Merge pull request #1 from software-students-spring2024/Jacklyn22

Original codes added and new html pages added.

docker-compose.yaml

@@ -0,0 +1,34 @@
+version: '3.8'
+
+services:
+  web-app:
+    build:
+      context: ./web-app
+      dockerfile: ./Dockerfile
+    ports:
+      - "10000:5000"
+    env_file:
+      - .env
+    depends_on:
+      - db
+
+  machine-learning-client:
+    build:
+      context: ./machine-learning-client
+      dockerfile: ./Dockerfile
+    ports:
+      - "5002:5002"
+    env_file:
+      - .env
+    depends_on:
+      - db
+
+
+  db:
+    image: mongo
+    ports:
+      - "27017:27017"
+    volumes:
+      - ./data:/data/db
+
+

machine-learning-client/Dockerfile

@@ -0,0 +1,18 @@
+# in Docker, it is common to base a new image on a previously-created image
+# Use an official Python runtime image as a parent image to base this image on
+FROM python:3
+# Set the working directory within the image to /app
+WORKDIR /main
+# the ADD command is how you add files from your local machine into a Docker image
+# Copy the current directory contents into the container at /app
+ADD . /main
+# Install any needed packages specified in requirements.txt
+# in Python, a requirements.txt file is a way of indicating dependencies in a way that the package manager, pip, can understand
+RUN pip install --trusted-host pypi.python.org -r requirements.txt
+# by default Docker containers are closed off to the external world
+# Make port 80 available to the world outside this container
+EXPOSE 5002
+# Define an environment variable... this will be available to programs running inside the container
+ENV NAME World
+# Run app.py when the container launches
+CMD ["python", "main.py"]

machine-learning-client/Pipfile

@@ -0,0 +1,13 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+pylint = "*"
+black = "*"
+
+[dev-packages]
+
+[requires]
+python_version = "3.10"

machine-learning-client/main.py

@@ -0,0 +1,123 @@
+import os
+from flask import Flask, request, jsonify
+import requests
+import pymongo
+from pymongo import MongoClient
+import json
+from dotenv import load_dotenv
+from bson import ObjectId
+
+import logging
+
+logging.basicConfig(level=logging.DEBUG)
+logger = logging.getLogger(__name__)
+
+# Use receipt-OCR.py to get response1.json
+# (can only do this a couple times an hour with the test API key)
+
+# Load response1.json
+with open("response1.json", "r") as f:
+    data = json.load(f)
+
+print('Receipt Keys:', data['receipts'][0].keys())
+items = data['receipts'][0]['items']
+print()
+print(f"Your purchase at {data['receipts'][0]['merchant_name']}")
+
+for item in items:
+    print(f"{item['description']} - {data['receipts'][0]['currency']} {item['amount']}")
+print("-" * 20)
+print(f"Subtotal: {data['receipts'][0]['currency']} {data['receipts'][0]['subtotal']}")
+print(f"Tax: {data['receipts'][0]['currency']} {data['receipts'][0]['tax']}")
+print("-" * 20)
+print(f"Total: {data['receipts'][0]['currency']} {data['receipts'][0]['total']}")
+# print(data['receipts'])
+
+
+# load credentials and configuration options from .env file
+# if you do not yet have a file named .env, make one based on the templatpip e in env.example
+load_dotenv()  # take environment variables from .env.
+
+# instantiate the app
+app = Flask(__name__)
+app.secret_key = 'a_unique_and_secret_key'
+# # turn on debugging if in development mode
+if os.getenv("FLASK_ENV", "development") == "development":
+#     # turn on debugging, if in development
+    app.debug = True  # debug mnode
+
+# connect to the database
+cxn = pymongo.MongoClient(os.getenv("MONGO_URI"))
+db = cxn[os.getenv("MONGO_DBNAME")]  # store a reference to the database
+
+@app.route('/predict', methods=['POST'])
+def pretdict_endpoint():
+    # Get the image data from the request
+    request_data = request.get_json()  # Extract JSON data from the request
+    if 'Object_ID' not in request_data:
+        return jsonify({'error': 'Object_ID not found in request data'}), 400
+
+    Object_ID = ObjectId(request_data['Object_ID']) 
+    logger.debug('OBJECT_ID MESSAGE:', Object_ID)
+    #image = db.receipts.find_one({"_id": Object_ID})['image']
+
+    # Here, you would add the code to perform OCR on the image
+    # For now, let's assume you have a function called perform_ocr that does this
+
+    # Uncomment next line to perform OCR
+    data = perform_ocr(Object_ID)
+    #data = json.load(open("response1.json", "r"))
+
+    # Connect to your collection (replace 'mycollection' with your collection name)
+    collection = db['receipts']
+
+    # Prepare the data to be inserted into the database
+    receipt = data['receipts'][0]
+    receipt_data = {
+        'receipt_name': receipt['merchant_name'],
+        'currency': receipt['currency'],
+        'items': [{'description': item['description'], 'amount': item['amount']} for item in receipt['items']],
+        'total': receipt['total'],
+        'tax': receipt['tax'],
+        'tip': receipt['tip'],
+        'subtotal': receipt['subtotal'],
+    }
+    logger.debug(receipt_data)
+
+    # Update the document with given ObjectId
+    collection.update_one({'_id': Object_ID}, {'$set': receipt_data})
+    inserted_id = Object_ID
+
+    # Return the inserted_id as a JSON response
+    return jsonify({'_id': str(inserted_id)})
+
+def perform_ocr(Object_ID):
+    logger.debug("starting perform_ocr function...") # debug
+    url = "https://ocr.asprise.com/api/v1/receipt"
+    image_data = db.receipts.find_one({"_id": Object_ID})['image']
+    file_path = f"receipt_{Object_ID}.jpg"  # Set the file path to save the image
+    logger.debug("file path: %s", file_path) # debug
+    with open(file_path, "wb") as f:
+        f.write(image_data)
+    file_path = file_path.replace('\x00', '')  # Remove any null bytes from the file path
+
+
+    # Get response (can only do this a couple times with the test API key)
+    res = requests.post(url, 
+                        data = {
+                            'api_key': 'TEST',
+                            'recognizer': 'auto',
+                            'ref_no': 'ocr_python_123'
+                        },
+
+                        files = {
+                            'file': open(file_path, "rb")
+                        })
+
+    with open("response.json", "w") as f:
+        f.write(res.text)
+
+    return res.json()
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5002)  # Run the app

machine-learning-client/requirements.txt

@@ -0,0 +1,6 @@
+pymongo
+pylint
+black
+requests
+Flask
+python-dotenv

machine-learning-client/response1.json

@@ -0,0 +1,166 @@
+{
+    "ocr_type" : "receipts",
+    "request_id" : "P_72.80.97.228_luxbmz9s_bz6",
+    "ref_no" : "ocr_python_123",
+    "file_name" : "RestaurantReceipt1.png",
+    "request_received_on" : 1712965847825,
+    "success" : true,
+    "image_width" : 812,
+    "image_height" : 1354,
+    "image_rotation" : 0,
+    "recognition_completed_on" : 1712965848215,
+    "receipts" : [ {
+      "merchant_name" : "HARBOR LANE CAFE",
+      "merchant_address" : "HARBOR LANE CAFE",
+      "merchant_phone" : null,
+      "merchant_website" : null,
+      "merchant_tax_reg_no" : null,
+      "merchant_company_reg_no" : null,
+      "region" : null,
+      "mall" : null,
+      "country" : "US",
+      "state" : "IL",
+      "city" : "CHICAGO",
+      "receipt_no" : null,
+      "date" : "2019-11-20",
+      "time" : null,
+      "items" : [ {
+        "amount" : 14.98,
+        "category" : null,
+        "description" : "Tacos Del Mal Shrimp",
+        "flags" : "",
+        "qty" : 1,
+        "remarks" : null,
+        "tags" : null,
+        "unitPrice" : null
+      }, {
+        "amount" : 12.50,
+        "category" : null,
+        "description" : "Especial Salad Chicken",
+        "flags" : "",
+        "qty" : 1,
+        "remarks" : null,
+        "tags" : null,
+        "unitPrice" : null
+      }, {
+        "amount" : 1.99,
+        "category" : null,
+        "description" : "Fountain Beverage",
+        "flags" : "",
+        "qty" : 1,
+        "remarks" : null,
+        "tags" : null,
+        "unitPrice" : null
+      } ],
+      "currency" : "USD",
+      "total" : 31.39,
+      "subtotal" : 29.47,
+      "tax" : 1.92,
+      "service_charge" : null,
+      "tip" : null,
+      "payment_method" : null,
+      "payment_details" : null,
+      "credit_card_type" : null,
+      "credit_card_number" : null,
+      "ocr_text" : " HARBOR LANE CAFE\n 3941 GREEN OAKS BLVD\n CHICAGO, IL\n      SALE\n 11/20/2019    11:05 AM\n BATCH #: 01A2A\n APPR #: 34362\n TRACE #: 9\n VISA 3483\n 1 Tacos Del Mal Shrimp     $14.98\n 1 Especial Salad Chicken   $12.50\n 1 Fountain Beverage         $1.99\n SUBTOTAL:   $29.47\n TAX:        $1.92\n TOTAL:      $31.39\n TIP:\n TOTAL:\n      APPROVED\n      THANK YOU\n      CUSTOMER COPY",
+      "ocr_confidence" : 98.50,
+      "width" : 596,
+      "height" : 1111,
+      "avg_char_width" : 16.9954,
+      "avg_line_height" : 28.3333,
+      "conf_amount" : 83,
+      "source_locations" : {
+        "date" : [ [ {
+          "x" : 46,
+          "y" : 216
+        }, {
+          "x" : 240,
+          "y" : 216
+        }, {
+          "x" : 240,
+          "y" : 246
+        }, {
+          "x" : 46,
+          "y" : 246
+        } ] ],
+        "total" : [ [ {
+          "x" : 275,
+          "y" : 696
+        }, {
+          "x" : 381,
+          "y" : 696
+        }, {
+          "x" : 381,
+          "y" : 726
+        }, {
+          "x" : 275,
+          "y" : 726
+        } ] ],
+        "subtotal" : [ [ {
+          "x" : 276,
+          "y" : 615
+        }, {
+          "x" : 384,
+          "y" : 615
+        }, {
+          "x" : 384,
+          "y" : 646
+        }, {
+          "x" : 276,
+          "y" : 646
+        } ] ],
+        "merchant_name" : [ [ {
+          "x" : 40,
+          "y" : 13
+        }, {
+          "x" : 357,
+          "y" : 15
+        }, {
+          "x" : 357,
+          "y" : 47
+        }, {
+          "x" : 40,
+          "y" : 46
+        } ] ],
+        "doc" : [ [ {
+          "x" : 24,
+          "y" : -40
+        }, {
+          "x" : 679,
+          "y" : -40
+        }, {
+          "x" : 679,
+          "y" : 1181
+        }, {
+          "x" : 24,
+          "y" : 1181
+        } ] ],
+        "tax" : [ [ {
+          "x" : 277,
+          "y" : 656
+        }, {
+          "x" : 361,
+          "y" : 656
+        }, {
+          "x" : 361,
+          "y" : 685
+        }, {
+          "x" : 277,
+          "y" : 685
+        } ] ],
+        "merchant_address" : [ [ {
+          "x" : 24,
+          "y" : 11
+        }, {
+          "x" : 373,
+          "y" : 13
+        }, {
+          "x" : 373,
+          "y" : 49
+        }, {
+          "x" : 24,
+          "y" : 48
+        } ] ]
+      }
+    } ]
+  }

web-app/Dockerfile

@@ -0,0 +1,12 @@
+# docs: https://hub.docker.com/_/python
+FROM python:3.8-slim-buster
+
+WORKDIR /web_app
+
+COPY requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 10000
+CMD [ "python3", "-m" , "flask", "run", "--host=0.0.0.0"]

web-app/Pipfile

@@ -0,0 +1,13 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+pylint = "*"
+black = "*"
+
+[dev-packages]
+
+[requires]
+python_version = "3.10"