Skip to content

fix(analyzer): stop UsSsnRecognizer from over-blocking 987-65-432X SSNs #2074

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
AUTHENSOR wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(analyzer): stop UsSsnRecognizer from over-blocking 987-65-432X SSNs #2074

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
10 changes: 7 additions & 3 deletions ...nalyzer/presidio_analyzer/predefined_recognizers/country_specific/us/us_ssn_recognizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,8 +77,12 @@ def invalidate_result(self, pattern_text: str) -> bool:
# groups cannot be all zeros
return True

for sample_ssn in ("000", "666", "123456789", "98765432", "078051120"):
if only_digits.startswith(sample_ssn):
return True
if only_digits[:3] in ("000", "666"):
# area number (first group) is never issued by the SSA
return True

if only_digits in ("123456789", "987654320", "078051120"):
# canonical sample/placeholder SSNs published for examples
return True

return False
21 changes: 21 additions & 0 deletions presidio-analyzer/tests/test_us_ssn_recognizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,20 @@ def entities():
("078.05.1123", 1, ((0, 11),), ((0.5, 0.6),),),
("078 05 1123", 1, ((0, 11),), ((0.5, 0.6),),),
("abc 078 05 1123 abc", 1, ((4, 15),), ((0.5, 0.6),),),
# The truncated "98765432" sample literal must not prefix-block the
# neighbouring 987-65-432X family; only the canonical 987-65-4320 sample
# is invalidated (by exact match), the rest are real SSN-shaped values
("987-65-4321", 1, ((0, 11),), ((0.5, 0.6),),),
("987-65-4322", 1, ((0, 11),), ((0.5, 0.6),),),
("987-65-4323", 1, ((0, 11),), ((0.5, 0.6),),),
("987-65-4324", 1, ((0, 11),), ((0.5, 0.6),),),
("987-65-4325", 1, ((0, 11),), ((0.5, 0.6),),),
("987-65-4326", 1, ((0, 11),), ((0.5, 0.6),),),
("987-65-4327", 1, ((0, 11),), ((0.5, 0.6),),),
("987-65-4328", 1, ((0, 11),), ((0.5, 0.6),),),
("987-65-4329", 1, ((0, 11),), ((0.5, 0.6),),),
# a normal valid SSN is still detected
("219-09-9999", 1, ((0, 11),), ((0.5, 0.6),),),
# no match
("0780511201", 0, (), (),),
("078051120", 0, (), (),),
Expand All @@ -35,6 +49,13 @@ def entities():
("078-05-0000", 0, (), (),),
("078 00 1123", 0, (), (),),
("693-09.4444", 0, (), (),),
# canonical sample SSNs stay invalidated (now via exact match)
("987-65-4320", 0, (), (),),
("078-05-1120", 0, (), (),),
("123-45-6789", 0, (), (),),
# never-issued area numbers (000/666) stay invalidated via the area check
("000-12-3456", 0, (), (),),
("666-12-3456", 0, (), (),),
# fmt: on
],
)
Expand Down