fix(ocr): Fix store profile extraction patterns and module loading

Major fixes to OCR store profiles for Romanian receipt extraction:

- Fix ProfileRegistry module path resolution (was loading 0 profiles)
- Add multiline TVA extraction for Brick, Electrobering, Gama Ink
- Add "CARTE CREDIT" payment detection for OMV/SOCAR gas stations
- Handle OCR artifacts: TVA→TUA, "-"→"4", I→L in CUI markers
- Add client CUI patterns for Brick receipts
- Add profile selection logging to ocr_extractor.py
- Create test script for all 29 PDFs (test_all_profiles.py)

Test results: 13/29 passing (improved from 9/29)
Remaining failures are primarily OCR quality issues.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Claude Agent
2026-01-07 09:40:58 +00:00
parent 099556213d
commit 28f259cd05
13 changed files with 1531 additions and 257 deletions

View File

@@ -100,11 +100,62 @@ class SocarProfile(BaseStoreProfile):
return entries
def extract_payment_methods(self, text: str) -> List[dict]:
"""
Extract SOCAR-specific payment methods.
Gas stations use "CARTE CREDIT" or "CARD" for card payments.
Args:
text: Raw OCR text from receipt
Returns:
List of payment methods with method, amount, and confidence
"""
payments = []
text_upper = text.upper()
# Get total amount first
total_amount, _ = self.extract_total(text)
if not total_amount:
return []
# Gas station payment patterns
payment_indicators = [
('CARTE CREDIT', 'CARD', 0.98),
('CARTE DE CREDIT', 'CARD', 0.98),
('CARD', 'CARD', 0.95),
('VISA', 'CARD', 0.95),
('MASTERCARD', 'CARD', 0.95),
('CONTACTLESS', 'CARD', 0.90),
('NUMERAR', 'NUMERAR', 0.95),
('CASH', 'NUMERAR', 0.90),
]
for indicator, method, confidence in payment_indicators:
if indicator in text_upper:
payments.append({
'method': method,
'amount': total_amount,
'confidence': confidence
})
return payments
# Fallback: If no explicit payment but has BON FISCAL, assume CARD
if 'BON FISCAL' in text_upper:
payments.append({
'method': 'CARD',
'amount': total_amount,
'confidence': 0.70
})
return payments
def get_validation_hints(self) -> Dict[str, Any]:
"""Return SOCAR-specific validation hints."""
return {
"has_multi_rate_tva": False,
"card_equals_total": False,
"card_equals_total": True, # Gas station: card equals total
"has_client_cui": True,
"has_efactura": False,
"is_non_vat_payer": False,