Re-structure the project.

tests/normalize/normalizers/test_ocr_normalizer.py

@@ -0,0 +1,65 @@
+"""
+Tests for OCRNormalizer
+
+Usage:
+    pytest tests/normalize/normalizers/test_ocr_normalizer.py -v
+"""
+
+import pytest
+from src.normalize.normalizers.ocr_normalizer import OCRNormalizer
+
+
+class TestOCRNormalizer:
+    """Test OCRNormalizer functionality"""
+
+    @pytest.fixture
+    def normalizer(self):
+        """Create normalizer instance for testing"""
+        return OCRNormalizer()
+
+    def test_pure_digits(self, normalizer):
+        """Pure digit OCR number should return as-is"""
+        result = normalizer.normalize('94228110015950070')
+        assert '94228110015950070' in result
+        assert len(result) == 1
+
+    def test_with_prefix(self, normalizer):
+        """OCR number with prefix should extract digits and keep original"""
+        result = normalizer.normalize('OCR: 94228110015950070')
+        assert 'OCR: 94228110015950070' in result
+        assert '94228110015950070' in result
+
+    def test_with_spaces(self, normalizer):
+        """OCR number with spaces should be normalized"""
+        result = normalizer.normalize('9422 8110 0159 50070')
+        assert '94228110015950070' in result
+
+    def test_with_hyphens(self, normalizer):
+        """OCR number with hyphens should be normalized"""
+        result = normalizer.normalize('1234-5678-9012')
+        assert '123456789012' in result
+
+    def test_empty_string(self, normalizer):
+        """Empty string should return empty list"""
+        result = normalizer('')
+        assert result == []
+
+    def test_none_value(self, normalizer):
+        """None value should return empty list"""
+        result = normalizer(None)
+        assert result == []
+
+    def test_callable_interface(self, normalizer):
+        """Normalizer should be callable via __call__"""
+        result = normalizer('OCR-12345')
+        assert '12345' in result
+
+    def test_mixed_separators(self, normalizer):
+        """OCR number with mixed separators should be normalized"""
+        result = normalizer.normalize('123 456-789 012')
+        assert '123456789012' in result
+
+    def test_very_long_ocr(self, normalizer):
+        """Very long OCR number should be handled"""
+        result = normalizer.normalize('12345678901234567890')
+        assert '12345678901234567890' in result