Add Indian UPI ID recognizer for NPCI payment compliance

presidio-analyzer/presidio_analyzer/predefined_recognizers/__init__.py

@@ -50,6 +50,7 @@
 from .country_specific.india.in_pan_recognizer import InPanRecognizer
 from .country_specific.india.in_passport_recognizer import InPassportRecognizer
 from .country_specific.india.in_voter_recognizer import InVoterRecognizer
+from .country_specific.india.in_upi_recognizer import InUpiRecognizer
 
 # Italy recognizers
 from .country_specific.italy.it_driver_license_recognizer import (
@@ -221,6 +222,7 @@
     "SgUenRecognizer",
     "InVoterRecognizer",
     "InPassportRecognizer",
+    "InUpiRecognizer",
     "FiPersonalIdentityCodeRecognizer",
     "EsNieRecognizer",
     "EsPassportRecognizer",

presidio-analyzer/presidio_analyzer/predefined_recognizers/country_specific/india/__init__.py

@@ -1,11 +1,11 @@
 """India-specific recognizers."""
-
 from .in_aadhaar_recognizer import InAadhaarRecognizer
 from .in_gstin_recognizer import InGstinRecognizer
 from .in_pan_recognizer import InPanRecognizer
 from .in_passport_recognizer import InPassportRecognizer
 from .in_vehicle_registration_recognizer import InVehicleRegistrationRecognizer
 from .in_voter_recognizer import InVoterRecognizer
+from .in_upi_recognizer import InUpiRecognizer
 
 __all__ = [
     "InAadhaarRecognizer",
@@ -14,4 +14,5 @@
     "InVoterRecognizer",
     "InVehicleRegistrationRecognizer",
     "InPassportRecognizer",
-]
+    "InUpiRecognizer",
+]

presidio-analyzer/presidio_analyzer/predefined_recognizers/country_specific/india/in_upi_recognizer.py

@@ -0,0 +1,65 @@
+from typing import List, Optional
+from presidio_analyzer import Pattern, PatternRecognizer
+
+
+class InUpiRecognizer(PatternRecognizer):
+    """
+    Recognizes Indian UPI (Unified Payments Interface) IDs.
+
+    UPI IDs are used for digital payments in India and follow the format:
+    username@bankhandle (e.g., shaurya@okicici, 9876543210@paytm)
+
+    Common UPI handles include: okicici, okhdfcbank, okaxis, paytm,
+    ybl, upi, apl, ibl, axl, timecosmos, waicici, wahdfcbank
+
+    This recognizer identifies UPI IDs using regex and context words.
+    Reference: https://www.npci.org.in/what-we-do/upi/product-overview
+
+    :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
+    """
+
+    COUNTRY_CODE = "in"
+
+    PATTERNS = [
+        Pattern(
+            "UPI ID (High)",
+            r"\b([a-zA-Z0-9.\-_]{2,256}@(okicici|okhdfcbank|okaxis|oksbi|paytm|ybl|upi|apl|ibl|axl|waicici|wahdfcbank|timecosmos|rapl|mbk|ikwik|freecharge))\b",
+            0.7,
+        ),
+        Pattern(
+            "UPI ID (Medium)",
+            r"\b([a-zA-Z0-9.\-_]{2,256}@[a-zA-Z]{2,64})\b",
+            0.4,
+        ),
+    ]
+
+    CONTEXT = [
+        "upi",
+        "upi id",
+        "payment",
+        "gpay",
+        "phonepe",
+        "paytm",
+        "bhim",
+        "transfer",
+        "pay",
+    ]
+
+    def __init__(
+        self,
+        patterns: Optional[List[Pattern]] = None,
+        context: Optional[List[str]] = None,
+        supported_language: str = "en",
+        supported_entity: str = "IN_UPI",
+    ):
+        patterns = patterns if patterns else self.PATTERNS
+        context = context if context else self.CONTEXT
+        super().__init__(
+            supported_entity=supported_entity,
+            patterns=patterns,
+            context=context,
+            supported_language=supported_language,
+        )

presidio-analyzer/tests/test_in_upi_recognizer.py

@@ -0,0 +1,56 @@
+import pytest
+from tests import assert_result
+from presidio_analyzer.predefined_recognizers import InUpiRecognizer
+
+
+@pytest.fixture(scope="module")
+def recognizer():
+    return InUpiRecognizer()
+
+
+@pytest.fixture(scope="module")
+def entities():
+    return ["IN_UPI"]
+
+
+@pytest.mark.parametrize(
+    "text, expected_len, expected_position, expected_score",
+    [
+        # fmt: off
+        # Valid UPI IDs with known handles (High confidence)
+        ("shaurya@okicici", 1, (0, 15), 0.7),
+        ("9876543210@paytm", 1, (0, 16), 0.7),
+        ("john.doe@okhdfcbank", 1, (0, 19), 0.7),
+        ("user123@ybl", 1, (0, 11), 0.7),
+
+        # Valid UPI IDs with unknown handles (Medium confidence)
+        ("myname@somebank", 1, (0, 15), 0.4),
+
+        # Invalid UPI IDs
+        ("notaupiid", 0, (), ()),
+        ("@okicici", 0, (), ()),
+
+        # UPI in sentence
+        ("Please pay to shaurya@okicici for the order", 1, (14, 29), 0.7),
+        # fmt: on
+    ],
+)
+def test_when_upi_in_text_then_all_upis_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,
+        )