125f48377a
Replaces Enterprise's account_invoice_extract with a Fusion-native pipeline: Stage 1 (text extraction): Tesseract OCRs the bill attachment via pytesseract + pdf2image. Pluggable OCRProvider adapter pattern allows future Mindee / Google Document AI / Ollama-vision backends. Stage 2 (field parsing): The fusion_accounting_ai LLMProvider reads the raw OCR text and returns structured invoice fields (vendor, invoice number, dates, amounts, line items) as JSON. Draft invoice fields are auto-populated for empty-only fields (never overwriting user-entered data). Vendor matching by name against res.partner with supplier_rank > 0. Adds: - account.move.ocr_state (selection: not_requested/pending/processing/ done/failed/manual) - account.move.ocr_raw_text, ocr_extracted_data (Json), ocr_backend, ocr_confidence - fusion.ocr.log (audit trail per OCR run) - res.company.fusion_ocr_enabled / fusion_ocr_default_backend / auto_run - /fusion/ocr/request_for_invoice JSON-RPC endpoint Backend availability detected at runtime via OCRProvider.is_available() classmethods. Tesseract 5.3.4 + pytesseract 0.3.13 + pdf2image 1.17.0 are installed in the container. Tests: 13 (TesseractAdapter availability + image OCR; flow tests for draft autofill, no-attachment guard, customer-invoice guard, ref-not- overwritten; field parser empty/clean-json/markdown-fence/bad-JSON/ provider-exception). All pass on westin-v19 OrbStack VM. Made-with: Cursor
118 lines
4.1 KiB
Python
118 lines
4.1 KiB
Python
import base64
|
|
import io
|
|
from unittest.mock import patch
|
|
|
|
from PIL import Image, ImageDraw
|
|
|
|
from odoo.exceptions import UserError
|
|
from odoo.tests import tagged
|
|
from odoo.tests.common import TransactionCase
|
|
|
|
|
|
@tagged('post_install', '-at_install')
|
|
class TestInvoiceOcrFlow(TransactionCase):
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
self.partner = self.env['res.partner'].create({
|
|
'name': 'Test Vendor',
|
|
'supplier_rank': 1,
|
|
})
|
|
self.move = self.env['account.move'].create({
|
|
'move_type': 'in_invoice',
|
|
'partner_id': self.partner.id,
|
|
})
|
|
|
|
def test_ocr_state_default(self):
|
|
self.assertEqual(self.move.ocr_state, 'not_requested')
|
|
|
|
def test_action_request_ocr_no_attachment_raises(self):
|
|
with self.assertRaises(UserError):
|
|
self.move.action_request_ocr()
|
|
|
|
def test_action_request_ocr_with_image(self):
|
|
img = Image.new('RGB', (800, 120), color='white')
|
|
draw = ImageDraw.Draw(img)
|
|
try:
|
|
from PIL import ImageFont
|
|
font = ImageFont.truetype(
|
|
'/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf', 36,
|
|
)
|
|
except Exception:
|
|
font = None
|
|
draw.text((20, 30), "TOTAL $50.00 INV-9999", fill='black', font=font)
|
|
buf = io.BytesIO()
|
|
img.save(buf, format='PNG')
|
|
|
|
self.env['ir.attachment'].create({
|
|
'name': 'test_invoice.png',
|
|
'datas': base64.b64encode(buf.getvalue()),
|
|
'res_model': 'account.move',
|
|
'res_id': self.move.id,
|
|
'mimetype': 'image/png',
|
|
})
|
|
|
|
# Mock the LLM call to avoid a real API roundtrip.
|
|
with patch(
|
|
'odoo.addons.fusion_accounting_ocr.models.account_move.parse_invoice_fields',
|
|
return_value={
|
|
'vendor_name': None,
|
|
'invoice_number': 'INV-9999',
|
|
'invoice_date': None,
|
|
'due_date': None,
|
|
'currency': None,
|
|
'subtotal': None,
|
|
'tax_total': None,
|
|
'total': 50.0,
|
|
'line_items': [],
|
|
},
|
|
):
|
|
self.move.action_request_ocr()
|
|
|
|
self.assertEqual(self.move.ocr_state, 'done')
|
|
self.assertEqual(self.move.ocr_backend, 'tesseract')
|
|
self.assertGreater(self.move.ocr_confidence, 0)
|
|
self.assertIsNotNone(self.move.ocr_extracted_data)
|
|
# Parsed invoice_number should land on the invoice's ref field.
|
|
self.assertEqual(self.move.ref, 'INV-9999')
|
|
# OCR log row was created.
|
|
self.assertEqual(len(self.move.ocr_log_ids), 1)
|
|
log = self.move.ocr_log_ids
|
|
self.assertEqual(log.backend, 'tesseract')
|
|
self.assertGreater(log.raw_text_length, 0)
|
|
|
|
def test_apply_does_not_overwrite_user_entered_ref(self):
|
|
self.move.ref = 'USER-SET-REF'
|
|
img = Image.new('RGB', (400, 80), color='white')
|
|
ImageDraw.Draw(img).text((10, 30), "INV-7777", fill='black')
|
|
buf = io.BytesIO()
|
|
img.save(buf, format='PNG')
|
|
self.env['ir.attachment'].create({
|
|
'name': 't.png',
|
|
'datas': base64.b64encode(buf.getvalue()),
|
|
'res_model': 'account.move',
|
|
'res_id': self.move.id,
|
|
'mimetype': 'image/png',
|
|
})
|
|
with patch(
|
|
'odoo.addons.fusion_accounting_ocr.models.account_move.parse_invoice_fields',
|
|
return_value={
|
|
'vendor_name': None, 'invoice_number': 'INV-7777',
|
|
'invoice_date': None, 'due_date': None, 'currency': None,
|
|
'subtotal': None, 'tax_total': None, 'total': None,
|
|
'line_items': [],
|
|
},
|
|
):
|
|
self.move.action_request_ocr()
|
|
|
|
# User-entered ref must not be overwritten.
|
|
self.assertEqual(self.move.ref, 'USER-SET-REF')
|
|
|
|
def test_only_vendor_bills_supported(self):
|
|
customer_invoice = self.env['account.move'].create({
|
|
'move_type': 'out_invoice',
|
|
'partner_id': self.partner.id,
|
|
})
|
|
with self.assertRaises(UserError):
|
|
customer_invoice.action_request_ocr()
|