Files
roa2web-service-auto/backend/modules/data_entry/services/ocr/profiles/brick.py
Claude Agent 099556213d feat(ocr): Add modular store profiles with hot-reload support
## Store Profiles System
- Add ProfileRegistry for CUI-based profile lookup
- Add BaseStoreProfile with generic extraction patterns
- Implement hot-reload via POST /api/data-entry/ocr/profiles/reload

## 12 Store Profiles
- LIDL: Multi-rate TVA (A, B, C, D codes)
- OMV, SOCAR: B2B with client CUI, YYYY.MM.DD dates
- BRICK, DEDEMAN: Standard TVA, e-factura support
- KINETERRA, BEST PRINT: Non-VAT payers (returns [])
- STEPOUT MARKET: TVA 5% (books/reduced rate)
- UNLIMITED KEYS: NUMERAR payment detection
- GAMA INK, ELECTROBERING, PICTUS VELUM: Standard TVA

## Flexible TVA Patterns
- All patterns use (\d{1,2})% to accept any rate
- Supports historical (19%, 9%, 5%) and current (21%, 11%)

## Payment Methods Fix
- Fixed base.py to support multiple payments of same type
- Changed deduplication from method-only to (method, amount) tuple
- Returns separate entries for split payments

## Tools
- Add generate_store_profile.py for automatic profile generation
- Analyzes PDFs via OCR API and detects patterns

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-06 23:07:07 +00:00

102 lines
3.2 KiB
Python

"""
BRICK (Five-Holding) store profile for OCR extraction.
Five-Holding S.A. operates BRICK stores with standard receipt format.
"""
import re
from decimal import Decimal, InvalidOperation
from typing import List, Dict, Any
from .base import BaseStoreProfile
from . import ProfileRegistry
@ProfileRegistry.register
class BrickProfile(BaseStoreProfile):
"""
FIVE-HOLDING S.A. (BRICK) - standard TVA format.
Key characteristics:
- Standard TVA format
- Single TVA rate typically
- No client CUI on receipts
"""
CUI_LIST = ["10562600"]
NAME_PATTERNS = ["BRICK", "FIVE-HOLDING", "FIVE HOLDING", "BR1CK"] # OCR variants
STORE_NAME = "FIVE-HOLDING S.A."
# Standard TVA patterns (flexible - accepts any rate)
TVA_PATTERNS = [
# "TVA A: XX% = YY,YY" or "TVA-A XX% YY,YY"
r'TVA\s*[-:]?\s*([A-D])\s*:?\s*(\d{1,2})\s*%\s*[=:]?\s*([\d.,]+)',
# "A - XX,XX% = YY,YY"
r'([A-D])\s*[-:]\s*(\d{1,2})[.,]?\d{0,2}\s*%\s*[=:]?\s*([\d.,]+)',
# Simple: "TVA XX% YY,YY"
r'TVA\s+(\d{1,2})\s*%\s*([\d.,]+)',
]
def extract_tva_entries(self, text: str) -> List[dict]:
"""
Extract BRICK-specific TVA entries.
Args:
text: Raw OCR text from receipt
Returns:
List of TVA entries with code, percent, and amount
"""
entries = []
seen = set()
# Try coded patterns first
for pattern in self.TVA_PATTERNS[:2]:
for match in re.finditer(pattern, text, re.IGNORECASE):
try:
code = match.group(1).upper()
percent = int(match.group(2))
amount = self._parse_decimal(match.group(3))
if amount and amount > 0:
entry_key = (code, percent)
if entry_key not in seen:
entries.append({
'code': code,
'percent': percent,
'amount': amount
})
seen.add(entry_key)
except (ValueError, InvalidOperation, IndexError):
continue
# Fallback to simple format
if not entries:
simple_pattern = self.TVA_PATTERNS[2]
for match in re.finditer(simple_pattern, text, re.IGNORECASE):
try:
percent = int(match.group(1))
amount = self._parse_decimal(match.group(2))
if amount and amount > 0:
entries.append({
'code': 'A',
'percent': percent,
'amount': amount
})
break
except (ValueError, InvalidOperation):
continue
return entries
def get_validation_hints(self) -> Dict[str, Any]:
"""Return BRICK-specific validation hints."""
return {
"has_multi_rate_tva": False,
"card_equals_total": False,
"has_client_cui": False,
"has_efactura": False,
"is_non_vat_payer": False,
}