DataFog · pranjalparmar · May 19, 2026 · May 19, 2026 · May 19, 2026 · May 22, 2026
diff --git a/datafog/core.py b/datafog/core.py
@@ -210,14 +210,21 @@ def get_supported_entities() -> List[str]:
     Example:
         >>> entities = get_supported_entities()
         >>> print(entities)
-        ['EMAIL', 'PHONE', 'SSN', 'CREDIT_CARD', 'IP_ADDRESS', 'DOB', 'ZIP']
+        ['EMAIL', 'PHONE', 'SSN', 'CREDIT_CARD', 'IP_ADDRESS', 'DE_VAT_ID', 'DE_IBAN', 'DE_TAX_ID', 'DE_SOCIAL_SECURITY_NUMBER', 'DE_POSTAL_CODE', 'DE_PASSPORT_NUMBER', 'DE_RESIDENCE_PERMIT_NUMBER', 'DATE', 'ZIP_CODE']
     """
     result = [
         "EMAIL",
         "PHONE",
         "SSN",
         "CREDIT_CARD",
         "IP_ADDRESS",
+        "DE_VAT_ID",
+        "DE_IBAN",
+        "DE_TAX_ID",
+        "DE_SOCIAL_SECURITY_NUMBER",
+        "DE_POSTAL_CODE",
+        "DE_PASSPORT_NUMBER",
+        "DE_RESIDENCE_PERMIT_NUMBER",
         "DATE",
         "ZIP_CODE",
     ]

diff --git a/datafog/engine.py b/datafog/engine.py
@@ -31,6 +31,13 @@
     "SSN",
     "CREDIT_CARD",
     "IP_ADDRESS",
+    "DE_VAT_ID",
+    "DE_IBAN",
+    "DE_TAX_ID",
+    "DE_SOCIAL_SECURITY_NUMBER",
+    "DE_POSTAL_CODE",
+    "DE_PASSPORT_NUMBER",
+    "DE_RESIDENCE_PERMIT_NUMBER",
     "DATE",
     "ZIP_CODE",
     "PERSON",

diff --git a/datafog/processing/text_processing/regex_annotator/regex_annotator.py b/datafog/processing/text_processing/regex_annotator/regex_annotator.py
@@ -28,7 +28,22 @@ class RegexAnnotator:
     """
 
     # Labels for PII entities
-    LABELS = ["EMAIL", "PHONE", "SSN", "CREDIT_CARD", "IP_ADDRESS", "DOB", "ZIP"]
+    LABELS = [
+        "EMAIL",
+        "PHONE",
+        "SSN",
+        "CREDIT_CARD",
+        "IP_ADDRESS",
+        "DOB",
+        "ZIP",
+        "DE_VAT_ID",
+        "DE_IBAN",
+        "DE_TAX_ID",
+        "DE_SOCIAL_SECURITY_NUMBER",
+        "DE_POSTAL_CODE",
+        "DE_PASSPORT_NUMBER",
+        "DE_RESIDENCE_PERMIT_NUMBER",
+    ]
 
     def __init__(self):
         # Compile all patterns once at initialization
@@ -175,6 +190,84 @@ def __init__(self):
                 """,
                 re.IGNORECASE | re.MULTILINE | re.VERBOSE,
             ),
+            # German VAT ID (USt-IdNr) - DE followed by 9 digits
+            "DE_VAT_ID": re.compile(
+                r"""
+                (?<![A-Za-z0-9])
+                DE
+                [\s-]?
+                \d{9}
+                (?![A-Za-z0-9])
+                """,
+                re.IGNORECASE | re.MULTILINE | re.VERBOSE,
+            ),
+            # German IBAN - DE followed by 20 digits (often grouped)
+            "DE_IBAN": re.compile(
+                r"""
+                (?<![A-Za-z0-9])
+                DE
+                \d{2}
+                (?:\s?\d{4}){4}
+                \s?\d{2}
+                (?![A-Za-z0-9])
+                """,
+                re.IGNORECASE | re.MULTILINE | re.VERBOSE,
+            ),
+            # German Tax ID (Steuer-ID) - 11 digits
+            "DE_TAX_ID": re.compile(
+                r"""
+                (?<![A-Za-z0-9])
+                (?:\d{11}|\d{2}\s?\d{3}\s?\d{3}\s?\d{3})
+                (?![A-Za-z0-9])
+                """,
+                re.IGNORECASE | re.MULTILINE | re.VERBOSE,
+            ),
+            # German Social Security Number (Rentenversicherungsnummer)
+            # Format: 2 digits + 6 digits (DOB) + 1 letter + 3 digits
+            "DE_SOCIAL_SECURITY_NUMBER": re.compile(
+                r"""
+                (?<![A-Za-z0-9])
+                \d{2}
+                \s?
+                \d{6}
+                \s?
+                [A-Z]
+                \s?
+                \d{3}
+                (?![A-Za-z0-9])
+                """,
+                re.IGNORECASE | re.MULTILINE | re.VERBOSE,
+            ),
+            # German postal code - prefixed format (PLZ/DE/D followed by 5 digits)
+            "DE_POSTAL_CODE": re.compile(
+                r"""
+                (?<![A-Za-z0-9])
+                (?:PLZ|DE|D)
+                \d{5}
+                (?![A-Za-z0-9])
+                """,
+                re.IGNORECASE | re.MULTILINE | re.VERBOSE,
+            ),
+            # German passport number - 1 letter followed by 8 digits
+            "DE_PASSPORT_NUMBER": re.compile(
+                r"""
+                (?<![A-Za-z0-9])
+                [A-Z]
+                \d{8}
+                (?![A-Za-z0-9])
+                """,
+                re.IGNORECASE | re.MULTILINE | re.VERBOSE,
+            ),
+            # German residence permit number - AT followed by 7 digits
+            "DE_RESIDENCE_PERMIT_NUMBER": re.compile(
+                r"""
+                (?<![A-Za-z0-9])
+                AT
+                \d{7}
+                (?![A-Za-z0-9])
+                """,
+                re.IGNORECASE | re.MULTILINE | re.VERBOSE,
+            ),
         }
 
     @classmethod

diff --git a/tests/corpus/structured_pii.json b/tests/corpus/structured_pii.json
@@ -733,5 +733,89 @@
         "end": 5
       }
     ]
+  },
+  {
+    "id": "de-vat-id-simple",
+    "input": "VAT number: DE123456789 for invoices.",
+    "expected_entities": [
+      {
+        "type": "DE_VAT_ID",
+        "text": "DE123456789",
+        "start": 12,
+        "end": 23
+      }
+    ]
+  },
+  {
+    "id": "de-iban-formatted",
+    "input": "IBAN: DE89 3704 0044 0532 0130 00 for payments.",
+    "expected_entities": [
+      {
+        "type": "DE_IBAN",
+        "text": "DE89 3704 0044 0532 0130 00",
+        "start": 6,
+        "end": 33
+      }
+    ]
+  },
+  {
+    "id": "de-tax-id-simple",
+    "input": "Steuer-ID 12345678901 liegt vor.",
+    "expected_entities": [
+      {
+        "type": "DE_TAX_ID",
+        "text": "12345678901",
+        "start": 10,
+        "end": 21
+      }
+    ]
+  },
+  {
+    "id": "de-social-security-number",
+    "input": "Rentenversicherungsnummer 65150804A123 liegt vor.",
+    "expected_entities": [
+      {
+        "type": "DE_SOCIAL_SECURITY_NUMBER",
+        "text": "65150804A123",
+        "start": 26,
+        "end": 38
+      }
+    ]
+  },
+  {
+    "id": "de-postal-code-prefixed",
+    "input": "PLZ10115 Berlin.",
+    "expected_entities": [
+      {
+        "type": "DE_POSTAL_CODE",
+        "text": "PLZ10115",
+        "start": 0,
+        "end": 8
+      }
+    ]
+  },
+  {
+    "id": "de-passport-number",
+    "input": "Passnummer C12345678 wurde geprueft.",
+    "expected_entities": [
+      {
+        "type": "DE_PASSPORT_NUMBER",
+        "text": "C12345678",
+        "start": 11,
+        "end": 20
+      }
+    ]
+  },
+  {
+    "id": "de-residence-permit-number",
+    "input": "Aufenthaltstitel AT1234567 gueltig.",
+    "expected_entities": [
+      {
+        "type": "DE_RESIDENCE_PERMIT_NUMBER",
+        "text": "AT1234567",
+        "start": 17,
+        "end": 26
+      }
+    ]
   }
 ]
diff --git a/tests/test_de_pii_regex.py b/tests/test_de_pii_regex.py
@@ -0,0 +1,105 @@
+import pytest
+
+from datafog.processing.text_processing.regex_annotator import RegexAnnotator
+
+
+@pytest.mark.parametrize(
+    "label,text,expected",
+    [
+        (
+            "DE_VAT_ID",
+            "USt-IdNr DE 123456789 ist gesetzt.",
+            "DE 123456789",
+        ),
+        (
+            "DE_VAT_ID",
+            "USt-IdNr DE-123456789 liegt vor.",
+            "DE-123456789",
+        ),
+        (
+            "DE_IBAN",
+            "IBAN DE44500105175407324931 ist gueltig.",
+            "DE44500105175407324931",
+        ),
+        (
+            "DE_IBAN",
+            "IBAN DE44 5001 0517 5407 3249 31 ist gueltig.",
+            "DE44 5001 0517 5407 3249 31",
+        ),
+        (
+            "DE_TAX_ID",
+            "Steuer-ID 12345678901 liegt vor.",
+            "12345678901",
+        ),
+        (
+            "DE_TAX_ID",
+            "Steuer-ID 12 345 678 901 ist gesetzt.",
+            "12 345 678 901",
+        ),
+        (
+            "DE_SOCIAL_SECURITY_NUMBER",
+            "Rentenversicherungsnummer 65150804A123 liegt vor.",
+            "65150804A123",
+        ),
+        (
+            "DE_SOCIAL_SECURITY_NUMBER",
+            "Rentenversicherungsnummer 65 150804 A123 liegt vor.",
+            "65 150804 A123",
+        ),
+        (
+            "DE_POSTAL_CODE",
+            "PLZ10115 Berlin.",
+            "PLZ10115",
+        ),
+        (
+            "DE_POSTAL_CODE",
+            "DE10115 Berlin.",
+            "DE10115",
+        ),
+        (
+            "DE_PASSPORT_NUMBER",
+            "Passnummer C12345678 wurde geprueft.",
+            "C12345678",
+        ),
+        (
+            "DE_RESIDENCE_PERMIT_NUMBER",
+            "Aufenthaltstitel AT1234567 gueltig.",
+            "AT1234567",
+        ),
+    ],
+)
+def test_de_regex_positive_cases(label: str, text: str, expected: str) -> None:
+    annotator = RegexAnnotator()
+    result = annotator.annotate(text)
+    assert expected in result[label]
+
+
+@pytest.mark.parametrize(
+    "label,text",
+    [
+        ("DE_VAT_ID", "USt-IdNr DE12345678 liegt vor."),
+        ("DE_VAT_ID", "USt-IdNr DE1234567890 liegt vor."),
+        ("DE_IBAN", "IBAN DE4450010517540732493 ist gueltig."),
+        ("DE_IBAN", "IBAN DE44 5001 0517 5407 3249 3X ist gueltig."),
+        ("DE_TAX_ID", "Steuer-ID 1234567890 liegt vor."),
+        ("DE_TAX_ID", "Steuer-ID 123456789012 liegt vor."),
+        (
+            "DE_SOCIAL_SECURITY_NUMBER",
+            "Rentenversicherungsnummer 65150804123 liegt vor.",
+        ),
+        (
+            "DE_SOCIAL_SECURITY_NUMBER",
+            "Rentenversicherungsnummer 65150804AA23 liegt vor.",
+        ),
+        ("DE_POSTAL_CODE", "10115 Berlin."),
+        ("DE_PASSPORT_NUMBER", "Passnummer 12345678 wurde geprueft."),
+        (
+            "DE_RESIDENCE_PERMIT_NUMBER",
+            "Aufenthaltstitel AT12345678 gueltig.",
+        ),
+    ],
+)
+def test_de_regex_negative_cases(label: str, text: str) -> None:
+    annotator = RegexAnnotator()
+    result = annotator.annotate(text)
+    assert not result[label]
diff --git a/tests/test_detection_accuracy.py b/tests/test_detection_accuracy.py
@@ -22,6 +22,13 @@
     "SSN",
     "CREDIT_CARD",
     "IP_ADDRESS",
+    "DE_VAT_ID",
+    "DE_IBAN",
+    "DE_TAX_ID",
+    "DE_SOCIAL_SECURITY_NUMBER",
+    "DE_POSTAL_CODE",
+    "DE_PASSPORT_NUMBER",
+    "DE_RESIDENCE_PERMIT_NUMBER",
     "DATE",
     "ZIP_CODE",
 }

diff --git a/tests/test_regex_annotator.py b/tests/test_regex_annotator.py
@@ -40,9 +40,23 @@ def test_regex_annotator_initialization():
     """Test that the RegexAnnotator can be initialized."""
     annotator = RegexAnnotator()
     assert annotator is not None
-    assert (
-        len(annotator.LABELS) == 7
-    )  # EMAIL, PHONE, SSN, CREDIT_CARD, IP_ADDRESS, DOB, ZIP
+    required_labels = {
+        "EMAIL",
+        "PHONE",
+        "SSN",
+        "CREDIT_CARD",
+        "IP_ADDRESS",
+        "DOB",
+        "ZIP",
+        "DE_VAT_ID",
+        "DE_IBAN",
+        "DE_TAX_ID",
+        "DE_SOCIAL_SECURITY_NUMBER",
+        "DE_POSTAL_CODE",
+        "DE_PASSPORT_NUMBER",
+        "DE_RESIDENCE_PERMIT_NUMBER",
+    }
+    assert required_labels.issubset(set(annotator.LABELS))
 
 
 def test_regex_annotator_create_method():