Files
odoo_ocr/tests/test_xml_builder.py
T
fegger e2becd6219 Add review stage coverage and fix XML tax deduplication
- Reviewer now sends all pages to the review VLM alongside extracted JSON.

- XML builder deduplicates account.tax records by rate.

- XML builder raises on confidence below min_confidence_threshold.

- Adds fractional tax-rate support with stable external IDs.

- Adds expected_invoice.xml fixture, reviewer tests, and XML regression tests.
2026-08-21 16:44:25 +02:00

159 lines
5.0 KiB
Python

"""Tests for the Odoo XML builder."""
from __future__ import annotations
from decimal import Decimal
from pathlib import Path
import pytest
from lxml import etree
from odoo_ocr.config import Settings
from odoo_ocr.pipeline.xml_builder import build_odoo_xml
from odoo_ocr.schemas import ExtractedInvoice, InvoiceLineItem, ReviewResult
def _fixture_invoice() -> ExtractedInvoice:
return ExtractedInvoice(
vendor_name="Acme Supplies",
vendor_vat="GB123456789",
invoice_number="INV-2024-001",
invoice_date="2024-05-01",
due_date="2024-06-01",
currency="EUR",
payment_terms="Net 30",
line_items=[
InvoiceLineItem(
description="Consulting services",
quantity=Decimal("10.0"),
unit_price=Decimal("100.00"),
total_price=Decimal("1000.00"),
tax_rate=Decimal("20"),
)
],
subtotal=Decimal("1000.00"),
tax_total=Decimal("200.00"),
total=Decimal("1200.00"),
)
def test_build_odoo_xml() -> None:
settings = Settings()
invoice = _fixture_invoice()
xml = build_odoo_xml(invoice, ReviewResult(valid=True, confidence=0.95), settings)
assert xml.startswith("<?xml version=")
assert 'model="res.partner"' in xml
assert 'model="account.move"' in xml
assert 'model="account.move.line"' in xml
assert "Acme Supplies" in xml
assert "INV-2024-001" in xml
assert "in_invoice" in xml
def test_xml_parses_with_lxml() -> None:
invoice = _fixture_invoice()
xml = build_odoo_xml(invoice, ReviewResult(valid=True, confidence=0.95), Settings())
root = etree.fromstring(xml.encode("utf-8"))
models = {record.get("model") for record in root.iter("record")}
assert models == {"res.partner", "account.tax", "account.move", "account.move.line"}
def test_xml_matches_expected_fixture() -> None:
invoice = _fixture_invoice()
xml = build_odoo_xml(invoice, ReviewResult(valid=True, confidence=0.95), Settings())
expected = (Path(__file__).parent / "fixtures" / "expected_invoice.xml").read_text(
encoding="utf-8"
)
def _normalize(doc: str) -> dict:
root = etree.fromstring(doc.encode("utf-8"))
def _el(element) -> dict:
return {
"tag": element.tag,
"attrs": dict(element.attrib.items()),
"text": (element.text or "").strip(),
"children": [_el(child) for child in element],
}
return _el(root)
assert _normalize(xml) == _normalize(expected)
def test_fractional_tax_rate_ids_are_distinct() -> None:
invoice = ExtractedInvoice(
vendor_name="X",
invoice_number="1",
invoice_date="2024-01-01",
line_items=[
InvoiceLineItem(description="A", tax_rate=Decimal("19.79")),
InvoiceLineItem(description="B", tax_rate=Decimal("15.2")),
InvoiceLineItem(description="C", tax_rate=Decimal("15.7")),
],
)
xml = build_odoo_xml(invoice, ReviewResult(valid=True, confidence=0.95), Settings())
assert 'id="purchase_vat_19_79"' in xml
assert 'id="purchase_vat_15_2"' in xml
assert 'id="purchase_vat_15_7"' in xml
assert xml.count('model="account.tax"') == 3
assert "Purchase VAT 19.79%" in xml
assert "<field name=\"amount\">19.79</field>" in xml
def test_xml_adds_review_comment_for_low_confidence() -> None:
settings = Settings()
invoice = ExtractedInvoice(
vendor_name="X",
invoice_number="1",
invoice_date="2024-01-01",
line_items=[],
subtotal=Decimal("0"),
tax_total=Decimal("0"),
total=Decimal("0"),
)
review = ReviewResult(valid=False, confidence=0.80)
xml = build_odoo_xml(invoice, review, settings)
assert "HUMAN REVIEW ADVISED" in xml
def test_duplicate_tax_rates_emit_one_record() -> None:
"""Multiple lines sharing the same tax rate must produce a single account.tax record."""
invoice = ExtractedInvoice(
vendor_name="X",
invoice_number="1",
invoice_date="2024-01-01",
line_items=[
InvoiceLineItem(description="A", tax_rate=Decimal("20")),
InvoiceLineItem(description="B", tax_rate=Decimal("20")),
InvoiceLineItem(description="C", tax_rate=Decimal("0")),
],
)
xml = build_odoo_xml(invoice, ReviewResult(valid=True, confidence=0.95), Settings())
assert xml.count('id="purchase_vat_20"') == 1
assert xml.count('id="purchase_vat_0"') == 1
assert xml.count('model="account.tax"') == 2
def test_xml_refuses_low_confidence() -> None:
settings = Settings()
invoice = ExtractedInvoice(
vendor_name="X",
invoice_number="1",
invoice_date="2024-01-01",
line_items=[],
subtotal=Decimal("0"),
tax_total=Decimal("0"),
total=Decimal("0"),
)
review = ReviewResult(valid=False, confidence=0.70)
with pytest.raises(ValueError, match="below the minimum threshold"):
build_odoo_xml(invoice, review, settings)