invoice-master-poc-v2/tests/domain/test_document_classifier.py

"""
Tests for DocumentClassifier - TDD RED phase.

Test document type classification based on extracted fields.
"""
import pytest

from backend.domain.document_classifier import DocumentClassifier, ClassificationResult


class TestDocumentClassifier:
    """Test document classification logic."""

    @pytest.fixture
    def classifier(self) -> DocumentClassifier:
        """Create classifier instance."""
        return DocumentClassifier()

    # ==================== Invoice Detection Tests ====================

    def test_classify_with_payment_line_returns_invoice(
        self, classifier: DocumentClassifier
    ) -> None:
        """Payment line is the strongest invoice indicator."""
        fields = {"payment_line": "# 123456 # 100 00 5 > 308-2963#"}

        result = classifier.classify(fields)

        assert result.document_type == "invoice"
        assert result.confidence >= 0.9
        assert "payment_line" in result.reason

    def test_classify_with_multiple_indicators_returns_invoice(
        self, classifier: DocumentClassifier
    ) -> None:
        """Multiple invoice indicators -> invoice with medium confidence."""
        fields = {
            "Amount": "1200.00",
            "Bankgiro": "123-4567",
            "payment_line": None,
        }

        result = classifier.classify(fields)

        assert result.document_type == "invoice"
        assert result.confidence >= 0.7

    def test_classify_with_ocr_and_amount_returns_invoice(
        self, classifier: DocumentClassifier
    ) -> None:
        """OCR + Amount is typical invoice pattern."""
        fields = {
            "OCR": "123456789012",
            "Amount": "500.00",
        }

        result = classifier.classify(fields)

        assert result.document_type == "invoice"
        assert result.confidence >= 0.7

    def test_classify_with_single_indicator_returns_invoice_lower_confidence(
        self, classifier: DocumentClassifier
    ) -> None:
        """Single indicator -> invoice but lower confidence."""
        fields = {"Amount": "100.00"}

        result = classifier.classify(fields)

        assert result.document_type == "invoice"
        assert 0.5 <= result.confidence < 0.8

    def test_classify_with_invoice_number_only(
        self, classifier: DocumentClassifier
    ) -> None:
        """Invoice number alone suggests invoice."""
        fields = {"InvoiceNumber": "INV-2024-001"}

        result = classifier.classify(fields)

        assert result.document_type == "invoice"

    # ==================== Letter Detection Tests ====================

    def test_classify_with_no_indicators_returns_letter(
        self, classifier: DocumentClassifier
    ) -> None:
        """No invoice indicators -> letter."""
        fields: dict[str, str | None] = {}

        result = classifier.classify(fields)

        assert result.document_type == "letter"
        assert result.confidence >= 0.5

    def test_classify_with_empty_fields_returns_letter(
        self, classifier: DocumentClassifier
    ) -> None:
        """All fields empty or None -> letter."""
        fields = {
            "payment_line": None,
            "OCR": None,
            "Amount": None,
            "Bankgiro": None,
        }

        result = classifier.classify(fields)

        assert result.document_type == "letter"

    def test_classify_with_only_non_indicator_fields_returns_letter(
        self, classifier: DocumentClassifier
    ) -> None:
        """Fields that don't indicate invoice -> letter."""
        fields = {
            "CustomerNumber": "C12345",
            "SupplierOrgNumber": "556677-8899",
        }

        result = classifier.classify(fields)

        assert result.document_type == "letter"

    # ==================== Edge Cases ====================

    def test_classify_with_empty_string_fields_returns_letter(
        self, classifier: DocumentClassifier
    ) -> None:
        """Empty strings should be treated as missing."""
        fields = {
            "payment_line": "",
            "Amount": "",
        }

        result = classifier.classify(fields)

        assert result.document_type == "letter"

    def test_classify_with_whitespace_only_fields_returns_letter(
        self, classifier: DocumentClassifier
    ) -> None:
        """Whitespace-only strings should be treated as missing."""
        fields = {
            "payment_line": "   ",
            "Amount": "\t\n",
        }

        result = classifier.classify(fields)

        assert result.document_type == "letter"

    # ==================== ClassificationResult Immutability ====================

    def test_classification_result_is_immutable(
        self, classifier: DocumentClassifier
    ) -> None:
        """ClassificationResult should be a frozen dataclass."""
        fields = {"payment_line": "test"}
        result = classifier.classify(fields)

        with pytest.raises((AttributeError, TypeError)):
            result.document_type = "modified"  # type: ignore

    def test_classification_result_has_required_fields(
        self, classifier: DocumentClassifier
    ) -> None:
        """ClassificationResult must have document_type, confidence, reason."""
        fields = {"Amount": "100.00"}
        result = classifier.classify(fields)

        assert hasattr(result, "document_type")
        assert hasattr(result, "confidence")
        assert hasattr(result, "reason")
        assert isinstance(result.document_type, str)
        assert isinstance(result.confidence, float)
        assert isinstance(result.reason, str)