Update app/routes.py

app/routes.py

@@ -1,140 +1,112 @@
-# routes.py
-from flask import Blueprint, jsonify, request
-import io
-from app.utils import OCRModel
-import logging
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-main = Blueprint('main', __name__)
-ocr_model = OCRModel()
-
-ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}
-
-KNOWN_ALLERGENS = {
-    'gluten': ['wheat', 'barley', 'rye', 'oats', 'gluten', 'flour', 'bread', 'pasta'],
-    'dairy': ['milk', 'yogurt', 'cheese', 'lactose', 'cream', 'butter', 'whey'],
-    'nuts': ['nuts', 'peanuts', 'almonds', 'walnuts', 'cashews', 'pistachios'],
-    'eggs': ['eggs', 'egg', 'albumin', 'mayonnaise'],
-    'soy': ['soy', 'soybeans', 'tofu', 'edamame'],
-    'fish': ['fish', 'salmon', 'tuna', 'cod', 'tilapia'],
-    'shellfish': ['shellfish', 'shrimp', 'crab', 'lobster', 'oyster', 'mussels'],
-    'sesame': ['sesame', 'tahini'],
-    'mustard': ['mustard'],
-    'celery': ['celery'],
-    'lupin': ['lupin'],
-    'sulfites': ['sulfites', 'sulphites']
-}
-
-def allowed_file(filename):
-    """Validate file extension"""
-    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
-
-def find_allergens(text, user_allergens):
-    """Finding Sensitivities in the Text"""
-    text = text.lower()
-    found_allergens = set()
-    allergen_details = {}
-    allergen_locations = {}
-
-    for allergen in user_allergens:
-        allergen = allergen.strip().lower()
-        if allergen in KNOWN_ALLERGENS:
-            for variant in KNOWN_ALLERGENS[allergen]:
-                if variant.lower() in text:
-                    found_allergens.add(allergen)
-                    allergen_details[allergen] = variant
-                    # Store the location of the word in the text
-                    allergen_locations[allergen] = text.index(variant.lower())
-        elif allergen in text:
-            found_allergens.add(allergen)
-            allergen_details[allergen] = allergen
-            allergen_locations[allergen] = text.index(allergen)
-
-    return found_allergens, allergen_details, allergen_locations
-
-@main.route('/')
-def index():
-    return jsonify({
-        "message": "Welcome to the Text Recognition and Sensitivity Checking Service",
-        "endpoints": {
-            "/api/ocr": "POST - Image analysis and sensitivity testing",
-            "/api/allergens": "GET - List of known allergens"
-        },
-        "supported_formats": list(ALLOWED_EXTENSIONS),
-        "known_allergens": list(KNOWN_ALLERGENS.keys())
-    })
-
-@main.route('/api/ocr', methods=['POST'])
-def process_image():
-    try:
-        # Check if file exists
-        if 'file' not in request.files:
-            logger.warning("No file uploaded")
-            return jsonify({"error": "No file uploaded"}), 400
-        
-        # Check the list of allergies
-        if 'allergens' not in request.form:
-            logger.warning("Allergens not specified")
-            return jsonify({"error": "Allergens not specified"}), 400
-        
-        file = request.files['file']
-        if file.filename == '':
-            logger.warning("No file selected")
-            return jsonify({"error": "No file selected"}), 400
-        
-        # Check file type
-        if not allowed_file(file.filename):
-            logger.warning(f"Invalid file type: {file.filename}")
-            return jsonify({
-                "error": "File type not supported",
-                "supported_formats": list(ALLOWED_EXTENSIONS)
-            }), 400
-
-        # Prepare a list of allergies.
-        user_allergens = request.form['allergens'].split(',')
-        logger.info(f"Processing image for allergens: {user_allergens}")
-        
-        # Read image
-        file_bytes = file.read()
-        file_stream = io.BytesIO(file_bytes)
-        
-        # Processing image
-        extracted_text = ocr_model.process_image(file_stream)
-        logger.info(f"Extracted text: {extracted_text}")
-        
-        # Searching for allergies
-        found_allergens, allergen_details, allergen_locations = find_allergens(extracted_text, user_allergens)
-        
-        # Response
-        response = {
-            "success": True,
-            "extracted_text": extracted_text,
-            "analysis": {
-                "found_allergens": list(found_allergens),
-                "allergen_details": allergen_details,
-                "allergen_locations": allergen_locations,
-                "has_allergens": len(found_allergens) > 0,
-                "warning": "⚠️ Warning: Allergens found!" if found_allergens else "✅ No allergens found",
-                "severity": "high" if len(found_allergens) > 0 else "none"
-            }
-        }
-        
-        logger.info(f"Analysis completed successfully: {found_allergens}")
-        return jsonify(response)
-        
-    except Exception as e:
-        logger.error(f"Error processing request: {str(e)}", exc_info=True)
-        return jsonify({
-            "error": "An error occurred while processing the image.",
-            "details": str(e)
-        }), 500
-
-@main.route('/api/allergens', methods=['GET'])
-def get_known_allergens():
-    return jsonify({
-        "allergens": KNOWN_ALLERGENS,
-        "total_count": len(KNOWN_ALLERGENS),
-        "last_updated": "2024-03-24"  # Update this date when the list is updated.
+from flask import Blueprint, jsonify, request, current_app
+import io
+import pandas as pd
+from app.utils import OCRModel, AllergyAnalyzer
+import logging
+import os
+import requests
+from PIL import Image
+import nltk
+nltk.download('punkt', quiet=True)
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+main = Blueprint('main', __name__)
+ocr_model = OCRModel()
+allergy_analyzer = AllergyAnalyzer(current_app.config['ALLERGY_DATASET_PATH'])
+
+ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}
+
+def allowed_file(filename):
+    """Validate file extension"""
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+@main.route('/')
+def index():
+    return jsonify({
+        "message": "Welcome to the Advanced OCR and Allergy Detection Service",
+        "endpoints": {
+            "/api/ocr": "POST - Image analysis and allergy detection",
+            "/api/allergens": "GET - List of known allergens from dataset"
+        },
+        "supported_formats": list(ALLOWED_EXTENSIONS),
+        "features": [
+            "OCR text extraction",
+            "Allergy detection from database",
+            "AI-powered allergy risk assessment"
+        ]
+    })
+
+@main.route('/api/ocr', methods=['POST'])
+def process_image():
+    try:
+        # التحقق من وجود الملف
+        if 'file' not in request.files:
+            logger.warning("No file uploaded")
+            return jsonify({"error": "No file uploaded"}), 400
+        
+        # التحقق من وجود قائمة الحساسيات
+        if 'allergens' not in request.form:
+            logger.warning("Allergens not specified")
+            return jsonify({"error": "Allergens not specified"}), 400
+        
+        file = request.files['file']
+        if file.filename == '':
+            logger.warning("No file selected")
+            return jsonify({"error": "No file selected"}), 400
+        
+        # التحقق من نوع الملف
+        if not allowed_file(file.filename):
+            logger.warning(f"Invalid file type: {file.filename}")
+            return jsonify({
+                "error": "File type not supported",
+                "supported_formats": list(ALLOWED_EXTENSIONS)
+            }), 400
+
+        # تحضير قائمة الحساسيات
+        user_allergens = [a.strip().lower() for a in request.form['allergens'].split(',')]
+        logger.info(f"Processing image for allergens: {user_allergens}")
+        
+        # قراءة الصورة
+        file_bytes = file.read()
+        file_stream = io.BytesIO(file_bytes)
+        image = Image.open(file_stream)
+        
+        # معالجة الصورة واستخراج النص
+        extracted_text = ocr_model.process_image(image)
+        logger.info(f"Extracted text: {extracted_text}")
+        
+        # تحليل الحساسيات
+        analysis_results = allergy_analyzer.analyze_text(extracted_text, user_allergens)
+        
+        # إعداد الرد
+        response = {
+            "success": True,
+            "extracted_text": extracted_text,
+            "analysis": analysis_results,
+            "warnings": {
+                "has_allergens": len(analysis_results['detected_allergens']) > 0,
+                "message": "⚠️ Warning: Allergens found!" if analysis_results['detected_allergens'] else "✅ No allergens found",
+                "severity": "high" if analysis_results['detected_allergens'] else "none"
+            }
+        }
+        
+        logger.info(f"Analysis completed successfully")
+        return jsonify(response)
+        
+    except Exception as e:
+        logger.error(f"Error processing request: {str(e)}", exc_info=True)
+        return jsonify({
+            "error": "An error occurred while processing the image.",
+            "details": str(e)
+        }), 500
+
+@main.route('/api/allergens', methods=['GET'])
+def get_known_allergens():
+    allergens = allergy_analyzer.get_allergen_list()
+    return jsonify({
+        "allergens": allergens,
+        "total_count": len(allergens),
+        "last_updated": "2024-03-24"
     })