Skip to content

Fix/parse time with parenthesized timezone in text #66

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
deKibi merged 4 commits into from
Jul 30, 2026
Merged

Fix/parse time with parenthesized timezone in text #66

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
5d528d3
fix: parse embedded token amounts and parenthesized UTC times
deKibi Jul 30, 2026
fd7920e
fix: narrow parser change to parenthesized timezones
deKibi Jul 30, 2026
6c91b62
test(time): document tolerant parenthesized timezone parsing
deKibi Jul 30, 2026
b596a48
fix(time): allow continuations after parenthesized timezone labels
deKibi Jul 30, 2026
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
23 changes: 23 additions & 0 deletions tests/time_converter/test_utc_time_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,9 +14,18 @@
@pytest.mark.parametrize(
("text", "timezone_label", "hour", "minute"),
[
("10:00 utc", "UTC", 10, 0),
("10:00 UTC", "UTC", 10, 0),
("10:00UTC", "UTC", 10, 0),
("10 UTC", "UTC", 10, 0),
("10:00 (UTC)", "UTC", 10, 0),
("10:00 (UTC)abc", "UTC", 10, 0),
("10:00 (UTC)+3", "UTC", 10, 0),
("10:00 (UTC)-3", "UTC", 10, 0),
("10:00 (UTC),", "UTC", 10, 0),
("10:00 (UTC).", "UTC", 10, 0),
("some text 10:00 (UTC)", "UTC", 10, 0),
("some text 10:00 (UTC)abc", "UTC", 10, 0),
("10:30 cet", "CET", 10, 30),
("10 CEST", "CEST", 10, 0),
("10:45kyiv", "KYIV", 10, 45),
Expand Down Expand Up @@ -94,6 +103,20 @@ def test_parse_utc_time_from_text_skips_non_utc_matches() -> None:
assert parsed_datetime.minute == 0


def test_parse_parenthesized_utc_time_from_long_message() -> None:
message_text = (
"Some announcement text before the schedule. Trading starts at "
"10:00 (UTC). Additional unrelated text follows after the time."
)

parsed_times = parse_times_from_text(message_text, limit=5)

assert len(parsed_times) == 1
assert parsed_times[0].timezone_label == "UTC"
assert parsed_times[0].source_datetime.hour == 10
assert parsed_times[0].source_datetime.minute == 0


@pytest.mark.parametrize(
"text",
[
Expand Down
9 changes: 6 additions & 3 deletions time_converter/utc_time_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,9 @@
# Time parsing
NAMED_TIME_PATTERN: Final[re.Pattern[str]] = re.compile(
r"(?<![\w:.\-+])(?P<hour>(?:[01]?\d|2[0-3]))"
r"(?::(?P<minute>[0-5]\d))? ?(?P<timezone>UTC|CEST|CET|KYIV)\b"
r"(?![+-])",
r"(?::(?P<minute>[0-5]\d))?"
r"(?: ?(?P<timezone>UTC|CEST|CET|KYIV)\b(?![+-])"
r"| ?\((?P<parenthesized_timezone>UTC|CEST|CET|KYIV)\))",
flags=re.IGNORECASE,
)
OFFSET_TIME_PATTERN: Final[re.Pattern[str]] = re.compile(
Expand All @@ -41,7 +42,9 @@ def _parse_named_time_match(match: re.Match[str]) -> Optional[ParsedTime]:
hour = int(match.group("hour"))
minute_group = match.group("minute")
minute = int(minute_group) if minute_group is not None else 0
timezone_label = match.group("timezone").upper()
timezone_label = (
match.group("timezone") or match.group("parenthesized_timezone")
).upper()
timezone = TIMEZONES_BY_LABEL[timezone_label]

return ParsedTime(
Expand Down
Loading