feat: Add new recognizer for IN_VOTER #1344 (#1345)

docs/supported_entities.md

@@ -85,6 +85,7 @@ For more information, refer to the [adding new recognizers documentation](analyz
 | IN_PAN     | The Indian Permanent Account Number (PAN) is a unique 12 character alphanumeric identifier issued to all business and individual entities registered as Tax Payers. | Pattern match, context |
 | IN_AADHAAR | Indian government issued unique 12 digit individual identity number                                                                                                 | Pattern match, context, and checksum |
 | IN_VEHICLE_REGISTRATION | Indian government issued transport (govt, personal, diplomatic, defence)  vehicle registration number                                                               | Pattern match, context, and checksum |
+| IN_VOTER | Indian Election Commission issued 10 digit alpha numeric voter id for all indian citizens (age 18 or above) | Pattern match, context |
 | IN_PASSPORT | Indian Passport Number | Pattern match, Context |
 
 ### Finland

presidio-analyzer/presidio_analyzer/predefined_recognizers/__init__.py

@@ -38,7 +38,7 @@
 from .in_aadhaar_recognizer import InAadhaarRecognizer
 from .in_vehicle_registration_recognizer import InVehicleRegistrationRecognizer
 from .sg_uen_recognizer import SgUenRecognizer
-
+from .in_voter_recognizer import InVoterRecognizer
 from .in_passport_recognizer import InPassportRecognizer
 from .fi_personal_identity_code_recognizer import FiPersonalIdentityCodeRecognizer
 
@@ -86,7 +86,7 @@
     "InAadhaarRecognizer",
     "InVehicleRegistrationRecognizer",
     "SgUenRecognizer",
-
+    "InVoterRecognizer",
     "InPassportRecognizer",
     "FiPersonalIdentityCodeRecognizer",
 ]

presidio-analyzer/presidio_analyzer/predefined_recognizers/in_voter_recognizer.py

@@ -0,0 +1,57 @@
+from typing import Optional, List
+from presidio_analyzer import Pattern, PatternRecognizer
+
+
+class InVoterRecognizer(PatternRecognizer):
+    """
+    Recognize Indian Voter/Election Id(EPIC).
+
+    The Elector's Photo Identity Card or Voter id is a ten digit
+    alpha-numeric code issued by Election Commission of India
+    to adult domiciles who have reached the age of 18
+    Ref: https://en.wikipedia.org/wiki/Voter_ID_(India)
+
+    :param patterns: List of patterns to be used by this recognizer
+    :param context: List of context words to increase confidence in detection
+    :param supported_language: Language this recognizer supports
+    :param supported_entity: The entity this recognizer can detect
+    :param replacement_pairs: List of tuples with potential replacement values
+    for different strings to be used during pattern matching.
+    This can allow a greater variety in input, for example by removing dashes or spaces.
+    """
+
+    PATTERNS = [
+        Pattern(
+            "VOTER",
+            r"\b([A-Za-z]{1}[ABCDGHJKMNPRSYabcdghjkmnprsy]{1}[A-Za-z]{1}([0-9]){7})\b",
+            0.4,
+        ),
+        Pattern(
+            "VOTER",
+            r"\b([A-Za-z]){3}([0-9]){7}\b",
+            0.3,
+        ),
+    ]
+
+    CONTEXT = [
+        "voter",
+        "epic",
+        "elector photo identity card",
+    ]
+
+    def __init__(
+        self,
+        patterns: Optional[List[Pattern]] = None,
+        context: Optional[List[str]] = None,
+        supported_language: str = "en",
+        supported_entity: str = "IN_VOTER",
+    ):
+
+        patterns = patterns if patterns else self.PATTERNS
+        context = context if context else self.CONTEXT
+        super().__init__(
+            patterns=patterns,
+            context=context,
+            supported_language=supported_language,
+            supported_entity=supported_entity,
+        )

presidio-analyzer/presidio_analyzer/recognizer_registry.py

@@ -47,6 +47,7 @@
     PlPeselRecognizer,
     InAadhaarRecognizer,
     InVehicleRegistrationRecognizer,
+    InVoterRecognizer,
     InPassportRecognizer,
 )
 
@@ -106,6 +107,7 @@ def load_predefined_recognizers(
                 InPanRecognizer,
                 InAadhaarRecognizer,
                 InVehicleRegistrationRecognizer,
+                InVoterRecognizer,
                 InPassportRecognizer,
             ],
             "es": [EsNifRecognizer],

presidio-analyzer/tests/test_in_voter_recognizer.py

@@ -0,0 +1,52 @@
+import pytest
+
+from tests import assert_result
+from presidio_analyzer.predefined_recognizers import InVoterRecognizer
+
+
+@pytest.fixture(scope="module")
+def recognizer():
+    return InVoterRecognizer()
+
+
+@pytest.fixture(scope="module")
+def entities():
+    return ["IN_VOTER"]
+
+
+@pytest.mark.parametrize(
+    "text, expected_len, expected_position, expected_score",
+    [
+        # fmt: off
+        # valid
+        ("KSD1287349", 1, (0, 10), 0.4),
+        ("my voter: DBJ2289013", 1, (10, 20), (0.4)),
+        ("uzb2345117", 1, (0, 10), 0.3),
+        ("this MUP5632811", 1, (5, 15), 0.3),
+        ("You can vote with your CPJ4467918 number", 1, (23, 33), 0.4),
+        # invalid
+        ("zxdf8923q1", 0, (), (),),
+        ("A8923571WZ", 0, (), (),),
+        # fmt: on
+    ],
+)
+def test_when_voter_in_text_then_all_voter_found(
+    text,
+    expected_len,
+    expected_position,
+    expected_score,
+    recognizer,
+    entities,
+):
+    results = recognizer.analyze(text, entities)
+    print(results)
+
+    assert len(results) == expected_len
+    if results:
+        assert_result(
+            results[0],
+            entities[0],
+            expected_position[0],
+            expected_position[1],
+            expected_score,
+        )

presidio-analyzer/tests/test_recognizer_registry.py

@@ -57,8 +57,8 @@ def test_when_get_recognizers_then_all_recognizers_returned(mock_recognizer_regi
     registry = mock_recognizer_registry
     registry.load_predefined_recognizers()
     recognizers = registry.get_recognizers(language="en", all_fields=True)
-    # 1 custom recognizer in english + 24 predefined
-    assert len(recognizers) == 1 + 25
+    # 1 custom recognizer in english + 26 predefined
+    assert len(recognizers) == 1 + 26
 
 
 def test_when_get_recognizers_then_return_all_fields(mock_recognizer_registry):