Init commit

.github/workflows/publish.yaml

@@ -0,0 +1,35 @@
+name: Publish to PyPI
+
+"on":
+  release:
+    types: [published]
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    environment: release
+    permissions:
+      id-token: write  # Required for PyPI trusted publishing
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Install UV
+      run: |
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        echo "$HOME/.cargo/bin" >> $GITHUB_PATH
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.11"
+
+    - name: Install build dependencies
+      run: |
+        uv pip install build
+
+    - name: Build package
+      run: python -m build
+
+    - name: Publish to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/test.yml

@@ -0,0 +1,35 @@
+name: Test
+
+on:
+  pull_request:
+    branches: [ main ]
+  push:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11"]
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Install the latest version of uv
+      uses: astral-sh/setup-uv@v5
+      with:
+        version: "0.5.x"
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install dependencies
+      run: |
+        uv sync --all-extras --dev
+
+    - name: Lint with ruff
+      run: |
+        uv run ruff check .
+
+    - name: Run tests
+      run: |
+        uv run pytest tests/ -v --cov=gitwalk

.gitignore

@@ -0,0 +1,171 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+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/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# 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/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# PyPI configuration file
+.pypirc

README.md

@@ -0,0 +1,36 @@
+# gitwalk
+
+A Python library that provides an os.walk()-compatible interface that respects .gitignore rules. Walk through your directories while automatically excluding paths matched by .gitignore patterns.
+
+## Installation
+
+Using uv:
+```bash
+uv pip install gitwalk
+```
+
+## Usage
+
+```python
+from gitwalk import gitwalk as walk
+
+# Walk through directory respecting .gitignore rules
+for dirpath, dirnames, filenames in walk("./my_project"):
+    print(f"Directory: {dirpath}")
+    print(f"Subdirectories: {dirnames}")
+    print(f"Files: {filenames}")
+```
+
+## Features
+
+- Same interface as `os.walk()`
+- Respects `.gitignore` patterns
+- Supports both topdown and bottom-up traversal
+- Handles error callbacks
+- Follows symbolic links (optional)
+
+## Tests
+```
+uv pip install -e ".[test]"
+pytest
+```

pyproject.toml

@@ -0,0 +1,24 @@
+[project]
+name = "gitwalk"
+version = "0.1.0"
+description = "A directory walker that respects .gitignore rules"
+authors = [
+    { name = "Avi Yeger", email = "yeger00@gmail.com" }
+]
+dependencies = [
+    "pathspec>=0.11.0",
+]
+requires-python = ">=3.7"
+readme = "README.md"
+license = { text = "MIT" }
+
+[project.optional-dependencies]
+test = [
+    "pytest>=7.0.0",
+    "pytest-cov>=4.0.0",
+    "ruff>=0.2.0",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"

src/gitwalk/__init__.py

@@ -0,0 +1,4 @@
+from .walker import gitwalk
+
+__version__ = "0.1.0"
+__all__ = ["gitwalk"]

src/gitwalk/walker.py

@@ -0,0 +1,68 @@
+import os
+from pathlib import Path
+from typing import Iterator, List, Literal, Tuple
+from pathspec import PathSpec
+from pathspec.patterns import GitWildMatchPattern
+
+def gitwalk(top: str, topdown: Literal[True] = True, onerror=None, followlinks: bool = False) -> Iterator[Tuple[str, List[str], List[str]]]:
+    """
+    Walk a directory tree similar to os.walk(), but respecting .gitignore rules.
+    
+    Args:
+        top: Starting directory path
+        topdown: If True, do a topdown traversal; if False, do a bottom-up traversal
+        onerror: Optional function to handle errors
+        followlinks: If True, follow symbolic links
+        
+    Yields:
+        A 3-tuple: (dirpath, dirnames, filenames) - same format as os.walk()
+    """
+    if not topdown:
+        raise ValueError("topdown must be True")
+
+    def load_gitignore(directory: str) -> PathSpec:
+        """Load .gitignore patterns from the given directory and its parents."""
+        patterns = []
+        current_dir = Path(directory)
+
+        while True:
+            gitignore_path = current_dir / '.gitignore'
+            if gitignore_path.is_file():
+                with open(gitignore_path, 'r') as f:
+                    patterns.extend(f.readlines())
+
+            if current_dir.parent == current_dir:
+                break
+            current_dir = current_dir.parent
+
+        return PathSpec.from_lines(GitWildMatchPattern, patterns)
+
+    try:
+        walk_generator = os.walk(top, topdown, onerror, followlinks)
+
+        for dirpath, dirnames, filenames in walk_generator:
+            gitignore = load_gitignore(dirpath)
+            rel_dirpath = os.path.relpath(dirpath, top)
+            if rel_dirpath == '.':
+                rel_dirpath = ''
+
+            filtered_dirs = []
+            for dirname in dirnames:
+                rel_path = os.path.join(rel_dirpath, dirname) if rel_dirpath else dirname
+                if not gitignore.match_file(rel_path + '/'):
+                    filtered_dirs.append(dirname)
+
+            filtered_files = []
+            for filename in filenames:
+                rel_path = os.path.join(rel_dirpath, filename) if rel_dirpath else filename
+                if not gitignore.match_file(rel_path):
+                    filtered_files.append(filename)
+
+            dirnames[:] = filtered_dirs
+            yield dirpath, filtered_dirs, filtered_files
+
+    except Exception as e:
+        if onerror is not None:
+            onerror(e)
+        else:
+            raise