File size: 5,578 Bytes
51dad1c
c30f358
 
 
51dad1c
 
 
 
 
c30f358
 
 
 
 
 
 
51dad1c
c30f358
51dad1c
 
 
 
 
 
 
 
 
 
 
 
c30f358
 
 
 
 
 
 
 
 
 
 
51dad1c
c30f358
 
 
 
 
 
 
 
51dad1c
 
c30f358
 
 
51dad1c
c30f358
51dad1c
c30f358
 
 
 
 
 
 
51dad1c
c30f358
 
 
 
 
 
 
 
51dad1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c30f358
 
 
 
 
 
51dad1c
c30f358
 
51dad1c
c30f358
 
 
 
 
 
 
 
51dad1c
c30f358
51dad1c
 
c30f358
 
 
51dad1c
c30f358
 
 
51dad1c
c30f358
 
 
 
 
 
 
 
51dad1c
 
 
c30f358
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
# routes.py
from flask import Blueprint, jsonify, request
import io
from app.utils import OCRModel
import logging

# إعداد التسجيل
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

main = Blueprint('main', __name__)
ocr_model = OCRModel()

# تحديد امتدادات الملفات المسموح بها
ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}

# قائمة الحساسيات المعروفة
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):
    """التحقق من صحة امتداد الملف"""
    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS

def find_allergens(text, user_allergens):
    """البحث عن الحساسيات في النص"""
    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
                    # تخزين موقع الكلمة في النص
                    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:
        # 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 = 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)
        
        # معالجة الصورة
        extracted_text = ocr_model.process_image(file_stream)
        logger.info(f"Extracted text: {extracted_text}")
        
        # البحث عن الحساسيات
        found_allergens, allergen_details, allergen_locations = find_allergens(extracted_text, user_allergens)
        
        # تحضير الرد
        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"  # تحديث هذا التاريخ عند تحديث القائمة
    })