KK KTP arsip

.gemini/settings.json

@@ -0,0 +1,8 @@
+{
+  "mcpServers": {
+    "context7": {
+      "command": "npx",
+      "args": ["-y", "@upstash/context7-mcp@latest"]
+    }
+  }
+}

database.py

@@ -0,0 +1,39 @@
+"""
+Database Configuration for OCR Application
+Using Flask-SQLAlchemy with MySQL (PyMySQL driver)
+"""
+
+import os
+from flask_sqlalchemy import SQLAlchemy
+
+db = SQLAlchemy()
+
+# Database configuration
+DB_CONFIG = {
+    'host': os.environ.get('DB_HOST', 'localhost'),
+    'port': os.environ.get('DB_PORT', '3306'),
+    'database': os.environ.get('DB_NAME', 'ocr_db'),
+    'user': os.environ.get('DB_USER', 'ocr_user'),
+    'password': os.environ.get('DB_PASSWORD', 'ocr_password123')
+}
+
+def get_database_uri():
+    """Generate SQLAlchemy database URI"""
+    return f"mysql+pymysql://{DB_CONFIG['user']}:{DB_CONFIG['password']}@{DB_CONFIG['host']}:{DB_CONFIG['port']}/{DB_CONFIG['database']}?charset=utf8mb4"
+
+def init_db(app):
+    """Initialize database with Flask app"""
+    app.config['SQLALCHEMY_DATABASE_URI'] = get_database_uri()
+    app.config['SQLALCHEMY_TRACK_MODIFICATIONS'] = False
+    app.config['SQLALCHEMY_ENGINE_OPTIONS'] = {
+        'pool_recycle': 3600,
+        'pool_pre_ping': True
+    }
+    
+    db.init_app(app)
+    
+    with app.app_context():
+        db.create_all()
+        print(f"✓ Database connected: {DB_CONFIG['database']}@{DB_CONFIG['host']}")
+    
+    return db

docker-compose.yml

@@ -0,0 +1,21 @@
+version: '3.8'
+
+services:
+  mysql:
+    image: mysql:8.0
+    container_name: mysql-server
+    restart: unless-stopped
+    environment:
+      MYSQL_ROOT_PASSWORD: root123
+      MYSQL_DATABASE: ocr_db
+      MYSQL_USER: ocr_user
+      MYSQL_PASSWORD: ocr_password123
+    ports:
+      - "3306:3306"
+    volumes:
+      - mysql_data:/var/lib/mysql
+    command: --default-authentication-plugin=mysql_native_password
+
+volumes:
+  mysql_data:
+    driver: local

image_processor.py

@@ -0,0 +1,174 @@
+"""
+KTP Image Processor - Enhanced Version
+Crop, resize, dan enhanced preprocessing untuk OCR yang lebih akurat
+
+Standar e-KTP: 85.6mm x 53.98mm = 1011x638 px @300dpi
+
+Improvements based on Context7 documentation:
+- Pillow ImageEnhance for contrast/sharpness
+- OpenCV CLAHE for adaptive histogram equalization
+- Denoising for cleaner text detection
+"""
+
+import cv2
+import numpy as np
+import os
+from PIL import Image, ImageEnhance, ImageFilter
+
+KTP_WIDTH = 1011
+KTP_HEIGHT = 638
+
+
+def enhance_image_pil(image_path: str, output_path: str = None) -> str:
+    """
+    Enhance image using Pillow (from Context7 docs)
+    - Contrast enhancement
+    - Sharpness enhancement  
+    - Detail filter for text clarity
+    
+    Args:
+        image_path: Path to input image
+        output_path: Optional path to save enhanced image
+        
+    Returns:
+        Path to enhanced image
+    """
+    try:
+        img = Image.open(image_path)
+        
+        # Contrast enhancement (factor 1.3 from Context7)
+        contrast = ImageEnhance.Contrast(img)
+        img = contrast.enhance(1.3)
+        
+        # Sharpness enhancement
+        sharpness = ImageEnhance.Sharpness(img)
+        img = sharpness.enhance(1.2)
+        
+        # Apply detail filter for text clarity
+        img = img.filter(ImageFilter.DETAIL)
+        
+        # Save
+        if output_path is None:
+            base, ext = os.path.splitext(image_path)
+            output_path = f"{base}_enhanced.jpg"
+        
+        img.save(output_path, quality=95)
+        print(f"  [ENHANCE] Pillow enhanced: {output_path}")
+        
+        return output_path
+        
+    except Exception as e:
+        print(f"  [ENHANCE] Pillow error: {e}")
+        return image_path  # Return original if enhancement fails
+
+
+def enhance_image_cv(image: np.ndarray) -> np.ndarray:
+    """
+    Enhance image using OpenCV (from Context7 docs)
+    - CLAHE for adaptive histogram equalization
+    - Denoising
+    - Sharpening using Laplacian kernel
+    
+    Args:
+        image: OpenCV image (BGR)
+        
+    Returns:
+        Enhanced image (BGR)
+    """
+    try:
+        # Convert to grayscale for processing
+        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+        
+        # Denoise (from Context7)
+        denoised = cv2.fastNlMeansDenoising(gray, None, 10, 7, 21)
+        
+        # Enhanced CLAHE for documents
+        clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8, 8))
+        enhanced = clahe.apply(denoised)
+        
+        # Sharpen using kernel (from Context7)
+        kernel = np.array([[0, -1, 0], [-1, 5, -1], [0, -1, 0]], dtype=np.float32)
+        sharpened = cv2.filter2D(enhanced, -1, kernel)
+        
+        # Convert back to BGR
+        return cv2.cvtColor(sharpened, cv2.COLOR_GRAY2BGR)
+        
+    except Exception as e:
+        print(f"  [ENHANCE] OpenCV error: {e}")
+        return image  # Return original if enhancement fails
+
+
+def crop_by_ocr_bounds(image, ocr_results, padding=0.03):
+    """Crop image based on OCR bounding boxes"""
+    if not ocr_results:
+        return image
+    
+    h, w = image.shape[:2]
+    all_x = []
+    all_y = []
+    
+    for r in ocr_results:
+        box = r.get('box', [])
+        if len(box) >= 4:
+            try:
+                for point in box:
+                    if isinstance(point, (list, tuple)) and len(point) >= 2:
+                        all_x.append(float(point[0]))
+                        all_y.append(float(point[1]))
+            except:
+                continue
+    
+    if not all_x or not all_y:
+        return image
+    
+    x1 = int(max(0, min(all_x) - w * padding))
+    y1 = int(max(0, min(all_y) - h * padding))
+    x2 = int(min(w, max(all_x) + w * padding))
+    y2 = int(min(h, max(all_y) + h * padding))
+    
+    return image[y1:y2, x1:x2]
+
+
+def normalize_ktp_image(image_path, output_path=None, ocr_results=None):
+    """
+    Normalisasi gambar KTP:
+    1. Crop berdasarkan OCR bounds
+    2. Ensure landscape
+    3. Resize ke ukuran standar
+    """
+    try:
+        image = cv2.imread(image_path)
+        if image is None:
+            return None, False, "Gagal membaca gambar"
+        
+        h, w = image.shape[:2]
+        print(f"  [IMAGE] Original: {w}x{h}")
+        
+        # Crop
+        if ocr_results:
+            image = crop_by_ocr_bounds(image, ocr_results)
+            h, w = image.shape[:2]
+            print(f"  [IMAGE] Cropped: {w}x{h}")
+        
+        # Landscape
+        if h > w:
+            image = cv2.rotate(image, cv2.ROTATE_90_CLOCKWISE)
+        
+        # Resize
+        resized = cv2.resize(image, (KTP_WIDTH, KTP_HEIGHT),
+                            interpolation=cv2.INTER_LANCZOS4)
+        
+        # Save
+        if output_path is None:
+            base, ext = os.path.splitext(image_path)
+            output_path = f"{base}_normalized.jpg"
+        
+        cv2.imwrite(output_path, resized, [cv2.IMWRITE_JPEG_QUALITY, 95])
+        print(f"  [IMAGE] Saved: {output_path}")
+        
+        return output_path, True, f"Normalized to {KTP_WIDTH}x{KTP_HEIGHT}"
+        
+    except Exception as e:
+        import traceback
+        traceback.print_exc()
+        return None, False, f"Error: {str(e)}"

ktp_extractor.py

@@ -2,17 +2,42 @@
 KTP Field Extractor
 Ekstraksi data terstruktur dari hasil OCR KTP Indonesia
 Mendukung berbagai format output OCR (full-width colon, standard colon, tanpa colon)
+
+OPTIMIZED: Pre-compiled regex patterns for better performance
 """
 
 import re
 from typing import Dict, Optional, List
+import difflib
 
+# Debug mode - set to False for production
+DEBUG_MODE = False
 
 class KTPExtractor:
     """Ekstrak field dari hasil OCR KTP"""
     
-    # Pattern colon yang berbeda-beda (standard, full-width, dll)
-    COLON_PATTERN = r'[:\：]'
+    # Pre-compiled regex patterns (optimization)
+    COLON_PATTERN = re.compile(r'[：:]')
+    NIK_PATTERN = re.compile(r'\b(\d{16})\b')
+    DATE_PATTERN = re.compile(r'(\d{2}[-/]\d{2}[-/]\d{4})')
+    RT_RW_PATTERN = re.compile(r'(\d{3})\s*/\s*(\d{3})')
+    GOL_DARAH_PATTERN = re.compile(r'([ABO]{1,2}[+\-]?)', re.IGNORECASE)
+    PROVINSI_SPLIT_PATTERN = re.compile(r'(?i)provinsi\s*')
+    KABUPATEN_SPLIT_PATTERN = re.compile(r'(?i)\s*(kabupaten|kota)\s*')
+    TTL_PATTERN = re.compile(r'(?i)tempat[/\s]*tgl[/\s]*lahir|tempat[/\s]*lahir|lahir')
+    
+    # Pattern colon string (for backward compatibility)
+    COLON_PATTERN_STR = r'[：:]'
+    
+    # Daftar Provinsi Indonesia (38 Provinsi)
+    PROVINSI_LIST = [
+        "ACEH", "SUMATERA UTARA", "SUMATERA BARAT", "RIAU", "JAMBI", "SUMATERA SELATAN", "BENGKULU", "LAMPUNG", 
+        "KEPULAUAN BANGKA BELITUNG", "KEPULAUAN RIAU", "DKI JAKARTA", "JAWA BARAT", "JAWA TENGAH", "DI YOGYAKARTA", 
+        "JAWA TIMUR", "BANTEN", "BALI", "NUSA TENGGARA BARAT", "NUSA TENGGARA TIMUR", "KALIMANTAN BARAT", 
+        "KALIMANTAN TENGAH", "KALIMANTAN SELATAN", "KALIMANTAN TIMUR", "KALIMANTAN UTARA", "SULAWESI UTARA", 
+        "SULAWESI TENGAH", "SULAWESI SELATAN", "SULAWESI TENGGARA", "GORONTALO", "SULAWESI BARAT", "MALUKU", 
+        "MALUKU UTARA", "PAPUA BARAT", "PAPUA", "PAPUA SELATAN", "PAPUA TENGAH", "PAPUA PEGUNUNGAN", "PAPUA BARAT DAYA"
+    ]
     
     # Keywords untuk jenis kelamin
     MALE_KEYWORDS = ['laki', 'pria', 'male']
@@ -26,6 +51,99 @@ class KTPExtractor:
                       'buruh', 'petani', 'nelayan', 'karyawan', 'ibu rumah tangga', 
                       'tidak bekerja', 'lainnya', 'mengurus rumah tangga']
     
+    # Status Perkawinan yang valid
+    STATUS_PERKAWINAN_LIST = ['BELUM KAWIN', 'KAWIN', 'CERAI HIDUP', 'CERAI MATI']
+    
+    # Field Labels untuk fuzzy matching (mengatasi typo OCR seperti "Aamat" -> "ALAMAT")
+    FIELD_LABELS = {
+        'nama': ['NAMA'],
+        'alamat': ['ALAMAT'],
+        'agama': ['AGAMA'],
+        'pekerjaan': ['PEKERJAAN'],
+        'kewarganegaraan': ['KEWARGANEGARAAN', 'WARGANEGARA'],
+        'tempat_lahir': ['TEMPAT', 'LAHIR', 'TEMPAT/TGL LAHIR'],
+        'jenis_kelamin': ['JENIS KELAMIN', 'JENIS', 'KELAMIN'],
+        'gol_darah': ['GOL. DARAH', 'GOL DARAH', 'GOLONGAN DARAH'],
+        'kel_desa': ['KEL/DESA', 'KELURAHAN', 'DESA'],
+        'kecamatan': ['KECAMATAN', 'KEC'],
+        'status_perkawinan': ['STATUS PERKAWINAN', 'PERKAWINAN'],
+        'berlaku_hingga': ['BERLAKU HINGGA', 'BERLAKU'],
+        'rt_rw': ['RT/RW', 'RT', 'RW'],
+    }
+    
+    # ============================================
+    # Sistem Penamaan Hindu Bali
+    # ============================================
+    # Struktur: [Prefix Gender] + [Gelar Kasta] + [Penanda Gender] + [Urutan Lahir] + [Nama Pribadi]
+    
+    # Prefix penanda gender (harus di awal nama)
+    BALI_GENDER_PREFIX = {
+        'NI': 'PEREMPUAN',      # Prefix untuk perempuan
+        'I': 'LAKI-LAKI',       # Prefix untuk laki-laki
+    }
+    
+    # Gelar Kasta (setelah prefix gender)
+    BALI_KASTA = {
+        'IDA': 'BRAHMANA',
+        'GUSTI': 'KSATRIA',
+        'ANAK AGUNG': 'KSATRIA',
+        'COKORDA': 'KSATRIA',
+        'DEWA': 'KSATRIA',
+        'DESAK': 'KSATRIA',
+        'AGUNG': 'KSATRIA',
+        'NGAKAN': 'WAISYA',
+        'SANG': 'WAISYA',
+        'SI': 'WAISYA',
+    }
+    
+    # Penanda gender tambahan (setelah kasta)
+    BALI_GENDER_MARKER = {
+        'AYU': 'PEREMPUAN',
+        'ISTRI': 'PEREMPUAN',
+        'LUH': 'PEREMPUAN',
+        'BAGUS': 'LAKI-LAKI',
+        'GEDE': 'LAKI-LAKI',
+        'AGUS': 'LAKI-LAKI',
+        'ALIT': 'LAKI-LAKI',    # Kecil/muda (untuk laki-laki)
+    }
+    
+    # Urutan kelahiran (bersiklus setiap 4 anak)
+    BALI_BIRTH_ORDER = {
+        'PUTU': 1, 'WAYAN': 1, 'GEDE': 1, 'ILUH': 1,
+        'MADE': 2, 'KADEK': 2, 'NENGAH': 2,
+        'NYOMAN': 3, 'KOMANG': 3,
+        'KETUT': 4,
+        'BALIK': 5,  # Untuk anak ke-5+ (siklus ulang)
+    }
+    
+    # Soroh/Klan Bali (identifikasi garis keturunan)
+    BALI_SOROH = {
+        'PASEK': 'SOROH',       # Klan mayoritas (~60% Hindu Bali)
+        'PANDE': 'SOROH',       # Klan pandai besi/metalurgi
+        'ARYA': 'SOROH',        # Klan Arya
+        'BENDESA': 'SOROH',     # Pemimpin adat
+        'TANGKAS': 'SOROH',     # Klan Tangkas
+        'CELAGI': 'SOROH',      # Klan Celagi
+        'SENGGUHU': 'SOROH',    # Klan Sengguhu
+        'KUBAYAN': 'SOROH',     # Klan Kubayan
+        'BANDESA': 'SOROH',     # Varian Bendesa
+    }
+    
+    # Gabungkan semua komponen untuk deteksi (urut dari panjang ke pendek)
+    BALI_NAME_COMPONENTS = [
+        # Prefix gender
+        'NI', 'I',
+        # Kasta (prioritas: yang lebih panjang dulu)
+        'ANAK AGUNG', 'COKORDA', 'NGAKAN', 
+        'IDA', 'GUSTI', 'DEWA', 'DESAK', 'AGUNG', 'SANG', 'SI',
+        # Soroh/Klan
+        'PASEK', 'PANDE', 'ARYA', 'BENDESA', 'BANDESA', 'TANGKAS', 'CELAGI', 'SENGGUHU', 'KUBAYAN',
+        # Gender marker
+        'AYU', 'ISTRI', 'LUH', 'BAGUS', 'GEDE', 'AGUS', 'ALIT',
+        # Urutan lahir
+        'WAYAN', 'PUTU', 'ILUH', 'MADE', 'KADEK', 'NENGAH', 'NYOMAN', 'KOMANG', 'KETUT', 'BALIK',
+    ]
+    
     # KTP Zone Template (normalized coordinates: x_min, y_min, x_max, y_max)
     # Based on standard KTP layout
     ZONES = {
@@ -74,6 +192,211 @@ class KTPExtractor:
         if len(parts) > 1:
             return parts[1].strip()
         return text.strip()
+
+    def _find_best_match(self, text: str, candidates: List[str], cutoff: float = 0.6) -> Optional[str]:
+        """Find best fuzzy match from candidates"""
+        matches = difflib.get_close_matches(text, candidates, n=1, cutoff=cutoff)
+        return matches[0] if matches else None
+    
+    def _is_label_match(self, text: str, field_name: str, cutoff: float = 0.7) -> bool:
+        """
+        Fuzzy match untuk label field - mengatasi typo OCR seperti "Aamat" -> "ALAMAT"
+        Returns True jika text cocok dengan salah satu label untuk field tersebut
+        """
+        if not text or not text.strip():
+            return False
+            
+        if field_name not in self.FIELD_LABELS:
+            return field_name.lower() in text.lower()
+        
+        text_upper = text.upper().strip()
+        
+        # Coba exact match dulu (lebih cepat)
+        for label in self.FIELD_LABELS[field_name]:
+            if label in text_upper:
+                return True
+        
+        # Fuzzy match jika tidak ada exact match
+        # Ekstrak kata pertama dari text (biasanya label ada di awal)
+        parts = text_upper.split(':')[0].split()
+        if not parts:
+            return False
+        first_word = parts[0]
+        
+        for label in self.FIELD_LABELS[field_name]:
+            label_parts = label.split()
+            if not label_parts:
+                continue
+            # Bandingkan dengan kata pertama
+            ratio = difflib.SequenceMatcher(None, first_word, label_parts[0]).ratio()
+            if ratio >= cutoff:
+                print(f"  [FUZZY LABEL] '{first_word}' matched '{label}' (ratio={ratio:.2f})")
+                return True
+        
+        return False
+    
+    def _parse_balinese_name(self, name: str) -> str:
+        """
+        Parse nama Bali yang digabung OCR dan tambahkan spasi yang tepat.
+        Contoh: "NIGUSTIAYUNYOMANSUWETRI" -> "NI GUSTI AYU NYOMAN SUWETRI"
+        
+        Struktur nama Bali:
+        [Prefix Gender] + [Gelar Kasta] + [Penanda Gender] + [Urutan Lahir] + [Nama Pribadi]
+        
+        PENTING: Hanya proses jika nama benar-benar mengandung komponen Bali!
+        """
+        if not name:
+            return name
+        
+        name_upper = name.upper().strip()
+        
+        # Jika sudah ada spasi dengan jumlah wajar, kembalikan apa adanya
+        if name_upper.count(' ') >= 2:
+            return name_upper
+        
+        # Cek apakah nama mengandung komponen Bali
+        # Nama harus dimulai dengan NI, I GUSTI, IDA, atau komponen urutan lahir Bali
+        name_clean = name_upper.replace(' ', '')
+        
+        is_balinese_name = False
+        # Cek prefix khas Bali
+        if name_clean.startswith('NI') and len(name_clean) > 3:
+            # NI harus diikuti komponen Bali lain (GUSTI, LUH, WAYAN, dll)
+            after_ni = name_clean[2:]
+            for comp in ['GUSTI', 'LUH', 'WAYAN', 'MADE', 'NYOMAN', 'KETUT', 'PUTU', 'KADEK', 'KOMANG', 'PASEK', 'PANDE']:
+                if after_ni.startswith(comp):
+                    is_balinese_name = True
+                    break
+        elif name_clean.startswith('IGUSTI') or name_clean.startswith('IDABAGUS') or name_clean.startswith('IDAAYU'):
+            is_balinese_name = True
+        elif any(name_clean.startswith(p) for p in ['GUSTI', 'WAYAN', 'PUTU', 'MADE', 'KADEK', 'NYOMAN', 'KOMANG', 'KETUT']):
+            is_balinese_name = True
+        
+        if not is_balinese_name:
+            # Bukan nama Bali, kembalikan dengan pemisahan spasi standar
+            # Jika ada 1 spasi, kembalikan apa adanya
+            if ' ' in name_upper:
+                return name_upper
+            # Jika tidak ada spasi sama sekali, kembalikan apa adanya (mungkin memang 1 kata)
+            return name_upper
+        
+        # Urutan komponen yang akan dicari (dari yang terpanjang ke terpendek untuk akurasi)
+        components_ordered = sorted(self.BALI_NAME_COMPONENTS, key=len, reverse=True)
+        
+        result_parts = []
+        remaining = name_clean
+        
+        # Parse prefix gender (NI atau I di awal)
+        if remaining.startswith('NI'):
+            result_parts.append('NI')
+            remaining = remaining[2:]
+        elif remaining.startswith('I') and len(remaining) > 1:
+            # Pastikan bukan bagian dari kata lain
+            next_char = remaining[1] if len(remaining) > 1 else ''
+            # Cek apakah karakter setelah I adalah konsonan (bukan vokal)
+            if next_char not in 'AIUEO':
+                result_parts.append('I')
+                remaining = remaining[1:]
+        
+        # Parse komponen-komponen lainnya
+        found = True
+        max_iterations = 10  # Prevent infinite loop
+        iteration = 0
+        
+        while remaining and found and iteration < max_iterations:
+            found = False
+            iteration += 1
+            
+            for component in components_ordered:
+                if remaining.startswith(component):
+                    # Skip jika komponen sudah ada di result (kecuali nama pribadi)
+                    if component not in result_parts or component not in self.BALI_NAME_COMPONENTS:
+                        result_parts.append(component)
+                        remaining = remaining[len(component):]
+                        found = True
+                        break
+        
+        # Sisa adalah nama pribadi
+        if remaining:
+            result_parts.append(remaining)
+        
+        parsed_name = ' '.join(result_parts)
+        
+        # Log jika ada perubahan
+        if parsed_name != name_upper:
+            print(f"  [BALI NAME] '{name_upper}' -> '{parsed_name}'")
+        
+        return parsed_name
+        
+    def _search_best_match_in_text(self, text: str, candidates: List[str], prefix: str = "") -> tuple:
+        """
+        Search if any candidate is present in text using multiple strategies:
+        1. Exact substring
+        2. Prefix + Candidate (Fuzzy) - e.g. "PROVINSI BALI"
+        3. Candidate Only (Fuzzy) - e.g. "BALI" (if prefix is missing/damaged)
+        Returns (best_candidate, confidence_score)
+        """
+        text_upper = text.upper()
+        best_match = None
+        best_ratio = 0.0
+        
+        # Strategy 1: Exact substring match (fastest & most reliable)
+        for candidate in candidates:
+            if candidate in text_upper:
+                if len(candidate) > len(best_match or ""):
+                    best_match = candidate
+                    best_ratio = 1.0
+        
+        if best_ratio == 1.0:
+            return best_match, best_ratio
+            
+        # Strategy 2: Prefix Construction & Fuzzy Match
+        prefix_upper = prefix.upper() if prefix else ""
+        
+        # DEBUG: Print checking (controlled by DEBUG_MODE)
+        if DEBUG_MODE:
+            print(f"DEBUG Check Text: '{text_upper}' with Prefix: '{prefix_upper}'")
+        
+        for candidate in candidates:
+            # 2a. Compare with Prefix + Space (e.g. "PROVINSI BALI")
+            if prefix:
+                target_spaced = f"{prefix_upper} {candidate}"
+                s_spaced = difflib.SequenceMatcher(None, target_spaced, text_upper)
+                ratio_spaced = s_spaced.ratio()
+                
+                # print(f"  -> Compare '{target_spaced}' vs '{text_upper}' = {ratio_spaced:.2f}")
+                
+                if ratio_spaced > best_ratio and ratio_spaced > 0.5:
+                    best_ratio = ratio_spaced
+                    best_match = candidate
+                    
+                # 2b. Compare with Prefix NO SPACE (e.g. "PROVINSIBALI")
+                # This handles "PROVNSIBALI" perfectly
+                target_merged = f"{prefix_upper}{candidate}"
+                s_merged = difflib.SequenceMatcher(None, target_merged, text_upper)
+                ratio_merged = s_merged.ratio()
+                
+                if DEBUG_MODE:
+                    print(f"  -> Compare Merged '{target_merged}' vs '{text_upper}' = {ratio_merged:.2f}")
+                
+                if ratio_merged > best_ratio and ratio_merged > 0.5:
+                    best_ratio = ratio_merged
+                    best_match = candidate
+
+            # 2c. Compare Candidate ONLY (e.g. "BALI")
+            if len(candidate) > 3:
+                 s_raw = difflib.SequenceMatcher(None, candidate, text_upper)
+                 ratio_raw = s_raw.ratio()
+                 
+                 # print(f"  -> Compare Raw '{candidate}' vs '{text_upper}' = {ratio_raw:.2f}")
+                 
+                 if ratio_raw > best_ratio and ratio_raw > 0.6:
+                     best_ratio = ratio_raw
+                     best_match = candidate
+        
+        if DEBUG_MODE:
+            print(f"DEBUG Best Match: {best_match} ({best_ratio:.2f})")
+        return best_match, best_ratio
     
     def _detect_image_size(self, ocr_results: List[Dict]) -> tuple:
         """Detect image dimensions from bounding boxes"""
@@ -93,10 +416,62 @@ class KTPExtractor:
         
         # PROVINSI from header
         if 'header_provinsi' in zone_texts:
+            print(f"DEBUG Zone Provinsi Content: {zone_texts['header_provinsi']}")
             for text in zone_texts['header_provinsi']:
-                if 'provinsi' in text.lower():
-                    val = re.sub(r'(?i)provinsi\s*', '', text).strip()
-                    if val:
+                text_clean = text.strip()
+                # Use prefix strategy: "PROVINSI " + result vs text
+                match, score = self._search_best_match_in_text(text_clean, self.PROVINSI_LIST, prefix="PROVINSI")
+                
+                # LOWER THRESHOLD to 0.5 because "PROVINSI BALI" vs "PROVNSIBALI" is roughly 0.5-0.6 range
+                if match and score > 0.5:  
+                    result['provinsi'] = match
+                    
+                    # Remove the found province (and label) from text to see what's left
+                    # If we matched "PROVINSI JAWA TIMUR", the text might be "PROVNSIJAWATMRKABUPATENSUMENEP"
+                    # It's hard to cleanly remove "PROVISI JAWA TIMUR" if it was fuzzy matched.
+                    
+                    # BUT, we can try to find "KABUPATEN" or "KOTA" in the original text
+                    # independent of the province match
+                    if 'kabupaten' in text_clean.lower() or 'kota' in text_clean.lower():
+                        parts = re.split(r'(?i)\s*(kabupaten|kota)', text_clean)
+                        if len(parts) > 1:
+                            kab_part = "".join(parts[1:]).strip()
+                            kab_val = re.sub(r'^(?i)(kabupaten|kota)\s*', '', kab_part).strip()
+                            if kab_val and result['kabupaten_kota'] is None:
+                                prefix = "KABUPATEN" if "kabupaten" in text_clean.lower() else "KOTA"
+                                result['kabupaten_kota'] = f"{prefix} {kab_val.upper()}"
+                    break
+                
+                # Fallback to keyword splitting (Legacy/Blurry fallback)
+                text_lower = text.lower()
+                val = text
+                
+                # If keyword exists, strip it
+                if 'provinsi' in text_lower:
+                    split_prov = re.split(r'(?i)provinsi\s*', text, 1)
+                    if len(split_prov) > 1:
+                        val = split_prov[1].strip()
+                    else:
+                        val = ""
+                
+                # Check for merged text
+                if 'kabupaten' in text_lower or 'kota' in text_lower:
+                    parts = re.split(r'(?i)\s*(kabupaten|kota)', val)
+                    val = parts[0].strip()
+                    
+                    if len(parts) > 1:
+                        kab_part = "".join(parts[1:]).strip()
+                        kab_val = re.sub(r'^(?i)(kabupaten|kota)\s*', '', kab_part).strip()
+                        if kab_val and result['kabupaten_kota'] is None:
+                            prefix = "KABUPATEN" if "kabupaten" in text_lower else "KOTA"
+                            result['kabupaten_kota'] = f"{prefix} {kab_val.upper()}"
+
+                if val and len(val) > 2:
+                    # Try fuzzy match again on the cleaned value
+                    best_match = self._find_best_match(val.upper(), self.PROVINSI_LIST, cutoff=0.6)
+                    if best_match:
+                        result['provinsi'] = best_match
+                    else:
                         result['provinsi'] = val.upper()
                     break
         
@@ -104,13 +479,32 @@ class KTPExtractor:
         if 'header_kabupaten' in zone_texts:
             for text in zone_texts['header_kabupaten']:
                 text_lower = text.lower()
+                val = text
+                
+                # Check keyword
                 if 'kabupaten' in text_lower or 'kota' in text_lower:
-                    val = re.sub(r'(?i)(kabupaten|kota)\s*', '', text).strip()
-                    if val:
-                        result['kabupaten_kota'] = val.upper()
+                    split_kab = re.split(r'(?i)\s*(kabupaten|kota)\s*', text, 1)
+                    if len(split_kab) > 1:
+                         val = split_kab[-1].strip()
                     else:
-                        result['kabupaten_kota'] = text.upper()
-                    break
+                         val = ""
+                
+                # If no keyword, but it's in the kabupaten zone, assume it's data
+                if val:
+                     # Re-add prefix standard if we separated it or if it was missing
+                     # Heuristic: if validation suggests it's a known regency, we are good.
+                     # For now, standardize format.
+                     if result['kabupaten_kota'] is None:
+                         prefix = "KABUPATEN" if "kabupaten" in text_lower else "KOTA"
+                         # If no keyword found, default to KABUPATEN? Or better check Wilayah?
+                         # Let's default to detected keyword or KABUPATEN
+                         if "kota" in text_lower: 
+                             prefix = "KOTA" 
+                         else: 
+                             prefix = "KABUPATEN"
+                             
+                         result['kabupaten_kota'] = f"{prefix} {val.upper()}"
+                     break
         
         # NAMA from nama zone (skip label line)
         if 'nama' in zone_texts:
@@ -161,6 +555,89 @@ class KTPExtractor:
                         result['alamat'] = val.upper()
                         break
         
+        # RT/RW
+        if 'rt_rw' in zone_texts:
+            for text in zone_texts['rt_rw']:
+                rt_rw_match = re.search(r'(\d{3})\s*/\s*(\d{3})', text)
+                if rt_rw_match:
+                    result['rt_rw'] = f"{rt_rw_match.group(1)}/{rt_rw_match.group(2)}"
+                    break
+                    
+        # KEL/DESA
+        if 'kel_desa' in zone_texts:
+            for text in zone_texts['kel_desa']:
+                if 'kel' in text.lower() or 'desa' in text.lower():
+                    val = self._extract_value_from_text(text)
+                    if val and 'kel' not in val.lower():
+                        result['kel_desa'] = val.upper()
+                        break
+                elif result['kel_desa'] is None:
+                    # Fallback context: simple text
+                     result['kel_desa'] = text.upper()
+
+        # KECAMATAN
+        if 'kecamatan' in zone_texts:
+            for text in zone_texts['kecamatan']:
+                if 'kec' in text.lower():
+                    val = self._extract_value_from_text(text)
+                    if val and 'kec' not in val.lower():
+                        result['kecamatan'] = val.upper()
+                        break
+                elif result['kecamatan'] is None:
+                     result['kecamatan'] = text.upper()
+
+        # AGAMA
+        if 'agama' in zone_texts:
+            for text in zone_texts['agama']:
+                val = text.upper()
+                if 'agama' in text.lower():
+                    val = self._extract_value_from_text(text).upper()
+                
+                # Verify against valid list
+                for agama in self.AGAMA_LIST:
+                    if agama.upper() in val:
+                        result['agama'] = agama.upper()
+                        break
+                if result['agama']: break
+
+        # STATUS PERKAWINAN
+        if 'status' in zone_texts:
+            for text in zone_texts['status']:
+                val = text.upper()
+                # Normalize common OCR errors (e.g. BELUMKAWIN)
+                val = val.replace("BELUMKAWIN", "BELUM KAWIN")
+                
+                # Check against official list
+                found_status = False
+                for status in self.STATUS_PERKAWINAN_LIST:
+                    if status in val:
+                        result['status_perkawinan'] = status
+                        found_status = True
+                        break
+                if found_status: break
+
+        # PEKERJAAN
+        if 'pekerjaan' in zone_texts:
+            for text in zone_texts['pekerjaan']:
+                val = text.upper()
+                if 'pekerjaan' in text.lower():
+                    val = self._extract_value_from_text(text).upper()
+                
+                # Check against list or take value
+                if len(val) > 3 and 'pekerjaan' not in val.lower():
+                    result['pekerjaan'] = val
+                    break
+
+        # WNI
+        if 'wni' in zone_texts:
+             for text in zone_texts['wni']:
+                 if 'wni' in text.lower():
+                     result['kewarganegaraan'] = 'WNI'
+                     break
+                 elif 'wna' in text.lower():
+                     result['kewarganegaraan'] = 'WNA'
+                     break
+        
         # PENERBITAN area (tempat & tanggal dalam satu zona)
         if 'penerbitan' in zone_texts:
             for text in zone_texts['penerbitan']:
@@ -194,7 +671,7 @@ class KTPExtractor:
             'status_perkawinan': None,
             'pekerjaan': None,
             'kewarganegaraan': None,
-            'berlaku_hingga': None,
+            'berlaku_hingga': 'SEUMUR HIDUP',  # Default sesuai peraturan pemerintah e-KTP
             'provinsi': None,
             'kabupaten_kota': None,
             'tanggal_penerbitan': None,
@@ -234,6 +711,14 @@ class KTPExtractor:
         
         # Fallback: Parse line by line for fields not found by zone
         for i, text in enumerate(texts):
+            # Skip baris yang hanya berisi punctuation atau kosong
+            text_stripped = text.strip()
+            if not text_stripped or text_stripped in [':', '：', '.', '-', '/', '|']:
+                continue
+            # Skip baris yang terlalu pendek (hanya 1-2 karakter non-alfanumerik)
+            if len(text_stripped) <= 2 and not any(c.isalnum() for c in text_stripped):
+                continue
+                
             text_lower = text.lower()
             
             # Normalize colons
@@ -242,19 +727,49 @@ class KTPExtractor:
             
             # ===== PROVINSI =====
             if 'provinsi' in text_lower and result['provinsi'] is None:
-                val = self._extract_after_label(text_normalized, 'provinsi')
-                if val:
-                    result['provinsi'] = val.upper()
-                elif i + 1 < len(texts) and 'provinsi' not in texts[i+1].lower():
-                    # Mungkin value di line berikutnya
-                    result['provinsi'] = texts[i+1].strip().upper()
+                # Split by PROVINSI and take remainder
+                split_prov = re.split(r'(?i)provinsi\s*', text, 1)
+                if len(split_prov) > 1:
+                    val = split_prov[1].strip()
+                    # Check if it contains kabupaten/kota (merged line case)
+                    if 'kabupaten' in val.lower() or 'kota' in val.lower():
+                        parts = re.split(r'(?i)\s*(kabupaten|kota)', val)
+                        val = parts[0].strip()
+                    
+                    if val:
+                        # Fuzzy match against valid provinces
+                        best_match = self._find_best_match(val.upper(), self.PROVINSI_LIST, cutoff=0.6)
+                        if best_match:
+                            result['provinsi'] = best_match
+                        else:
+                            result['provinsi'] = val.upper()
+                
+                # Check for next line if current line only had 'PROVINSI'
+                if result['provinsi'] is None and i + 1 < len(texts):
+                    next_text = texts[i+1].strip()
+                    next_lower = next_text.lower()
+                    # Only take next line if it doesn't look like another field
+                    if not any(kw in next_lower for kw in ['provinsi', 'kabupaten', 'kota', 'nik']):
+                         # Fuzzy match next line
+                        val = next_text.upper()
+                        best_match = self._find_best_match(val, self.PROVINSI_LIST, cutoff=0.6)
+                        if best_match:
+                            result['provinsi'] = best_match
+                        else:
+                            result['provinsi'] = val
             
             # ===== KABUPATEN/KOTA =====
             if ('kabupaten' in text_lower or 'kota' in text_lower or 'jakarta' in text_lower) and result['kabupaten_kota'] is None:
                 if 'provinsi' not in text_lower:  # Bukan bagian dari provinsi
-                    val = self._extract_after_label(text_normalized, 'kabupaten|kota')
-                    if val:
-                        result['kabupaten_kota'] = val.upper()
+                    # Split by KABUPATEN or KOTA and take remainder
+                    split_kab = re.split(r'(?i)\s*(kabupaten|kota)\s*', text, 1)
+                    if len(split_kab) > 1:
+                         prefix = "KABUPATEN" if "kabupaten" in text_lower else "KOTA"
+                         val = split_kab[-1].strip()
+                         if val:
+                             result['kabupaten_kota'] = f"{prefix} {val.upper()}"
+                         else:
+                             result['kabupaten_kota'] = text.strip().upper()
                     else:
                         result['kabupaten_kota'] = text.strip().upper()
             
@@ -312,13 +827,17 @@ class KTPExtractor:
                 if re.match(r'^[ABO]{1,2}[+\-]?$', text.strip(), re.IGNORECASE) and len(text.strip()) <= 3:
                     result['gol_darah'] = text.strip().upper()
             
-            # ===== ALAMAT =====
-            if 'alamat' in text_lower and result['alamat'] is None:
-                val = self._extract_after_label(text_normalized, 'alamat')
+            # ===== ALAMAT ===== (dengan fuzzy label matching)
+            if result['alamat'] is None and self._is_label_match(text, 'alamat'):
+                val = self._extract_after_label(text_normalized, r'a{1,2}l{0,2}a?m{0,2}a?t')
                 if val:
                     result['alamat'] = val.upper()
                 elif i + 1 < len(texts):
-                    result['alamat'] = texts[i+1].strip().upper()
+                    # Ambil nilai dari baris berikutnya
+                    next_text = texts[i+1].strip()
+                    # Pastikan bukan label field lain
+                    if len(next_text) > 2 and not self._is_label_match(next_text, 'rt_rw'):
+                        result['alamat'] = next_text.upper()
             
             # ===== RT/RW =====
             rt_rw_match = re.search(r'(\d{3})\s*/\s*(\d{3})', text)
@@ -346,9 +865,9 @@ class KTPExtractor:
                         if len(next_text) > 2 and not any(kw in next_text.lower() for kw in ['agama', 'status', 'pekerjaan']):
                             result['kecamatan'] = next_text.upper()
             
-            # ===== AGAMA =====
-            if 'agama' in text_lower:
-                val = self._extract_after_label(text_normalized, 'agama')
+            # ===== AGAMA ===== (dengan fuzzy label matching)
+            if self._is_label_match(text, 'agama'):
+                val = self._extract_after_label(text_normalized, r'a?g{0,2}a?m{0,2}a')
                 if val and result['agama'] is None:
                     result['agama'] = val.upper()
                 elif result['agama'] is None and i + 1 < len(texts):
@@ -367,17 +886,18 @@ class KTPExtractor:
             # ===== STATUS PERKAWINAN =====
             if 'kawin' in text_lower:
                 if result['status_perkawinan'] is None:
-                    val = self._extract_after_label(text_normalized, 'status.*kawin|perkawinan')
-                    if val:
-                        result['status_perkawinan'] = val.upper()
-                    elif 'belum' in text_lower:
-                        result['status_perkawinan'] = 'BELUM KAWIN'
-                    elif 'kawin' in text_lower and 'cerai' not in text_lower:
-                        result['status_perkawinan'] = 'KAWIN'
-                    elif 'cerai hidup' in text_lower:
-                        result['status_perkawinan'] = 'CERAI HIDUP'
-                    elif 'cerai mati' in text_lower:
-                        result['status_perkawinan'] = 'CERAI MATI'
+                    # Check against official list first
+                    text_upper = text.upper().replace("BELUMKAWIN", "BELUM KAWIN")
+                    for status in self.STATUS_PERKAWINAN_LIST:
+                        if status in text_upper:
+                            result['status_perkawinan'] = status
+                            break
+                    
+                    # Fallback to extraction if not found in list
+                    if result['status_perkawinan'] is None:
+                        val = self._extract_after_label(text_normalized, 'status.*kawin|perkawinan')
+                        if val:
+                            result['status_perkawinan'] = val.upper()
             
             # ===== PEKERJAAN =====
             if 'pekerjaan' in text_lower:
@@ -430,6 +950,88 @@ class KTPExtractor:
                         if result['berlaku_hingga'] or i > len(texts) * 0.7:
                             result['tanggal_penerbitan'] = found_date
         
+        # ============================================
+        # AGGRESSIVE SCAN: Cari agama dari semua teks OCR
+        # ============================================
+        # Indonesia hanya punya 6 agama resmi, mudah dideteksi
+        if result['agama'] is None:
+            # Daftar agama dengan variasi penulisan
+            agama_patterns = {
+                'ISLAM': ['ISLAM', 'ISLM', 'ISIAM', 'ISLAMI'],
+                'KRISTEN': ['KRISTEN', 'KRISTEN PROTESTAN', 'PROTESTAN', 'KRISTN'],
+                'KATOLIK': ['KATOLIK', 'KATHOLIK', 'KATHOLK', 'KATOLIK ROMA', 'KATOLIK.'],
+                'HINDU': ['HINDU', 'HNDU', 'HINDU DHARMA', 'HINDHU'],
+                'BUDDHA': ['BUDDHA', 'BUDHA', 'BUDDA', 'BUDDHIS'],
+                'KONGHUCU': ['KONGHUCU', 'KHONGHUCU', 'KONGHUCHU', 'CONFUCIUS'],
+            }
+            
+            for text in texts:
+                text_upper = text.upper().strip()
+                # Skip jika teks terlalu pendek atau terlalu panjang
+                if len(text_upper) < 4 or len(text_upper) > 30:
+                    continue
+                
+                for agama_std, variants in agama_patterns.items():
+                    for variant in variants:
+                        if variant in text_upper:
+                            result['agama'] = agama_std
+                            print(f"  [AGAMA SCAN] Found '{variant}' in '{text_upper}' -> {agama_std}")
+                            break
+                    if result['agama']:
+                        break
+                if result['agama']:
+                    break
+        
+        # ============================================
+        # AGGRESSIVE SCAN: Cari golongan darah dari semua teks OCR
+        # ============================================
+        # Golongan darah hanya 4: A, B, AB, O (dengan/tanpa rhesus +/-)
+        if result['gol_darah'] is None:
+            gol_darah_patterns = ['AB+', 'AB-', 'A+', 'A-', 'B+', 'B-', 'O+', 'O-', 'AB', 'A', 'B', 'O']
+            
+            for text in texts:
+                text_upper = text.upper().strip()
+                # Hapus punctuation umum
+                text_clean = re.sub(r'[:\.\,\s]+', '', text_upper)
+                # Konversi 0 (nol) menjadi O (huruf) - OCR sering salah baca
+                text_clean = text_clean.replace('0', 'O')
+                
+                # Skip jika teks terlalu panjang (bukan gol darah)
+                if len(text_clean) > 10:
+                    continue
+                
+                # Cari match untuk gol darah (dari panjang ke pendek untuk prioritas AB sebelum A/B)
+                for gol in gol_darah_patterns:
+                    # Exact match setelah dibersihkan
+                    if text_clean == gol:
+                        result['gol_darah'] = gol
+                        print(f"  [GOL DARAH SCAN] Found '{text_upper}' -> {gol}")
+                        break
+                    # Match dengan prefix GOL
+                    if text_clean == f"GOL{gol}" or text_clean == f"GOLDARAH{gol}":
+                        result['gol_darah'] = gol
+                        print(f"  [GOL DARAH SCAN] Found '{text_upper}' -> {gol}")
+                        break
+                    # Match sebagai single character di akhir teks pendek
+                    if len(text_clean) <= 3 and text_clean.endswith(gol):
+                        result['gol_darah'] = gol
+                        print(f"  [GOL DARAH SCAN] Found '{text_upper}' -> {gol}")
+                        break
+                        
+                if result['gol_darah']:
+                    break
+        
+        # ============================================
+        # AGGRESSIVE SCAN: Cari berlaku hingga dari semua teks OCR
+        # ============================================
+        if result['berlaku_hingga'] is None:
+            for text in texts:
+                text_upper = text.upper().strip()
+                if 'SEUMUR' in text_upper or 'HIDUP' in text_upper:
+                    result['berlaku_hingga'] = 'SEUMUR HIDUP'
+                    print(f"  [BERLAKU SCAN] Found '{text_upper}' -> SEUMUR HIDUP")
+                    break
+        
         # Post-processing
         result = self._post_process(result)
         
@@ -505,6 +1107,21 @@ class KTPExtractor:
             else:
                 result['nik'] = None
         
+        # Fix format tanggal lahir yang salah
+        # Pattern: DDMM-YYYY (contoh: 1608-1976) -> DD-MM-YYYY (16-08-1976)
+        if result['tanggal_lahir']:
+            tl = result['tanggal_lahir']
+            # Match DDMM-YYYY format (salah)
+            wrong_format = re.match(r'^(\d{2})(\d{2})-(\d{4})$', tl)
+            if wrong_format:
+                result['tanggal_lahir'] = f"{wrong_format.group(1)}-{wrong_format.group(2)}-{wrong_format.group(3)}"
+                print(f"  [DATE FIX] '{tl}' -> '{result['tanggal_lahir']}'")
+            # Match DDMMYYYY format (tanpa separator)
+            no_sep_format = re.match(r'^(\d{2})(\d{2})(\d{4})$', tl)
+            if no_sep_format:
+                result['tanggal_lahir'] = f"{no_sep_format.group(1)}-{no_sep_format.group(2)}-{no_sep_format.group(3)}"
+                print(f"  [DATE FIX] '{tl}' -> '{result['tanggal_lahir']}'")
+        
         # Clean all string values - remove leading colons and extra whitespace
         for field in result:
             if result[field] and isinstance(result[field], str):
@@ -540,6 +1157,54 @@ class KTPExtractor:
                 result['berlaku_hingga'] = 'SEUMUR HIDUP'
             else:
                 result['berlaku_hingga'] = bh
+        else:
+            # Fallback: Sesuai peraturan pemerintah, e-KTP berlaku seumur hidup
+            # Berlaku untuk e-KTP yang diterbitkan sejak 2011
+            result['berlaku_hingga'] = 'SEUMUR HIDUP'
+            print("  [FALLBACK] berlaku_hingga = SEUMUR HIDUP (peraturan pemerintah)")
+        
+        # ============================================
+        # Parse nama Bali jika terdeteksi
+        # ============================================
+        # Deteksi apakah ini KTP Bali berdasarkan:
+        # 1. Provinsi = BALI
+        # 2. NIK dimulai dengan 51 (kode Bali)
+        # 3. Nama mengandung komponen khas Bali (NI, I GUSTI, dll)
+        is_bali = False
+        if result.get('provinsi') and 'BALI' in result['provinsi'].upper():
+            is_bali = True
+        elif result.get('nik') and result['nik'].startswith('51'):
+            is_bali = True
+        elif result.get('nama'):
+            nama_upper = result['nama'].upper()
+            # Cek apakah nama dimulai dengan prefix Bali
+            if nama_upper.startswith('NI') or nama_upper.startswith('IGUSTI') or \
+               nama_upper.startswith('IDABAGUS') or nama_upper.startswith('IDAAYU') or \
+               any(nama_upper.startswith(p) for p in ['GUSTI', 'WAYAN', 'MADE', 'NYOMAN', 'KETUT', 'PUTU', 'KADEK', 'KOMANG']):
+                is_bali = True
+        
+        if is_bali and result.get('nama'):
+            result['nama'] = self._parse_balinese_name(result['nama'])
+        
+        # ============================================
+        # Validasi dan koreksi Agama
+        # ============================================
+        if result.get('agama'):
+            agama = result['agama'].upper().strip()
+            # Fuzzy match terhadap daftar agama valid
+            agama_match = None
+            best_ratio = 0
+            for valid_agama in self.AGAMA_LIST:
+                ratio = difflib.SequenceMatcher(None, agama, valid_agama.upper()).ratio()
+                if ratio > best_ratio and ratio > 0.6:
+                    best_ratio = ratio
+                    agama_match = valid_agama.upper()
+            
+            if agama_match:
+                if agama_match != agama:
+                    print(f"  [AGAMA VALIDATE] '{agama}' -> '{agama_match}' (ratio={best_ratio:.2f})")
+                result['agama'] = agama_match
+        # Tidak ada fallback otomatis untuk agama - harus dari OCR
         
         # Fix merged kabupaten/kota names (e.g., JAKARTASELATAN -> JAKARTA SELATAN)
         if result['kabupaten_kota']:
@@ -572,6 +1237,29 @@ class KTPExtractor:
             alamat = re.sub(r'\b(NO|BLOK)(\d+|[A-Z])\b', r'\1 \2', alamat, flags=re.IGNORECASE)
             result['alamat'] = alamat.upper()
         
+        # ============================================
+        # Cross-validation: Tempat Lahir vs Kel/Desa
+        # ============================================
+        # Pada KTP, tempat lahir sering sama dengan desa/kelurahan
+        # Jika tempat_lahir mirip dengan kel_desa, gunakan yang tervalidasi
+        if result.get('tempat_lahir') and result.get('kel_desa'):
+            tl = result['tempat_lahir'].upper()
+            kd = result['kel_desa'].upper()
+            
+            # Hitung similarity
+            ratio = difflib.SequenceMatcher(None, tl, kd).ratio()
+            
+            if ratio > 0.7:
+                # Tempat lahir mirip dengan kel/desa, gunakan kel/desa yang sudah divalidasi
+                print(f"  [CROSS-VALIDATE] Tempat Lahir '{tl}' mirip dengan Kel/Desa '{kd}' (ratio={ratio:.2f})")
+                result['tempat_lahir'] = kd
+            elif ratio > 0.5:
+                # Cukup mirip, log untuk debugging
+                print(f"  [CROSS-VALIDATE] Tempat Lahir '{tl}' mungkin sama dengan Kel/Desa '{kd}' (ratio={ratio:.2f})")
+        
+        # Jika tempat_lahir kosong tapi kel_desa ada, mungkin sama
+        # (tidak otomatis mengisi karena bisa beda)
+        
         return result
 
 

migrate_db.py

@@ -0,0 +1,48 @@
+import os
+import pymysql
+from database import DB_CONFIG
+
+def migrate_db():
+    conn = pymysql.connect(
+        host=DB_CONFIG['host'],
+        port=int(DB_CONFIG['port']),
+        user=DB_CONFIG['user'],
+        password=DB_CONFIG['password'],
+        database=DB_CONFIG['database']
+    )
+    
+    try:
+        with conn.cursor() as cursor:
+            # Check if column exists
+            print("Checking schema...")
+            cursor.execute("SHOW COLUMNS FROM ktp_records LIKE 'image_path'")
+            result = cursor.fetchone()
+            
+            if not result:
+                print("Adding image_path column to ktp_records...")
+                cursor.execute("ALTER TABLE ktp_records ADD COLUMN image_path VARCHAR(255) NULL AFTER berlaku_hingga")
+                conn.commit()
+                print("Migration successful: Added image_path column.")
+            else:
+                print("Column image_path already exists in KTP. No migration needed.")
+            
+            # Check KK
+            print("Checking KK schema...")
+            cursor.execute("SHOW COLUMNS FROM kk_records LIKE 'image_path'")
+            result_kk = cursor.fetchone()
+            
+            if not result_kk:
+                print("Adding image_path column to kk_records...")
+                cursor.execute("ALTER TABLE kk_records ADD COLUMN image_path VARCHAR(255) NULL AFTER kode_pos")
+                conn.commit()
+                print("Migration successful: Added image_path column to KK.")
+            else:
+                print("Column image_path already exists in KK.")
+                
+    except Exception as e:
+        print(f"Migration error: {e}")
+    finally:
+        conn.close()
+
+if __name__ == "__main__":
+    migrate_db()

models.py

@@ -0,0 +1,138 @@
+"""
+Database Models for OCR Application
+"""
+
+from datetime import datetime
+from database import db
+
+
+class KTPRecord(db.Model):
+    """Model untuk menyimpan data KTP hasil OCR"""
+    __tablename__ = 'ktp_records'
+    
+    id = db.Column(db.Integer, primary_key=True, autoincrement=True)
+    nik = db.Column(db.String(16), unique=True, nullable=True, index=True)
+    nama = db.Column(db.String(100), nullable=True)
+    tempat_lahir = db.Column(db.String(50), nullable=True)
+    tanggal_lahir = db.Column(db.String(20), nullable=True)
+    jenis_kelamin = db.Column(db.String(20), nullable=True)
+    gol_darah = db.Column(db.String(5), nullable=True)
+    alamat = db.Column(db.Text, nullable=True)
+    rt_rw = db.Column(db.String(10), nullable=True)
+    kel_desa = db.Column(db.String(50), nullable=True)
+    kecamatan = db.Column(db.String(50), nullable=True)
+    kabupaten_kota = db.Column(db.String(50), nullable=True)
+    provinsi = db.Column(db.String(50), nullable=True)
+    agama = db.Column(db.String(20), nullable=True)
+    status_perkawinan = db.Column(db.String(30), nullable=True)
+    pekerjaan = db.Column(db.String(50), nullable=True)
+    kewarganegaraan = db.Column(db.String(10), nullable=True)
+    berlaku_hingga = db.Column(db.String(20), nullable=True)
+    image_path = db.Column(db.String(255), nullable=True)  # Path to saved KTP image
+    raw_text = db.Column(db.Text, nullable=True)
+    created_at = db.Column(db.DateTime, default=datetime.utcnow)
+    updated_at = db.Column(db.DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+    
+    def to_dict(self):
+        """Convert model to dictionary"""
+        return {
+            'id': self.id,
+            'nik': self.nik,
+            'nama': self.nama,
+            'tempat_lahir': self.tempat_lahir,
+            'tanggal_lahir': self.tanggal_lahir,
+            'jenis_kelamin': self.jenis_kelamin,
+            'gol_darah': self.gol_darah,
+            'alamat': self.alamat,
+            'rt_rw': self.rt_rw,
+            'kel_desa': self.kel_desa,
+            'kecamatan': self.kecamatan,
+            'kabupaten_kota': self.kabupaten_kota,
+            'provinsi': self.provinsi,
+            'agama': self.agama,
+            'status_perkawinan': self.status_perkawinan,
+            'pekerjaan': self.pekerjaan,
+            'kewarganegaraan': self.kewarganegaraan,
+            'berlaku_hingga': self.berlaku_hingga,
+            'image_path': self.image_path,
+            'created_at': self.created_at.isoformat() if self.created_at else None,
+            'updated_at': self.updated_at.isoformat() if self.updated_at else None
+        }
+    
+    @classmethod
+    def from_ocr_data(cls, ocr_data, raw_text=None):
+        """Create KTPRecord from OCR extracted data"""
+        return cls(
+            nik=ocr_data.get('nik'),
+            nama=ocr_data.get('nama'),
+            tempat_lahir=ocr_data.get('tempat_lahir'),
+            tanggal_lahir=ocr_data.get('tanggal_lahir'),
+            jenis_kelamin=ocr_data.get('jenis_kelamin'),
+            gol_darah=ocr_data.get('gol_darah'),
+            alamat=ocr_data.get('alamat'),
+            rt_rw=ocr_data.get('rt_rw'),
+            kel_desa=ocr_data.get('kel_desa'),
+            kecamatan=ocr_data.get('kecamatan'),
+            kabupaten_kota=ocr_data.get('kabupaten_kota'),
+            provinsi=ocr_data.get('provinsi'),
+            agama=ocr_data.get('agama'),
+            status_perkawinan=ocr_data.get('status_perkawinan'),
+            pekerjaan=ocr_data.get('pekerjaan'),
+            kewarganegaraan=ocr_data.get('kewarganegaraan'),
+            berlaku_hingga=ocr_data.get('berlaku_hingga'),
+            raw_text=raw_text
+        )
+
+
+class KKRecord(db.Model):
+    """Model untuk menyimpan data Kartu Keluarga hasil OCR"""
+    __tablename__ = 'kk_records'
+    
+    id = db.Column(db.Integer, primary_key=True, autoincrement=True)
+    no_kk = db.Column(db.String(16), unique=True, nullable=True, index=True)
+    kepala_keluarga = db.Column(db.String(100), nullable=True)
+    alamat = db.Column(db.Text, nullable=True)
+    rt_rw = db.Column(db.String(10), nullable=True)
+    kel_desa = db.Column(db.String(50), nullable=True)
+    kecamatan = db.Column(db.String(50), nullable=True)
+    kabupaten_kota = db.Column(db.String(50), nullable=True)
+    provinsi = db.Column(db.String(50), nullable=True)
+    kode_pos = db.Column(db.String(10), nullable=True)
+    image_path = db.Column(db.String(255), nullable=True)  # Path to saved KK image
+    raw_text = db.Column(db.Text, nullable=True)
+    created_at = db.Column(db.DateTime, default=datetime.utcnow)
+    updated_at = db.Column(db.DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+    
+    def to_dict(self):
+        """Convert model to dictionary"""
+        return {
+            'id': self.id,
+            'no_kk': self.no_kk,
+            'kepala_keluarga': self.kepala_keluarga,
+            'alamat': self.alamat,
+            'rt_rw': self.rt_rw,
+            'kel_desa': self.kel_desa,
+            'kecamatan': self.kecamatan,
+            'kabupaten_kota': self.kabupaten_kota,
+            'provinsi': self.provinsi,
+            'kode_pos': self.kode_pos,
+            'image_path': self.image_path,
+            'created_at': self.created_at.isoformat() if self.created_at else None,
+            'updated_at': self.updated_at.isoformat() if self.updated_at else None
+        }
+    
+    @classmethod
+    def from_ocr_data(cls, ocr_data, raw_text=None):
+        """Create KKRecord from OCR extracted data"""
+        return cls(
+            no_kk=ocr_data.get('no_kk'),
+            kepala_keluarga=ocr_data.get('kepala_keluarga'),
+            alamat=ocr_data.get('alamat'),
+            rt_rw=ocr_data.get('rt_rw'),
+            kel_desa=ocr_data.get('kel_desa'),
+            kecamatan=ocr_data.get('kecamatan'),
+            kabupaten_kota=ocr_data.get('kabupaten_kota'),
+            provinsi=ocr_data.get('provinsi'),
+            kode_pos=ocr_data.get('kode_pos'),
+            raw_text=raw_text
+        )

ocr_engine.py

@@ -20,16 +20,19 @@ class OCREngine:
     
     def preprocess_image(self, image_path: str) -> np.ndarray:
         """
-        Preprocessing gambar untuk hasil OCR lebih baik
+        Enhanced preprocessing untuk hasil OCR lebih baik
+        Based on Context7 OpenCV documentation:
         - Resize jika terlalu besar
-        - Enhance contrast
+        - Denoising untuk mengurangi noise
+        - CLAHE untuk adaptive histogram equalization
+        - Sharpening untuk teks lebih jelas
         """
         img = cv2.imread(image_path)
         if img is None:
             raise ValueError(f"Tidak dapat membaca gambar: {image_path}")
         
-        # Resize jika terlalu besar (max 2000px)
-        max_dim = 2000
+        # Resize jika terlalu besar (max 1500px - optimized for speed)
+        max_dim = 1500
         height, width = img.shape[:2]
         if max(height, width) > max_dim:
             scale = max_dim / max(height, width)
@@ -38,12 +41,20 @@ class OCREngine:
         # Convert ke grayscale untuk preprocessing
         gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
         
-        # Enhance contrast menggunakan CLAHE
-        clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
-        enhanced = clahe.apply(gray)
+        # Denoise (from Context7) - mengurangi noise tanpa blur teks
+        denoised = cv2.fastNlMeansDenoising(gray, None, 10, 7, 21)
+        
+        # Enhanced CLAHE untuk dokumen (from Context7)
+        # clipLimit lebih tinggi untuk kontras lebih baik
+        clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8, 8))
+        enhanced = clahe.apply(denoised)
+        
+        # Sharpen using kernel (from Context7)
+        kernel = np.array([[0, -1, 0], [-1, 5, -1], [0, -1, 0]], dtype=np.float32)
+        sharpened = cv2.filter2D(enhanced, -1, kernel)
         
         # Convert kembali ke BGR untuk PaddleOCR
-        enhanced_bgr = cv2.cvtColor(enhanced, cv2.COLOR_GRAY2BGR)
+        enhanced_bgr = cv2.cvtColor(sharpened, cv2.COLOR_GRAY2BGR)
         
         return enhanced_bgr
     

requirements.txt

@@ -3,3 +3,6 @@ paddleocr
 flask
 pillow
 opencv-python
+pymysql
+flask-sqlalchemy
+requests

static/style.css

@@ -175,6 +175,121 @@ header h1 {
     max-height: 400px;
     border-radius: var(--radius);
     cursor: pointer;
+    display: block;
+    margin: 0 auto;
+}
+
+/* Crop Container */
+.crop-container {
+    position: relative;
+    max-width: 100%;
+    margin-bottom: 1rem;
+    overflow: hidden;
+    border-radius: var(--radius);
+    background: #000;
+}
+
+.crop-area {
+    position: absolute;
+    top: 0;
+    left: 0;
+    pointer-events: none;
+    /* Let clicks pass through, handles catch them */
+}
+
+/* Perspective Crop Handles */
+.crop-handle {
+    position: absolute;
+    width: 20px;
+    height: 20px;
+    background: var(--accent-primary);
+    border: 2px solid #fff;
+    border-radius: 50%;
+    transform: translate(-50%, -50%);
+    cursor: move;
+    pointer-events: auto;
+    z-index: 10;
+    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.5);
+    transition: transform 0.1s ease;
+}
+
+.crop-handle:hover,
+.crop-handle.active {
+    background: #fff;
+    border-color: var(--accent-primary);
+    transform: translate(-50%, -50%) scale(1.2);
+}
+
+/* Crop Actions & Controls */
+.crop-actions-container {
+    display: flex;
+    flex-direction: column;
+    gap: 1rem;
+    margin-top: 1rem;
+    padding: 1rem;
+    background: var(--bg-secondary);
+    border-radius: var(--radius);
+    border: 1px solid var(--border);
+}
+
+.rotation-control {
+    display: flex;
+    align-items: center;
+    gap: 1rem;
+    color: var(--text-secondary);
+}
+
+.rotation-control label {
+    font-weight: 500;
+    min-width: 80px;
+}
+
+.rotation-control input[type="range"] {
+    flex: 1;
+    cursor: pointer;
+    accent-color: var(--accent-primary);
+}
+
+.crop-buttons {
+    display: flex;
+    gap: 1rem;
+    justify-content: center;
+}
+
+.crop-action-btn {
+    padding: 0.5rem 1rem;
+    border: none;
+    border-radius: var(--radius);
+    cursor: pointer;
+    font-weight: 500;
+    transition: all 0.2s ease;
+    flex: 1;
+}
+
+.crop-action-btn.primary {
+    background: var(--accent-gradient);
+    color: white;
+}
+
+.crop-action-btn.primary:hover:not(:disabled) {
+    transform: translateY(-2px);
+    box-shadow: var(--shadow);
+}
+
+.crop-action-btn.primary:disabled {
+    opacity: 0.6;
+    cursor: not-allowed;
+}
+
+.crop-action-btn.secondary {
+    background: var(--bg-tertiary);
+    color: var(--text-secondary);
+    border: 1px solid var(--border);
+}
+
+.crop-action-btn.secondary:hover {
+    background: var(--bg-primary);
+    color: var(--text-primary);
 }
 
 /* Process Button */
@@ -533,6 +648,290 @@ footer a:hover {
     border-radius: 4px;
 }
 
-::-webkit-scrollbar-thumb:hover {
-    background: var(--text-muted);
+/* Archive Header Button */
+.header-actions {
+    display: flex;
+    gap: 1rem;
+    justify-content: center;
+    margin-top: 1rem;
+}
+
+.archive-header-btn {
+    padding: 0.5rem 1.25rem;
+    background: transparent;
+    border: 1px solid var(--accent-secondary);
+    color: var(--accent-secondary);
+    border-radius: var(--radius);
+    cursor: pointer;
+    font-weight: 600;
+    transition: all 0.2s ease;
+}
+
+.archive-header-btn:hover {
+    background: var(--accent-primary);
+    color: white;
+    border-color: var(--accent-primary);
+}
+
+/* Modal Styles */
+.modal {
+    position: fixed;
+    z-index: 1000;
+    left: 0;
+    top: 0;
+    width: 100%;
+    height: 100%;
+    background-color: rgba(0, 0, 0, 0.7);
+    backdrop-filter: blur(4px);
+    overflow: auto;
+    animation: fadeIn 0.3s;
+}
+
+@keyframes fadeIn {
+    from {
+        opacity: 0;
+    }
+
+    to {
+        opacity: 1;
+    }
+}
+
+.modal-content {
+    background-color: var(--bg-secondary);
+    margin: 5% auto;
+    padding: 2rem;
+    border: 1px solid var(--border);
+    border-radius: var(--radius-lg);
+    width: 90%;
+    max-width: 1000px;
+    box-shadow: 0 25px 50px -12px rgba(0, 0, 0, 0.5);
+    position: relative;
+    animation: slideDown 0.3s;
+}
+
+@keyframes slideDown {
+    from {
+        transform: translateY(-50px);
+        opacity: 0;
+    }
+
+    to {
+        transform: translateY(0);
+        opacity: 1;
+    }
+}
+
+.modal-header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-bottom: 2rem;
+    padding-bottom: 1rem;
+    border-bottom: 1px solid var(--border);
+}
+
+.modal-header h2 {
+    color: var(--text-primary);
+    font-size: 1.5rem;
+}
+
+.close-btn {
+    background: transparent;
+    border: none;
+    color: var(--text-muted);
+    font-size: 2rem;
+    cursor: pointer;
+    line-height: 1;
+    transition: color 0.2s;
+}
+
+.close-btn:hover {
+    color: var(--text-primary);
+}
+
+/* Archive List Grid */
+.archive-list {
+    display: grid;
+    grid-template-columns: repeat(auto-fill, minmax(250px, 1fr));
+    gap: 1.5rem;
+    max-height: 70vh;
+    overflow-y: auto;
+    padding-right: 0.5rem;
+}
+
+.archive-card {
+    background: var(--bg-tertiary);
+    border: 1px solid var(--border);
+    border-radius: var(--radius);
+    overflow: hidden;
+    transition: transform 0.2s, box-shadow 0.2s;
+    display: flex;
+    flex-direction: column;
+}
+
+.archive-card:hover {
+    transform: translateY(-4px);
+    box-shadow: var(--shadow-lg);
+    border-color: var(--accent-primary);
+}
+
+.archive-card-img {
+    width: 100%;
+    height: 160px;
+    background: #000;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    overflow: hidden;
+}
+
+.archive-card-img img {
+    width: 100%;
+    height: 100%;
+    object-fit: cover;
+    transition: transform 0.3s;
+}
+
+.archive-card:hover .archive-card-img img {
+    transform: scale(1.05);
+}
+
+.archive-card-content {
+    padding: 1rem;
+    flex: 1;
+    display: flex;
+    flex-direction: column;
+}
+
+.archive-card-content h3 {
+    font-size: 1rem;
+    margin-bottom: 0.5rem;
+    color: var(--text-primary);
+    white-space: nowrap;
+    overflow: hidden;
+    text-overflow: ellipsis;
+}
+
+.archive-card-meta {
+    margin-bottom: 1rem;
+    font-size: 0.8rem;
+    color: var(--text-muted);
+    display: flex;
+    flex-direction: column;
+    gap: 0.25rem;
+}
+
+.archive-card-actions {
+    margin-top: auto;
+}
+
+.view-btn {
+    width: 100%;
+    padding: 0.5rem;
+    background: var(--bg-primary);
+    border: 1px solid var(--border);
+    color: var(--text-secondary);
+    border-radius: 6px;
+    cursor: pointer;
+    font-size: 0.875rem;
+    transition: all 0.2s;
+}
+
+.view-btn:hover {
+    background: var(--accent-primary);
+    color: white;
+    border-color: var(--accent-primary);
+}
+
+.archive-loading,
+.archive-empty {
+    text-align: center;
+    padding: 3rem;
+    color: var(--text-muted);
+    font-size: 1.1rem;
+}
+
+/* Print Styles */
+@media print {
+
+    /* Reset Page */
+    @page {
+        margin: 0;
+        size: auto;
+    }
+
+    body {
+        margin: 0;
+        padding: 0;
+        background: white !important;
+        /* Ensure no scroll or extra pages from hidden content */
+        height: 100vh !important;
+        overflow: hidden !important;
+    }
+
+    /* Hide EVERYTHING initially with high specificity */
+    body * {
+        visibility: hidden !important;
+        display: none !important;
+        /* Force display none to remove layout space */
+    }
+
+    /* Show ONLY Print Area and its children */
+    #printArea,
+    #printArea * {
+        visibility: visible !important;
+        display: flex !important;
+        /* Restore display for parent */
+    }
+
+    /* Reset display for children of printArea specifically */
+    #printArea * {
+        display: block !important;
+        /* Default to block or whatever needed */
+    }
+
+    /* Specific fix for image inside */
+    #printArea img {
+        display: inline-block !important;
+    }
+
+    #printArea {
+        position: fixed !important;
+        /* Fixed helps detach from flow */
+        left: 0 !important;
+        top: 0 !important;
+        width: 100% !important;
+        height: 100% !important;
+        overflow: visible !important;
+        z-index: 99999 !important;
+        background: white !important;
+
+        display: flex !important;
+        justify-content: center;
+        align-items: flex-start;
+        padding-top: 5cm;
+        /* Adjust padding as needed */
+    }
+
+    .ktp-print-size {
+        /* Standar ISO/IEC 7810 ID-1: 85.60 × 53.98 mm */
+        width: 85.60mm !important;
+        height: 53.98mm !important;
+        max-width: none !important;
+        max-height: none !important;
+        border: 1px dashed #ccc;
+        box-shadow: none !important;
+        /* Remove any shadow */
+    }
+
+    .a4-print-size {
+        /* A4 Landscape: 297mm x 210mm */
+        /* Use slightly less to account for margins if necessary, but standard is distinct */
+        width: 297mm !important;
+        height: 210mm !important;
+        max-width: none !important;
+        max-height: none !important;
+        border: none;
+    }
 }

templates/index.html

@@ -13,6 +13,12 @@
         <header>
             <h1>📄 OCR KTP/KK</h1>
             <p class="subtitle">Pembaca Dokumen Indonesia Offline</p>
+            <div class="header-actions">
+                <button id="reloadBtn" class="archive-header-btn secondary" title="Reload halaman">🔄 Reset /
+                    Baru</button>
+                <button id="archiveBtn" class="archive-header-btn">📂 Arsip KTP</button>
+                <button id="archiveKKBtn" class="archive-header-btn">📂 Arsip KK</button>
+            </div>
         </header>
 
         <main>
@@ -40,7 +46,42 @@
                         </label>
                         <p class="file-types">PNG, JPG, JPEG, BMP, WEBP (max 16MB)</p>
                     </div>
-                    <img id="preview" class="preview-image" style="display: none;">
+
+                    <!-- Crop Container -->
+                    <div id="cropContainer" class="crop-container" style="display: none;">
+                        <!-- Canvas for editing (rotation & crop) -->
+                        <canvas id="cropCanvas" class="preview-image"></canvas>
+                        <!-- Keep img for simple viewing if needed, or just use canvas. Let's rely on canvas for editor -->
+                        <img id="preview" class="preview-image" style="display: none;">
+
+                        <div id="cropArea" class="crop-area">
+                            <svg width="100%" height="100%"
+                                style="position: absolute; top:0; left:0; overflow:visible;">
+                                <polygon id="cropPolygon" points=""
+                                    style="fill: rgba(255, 255, 255, 0.1); stroke: var(--accent-primary); stroke-width: 2; vector-effect: non-scaling-stroke;">
+                                </polygon>
+                            </svg>
+                            <!-- Handles TL, TR, BR, BL -->
+                            <div class="crop-handle" data-index="0"></div>
+                            <div class="crop-handle" data-index="1"></div>
+                            <div class="crop-handle" data-index="2"></div>
+                            <div class="crop-handle" data-index="3"></div>
+                        </div>
+                    </div>
+                </div>
+
+                <!-- Crop Actions -->
+                <div id="cropActions" class="crop-actions-container" style="display: none;">
+                    <div class="rotation-control">
+                        <label for="rotationSlider">Rotasi: <span id="rotationValue">0°</span></label>
+                        <input type="range" id="rotationSlider" min="-45" max="45" value="0" step="1">
+                    </div>
+
+                    <div class="crop-buttons">
+                        <button type="button" id="resetCropBtn" class="crop-action-btn secondary">🔄 Reset</button>
+                        <button type="button" id="applyCropBtn" class="crop-action-btn primary">✂️ Terapkan
+                            Crop</button>
+                    </div>
                 </div>
 
                 <button id="processBtn" class="process-btn" disabled>
@@ -54,8 +95,11 @@
                 <div class="results-header">
                     <h2>📋 Hasil Ekstraksi</h2>
                     <div class="results-actions">
-                        <button class="action-btn" id="copyBtn" title="Copy JSON">📋 Copy</button>
-                        <button class="action-btn" id="exportBtn" title="Export JSON">💾 Export</button>
+                        <button class="action-btn secondary" id="printBtn">🖨️ Cetak</button>
+                        <button class="action-btn secondary" id="downloadBtn">⬇️ Unduh</button>
+                        <button class="action-btn primary" id="saveBtn" title="Simpan KTP">💾 Simpan</button>
+                        <button class="action-btn" id="copyBtn" title="Copy Text (Word)">📋 Copy</button>
+                        <button class="action-btn" id="exportBtn" title="Download Excel (.xlsx)">📤 Excel</button>
                         <button class="action-btn secondary" id="toggleRaw">📝 Raw Text</button>
                     </div>
                 </div>
@@ -88,6 +132,52 @@
             </section>
         </main>
 
+        <!-- Login Modal -->
+        <div id="loginModal" class="modal" style="display: none;">
+            <div class="modal-content" style="max-width: 400px;">
+                <div class="modal-header">
+                    <h2>🔐 Login Arsip</h2>
+                    <span class="close-btn" id="closeLoginBtn">&times;</span>
+                </div>
+                <div class="modal-body">
+                    <p style="margin-bottom:1rem; color:var(--text-secondary);">Masukkan password untuk mengakses arsip
+                        (Default: admin / 123).</p>
+                    <div class="form-group">
+                        <label>Username</label>
+                        <input type="text" id="loginUser" class="form-control" value="admin">
+                    </div>
+                    <div class="form-group">
+                        <label>Password</label>
+                        <input type="password" id="loginPass" class="form-control" placeholder="Password">
+                    </div>
+                    <div id="loginError"
+                        style="color:var(--text-error); display:none; margin-bottom:1rem; font-size:0.9rem;"></div>
+                    <button id="submitLoginBtn" class="action-btn primary" style="width:100%;">Masuk</button>
+                </div>
+            </div>
+        </div>
+
+        <!-- Archive Modal -->
+        <div id="archiveModal" class="modal" style="display: none;">
+            <div class="modal-content">
+                <div class="modal-header">
+                    <h2>📂 Arsip KTP</h2>
+                    <button id="closeModalBtn" class="close-btn">&times;</button>
+                </div>
+                <div class="modal-body">
+                    <div id="archiveList" class="archive-list">
+                        <!-- Cards will be loaded here -->
+                    </div>
+                    <div id="archiveLoading" class="archive-loading" style="display: none;">
+                        ⏳ Memuat...
+                    </div>
+                    <div id="archiveEmpty" class="archive-empty" style="display: none;">
+                        Belum ada KTP yang disimpan
+                    </div>
+                </div>
+            </div>
+        </div>
+
         <footer>
             <p>OCR menggunakan <a href="https://github.com/PaddlePaddle/PaddleOCR" target="_blank">PaddleOCR</a> • Data
                 diproses secara lokal</p>
@@ -97,8 +187,10 @@
     <script>
         // State
         let selectedFile = null;
-        let docType = 'ktp';
+        let originalImageObject = null; // For cropping
         let extractedData = null;
+        let currentDocType = 'ktp'; // Default
+        let currentArchiveType = 'ktp'; // Default for archive view
 
         // Elements
         const dropzone = document.getElementById('dropzone');
@@ -146,7 +238,7 @@
             btn.addEventListener('click', () => {
                 docBtns.forEach(b => b.classList.remove('active'));
                 btn.classList.add('active');
-                docType = btn.dataset.type;
+                currentDocType = btn.dataset.type;
             });
         });
 
@@ -177,12 +269,20 @@
         });
 
         // Click on dropzone
+        // Click on dropzone - DISABLED (User request: Only 'Pilih File' button should work)
         dropzone.addEventListener('click', (e) => {
-            if (e.target === dropzone || e.target.closest('.dropzone-content')) {
-                fileInput.click();
-            }
+            // Do nothing. Label 'file-btn' handles clicks on itself automatically.
+            // preventing accidental uploads when clicking background/crop area.
         });
 
+        // Canvas & Rotation Variables
+        const cropCanvas = document.getElementById('cropCanvas');
+        const rotationSlider = document.getElementById('rotationSlider');
+        const rotationValue = document.getElementById('rotationValue');
+
+        let currentRotation = 0;
+        // let originalImageObject = null; // Store Image object for redraws - moved to global state
+
         function handleFile(file) {
             if (!file.type.startsWith('image/')) {
                 showError('File harus berupa gambar');
@@ -194,14 +294,36 @@
                 return;
             }
 
+            originalFile = file;
             selectedFile = file;
+            currentRotation = 0;
+            updateRotationUI();
 
-            // Show preview
+            // Load image
             const reader = new FileReader();
             reader.onload = (e) => {
-                preview.src = e.target.result;
-                preview.style.display = 'block';
-                dropzone.querySelector('.dropzone-content').style.display = 'none';
+                originalImageData = e.target.result;
+
+                // Create Image object
+                const img = new Image();
+                img.onload = () => {
+                    originalImageObject = img;
+                    preview.src = e.target.result; // Keep this for backup/debugging
+
+                    // Render to canvas
+                    renderEditor();
+
+                    cropCanvas.style.display = 'block';
+                    preview.style.display = 'none';
+                    cropContainer.style.display = 'block';
+                    dropzone.querySelector('.dropzone-content').style.display = 'none';
+                    cropActions.style.display = 'flex';
+
+                    // Init crop area after first render
+                    // Small timeout to ensure layout is done
+                    setTimeout(initCropArea, 50);
+                };
+                img.src = e.target.result;
             };
             reader.readAsDataURL(file);
 
@@ -210,6 +332,272 @@
             resultsSection.style.display = 'none';
         }
 
+        // Handle Rotation
+        rotationSlider.addEventListener('input', (e) => {
+            currentRotation = parseInt(e.target.value);
+            updateRotationUI();
+            renderEditor();
+        });
+
+        function updateRotationUI() {
+            rotationSlider.value = currentRotation;
+            rotationValue.textContent = currentRotation + '°';
+        }
+
+        function renderEditor() {
+            if (!originalImageObject) return;
+
+            const angleRad = currentRotation * Math.PI / 180;
+            const sin = Math.abs(Math.sin(angleRad));
+            const cos = Math.abs(Math.cos(angleRad));
+
+            // Calculate new bounding box size
+            const width = originalImageObject.naturalWidth;
+            const height = originalImageObject.naturalHeight;
+            const newWidth = width * cos + height * sin;
+            const newHeight = width * sin + height * cos;
+
+            // Set canvas internal size
+            cropCanvas.width = newWidth;
+            cropCanvas.height = newHeight;
+
+            const ctx = cropCanvas.getContext('2d');
+
+            // Clear & Draw
+            ctx.clearRect(0, 0, newWidth, newHeight);
+            ctx.save();
+            ctx.translate(newWidth / 2, newHeight / 2);
+            ctx.rotate(angleRad);
+            ctx.drawImage(originalImageObject, -width / 2, -height / 2);
+            ctx.restore();
+        }
+
+        // Crop functionality (Perspective / 4-Point)
+        const cropContainer = document.getElementById('cropContainer');
+
+        // Prevent clicks in crop area from triggering file upload
+        cropContainer.addEventListener('click', (e) => {
+            e.stopPropagation();
+        });
+        cropContainer.addEventListener('mousedown', (e) => {
+            e.stopPropagation();
+        });
+
+        const cropArea = document.getElementById('cropArea');
+        const cropPolygon = document.getElementById('cropPolygon');
+        const cropActions = document.getElementById('cropActions');
+        const resetCropBtn = document.getElementById('resetCropBtn');
+        const applyCropBtn = document.getElementById('applyCropBtn');
+
+        let originalFile = null;
+        let originalImageData = null;
+        let cropPoints = []; // [{x,y}, {x,y}, {x,y}, {x,y}]
+        let isDragging = false;
+        let activeHandleIndex = null;
+
+        // KTP aspect ratio: 85.6mm x 53.98mm = ~1.586
+        const KTP_ASPECT_RATIO = 85.6 / 53.98;
+        // KK aspect ratio (A4 Landscape): 297mm x 210mm = ~1.414
+        const KK_ASPECT_RATIO = 297 / 210;
+
+        function initCropArea() {
+            // Match cropArea size/pos to canvas size/pos
+            cropArea.style.left = cropCanvas.offsetLeft + 'px';
+            cropArea.style.top = cropCanvas.offsetTop + 'px';
+            cropArea.style.width = cropCanvas.offsetWidth + 'px';
+            cropArea.style.height = cropCanvas.offsetHeight + 'px';
+
+            const w = cropCanvas.offsetWidth;
+            const h = cropCanvas.offsetHeight;
+
+            // Initialize default box (Centered Rectangle with appropriate ratio)
+            const targetRatio = currentDocType === 'kk' ? KK_ASPECT_RATIO : KTP_ASPECT_RATIO;
+
+            let boxW, boxH;
+            if (w / h > targetRatio) {
+                boxH = h * 0.7;
+                boxW = boxH * targetRatio;
+            } else {
+                boxW = w * 0.7;
+                boxH = boxW / targetRatio;
+            }
+
+            const cx = w / 2;
+            const cy = h / 2;
+
+            // 0: TL, 1: TR, 2: BR, 3: BL
+            cropPoints = [
+                { x: cx - boxW / 2, y: cy - boxH / 2 },
+                { x: cx + boxW / 2, y: cy - boxH / 2 },
+                { x: cx + boxW / 2, y: cy + boxH / 2 },
+                { x: cx - boxW / 2, y: cy + boxH / 2 }
+            ];
+
+            updateCropVisuals();
+            cropArea.style.display = 'block';
+        }
+
+        function updateCropVisuals() {
+            // Update Handles
+            const handles = cropArea.querySelectorAll('.crop-handle');
+            cropPoints.forEach((p, i) => {
+                if (handles[i]) {
+                    handles[i].style.left = p.x + 'px';
+                    handles[i].style.top = p.y + 'px';
+                }
+            });
+
+            // Update Polygon
+            // SVG points format: x1,y1 x2,y2 ...
+            const pointsStr = cropPoints.map(p => `${p.x},${p.y}`).join(' ');
+            cropPolygon.setAttribute('points', pointsStr);
+        }
+
+        // Handle Dragging
+        const handles = cropArea.querySelectorAll('.crop-handle');
+        handles.forEach(handle => {
+            handle.addEventListener('mousedown', (e) => {
+                e.stopPropagation();
+                activeHandleIndex = parseInt(handle.dataset.index);
+                isDragging = true;
+            });
+            handle.addEventListener('touchstart', (e) => {
+                e.stopPropagation();
+                activeHandleIndex = parseInt(handle.dataset.index);
+                isDragging = true;
+            }, { passive: false });
+        });
+
+        document.addEventListener('mousemove', handleDragMove);
+        document.addEventListener('touchmove', handleDragMove, { passive: false });
+        document.addEventListener('mouseup', handleDragEnd);
+        document.addEventListener('touchend', handleDragEnd);
+
+        // Also allow updating cropArea size on window resize (since canvas might resize)
+        window.addEventListener('resize', () => {
+            if (cropCanvas.offsetParent) {
+                cropArea.style.left = cropCanvas.offsetLeft + 'px';
+                cropArea.style.top = cropCanvas.offsetTop + 'px';
+                cropArea.style.width = cropCanvas.offsetWidth + 'px';
+                cropArea.style.height = cropCanvas.offsetHeight + 'px';
+            }
+        });
+
+        function getEventPos(e) {
+            const rect = cropArea.getBoundingClientRect();
+            let clientX, clientY;
+
+            if (e.touches && e.touches.length > 0) {
+                clientX = e.touches[0].clientX;
+                clientY = e.touches[0].clientY;
+            } else {
+                clientX = e.clientX;
+                clientY = e.clientY;
+            }
+
+            return {
+                x: clientX - rect.left,
+                y: clientY - rect.top
+            };
+        }
+
+        function handleDragMove(e) {
+            if (!isDragging || activeHandleIndex === null) return;
+            e.preventDefault();
+
+            const pos = getEventPos(e);
+
+            // Constrain to bounds
+            // Allow slightly outside? No, keep inside for UI sanity
+            const x = Math.max(0, Math.min(pos.x, cropArea.offsetWidth));
+            const y = Math.max(0, Math.min(pos.y, cropArea.offsetHeight));
+
+            cropPoints[activeHandleIndex] = { x, y };
+            updateCropVisuals();
+        }
+
+        function handleDragEnd() {
+            isDragging = false;
+            activeHandleIndex = null;
+        }
+
+        // Hook rotation to reset crop
+        rotationSlider.addEventListener('input', () => {
+            // We need to re-init crop area because canvas content changed
+            initCropArea();
+        });
+
+        // Reset crop button
+        resetCropBtn.addEventListener('click', () => {
+            currentRotation = 0;
+            updateRotationUI();
+
+            if (originalImageObject) {
+                renderEditor();
+                cropCanvas.style.display = 'block';
+                preview.style.display = 'none';
+                setTimeout(initCropArea, 50);
+                selectedFile = originalFile;
+            }
+        });
+
+        // Apply crop button (Perspective Transform API)
+        applyCropBtn.addEventListener('click', async () => {
+            if (!originalImageObject) return;
+
+            applyCropBtn.disabled = true;
+            applyCropBtn.textContent = '⏳ Memproses...';
+
+            try {
+                // 1. Get current Canvas blob (Rotated image)
+                const canvasBlob = await new Promise(resolve => cropCanvas.toBlob(resolve, 'image/jpeg', 0.95));
+
+                // 2. Calculate points relative to internal canvas resolution
+                const scaleX = cropCanvas.width / cropCanvas.offsetWidth;
+                const scaleY = cropCanvas.height / cropCanvas.offsetHeight;
+
+                // Map points to actual image coordinates
+                // Note: The backend expects [TL, TR, BR, BL] which is how cropPoints is ordered [0,1,2,3]
+                const realPoints = cropPoints.map(p => [p.x * scaleX, p.y * scaleY]);
+
+                // 3. Send to server
+                const formData = new FormData();
+                formData.append('image', canvasBlob, 'rotated_temp.jpg');
+                formData.append('image', canvasBlob, 'rotated_temp.jpg');
+                formData.append('points', JSON.stringify(realPoints));
+                formData.append('doc_type', currentDocType);
+
+                const response = await fetch('/api/transform-perspective', {
+                    method: 'POST',
+                    body: formData
+                });
+
+                const result = await response.json();
+
+                if (result.success) {
+                    // Update preview with transformed image
+                    preview.src = result.image_url;
+                    preview.style.display = 'block';
+                    cropCanvas.style.display = 'none';
+                    cropArea.style.display = 'none';
+
+                    // Fetch blob to update selectedFile
+                    const resBlob = await fetch(result.image_url).then(r => r.blob());
+                    selectedFile = new File([resBlob], result.filename || 'perspective_cropped.jpg', { type: 'image/jpeg' });
+
+                } else {
+                    showError('Gagal transformasi: ' + result.error);
+                }
+
+            } catch (error) {
+                console.error('Crop error:', error);
+                showError('Gagal memproses crop: ' + error.message);
+            } finally {
+                applyCropBtn.disabled = false;
+                applyCropBtn.textContent = '✂️ Terapkan Crop';
+            }
+        });
+
         // Process button
         processBtn.addEventListener('click', async () => {
             if (!selectedFile) return;
@@ -224,7 +612,7 @@
             try {
                 const formData = new FormData();
                 formData.append('file', selectedFile);
-                formData.append('doc_type', docType);
+                formData.append('doc_type', currentDocType);
 
                 const response = await fetch('/upload', {
                     method: 'POST',
@@ -235,6 +623,10 @@
 
                 if (result.success) {
                     extractedData = result.data;
+                    currentDocType = result.doc_type || 'ktp';
+                    if (result.validation) {
+                        validationResult = result.validation;
+                    }
                     displayResults(result);
                     hideError();
                 } else {
@@ -526,24 +918,61 @@
             rawTextSection.style.display = isVisible ? 'none' : 'block';
         });
 
-        // Copy to clipboard
+        // Copy to clipboard (Formatted Text for Word)
         document.getElementById('copyBtn').addEventListener('click', () => {
             if (extractedData) {
-                navigator.clipboard.writeText(JSON.stringify(extractedData, null, 2))
-                    .then(() => alert('Data berhasil disalin!'));
+                // Format as Key: Value text
+                const excludeKeys = ['raw_text', 'image_path', 'id', 'created_at', 'updated_at'];
+                const text = Object.entries(extractedData)
+                    .filter(([k, v]) => !excludeKeys.includes(k) && v)
+                    .map(([k, v]) => {
+                        const label = k.replace(/_/g, ' ').toUpperCase();
+                        return `${label}: ${v}`;
+                    })
+                    .join('\n');
+
+                navigator.clipboard.writeText(text)
+                    .then(() => alert('Data berhasil disalin (Format Teks)! Bisa dipaste di Word/Notepad.'));
             }
         });
 
-        // Export JSON
-        document.getElementById('exportBtn').addEventListener('click', () => {
-            if (extractedData) {
-                const blob = new Blob([JSON.stringify(extractedData, null, 2)], { type: 'application/json' });
-                const url = URL.createObjectURL(blob);
-                const a = document.createElement('a');
-                a.href = url;
-                a.download = `${docType}_data.json`;
-                a.click();
-                URL.revokeObjectURL(url);
+        // Export Excel (Real .xlsx via Backend)
+        document.getElementById('exportBtn').addEventListener('click', async () => {
+            if (!extractedData) return;
+
+            const btn = document.getElementById('exportBtn');
+            const originalText = btn.innerHTML;
+            btn.innerHTML = '⏳...';
+            btn.disabled = true;
+
+            try {
+                const res = await fetch('/api/export-excel', {
+                    method: 'POST',
+                    headers: { 'Content-Type': 'application/json' },
+                    body: JSON.stringify(extractedData)
+                });
+
+                if (res.ok) {
+                    const blob = await res.blob();
+                    const url = window.URL.createObjectURL(blob);
+                    const a = document.createElement('a');
+                    a.href = url;
+                    const filename = extractedData.nik ? `Data_KTP_${extractedData.nik}.xlsx` : 'Data_KTP.xlsx';
+                    a.download = filename;
+                    document.body.appendChild(a);
+                    a.click();
+                    document.body.removeChild(a);
+                    window.URL.revokeObjectURL(url);
+                } else {
+                    const err = await res.json();
+                    alert('Gagal export excel: ' + (err.error || 'Unknown error'));
+                }
+            } catch (e) {
+                console.error(e);
+                alert('Error export excel.');
+            } finally {
+                btn.innerHTML = originalText;
+                btn.disabled = false;
             }
         });
 
@@ -556,14 +985,371 @@
             errorSection.style.display = 'none';
         }
 
-        // Reset on new file selection
-        preview.addEventListener('click', () => {
-            preview.style.display = 'none';
-            dropzone.querySelector('.dropzone-content').style.display = 'flex';
-            selectedFile = null;
-            processBtn.disabled = true;
-            fileInput.value = '';
+        // Save KTP Button
+        const saveBtn = document.getElementById('saveBtn');
+        saveBtn.addEventListener('click', async () => {
+            if (!extractedData || !selectedFile) return;
+
+            saveBtn.disabled = true;
+            saveBtn.innerHTML = '⏳ Menyimpan...';
+
+            // Determine endpoint based on currentDocType
+            const endpoint = currentDocType === 'kk' ? '/api/save-kk' : '/api/save-ktp';
+
+            try {
+                // Use selectedFile directly (it is already cropped/rotated by Apply Crop)
+                const formData = new FormData();
+                // Rename file based on type just for neatness
+                const filename = currentDocType === 'kk' ? 'kk_saved.jpg' : 'ktp_saved.jpg';
+                formData.append('image', selectedFile, filename);
+                formData.append('data', JSON.stringify(extractedData));
+
+                // Send to server
+                const response = await fetch(endpoint, {
+                    method: 'POST',
+                    body: formData
+                });
+
+                const result = await response.json();
+
+                if (result.success) {
+                    const docName = currentDocType === 'kk' ? 'Kartu Keluarga' : 'KTP';
+                    alert(`Data ${docName} berhasil disimpan!`);
+                    saveBtn.innerHTML = '✅ Tersimpan';
+                } else {
+                    alert('Gagal menyimpan: ' + result.error);
+                    saveBtn.innerHTML = '💾 Simpan';
+                    saveBtn.disabled = false;
+                }
+            } catch (error) {
+                alert('Terjadi kesalahan: ' + error.message);
+                saveBtn.innerHTML = '💾 Simpan';
+                saveBtn.disabled = false;
+            }
         });
+
+        // Print functionality
+        const printBtn = document.getElementById('printBtn');
+
+        printBtn.addEventListener('click', () => {
+            const printArea = document.getElementById('printArea');
+            console.log('Print button clicked');
+
+            // Determine source: preview image or crop canvas?
+            const isPreviewVisible = preview.style.display !== 'none' && preview.getAttribute('src') !== '#' && preview.src;
+            const isCanvasVisible = cropCanvas.style.display !== 'none';
+
+            if (!isPreviewVisible) {
+                if (isCanvasVisible) {
+                    if (!confirm('Gambar belum diterapkan (Apply). Cetak tampilan canvas saat ini?')) return;
+                    // Use canvas data
+                    const img = new Image();
+                    img.src = cropCanvas.toDataURL('image/jpeg', 0.95);
+                    img.className = currentDocType === 'kk' ? 'a4-print-size' : 'ktp-print-size';
+                    printArea.innerHTML = '';
+                    printArea.appendChild(img);
+                    // Canvas data is instant, no onload needed usually, but to be safe:
+                    setTimeout(() => window.print(), 100);
+                    return;
+                }
+                alert('Tidak ada gambar KTP untuk dicetak! Silakan upload atau pilih dari arsip.');
+                return;
+            }
+
+            printArea.innerHTML = '';
+            const img = new Image();
+            // Use current preview src
+            img.src = preview.src;
+            img.className = currentDocType === 'kk' ? 'a4-print-size' : 'ktp-print-size';
+            printArea.appendChild(img);
+
+            // Robust print trigger
+            img.onload = () => {
+                // Short delay to ensure rendering
+                setTimeout(() => window.print(), 100);
+            };
+
+            // Fallback if image cached or instant
+            if (img.complete) {
+                img.onload();
+            }
+
+            // Error handling
+            img.onerror = () => {
+                alert('Gagal memuat gambar untuk dicetak.');
+            };
+        });
+
+        // Download functionality
+        const downloadBtn = document.getElementById('downloadBtn');
+        downloadBtn.addEventListener('click', () => {
+            // Check if preview is valid
+            const isPreviewVisible = preview.style.display !== 'none' && preview.getAttribute('src') !== '#' && preview.src;
+
+            if (!isPreviewVisible) {
+                if (cropCanvas.style.display !== 'none') {
+                    // Allow download canvas
+                    const link = document.createElement('a');
+                    link.download = 'ktp_scan_raw.jpg';
+                    link.href = cropCanvas.toDataURL('image/jpeg', 0.95);
+                    link.click();
+                    return;
+                }
+                alert('Tidak ada gambar untuk diunduh');
+                return;
+            }
+
+            const link = document.createElement('a');
+            link.href = preview.src;
+
+            // Construct filename from Extracted Data if available
+            let filename = 'ktp_scan.jpg';
+            const nikInput = document.getElementById('field-nik'); // ID format might be different, let's check render logic
+            // renderEditableFields generates identifiers? No, extractedData global var is safest.
+            if (typeof extractedData !== 'undefined' && extractedData.nik) {
+                filename = `KTP_${extractedData.nik}.jpg`;
+            } else {
+                // Try getting from DOM inputs if extractedData not set
+                const domNik = document.querySelector('input[data-key="nik"]');
+                if (domNik && domNik.value) filename = `KTP_${domNik.value}.jpg`;
+            }
+
+            link.download = filename;
+            document.body.appendChild(link);
+            link.click();
+            document.body.removeChild(link);
+        });
+
+        // Archive Modal Logic
+        const archiveBtn = document.getElementById('archiveBtn');
+        const archiveModal = document.getElementById('archiveModal');
+        const closeModalBtn = document.getElementById('closeModalBtn');
+        const archiveList = document.getElementById('archiveList');
+        const archiveLoading = document.getElementById('archiveLoading');
+        const archiveEmpty = document.getElementById('archiveEmpty');
+
+        // Login Logic Vars
+        const loginModal = document.getElementById('loginModal');
+        const loginUser = document.getElementById('loginUser');
+        const loginPass = document.getElementById('loginPass');
+        const submitLoginBtn = document.getElementById('submitLoginBtn');
+        const loginError = document.getElementById('loginError');
+        const closeLoginBtn = document.getElementById('closeLoginBtn');
+
+        // Check Auth Helper
+        async function checkAuth() {
+            try {
+                const res = await fetch('/api/check-auth');
+                if (res.ok) {
+                    const data = await res.json();
+                    return data.authenticated;
+                }
+                return false;
+            } catch (e) { return false; }
+        }
+
+        // Archive Button Logic
+        // const archiveBtn = document.getElementById('archiveBtn'); // Already declared
+        const archiveKKBtn = document.getElementById('archiveKKBtn');
+
+        async function openArchive(type) {
+            currentArchiveType = type;
+            const title = type === 'kk' ? 'Arsip Kartu Keluarga' : 'Arsip KTP';
+            document.querySelector('#archiveModal h2').textContent = '📂 ' + title;
+
+            if (await checkAuth()) {
+                archiveModal.style.display = 'block';
+                loadArchive();
+            } else {
+                loginModal.style.display = 'block';
+                // Reset login form
+                loginPass.value = '';
+                loginError.style.display = 'none';
+                loginPass.focus();
+            }
+        }
+
+        archiveBtn.addEventListener('click', () => openArchive('ktp'));
+        if (archiveKKBtn) {
+            archiveKKBtn.addEventListener('click', () => openArchive('kk'));
+        }
+
+        // Submit Login Logic
+        submitLoginBtn.addEventListener('click', async () => {
+            const user = loginUser.value;
+            const pass = loginPass.value;
+
+            if (!user || !pass) {
+                loginError.textContent = 'Username dan Password harus diisi';
+                loginError.style.display = 'block';
+                return;
+            }
+
+            loginError.style.display = 'none';
+            submitLoginBtn.disabled = true;
+            submitLoginBtn.innerHTML = 'Memeriksa...';
+
+            try {
+                const res = await fetch('/api/login', {
+                    method: 'POST',
+                    headers: { 'Content-Type': 'application/json' },
+                    body: JSON.stringify({ username: user, password: pass })
+                });
+                const data = await res.json();
+
+                if (data.success) {
+                    loginModal.style.display = 'none';
+                    archiveModal.style.display = 'block';
+                    loadArchive();
+                } else {
+                    loginError.textContent = data.error || 'Login gagal';
+                    loginError.style.display = 'block';
+                }
+            } catch (e) {
+                loginError.textContent = 'Gagal terhubung ke server';
+                loginError.style.display = 'block';
+            } finally {
+                submitLoginBtn.disabled = false;
+                submitLoginBtn.innerHTML = 'Masuk';
+            }
+        });
+
+        // Handle Enter Key
+        loginPass.addEventListener('keypress', (e) => {
+            if (e.key === 'Enter') submitLoginBtn.click();
+        });
+
+        // Close Login Modal
+        closeLoginBtn.addEventListener('click', () => { loginModal.style.display = 'none'; });
+        // Close Archive Modal (Restored)
+        closeModalBtn.addEventListener('click', () => { archiveModal.style.display = 'none'; });
+
+        // Window click handler for both modals
+        window.addEventListener('click', (e) => {
+            if (e.target === archiveModal) archiveModal.style.display = 'none';
+            if (e.target === loginModal) loginModal.style.display = 'none';
+        });
+
+        async function loadArchive() {
+            archiveList.innerHTML = '';
+            archiveLoading.style.display = 'block';
+            archiveEmpty.style.display = 'none';
+
+            try {
+                const endpoint = `/api/${currentArchiveType}-archive?per_page=50`;
+                const response = await fetch(endpoint);
+                const result = await response.json();
+
+                archiveLoading.style.display = 'none';
+
+                if (result.success && result.data.length > 0) {
+                    renderArchiveList(result.data);
+                } else {
+                    archiveEmpty.style.display = 'block';
+                }
+            } catch (error) {
+                console.error('Archive load error:', error);
+                archiveLoading.innerHTML = '❌ Gagal memuat data';
+            }
+        }
+
+        function renderArchiveList(records) {
+            const imgPrefix = currentArchiveType === 'kk' ? '/kk-images/' : '/ktp-images/';
+
+            records.forEach(record => {
+                const card = document.createElement('div');
+                card.className = 'archive-card';
+
+                const date = new Date(record.created_at).toLocaleDateString('id-ID', {
+                    year: 'numeric', month: 'short', day: 'numeric', hour: '2-digit', minute: '2-digit'
+                });
+
+                const title = currentArchiveType === 'kk' ? (record.kepala_keluarga || 'Tanpa Nama') : (record.nama || 'Tanpa Nama');
+                const idVal = currentArchiveType === 'kk' ? (record.no_kk || '-') : (record.nik || '-');
+
+                card.innerHTML = `
+                    <div class="archive-card-img">
+                        <img src="${imgPrefix}${record.image_path}" alt="${title}" loading="lazy">
+                    </div>
+                    <div class="archive-card-content">
+                        <h3>${title}</h3>
+                        <div class="archive-card-meta">
+                            <span class="nik">${idVal}</span>
+                            <span class="date">${date}</span>
+                        </div>
+                        <div class="archive-card-actions" style="display:flex; gap:0.5rem;">
+                            <button class="view-btn" onclick='viewArchiveDetail(${JSON.stringify(record).replace(/'/g, "&#39;")})' style="flex:1;">👁️ Lihat</button>
+                            <a href="${imgPrefix}${record.image_path}" download="${currentArchiveType.toUpperCase()}_${idVal}.jpg" class="view-btn" style="flex:1; text-align:center; text-decoration:none; display:flex; align-items:center; justify-content:center;">⬇️</a>
+                        </div>
+                    </div>
+                `;
+                archiveList.appendChild(card);
+            });
+        }
+
+        // Global function to view detail from archive
+        window.viewArchiveDetail = (record) => {
+            extractedData = record;
+            currentDocType = currentArchiveType; // Sync type so Save works correctly
+
+            // 1. Display results
+            displayResults({ data: record, raw_text: record.raw_text || '' });
+
+            // 2. Load image into preview
+            if (record.image_path) {
+                const imgPrefix = currentArchiveType === 'kk' ? '/kk-images/' : '/ktp-images/';
+                const imgUrl = `${imgPrefix}${record.image_path}`;
+                preview.src = imgUrl;
+
+                // Set originalImageData to allow re-cropping or re-saving if needed
+                fetch(imgUrl)
+                    .then(res => res.blob())
+                    .then(blob => {
+                        const reader = new FileReader();
+                        reader.onloadend = () => {
+                            originalImageData = reader.result;
+                            selectedFile = new File([blob], record.image_path, { type: blob.type });
+
+                            // Initialize Image Object for rotation editor
+                            const img = new Image();
+                            img.onload = () => {
+                                originalImageObject = img;
+                                // We don't necessarily need to renderEditor() immediately if we are in "View" mode
+                                // But having it ready is good for "Reset"
+                            };
+                            img.src = reader.result;
+                        };
+                        reader.readAsDataURL(blob);
+                    });
+
+                // Show preview area (static image result), hide dropzone/canvas
+                preview.style.display = 'block';
+                cropCanvas.style.display = 'none';
+                dropzone.querySelector('.dropzone-content').style.display = 'none';
+
+                // Setup crop ui visibility
+                cropContainer.style.display = 'block';
+                cropArea.style.display = 'none';
+                cropActions.style.display = 'flex';
+
+                // Reset rotation slider for viewing (since we are viewing already cropped/straightened result)
+                currentRotation = 0;
+                updateRotationUI();
+            }
+
+            archiveModal.style.display = 'none';
+        };
+
+        // Reload Button
+        document.getElementById('reloadBtn').addEventListener('click', () => {
+            window.location.reload();
+        });
+    </script>
+    <!-- Print Area: Use visibility hidden/height 0 to ensure images load but are invisible on screen -->
+    <div id="printArea" style="visibility: hidden; height: 0; overflow: hidden; position: absolute; z-index: -1;"></div>
+
+    <script>
+        // ... (this comment is just marker, main script is above)
     </script>
 </body>