romfast/roa2web-service-auto
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(data-entry): Add unified receipt form with OCR confidence tracking

Browse Source 
New unified receipt creation system with:
- UnifiedReceiptForm component with inline OCR preview and confidence indicators
- Compact upload zone with drag-drop and camera support
- TVA and Payment fields with dynamic add/remove
- Supplier dual-field with autocomplete and OCR hint
- Receipt form sections with collapsible auxiliary data

Backend OCR improvements:
- Add confidence_tva and confidence_payment to extraction results
- Update TVA extraction to return confidence scores
- Include TVA (15%) and payment (10%) in overall_confidence calculation

Also includes:
- CSS design system rules documentation
- Port check helper function for service scripts
- Expanded design tokens documentation in CLAUDE.md

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Claude Agent
2026-01-08 21:48:37 +00:00
parent cc98d6f21f
commit b4a226409c
21 changed files with 4876 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
backend/modules/data_entry/services/ocr_extractor.py
View File

@@ -38,6 +38,8 @@ class ExtractionResult:
confidence_date: float = 0.0
confidence_vendor: float = 0.0
confidence_client: float = 0.0
confidence_tva: float = 0.0
confidence_payment: float = 0.0
raw_text: str = ""
ocr_engine: str = "" # OCR engine used: paddleocr or tesseract
processing_time_ms: int = 0 # Processing time in milliseconds
@@ -51,12 +53,20 @@ class ExtractionResult:
@property
def overall_confidence(self) -> float:
"""Calculate weighted overall confidence score."""
weights = {'amount': 0.4, 'date': 0.3, 'vendor': 0.3}
"""Calculate weighted overall confidence score including TVA and payment."""
weights = {
'amount': 0.35, # Most important - receipt total
'date': 0.20, # Receipt date
'vendor': 0.20, # Vendor identification
'tva': 0.15, # TVA extraction accuracy
'payment': 0.10 # Payment method detection
}
return round(
self.confidence_amount * weights['amount'] +
self.confidence_date * weights['date'] +
self.confidence_vendor * weights['vendor'],
self.confidence_vendor * weights['vendor'] +
self.confidence_tva * weights['tva'] +
self.confidence_payment * weights['payment'],
2
)
@@ -468,9 +478,15 @@ class ReceiptExtractor:
result.amount, result.confidence_amount = store_profile.extract_total(text_upper)
result.receipt_date, result.confidence_date = store_profile.extract_date(text_upper)
result.receipt_number, _ = store_profile.extract_receipt_number(text_upper)
result.tva_entries = store_profile.extract_tva_entries(text_upper)
result.tva_total = sum(e['amount'] for e in result.tva_entries) if result.tva_entries else None
result.tva_entries, result.confidence_tva = store_profile.extract_tva_entries(text_upper)
result.tva_total = sum((e['amount'] for e in result.tva_entries), Decimal(0)) if result.tva_entries else None
result.payment_methods = store_profile.extract_payment_methods(text_upper)
# Calculate payment confidence from individual payment method confidences
if result.payment_methods:
payment_confidences = [pm.get('confidence', 0.0) for pm in result.payment_methods]
result.confidence_payment = max(payment_confidences) if payment_confidences else 0.0
else:
result.confidence_payment = 0.0
# Client data extraction via profile (CUI + name)
profile_client_cui, cui_confidence = store_profile.extract_client_cui(text_upper)
@@ -502,8 +518,8 @@ class ReceiptExtractor:
result.amount, result.confidence_amount = self._extract_amount(text_upper)
result.receipt_date, result.confidence_date = self._extract_date(text_upper)
result.receipt_number, _ = self._extract_number(text_upper)
result.tva_entries, result.tva_total = self._extract_tva_entries(text_upper)
result.payment_methods = self._extract_payment_methods(text_upper)
result.tva_entries, result.tva_total, result.confidence_tva = self._extract_tva_entries(text_upper)
result.payment_methods, result.confidence_payment = self._extract_payment_methods(text_upper)
# Generic client extraction
client_name, client_cui, client_address, confidence = self._extract_client_data(text_upper, text)
@@ -1289,7 +1305,7 @@ class ReceiptExtractor:
self,
candidates: List[tuple],
tva_bon_total: Optional[Decimal]
) -> Tuple[List[dict], Optional[Decimal]]:
) -> Tuple[List[dict], Optional[Decimal], float]:
"""
Select the best TVA candidate from collected candidates.
@@ -1303,10 +1319,10 @@ class ReceiptExtractor:
tva_bon_total: Authoritative TOTAL TVA BON value (if extracted)
Returns:
(best_entries, best_sum)
(best_entries, best_sum, confidence)
"""
if not candidates:
return [], None
return [], None, 0.0
# Score each candidate
scored = []
@@ -1334,9 +1350,9 @@ class ReceiptExtractor:
best = scored[0]
print(f"[TVA Select] Winner: {best[1]} (score={best[0]:.1f})", flush=True)
return best[3], best[4]
return best[3], best[4], best[2] # entries, sum, confidence
def _extract_tva_entries(self, text: str) -> Tuple[List[dict], Optional[Decimal]]:
def _extract_tva_entries(self, text: str) -> Tuple[List[dict], Optional[Decimal], float]:
"""
Extract multiple TVA (VAT) entries from text.
Romanian receipts can have multiple TVA rates (A=19%, B=9%, C=5%, D=0%).
@@ -1345,11 +1361,12 @@ class ReceiptExtractor:
- Try ALL patterns and collect candidates
- Select best candidate based on matching TOTAL TVA BON
Returns (tva_entries, tva_total) where tva_entries is a list of:
Returns (tva_entries, tva_total, confidence) where tva_entries is a list of:
{'code': 'A', 'percent': 19, 'amount': Decimal('15.20')}
"""
tva_entries = []
seen_entries = set() # To avoid duplicates
confidence = 0.0 # Track extraction confidence
# Check for non-VAT payer (NEPLATITOR DE TVA) - TVA = 0
# OCR variants: NEPLATTOR, NEPLATITOR, NEPLATOR, NEPLATTOR, ANEPLATHTOR, MEPLATITOR, etc.
@@ -1366,8 +1383,8 @@ class ReceiptExtractor:
]
for pattern in non_vat_patterns:
if re.search(pattern, text, re.IGNORECASE):
# Non-VAT payer - return TVA = 0
return [{'code': 'D', 'percent': 0, 'amount': Decimal('0.00')}], Decimal('0.00')
# Non-VAT payer - return TVA = 0, high confidence
return [{'code': 'D', 'percent': 0, 'amount': Decimal('0.00')}], Decimal('0.00'), 0.95
# Normalize spaces in numbers first (OCR may produce "32. 31" or "49, 58")
normalized_text = re.sub(r'(\d+)[.,]\s+(\d{2})', r'\1.\2', text)
@@ -1717,7 +1734,7 @@ class ReceiptExtractor:
# === CANDIDATE SELECTION ===
# Select best candidate using TOTAL TVA BON as authoritative reference
if all_candidates:
best_entries, best_sum = self._select_best_tva_candidate(all_candidates, tva_bon_total)
best_entries, best_sum, confidence = self._select_best_tva_candidate(all_candidates, tva_bon_total)
if best_entries:
tva_entries = best_entries
entries_sum = best_sum
@@ -1725,7 +1742,7 @@ class ReceiptExtractor:
# Calculate sum from entries (if not set by candidate selection)
entries_sum = None
if tva_entries:
entries_sum = sum(entry['amount'] for entry in tva_entries)
entries_sum = sum((entry['amount'] for entry in tva_entries), Decimal(0))
# Validate and correct TVA values
tva_entries, tva_total = self._validate_and_correct_tva(
@@ -1735,7 +1752,7 @@ class ReceiptExtractor:
# Sort by code (A, B, C, D)
tva_entries.sort(key=lambda x: x.get('code', 'Z'))
return tva_entries, tva_total
return tva_entries, tva_total, confidence if tva_entries else 0.0
def _get_tva_code_from_percent(self, percent: int) -> str:
"""Map TVA percentage to standard Romanian code.
@@ -1843,7 +1860,7 @@ class ReceiptExtractor:
tva_entries = corrected_entries
# Recalculate sum after corrections
entries_sum = sum(entry['amount'] for entry in tva_entries) if tva_entries else None
entries_sum = sum((entry['amount'] for entry in tva_entries), Decimal(0)) if tva_entries else None
# Validate sum against TOTAL TVA BON
if tva_bon_total and entries_sum:
@@ -1876,7 +1893,7 @@ class ReceiptExtractor:
seen.add(key)
unique_entries.append(entry)
tva_entries = unique_entries
entries_sum = sum(e['amount'] for e in tva_entries)
entries_sum = sum((e['amount'] for e in tva_entries), Decimal(0))
# Final total
tva_total = entries_sum if entries_sum else tva_bon_total
@@ -2032,15 +2049,16 @@ class ReceiptExtractor:
return None
def _extract_payment_methods(self, text: str) -> List[dict]:
def _extract_payment_methods(self, text: str) -> Tuple[List[dict], float]:
"""
Extract payment methods (CARD/NUMERAR) from receipt.
These appear after TOTAL LEI and before TOTAL TVA section.
Returns list of: {'method': 'CARD'/'NUMERAR', 'amount': Decimal}
Returns tuple of: (list of {'method': 'CARD'/'NUMERAR', 'amount': Decimal}, confidence)
"""
payment_methods = []
seen_methods = set()
max_confidence = 0.0
# Normalize spaces in numbers
normalized_text = re.sub(r'(\d+)[.,]\s+(\d{2})', r'\1.\2', text)
@@ -2071,13 +2089,15 @@ class ReceiptExtractor:
'amount': amount
})
seen_methods.add(method)
print(f"[Payment] Found {method}: {amount} (pattern matched)", flush=True)
if confidence > max_confidence:
max_confidence = confidence
print(f"[Payment] Found {method}: {amount} (pattern matched, conf={confidence})", flush=True)
elif amount >= self.MAX_REASONABLE_PAYMENT:
print(f"[Payment] Rejected unreasonable amount {amount} for {method} (likely OCR error)", flush=True)
except (InvalidOperation, ValueError):
continue
return payment_methods
return payment_methods, max_confidence if payment_methods else 0.0
def _validate_payment_methods(
self, payment_methods: List[dict], total: Optional[Decimal]