Merge pull request #5 from ryankert01/copilot/add-unit-tests-and-workflow

Add unit tests with modular Python structure and CI workflow

Author: ryankert01

.github/workflows/deploy.yml

@@ -1,19 +1,18 @@
-name: scrape rss from friends
+name: Deploy RSS Feed
 
 on:
   push:
     branches:
       - main
-  pull_request:
-    branches:
-      - main
   schedule:
     - cron: "0 10,22 * * *"
 
 jobs:
   build:
     runs-on: ubuntu-latest
-
+    permissions:
+      contents: write
+    
     steps:
       - uses: actions/checkout@v3
       - uses: actions/setup-python@v3

.github/workflows/test.yml

@@ -0,0 +1,45 @@
+name: Test
+
+on:
+  push:
+    branches:
+      - main
+      - develop
+  pull_request:
+    branches:
+      - main
+      - develop
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+      
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v3
+        with:
+          python-version: 3.11
+      
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install -r requirements-dev.txt
+      
+      - name: Run tests with pytest
+        run: |
+          pytest
+      
+      - name: Generate JSON (deploy test)
+        run: python src/main.py
+      
+      - name: Upload coverage reports
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-report
+          path: htmlcov/

.gitignore

@@ -1,3 +1,42 @@
 node_modules/
 dist/
-assets/
+assets/
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+venv/
+ENV/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+.hypothesis/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~

CONTRIBUTING.md

@@ -0,0 +1,71 @@
+# Contributing to RSS Friend
+
+Thank you for your interest in contributing to RSS Friend!
+
+## Development Setup
+
+1. Clone the repository:
+   ```bash
+   git clone https://github.com/ryankert01/rss-friend.git
+   cd rss-friend
+   ```
+
+2. Install dependencies:
+   ```bash
+   pip install -r requirements.txt
+   pip install -r requirements-dev.txt
+   ```
+
+## Running Tests
+
+Run all tests:
+```bash
+pytest
+```
+
+Run tests with coverage report:
+```bash
+pytest --cov=src --cov-report=html
+```
+
+Run specific test file:
+```bash
+pytest tests/test_rss_aggregator.py
+```
+
+Run specific test:
+```bash
+pytest tests/test_rss_aggregator.py::TestParseRssFeed::test_parses_valid_rss_feed
+```
+
+## Code Style
+
+- Follow PEP 8 style guidelines
+- Write descriptive docstrings for all functions
+- Add type hints where appropriate
+- Keep functions small and focused
+
+## Pull Request Process
+
+1. Create a feature branch from `main`
+2. Make your changes
+3. Add tests for new functionality
+4. Ensure all tests pass locally
+5. Update documentation as needed
+6. Submit a pull request
+
+The CI will automatically:
+- Run tests on Python 3.11
+- Generate coverage reports
+- Check code quality
+
+## Testing Guidelines
+
+- Write tests for all new functions
+- Test edge cases and error conditions
+- Use mocking for external dependencies (HTTP requests, etc.)
+- Aim for high code coverage (>90%)
+
+## Questions?
+
+Feel free to open an issue if you have questions or need help!

README.md

@@ -78,6 +78,7 @@ https://ryankert01.github.io/rss-friend/unsort.json
 
 ```zsh
 pip install -r requirements.txt
+pip install -r requirements-dev.txt  # For testing
 ```
 
 ### To generate JSON file
@@ -86,3 +87,38 @@ run the script to generate JSON file
 ```zsh
 python src/main.py
 ```
+
+### To run tests
+
+Run the unit tests with pytest:
+```zsh
+pytest
+```
+
+Run tests with coverage report:
+```zsh
+pytest --cov=src --cov-report=html
+```
+
+## Project Structure
+
+```
+rss-friend/
+├── src/
+│   ├── __init__.py
+│   ├── main.py              # Main entry point
+│   └── rss_aggregator.py    # Core RSS aggregation logic
+├── tests/
+│   ├── __init__.py
+│   └── test_rss_aggregator.py  # Unit tests
+├── _data/
+│   └── friends.json          # Configuration for RSS feeds
+├── requirements.txt          # Production dependencies
+├── requirements-dev.txt      # Development dependencies
+└── pytest.ini                # Pytest configuration
+```
+
+## CI/CD
+
+- **Test Workflow**: Runs automatically on pull requests and commits to main/develop branches
+- **Deploy Workflow**: Runs on push to main branch and scheduled twice daily (10:00 and 22:00 UTC)

pytest.ini

@@ -0,0 +1,12 @@
+[pytest]
+testpaths = tests
+python_files = test_*.py
+python_classes = Test*
+python_functions = test_*
+addopts = 
+    -v
+    --strict-markers
+    --tb=short
+    --cov=src
+    --cov-report=term-missing
+    --cov-report=html

requirements-dev.txt

@@ -0,0 +1,3 @@
+pytest>=7.4.0
+pytest-cov>=4.1.0
+pytest-mock>=3.11.1

src/__init__.py

@@ -0,0 +1,3 @@
+"""RSS Friend - Aggregates RSS feeds from friends' blogs."""
+
+__version__ = "1.0.0"

src/main.py

@@ -1,104 +1,21 @@
+"""Main entry point for RSS Friend aggregator."""
 
-import json
-import os
-import time
 from pathlib import Path
-import feedparser
-import requests
+from rss_aggregator import aggregate_rss_feeds
 
 # Constants
 ASSETS_DIR = Path(__file__).parent / 'assets'
 MAX_POSTS = 30
 FRIENDS_JSON_PATH = Path(__file__).parent.parent / '_data' / 'friends.json'
 
-def ensure_directory_exists(dir_path: Path):
-    """Ensures a directory exists, creating it if necessary."""
-    dir_path.mkdir(parents=True, exist_ok=True)
-
-def write_json_file(file_path: Path, data):
-    """Writes data to a JSON file."""
-    with open(file_path, 'w', encoding='utf-8') as f:
-        json.dump(data, f, ensure_ascii=False, indent=2)
-
-def parse_rss_feed(friend: dict) -> list:
-    """Parses a single RSS feed."""
-    friend_name = friend.get("title", "")
-    friend_link = friend.get("link", "")
-    rss_url = friend.get("feed", "")
-    posts = []
-
-    if not rss_url or not rss_url.startswith('http'):
-        print(f"Invalid RSS URL: {rss_url} (from: {friend_name})")
-        return []
 
+def main():
+    """Main entry point."""
     try:
-        # Use requests to fetch the feed with a timeout and user-agent
-        response = requests.get(rss_url, timeout=10, headers={'User-Agent': 'RSS Aggregator Bot'})
-        response.raise_for_status()  # Raise an exception for bad status codes
-        
-        # Parse the feed content using feedparser
-        feed = feedparser.parse(response.content)
-
-        for entry in feed.entries:
-            # Get date
-            date_tuple = entry.get("published_parsed") or entry.get("updated_parsed") or time.gmtime()
-            date = time.strftime('%Y-%m-%dT%H:%M:%SZ', date_tuple)
-
-            posts.append({
-                "title": entry.get("title", "No Title"),
-                "link": entry.get("link", friend_link),
-                "date": date,
-                "author": {
-                    "name": friend_name,
-                    "link": friend_link
-                }
-            })
-    except Exception as e:
-        print(f"Failed to parse RSS feed ({friend_name} - {rss_url}): {e}")
-
-    return posts
-
-def aggregate_rss_feeds():
-    """Aggregates RSS feeds from a list of friends."""
-    try:
-        ensure_directory_exists(ASSETS_DIR)
-
-        with open(FRIENDS_JSON_PATH, 'r', encoding='utf-8') as f:
-            friends = json.load(f)
-
-        if not isinstance(friends, list) or not friends:
-            print("No valid friends data found.")
-            return
-
-        all_posts = []
-        for friend in friends:
-            all_posts.extend(parse_rss_feed(friend))
-
-        write_json_file(ASSETS_DIR / 'unsort.json', all_posts)
-
-        # Sort posts by date (newest first)
-        sorted_posts = sorted(all_posts, key=lambda x: x['date'], reverse=True)[:MAX_POSTS]
-        write_json_file(ASSETS_DIR / 'sorted.json', sorted_posts)
-
-        # Format posts
-        formatted_posts = []
-        for post in sorted_posts:
-            t = time.strptime(post['date'], '%Y-%m-%dT%H:%M:%SZ')
-            formatted_posts.append({
-                "title": post["title"],
-                "link": post["link"],
-                "year": t.tm_year,
-                "month": t.tm_mon,
-                "day": t.tm_mday,
-                "author": post["author"]
-            })
-
-        write_json_file(ASSETS_DIR / 'rss.json', formatted_posts)
-
-        print(f"Processing complete - Aggregated {len(all_posts)} posts, saved the top {len(sorted_posts)}.")
-
+        aggregate_rss_feeds(FRIENDS_JSON_PATH, ASSETS_DIR, MAX_POSTS)
     except Exception as e:
         print(f"Main process failed: {e}")
 
+
 if __name__ == "__main__":
-    aggregate_rss_feeds()
+    main()