099556213d
## 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>
112 lines
3.7 KiB
Python
112 lines
3.7 KiB
Python
"""
|
|
SOCAR Petroleum store profile for OCR extraction.
|
|
|
|
SOCAR receipts are similar to OMV - gas station with client CUI support.
|
|
Date format may use YYYY. MM. DD with spaces.
|
|
"""
|
|
|
|
import re
|
|
from datetime import date
|
|
from decimal import Decimal, InvalidOperation
|
|
from typing import List, Dict, Any, Tuple, Optional
|
|
|
|
from .base import BaseStoreProfile
|
|
from . import ProfileRegistry
|
|
|
|
|
|
@ProfileRegistry.register
|
|
class SocarProfile(BaseStoreProfile):
|
|
"""
|
|
SOCAR PETROLEUM S.A. - standard TVA with client CUI.
|
|
|
|
Key characteristics:
|
|
- Standard TVA format (usually single rate)
|
|
- Includes client CUI on receipt (for business purchases)
|
|
- Similar format to OMV/Petrom
|
|
- Date format may use YYYY. MM. DD (with spaces)
|
|
"""
|
|
|
|
CUI_LIST = ["12546600"]
|
|
NAME_PATTERNS = ["SOCAR", "S0CAR", "SOCAR PETROLEUM"] # OCR variants
|
|
STORE_NAME = "SOCAR PETROLEUM S.A."
|
|
|
|
# Standard TVA patterns for gas stations
|
|
TVA_PATTERNS = [
|
|
# Table format: "A-19,00% 285,66 49,58"
|
|
r'([A-D])\s*[-:]\s*(\d{1,2})[.,]\d{2}\s*%\s+([\d.,]+)\s+([\d.,]+)',
|
|
# Simple format: "TVA 19% 49,58"
|
|
r'TVA\s+(\d{1,2})\s*%\s*([\d.,]+)',
|
|
]
|
|
|
|
# Gas stations may use YYYY. MM. DD format
|
|
DATE_PATTERNS_OCR_SPACES = [
|
|
(r'(\d{4})[.,]\s*(\d{2})[.,]\s*(\d{2})\s+\d{2}:\d{2}', 0.98, 'ymd'),
|
|
(r'(\d{4})[.,]\s*(\d{2})[.,]\s*(\d{2})', 0.95, 'ymd'),
|
|
(r'(\d{2})[.,]\s*(\d{2})[.,]\s*(\d{4})\s+\d{2}:\d{2}', 0.92, 'dmy'),
|
|
(r'(\d{2})[.,]\s*(\d{2})[.,]\s*(\d{4})', 0.85, 'dmy'),
|
|
]
|
|
|
|
def extract_tva_entries(self, text: str) -> List[dict]:
|
|
"""
|
|
Extract SOCAR-specific TVA entries.
|
|
|
|
Args:
|
|
text: Raw OCR text from receipt
|
|
|
|
Returns:
|
|
List of TVA entries with code, percent, and amount
|
|
"""
|
|
entries = []
|
|
seen = set()
|
|
|
|
# Try table format first
|
|
table_pattern = self.TVA_PATTERNS[0]
|
|
for match in re.finditer(table_pattern, text, re.IGNORECASE):
|
|
try:
|
|
code = match.group(1).upper()
|
|
percent = int(match.group(2))
|
|
tva_amount = self._parse_decimal(match.group(4))
|
|
|
|
if tva_amount and tva_amount > 0:
|
|
entry_key = (code, percent)
|
|
if entry_key not in seen:
|
|
entries.append({
|
|
'code': code,
|
|
'percent': percent,
|
|
'amount': tva_amount
|
|
})
|
|
seen.add(entry_key)
|
|
except (ValueError, InvalidOperation):
|
|
continue
|
|
|
|
# Fallback to simple format if no table entries found
|
|
if not entries:
|
|
simple_pattern = self.TVA_PATTERNS[1]
|
|
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:
|
|
# Default to code 'A' for simple format
|
|
entries.append({
|
|
'code': 'A',
|
|
'percent': percent,
|
|
'amount': amount
|
|
})
|
|
break # Only take first match for simple format
|
|
except (ValueError, InvalidOperation):
|
|
continue
|
|
|
|
return entries
|
|
|
|
def get_validation_hints(self) -> Dict[str, Any]:
|
|
"""Return SOCAR-specific validation hints."""
|
|
return {
|
|
"has_multi_rate_tva": False,
|
|
"card_equals_total": False,
|
|
"has_client_cui": True,
|
|
"has_efactura": False,
|
|
"is_non_vat_payer": False,
|
|
}
|