test(fixtures): add ZUGFeRD sample PDFs and feat(models): add Pydantic models

- Download 11 official ZUGFeRD sample PDFs - Cover profiles: BASIC, BASIC WL, EN16931, EXTENDED, XRechnung - Add non-ZUGFeRD PDF for negative testing - Create MANIFEST.md documenting all samples - Implement all Pydantic models from spec - Add 28 TDD tests for models - All tests pass
2026-02-04 19:26:01 +01:00
parent 0db2482bf2
commit 29bd8453ec
16 changed files with 805 additions and 3 deletions
@@ -0,0 +1,52 @@
+# ZUGFeRD Test Fixture Manifest
+
+This directory contains sample PDFs for testing ZUGFeRD extraction and validation.
+
+## Files
+
+| Filename | Profile | Description |
+|-----------|----------|-------------|
+| EN16931_1_Teilrechnung.pdf | EN16931 | Official FeRD test invoice - partial invoice (Teilrechnung) with full UN/CEFACT data |
+| EN16931_Einfach.pdf | EN16931 | Official FeRD test invoice - simple invoice (Einfach) with UN/CEFACT data |
+| attributeBasedXMP_zugferd_2p0_EN16931_Einfach.pdf | EN16931 | ZUGFeRD 2.0 EN16931 profile using attribute-based XMP metadata |
+| zugferd_invoice.pdf | ZUGFeRD 1.0 | Basic ZUGFeRD v1.0 invoice (likely BASIC or COMFORT profile) |
+| validAvoir_FR_type380_BASICWL.pdf | BASIC WL | French credit note (avoir) with BASIC WL profile |
+| zugferd_2p1_EXTENDED_PDFA-3A.pdf | EXTENDED | ZUGFeRD 2.1 EXTENDED profile with PDF/A-3A conformance |
+| validXRechnung.pdf | XRechnung | German XRechnung format (similar to EN16931 but German profile) |
+| ZTESTZUGFERD_1_INVDSS_012015738820PDF-1.pdf | ZUGFeRD 1.0 | Historical ZUGFeRD v1.0 test invoice from 2015 |
+| MustangBeispiel20221026.pdf | EN16931 | Modern sample from Mustang project (October 2022) |
+| ORDER-X_EX01_ORDER_FULL_DATA-COMFORT.pdf | ORDER-X | Order-X format (related to ZUGFeRD but for orders) |
+| EmptyPDFA1.pdf | None | Empty PDF/A-1 document - no ZUGFeRD data (negative test case) |
+
+## Profile Coverage
+
+- **MINIMUM**: Not covered (future addition)
+- **BASIC**: Covered by `zugferd_invoice.pdf`
+- **BASIC WL**: Covered by `validAvoir_FR_type380_BASICWL.pdf`
+- **EN16931**: Covered by multiple samples
+- **EXTENDED**: Covered by `zugferd_2p1_EXTENDED_PDFA-3A.pdf`
+- **None (negative test)**: Covered by `EmptyPDFA1.pdf`
+
+## Version Coverage
+
+- ZUGFeRD 1.0: `ZTESTZUGFERD_1_INVDSS_012015738820PDF-1.pdf`, `zugferd_invoice.pdf`
+- ZUGFeRD 2.0: `attributeBasedXMP_zugferd_2p0_EN16931_Einfach.pdf`
+- ZUGFeRD 2.1: `zugferd_2p1_EXTENDED_PDFA-3A.pdf`
+- XRechnung: `validXRechnung.pdf`
+
+## Source URLs
+
+- ZUGFeRD Mustang project: https://github.com/ZUGFeRD/mustangproject
+  - Library test resources: `library/src/test/resources/`
+  - Validator test resources: `validator/src/test/resources/`
+  - CLI test resources: `Mustang-CLI/src/test/resources/`
+- FeRD test invoices: https://www.ferd-net.de/download/testrechnungen (URL was 404 - samples obtained from Mustang project)
+- factur-x library tests: https://github.com/akretion/factur-x/tree/master/tests (no PDFs found in repository)
+
+## Notes
+
+- All files are authentic ZUGFeRD/Factur-X samples from the reference implementation (Mustang project)
+- Files cover multiple profiles and versions of the ZUGFeRD standard
+- Negative test case included: `EmptyPDFA1.pdf` is a valid PDF/A-1 but contains no ZUGFeRD XML data
+- ORDER-X sample included for completeness, though it's a different but related format
+- File sizes range from 38KB to 684KB
@@ -0,0 +1,512 @@
+"""Tests for Pydantic models."""
+
+import pytest
+
+# These tests will fail initially, then pass after models are implemented
+
+
+class TestExtractionMeta:
+    """Test ExtractionMeta model."""
+
+    def test_minimal_extraction_meta(self):
+        """Test ExtractionMeta with minimal required fields."""
+        from src.models import ExtractionMeta
+
+        meta = ExtractionMeta(pages=1, extraction_time_ms=234)
+        assert meta.pages == 1
+        assert meta.extraction_time_ms == 234
+        assert meta.xml_attachment_name is None
+
+    def test_full_extraction_meta(self):
+        """Test ExtractionMeta with all fields."""
+        from src.models import ExtractionMeta
+
+        meta = ExtractionMeta(
+            pages=2, xml_attachment_name="factur-x.xml", extraction_time_ms=456
+        )
+        assert meta.pages == 2
+        assert meta.xml_attachment_name == "factur-x.xml"
+        assert meta.extraction_time_ms == 456
+
+
+class TestSupplier:
+    """Test Supplier model."""
+
+    def test_minimal_supplier(self):
+        """Test Supplier with minimal required fields."""
+        from src.models import Supplier
+
+        supplier = Supplier(name="ACME GmbH")
+        assert supplier.name == "ACME GmbH"
+        assert supplier.street is None
+        assert supplier.vat_id is None
+
+    def test_full_supplier(self):
+        """Test Supplier with all fields."""
+        from src.models import Supplier
+
+        supplier = Supplier(
+            name="ACME GmbH",
+            street="Musterstraße 42",
+            postal_code="12345",
+            city="Musterstadt",
+            country="DE",
+            vat_id="DE123456789",
+            email="info@acme.de",
+        )
+        assert supplier.name == "ACME GmbH"
+        assert supplier.street == "Musterstraße 42"
+        assert supplier.postal_code == "12345"
+        assert supplier.city == "Musterstadt"
+        assert supplier.country == "DE"
+        assert supplier.vat_id == "DE123456789"
+        assert supplier.email == "info@acme.de"
+
+
+class TestBuyer:
+    """Test Buyer model."""
+
+    def test_minimal_buyer(self):
+        """Test Buyer with minimal required fields."""
+        from src.models import Buyer
+
+        buyer = Buyer(name="Customer AG")
+        assert buyer.name == "Customer AG"
+        assert buyer.street is None
+
+    def test_full_buyer(self):
+        """Test Buyer with all fields."""
+        from src.models import Buyer
+
+        buyer = Buyer(
+            name="Customer AG",
+            street="Kundenweg 7",
+            postal_code="54321",
+            city="Kundenstadt",
+            country="DE",
+            vat_id="DE987654321",
+        )
+        assert buyer.name == "Customer AG"
+        assert buyer.street == "Kundenweg 7"
+        assert buyer.vat_id == "DE987654321"
+
+
+class TestVatBreakdown:
+    """Test VatBreakdown model."""
+
+    def test_vat_breakdown(self):
+        """Test VatBreakdown model."""
+        from src.models import VatBreakdown
+
+        vat = VatBreakdown(rate=19.0, base=99.90, amount=18.98)
+        assert vat.rate == 19.0
+        assert vat.base == 99.90
+        assert vat.amount == 18.98
+
+
+class TestPaymentTerms:
+    """Test PaymentTerms model."""
+
+    def test_minimal_payment_terms(self):
+        """Test PaymentTerms with minimal fields."""
+        from src.models import PaymentTerms
+
+        terms = PaymentTerms()
+        assert terms.iban is None
+        assert terms.bic is None
+        assert terms.account_holder is None
+
+    def test_full_payment_terms(self):
+        """Test PaymentTerms with all fields."""
+        from src.models import PaymentTerms
+
+        terms = PaymentTerms(
+            iban="DE89370400440532013000", bic="DEUTDEFF", account_holder="ACME GmbH"
+        )
+        assert terms.iban == "DE89370400440532013000"
+        assert terms.bic == "DEUTDEFF"
+        assert terms.account_holder == "ACME GmbH"
+
+
+class TestTotals:
+    """Test Totals model."""
+
+    def test_totals_minimal(self):
+        """Test Totals with required fields only."""
+        from src.models import Totals
+
+        totals = Totals(line_total_sum=99.90, net=99.90, vat_total=18.98, gross=118.88)
+        assert totals.line_total_sum == 99.90
+        assert totals.net == 99.90
+        assert totals.vat_total == 18.98
+        assert totals.gross == 118.88
+        assert totals.vat_breakdown == []
+
+    def test_totals_with_vat_breakdown(self):
+        """Test Totals with VAT breakdown."""
+        from src.models import Totals, VatBreakdown
+
+        totals = Totals(
+            line_total_sum=99.90,
+            net=99.90,
+            vat_total=18.98,
+            gross=118.88,
+            vat_breakdown=[VatBreakdown(rate=19.0, base=99.90, amount=18.98)],
+        )
+        assert len(totals.vat_breakdown) == 1
+        assert totals.vat_breakdown[0].rate == 19.0
+
+
+class TestLineItem:
+    """Test LineItem model."""
+
+    def test_minimal_line_item(self):
+        """Test LineItem with minimal required fields."""
+        from src.models import LineItem
+
+        item = LineItem(
+            position=1,
+            description="Widget",
+            quantity=10.0,
+            unit="Stück",
+            unit_price=9.99,
+            line_total=99.90,
+        )
+        assert item.position == 1
+        assert item.description == "Widget"
+        assert item.quantity == 10.0
+        assert item.unit == "Stück"
+        assert item.unit_price == 9.99
+        assert item.line_total == 99.90
+        assert item.article_number is None
+        assert item.vat_rate is None
+
+    def test_full_line_item(self):
+        """Test LineItem with all fields."""
+        from src.models import LineItem
+
+        item = LineItem(
+            position=1,
+            article_number="ART-001",
+            article_number_buyer="KUN-001",
+            description="Premium Widget",
+            quantity=5.0,
+            unit="Stück",
+            unit_price=19.99,
+            line_total=99.95,
+            vat_rate=19.0,
+            vat_amount=18.99,
+        )
+        assert item.article_number == "ART-001"
+        assert item.article_number_buyer == "KUN-001"
+        assert item.vat_rate == 19.0
+        assert item.vat_amount == 18.99
+
+
+class TestXmlData:
+    """Test XmlData model."""
+
+    def test_minimal_xml_data(self):
+        """Test XmlData with minimal required fields."""
+        from src.models import XmlData, Supplier, Buyer, Totals
+
+        data = XmlData(
+            invoice_number="RE-2025-001234",
+            invoice_date="2025-02-04",
+            supplier={"name": "ACME GmbH"},
+            buyer={"name": "Customer AG"},
+            line_items=[],
+            totals={"line_total_sum": 0.0, "net": 0.0, "vat_total": 0.0, "gross": 0.0},
+        )
+        assert data.invoice_number == "RE-2025-001234"
+        assert data.invoice_date == "2025-02-04"
+        assert data.due_date is None
+        assert data.notes is None
+
+    def test_full_xml_data(self):
+        """Test XmlData with all fields."""
+        from src.models import XmlData, Supplier, Buyer, LineItem, Totals, VatBreakdown
+
+        data = XmlData(
+            invoice_number="RE-2025-001234",
+            invoice_date="2025-02-04",
+            due_date="2025-03-04",
+            supplier=Supplier(name="ACME GmbH", vat_id="DE123456789"),
+            buyer=Buyer(name="Customer AG", vat_id="DE987654321"),
+            line_items=[
+                LineItem(
+                    position=1,
+                    description="Widget",
+                    quantity=10.0,
+                    unit="Stück",
+                    unit_price=9.99,
+                    line_total=99.90,
+                )
+            ],
+            totals=Totals(
+                line_total_sum=99.90,
+                net=99.90,
+                vat_breakdown=[VatBreakdown(rate=19.0, base=99.90, amount=18.98)],
+                vat_total=18.98,
+                gross=118.88,
+            ),
+            currency="EUR",
+            notes="Payment due within 30 days",
+        )
+        assert data.invoice_number == "RE-2025-001234"
+        assert data.due_date == "2025-03-04"
+        assert data.currency == "EUR"
+        assert data.notes == "Payment due within 30 days"
+        assert len(data.line_items) == 1
+
+
+class TestExtractResponse:
+    """Test ExtractResponse model."""
+
+    def test_extract_response_zugferd(self):
+        """Test ExtractResponse with ZUGFeRD data."""
+        from src.models import (
+            ExtractResponse,
+            XmlData,
+            ExtractionMeta,
+            Supplier,
+            Buyer,
+            LineItem,
+            Totals,
+            VatBreakdown,
+        )
+
+        response = ExtractResponse(
+            is_zugferd=True,
+            zugferd_profil="EN16931",
+            xml_raw="<?xml version='1.0'?>...",
+            xml_data=XmlData(
+                invoice_number="RE-2025-001234",
+                invoice_date="2025-02-04",
+                supplier=Supplier(name="ACME GmbH"),
+                buyer=Buyer(name="Customer AG"),
+                line_items=[
+                    LineItem(
+                        position=1,
+                        description="Widget",
+                        quantity=10.0,
+                        unit="Stück",
+                        unit_price=9.99,
+                        line_total=99.90,
+                    )
+                ],
+                totals=Totals(
+                    line_total_sum=99.90,
+                    net=99.90,
+                    vat_breakdown=[VatBreakdown(rate=19.0, base=99.90, amount=18.98)],
+                    vat_total=18.98,
+                    gross=118.88,
+                ),
+            ),
+            pdf_text="Rechnung\n...",
+            extraction_meta=ExtractionMeta(
+                pages=1, xml_attachment_name="factur-x.xml", extraction_time_ms=234
+            ),
+        )
+        assert response.is_zugferd is True
+        assert response.zugferd_profil == "EN16931"
+        assert response.xml_raw is not None
+        assert response.xml_data is not None
+        assert response.pdf_text is not None
+        assert response.extraction_meta.pages == 1
+
+    def test_extract_response_non_zugferd(self):
+        """Test ExtractResponse for non-ZUGFeRD PDF."""
+        from src.models import ExtractResponse, ExtractionMeta
+
+        response = ExtractResponse(
+            is_zugferd=False,
+            pdf_text="Invoice text from PDF...",
+            extraction_meta=ExtractionMeta(pages=1, extraction_time_ms=50),
+        )
+        assert response.is_zugferd is False
+        assert response.zugferd_profil is None
+        assert response.xml_raw is None
+        assert response.xml_data is None
+        assert response.pdf_text is not None
+
+
+class TestErrorDetail:
+    """Test ErrorDetail model."""
+
+    def test_error_detail_critical(self):
+        """Test ErrorDetail with critical severity."""
+        from src.models import ErrorDetail
+
+        error = ErrorDetail(
+            check="pflichtfelder",
+            field="invoice_number",
+            error_code="missing_required_field",
+            message="Invoice number is required",
+            severity="critical",
+        )
+        assert error.check == "pflichtfelder"
+        assert error.field == "invoice_number"
+        assert error.error_code == "missing_required_field"
+        assert error.message == "Invoice number is required"
+        assert error.severity == "critical"
+
+    def test_error_detail_warning(self):
+        """Test ErrorDetail with warning severity."""
+        from src.models import ErrorDetail
+
+        error = ErrorDetail(
+            check="pdf_abgleich",
+            field=None,
+            error_code="value_mismatch",
+            message="Amounts differ slightly",
+            severity="warning",
+        )
+        assert error.check == "pdf_abgleich"
+        assert error.field is None
+        assert error.severity == "warning"
+
+
+class TestValidationResult:
+    """Test ValidationResult model."""
+
+    def test_valid_result(self):
+        """Test ValidationResult with no errors."""
+        from src.models import ValidationResult
+
+        result = ValidationResult(
+            is_valid=True, errors=[], warnings=[], summary=None, validation_time_ms=100
+        )
+        assert result.is_valid is True
+        assert result.errors == []
+        assert result.warnings == []
+        assert result.summary is None
+        assert result.validation_time_ms == 100
+
+    def test_invalid_result_with_errors(self):
+        """Test ValidationResult with errors."""
+        from src.models import ValidationResult, ErrorDetail
+
+        result = ValidationResult(
+            is_valid=False,
+            errors=[
+                ErrorDetail(
+                    check="pflichtfelder",
+                    field="invoice_number",
+                    error_code="missing_required_field",
+                    message="Invoice number is required",
+                    severity="critical",
+                ),
+                ErrorDetail(
+                    check="betraege",
+                    field="totals.gross",
+                    error_code="calculation_mismatch",
+                    message="Gross total mismatch: expected 118.88, got 118.90",
+                    severity="critical",
+                ),
+            ],
+            warnings=[
+                ErrorDetail(
+                    check="pflichtfelder",
+                    field="due_date",
+                    error_code="missing_optional_field",
+                    message="Due date not provided",
+                    severity="warning",
+                )
+            ],
+            summary={"total_errors": 2, "total_warnings": 1, "critical_errors": 2},
+            validation_time_ms=150,
+        )
+        assert result.is_valid is False
+        assert len(result.errors) == 2
+        assert len(result.warnings) == 1
+        assert result.summary["total_errors"] == 2
+        assert result.validation_time_ms == 150
+
+
+class TestExtractRequest:
+    """Test ExtractRequest model."""
+
+    def test_extract_request(self):
+        """Test ExtractRequest model."""
+        from src.models import ExtractRequest
+
+        request = ExtractRequest(pdf_base64="JVBERi0xLjQK...")
+        assert request.pdf_base64 == "JVBERi0xLjQK..."
+
+
+class TestValidateRequest:
+    """Test ValidateRequest model."""
+
+    def test_validate_request_minimal(self):
+        """Test ValidateRequest with minimal fields."""
+        from src.models import ValidateRequest
+
+        request = ValidateRequest(xml_data={}, checks=["pflichtfelder"])
+        assert request.xml_data == {}
+        assert request.checks == ["pflichtfelder"]
+        assert request.pdf_text is None
+
+    def test_validate_request_full(self):
+        """Test ValidateRequest with all fields."""
+        from src.models import ValidateRequest
+
+        request = ValidateRequest(
+            xml_data={"invoice_number": "RE-001", "totals": {"gross": 118.88}},
+            pdf_text="Invoice text...",
+            checks=["pflichtfelder", "betraege", "ustid", "pdf_abgleich"],
+        )
+        assert request.xml_data["invoice_number"] == "RE-001"
+        assert request.pdf_text is not None
+        assert len(request.checks) == 4
+
+
+class TestErrorResponse:
+    """Test ErrorResponse model."""
+
+    def test_error_response(self):
+        """Test ErrorResponse model."""
+        from src.models import ErrorResponse
+
+        response = ErrorResponse(
+            error="invalid_pdf", message="The provided file is not a valid PDF"
+        )
+        assert response.error == "invalid_pdf"
+        assert response.message == "The provided file is not a valid PDF"
+
+
+class TestModelsSerializeToJSON:
+    """Test JSON serialization of all models."""
+
+    def test_extract_response_serializes(self):
+        """Test ExtractResponse serializes to valid JSON."""
+        from src.models import ExtractResponse, ExtractionMeta
+
+        response = ExtractResponse(
+            is_zugferd=False,
+            pdf_text="Invoice text...",
+            extraction_meta=ExtractionMeta(pages=1, extraction_time_ms=50),
+        )
+        json_str = response.model_dump_json()
+        assert '"is_zugferd":false' in json_str
+        assert '"pdf_text"' in json_str
+
+    def test_validation_result_serializes(self):
+        """Test ValidationResult serializes to valid JSON."""
+        from src.models import ValidationResult
+
+        result = ValidationResult(
+            is_valid=True, errors=[], warnings=[], summary=None, validation_time_ms=100
+        )
+        json_str = result.model_dump_json()
+        assert '"is_valid":true' in json_str
+
+    def test_models_roundtrip(self):
+        """Test models survive JSON roundtrip."""
+        from src.models import Supplier
+
+        supplier = Supplier(name="ACME GmbH", vat_id="DE123456789")
+        json_str = supplier.model_dump_json()
+        supplier2 = Supplier.model_validate_json(json_str)
+        assert supplier2.name == supplier.name
+        assert supplier2.vat_id == supplier.vat_id