first implemenation

.github/workflows/python-publish.yml

@@ -0,0 +1,30 @@
+name: Upload Python Package
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade setuptools wheel twine
+    - name: Build and publish
+      env:
+        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+      run: |
+        python setup.py sdist bdist_wheel
+        twine upload dist/*

.gitignore

@@ -0,0 +1,130 @@
+*.pyc
+collated-code.md
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+Pipfile.lock
+
+# poetry
+poetry.lock
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/

LICENSE

@@ -0,0 +1 @@
+MIT License

README.md

@@ -0,0 +1,40 @@
+# Code Collator
+
+Code Collator is a powerful CLI tool designed to streamline your code review and documentation process by collating your entire codebase into a single, organised Markdown file. This is particularly useful for sharing with AI tools like ChatGPT or Claude for analysis, troubleshooting, or documentation.
+
+## Use Case
+
+Have you ever needed to provide a comprehensive overview of your codebase for a code review, AI analysis, or detailed documentation? Code Collator simplifies this task by aggregating all your code files into a single Markdown file. This makes it easy to:
+- Share your code with AI tools like ChatGPT or Claude for intelligent analysis.
+- Generate a unified document for code reviews or team collaboration.
+- Create comprehensive documentation for your projects with minimal effort.
+
+## Features
+- **Full Codebase Collation**: Collates all files in the specified directory and subdirectories into one Markdown file.
+- **.gitignore Support**: Automatically ignores files specified in the `.gitignore` file if one exists.
+- **Customizable Output**: Outputs a single Markdown file named `collated-code.md` by default, with options to specify the path to the codebase directory and output file name.
+- **Binary File Inclusion**: Includes binary files such as images in the output with a note about their file type.
+- **Help Command**: Provides a help command to display usage instructions.
+
+## Installation
+
+You can easily install Code Collator using pip:
+
+```sh
+pip install code-collator
+```
+
+## Usage
+
+Here’s a basic example of how to use Code Collator:
+
+```sh
+code-collator --path /path/to/codebase --output my-collated-code.md
+```
+
+For more detailed usage instructions, use the help command:
+
+```sh
+code-collator --help
+```
+

code_collator/collate.py

@@ -0,0 +1,94 @@
+import os
+import argparse
+from pathlib import Path
+import logging
+
+def setup_logging():
+    """Set up logging configuration."""
+    logging.basicConfig(
+        level=logging.INFO,
+        format='%(asctime)s - %(levelname)s - %(message)s'
+    )
+
+def is_binary_file(filepath):
+    """Check if a file is binary."""
+    try:
+        with open(filepath, 'rb') as f:
+            for byte in f.read():
+                if byte > 127:
+                    return True
+    except Exception as e:
+        logging.error(f"Error reading file {filepath}: {e}")
+        return False
+    return False
+
+def read_gitignore(path):
+    """Read the .gitignore file and return patterns to ignore."""
+    gitignore_path = os.path.join(path, '.gitignore')
+    if not os.path.exists(gitignore_path):
+        return []
+
+    try:
+        with open(gitignore_path, 'r') as f:
+            patterns = f.read().splitlines()
+        logging.info(f"Loaded .gitignore patterns from {gitignore_path}")
+        return patterns
+    except Exception as e:
+        logging.error(f"Error reading .gitignore file {gitignore_path}: {e}")
+        return []
+
+def should_ignore(file_path, ignore_patterns):
+    """Check if a file should be ignored based on .gitignore patterns and if it's in the .git directory."""
+    from fnmatch import fnmatch
+    if '.git' in Path(file_path).parts:
+        return True
+    for pattern in ignore_patterns:
+        if fnmatch(file_path, pattern):
+            return True
+    return False
+
+def collate_codebase(path, output_file):
+    """Aggregate the codebase into a single Markdown file."""
+    ignore_patterns = read_gitignore(path)
+    try:
+        with open(output_file, 'w') as output:
+            output.write("# Collated Codebase\n\n")
+            for root, _, files in os.walk(path):
+                for file in files:
+                    file_path = os.path.join(root, file)
+                    if should_ignore(file_path, ignore_patterns):
+                        logging.info(f"Ignored file {file_path}")
+                        continue
+
+                    output.write(f"## {file_path}\n\n")
+                    if is_binary_file(file_path):
+                        output.write(f"**Note**: This is a binary file.\n\n")
+                    elif file.endswith('.svg'):
+                        output.write(f"**Note**: This is an SVG file.\n\n")
+                    else:
+                        try:
+                            with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
+                                content = f.read()
+                                output.write(f"```\n{content}\n```\n\n")
+                        except Exception as e:
+                            logging.error(f"Error reading file {file_path}: {e}")
+                            output.write(f"**Note**: Error reading this file.\n\n")
+        logging.info(f"Collated codebase written to {output_file}")
+    except Exception as e:
+        logging.error(f"Error writing to output file {output_file}: {e}")
+
+def main():
+    """Parse arguments and initiate codebase collation."""
+    setup_logging()
+    parser = argparse.ArgumentParser(description="Aggregate codebase into a single Markdown file.")
+    parser.add_argument('-p', '--path', type=str, default='.', help="Specify the path to the codebase directory (default: current directory)")
+    parser.add_argument('-o', '--output', type=str, default='collated-code.md', help="Specify output file (default: collated-code.md)")
+
+    args = parser.parse_args()
+
+    logging.info(f"Starting code collation for directory: {args.path}")
+    collate_codebase(args.path, args.output)
+    logging.info("Code collation completed.")
+
+if __name__ == "__main__":
+    main()

setup.py

@@ -0,0 +1,41 @@
+from setuptools import setup, find_packages
+import pathlib
+
+here = pathlib.Path(__file__).parent.resolve()
+
+setup(
+    name="code-collator",
+    version="0.1",
+    description="A CLI tool to aggregate codebase into a single Markdown file",
+    long_description=(here / 'README.md').read_text(encoding='utf-8'),
+    long_description_content_type='text/markdown',
+    url="https://github.com/tawanda-kembo/code-collator",
+    author="Tawanda Kembo",
+    author_email="[email protected]",
+    classifiers=[
+        "Development Status :: 3 - Alpha",
+        "Intended Audience :: Developers",
+        "Topic :: Software Development :: Build Tools",
+        "License :: OSI Approved :: MIT License",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+    ],
+    keywords="cli, development, documentation",
+    packages=find_packages(),
+    python_requires=">=3.6, <4",
+    install_requires=[
+        # Add any dependencies here
+    ],
+    entry_points={
+        "console_scripts": [
+            "code-collator=code_collator.collate:main",
+        ],
+    },
+    project_urls={
+        "Bug Reports": "https://github.com/tawanda-kembo/code-collator/issues",
+        "Source": "https://github.com/tawanda-kembo/code-collator",
+    },
+)