Add codebase organization scripts

.github/actions/setup-environment/action.yml

@@ -9,7 +9,7 @@ runs:
   using: "composite"
   steps:
     - name: Install UV
-      uses: astral-sh/setup-uv@v5.3
+      uses: astral-sh/setup-uv@v5.4
       id: setup-uv
       with:
         enable-cache: true

.github/workflows/bot-pr-checks.yml

@@ -0,0 +1,50 @@
+name: Bot PR Checks
+
+on:
+  pull_request_target:
+    types: [ opened, synchronize, reopened, labeled ]
+    branches:
+      - "develop"
+
+jobs:
+  bot-check:
+    runs-on: ubuntu-latest
+    if: contains(github.triggering_actor, '[bot]')
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Setup environment
+        uses: ./.github/actions/setup-environment
+
+      - name: Run tests
+        timeout-minutes: 5
+        run: |
+          uv run pytest \
+            -n auto \
+            --cov src \
+            --timeout 15 \
+            -o junit_suite_name="bot-unit-tests" \
+            tests/unit
+
+      - uses: ./.github/actions/report
+        with:
+          flag: bot-unit-tests
+          codecov_token: ${{ secrets.CODECOV_TOKEN }}
+
+  # Add a job to handle the Build & Release workflow for bot PRs
+  bot-build:
+    runs-on: ubuntu-latest
+    if: contains(github.triggering_actor, '[bot]')
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Skip build for bot PRs
+        run: echo "Skipping build for bot PRs"

.github/workflows/mypy.yml

@@ -1,7 +1,7 @@
 name: Mypy Checks
 
 on:
-  pull_request:
+  pull_request_target:
     branches:
       - "develop"
 
@@ -19,6 +19,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
+          ref: ${{ github.event.pull_request.head.sha }}
 
       - name: Setup environment
         uses: ./.github/actions/setup-environment

.github/workflows/pre-commit.yml

@@ -1,7 +1,7 @@
 name: pre-commit
 
 on:
-  pull_request:
+  pull_request_target:
     branches:
       - "develop"
   push:
@@ -21,6 +21,7 @@ jobs:
         with:
           fetch-depth: 0
           token: ${{ env.REPO_SCOPED_TOKEN || github.token }}
+          ref: ${{ github.event.pull_request.head.sha }}
 
       - name: Setup environment
         uses: ./.github/actions/setup-environment

.github/workflows/release.yml

@@ -25,8 +25,26 @@ permissions:
   contents: read
 
 jobs:
+  # Add a check to skip the build for bot PRs
+  check-bot:
+    runs-on: ubuntu-latest
+    outputs:
+      is_bot: ${{ steps.check-bot.outputs.is_bot }}
+    steps:
+      - name: Check if user is bot
+        id: check-bot
+        run: |
+          if [[ "${{ github.triggering_actor }}" == *"[bot]" ]]; then
+            echo "is_bot=true" >> $GITHUB_OUTPUT
+          else
+            echo "is_bot=false" >> $GITHUB_OUTPUT
+          fi
+
   build:
     name: Build 3.${{ matrix.python }} ${{ matrix.os }}
+    needs: check-bot
+    # Skip this job if the PR is from a bot
+    if: needs.check-bot.outputs.is_bot != 'true'
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: false
@@ -55,7 +73,7 @@ jobs:
           repository: ${{ github.event.pull_request.head.repo.full_name || github.event.repository.full_name }}
 
       - name: Install UV
-        uses: astral-sh/setup-uv@v5.3
+        uses: astral-sh/setup-uv@v5.4
         id: setup-uv
         with:
           enable-cache: false

.github/workflows/test.yml

@@ -14,7 +14,17 @@ jobs:
   access-check:
     runs-on: ubuntu-latest
     steps:
+      - name: Check if user is bot
+        id: check-bot
+        run: |
+          if [[ "${{ github.triggering_actor }}" == *"[bot]" ]]; then
+            echo "is_bot=true" >> $GITHUB_OUTPUT
+          else
+            echo "is_bot=false" >> $GITHUB_OUTPUT
+          fi
+
       - uses: actions-cool/check-user-permission@v2
+        if: steps.check-bot.outputs.is_bot != 'true'
         with:
           require: write
           username: ${{ github.triggering_actor }}
@@ -32,15 +42,20 @@ jobs:
       - name: Setup environment
         uses: ./.github/actions/setup-environment
 
-      - name: Run ATS and Tests
-        uses: ./.github/actions/run-ats
-        timeout-minutes: 15
+      - name: Test with pytest
+        timeout-minutes: 5
+        run: |
+          uv run pytest \
+            -n auto \
+            --cov src \
+            --timeout 15 \
+            -o junit_suite_name="${{github.job}}" \
+            tests/unit
+
+      - uses: ./.github/actions/report
         with:
-          default_tests: "tests/unit"
-          codecov_static_token: ${{ secrets.CODECOV_STATIC_TOKEN }}
+          flag: unit-tests
           codecov_token: ${{ secrets.CODECOV_TOKEN }}
-          collect_args: "--timeout 15"
-          codecov_flags: unit-tests
 
   codemod-tests:
     needs: access-check

README.md

@@ -1,117 +1,114 @@
-<br />
-
-<p align="center">
-  <a href="https://docs.codegen.com">
-    <img src="https://i.imgur.com/6RF9W0z.jpeg" />
-  </a>
-</p>
-
-<h2 align="center">
-  Scriptable interface to a powerful, multi-lingual language server.
-</h2>
-
-<div align="center">
-
-[![PyPI](https://img.shields.io/badge/PyPi-codegen-gray?style=flat-square&color=blue)](https://pypi.org/project/codegen/)
-[![Documentation](https://img.shields.io/badge/Docs-docs.codegen.com-purple?style=flat-square)](https://docs.codegen.com)
-[![Slack Community](https://img.shields.io/badge/Slack-Join-4A154B?logo=slack&style=flat-square)](https://community.codegen.com)
-[![License](https://img.shields.io/badge/Code%20License-Apache%202.0-gray?&color=gray)](https://github.com/codegen-sh/codegen-sdk/tree/develop?tab=Apache-2.0-1-ov-file)
-[![Follow on X](https://img.shields.io/twitter/follow/codegen?style=social)](https://x.com/codegen)
-
-</div>
-
-<br />
-
-[Codegen](https://docs.codegen.com) is a python library for manipulating codebases.
-
-```python
-from codegen import Codebase
-
-# Codegen builds a complete graph connecting
-# functions, classes, imports and their relationships
-codebase = Codebase("./")
-
-# Work with code without dealing with syntax trees or parsing
-for function in codebase.functions:
-    # Comprehensive static analysis for references, dependencies, etc.
-    if not function.usages:
-        # Auto-handles references and imports to maintain correctness
-        function.move_to_file("deprecated.py")
+# Comprehensive Codebase Analyzer
+
+A powerful static code analysis system that provides extensive information about your codebase using the Codegen SDK.
+
+## Features
+
+This analyzer provides comprehensive analysis of your codebase, including:
+
+### 1. Codebase Structure Analysis
+- File Statistics (count, language, size)
+- Symbol Tree Analysis
+- Import/Export Analysis
+- Module Organization
+
+### 2. Symbol-Level Analysis
+- Function Analysis (parameters, return types, complexity)
+- Class Analysis (methods, attributes, inheritance)
+- Variable Analysis
+- Type Analysis
+
+### 3. Dependency and Flow Analysis
+- Call Graph Generation
+- Data Flow Analysis
+- Control Flow Analysis
+- Symbol Usage Analysis
+
+### 4. Code Quality Analysis
+- Unused Code Detection
+- Code Duplication Analysis
+- Complexity Metrics
+- Style and Convention Analysis
+
+### 5. Visualization Capabilities
+- Dependency Graphs
+- Call Graphs
+- Symbol Trees
+- Heat Maps
+
+### 6. Language-Specific Analysis
+- Python-Specific Analysis
+- TypeScript-Specific Analysis
+
+### 7. Code Metrics
+- Monthly Commits
+- Cyclomatic Complexity
+- Halstead Volume
+- Maintainability Index
+
+## Installation
+
+1. Clone the repository:
+```bash
+git clone https://github.com/yourusername/codebase-analyzer.git
+cd codebase-analyzer
 ```
 
-Write code that transforms code. Codegen combines the parsing power of [Tree-sitter](https://tree-sitter.github.io/tree-sitter/) with the graph algorithms of [rustworkx](https://github.com/Qiskit/rustworkx) to enable scriptable, multi-language code manipulation at scale.
-
-## Installation and Usage
-
-We support
-
-- Running Codegen in Python 3.12 - 3.13 (recommended: Python 3.13+)
-- macOS and Linux
-  - macOS is supported
-  - Linux is supported on x86_64 and aarch64 with glibc 2.34+
-  - Windows is supported via WSL. See [here](https://docs.codegen.com/building-with-codegen/codegen-with-wsl) for more details.
-- Python, Typescript, Javascript and React codebases
-
-```
-# Install inside existing project
-uv pip install codegen
-
-# Install global CLI
-uv tool install codegen --python 3.13
-
-# Create a codemod for a given repo
-cd path/to/repo
-codegen init
-codegen create test-function
-
-# Run the codemod
-codegen run test-function
-
-# Create an isolated venv with codegen => open jupyter
-codegen notebook
+2. Install dependencies:
+```bash
+pip install -r requirements.txt
 ```
 
 ## Usage
 
-See [Getting Started](https://docs.codegen.com/introduction/getting-started) for a full tutorial.
+### Analyzing a Repository
 
-```
-from codegen import Codebase
-```
-
-## Troubleshooting
+```bash
+# Analyze from URL
+python codebase_analyzer.py --repo-url https://github.com/username/repo
 
-Having issues? Here are some common problems and their solutions:
+# Analyze local repository
+python codebase_analyzer.py --repo-path /path/to/repo
 
-- **I'm hitting an UV error related to `[[ packages ]]`**: This means you're likely using an outdated version of UV. Try updating to the latest version with: `uv self update`.
-- **I'm hitting an error about `No module named 'codegen.sdk.extensions.utils'`**: The compiled cython extensions are out of sync. Update them with `uv sync --reinstall-package codegen`.
-- **I'm hitting a `RecursionError: maximum recursion depth exceeded` error while parsing my codebase**: If you are using python 3.12, try upgrading to 3.13. If you are already on 3.13, try upping the recursion limit with `sys.setrecursionlimit(10000)`.
+# Specify language
+python codebase_analyzer.py --repo-url https://github.com/username/repo --language python
 
-If you run into additional issues not listed here, please [join our slack community](https://community.codegen.com) and we'll help you out!
-
-## Resources
+# Analyze specific categories
+python codebase_analyzer.py --repo-url https://github.com/username/repo --categories codebase_structure code_quality
+```
 
-- [Docs](https://docs.codegen.com)
-- [Getting Started](https://docs.codegen.com/introduction/getting-started)
-- [Contributing](CONTRIBUTING.md)
-- [Contact Us](https://codegen.com/contact)
+### Output Formats
 
-## Why Codegen?
+```bash
+# Output as JSON
+python codebase_analyzer.py --repo-url https://github.com/username/repo --output-format json --output-file analysis.json
 
-Software development is fundamentally programmatic. Refactoring a codebase, enforcing patterns, or analyzing control flow - these are all operations that can (and should) be expressed as programs themselves.
+# Generate HTML report
+python codebase_analyzer.py --repo-url https://github.com/username/repo --output-format html --output-file report.html
 
-We built Codegen backwards from real-world refactors performed on enterprise codebases. Instead of starting with theoretical abstractions, we focused on creating APIs that match how developers actually think about code changes:
+# Print to console (default)
+python codebase_analyzer.py --repo-url https://github.com/username/repo --output-format console
+```
 
-- **Natural mental model**: Write transforms that read like your thought process - "move this function", "rename this variable", "add this parameter". No more wrestling with ASTs or manual import management.
+## Available Analysis Categories
 
-- **Battle-tested on complex codebases**: Handle Python, TypeScript, and React codebases with millions of lines of code.
+- `codebase_structure`: File statistics, symbol tree, import/export analysis, module organization
+- `symbol_level`: Function, class, variable, and type analysis
+- `dependency_flow`: Call graphs, data flow, control flow, symbol usage
+- `code_quality`: Unused code, duplication, complexity, style
+- `visualization`: Dependency graphs, call graphs, symbol trees, heat maps
+- `language_specific`: Language-specific analysis features
+- `code_metrics`: Commits, complexity, volume, maintainability
 
-- **Built for advanced intelligences**: As AI developers become more sophisticated, they need expressive yet precise tools to manipulate code. Codegen provides a programmatic interface that both humans and AI can use to express complex transformations through code itself.
+## Requirements
 
-## Contributing
+- Python 3.8+
+- Codegen SDK
+- NetworkX
+- Matplotlib
+- Rich
 
-Please see our [Contributing Guide](CONTRIBUTING.md) for instructions on how to set up the development environment and submit contributions.
+## License
 
-## Enterprise
+MIT
 
-For more information on enterprise engagements, please [contact us](https://codegen.com/contact) or [request a demo](https://codegen.com/request-demo).