite(search_term):
"""Takes a plain unicode string from the user and converts it into a form """Takes a plain unicode string from the user and converts it into a form
that can be passed to database. that can be passed to database.
We use this so that we can add prefix matching, which isn't something We use this so that we can add prefix matching, which isn't something
@ -451,11 +468,21 @@ def _parse_query(database_engine, search_term):
# Pull out the individual words, discarding any non-word characters. # Pull out the individual words, discarding any non-word characters.
results = re.findall(r"([\w\-]+)", search_term, re.UNICODE) results = re.findall(r"([\w\-]+)", search_term, re.UNICODE)
return " & ".join("(%s* | %s)" % (result, result,) for result in results)
if isinstance(database_engine, PostgresEngine):
return " & ".join("(%s:* | %s)" % (result, result,) for result in results) def _parse_query_postgres(search_term):
elif isinstance(database_engine, Sqlite3Engine): """Takes a plain unicode string from the user and converts it into a form
return " & ".join("(%s* | %s)" % (result, result,) for result in results) that can be passed to database.
else: We use this so that we can add prefix matching, which isn't something
# This should be unreachable. that is supported by default.
raise Exception("Unrecognized database engine") """
# Pull out the individual words, discarding any non-word characters.
results = re.findall(r"([\w\-]+)", search_term, re.UNICODE)
both = " & ".join("(%s:* | %s)" % (result, result,) for result in results)
exact = " & ".join("%s" % (result,) for result in results)
prefix = " & ".join("%s:*" % (result,) for result in results)
return both, exact, prefix