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>
94 lines
3.1 KiB
Python
94 lines
3.1 KiB
Python
"""
|
|
LIDL store profile for OCR extraction.
|
|
|
|
Lidl receipts have a specific TVA format without hyphen/colon separators:
|
|
TOTAL TVA 9,84
|
|
TVA A 21,00% 7,71
|
|
TVA B 11,00% 2,13
|
|
|
|
This profile handles multi-rate TVA extraction for Lidl receipts.
|
|
"""
|
|
|
|
import re
|
|
from decimal import Decimal, InvalidOperation
|
|
from typing import List, Dict, Any
|
|
|
|
from .base import BaseStoreProfile
|
|
from . import ProfileRegistry
|
|
|
|
|
|
@ProfileRegistry.register
|
|
class LidlProfile(BaseStoreProfile):
|
|
"""
|
|
LIDL DISCOUNT S.R.L. - multi-rate TVA profile.
|
|
|
|
Key characteristics:
|
|
- Multi-rate TVA (codes A, B, C, D with any percentage - patterns are flexible)
|
|
- TVA format: "TVA A XX,XX% YY,YY" (code + percent + amount on same line)
|
|
- Supports historical rates (19%, 9%, 5%) and current rates (21%, 11%)
|
|
- CARD payment usually equals total
|
|
- No client CUI on receipts
|
|
"""
|
|
|
|
CUI_LIST = ["22891860"]
|
|
NAME_PATTERNS = ["LIDL", "LDL", "L1DL", "LIDL DISCOUNT"] # OCR variants
|
|
STORE_NAME = "LIDL DISCOUNT S.R.L."
|
|
|
|
# Lidl-specific TVA patterns
|
|
# Format: "TVA A 21,00% 7,71" (code + percent + amount on same line)
|
|
TVA_PATTERNS = [
|
|
# Primary: "TVA A 21,00% 7.71" with various spacing
|
|
r'T[VU][AR]\s+([A-D])\s+(\d{1,2})[.,]?\d{0,2}\s*%\s+([\d.,]+)',
|
|
# With backslash OCR artifact: "TVA A \21,00% 7.71"
|
|
r'T[VU][AR]\s+([A-D])\s+\\?(\d{1,2})[.,]?\d{0,2}\s*%\s+([\d.,]+)',
|
|
# IVA variant (rare OCR misread)
|
|
r'IVA\s+([A-D])\s+(\d{1,2})[.,]?\d{0,2}\s*%\s+([\d.,]+)',
|
|
]
|
|
|
|
def extract_tva_entries(self, text: str) -> List[dict]:
|
|
"""
|
|
Extract Lidl-specific TVA entries.
|
|
|
|
Handles multiple TVA rates (A, B, C, D) commonly found on Lidl receipts.
|
|
Uses deduplication to avoid counting the same entry twice from different patterns.
|
|
|
|
Args:
|
|
text: Raw OCR text from receipt
|
|
|
|
Returns:
|
|
List of TVA entries with code, percent, and amount
|
|
"""
|
|
entries = []
|
|
seen = set() # Deduplication key: (code, percent)
|
|
|
|
for pattern in self.TVA_PATTERNS:
|
|
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):
|
|
continue
|
|
|
|
return entries
|
|
|
|
def get_validation_hints(self) -> Dict[str, Any]:
|
|
"""Return Lidl-specific validation hints."""
|
|
return {
|
|
"has_multi_rate_tva": True,
|
|
"card_equals_total": True,
|
|
"has_client_cui": False,
|
|
"has_efactura": False,
|
|
"is_non_vat_payer": False,
|
|
}
|