Skip to content

Fix ISO 8601 date pattern accepting impossible month/day values #2113

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
SharonHart merged 3 commits into from
Jul 5, 2026
Merged

Fix ISO 8601 date pattern accepting impossible month/day values #2113

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
72e86dc
Fix ISO 8601 date pattern accepting impossible month/day values
jichaowang02-lang Jun 27, 2026
b63950a
Address review: apply word boundary across all alternatives, rename p…
jichaowang02-lang Jul 2, 2026
603929c
Merge branch 'main' into fix/date-iso8601-month-day-range
SharonHart Jul 5, 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
4 changes: 2 additions & 2 deletions presidio-analyzer/presidio_analyzer/predefined_recognizers/generic/date_recognizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,8 +15,8 @@ class DateRecognizer(PatternRecognizer):

PATTERNS = [
Pattern(
"ISO 8601 datetime",
r"\b(\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d:[0-5]\d\.\d+([+-][0-2]\d:[0-5]\d|Z))|(\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z))|(\d{4}-[01]\d-[0-3]\dT[0-2]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z))\b",
"Datetime (yyyy-mm-ddThh:mm[:ss[.f]] with timezone)",
r"\b(?:(\d{4}-(?:0[1-9]|1[0-2])-(?:0[1-9]|[12]\d|3[01])T[0-2]\d:[0-5]\d:[0-5]\d\.\d+([+-][0-2]\d:[0-5]\d|Z))|(\d{4}-(?:0[1-9]|1[0-2])-(?:0[1-9]|[12]\d|3[01])T[0-2]\d:[0-5]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z))|(\d{4}-(?:0[1-9]|1[0-2])-(?:0[1-9]|[12]\d|3[01])T[0-2]\d:[0-5]\d([+-][0-2]\d:[0-5]\d|Z)))\b",
0.8,
),
Pattern(
Expand Down
10 changes: 10 additions & 0 deletions presidio-analyzer/tests/test_date_recognizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,17 @@ def entities():
("Today is 2024-03-15T14:30:00Z\r or not?", 1, ((9, 29),), ((0.6, 0.81),),),
("Today is 2024-03-15T14:30Z\n or not?", 1, ((9, 26),), ((0.6, 0.81),),),
("2024-03-15T14:30Z", 1, ((0, 17),), ((0.6, 1),),),
# Invalid ISO 8601 month/day values must not be detected as a date
("2024-13-15T14:30:00Z", 0, (), (),),
("2024-00-15T14:30:00Z", 0, (), (),),
("2024-12-32T14:30Z", 0, (), (),),
("2024-12-00T14:30Z", 0, (), (),),
("Today is2024-06-05T09:15:30.500-07:00", 0, (), (),),
# The leading `\b` must apply to every alternative in the pattern,
# not just the first one. Without a non-capturing wrapper, the
# seconds and minutes-only alternatives could match mid-word.
("Today is2024-03-15T14:30:00+02:00", 0, (), (),),
("Today is2024-03-15T14:30Z", 0, (), (),),
# Word boundary tests
("Today is5/21", 0, (), (),),
("Today is5/21and it's sunny", 0, (), (),),
Expand Down
Loading