Modernize Codebase and Enhance CI Workflow (#67)

Updated Type Hints:

Used pyupgrade with --py39-plus and --py310-plus flags to upgrade type hints to Python 3.9+ and 3.10+ syntax.
Enforced Double Quotes:

Removed skip-string-normalization = true from the black configuration in pyproject.toml.
Reran black via pre-commit hooks to enforce double quotes in the codebase.
Refactored Dependency Management:

Split requirements.txt into requirements.txt (runtime dependencies) and requirements-dev.txt (development dependencies).
Enhanced CI Workflow:

Integrated pre-commit hooks into the CI pipeline to enforce code quality checks automatically.
Added pip caching to the CI workflow to speed up dependency installation.
Automated Package Publishing:

Added a publish.yml GitHub Actions workflow to automate publishing to PyPI.
The workflow triggers on release creation or manual dispatch, builds the package, and publishes it to PyPI using twine.

.github/workflows/ci.yml

@@ -0,0 +1,47 @@
+name: CI
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: true
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Cache pip
+      uses: actions/cache@v4
+      with:
+        path: ~/.cache/pip
+        key: ${{ runner.os }}-pip-${{ hashFiles('**/*requirements*.txt') }}
+        restore-keys: |
+          ${{ runner.os }}-pip-
+
+    - name: Install dependencies
+      run: |
+        pip install --upgrade pip
+        pip install -r requirements-dev.txt
+
+    - name: Run tests
+      run: |
+        pytest
+
+    #  Run pre-commit only on Python 3.13 + ubuntu.
+    - name: Run pre-commit hooks
+      if: ${{ matrix.python-version == '3.13' && matrix.os == 'ubuntu-latest' }}
+      run: |
+        pre-commit run --all-files

.github/workflows/publish.yml

@@ -0,0 +1,41 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [created] # Trigger only when a release is created
+  workflow_dispatch: # Allows manual triggering of the workflow
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+
+    steps:
+      # Step 1: Check out the code
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      # Step 2: Set up Python
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.13
+
+      # Step 3: Install dependencies for building and publishing
+      - name: Install build tools
+        run: |
+          pip install --upgrade pip
+          pip install build twine
+
+      # Step 4: Build the package
+      - name: Build the package
+        run: |
+          python -m build
+
+      # Step 5: Publish to PyPI
+      - name: Publish to PyPI
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
+        run: |
+          python -m twine check dist/*
+          python -m twine upload --skip-existing dist/*

.pre-commit-config.yaml

@@ -4,39 +4,39 @@ repos:
     hooks:
       # Files
       - id: check-added-large-files
-        description: 'Prevent large files from being committed.'
-        args: ['--maxkb=10000']
+        description: "Prevent large files from being committed."
+        args: ["--maxkb=10000"]
       - id: check-case-conflict
-        description: 'Check for files that would conflict in case-insensitive filesystems.'
+        description: "Check for files that would conflict in case-insensitive filesystems."
       - id: fix-byte-order-marker
-        description: 'Remove utf-8 byte order marker.'
+        description: "Remove utf-8 byte order marker."
       - id: mixed-line-ending
-        description: 'Replace mixed line ending.'
+        description: "Replace mixed line ending."
 
       # Links
       - id: destroyed-symlinks
-        description: 'Detect symlinks which are changed to regular files with a content of a path which that symlink was pointing to.'
+        description: "Detect symlinks which are changed to regular files with a content of a path which that symlink was pointing to."
 
       # File files for parseable syntax: python
       - id: check-ast
 
       # File and line endings
       - id: end-of-file-fixer
-        description: 'Ensure that a file is either empty, or ends with one newline.'
+        description: "Ensure that a file is either empty, or ends with one newline."
       - id: trailing-whitespace
-        description: 'Trim trailing whitespace.'
+        description: "Trim trailing whitespace."
 
       # Python
       - id: check-docstring-first
-        description: 'Check a common error of defining a docstring after code.'
+        description: "Check a common error of defining a docstring after code."
       - id: requirements-txt-fixer
-        description: 'Sort entries in requirements.txt.'
+        description: "Sort entries in requirements.txt."
 
   - repo: https://github.com/MarcoGorelli/absolufy-imports
     rev: v0.3.1
     hooks:
       - id: absolufy-imports
-        description: 'Automatically convert relative imports to absolute. (Use `args: [--never]` to revert.)'
+        description: "Automatically convert relative imports to absolute. (Use `args: [--never]` to revert.)"
 
   - repo: https://github.com/psf/black
     rev: 24.10.0
@@ -47,30 +47,30 @@ repos:
     rev: v3.19.1
     hooks:
       - id: pyupgrade
-        description: 'Automatically upgrade syntax for newer versions.'
-        args: [--py3-plus, --py36-plus, --py38-plus]
+        description: "Automatically upgrade syntax for newer versions."
+        args: [--py3-plus, --py36-plus, --py38-plus, --py39-plus, --py310-plus]
 
   - repo: https://github.com/pre-commit/pygrep-hooks
     rev: v1.10.0
     hooks:
       - id: python-check-blanket-noqa
-        description: 'Enforce that `noqa` annotations always occur with specific codes. Sample annotations: `# noqa: F401`, `# noqa: F401,W203`.'
+        description: "Enforce that `noqa` annotations always occur with specific codes. Sample annotations: `# noqa: F401`, `# noqa: F401,W203`."
       - id: python-check-blanket-type-ignore
-        description: 'Enforce that `# type: ignore` annotations always occur with specific codes. Sample annotations: `# type: ignore[attr-defined]`, `# type: ignore[attr-defined, name-defined]`.'
+        description: "Enforce that `# type: ignore` annotations always occur with specific codes. Sample annotations: `# type: ignore[attr-defined]`, `# type: ignore[attr-defined, name-defined]`."
       - id: python-use-type-annotations
-        description: 'Enforce that python3.6+ type annotations are used instead of type comments.'
+        description: "Enforce that python3.6+ type annotations are used instead of type comments."
 
   - repo: https://github.com/PyCQA/isort
     rev: 5.13.2
     hooks:
       - id: isort
-        description: 'Sort imports alphabetically, and automatically separated into sections and by type.'
+        description: "Sort imports alphabetically, and automatically separated into sections and by type."
 
   - repo: https://github.com/hadialqattan/pycln
     rev: v2.4.0
     hooks:
       - id: pycln
-        description: 'Remove unused import statements.'
+        description: "Remove unused import statements."
 
   - repo: https://github.com/djlint/djLint
     rev: v1.36.4

pyproject.toml

@@ -14,4 +14,3 @@ filter_files = true
 
 [tool.black]
 line-length = 119
-skip-string-normalization = true

requirements-dev.txt

@@ -0,0 +1,7 @@
+-r requirements.txt
+black
+djlint
+pre-commit
+pylint
+pytest
+pytest-asyncio

requirements.txt

@@ -1,11 +1,6 @@
-black
 click>=8.0.0
-djlint
 fastapi-analytics
 fastapi[standard]
-pre-commit
-pytest
-pytest-asyncio
 python-dotenv
 slowapi
 starlette

src/gitingest/cli.py

@@ -1,9 +1,7 @@
 import os
-from typing import Optional, Tuple
 
 import click
 
-from gitingest.ignore_patterns import DEFAULT_IGNORE_PATTERNS
 from gitingest.ingest import ingest
 from gitingest.ingest_from_query import MAX_FILE_SIZE
 
@@ -17,17 +15,17 @@ def normalize_pattern(pattern: str) -> str:
 
 
 @click.command()
-@click.argument('source', type=str, required=True)
-@click.option('--output', '-o', default=None, help='Output file path (default: <repo_name>.txt in current directory)')
-@click.option('--max-size', '-s', default=MAX_FILE_SIZE, help='Maximum file size to process in bytes')
-@click.option('--exclude-pattern', '-e', multiple=True, help='Patterns to exclude')
-@click.option('--include-pattern', '-i', multiple=True, help='Patterns to include')
+@click.argument("source", type=str, required=True)
+@click.option("--output", "-o", default=None, help="Output file path (default: <repo_name>.txt in current directory)")
+@click.option("--max-size", "-s", default=MAX_FILE_SIZE, help="Maximum file size to process in bytes")
+@click.option("--exclude-pattern", "-e", multiple=True, help="Patterns to exclude")
+@click.option("--include-pattern", "-i", multiple=True, help="Patterns to include")
 def main(
     source: str,
-    output: Optional[str],
+    output: str | None,
     max_size: int,
-    exclude_pattern: Tuple[str, ...],
-    include_pattern: Tuple[str, ...],
+    exclude_pattern: tuple[str, ...],
+    include_pattern: tuple[str, ...],
 ) -> None:
     """Analyze a directory and create a text dump of its contents."""
     try:
@@ -48,5 +46,5 @@ def main(
         raise click.Abort()
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()

src/gitingest/clone.py

@@ -1,6 +1,5 @@
 import asyncio
 from dataclasses import dataclass
-from typing import Optional, Tuple
 
 from gitingest.utils import AsyncTimeoutError, async_timeout
 
@@ -11,8 +10,9 @@
 class CloneConfig:
     url: str
     local_path: str
-    commit: Optional[str] = None
-    branch: Optional[str] = None
+    commit: str | None = None
+    branch: str | None = None
+
 
 
 async def check_repo_exists(url: str) -> bool:
@@ -44,7 +44,8 @@ async def check_repo_exists(url: str) -> bool:
     return "HTTP/1.1 404" not in stdout_str and "HTTP/2 404" not in stdout_str
 
 
-async def run_git_command(*args: str) -> Tuple[bytes, bytes]:
+async def run_git_command(*args: str) -> tuple[bytes, bytes]:
+
     """
     Executes a git command asynchronously and captures its output.
 
@@ -77,7 +78,7 @@ async def run_git_command(*args: str) -> Tuple[bytes, bytes]:
 
 
 @async_timeout(CLONE_TIMEOUT)
-async def clone_repo(config: CloneConfig) -> Tuple[bytes, bytes]:
+async def clone_repo(config: CloneConfig) -> tuple[bytes, bytes]:
     """
     Clones a repository to a local path based on the provided query parameters.
 
@@ -107,8 +108,9 @@ async def clone_repo(config: CloneConfig) -> Tuple[bytes, bytes]:
     # Extract and validate query parameters
     url: str = config.url
     local_path: str = config.local_path
-    commit: Optional[str] = config.commit
-    branch: Optional[str] = config.branch
+    commit: str | None = config.commit
+    branch: str | None = config.branch
+
 
     if not url:
         raise ValueError("The 'url' parameter is required.")
@@ -131,7 +133,8 @@ async def clone_repo(config: CloneConfig) -> Tuple[bytes, bytes]:
             checkout_cmd = ["git", "-C", local_path, "checkout", commit]
             return await run_git_command(*checkout_cmd)
 
-        if branch and branch.lower() not in ('main', 'master'):
+        if branch and branch.lower() not in ("main", "master"):
+
             # Scenario 2: Clone a specific branch with shallow depth
             clone_cmd = ["git", "clone", "--depth=1", "--single-branch", "--branch", branch, url, local_path]
             return await run_git_command(*clone_cmd)