Skip to content

fix: Improve Korean RRN regex pattern validation #1807

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 5 commits into from
Dec 9, 2025
Merged

fix: Improve Korean RRN regex pattern validation #1807

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
458d323
fix: Improve Korean RRN regex pattern validation
kyoungbinkim Dec 4, 2025
4949d65
Fix: correct invalid gender digits to valid ones
kyoungbinkim Dec 5, 2025
5805571
fix: Update KR_RRN test scores to match actual recognizer output
kyoungbinkim Dec 7, 2025
df8cbc2
add: invalid RRN test cases
kyoungbinkim Dec 8, 2025
a667991
Merge branch 'main' into patch-1
omri374 Dec 8, 2025
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
2 changes: 1 addition & 1 deletion ...yzer/presidio_analyzer/predefined_recognizers/country_specific/korea/kr_rrn_recognizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ class KrRrnRecognizer(PatternRecognizer):
PATTERNS = [
Pattern(
"RRN (Medium)",
r"\b\d{2}(0[1-9]|1[0-2])(0[1-9]|[1-2][0-9]|3[0-1])(-?)\d{7}\b",
r"(?<!\d)\d{2}(0[1-9]|1[0-2])(0[1-9]|[12]\d|3[01])(-?)[1-4]\d{6}(?!\d)",
0.5,
)
]
Expand Down
16 changes: 10 additions & 6 deletions presidio-analyzer/tests/test_kr_rrn_recognizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,22 +17,26 @@ def entities():
# Valid RRNs, but medium match
("960121-1234567", 1, ((0, 14),), ((0.5, 0.5),), ),
("9601211234567", 1, ((0, 13),), ((0.5, 0.5),), ),
("000505-7637892", 1, ((0, 14),), ((0.5, 0.5),), ),
("0005057637892", 1, ((0, 13),), ((0.5, 0.5),), ),
("000505-3637892", 1, ((0, 14),), ((0.5, 0.5),), ),
("0005053637892", 1, ((0, 13),), ((0.5, 0.5),), ),
("His Korean RRN is 960121-1234567", 1, ((18, 32),), ((0.5, 0.5),), ),

# Valid RRNs, strong match by validate_result()
("960121-1021413", 1, ((0, 14),), ((1.0, 1.0),), ),
("9601211021413", 1, ((0, 13),), ((1.0, 1.0),), ),
("050912-0000008", 1, ((0, 14),), ((1.0, 1.0),), ),
("0509120000008", 1, ((0, 13),), ((1.0, 1.0),), ),
("050912-2000019", 1, ((0, 14),), ((1.0, 1.0),), ),
("0509122000019", 1, ((0, 13),), ((1.0, 1.0),), ),
("His RRN is 9601211021413", 1, ((11, 24),), ((1.0, 1.0),), ),

# Invalid RRNs
("001332-1234567", 0, (), (),),
("0013321234567", 0, (), (),),
("960121+1021413", 0, (), (),),
("960121-10214131", 0, (), (),),
("960111-10214131", 0, (), (),),
("960303-0021413", 0, (), (),),
("760413-5212134", 0, (), (),),
("000402-6214431", 0, (), (),),
("051102-9234110", 0, (), (),),
],
)
def test_when_all_rrns_then_succeed(
Expand All @@ -53,4 +57,4 @@ def test_when_all_rrns_then_succeed(
fn_score = max_score
assert_result_within_score_range(
res, entities[0], st_pos, fn_pos, st_score, fn_score
)
)
Loading