Workflows updated.

.env-sample

@@ -5,4 +5,4 @@ FLASK_ENV=development
 FLASK_PORT=10000
 GITHUB_REPO=https://github.com/your-repository-url # unnecessary for basic operation
 GITHUB_SECRET=your_github_secret # unnecessary for basic operation
-OCR_API_KEY=your_ocr_api_key # replace with your own OCR API key from mindee
+OCR_API_KEY=37bacde1f840522b837426aa425f62db # replace with your own OCR API key from mindee

machine-learning-client/.github/workflows/build-main.yml → .github/workflows/ml.yml

@@ -1,4 +1,4 @@
-name: CI / CD
+name: ML Service CI
 
 on:
   push:
@@ -13,15 +13,21 @@ jobs:
 
     steps:
     - uses: actions/checkout@v2
-    - name: Set up Python 3.8
+
+    - name: Set up Python
       uses: actions/setup-python@v2
       with:
-        python-version: 3.8
+        python-version: '3.8'
+
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-    - name: Run tests
+        pip install -r requirements.txt
+
+    - name: Test with pytest
       run: |
-        # Run your test commands
+        pip install pytest
         pytest
+
+    - name: Build Docker image
+      run: docker build . --file Dockerfile

.github/workflows/web-app.yml

@@ -0,0 +1,44 @@
+name: Web App CI
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.8'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+
+    - name: Lint with pylint
+      run: |
+        pip install pylint
+        pylint --load-plugins=pylint_flask *.py
+
+    - name: Run tests
+      run: |
+        pip install pytest flask_testing
+        pytest
+
+    - name: Build Docker image
+      run: docker build . --file Dockerfile
+
+    - name: Push Docker image
+      uses: docker/build-push-action@v2
+      with:
+        push: true
+        tags: user/app:latest

README.md

@@ -1,24 +1,3 @@
 # Final Project
 
-[link to our project](http://161.35.189.70:10000)
-
 An exercise to put to practice software development teamwork, subsystem communication, containers, deployment, and CI/CD pipelines. See [instructions](./instructions.md) for details.
-
-# Team Members
-
-[Edison Chen](https://github.com/ebc5802), [Natalie Wu](https://github.com/nawubyte), [Chelsea Li](https://github.com/qiaoxixi1), and [Jacklyn Hu](https://github.com/Jacklyn22)
-
-# How To Run ChequeMate
-
-First, rename the `env.sample` file to `.env` and make any necessary adjustments including changing the OCR API key to a valid API key from mindee.
-
-Next, from the root directory, run `docker compose up --build`
-
-Finally, open `http://localhost:10000/` in your local browser to view our web app.
-
-# Docker Images 
-- [Docker Hub repo](https://hub.docker.com/repository/docker/sennyy/5-final-project-spring-2024-best-swes/general)
-- [Machine Learning Client](https://hub.docker.com/layers/sennyy/5-final-project-spring-2024-best-swes/latest/images/sha256-8e6f5dc5c28f64ee5f8deb15ed03da005c09c8933a5b3f9f6d3aca934774eb17?context=repo)
-- [Webapp](https://hub.docker.com/layers/sennyy/5-final-project-spring-2024-best-swes/webapp/images/sha256-a2177768a9c1b34b5995fa325076f42fb24d56aeb087b8824f203efdae94cd96?context=repo)
-
-

data/WiredTiger.lock

@@ -1,2 +1 @@
 WiredTiger lock file
-

data/WiredTiger.turtle

@@ -3,4 +3,4 @@ WiredTiger 11.2.0: (November 10, 2022)
 WiredTiger version
 major=11,minor=2,patch=0
 file:WiredTiger.wt
-access_pattern_hint=none,allocation_size=4KB,app_metadata=,assert=(commit_timestamp=none,durable_timestamp=none,read_timestamp=none,write_timestamp=off),block_allocation=best,block_compressor=,cache_resident=false,checksum=on,collator=,columns=,dictionary=0,encryption=(keyid=,name=),format=btree,huffman_key=,huffman_value=,id=0,ignore_in_memory_cache_size=false,internal_item_max=0,internal_key_max=0,internal_key_truncate=true,internal_page_max=4KB,key_format=S,key_gap=10,leaf_item_max=0,leaf_key_max=0,leaf_page_max=32KB,leaf_value_max=0,log=(enabled=true),memory_page_image_max=0,memory_page_max=5MB,os_cache_dirty_max=0,os_cache_max=0,prefix_compression=false,prefix_compression_min=4,readonly=false,split_deepen_min_child=0,split_deepen_per_child=0,split_pct=90,tiered_object=false,tiered_storage=(auth_token=,bucket=,bucket_prefix=,cache_directory=,local_retention=300,name=,object_target_size=0),value_format=S,verbose=[],version=(major=1,minor=1),write_timestamp_usage=none,checkpoint=(WiredTigerCheckpoint.12=(addr="018381e4d2658b3d8481e4922db30e8581e497411dd2808080e2bfc0e22fc0",order=12,time=1714578634,size=24576,newest_start_durable_ts=0,oldest_start_ts=0,newest_txn=4,newest_stop_durable_ts=0,newest_stop_ts=-1,newest_stop_txn=-11,prepare=0,write_gen=32,run_write_gen=28)),checkpoint_backup_info=,checkpoint_lsn=(4,4864)
+access_pattern_hint=none,allocation_size=4KB,app_metadata=,assert=(commit_timestamp=none,durable_timestamp=none,read_timestamp=none,write_timestamp=off),block_allocation=best,block_compressor=,cache_resident=false,checksum=on,collator=,columns=,dictionary=0,encryption=(keyid=,name=),format=btree,huffman_key=,huffman_value=,id=0,ignore_in_memory_cache_size=false,internal_item_max=0,internal_key_max=0,internal_key_truncate=true,internal_page_max=4KB,key_format=S,key_gap=10,leaf_item_max=0,leaf_key_max=0,leaf_page_max=32KB,leaf_value_max=0,log=(enabled=true),memory_page_image_max=0,memory_page_max=5MB,os_cache_dirty_max=0,os_cache_max=0,prefix_compression=false,prefix_compression_min=4,readonly=false,split_deepen_min_child=0,split_deepen_per_child=0,split_pct=90,tiered_object=false,tiered_storage=(auth_token=,bucket=,bucket_prefix=,cache_directory=,local_retention=300,name=,object_target_size=0),value_format=S,verbose=[],version=(major=1,minor=1),write_timestamp_usage=none,checkpoint=(WiredTigerCheckpoint.59=(addr="018381e42c9ad31c8481e467d0d3748581e46d920d70808080e2efc0e22fc0",order=59,time=1714592877,size=24576,newest_start_durable_ts=0,oldest_start_ts=0,newest_txn=4,newest_stop_durable_ts=0,newest_stop_ts=-1,newest_stop_txn=-11,prepare=0,write_gen=165,run_write_gen=161)),checkpoint_backup_info=,checkpoint_lsn=(12,4864)

machine-learning-client/main.py

@@ -7,7 +7,6 @@
 from dotenv import load_dotenv
 from bson import ObjectId
 from mindee import Client, PredictResponse, product # To access mindee OCR API
-import uuid
 
 import logging
 
@@ -83,7 +82,7 @@ def pretdict_endpoint():
     receipt_data = {
         'receipt_name': receipt['supplier_name']['raw_value'],
         'currency': receipt['locale']['currency'],
-        'items': [{'description': item['description'], 'amount': item['amount'], '_id': str(uuid.uuid4())} for item in receipt['items']],# generate a unique ID for each item
+        'items': [{'description': item['description'], 'amount': item['total_amount'], 'quantity': item['quantity']} for item in receipt['line_items']],
         'total': receipt['total_amount']['value'],
         'tax': receipt['total_tax']['value'],
         'tip': receipt['tip']['value'],
@@ -122,58 +121,5 @@ def perform_ocr(Object_ID):
         print("response.text: %s", response.text)
         return response.json()
 
-# def perform_ocr(Object_ID):
-#     logging.debug("starting perform_ocr function with mindee api...") # debug
-#     # Init a new client
-#     api_key = os.getenv("OCR_API_KEY")  # Get the API key from environment variable
-#     mindee_client = Client(api_key)
-
-#     # Fetch the image data from the database
-#     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
-#     logging.debug("file path: %s", file_path) # debug
-
-#     # Save the image data to a file
-#     with open(file_path, "wb") as f:
-#         f.write(image_data)
-
-#     # Load the file
-#     input_doc = mindee_client.source_from_path(file_path)
-
-#     # Parse the file with the Mindee API
-#     result: PredictResponse = mindee_client.parse(product.ReceiptV5, input_doc)
-#     logging.debug("result: %s", result.document) # debug
-
-#     # Return the result as a JSON response
-#     return jsonify(result.document)
-
-# def perform_ocr_old_version(Object_ID):
-#     logging.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
-#     logging.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

@@ -4,5 +4,4 @@ black
 requests
 Flask
 python-dotenv
-mindee
-uuid
+mindee