28f259cd05
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>
270 lines
9.3 KiB
Python
270 lines
9.3 KiB
Python
"""
|
|
UNLIMITED KEYS S.R.L. store profile for OCR extraction.
|
|
|
|
Key duplication service. Notable for CASH (NUMERAR) payments.
|
|
"""
|
|
|
|
import re
|
|
from decimal import Decimal, InvalidOperation
|
|
from typing import List, Dict, Any, Optional, Tuple
|
|
|
|
from .base import BaseStoreProfile
|
|
from . import ProfileRegistry
|
|
|
|
|
|
@ProfileRegistry.register
|
|
class UnlimitedKeysProfile(BaseStoreProfile):
|
|
"""
|
|
UNLIMITED KEYS S.R.L. - standard TVA profile with NUMERAR payment.
|
|
|
|
Key characteristics:
|
|
- Standard TVA format (single rate, any percentage)
|
|
- Key duplication service
|
|
- NUMERAR (cash) payment common - different from most stores!
|
|
- May also accept CARD
|
|
- OCR often reads "TVA" as "TUA" - need OCR error variants
|
|
"""
|
|
|
|
CUI_LIST = ["18993187"]
|
|
NAME_PATTERNS = ["UNLIMITED KEYS", "UNLIMITED", "UNL1MITED", "UNLIMITED KEYS SRL"]
|
|
STORE_NAME = "UNLIMITED KEYS S.R.L."
|
|
|
|
# Standard TVA patterns - including OCR error variants (TVA -> TUA)
|
|
TVA_PATTERNS = [
|
|
# "TVA A: XX% = YY,YY" or "TVA-A XX% YY,YY" (including TUA OCR error)
|
|
r'T[UV]A\s*[-:]?\s*([A-D])\s*:?\s*(\d{1,2})\s*%\s*[=:]?\s*([\d.,\s]+)',
|
|
# "A - XX,XX% = YY,YY"
|
|
r'([A-D])\s*[-:]\s*(\d{1,2})[.,]?\d{0,2}\s*%\s*[=:]?\s*([\d.,\s]+)',
|
|
# "TVA XX% YY,YY" (simple format, includes TUA)
|
|
r'T[UV]A\s+(\d{1,2})\s*%\s*([\d.,\s]+)',
|
|
# "XX.XX% TUA*A YY.YY" (OCR format with TUA*A or TUA)
|
|
r'(\d{1,2})[.,]\d{0,2}\s*%\s*T[UV]A\*?[A-D]?\s*([\d.,\s]+)',
|
|
# "TOTAL TUA: YY.YY" (total TVA amount only)
|
|
r'TOTAL\s+T[UV]A\s*:?\s*([\d.,\s]+)',
|
|
]
|
|
|
|
# TOTAL patterns for UNLIMITED KEYS (handles "80 .00" format)
|
|
TOTAL_PATTERNS = [
|
|
# "SUMA TOTALA: 80 .00" (with space before decimal)
|
|
(r'SUMA\s+TOTALA\s*:?\s*([\d\s.,]+)', 0.98),
|
|
# "TOTALA: 80,00"
|
|
(r'TOTALA\s*:?\s*([\d.,]+)', 0.95),
|
|
# Standard TOTAL patterns from base class
|
|
(r'TOTAL\s+(?:DE\s+PLATA|ACHITAT|LEI)\s*:?\s*([\d.,]+)', 0.95),
|
|
(r'TOTAL\s*:?\s*([\d.,]+)', 0.90),
|
|
]
|
|
|
|
# Payment patterns - NUMERAR is primary for this store
|
|
PAYMENT_PATTERNS = [
|
|
# "NUMERAR 80.00" or "NUMERAR: 80.00"
|
|
(r'NUMERAR\s*:?\s*([\d.,\s]+)', 'NUMERAR', 0.98),
|
|
# "CARD 80.00" or "CARD: 80.00"
|
|
(r'CARD\s*:?\s*([\d.,\s]+)', 'CARD', 0.95),
|
|
]
|
|
|
|
# Client CUI patterns - specific to this receipt format
|
|
CLIENT_CUI_PATTERNS = [
|
|
# "CIF CLIENT:1879855" (exact format from OCR)
|
|
(r'CIF\s+CLIENT\s*:?\s*(R?[O0]?\s*\d{6,10})', 0.99),
|
|
# "CLIENT CIF: ROXXXXXXX"
|
|
(r'CLIENT\s+CIF\s*:?\s*(R?[O0]?\s*\d{6,10})', 0.98),
|
|
# "C.I.F. CLIENT: XXXXXXX"
|
|
(r'C\.?I\.?F\.?\s+CLIENT\s*:?\s*(R?[O0]?\s*\d{6,10})', 0.98),
|
|
]
|
|
|
|
# Override client markers to be less strict
|
|
CLIENT_MARKERS = [
|
|
r'CIF\s+CLIENT',
|
|
r'CLIENT\s+CIF',
|
|
r'C\.?I\.?F\.?\s+CLIENT',
|
|
r'CLIENT\s*:',
|
|
]
|
|
|
|
def extract_total(self, text: str) -> Tuple[Optional[Decimal], float]:
|
|
"""
|
|
Extract total amount from receipt text.
|
|
|
|
Handles UNLIMITED KEYS format with space before decimal (e.g., "80 .00").
|
|
|
|
Args:
|
|
text: Raw OCR text from receipt
|
|
|
|
Returns:
|
|
Tuple of (total_amount, confidence) or (None, 0.0)
|
|
"""
|
|
text_upper = text.upper()
|
|
|
|
for pattern, confidence in self.TOTAL_PATTERNS:
|
|
match = re.search(pattern, text_upper, re.IGNORECASE)
|
|
if match:
|
|
try:
|
|
# Clean up amount string (remove spaces, fix decimal)
|
|
amount_str = match.group(1)
|
|
# Remove spaces that might appear before decimal
|
|
amount_str = re.sub(r'\s+', '', amount_str)
|
|
amount = self._parse_decimal(amount_str)
|
|
|
|
if amount and amount > 0:
|
|
return (amount, confidence)
|
|
except (ValueError, InvalidOperation):
|
|
continue
|
|
|
|
return (None, 0.0)
|
|
|
|
def extract_tva_entries(self, text: str) -> List[dict]:
|
|
"""
|
|
Extract TVA entries from receipt text.
|
|
|
|
Handles OCR errors where TVA is read as TUA.
|
|
|
|
Args:
|
|
text: Raw OCR text from receipt
|
|
|
|
Returns:
|
|
List of TVA entries with code, percent, and amount
|
|
"""
|
|
entries = []
|
|
text_upper = text.upper()
|
|
|
|
# Pattern 4: "XX.XX% TUA*A YY.YY" - common OCR format
|
|
pattern4 = self.TVA_PATTERNS[3]
|
|
match = re.search(pattern4, text_upper)
|
|
if match:
|
|
try:
|
|
percent = int(match.group(1))
|
|
amount_str = re.sub(r'\s+', '', match.group(2))
|
|
amount = self._parse_decimal(amount_str)
|
|
if amount and amount > 0:
|
|
entries.append({
|
|
'code': 'A',
|
|
'percent': percent,
|
|
'amount': amount
|
|
})
|
|
return entries
|
|
except (ValueError, InvalidOperation, IndexError):
|
|
pass
|
|
|
|
# Pattern 5: "TOTAL TUA: YY.YY" - fallback to total TVA
|
|
pattern5 = self.TVA_PATTERNS[4]
|
|
match = re.search(pattern5, text_upper)
|
|
if match:
|
|
try:
|
|
amount_str = re.sub(r'\s+', '', match.group(1))
|
|
amount = self._parse_decimal(amount_str)
|
|
if amount and amount > 0:
|
|
# Infer percent from amount vs total ratio
|
|
entries.append({
|
|
'code': 'A',
|
|
'percent': 19, # Standard Romanian TVA rate
|
|
'amount': amount
|
|
})
|
|
return entries
|
|
except (ValueError, InvalidOperation, IndexError):
|
|
pass
|
|
|
|
# Try coded patterns
|
|
for pattern in self.TVA_PATTERNS[:3]:
|
|
for match in re.finditer(pattern, text_upper, re.IGNORECASE):
|
|
try:
|
|
groups = match.groups()
|
|
if len(groups) == 3:
|
|
code = groups[0].upper()
|
|
percent = int(groups[1])
|
|
amount_str = re.sub(r'\s+', '', groups[2])
|
|
else:
|
|
code = 'A'
|
|
percent = int(groups[0])
|
|
amount_str = re.sub(r'\s+', '', groups[1])
|
|
|
|
amount = self._parse_decimal(amount_str)
|
|
if amount and amount > 0:
|
|
entries.append({
|
|
'code': code,
|
|
'percent': percent,
|
|
'amount': amount
|
|
})
|
|
return entries
|
|
except (ValueError, InvalidOperation, IndexError):
|
|
continue
|
|
|
|
return entries
|
|
|
|
def extract_payment_methods(self, text: str) -> List[dict]:
|
|
"""
|
|
Extract payment methods from receipt text.
|
|
|
|
Handles NUMERAR (cash) as primary payment for this store.
|
|
|
|
Args:
|
|
text: Raw OCR text from receipt
|
|
|
|
Returns:
|
|
List of payment methods with method, amount, and confidence
|
|
"""
|
|
payments = []
|
|
text_upper = text.upper()
|
|
|
|
for pattern, method, confidence in self.PAYMENT_PATTERNS:
|
|
match = re.search(pattern, text_upper, re.IGNORECASE)
|
|
if match:
|
|
try:
|
|
amount_str = re.sub(r'\s+', '', match.group(1))
|
|
amount = self._parse_decimal(amount_str)
|
|
|
|
if amount and amount > 0:
|
|
payments.append({
|
|
'method': method,
|
|
'amount': amount,
|
|
'confidence': confidence
|
|
})
|
|
except (ValueError, InvalidOperation):
|
|
continue
|
|
|
|
return payments
|
|
|
|
def extract_client_cui(self, text: str) -> Tuple[Optional[str], float]:
|
|
"""
|
|
Extract client CUI from receipt text.
|
|
|
|
Handles "CIF CLIENT:1879855" format specific to this store.
|
|
|
|
Args:
|
|
text: Raw OCR text from receipt
|
|
|
|
Returns:
|
|
Tuple of (cui, confidence) or (None, 0.0)
|
|
"""
|
|
text_upper = text.upper()
|
|
|
|
# Check for client markers
|
|
has_client = any(
|
|
re.search(marker, text_upper, re.IGNORECASE)
|
|
for marker in self.CLIENT_MARKERS
|
|
)
|
|
|
|
if not has_client:
|
|
return (None, 0.0)
|
|
|
|
# Try client CUI patterns
|
|
for pattern, confidence in self.CLIENT_CUI_PATTERNS:
|
|
match = re.search(pattern, text_upper, re.IGNORECASE)
|
|
if match:
|
|
cui = match.group(1)
|
|
# Clean up: remove RO prefix, spaces
|
|
cui_digits = re.sub(r'[^0-9]', '', cui)
|
|
if 6 <= len(cui_digits) <= 10:
|
|
return (cui_digits, confidence)
|
|
|
|
return (None, 0.0)
|
|
|
|
def get_validation_hints(self) -> Dict[str, Any]:
|
|
"""Return UNLIMITED KEYS-specific validation hints."""
|
|
return {
|
|
"has_multi_rate_tva": False,
|
|
"card_equals_total": False, # May be NUMERAR (cash)
|
|
"has_client_cui": True, # May have client CUI
|
|
"has_efactura": False,
|
|
"is_non_vat_payer": False,
|
|
"common_payment": "NUMERAR", # Cash payments common
|
|
}
|