app.py

from flask import Flask, request, jsonify
import sys
import os
import subprocess
import json

# Suppress PaddleOCR verbose logging
os.environ['PADDLEOCR_LOG_LEVEL'] = 'ERROR'
os.environ['QT_QPA_PLATFORM'] = 'offscreen'
os.environ['DISPLAY'] = ':99'

def run_extraction_script(script_name, document_url):
    """Generic function to run OCR extraction scripts"""
    try:
        cmd = [sys.executable, script_name, document_url]
        result = subprocess.run(
            cmd, 
            capture_output=True, 
            text=True, 
            timeout=300,
            cwd=os.getcwd()
        )
        
        if result.returncode != 0:
            return {
                'success': False,
                'error': f'Script failed with return code {result.returncode}',
                'stderr': result.stderr,
                'stdout': result.stdout
            }
        
        # Parse JSON output
        try:
            output_str = result.stdout.strip()
            
            # Try direct parse first
            try:
                return json.loads(output_str)
            except json.JSONDecodeError:
                # Find the last JSON object in output
                lines = output_str.split('\n')
                json_lines = [line.strip() for line in lines if line.strip().startswith('{')]
                
                if json_lines:
                    return json.loads(json_lines[-1])
                
                # Try extracting JSON from the output
                start_idx = output_str.rfind('{')
                end_idx = output_str.rfind('}')
                if start_idx != -1 and end_idx != -1 and end_idx >= start_idx:
                    return json.loads(output_str[start_idx:end_idx+1])
                
                raise ValueError("No valid JSON found in output")
                
        except Exception as e:
            return {
                'success': False,
                'error': 'Invalid JSON output from script',
                'raw_output': result.stdout[:500],  # Limit output size
                'json_error': str(e)
            }
            
    except subprocess.TimeoutExpired:
        return {
            'success': False,
            'error': 'Script execution timed out after 5 minutes'
        }
    except Exception as e:
        return {
            'success': False,
            'error': f'Unexpected error: {str(e)}'
        }

# Create Flask app
app = Flask(__name__)

# Configure Flask for production
app.config['JSON_SORT_KEYS'] = False
app.config['JSONIFY_PRETTYPRINT_REGULAR'] = False

# ============================================================================
# PHILIPPINE ID OCR EXTRACTION ENDPOINTS
# ============================================================================

@app.route('/api/extract-national-id', methods=['POST'])
def api_extract_national_id():
    """Extract Philippine National ID details"""
    try:
        data = request.json
        document_url = data.get('document_url')
        
        if not document_url:
            return jsonify({'error': 'Missing document_url'}), 400
        
        result = run_extraction_script('extract_national_id.py', document_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

@app.route('/api/extract-drivers-license', methods=['POST'])
def api_extract_drivers_license():
    """Extract Philippine Driver's License details"""
    try:
        data = request.json
        document_url = data.get('document_url')
        
        if not document_url:
            return jsonify({'error': 'Missing document_url'}), 400
        
        result = run_extraction_script('extract_drivers_license.py', document_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

@app.route('/api/extract-prc', methods=['POST'])
def api_extract_prc():
    """Extract PRC ID details"""
    try:
        data = request.json
        document_url = data.get('document_url')
        
        if not document_url:
            return jsonify({'error': 'Missing document_url'}), 400
        
        result = run_extraction_script('extract_prc.py', document_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

@app.route('/api/extract-umid', methods=['POST'])
def api_extract_umid():
    """Extract UMID details"""
    try:
        data = request.json
        document_url = data.get('document_url')
        
        if not document_url:
            return jsonify({'error': 'Missing document_url'}), 400
        
        result = run_extraction_script('extract_umid.py', document_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

@app.route('/api/extract-sss', methods=['POST'])
def api_extract_sss():
    """Extract SSS ID details"""
    try:
        data = request.json
        document_url = data.get('document_url')
        
        if not document_url:
            return jsonify({'error': 'Missing document_url'}), 400
        
        result = run_extraction_script('extract_sss.py', document_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

@app.route('/api/extract-passport', methods=['POST'])
def api_extract_passport():
    """Extract Philippine Passport details"""
    try:
        data = request.json
        document_url = data.get('document_url')
        
        if not document_url:
            return jsonify({'error': 'Missing document_url'}), 400
        
        result = run_extraction_script('extract_passport.py', document_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

@app.route('/api/extract-postal', methods=['POST'])
def api_extract_postal():
    """Extract Postal ID details"""
    try:
        data = request.json
        document_url = data.get('document_url')
        
        if not document_url:
            return jsonify({'error': 'Missing document_url'}), 400
        
        result = run_extraction_script('extract_postal.py', document_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

@app.route('/api/extract-phic', methods=['POST'])
def api_extract_phic():
    """Extract PhilHealth ID details"""
    try:
        data = request.json
        document_url = data.get('document_url')
        
        if not document_url:
            return jsonify({'error': 'Missing document_url'}), 400
        
        result = run_extraction_script('extract_phic.py', document_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

# ============================================================================
# CLEARANCE & CERTIFICATE OCR EXTRACTION ENDPOINTS
# ============================================================================

@app.route('/api/extract-nbi', methods=['POST'])
def api_extract_nbi():
    """Extract NBI Clearance details"""
    try:
        data = request.json
        document_url = data.get('document_url')
        
        if not document_url:
            return jsonify({'error': 'Missing document_url'}), 400
        
        result = run_extraction_script('extract_nbi_ocr.py', document_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

@app.route('/api/extract-police-clearance', methods=['POST'])
def api_extract_police_clearance():
    """Extract Police Clearance details"""
    try:
        data = request.json
        document_url = data.get('document_url')
        
        if not document_url:
            return jsonify({'error': 'Missing document_url'}), 400
        
        result = run_extraction_script('extract_police_ocr.py', document_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

@app.route('/api/extract-tesda', methods=['POST'])
def api_extract_tesda():
    """Extract TESDA Certificate details"""
    try:
        data = request.json
        document_url = data.get('document_url')
        
        if not document_url:
            return jsonify({'error': 'Missing document_url'}), 400
        
        result = run_extraction_script('extract_tesda_ocr.py', document_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

# ============================================================================
# DOCUMENT ANALYSIS ENDPOINT
# ============================================================================

@app.route('/api/analyze-document', methods=['POST'])
def api_analyze_document():
    """Analyze and identify document type"""
    try:
        data = request.json
        image_url = data.get('image_url')
        
        if not image_url:
            return jsonify({'error': 'Missing image_url'}), 400
        
        result = run_extraction_script('analyze_document.py', image_url)
        return jsonify(result)
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

@app.route('/api/analyze-documents', methods=['POST'])
def api_analyze_documents():
    """Analyze multiple documents for tampering detection and metadata"""
    try:
        data = request.json
        image_urls = data.get('image_urls', [])
        
        if not image_urls:
            return jsonify({'error': 'Missing image_urls array'}), 400
        
        if len(image_urls) > 3:
            return jsonify({'error': 'Maximum 3 documents allowed'}), 400
        
        # Run analyze_documents.py with multiple URLs
        cmd = [sys.executable, 'analyze_documents.py'] + image_urls
        result = subprocess.run(
            cmd,
            capture_output=True,
            text=True,
            timeout=300,
            cwd=os.getcwd()
        )
        
        if result.returncode != 0:
            return jsonify({
                'success': False,
                'error': f'Script failed with return code {result.returncode}',
                'stderr': result.stderr
            })
        
        # Parse JSON output
        try:
            output_str = result.stdout.strip()
            return jsonify(json.loads(output_str))
        except Exception as e:
            return jsonify({
                'success': False,
                'error': 'Invalid JSON output from script',
                'raw_output': result.stdout[:500]
            })
        
    except Exception as e:
        return jsonify({'success': False, 'error': str(e)}), 500

# ============================================================================
# UTILITY ENDPOINTS
# ============================================================================

@app.route('/health', methods=['GET'])
def health_check():
    """Health check endpoint"""
    return jsonify({
        'status': 'healthy', 
        'service': 'handyhome-ocr-api',
        'version': '1.0.0'
    })

@app.route('/', methods=['GET'])
def index():
    """API documentation endpoint"""
    return jsonify({
        'service': 'HandyHome OCR Extraction API',
        'version': '1.0.0',
        'description': 'Philippine ID and Document OCR Extraction using PaddleOCR',
        'endpoints': {
            'Philippine IDs': {
                'POST /api/extract-national-id': {
                    'description': 'Extract Philippine National ID details',
                    'fields': ['id_number', 'full_name', 'birth_date']
                },
                'POST /api/extract-drivers-license': {
                    'description': 'Extract Driver\'s License details',
                    'fields': ['license_number', 'full_name', 'birth_date', 'address']
                },
                'POST /api/extract-prc': {
                    'description': 'Extract PRC ID details',
                    'fields': ['prc_number', 'full_name', 'profession', 'valid_until']
                },
                'POST /api/extract-umid': {
                    'description': 'Extract UMID details',
                    'fields': ['crn', 'full_name', 'birth_date']
                },
                'POST /api/extract-sss': {
                    'description': 'Extract SSS ID details',
                    'fields': ['sss_number', 'full_name', 'birth_date']
                },
                'POST /api/extract-passport': {
                    'description': 'Extract Philippine Passport details',
                    'fields': ['passport_number', 'surname', 'given_names', 'birth_date']
                },
                'POST /api/extract-postal': {
                    'description': 'Extract Postal ID details',
                    'fields': ['prn', 'full_name', 'address', 'birth_date']
                },
                'POST /api/extract-phic': {
                    'description': 'Extract PhilHealth ID details',
                    'fields': ['id_number', 'full_name', 'birth_date', 'sex', 'address']
                }
            },
            'Clearances & Certificates': {
                'POST /api/extract-nbi': {
                    'description': 'Extract NBI Clearance details',
                    'fields': ['id_number', 'full_name', 'birth_date']
                },
                'POST /api/extract-police-clearance': {
                    'description': 'Extract Police Clearance details',
                    'fields': ['id_number', 'full_name', 'address', 'birth_date', 'status']
                },
                'POST /api/extract-tesda': {
                    'description': 'Extract TESDA Certificate details',
                    'fields': ['registry_number', 'full_name', 'qualification', 'date_issued']
                }
            },
            'Document Analysis': {
                'POST /api/analyze-document': {
                    'description': 'Analyze and identify document type from image',
                    'fields': ['document_type', 'confidence']
                },
                'POST /api/analyze-documents': {
                    'description': 'Analyze multiple documents for tampering detection and metadata (max 3)',
                    'fields': ['tampering_results', 'metadata_results'],
                    'body': {'image_urls': 'array of image URLs (max 3)'}
                }
            },
            'Utility': {
                'GET /health': 'Health check endpoint',
                'GET /': 'This API documentation'
            }
        },
        'request_format': {
            'body': {
                'document_url': 'string (required) - URL of the document image to process'
            },
            'example': {
                'document_url': 'https://example.com/national_id.jpg'
            }
        },
        'response_format': {
            'success': 'boolean - Whether extraction was successful',
            'extracted_fields': 'object - Extracted data fields',
            'error': 'string - Error message if failed'
        }
    })

@app.route('/api/routes', methods=['GET'])
def list_routes():
    """List all available API routes"""
    routes = []
    for rule in app.url_map.iter_rules():
        if rule.endpoint != 'static':
            methods = sorted(rule.methods - {'HEAD', 'OPTIONS'})
            routes.append({
                'endpoint': rule.endpoint,
                'methods': methods,
                'path': rule.rule
            })
    
    routes.sort(key=lambda x: x['path'])
    return jsonify({
        'total_routes': len(routes),
        'routes': routes
    })

# Launch Flask app
if __name__ == '__main__':
    port = int(os.environ.get('PORT', 7860))
    app.run(host='0.0.0.0', port=port, debug=False)