merge files to iteration 2 branch

.github/workflows/ci_be.yml

@@ -7,10 +7,13 @@ on:
       - 'be_repo/**'
 
 permissions:
-  contents: read
+  contents: write
+  checks: write
+  pull-requests: write
 
 jobs:
-  build:
+  live-test:
+    name: Live Test
     runs-on: ubuntu-latest
 
     defaults:
@@ -19,15 +22,15 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
-      - name: Set up Python 3.10
+      - name: Set up Python 3.9
         uses: actions/setup-python@v3
         with:
-          python-version: "3.10"
+          python-version: "3.9"
 
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install flake8 pytest
+          pip install flake8 pytest pytest-cov
           if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
 
       - name: Lint with flake8
@@ -37,6 +40,31 @@ jobs:
           # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
           flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
 
-      - name: Test with pytest
+      - name: Build coverage file
         run: |
-          pytest --ignore=tests/test_e2e.py
+          pytest --ignore=tests/test_e2e.py --junitxml=pytest.xml \
+                 --cov=app --cov=modules \
+                 --cov-report=term-missing:skip-covered tests/ | tee pytest-coverage.txt
+
+      - name: Pytest coverage comment
+        id: coverageComment
+        uses: MishaKav/pytest-coverage-comment@main
+        with:
+          pytest-coverage-path: ./be_repo/pytest-coverage.txt
+          junitxml-path: ./be_repo/pytest.xml
+
+      - uses: actions/checkout@v3
+        with:
+          persist-credentials: false
+          fetch-depth: 0
+
+      - name: Update Readme with Coverage Html
+        run: |
+          sed -i '/<!-- Pytest Coverage Comment:Begin -->/,/<!-- Pytest Coverage Comment:End -->/c\<!-- Pytest Coverage Comment:Begin -->\n\${{ steps.coverageComment.outputs.coverageHtml }}\n<!-- Pytest Coverage Comment:End -->' ../README.md
+
+      - name: Commit & Push changes to Readme
+        uses: actions-js/push@master
+        with:
+          branch: dev/backend
+          message: Update coverage on Readme
+          github_token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/ci_e2e.yml

@@ -69,11 +69,11 @@ jobs:
         run: sudo apt purge google-chrome-stable
 
       - name: Installing all necessary packages
-        run: pip install chromedriver-autoinstaller selenium pyvirtualdisplay
+        run: pip install chromedriver-autoinstaller selenium pyvirtualdisplay pytest
       - name: Install xvfb
         run: sudo apt-get install xvfb
 
 
       - name: Run E2E tests
         run: |
-          python ./be_repo/tests/test_e2e.py
+          pytest ./be_repo/tests/test_e2e.py

README.md

@@ -1,17 +1,45 @@
 # CVCoach
 
 [![CI for FE](https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/actions/workflows/ci_fe.yml/badge.svg)](https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/actions/workflows/ci_fe.yml)
+[![CI for BE](https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/actions/workflows/ci_be.yml/badge.svg)](https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/actions/workflows/ci_be.yml)
+[![CI for E2E](https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/actions/workflows/ci_e2e.yml/badge.svg)](https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/actions/workflows/ci_e2e.yml)
+
 [![CD Pipeline](https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/actions/workflows/cd.yml/badge.svg)](https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/actions/workflows/cd.yml)
 [![Conventional Commits](https://img.shields.io/badge/Conventional%20Commits-1.0.0-%23FE5196?logo=conventionalcommits&logoColor=white)](https://conventionalcommits.org)
 
+<!-- Pytest Coverage Comment:Begin -->
+<a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/README.md"><img alt="Coverage" src="https://img.shields.io/badge/Coverage-69%25-yellow.svg" /></a><details><summary>Coverage Report </summary><table><tr><th>File</th><th>Stmts</th><th>Miss</th><th>Cover</th><th>Missing</th></tr><tbody><tr><td><a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py">app.py</a></td><td>85</td><td>36</td><td>58%</td><td><a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L34-L35">34&ndash;35</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L40-L48">40&ndash;48</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L52-L82">52&ndash;82</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L88">88</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L92">92</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L97">97</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L101">101</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L112">112</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L117">117</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L119">119</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L124">124</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L128">128</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/app.py#L136">136</a></td></tr><tr><td colspan="5"><b>modules</b></td></tr><tr><td>&nbsp; &nbsp;<a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/modules/evaluator.py">evaluator.py</a></td><td>56</td><td>14</td><td>75%</td><td><a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/modules/evaluator.py#L96-L97">96&ndash;97</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/modules/evaluator.py#L104-L122">104&ndash;122</a></td></tr><tr><td>&nbsp; &nbsp;<a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/modules/parser.py">parser.py</a></td><td>12</td><td>1</td><td>92%</td><td><a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/modules/parser.py#L20">20</a></td></tr><tr><td>&nbsp; &nbsp;<a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/modules/upload.py">upload.py</a></td><td>23</td><td>3</td><td>87%</td><td><a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/modules/upload.py#L23">23</a>, <a href="https://github.com/BUMETCS673/seprojects-cs673a2f24_team5/blob/main/modules/upload.py#L39-L40">39&ndash;40</a></td></tr><tr><td><b>TOTAL</b></td><td><b>176</b></td><td><b>54</b></td><td><b>69%</b></td><td>&nbsp;</td></tr></tbody></table></details>
+<!-- Pytest Coverage Comment:End -->
+
 <p>
   <!-- <img src="https://img.shields.io/github/license/BUMETCS673/seprojects-cs673a2f24_team5" alt="license"/> -->
   <img src="https://img.shields.io/docker/pulls/adamma1024/cvcoach_web" alt="docker-pull-count" />
+  <img src="https://img.shields.io/docker/pulls/adamma1024/cvcoach_be" alt="be-docker-pull-count" />
   <a href="https://img.shields.io/badge/price-free-ff69b4"><img alt="Price" src="https://img.shields.io/badge/price-free-ff69b4?style=flat-square" /></a>
 </p>
 
 This repository is a project for METCS673. This project focuses on using AI to automate and improve the process of resume evaluation and interview preparation. By incorporating Retrieval-Augmented Generation (RAG), we ensure that our application can provide more accurate, context-relevant reviews.
 
+## Steps to start up and test (For TA and professor)
+
+### If you'd like to clone our project (Recommended)
+
+```bash
+cd /rootPath
+docker compose up --build -d # Detach from the terminal
+```
+
+Then you can open your browser, and navigate to the <http://localhost:8081>
+
+### If you'd like to pull docker images
+
+We have two images separated for BE and FE.  
+
+1. adamma1024/cvcoach_be
+2. adamma1024/cvcoach_web
+
+Please make sure you've pulled all them on latest version (check it on Docker Hub) and start them correctly.
+
 ## Task Management
 
 As per github's task tracking flow is difficult to use, we decide to use [JIRA Boards](https://bu-cs673a2f24-team-5.atlassian.net/jira/software/projects/SCRUM/boards/1) to trace the progress and manage the risk. Click the hyperlink to check details.

be_repo/Dockerfile

@@ -1,5 +1,5 @@
 # Use an official Python runtime as a parent image
-FROM python:3.10-slim
+FROM python:3.9-slim
 
 # Set the workdir to avoid the "pytest Collecting hang"
 WORKDIR /app
@@ -12,7 +12,7 @@ RUN pip3 install -r requirements.txt
 
 # Install pytest for lab3(Even though it's ugly, from my perspective we should not add test codes in docker.)
 RUN pip3 install pytest
-RUN pytest
+RUN pytest --ignore=tests/test_e2e.py
 
 # Run the command to start the application
 CMD ["python3", "app.py"]

be_repo/app.py

@@ -23,7 +23,7 @@
     PERMANENT_SESSION_LIFETIME=timedelta(minutes=30),
 )
 
-GOOGLE_CLIENT_ID = ''
+GOOGLE_CLIENT_ID = '120137358324-l62fq2hlj9r31evvitg55rcl4rf21udd.apps.googleusercontent.com'
 
 # Test MongoDB connection
 try:
@@ -36,11 +36,11 @@
 
 
 @app.route('/upload', methods=['POST', 'OPTIONS'])
-def upload_resume(): 
+def upload_resume():
     if request.method == 'OPTIONS':
         # Allows the preflight request to succeed
         return jsonify({'status': 'OK'}), 200
-   
+
     user_id = request.form.get('user_id')
     if not user_id:
         return jsonify({"error": "No user ID provided."}), 400
@@ -52,15 +52,15 @@ def login():
     if request.method == 'OPTIONS':
         # Allows the preflight request to succeed
         return jsonify({'status': 'OK'}), 200
-    
+
     token = request.form.get('access_token')
     if not token:
         return jsonify({'status': 'error', 'message': 'ID token is missing'}), 400
-    
+
     try:
         # Verify the token with Google
         idinfo = id_token.verify_oauth2_token(token, google_requests.Request(), GOOGLE_CLIENT_ID)
-        
+
         if idinfo['aud'] != GOOGLE_CLIENT_ID:
             return jsonify({'status': 'error', 'message': 'Token audience mismatch'}), 400
 
@@ -70,12 +70,12 @@ def login():
         name = idinfo.get('name', 'No name available')
 
         # Create a session or JWT for the user
-        session.permanent = True 
+        session.permanent = True
         session['user'] = {'userid': userid, 'email': email, 'name': name}
 
         # Respond with success and optional user data
         return jsonify({'status': 'success', 'email': email, 'name': name}), 200
- 
+
     except ValueError as e:
         # Token verification failed
         print(f"Error verifying token: {str(e)}")
@@ -86,11 +86,11 @@ def resume_evaluate():
     if request.method == 'OPTIONS':
         # Allows the preflight request to succeed
         return jsonify({'status': 'OK'}), 200
-    
+
     user_id = request.form.get('user_id')
     if not user_id:
         return jsonify({"error": "No user ID provided."}), 400
-    
+
     # Load resume from database
     resume = resume_collection.find_one({"user_id": user_id})
     if not resume:
@@ -110,7 +110,7 @@ def resume_evaluate_with_JD():
     if request.method == 'OPTIONS':
         # Allows the preflight request to succeed
         return jsonify({'status': 'OK'}), 200
-    
+
     user_id = request.form.get('user_id')
     jd_text = request.form.get('jd_text')
     if not user_id:
@@ -133,4 +133,4 @@ def resume_evaluate_with_JD():
 
 
 if __name__ == '__main__':
-    app.run(host='0.0.0.0', debug=True, port=5000)
+    app.run(host='0.0.0.0', debug=True, port=5000)

be_repo/requirements.txt

@@ -8,4 +8,6 @@ qdrant_client==1.12.0
 tqdm==4.66.2
 selenium==4.26.1
 google-auth==2.36.0
-google-auth-oauthlib==1.2.1
+google-auth-oauthlib==1.2.1
+chromedriver-autoinstaller==0.6.4
+pyvirtualdisplay

be_repo/tests/test_e2e.py

@@ -1,101 +1,99 @@
+import pytest
+import os
+import time
 from selenium import webdriver
 import chromedriver_autoinstaller
 from selenium.webdriver.common.by import By
 from selenium.webdriver.common.keys import Keys
 from selenium.webdriver.support.ui import WebDriverWait
-from selenium.webdriver.chrome.options import Options
-from selenium.webdriver.chrome.service import Service
 from selenium.webdriver.support import expected_conditions as EC
-import time
-import os
 from pyvirtualdisplay import Display
 
 FRONTEND_URL = "http://localhost:3001"
+keywords = [
+    "Analysis Result",
+    "Consistency and Chronology",
+    "Education",
+    "Project and Work Experience",
+    "Resume Structure and Presentation",
+    "Skills and Certifications",
+    "Soft Skills"
+]
 
-display = Display(visible=0, size=(800, 800))
-display.start()
 
-chromedriver_autoinstaller.install()
+@pytest.fixture(scope="module")
+def driver():
+    # Start display
+    display = Display(visible=0, size=(800, 800))
+    display.start()
 
-chrome_options = webdriver.ChromeOptions()
-options = [
-    "--window-size=1200,1200",
-    "--ignore-certificate-errors"
-    "--headless",
-]
+    # Install and set up Chrome driver
+    chromedriver_autoinstaller.install()
+    chrome_options = webdriver.ChromeOptions()
+    chrome_options.add_argument("--window-size=1200,1200")
+    chrome_options.add_argument("--ignore-certificate-errors")
+    chrome_options.add_argument("--headless")
 
-for option in options:
-    chrome_options.add_argument(option)
+    driver = webdriver.Chrome(options=chrome_options)
+    yield driver
+    driver.quit()
+    display.stop()
 
-driver = webdriver.Chrome(options=chrome_options)
 
-driver.get(FRONTEND_URL)
-wait = WebDriverWait(driver, 20)
+@pytest.fixture
+def wait(driver):
+    return WebDriverWait(driver, 20)
 
-try:
-    wait.until(
-        lambda driver: driver.execute_script("return document.readyState") == "complete"
-    )
 
-    # Google login
-    # google_login_button = driver.find_element(By.CSS_SELECTOR, '[aria-labelledby="button-label"]')
-    # google_login_button.click()
+def test_resume_upload(driver, wait):
+    driver.get(FRONTEND_URL)
+    wait.until(lambda d: d.execute_script("return document.readyState") == "complete")
 
-    # Upload Resume
+    # Upload resume
     upload_div = driver.find_element(By.CSS_SELECTOR, "div[style*='cursor: pointer'][style*='display: flex']")
-    # upload_div.click()
-
     file_input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "input[type='file']")))
 
     file_path = os.path.join(os.path.dirname(__file__), 'test_resume.pdf')
     file_input.send_keys(file_path)
 
+    # Check for alert after upload
     alert = wait.until(EC.alert_is_present())
     alert_text = alert.text
     assert "Resume uploaded successfully" in alert_text
     alert.accept()
 
+
+def test_analyze_resume(driver, wait):
     # Analyze resume
     analyze_button = driver.find_element(By.CLASS_NAME, "cursor-pointer")
     analyze_button.click()
 
     submit_button = driver.find_element(By.CLASS_NAME, "mt-6")
     submit_button.click()
 
-    time.sleep(20)
-
-    keywords = [
-        "Analysis Result",
-        "Consistency and Chronology",
-        "Education",
-        "Project and Work Experience",
-        "Resume Structure and Presentation",
-        "Skills and Certifications",
-        "Soft Skills"
-    ]
+    time.sleep(20)  # Ensure analysis completes
 
     elements = driver.find_elements(By.CLASS_NAME, "font-bold")
     content_text = " ".join([element.text for element in elements])
     for keyword in keywords:
         count = content_text.count(keyword)
-        assert count == 1, f"'{keyword}' does not appear exactly twice in the content (found {count} times)"
+        assert count == 1, f"'{keyword}' does not appear exactly once in the content (found {count} times)"
 
+
+def test_analyze_resume_with_jd(driver, wait):
     # Analyze resume with JD
+    analyze_button = driver.find_element(By.CLASS_NAME, "cursor-pointer")
     analyze_button.click()
-    textarea = wait.until(
-        EC.presence_of_element_located((By.CSS_SELECTOR, "textarea.w-full.h-40.p-4.border-2"))
-    )
+    textarea = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "textarea.w-full.h-40.p-4.border-2")))
     textarea.send_keys("Sample job description text")
+
     submit_button = driver.find_element(By.CLASS_NAME, "mt-6")
     submit_button.click()
 
-    time.sleep(20)
+    time.sleep(20)  # Ensure analysis completes
 
     elements = driver.find_elements(By.CLASS_NAME, "font-bold")
     content_text = " ".join([element.text for element in elements])
     for keyword in keywords:
         count = content_text.count(keyword)
         assert count == 2, f"'{keyword}' does not appear exactly twice in the content (found {count} times)"
-
-finally:
-    driver.quit()