Skip to content

Fix fractional seconds in core property timestamps #1608

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

Open
ryanchou1994 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix fractional seconds in core property timestamps #1608

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 6 additions & 0 deletions src/docx/oxml/coreprops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -234,6 +234,7 @@ def _parse_W3CDTF_to_datetime(cls, w3cdtf_str: str) -> dt.datetime:
# yyyy-mm-dd e.g. "2003-12-31"
# UTC timezone e.g. "2003-12-31T10:14:55Z"
# numeric timezone e.g. "2003-12-31T10:14:55-08:00"
# fractional seconds e.g. "2003-12-31T10:14:55.123-08:00"
templates = (
"%Y-%m-%dT%H:%M:%S",
"%Y-%m-%d",
Expand All @@ -253,6 +254,11 @@ def _parse_W3CDTF_to_datetime(cls, w3cdtf_str: str) -> dt.datetime:
if dt_ is None:
tmpl = "could not parse W3CDTF datetime string '%s'"
raise ValueError(tmpl % w3cdtf_str)
fraction_match = re.fullmatch(r"\.([0-9]+)(Z|[+-][0-9]{2}:[0-9]{2})?", offset_str)
if fraction_match is not None:
fraction, offset_str = fraction_match.groups(default="")
# datetime supports microseconds; truncate any finer precision.
dt_ = dt_.replace(microsecond=int(fraction[:6].ljust(6, "0")))
if len(offset_str) == 6:
dt_ = cls._offset_dt(dt_, offset_str)
return dt_.replace(tzinfo=dt.timezone.utc)
Expand Down
54 changes: 54 additions & 0 deletions tests/opc/test_coreprops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,60 @@ def it_knows_the_date_property_values(
actual_datetime = getattr(core_properties, prop_name)
assert actual_datetime == expected_datetime

@pytest.mark.parametrize(
("prop_name", "tagname"),
[
("created", "dcterms:created"),
("modified", "dcterms:modified"),
("last_printed", "cp:lastPrinted"),
],
)
@pytest.mark.parametrize(
("str_val", "expected_datetime"),
[
("1997", dt.datetime(1997, 1, 1, tzinfo=dt.timezone.utc)),
("1997-07", dt.datetime(1997, 7, 1, tzinfo=dt.timezone.utc)),
("1997-07-16", dt.datetime(1997, 7, 16, tzinfo=dt.timezone.utc)),
("1997-07-16T19:20:30Z", dt.datetime(1997, 7, 16, 19, 20, 30, tzinfo=dt.timezone.utc)),
(
"1997-07-16T19:20:30+01:00",
dt.datetime(1997, 7, 16, 18, 20, 30, tzinfo=dt.timezone.utc),
),
(
"1997-07-16T19:20:30.45+01:00",
dt.datetime(1997, 7, 16, 18, 20, 30, 450000, tzinfo=dt.timezone.utc),
),
(
"1997-07-16T19:20:30.1234Z",
dt.datetime(1997, 7, 16, 19, 20, 30, 123400, tzinfo=dt.timezone.utc),
),
(
"1997-07-16T23:45:30.987654-05:30",
dt.datetime(1997, 7, 17, 5, 15, 30, 987654, tzinfo=dt.timezone.utc),
),
(
"1997-01-01T00:15:30.1+05:45",
dt.datetime(1996, 12, 31, 18, 30, 30, 100000, tzinfo=dt.timezone.utc),
),
(
"1997-07-16T19:20:30.123456789Z",
dt.datetime(1997, 7, 16, 19, 20, 30, 123456, tzinfo=dt.timezone.utc),
),
(
"1997-07-16T19:20:30.0Z",
dt.datetime(1997, 7, 16, 19, 20, 30, tzinfo=dt.timezone.utc),
),
("not a date", None),
],
)
def it_reads_date_properties_with_fractional_seconds(
self, prop_name: str, tagname: str, str_val: str, expected_datetime: dt.datetime | None
):
xml = self.coreProperties(tagname, str_val)
core_properties = CoreProperties(cast("CT_CoreProperties", parse_xml(xml)))

assert getattr(core_properties, prop_name) == expected_datetime

@pytest.mark.parametrize(
("prop_name", "tagname", "value", "str_val", "attrs"),
[
Expand Down