Matrix-Mirrors/anonymousland-synapse
1
0
Fork 0
mirror of https://git.anonymousland.org/anonymousland/synapse.git synced 2025-07-24 06:10:50 -04:00
Code Issues Projects Releases Packages Wiki Activity

Fix a bug introduced in Synapse v1.74.0 where searching with colons when using ICU for search term tokenisation would fail with an error. (#15079)

Browse source 
Co-authored-by: David Robertson <davidr@element.io>
This commit is contained in:
reivilibre 2023-02-20 12:00:18 +00:00 • committed by GitHub
parent 7ee7f49316
commit 1cbc3f197c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 90 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

24
synapse/storage/databases/main/user_directory.py
View file

@ -918,11 +918,19 @@ def _parse_query_postgres(search_term: str) -> Tuple[str, str, str]:
We use this so that we can add prefix matching, which isn't something
that is supported by default.
"""
results = _parse_words(search_term)
escaped_words = []
for word in _parse_words(search_term):
# Postgres tsvector and tsquery quoting rules:
# words potentially containing punctuation should be quoted
# and then existing quotes and backslashes should be doubled
# See: https://www.postgresql.org/docs/current/datatype-textsearch.html#DATATYPE-TSQUERY
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)
quoted_word = word.replace("'", "''").replace("\\", "\\\\")
escaped_words.append(f"'{quoted_word}'")
both = " & ".join("(%s:* | %s)" % (word, word) for word in escaped_words)
exact = " & ".join("%s" % (word,) for word in escaped_words)
prefix = " & ".join("%s:*" % (word,) for word in escaped_words)
return both, exact, prefix
@ -944,6 +952,14 @@ def _parse_words(search_term: str) -> List[str]:
if USE_ICU:
return _parse_words_with_icu(search_term)
return _parse_words_with_regex(search_term)
def _parse_words_with_regex(search_term: str) -> List[str]:
"""
Break down search term into words, when we don't have ICU available.
See: `_parse_words`
"""
return re.findall(r"([\w\-]+)", search_term, re.UNICODE)