feat: Add multiple TVA entries support for Romanian receipts

- Add TvaEntry schema supporting multiple TVA rates (A, B, C, D codes)
- Update OCR extractor to extract multiple TVA entries from receipts
- Support both old (19%, 9%, 5%) and new Romanian rates (21%, 11% from Aug 2025)
- Add tva_breakdown, tva_total, items_count, vendor_address to Receipt model
- Update OCRPreview.vue to display TVA entries with rate badges
- Add "Detalii Suplimentare" section in ReceiptCreateView with editable TVA table
- Add TVA breakdown display in ReceiptDetailView
- Create database migration for new TVA columns

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

data-entry-app/backend/app/db/models/receipt.py

@@ -51,6 +51,12 @@ class Receipt(SQLModel, table=True):
     amount: Decimal = Field(decimal_places=2, max_digits=15)
     description: Optional[str] = Field(default=None, max_length=500)
 
+    # TVA info (extracted from OCR) - stored as JSON for multiple entries
+    tva_breakdown: Optional[str] = Field(default=None, max_length=1000)  # JSON: [{"code":"A","percent":19,"amount":"15.20"}]
+    tva_total: Optional[Decimal] = Field(default=None, decimal_places=2, max_digits=15)
+    items_count: Optional[int] = Field(default=None)
+    vendor_address: Optional[str] = Field(default=None, max_length=500)
+
     # Expense type (for auto-generating accounting entries)
     expense_type_code: Optional[str] = Field(default=None, max_length=20)
 

data-entry-app/backend/app/routers/ocr.py

@@ -11,7 +11,7 @@ from app.db.database import get_session
 from app.db.crud.attachment import AttachmentCRUD
 from app.services.ocr_service import ocr_service
 from app.services.ocr_engine import OCREngine
-from app.schemas.ocr import OCRResponse, OCRStatusResponse, ExtractionData
+from app.schemas.ocr import OCRResponse, OCRStatusResponse, ExtractionData, TvaEntry
 
 router = APIRouter()
 
@@ -78,6 +78,12 @@ async def extract_from_image(file: UploadFile = File(...)):
             raise HTTPException(status_code=422, detail=message)
 
         # Convert ExtractionResult to ExtractionData schema
+        # Convert tva_entries from dict to TvaEntry objects
+        tva_entries_schema = [
+            TvaEntry(code=e.get('code'), percent=e['percent'], amount=e['amount'])
+            for e in result.tva_entries
+        ] if result.tva_entries else []
+
         data = ExtractionData(
             receipt_type=result.receipt_type,
             receipt_number=result.receipt_number,
@@ -87,6 +93,10 @@ async def extract_from_image(file: UploadFile = File(...)):
             partner_name=result.partner_name,
             cui=result.cui,
             description=result.description,
+            tva_entries=tva_entries_schema,
+            tva_total=result.tva_total,
+            address=result.address,
+            items_count=result.items_count,
             confidence_amount=result.confidence_amount,
             confidence_date=result.confidence_date,
             confidence_vendor=result.confidence_vendor,
@@ -137,6 +147,12 @@ async def extract_from_attachment(
         raise HTTPException(status_code=422, detail=message)
 
     # Convert ExtractionResult to ExtractionData schema
+    # Convert tva_entries from dict to TvaEntry objects
+    tva_entries_schema = [
+        TvaEntry(code=e.get('code'), percent=e['percent'], amount=e['amount'])
+        for e in result.tva_entries
+    ] if result.tva_entries else []
+
     data = ExtractionData(
         receipt_type=result.receipt_type,
         receipt_number=result.receipt_number,
@@ -146,6 +162,10 @@ async def extract_from_attachment(
         partner_name=result.partner_name,
         cui=result.cui,
         description=result.description,
+        tva_entries=tva_entries_schema,
+        tva_total=result.tva_total,
+        address=result.address,
+        items_count=result.items_count,
         confidence_amount=result.confidence_amount,
         confidence_date=result.confidence_date,
         confidence_vendor=result.confidence_vendor,

data-entry-app/backend/app/schemas/ocr.py

@@ -2,11 +2,18 @@
 
 from datetime import date
 from decimal import Decimal
-from typing import Optional
+from typing import Optional, List
 
 from pydantic import BaseModel, Field
 
 
+class TvaEntry(BaseModel):
+    """Single TVA entry with code, percentage and amount."""
+    code: Optional[str] = Field(default=None, description="TVA code: A, B, C, D")
+    percent: int = Field(description="TVA percentage: 0, 5, 9, 19, 21")
+    amount: Decimal = Field(description="TVA amount for this rate")
+
+
 class ExtractionData(BaseModel):
     """Extracted receipt data from OCR."""
 
@@ -19,6 +26,12 @@ class ExtractionData(BaseModel):
     cui: Optional[str] = Field(default=None, description="CUI (fiscal identification code)")
     description: Optional[str] = Field(default=None, description="Optional description")
 
+    # Additional extracted fields - Multiple TVA entries support
+    tva_entries: List[TvaEntry] = Field(default=[], description="List of TVA entries by rate (A, B, C, D)")
+    tva_total: Optional[Decimal] = Field(default=None, description="Total TVA amount")
+    address: Optional[str] = Field(default=None, description="Vendor address")
+    items_count: Optional[int] = Field(default=None, description="Number of items/articles")
+
     confidence_amount: float = Field(default=0.0, ge=0, le=1, description="Amount extraction confidence")
     confidence_date: float = Field(default=0.0, ge=0, le=1, description="Date extraction confidence")
     confidence_vendor: float = Field(default=0.0, ge=0, le=1, description="Vendor extraction confidence")
@@ -30,18 +43,25 @@ class ExtractionData(BaseModel):
         json_schema_extra = {
             "example": {
                 "receipt_type": "bon_fiscal",
-                "receipt_number": "12345",
-                "receipt_series": None,
-                "receipt_date": "2024-01-15",
-                "amount": 125.50,
-                "partner_name": "MEGA IMAGE SRL",
-                "cui": "12345678",
+                "receipt_number": "1360760",
+                "receipt_series": "0146",
+                "receipt_date": "2025-10-11",
+                "amount": 186.16,
+                "partner_name": "FIVE-HOLDING S.A.",
+                "cui": "10562600",
                 "description": None,
-                "confidence_amount": 0.95,
-                "confidence_date": 0.90,
-                "confidence_vendor": 0.75,
-                "overall_confidence": 0.87,
-                "raw_text": "BON FISCAL\nMEGA IMAGE SRL\n..."
+                "tva_entries": [
+                    {"code": "A", "percent": 19, "amount": 25.00},
+                    {"code": "B", "percent": 9, "amount": 7.31}
+                ],
+                "tva_total": 32.31,
+                "address": "JUD. CONSTANTA, MUN. CONSTANTA, STR. ION ROATA NR. 3",
+                "items_count": 17,
+                "confidence_amount": 0.98,
+                "confidence_date": 0.98,
+                "confidence_vendor": 0.95,
+                "overall_confidence": 0.97,
+                "raw_text": "FIVE-HOLDING S.A.\nCIF: RO10562600\n..."
             }
         }
 

data-entry-app/backend/app/schemas/receipt.py

@@ -64,6 +64,15 @@ class AttachmentResponse(BaseModel):
     uploaded_at: datetime
 
 
+# ============ TVA Schema ============
+
+class TvaEntrySchema(BaseModel):
+    """Single TVA entry with code, percentage and amount."""
+    code: Optional[str] = Field(default=None, description="TVA code: A, B, C, D")
+    percent: int = Field(description="TVA percentage: 0, 5, 9, 19, 21")
+    amount: Decimal = Field(description="TVA amount for this rate")
+
+
 # ============ Receipt Schemas ============
 
 class ReceiptBase(BaseModel):
@@ -75,6 +84,12 @@ class ReceiptBase(BaseModel):
     receipt_date: date
     amount: Decimal = Field(gt=0)
     description: Optional[str] = Field(default=None, max_length=500)
+    # TVA info (multiple entries support)
+    tva_breakdown: Optional[List[TvaEntrySchema]] = Field(default=None, description="List of TVA entries")
+    tva_total: Optional[Decimal] = Field(default=None, description="Total TVA amount")
+    items_count: Optional[int] = Field(default=None, description="Number of items")
+    vendor_address: Optional[str] = Field(default=None, max_length=500, description="Vendor address")
+    # Other fields
     expense_type_code: Optional[str] = Field(default=None, max_length=20)
     company_id: int
     partner_id: Optional[int] = None
@@ -98,6 +113,12 @@ class ReceiptUpdate(BaseModel):
     receipt_date: Optional[date] = None
     amount: Optional[Decimal] = Field(default=None, gt=0)
     description: Optional[str] = Field(default=None, max_length=500)
+    # TVA info (multiple entries support)
+    tva_breakdown: Optional[List[TvaEntrySchema]] = Field(default=None, description="List of TVA entries")
+    tva_total: Optional[Decimal] = Field(default=None, description="Total TVA amount")
+    items_count: Optional[int] = Field(default=None, description="Number of items")
+    vendor_address: Optional[str] = Field(default=None, max_length=500, description="Vendor address")
+    # Other fields
     expense_type_code: Optional[str] = Field(default=None, max_length=20)
     partner_id: Optional[int] = None
     partner_name: Optional[str] = Field(default=None, max_length=200)

data-entry-app/backend/app/services/image_preprocessor.py

@@ -23,24 +23,37 @@ class ImagePreprocessor:
             raise ValueError(f"Could not load image: {path}")
         return image
 
-    def pdf_to_images(self, path: Path, dpi: int = 300) -> List[np.ndarray]:
-        """Convert PDF to images."""
+    def pdf_to_images(self, path: Path, dpi: int = 400) -> List[np.ndarray]:
+        """
+        Convert PDF to images with high DPI for better OCR.
+
+        Args:
+            path: Path to PDF file
+            dpi: Resolution (400 recommended for receipts, higher = better quality but slower)
+        """
         if not PDF_AVAILABLE:
             raise RuntimeError("pdf2image not available. Install with: pip install pdf2image")
+        # Use 400 DPI for better text recognition on thermal receipts
         images = pdf2image.convert_from_path(str(path), dpi=dpi)
         return [np.array(img) for img in images]
 
-    def preprocess(self, image: np.ndarray) -> np.ndarray:
+    def preprocess(self, image: np.ndarray, high_quality: bool = True) -> np.ndarray:
         """
         Apply preprocessing pipeline for thermal receipt images.
 
         Pipeline:
         1. Convert to grayscale
-        2. Resize if too small (min 1000px width)
+        2. Resize if too small (min 1500px width for high quality)
         3. Deskew (straighten rotated text)
-        4. Denoise (Non-local means)
-        5. Adaptive thresholding (binarization)
-        6. Morphological close (connect broken chars)
+        4. Contrast enhancement (CLAHE)
+        5. Denoise (Non-local means)
+        6. Sharpening (for clearer text edges)
+        7. Adaptive thresholding (binarization)
+        8. Morphological operations (connect broken chars)
+
+        Args:
+            image: Input image (BGR or grayscale)
+            high_quality: If True, apply more aggressive preprocessing
         """
         # 1. Grayscale
         if len(image.shape) == 3:
@@ -48,10 +61,11 @@ class ImagePreprocessor:
         else:
             gray = image.copy()
 
-        # 2. Resize if too small
+        # 2. Resize if too small (larger = better OCR)
         height, width = gray.shape
-        if width < 1000:
-            scale = 1000 / width
+        min_width = 1500 if high_quality else 1000
+        if width < min_width:
+            scale = min_width / width
             gray = cv2.resize(
                 gray, None, fx=scale, fy=scale,
                 interpolation=cv2.INTER_CUBIC
@@ -60,24 +74,43 @@ class ImagePreprocessor:
         # 3. Deskew
         gray = self._deskew(gray)
 
-        # 4. Denoise
+        # 4. Contrast enhancement with CLAHE (Contrast Limited Adaptive Histogram Equalization)
+        clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
+        enhanced = clahe.apply(gray)
+
+        # 5. Denoise (slightly less aggressive to preserve text details)
         denoised = cv2.fastNlMeansDenoising(
-            gray, h=10,
+            enhanced, h=8,  # Lower h = preserve more details
             templateWindowSize=7,
             searchWindowSize=21
         )
 
-        # 5. Adaptive thresholding
+        # 6. Sharpening to enhance text edges
+        if high_quality:
+            # Unsharp mask for better text clarity
+            gaussian = cv2.GaussianBlur(denoised, (0, 0), 2.0)
+            sharpened = cv2.addWeighted(denoised, 1.5, gaussian, -0.5, 0)
+        else:
+            sharpened = denoised
+
+        # 7. Adaptive thresholding with optimized parameters
         binary = cv2.adaptiveThreshold(
-            denoised, 255,
+            sharpened, 255,
             cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
             cv2.THRESH_BINARY,
-            blockSize=15, C=8
+            blockSize=11,  # Smaller block = better for small text
+            C=5  # Lower C = darker result, better for faded receipts
         )
 
-        # 6. Morphological close
-        kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (2, 2))
-        result = cv2.morphologyEx(binary, cv2.MORPH_CLOSE, kernel)
+        # 8. Morphological operations
+        # Close small gaps in characters
+        kernel_close = cv2.getStructuringElement(cv2.MORPH_RECT, (2, 2))
+        result = cv2.morphologyEx(binary, cv2.MORPH_CLOSE, kernel_close)
+
+        # Optional: Remove small noise spots
+        if high_quality:
+            kernel_open = cv2.getStructuringElement(cv2.MORPH_RECT, (1, 1))
+            result = cv2.morphologyEx(result, cv2.MORPH_OPEN, kernel_open)
 
         return result
 

data-entry-app/backend/app/services/ocr_engine.py

@@ -64,11 +64,17 @@ class OCREngine:
                 PaddleOCR = _PaddleOCR
 
                 print("Initializing PaddleOCR engine...")
-                # PaddleOCR 3.x API - simplified parameters
+                # PaddleOCR 3.x API - optimized for Romanian receipts
                 self._paddle = PaddleOCR(
-                    lang='en',  # Better for mixed text with numbers
+                    lang='en',  # 'en' works better than 'ro' for mixed alphanumeric
+                    # High quality settings for better accuracy
+                    det_db_thresh=0.3,      # Lower threshold = detect more text (default 0.3)
+                    det_db_box_thresh=0.5,  # Box confidence threshold (default 0.5)
+                    det_db_unclip_ratio=1.8,  # Expand detected boxes slightly (default 1.5)
+                    rec_batch_num=6,        # Batch size for recognition
+                    use_angle_cls=True,     # Enable text angle classification
                 )
-                print("PaddleOCR initialized successfully")
+                print("PaddleOCR initialized successfully with high-quality settings")
             except Exception as e:
                 print(f"Warning: Failed to initialize PaddleOCR: {e}")
                 self._paddle = None

data-entry-app/backend/app/services/ocr_extractor.py

@@ -3,7 +3,7 @@
 import re
 from datetime import date, datetime
 from decimal import Decimal, InvalidOperation
-from typing import Optional, Tuple
+from typing import Optional, Tuple, List
 from dataclasses import dataclass, field
 
 
@@ -18,6 +18,11 @@ class ExtractionResult:
     partner_name: Optional[str] = None
     cui: Optional[str] = None
     description: Optional[str] = None
+    # Additional extracted fields - Multiple TVA entries support
+    tva_entries: List[dict] = field(default_factory=list)  # [{code, percent, amount}]
+    tva_total: Optional[Decimal] = None
+    address: Optional[str] = None
+    items_count: Optional[int] = None
 
     confidence_amount: float = 0.0
     confidence_date: float = 0.0
@@ -40,44 +45,158 @@ class ReceiptExtractor:
     """Extract receipt fields using pattern matching for Romanian receipts."""
 
     # Total amount patterns (most specific first)
+    # Romanian receipts use various formats: TOTAL LEI, TOTAL:, TOTAL RON, etc.
+    # OCR often produces errors, so patterns must be tolerant
     TOTAL_PATTERNS = [
+        # Most common: TOTAL LEI followed by amount
+        (r'TOTAL\s+LEI\s*([\d\s.,]+)', 0.98),
+        (r'[OT]?OTAL\s+LEI\s*([\d\s.,]+)', 0.95),  # OCR may miss first letter
+        # Standard patterns
         (r'TOTAL\s*:?\s*([\d\s.,]+)\s*(?:RON|LEI)?', 0.95),
         (r'TOTAL\s+(?:RON|LEI)\s*([\d\s.,]+)', 0.95),
+        # SUBTOTAL when TOTAL not found
+        (r'SUBTOTAL\s*([\d\s.,]+)', 0.90),
+        (r'[SB]?UBTOTAL\s*([\d\s.,]+)', 0.88),  # OCR variations
+        # Payment methods
         (r'DE\s+PLATA\s*:?\s*([\d\s.,]+)', 0.90),
         (r'SUMA\s*:?\s*([\d\s.,]+)', 0.85),
         (r'PLATA\s+CARD\s*:?\s*([\d\s.,]+)', 0.85),
         (r'NUMERAR\s*:?\s*([\d\s.,]+)', 0.80),
+        (r'REST\s*:?\s*([\d\s.,]+)', 0.70),  # Sometimes total is near REST
     ]
 
-    # Date patterns
+    # Fallback: Find the largest repeated amount (likely the total)
+    # This handles cases where OCR doesn't capture "TOTAL" keyword
+
+    # Date patterns - support dash, dot, and slash separators
+    # OCR may produce DRTA instead of DATA, DAIA, etc.
     DATE_PATTERNS = [
-        (r'DATA\s*:?\s*(\d{2}[./]\d{2}[./]\d{4})', 0.95),
-        (r'(\d{2}[./]\d{2}[./]\d{4})\s+\d{2}:\d{2}', 0.90),
-        (r'(\d{2}[./]\d{2}[./]\d{4})', 0.80),
-        (r'(\d{4}[./]\d{2}[./]\d{2})', 0.75),  # YYYY.MM.DD format
+        # DATA/DRTA/DAIA: DD-MM-YYYY (OCR tolerant)
+        (r'D[AR]TA\s*:?\s*(\d{2}[-./]\d{2}[-./]\d{4})', 0.98),
+        (r'DATA\s*:?\s*(\d{2}[-./]\d{2}[-./]\d{4})', 0.98),
+        # Date followed by ORA (time) - OCR may produce 0RA
+        (r'(\d{2}[-./]\d{2}[-./]\d{4})\s+[O0]RA\s*:?\s*\d{2}:\d{2}', 0.95),
+        # Date followed by time without ORA keyword
+        (r'(\d{2}[-./]\d{2}[-./]\d{4})\s+\d{2}:\d{2}', 0.90),
+        # Standalone date
+        (r'(\d{2}[-./]\d{2}[-./]\d{4})', 0.80),
+        # YYYY-MM-DD format (less common)
+        (r'(\d{4}[-./]\d{2}[-./]\d{2})', 0.75),
     ]
 
-    # Receipt number patterns
+    # Receipt number patterns - Romanian fiscal receipt formats
+    # OCR may produce N instead of : or other errors
     NUMBER_PATTERNS = [
+        # NDS format (common in Romanian POS)
+        (r'NDS\s*:?\s*(\d+)', 0.98),
+        # C3POS terminal format - OCR may have N instead of : (C3POS-CT2N1360760)
+        (r'C3POS[-A-Z0-9]*[N:](\d{6,7})', 0.98),  # CT2N1360760 format
+        (r'C3POS.*?(\d{6,7})\b', 0.95),  # Any C3POS followed by 6-7 digit number
+        (r'CT2[N:]\s*(\d{6,})', 0.95),  # CT2N prefix
+        # BF (Bon Fiscal) number
+        (r'BF\s*:?\s*(\d+)', 0.93),
+        # NIVS format
+        (r'NIVS\s*:?\s*(\d+)', 0.95),
+        # Standard NR BON formats
         (r'NR\.?\s*BON\s*:?\s*(\d+)', 0.95),
         (r'BON\s+(?:FISCAL\s+)?NR\.?\s*:?\s*(\d+)', 0.95),
         (r'CHITANTA\s+NR\.?\s*:?\s*(\d+)', 0.95),
+        # Document number
         (r'NR\.?\s+DOCUMENT\s*:?\s*(\d+)', 0.90),
-        (r'NR\.?\s*:?\s*(\d{4,})', 0.70),
+        # ID BF format
+        (r'ID\s*BF\s*:?\s*(\d+)', 0.90),
+        # TD format (transaction ID)
+        (r'TD\s*:?\s*(\d+)', 0.85),
+        # 6-8 digit number (typical receipt number length)
+        (r'\b(\d{6,8})\b', 0.70),
+        # Generic long number at end (fallback)
+        (r'NR\.?\s*:?\s*(\d{4,})', 0.65),
     ]
 
-    # CUI (fiscal code) patterns
+    # CUI (fiscal code) patterns - IMPORTANT: exclude CLIENT CUI
+    # CIF = Cod de Identificare Fiscală (vendor's tax ID)
+    # CLIENT C.U.I. = client's tax ID (should be ignored)
+    # OCR errors: R0 instead of RO, C1F instead of CIF
     CUI_PATTERNS = [
-        (r'C\.?U\.?I\.?\s*:?\s*(?:RO)?(\d{6,10})', 0.95),
-        (r'C\.?I\.?F\.?\s*:?\s*(?:RO)?(\d{6,10})', 0.95),
-        (r'COD\s+FISCAL\s*:?\s*(?:RO)?(\d{6,10})', 0.90),
-        (r'(?:RO)?(\d{6,10})\s*-?\s*(?:J|CUI)', 0.80),
+        # CIF at start of line (definitely vendor) - tolerant to OCR errors
+        (r'^CIF\s*:?\s*(?:R[O0])?(\d{6,10})', 0.98),
+        (r'^C[I1]F\s*:?\s*(?:R[O0])?(\d{6,10})', 0.95),  # C1F OCR error
+        # CIF not preceded by CLIENT (negative lookbehind)
+        (r'(?<!CLIENT\s)(?<!LIENT\s)CIF\s*:?\s*(?:R[O0])?(\d{6,10})', 0.95),
+        # Standalone CIF: format with OCR tolerance
+        (r'\bC[I1]F\s*:?\s*(?:R[O0])?(\d{6,10})\b', 0.90),
+        # COD FISCAL (vendor)
+        (r'COD\s+FISCAL\s*:?\s*(?:R[O0])?(\d{6,10})', 0.90),
+        # C.I.F. format (with dots)
+        (r'(?<!CLIENT\s)C\.[I1]\.F\.?\s*:?\s*(?:R[O0])?(\d{6,10})', 0.88),
+        # CUI format (less specific, use with caution)
+        (r'(?<!CLIENT\s)C\.?U\.?[I1]\.?\s*:?\s*(?:R[O0])?(\d{6,10})', 0.85),
     ]
 
-    # Series patterns
+    # Series patterns - be strict to avoid false matches
     SERIES_PATTERNS = [
         (r'SERIE\s*:?\s*([A-Z]{1,4})', 0.90),
-        (r'([A-Z]{2,4})\s+NR\.?\s*\d+', 0.80),
+        # Z: format from Romanian fiscal receipts (must be at start of line or after space)
+        (r'(?:^|\s)Z\s*:\s*(\d{4})', 0.85),
+        # BF series with explicit marker
+        (r'(?:^|\s)BF\s*:\s*(\d{4})', 0.85),
+    ]
+
+    # TVA (VAT) patterns - OCR may produce TUA, TVR, etc.
+    TVA_PATTERNS = [
+        # TOTAL TVA BON format (OCR tolerant: TUA, TVR)
+        (r'TOTAL\s+T[VU][AR]\s+BON\s*:?\s*([\d\s.,]+)', 0.98),
+        (r'T[O0]TAL\s+T[VU][AR]\s*:?\s*([\d\s.,]+)', 0.95),
+        # TVA with percentage (OCR tolerant)
+        (r'T[VU][AR]\s+(?:A\s*[-:]?\s*)?(\d{1,2})\s*%\s*:?\s*([\d\s.,]+)', 0.95),
+        (r'T[VU][AR]\s+[A-Z]\s*[-:]\s*(\d{1,2})\s*%\s*([\d\s.,]+)', 0.93),
+        # Simple TVA pattern
+        (r'T[VU][AR]\s*:?\s*([\d\s.,]+)', 0.85),
+        # Standalone percentage line near TVA
+        (r'(\d{1,2})\s*%\s*:?\s*([\d\s.,]+)', 0.75),
+    ]
+
+    # Items count patterns - OCR may produce OZ instead of POZ, etc.
+    # Number may be on separate line before or after the label
+    ITEMS_COUNT_PATTERNS = [
+        # NR. POZ. ART. IN BON: 17 (Romanian format with dots and spaces)
+        # OCR tolerant: OZ instead of POZ, ARI instead of ART
+        (r'NR\.?\s*P?[O0]Z\.?\s*ART\.?\s*(?:IN\s+BON)?\s*:?\s*(\d+)', 0.98),
+        # Number on line BEFORE "OZ. ART. IN BON:" - OCR sometimes reorders
+        (r'(\d{1,2})\s*\n\s*[O0]Z\.?\s*ART', 0.95),
+        # Number may be on next line after label
+        (r'[O0]Z\.?\s*ART\.?\s*(?:IN\s+BON)?\s*:?\s*[\n\s]*(\d+)', 0.93),
+        (r'NR\.?\s*(?:P?[O0]Z\.?)?\s*ART(?:ICOLE)?\.?\s*(?:IN\s+BON)?\s*:?\s*[\n\s]*(\d+)', 0.90),
+        # Simpler patterns
+        (r'ARTIC[O0]LE\s*:?\s*(\d+)', 0.88),
+        (r'P?[O0]Z\s*:?\s*(\d+)', 0.85),
+        # X articole/pozitii
+        (r'(\d+)\s*(?:ARTIC[O0]LE|P[O0]ZITII|BUC)', 0.80),
+    ]
+
+    # Address patterns (Romanian format)
+    ADDRESS_PATTERNS = [
+        # Street patterns
+        (r'(STR\.?\s+[A-Z0-9\s.,]+(?:NR\.?\s*\d+)?)', 0.90),
+        # Full address with JUD (county)
+        (r'(JUD\.?\s+[A-Z]+,?\s*(?:MUN\.?|OR\.?|COM\.?)?\s*[A-Z]+)', 0.85),
+    ]
+
+    # Vendor name indicators (lines containing these are likely vendor names)
+    VENDOR_INDICATORS = [
+        r'\bS\.?R\.?L\.?\b',      # S.R.L.
+        r'\bS\.?A\.?\b',          # S.A.
+        r'\bS\.?N\.?C\.?\b',      # S.N.C.
+        r'\bS\.?C\.?S\.?\b',      # S.C.S.
+        r'\bI\.?I\.?\b',          # I.I. (Individual)
+        r'\bP\.?F\.?A\.?\b',      # P.F.A.
+        r'\bS\.?C\.?\b',          # S.C.
+        r'HOLDING',
+        r'COMPANY',
+        r'GROUP',
+        r'MAGAZIN',
+        r'MARKET',
+        r'SHOP',
     ]
 
     def extract(self, text: str) -> ExtractionResult:
@@ -86,13 +205,18 @@ class ReceiptExtractor:
         result.raw_text = text
         text_upper = text.upper()
 
-        # Extract fields
+        # Extract core fields
         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.receipt_series, _ = self._extract_series(text_upper)
         result.partner_name, result.confidence_vendor = self._extract_vendor(text)
-        result.cui, _ = self._extract_cui(text_upper)
+        result.cui, _ = self._extract_cui(text_upper, text)
+
+        # Extract additional fields - Multiple TVA entries
+        result.tva_entries, result.tva_total = self._extract_tva_entries(text_upper)
+        result.items_count = self._extract_items_count(text_upper)
+        result.address = self._extract_address(text_upper)
 
         # Detect receipt type
         result.receipt_type = self._detect_receipt_type(text_upper)
@@ -101,18 +225,85 @@ class ReceiptExtractor:
 
     def _extract_amount(self, text: str) -> Tuple[Optional[Decimal], float]:
         """Extract total amount from text."""
+        # First try standard patterns (TOTAL, SUBTOTAL, etc.)
         for pattern, confidence in self.TOTAL_PATTERNS:
             match = re.search(pattern, text, re.IGNORECASE | re.MULTILINE)
             if match:
                 try:
                     amount_str = re.sub(r'[^\d.,]', '', match.group(1))
-                    # Handle Romanian number format (1.234,56)
                     amount_str = self._normalize_number(amount_str)
                     amount = Decimal(amount_str)
                     if amount > 0:
                         return amount, confidence
                 except (InvalidOperation, ValueError):
                     continue
+
+        # Strategy 2: Find amounts AFTER product lines end
+        # Products have pattern: "X BUC/ROLA X price = price"
+        # Total appears after all products
+        product_pattern = r'\d\s+(?:BUC|ROLA|ROLN|ROL)\s+X'
+        product_matches = list(re.finditer(product_pattern, text, re.IGNORECASE))
+        if product_matches:
+            # Get text after the last product line
+            last_product_pos = product_matches[-1].end()
+            after_products = text[last_product_pos:]
+
+            # Find standalone amounts on their own line after products
+            line_amount_pattern = r'^[\s]*(\d{2,4}[.,]\s*\d{2})[\s]*$'
+            standalone_amounts = []
+            for match in re.finditer(line_amount_pattern, after_products, re.MULTILINE):
+                try:
+                    amount_str = match.group(1).replace(' ', '')
+                    amount_str = self._normalize_number(amount_str)
+                    amount = Decimal(amount_str)
+                    if amount > 10:  # Filter out small values
+                        standalone_amounts.append(amount)
+                except (InvalidOperation, ValueError):
+                    continue
+
+            if standalone_amounts:
+                # The largest standalone amount after products is likely the total
+                max_amount = max(standalone_amounts)
+                # Higher confidence if it appears multiple times
+                count = standalone_amounts.count(max_amount)
+                confidence = 0.85 if count >= 2 else 0.75
+                return max_amount, confidence
+
+        # Strategy 3: Find the most repeated large amount
+        # Normalize spaces in numbers (OCR may produce "186. 16")
+        normalized_text = re.sub(r'(\d+)[.,]\s+(\d{2})', r'\1.\2', text)
+        amount_pattern = r'(\d{2,4}[.,]\d{2})\b'
+        amounts = re.findall(amount_pattern, normalized_text)
+        if amounts:
+            from collections import Counter
+            amount_counts = Counter(amounts)
+            # Filter amounts that appear 2+ times and are > 20
+            candidates = []
+            for amt_str, count in amount_counts.items():
+                try:
+                    amt = Decimal(self._normalize_number(amt_str))
+                    if count >= 2 and amt > 20:
+                        candidates.append((amt, count))
+                except (InvalidOperation, ValueError):
+                    continue
+
+            if candidates:
+                # Return the LARGEST amount that appears multiple times
+                candidates.sort(key=lambda x: x[0], reverse=True)
+                return candidates[0][0], 0.65
+
+        # Last resort: Find any standalone large amount
+        line_amount_pattern = r'^[\s]*(\d{2,4}[.,]\s*\d{2})[\s]*$'
+        for match in re.finditer(line_amount_pattern, text, re.MULTILINE):
+            try:
+                amount_str = match.group(1).replace(' ', '')
+                amount_str = self._normalize_number(amount_str)
+                amount = Decimal(amount_str)
+                if amount > 50:  # Higher threshold for fallback
+                    return amount, 0.50
+            except (InvalidOperation, ValueError):
+                continue
+
         return None, 0.0
 
     def _normalize_number(self, num_str: str) -> str:
@@ -147,7 +338,8 @@ class ReceiptExtractor:
             match = re.search(pattern, text)
             if match:
                 try:
-                    date_str = match.group(1).replace('/', '.')
+                    # Normalize separators to dots
+                    date_str = match.group(1).replace('/', '.').replace('-', '.')
 
                     # Try DD.MM.YYYY format first
                     try:
@@ -181,23 +373,68 @@ class ReceiptExtractor:
         return None, 0.0
 
     def _extract_vendor(self, text: str) -> Tuple[Optional[str], float]:
-        """Extract vendor/partner name from text."""
+        """
+        Extract vendor/partner name from text.
+        Uses multiple strategies:
+        1. Look for lines with company type indicators (S.R.L., S.A., etc.)
+        2. Look for lines near CIF
+        3. Use first valid line as fallback
+        """
         lines = text.split('\n')
         skip_keywords = [
             'BON', 'FISCAL', 'TOTAL', 'DATA', 'NR', 'ORA',
             'SUBTOTAL', 'TVA', 'PLATA', 'CARD', 'NUMERAR',
-            'RON', 'LEI', 'CHITANTA', 'REST'
+            'RON', 'LEI', 'CHITANTA', 'REST', 'CLIENT',
+            'OPERATOR', 'CASIER', 'POS', 'AMEF', 'BINE ATI VENIT',
+            'VA RUGAM', 'PASTRATI', 'VOCEA', 'TIPARIT',
+            'DETERGENT', 'PROSOP', 'HARTIE', 'SACI', 'SPRAY',
+            'BUC', 'ROLA', 'CUMPARATOR'
         ]
 
-        for i, line in enumerate(lines[:7]):  # Check first 7 lines
+        # Strategy 1: Look for lines with vendor indicators (S.R.L., S.A., HOLDING, etc.)
+        for i, line in enumerate(lines[:15]):  # Check first 15 lines
+            line = line.strip()
+            if not line or len(line) < 3:
+                continue
+
+            line_upper = line.upper()
+
+            # Check for vendor indicators
+            for indicator in self.VENDOR_INDICATORS:
+                if re.search(indicator, line_upper):
+                    # Found a company name indicator
+                    vendor = self._clean_vendor_name(line)
+                    if vendor and len(vendor) >= 3:
+                        # High confidence for lines with company indicators
+                        return vendor, 0.95
+
+        # Strategy 2: Look for lines right before or after CIF
+        for i, line in enumerate(lines[:15]):
+            line_upper = line.upper()
+            if 'CIF' in line_upper and 'CLIENT' not in line_upper:
+                # Check line before
+                if i > 0:
+                    prev_line = lines[i-1].strip()
+                    if prev_line and len(prev_line) >= 3:
+                        if not any(kw in prev_line.upper() for kw in skip_keywords):
+                            vendor = self._clean_vendor_name(prev_line)
+                            if vendor:
+                                return vendor, 0.85
+
+        # Strategy 3: First valid line as fallback
+        for i, line in enumerate(lines[:10]):
             line = line.strip()
 
             # Skip empty lines
-            if not line:
+            if not line or len(line) < 3:
                 continue
 
-            # Skip lines that are just numbers
-            if re.match(r'^[\d.,\s]+$', line):
+            # Skip lines that are just numbers or codes
+            if re.match(r'^[\d.,\s:]+$', line):
+                continue
+
+            # Skip lines with barcodes/product codes
+            if re.match(r'^[A-Z]*\d{6,}', line):
                 continue
 
             # Skip lines with keywords
@@ -205,23 +442,68 @@ class ReceiptExtractor:
                 continue
 
             # Clean the line
-            vendor = re.sub(r'[^\w\s.,&-]', '', line).strip()
+            vendor = self._clean_vendor_name(line)
 
-            if len(vendor) >= 3:
+            if vendor and len(vendor) >= 3:
                 # Confidence decreases for lines further down
-                confidence = max(0.3, 0.8 - (i * 0.1))
+                confidence = max(0.3, 0.7 - (i * 0.05))
                 return vendor, confidence
 
         return None, 0.0
 
-    def _extract_cui(self, text: str) -> Tuple[Optional[str], float]:
-        """Extract CUI (fiscal identification code) from text."""
+    def _clean_vendor_name(self, name: str) -> Optional[str]:
+        """Clean and normalize vendor name."""
+        if not name:
+            return None
+
+        # Remove common OCR artifacts
+        name = re.sub(r'[^\w\s.,&\-()]', ' ', name)
+        # Normalize whitespace
+        name = re.sub(r'\s+', ' ', name).strip()
+
+        # Skip if it looks like an address line only
+        if re.match(r'^(STR|JUD|MUN|NR|BL|SC|ET|AP)\.?\s', name.upper()):
+            return None
+
+        # Skip if too short after cleaning
+        if len(name) < 3:
+            return None
+
+        return name
+
+    def _extract_cui(self, text_upper: str, original_text: str) -> Tuple[Optional[str], float]:
+        """
+        Extract vendor CUI (fiscal identification code) from text.
+        Excludes CLIENT CUI which appears as 'CLIENT C.U.I./C.I.F.:...'
+        """
+        # First, try to find CIF on a line that doesn't contain CLIENT
+        lines = text_upper.split('\n')
+        for line in lines:
+            # Skip lines that contain CLIENT (these are buyer's CUI, not vendor's)
+            if 'CLIENT' in line or 'CUMPARATOR' in line or 'LIENT' in line:
+                continue
+
+            # Look for CIF in this line
+            for pattern, confidence in self.CUI_PATTERNS:
+                match = re.search(pattern, line, re.IGNORECASE | re.MULTILINE)
+                if match:
+                    cui = match.group(1)
+                    if 6 <= len(cui) <= 10:
+                        return cui, confidence
+
+        # Fallback: search entire text but exclude CLIENT patterns
         for pattern, confidence in self.CUI_PATTERNS:
-            match = re.search(pattern, text, re.IGNORECASE)
-            if match:
+            # Find all matches
+            for match in re.finditer(pattern, text_upper, re.IGNORECASE | re.MULTILINE):
                 cui = match.group(1)
                 if 6 <= len(cui) <= 10:
-                    return cui, confidence
+                    # Check if this match is preceded by CLIENT in the same line
+                    start = match.start()
+                    line_start = text_upper.rfind('\n', 0, start) + 1
+                    line_text = text_upper[line_start:start]
+                    if 'CLIENT' not in line_text and 'LIENT' not in line_text:
+                        return cui, confidence
+
         return None, 0.0
 
     def _detect_receipt_type(self, text: str) -> str:
@@ -229,3 +511,223 @@ class ReceiptExtractor:
         if 'CHITANTA' in text or 'CHITANȚĂ' in text:
             return 'chitanta'
         return 'bon_fiscal'
+
+    def _extract_tva_entries(self, text: str) -> Tuple[List[dict], Optional[Decimal]]:
+        """
+        Extract multiple TVA (VAT) entries from text.
+        Romanian receipts can have multiple TVA rates (A=19%, B=9%, C=5%, D=0%).
+
+        Returns (tva_entries, tva_total) where tva_entries is a list of:
+            {'code': 'A', 'percent': 19, 'amount': Decimal('15.20')}
+        """
+        tva_entries = []
+        seen_entries = set()  # To avoid duplicates
+
+        # Normalize spaces in numbers first (OCR may produce "32. 31")
+        normalized_text = re.sub(r'(\d+)[.,]\s+(\d{2})', r'\1.\2', text)
+
+        # Pattern 1: "TVA A - 19%: 15.20" or "TVAA - 21% 32.31" (with code)
+        # OCR tolerant: TUA, TVR, etc.
+        pattern_with_code = r'T[VU][AR]\s*([A-D])\s*[-:]\s*(\d{1,2})\s*%\s*:?\s*([\d\s.,]+)'
+        for match in re.finditer(pattern_with_code, normalized_text, re.IGNORECASE):
+            try:
+                code = match.group(1).upper()
+                percent = int(match.group(2))
+                amount_str = match.group(3).replace(' ', '')
+                amount_str = self._normalize_number(re.sub(r'[^\d.,]', '', amount_str))
+                amount = Decimal(amount_str)
+                if amount > 0:
+                    entry_key = (code, percent)
+                    if entry_key not in seen_entries:
+                        tva_entries.append({
+                            'code': code,
+                            'percent': percent,
+                            'amount': amount
+                        })
+                        seen_entries.add(entry_key)
+            except (ValueError, InvalidOperation):
+                continue
+
+        # Pattern 2: "TVA - 21%: 32.31" (without explicit code, assume 'A')
+        if not tva_entries:
+            pattern_no_code = r'T[VU][AR]\s*[-:]\s*(\d{1,2})\s*%\s*:?\s*([\d\s.,]+)'
+            for match in re.finditer(pattern_no_code, normalized_text, re.IGNORECASE):
+                try:
+                    percent = int(match.group(1))
+                    amount_str = match.group(2).replace(' ', '')
+                    amount_str = self._normalize_number(re.sub(r'[^\d.,]', '', amount_str))
+                    amount = Decimal(amount_str)
+                    if amount > 0:
+                        # Determine code based on percent
+                        code = self._get_tva_code_from_percent(percent)
+                        entry_key = (code, percent)
+                        if entry_key not in seen_entries:
+                            tva_entries.append({
+                                'code': code,
+                                'percent': percent,
+                                'amount': amount
+                            })
+                            seen_entries.add(entry_key)
+                except (ValueError, InvalidOperation):
+                    continue
+
+        # Pattern 3: "TVAA - 21%" on one line, amount on next line
+        if not tva_entries:
+            tva_line_pattern = r'T[VU][AR]\s*([A-D])?\s*[-:]\s*(\d{1,2})\s*%'
+            for match in re.finditer(tva_line_pattern, normalized_text, re.IGNORECASE):
+                try:
+                    code = (match.group(1) or 'A').upper()
+                    percent = int(match.group(2))
+
+                    # Look for amount on the next line or immediately after
+                    after_tva = normalized_text[match.end():]
+                    amount_match = re.search(r'^[\s\n]*([\d.,]+)', after_tva)
+                    if amount_match:
+                        amount_str = self._normalize_number(amount_match.group(1))
+                        amount = Decimal(amount_str)
+                        if amount > 0:
+                            entry_key = (code, percent)
+                            if entry_key not in seen_entries:
+                                tva_entries.append({
+                                    'code': code,
+                                    'percent': percent,
+                                    'amount': amount
+                                })
+                                seen_entries.add(entry_key)
+                except (ValueError, InvalidOperation):
+                    continue
+
+        # Pattern 4: Use TVA_PATTERNS for fallback
+        if not tva_entries:
+            for pattern, _ in self.TVA_PATTERNS:
+                match = re.search(pattern, normalized_text, re.IGNORECASE)
+                if match:
+                    try:
+                        # Some patterns have 2 groups (percent, amount), others just amount
+                        if match.lastindex >= 2:
+                            percent = int(match.group(1))
+                            amount_str = match.group(2)
+                        else:
+                            amount_str = match.group(1)
+                            # Try to detect percent from text
+                            percent = self._detect_tva_percent(text)
+
+                        amount_str = amount_str.replace(' ', '')
+                        amount_str = self._normalize_number(re.sub(r'[^\d.,]', '', amount_str))
+                        amount = Decimal(amount_str)
+                        if amount > 0 and percent:
+                            code = self._get_tva_code_from_percent(percent)
+                            entry_key = (code, percent)
+                            if entry_key not in seen_entries:
+                                tva_entries.append({
+                                    'code': code,
+                                    'percent': percent,
+                                    'amount': amount
+                                })
+                                seen_entries.add(entry_key)
+                                break  # Only use first match from fallback
+                    except (ValueError, InvalidOperation):
+                        continue
+
+        # Calculate total
+        tva_total = None
+        if tva_entries:
+            tva_total = sum(entry['amount'] for entry in tva_entries)
+
+        # Sort by code (A, B, C, D)
+        tva_entries.sort(key=lambda x: x.get('code', 'Z'))
+
+        return tva_entries, tva_total
+
+    def _get_tva_code_from_percent(self, percent: int) -> str:
+        """Map TVA percentage to standard Romanian code.
+
+        Romanian TVA rates changed in August 2025:
+        - Standard rate: 19% → 21%
+        - Reduced rate: 9% → 11%
+        - Other rates (5%, 0%) remain unchanged
+
+        Old rates (before Aug 2025):  New rates (from Aug 2025):
+        - A = 19% (standard)          - A = 21% (standard)
+        - B = 9%  (reduced)           - B = 11% (reduced)
+        - C = 5%  (reduced)           - C = 5%  (reduced)
+        - D = 0%  (exempt)            - D = 0%  (exempt)
+
+        Both old and new rates are supported for historical receipts.
+        """
+        if percent in (19, 21):
+            return 'A'  # Standard rate (19% old, 21% new from Aug 2025)
+        elif percent in (9, 11):
+            return 'B'  # Reduced rate (9% old, 11% new from Aug 2025)
+        elif percent == 5:
+            return 'C'  # Reduced rate (unchanged)
+        elif percent == 0:
+            return 'D'  # Exempt (unchanged)
+        else:
+            return 'A'  # Default to standard rate
+
+    def _detect_tva_percent(self, text: str) -> Optional[int]:
+        """Detect TVA percentage from text content."""
+        # Look for common Romanian TVA percentages
+        if '19%' in text or '19 %' in text:
+            return 19
+        elif '21%' in text or '21 %' in text:
+            return 21
+        elif '11%' in text or '11 %' in text:
+            return 11
+        elif '9%' in text or '9 %' in text:
+            return 9
+        elif '5%' in text or '5 %' in text:
+            return 5
+        return None
+
+    def _extract_items_count(self, text: str) -> Optional[int]:
+        """Extract number of items/articles from receipt."""
+        for pattern, _ in self.ITEMS_COUNT_PATTERNS:
+            match = re.search(pattern, text, re.IGNORECASE)
+            if match:
+                try:
+                    count = int(match.group(1))
+                    if 0 < count < 1000:  # Reasonable range
+                        return count
+                except ValueError:
+                    continue
+        return None
+
+    def _extract_address(self, text: str) -> Optional[str]:
+        """Extract vendor address from text."""
+        lines = text.split('\n')
+        address_parts = []
+
+        for line in lines[:15]:  # Check first 15 lines
+            line = line.strip()
+            if not line:
+                continue
+
+            # Check for address patterns
+            line_upper = line.upper()
+
+            # JUD. (county) pattern
+            if re.search(r'\bJUD\.?\s+', line_upper):
+                address_parts.append(line)
+                continue
+
+            # STR. (street) pattern
+            if re.search(r'\bSTR\.?\s+', line_upper):
+                address_parts.append(line)
+                continue
+
+            # MUN./OR./COM. (city/town) pattern
+            if re.search(r'\b(MUN|OR|COM)\.?\s+', line_upper):
+                address_parts.append(line)
+                continue
+
+        if address_parts:
+            # Join and clean address parts
+            address = ', '.join(address_parts)
+            # Clean up
+            address = re.sub(r'\s+', ' ', address).strip()
+            address = re.sub(r',\s*,', ',', address)
+            return address if len(address) >= 5 else None
+
+        return None

data-entry-app/backend/migrations/versions/20251212_140422_add_tva_breakdown_to_receipt.py

@@ -0,0 +1,37 @@
+"""add_tva_breakdown_to_receipt
+
+Revision ID: 1cfb423c6953
+Revises: 001_initial
+Create Date: 2025-12-12 14:04:22.464289+00:00
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import sqlmodel
+
+
+# revision identifiers, used by Alembic.
+revision: str = '1cfb423c6953'
+down_revision: Union[str, None] = '001_initial'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Add TVA-related columns to receipts table
+    with op.batch_alter_table('receipts', schema=None) as batch_op:
+        batch_op.add_column(sa.Column('tva_breakdown', sqlmodel.sql.sqltypes.AutoString(length=1000), nullable=True))
+        batch_op.add_column(sa.Column('tva_total', sa.Numeric(precision=15, scale=2), nullable=True))
+        batch_op.add_column(sa.Column('items_count', sa.Integer(), nullable=True))
+        batch_op.add_column(sa.Column('vendor_address', sqlmodel.sql.sqltypes.AutoString(length=500), nullable=True))
+
+
+def downgrade() -> None:
+    # Remove TVA-related columns from receipts table
+    with op.batch_alter_table('receipts', schema=None) as batch_op:
+        batch_op.drop_column('vendor_address')
+        batch_op.drop_column('items_count')
+        batch_op.drop_column('tva_total')
+        batch_op.drop_column('tva_breakdown')

data-entry-app/frontend/src/components/ocr/OCRPreview.vue

@@ -71,6 +71,37 @@
             <span v-if="data.cui" class="cui-badge">CUI: {{ data.cui }}</span>
           </div>
         </div>
+
+        <!-- TVA Entries (multiple rates) -->
+        <div class="preview-field full-width" v-if="data.tva_entries?.length > 0 || data.tva_total">
+          <label>TVA</label>
+          <div class="tva-breakdown">
+            <div v-for="(entry, idx) in data.tva_entries" :key="idx" class="tva-entry">
+              <span class="tva-code" v-if="entry.code">{{ entry.code }}</span>
+              <span class="tva-percent-badge">{{ entry.percent }}%</span>
+              <span class="tva-amount">{{ formatAmount(entry.amount) }} RON</span>
+            </div>
+            <div v-if="data.tva_total && data.tva_entries?.length > 1" class="tva-total">
+              <strong>Total TVA:</strong> {{ formatAmount(data.tva_total) }} RON
+            </div>
+          </div>
+        </div>
+
+        <!-- Items Count -->
+        <div class="preview-field" v-if="data.items_count">
+          <label>Nr. Articole</label>
+          <div class="field-value">
+            {{ data.items_count }} articole
+          </div>
+        </div>
+
+        <!-- Address -->
+        <div class="preview-field full-width" v-if="data.address">
+          <label>Adresa</label>
+          <div class="field-value address-text">
+            {{ data.address }}
+          </div>
+        </div>
       </div>
 
       <!-- Raw Text Toggle -->
@@ -224,6 +255,50 @@ const formatDate = (dateStr) => {
   color: #475569;
 }
 
+.tva-breakdown {
+  display: flex;
+  flex-direction: column;
+  gap: 0.25rem;
+}
+
+.tva-entry {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+}
+
+.tva-code {
+  font-weight: 600;
+  color: #475569;
+  min-width: 1rem;
+}
+
+.tva-percent-badge {
+  display: inline-block;
+  padding: 0.15rem 0.5rem;
+  background: #dbeafe;
+  border-radius: 4px;
+  font-size: 0.8rem;
+  color: #1e40af;
+  min-width: 2.5rem;
+  text-align: center;
+}
+
+.tva-amount {
+  font-weight: 500;
+}
+
+.tva-total {
+  margin-top: 0.25rem;
+  padding-top: 0.25rem;
+  border-top: 1px dashed #cbd5e1;
+}
+
+.address-text {
+  font-size: 0.9rem;
+  color: #475569;
+}
+
 .raw-text-section {
   margin-top: 1rem;
   padding-top: 1rem;

data-entry-app/frontend/src/views/receipts/ReceiptCreateView.vue

@@ -246,11 +246,59 @@
             <Textarea
               v-model="form.description"
               rows="3"
-              placeholder="Detalii suplimentare..."
+              placeholder="Descriere optionala..."
             />
           </div>
         </div>
 
+        <!-- Detalii Suplimentare (populated from OCR) -->
+        <div v-if="form.tva_breakdown?.length > 0 || form.items_count || form.vendor_address" class="extra-details-section">
+          <h3>
+            <i class="pi pi-list"></i>
+            Detalii Suplimentare (din OCR)
+          </h3>
+
+          <!-- TVA Breakdown -->
+          <div class="form-field form-field-full" v-if="form.tva_breakdown?.length > 0">
+            <label>Defalcare TVA</label>
+            <div class="tva-table">
+              <div v-for="(entry, idx) in form.tva_breakdown" :key="idx" class="tva-row">
+                <span class="tva-label">TVA {{ entry.code }} ({{ entry.percent }}%):</span>
+                <InputNumber
+                  v-model="form.tva_breakdown[idx].amount"
+                  mode="currency"
+                  currency="RON"
+                  locale="ro-RO"
+                  :minFractionDigits="2"
+                  class="tva-input"
+                />
+              </div>
+              <div class="tva-row total" v-if="form.tva_breakdown.length > 0">
+                <span class="tva-label"><strong>Total TVA:</strong></span>
+                <span class="tva-value">{{ formatTvaTotal() }} RON</span>
+              </div>
+            </div>
+          </div>
+
+          <div class="form-grid">
+            <div class="form-field" v-if="form.items_count">
+              <label>Nr. Articole</label>
+              <InputNumber
+                v-model="form.items_count"
+                :min="1"
+                placeholder="Ex: 17"
+              />
+            </div>
+            <div class="form-field" v-if="form.vendor_address">
+              <label>Adresa Furnizor</label>
+              <InputText
+                v-model="form.vendor_address"
+                placeholder="Adresa din bon"
+              />
+            </div>
+          </div>
+        </div>
+
         <Divider />
 
         <!-- Actions -->
@@ -314,6 +362,11 @@ const form = ref({
   receipt_number: '',
   description: '',
   company_id: 1, // Default company for Phase 1
+  // TVA info (multiple entries support)
+  tva_breakdown: [],  // Array of {code, percent, amount}
+  tva_total: null,
+  items_count: null,
+  vendor_address: '',
 })
 
 const selectedFiles = ref([])
@@ -435,6 +488,24 @@ const applyOCRData = (data) => {
     }
   }
 
+  // Apply TVA entries
+  if (data.tva_entries?.length > 0) {
+    form.value.tva_breakdown = data.tva_entries.map(e => ({
+      code: e.code,
+      percent: e.percent,
+      amount: parseFloat(e.amount)
+    }))
+  }
+  if (data.tva_total) {
+    form.value.tva_total = parseFloat(data.tva_total)
+  }
+  if (data.items_count) {
+    form.value.items_count = data.items_count
+  }
+  if (data.address) {
+    form.value.vendor_address = data.address
+  }
+
   // Clear OCR preview
   ocrData.value = null
 
@@ -499,6 +570,12 @@ const formatFileSize = (bytes) => {
   return (bytes / (1024 * 1024)).toFixed(1) + ' MB'
 }
 
+const formatTvaTotal = () => {
+  if (!form.value.tva_breakdown?.length) return '0.00'
+  const total = form.value.tva_breakdown.reduce((sum, e) => sum + (e.amount || 0), 0)
+  return total.toLocaleString('ro-RO', { minimumFractionDigits: 2, maximumFractionDigits: 2 })
+}
+
 const validateForm = () => {
   // Check if we have at least one file (for new receipts)
   if (!isEditMode.value && selectedFiles.value.length === 0) {
@@ -725,4 +802,55 @@ const submitForReview = async () => {
   font-size: 0.85rem;
   color: #64748b;
 }
+
+/* Extra details section (TVA, items, address) */
+.extra-details-section {
+  margin-top: 1.5rem;
+  padding: 1rem;
+  background: #f0f9ff;
+  border: 1px solid #bae6fd;
+  border-radius: 8px;
+}
+
+.extra-details-section h3 {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+  margin-bottom: 1rem;
+  color: #0284c7;
+}
+
+.tva-table {
+  display: flex;
+  flex-direction: column;
+  gap: 0.5rem;
+  margin-bottom: 1rem;
+}
+
+.tva-row {
+  display: flex;
+  align-items: center;
+  gap: 1rem;
+}
+
+.tva-row.total {
+  margin-top: 0.5rem;
+  padding-top: 0.5rem;
+  border-top: 1px dashed #0284c7;
+}
+
+.tva-label {
+  min-width: 150px;
+  font-weight: 500;
+  color: #334155;
+}
+
+.tva-input {
+  max-width: 150px;
+}
+
+.tva-value {
+  font-weight: 600;
+  color: #0284c7;
+}
 </style>

data-entry-app/frontend/src/views/receipts/ReceiptDetailView.vue

@@ -112,6 +112,43 @@
             </div>
           </div>
 
+          <!-- Detalii Suplimentare (TVA, items, address from OCR) -->
+          <template v-if="hasTvaData || receipt.items_count || receipt.vendor_address">
+            <Divider />
+
+            <h4 style="margin-bottom: 0.75rem; color: #0284c7;">
+              <i class="pi pi-list"></i>
+              Detalii Suplimentare
+            </h4>
+
+            <div class="detail-list">
+              <!-- TVA Breakdown -->
+              <div v-if="parsedTvaBreakdown?.length > 0" class="detail-item tva-detail">
+                <span class="label">TVA</span>
+                <div class="tva-breakdown-display">
+                  <div v-for="(entry, idx) in parsedTvaBreakdown" :key="idx" class="tva-line">
+                    <span class="tva-code" v-if="entry.code">{{ entry.code }}:</span>
+                    <span class="tva-percent">{{ entry.percent }}%</span>
+                    <span class="tva-amount">= {{ formatAmount(entry.amount) }}</span>
+                  </div>
+                  <div v-if="receipt.tva_total && parsedTvaBreakdown.length > 1" class="tva-total-line">
+                    <strong>Total TVA: {{ formatAmount(receipt.tva_total) }}</strong>
+                  </div>
+                </div>
+              </div>
+
+              <div class="detail-item" v-if="receipt.items_count">
+                <span class="label">Nr. Articole</span>
+                <span class="value">{{ receipt.items_count }} articole</span>
+              </div>
+
+              <div class="detail-item" v-if="receipt.vendor_address">
+                <span class="label">Adresa Furnizor</span>
+                <span class="value">{{ receipt.vendor_address }}</span>
+              </div>
+            </div>
+          </template>
+
           <Divider />
 
           <div class="detail-list">
@@ -283,6 +320,22 @@ const isBalanced = computed(() => {
   return Math.abs(totalDebit.value - totalCredit.value) < 0.01
 })
 
+const parsedTvaBreakdown = computed(() => {
+  if (!receipt.value?.tva_breakdown) return []
+  try {
+    // Handle both string (JSON) and array formats
+    return typeof receipt.value.tva_breakdown === 'string'
+      ? JSON.parse(receipt.value.tva_breakdown)
+      : receipt.value.tva_breakdown
+  } catch {
+    return []
+  }
+})
+
+const hasTvaData = computed(() => {
+  return parsedTvaBreakdown.value?.length > 0 || receipt.value?.tva_total
+})
+
 onMounted(async () => {
   await loadReceipt()
 })
@@ -521,4 +574,56 @@ const resubmitReceipt = async () => {
   border-radius: 8px;
   color: #f57c00;
 }
+
+/* TVA Breakdown Display */
+.detail-item.tva-detail {
+  flex-direction: column;
+  align-items: flex-start;
+  gap: 0.5rem;
+}
+
+.tva-breakdown-display {
+  display: flex;
+  flex-direction: column;
+  gap: 0.25rem;
+  padding: 0.5rem;
+  background: #f0f9ff;
+  border-radius: 6px;
+  width: 100%;
+}
+
+.tva-line {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+}
+
+.tva-code {
+  font-weight: 600;
+  color: #475569;
+  min-width: 1.5rem;
+}
+
+.tva-percent {
+  display: inline-block;
+  padding: 0.1rem 0.4rem;
+  background: #dbeafe;
+  border-radius: 4px;
+  font-size: 0.85rem;
+  color: #1e40af;
+  min-width: 2.5rem;
+  text-align: center;
+}
+
+.tva-amount {
+  font-weight: 500;
+  color: #334155;
+}
+
+.tva-total-line {
+  margin-top: 0.25rem;
+  padding-top: 0.25rem;
+  border-top: 1px dashed #0284c7;
+  color: #0284c7;
+}
 </style>