GitHub PR & Commit Analyzer

中文文档 | English

A powerful command-line tool for intelligently collecting, analyzing, and summarizing GitHub Pull Requests and commit records. Supports keyword-based smart search and AI-powered analysis features.

✨ Key Features

• 🔍 Smart Search: AI-powered keyword extraction and intelligent PR/Commit search
• 📊 Data Collection: Automatically collect open and merged PRs, as well as merge commits
• 🔄 Diff Viewing: Complete code change viewing functionality
• 🤖 AI Analysis: Integrated with cursor-agent CLI for intelligent change summarization
• 📅 DateTime Display: Comprehensive date/time information for all PRs and commits
• 💼 Production Quality: Complete error handling, logging, and user experience
• 🎨 Beautiful Output: Professional terminal output using Rich library
• ⚙️ Environment Variables: Direct environment variable configuration (no config files needed)

📋 Prerequisites

Before using this tool, ensure the following dependencies are installed:

Required Dependencies

1. Python 3.8+

   python --version  # should be >= 3.8

2. Git

   git --version

3. GitHub CLI (gh)

   # Ubuntu/Debian
   sudo apt install gh
   
   # macOS
   brew install gh
   
   # Windows
   choco install gh

   After installation, you need to login:

   gh auth login

Optional Dependencies

4. cursor-agent CLI (for AI analysis features)
   • If you need AI analysis features, please deploy cursor-agent in advance
   • Configure the path in the .env file

🚀 Installation

Method 1: Install from Source

# Clone or download the project
cd github-pr-analyzer

# Install dependencies
pip install -r requirements.txt

# Or install using setup.py
pip install -e .

Method 2: Using Virtual Environment (Recommended)

# Create virtual environment
python -m venv venv

# Activate virtual environment
# Linux/macOS:
source venv/bin/activate
# Windows:
venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

⚙️ Configuration

Configure the tool using environment variables:

# AI Configuration (Optional)
export CURSOR_AGENT_PATH=/path/to/cursor-agent

# Default Settings (Optional)
export DEFAULT_MONTHS=3
export DEFAULT_REPO_PATH=.

No configuration files needed - just set environment variables directly!

📖 Usage

Basic Commands

1. Collect PRs and Commits

# Auto-detect current repository
python main.py collect

# Specify repository
python main.py collect --repo owner/repo

# Specify time range (months)
python main.py collect --months 6

2. Search for Relevant Changes

# Basic search
python main.py search "bug fix authentication"

# With AI analysis
python main.py search "add new feature" --analyze

# Show diff
python main.py search "optimization" --show-diff

# Advanced options with smart search
python main.py search "refactor" \
  --repo owner/repo \
  --months 6 \
  --min-score 50 \
  --max-results 10 \
  --analyze \
  --smart-search

# Disable smart search (use traditional search)
python main.py search "refactor" --no-smart-search

3. View Specific PR

# View PR details
python main.py view-pr 123

# View PR with AI analysis
python main.py view-pr 123 --analyze

# Specify repository
python main.py view-pr 123 --repo owner/repo

4. View Specific Commit

# View commit details
python main.py view-commit abc1234

# View and analyze
python main.py view-commit abc1234 --analyze

5. Interactive Mode

# Launch interactive interface
python main.py interactive

🎯 Use Cases

Scenario 1: Find All Changes Related to Specific Feature

# Search for all PRs and commits related to "authentication"
python main.py search "authentication" --months 3 --analyze

# Output:
# - List of matching PRs and commits (sorted by relevance)
# - AI-generated summary for each change
# - Option to save analysis report

Scenario 2: Review Recent Merges

# Collect all merges from the last 3 months
python main.py collect --months 3

# Then search for specific types of changes
python main.py search "performance optimization" --show-diff

Scenario 3: Deep Dive into Specific PR

# View complete information for PR #456
python main.py view-pr 456 --analyze

# Output includes:
# - PR basic information
# - Complete diff
# - AI analysis: purpose, impact, technical details

🛠️ Development

Project Structure

github-pr-analyzer/
├── main.py                 # Program entry point
├── setup.py               # Installation configuration
├── requirements.txt       # Dependency list
├── .env.example          # Configuration template
├── .gitignore            # Git ignore rules
├── README.md             # This document
└── src/
    ├── __init__.py
    ├── config.py         # Configuration management
    ├── utils.py          # Utility functions
    ├── pr_collector.py   # PR collection module
    ├── commit_collector.py  # Commit collection module
    ├── diff_viewer.py    # Diff viewing module
    ├── matcher.py        # Smart matching module
    ├── ai_analyzer.py    # AI analysis module
    └── cli.py            # Command-line interface

Running Tests

# Basic functionality test
python main.py --help

# Check dependencies
python test_installation.py

📝 FAQ

Q: Getting "gh CLI not authenticated"

A: Run gh auth login and complete GitHub authentication.

Q: Repository not found

A: Make sure you're in a Git repository directory, or use --repo owner/repo to specify explicitly.

Q: AI analysis not available

A: Configure CURSOR_AGENT_PATH in the .env file. AI features are optional.

Q: Too many/too few search results

A: Adjust the --min-score parameter (lower for more results, higher for more precise results).

🤝 Contributing

Issues and Pull Requests are welcome!

📄 License

This project is licensed under the MIT License - free for commercial and personal use.

Copyright (c) 2025 GitHub PR Analyzer Team

🔗 Related Resources

• GitHub CLI Documentation
• GitPython Documentation
• Rich Library Documentation

📧 Contact

For questions or suggestions, please contact us via Issues.

---

Enjoy analyzing! 🎉