QT/superset2
1
0
Fork 0
mirror of https://github.com/apache/superset.git synced 2026-07-27 00:52:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf(date_parser): bound regex quantifiers for deterministic parsing performance (#36983)

Browse Source 
Cherry-picked from master commit 459b4cb23d

Accepted:
- Bounded \s+ to \s{1,5} and \s* to \s{0,5} in time_range_lookup regexes
- Added tests for bounded whitespace validation

Adapted:
- Preserved 6.0-release "first/1st of" patterns between modified sections
- Kept existing tests for "first of" expressions

Original author: Jean Massucatto <massucattoj@gmail.com>
This commit is contained in:
Jean Massucatto
2026-01-12 06:52:19 -03:00
committed by Joe Li
parent a9a03db940
commit 5606d5d2e3
2 changed files with 52 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
tests/unit_tests/utils/date_parser_tests.py
View File

@@ -675,3 +675,50 @@ def test_first_subunit_of_with_default_scope() -> None:
result = get_since_until("first month of the quarter")
assert result == (datetime(2016, 10, 1), datetime(2016, 11, 1))
# Tests for bounded whitespace regex patterns in time_range_lookup
@pytest.mark.parametrize(
"time_range",
[
"last 7 days : ",
"this week : ",
"start of next month : ",
"prior quarter : ",
"last 7 days : ",
"last 7 days : ",
"last 7 days : ",
"last 7 days : ",
"start of next month : ", # 5 spaces - valid
"last week : ",
"last week : ",
"last week : ",
"next 12 months : ",
"next 12 months : ",
"next 12 months : ",
"last 7days : ", # \s{0,5} allows 0 spaces after number - valid
],
)
@patch("superset.utils.date_parser.parse_human_datetime", mock_parse_human_datetime)
def test_time_range_bounded_whitespace_regex_valid(time_range: str) -> None:
"""Match expressions with 1-5 spaces between tokens."""
result = get_since_until(time_range)
assert result[0] is not None, f"Expected '{time_range}' to parse successfully"
@pytest.mark.parametrize(
"time_range",
[
"last 7 days : ",
"last7days : ",
"lastweek : ",
"last : ",
"start of : ",
"last 7 days extra : ",
],
)
@patch("superset.utils.date_parser.parse_human_datetime", mock_parse_human_datetime)
def test_time_range_bounded_whitespace_regex_invalid(time_range: str) -> None:
"""Reject expressions with 0 or 6+ spaces (fall back to DATETIME wrapping)."""
result = get_since_until(time_range)
assert result[0] is None, f"Expected '{time_range}' to NOT match bounded regex"