Merge branch 'main' into main

Author: cyclotruc

.dockerignore

@@ -37,5 +37,4 @@ docs/
 tests/
 *.md
 LICENSE
-pytest.ini
 setup.py

.pre-commit-config.yaml

@@ -83,3 +83,51 @@ repos:
       - id: markdownlint
         description: "Lint markdown files."
         args: ["--disable=line-length"]
+
+  - repo: https://github.com/terrencepreilly/darglint
+    rev: v1.8.1
+    hooks:
+      - id: darglint
+        name: darglint for source
+        args: [--docstring-style=numpy]
+        files: ^src/
+
+  - repo: https://github.com/pycqa/pylint
+    rev: v3.3.3
+    hooks:
+      - id: pylint
+        name: pylint for source
+        files: ^src/
+        additional_dependencies:
+          [
+            click,
+            fastapi-analytics,
+            pytest-asyncio,
+            python-dotenv,
+            slowapi,
+            starlette,
+            tiktoken,
+            uvicorn,
+          ]
+      - id: pylint
+        name: pylint for tests
+        files: ^tests/
+        args:
+          - --rcfile=tests/.pylintrc
+        additional_dependencies:
+          [
+            click,
+            fastapi-analytics,
+            pytest,
+            pytest-asyncio,
+            python-dotenv,
+            slowapi,
+            starlette,
+            tiktoken,
+            uvicorn,
+          ]
+
+  - repo: meta
+    hooks:
+      - id: check-hooks-apply
+      - id: check-useless-excludes

Dockerfile

@@ -22,7 +22,7 @@ ENV PYTHONDONTWRITEBYTECODE=1
 
 # Install git
 RUN apt-get update \
-    && apt-get install -y --no-install-recommends git \
+    && apt-get install -y --no-install-recommends git curl\
     && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app

README.md

@@ -4,18 +4,21 @@
 
 [![License](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/cyclotruc/gitingest/blob/main/LICENSE)
 [![PyPI version](https://badge.fury.io/py/gitingest.svg)](https://badge.fury.io/py/gitingest)
+[![GitHub stars](https://img.shields.io/github/stars/cyclotruc/gitingest?style=social.svg)](https://github.com/cyclotruc/gitingest)
 [![Downloads](https://pepy.tech/badge/gitingest)](https://pepy.tech/project/gitingest)
 [![GitHub issues](https://img.shields.io/github/issues/cyclotruc/gitingest)](https://github.com/cyclotruc/gitingest/issues)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+
 [![Discord](https://dcbadge.limes.pink/api/server/https://discord.com/invite/zerRaGK9EC)](https://discord.com/invite/zerRaGK9EC)
 
 Turn any Git repository into a prompt-friendly text ingest for LLMs.
 
-You can also replace `hub` with `ingest` in any github url to access the coresponding digest.
+You can also replace `hub` with `ingest` in any GitHub URL to access the coresponding digest
 
 [gitingest.com](https://gitingest.com/) · [Chrome Extension](https://chromewebstore.google.com/detail/adfjahbijlkjfoicpjkhjicpjpjfaood) · [Firefox Add-on](https://addons.mozilla.org/firefox/addon/gitingest/)
 
 
+
 ## 🚀 Features
 
 - **Easy code context**: Get a text digest from a git repository URL or a directory
@@ -24,7 +27,7 @@ You can also replace `hub` with `ingest` in any github url to access the corespo
   - File and directory structure
   - Size of the extract
   - Token count
-- **CLI tool**: Run it as a command (Currently on Linux only)
+- **CLI tool**: Run it as a shell command (currently on Linux only)
 - **Python package**: Import it in your code
 
 ## 📦 Installation
@@ -43,15 +46,16 @@ The extension is open source at [lcandy2/gitingest-extension](https://github.com
 For anyone who wants install it manually, you may download it [here](https://github.com/lcandy2/gitingest-extension/releases).  
 Issues and feature requests are welcome to the repo.
 
-## 💡 Command Line usage
+## 💡 Command line usage
+
 
 The `gitingest` command line tool allows you to analyze codebases and create a text dump of their contents.
 
 ```bash
 # Basic usage
 gitingest /path/to/directory
 
-# From url
+# From URL
 gitingest https://github.com/cyclotruc/gitingest
 
 # See more options
@@ -111,8 +115,8 @@ Gitingest aims to be friendly for first time contributors, with a simple python
 
 ### Ways to help (non-technical)
 
-- Provide your feedback and ideas on discord
-- Open an Issue on github to report a bug / submit an feature request
+- Provide your feedback and ideas on Discord
+- Open an issue on GitHub to report a bug / submit a feature request
 - Talk about Gitingest on social media
 
 ### How to submit a PR
@@ -128,14 +132,14 @@ Gitingest aims to be friendly for first time contributors, with a simple python
 
 ### Run web UI locally
 
-1. Clone the repository
+1. Clone the repository:
 
    ```bash
    git clone https://github.com/cyclotruc/gitingest.git
    cd gitingest
    ```
 
-2. Install dependencies
+2. Install dependencies:
 
    ```bash
    pip install -r requirements-dev.txt
@@ -151,7 +155,7 @@ Gitingest aims to be friendly for first time contributors, with a simple python
    uvicorn main:app --reload
    ```
 
-4. Run unit tests
+4. Run unit tests:
 
    ```bash
    pytest
@@ -161,13 +165,13 @@ The application should be available at `http://localhost:8000`
 
 ### Working on the CLI
 
-1. Install the package in dev mode
+1. Install the package in dev mode:
 
    ```bash
    pip install -e .
    ```
 
-2. Run the CLI
+2. Run the CLI:
 
    ```bash
    gitingest --help

pyproject.toml

@@ -1,6 +1,60 @@
+[project]
+name = "gitingest"
+version = "0.1.2"
+description="CLI tool to analyze and create text dumps of codebases for LLMs"
+readme = {file = "README.md", content-type = "text/markdown" }
+requires-python = ">= 3.10"
+dependencies = [
+    "click>=8.0.0",
+    "fastapi-analytics",
+    "fastapi[standard]",
+    "python-dotenv",
+    "slowapi",
+    "starlette",
+    "tiktoken",
+    "uvicorn",
+]
+license = {file = "LICENSE"}
+authors = [{name = "Romain Courtois", email = "romain@coderamp.io"}]
+classifiers=[
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+]
+
+[project.scripts]
+gitingest = "gitingest.cli:main"
+
+[project.urls]
+homepage = "https://gitingest.com"
+github = "https://github.com/cyclotruc/gitingest"
+
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+packages = {find = {where = ["src"]}}
+include-package-data = true
+
+# Linting configuration
 [tool.pylint.format]
 max-line-length = 119
 
+[tool.pylint.'MESSAGES CONTROL']
+disable = [
+    "too-many-arguments",
+    "too-many-positional-arguments",
+    "too-many-locals",
+    "too-few-public-methods",
+    "broad-exception-caught",
+    "duplicate-code",
+]
+
 [tool.pycln]
 all = true
 
@@ -14,3 +68,12 @@ filter_files = true
 
 [tool.black]
 line-length = 119
+
+# Test configuration
+[tool.pytest.ini_options]
+pythonpath = ["src"]
+testpaths = ["tests/"]
+python_files = "test_*.py"
+asyncio_mode = "auto"
+python_classes = "Test*"
+python_functions = "test_*"

pytest.ini

@@ -1,8 +1,11 @@
+""" Configuration file for the project. """
+
 MAX_DISPLAY_SIZE: int = 300_000
-TMP_BASE_PATH: str = "../tmp"
+TMP_BASE_PATH: str = "/tmp/gitingest"
+DELETE_REPO_AFTER: int = 60 * 60  # In seconds
 
 EXAMPLE_REPOS: list[dict[str, str]] = [
-    {"name": "Gitingest", "url": "https://github.com/cyclotruc/gitingest"},
+    {"name": "GitIngest", "url": "https://github.com/cyclotruc/gitingest"},
     {"name": "FastAPI", "url": "https://github.com/tiangolo/fastapi"},
     {"name": "Flask", "url": "https://github.com/pallets/flask"},
     {"name": "Tldraw", "url": "https://github.com/tldraw/tldraw"},

src/config.py

@@ -1,3 +1,5 @@
+""" gitingest: A package for ingesting data from git repositories. """
+
 from gitingest.clone import clone_repo
 from gitingest.ingest import ingest
 from gitingest.ingest_from_query import ingest_from_query

src/gitingest/__init__.py

@@ -1,3 +1,7 @@
+""" Command-line interface for the GitIngest package. """
+
+# pylint: disable=no-value-for-parameter
+
 import click
 
 from gitingest.ingest import ingest
@@ -40,7 +44,7 @@ def main(
 
     Raises
     ------
-    click.Abort
+    Abort
         If there is an error during the execution of the command, this exception is raised to abort the process.
     """
     try:

src/gitingest/cli.py

@@ -1,7 +1,8 @@
+""" This module contains functions for cloning a Git repository to a local path. """
+
 import asyncio
 from dataclasses import dataclass
 
-from gitingest.exceptions import AsyncTimeoutError
 from gitingest.utils import async_timeout
 
 CLONE_TIMEOUT: int = 20
@@ -59,11 +60,7 @@ async def clone_repo(config: CloneConfig) -> tuple[bytes, bytes]:
     Raises
     ------
     ValueError
-        If the repository does not exist or if required query parameters are missing.
-    RuntimeError
-        If any git command fails during execution.
-    AsyncTimeoutError
-        If the cloning process exceeds the specified timeout.
+        If the 'url' or 'local_path' parameters are missing, or if the repository is not found.
     """
     # Extract and validate query parameters
     url: str = config.url
@@ -81,29 +78,25 @@ async def clone_repo(config: CloneConfig) -> tuple[bytes, bytes]:
     if not await _check_repo_exists(url):
         raise ValueError("Repository not found, make sure it is public")
 
-    try:
-        if commit:
-            # Scenario 1: Clone and checkout a specific commit
-            # Clone the repository without depth to ensure full history for checkout
-            clone_cmd = ["git", "clone", "--single-branch", url, local_path]
-            await _run_git_command(*clone_cmd)
-
-            # Checkout the specific commit
-            checkout_cmd = ["git", "-C", local_path, "checkout", commit]
-            return await _run_git_command(*checkout_cmd)
+    if commit:
+        # Scenario 1: Clone and checkout a specific commit
+        # Clone the repository without depth to ensure full history for checkout
+        clone_cmd = ["git", "clone", "--single-branch", url, local_path]
+        await _run_git_command(*clone_cmd)
 
-        if branch and branch.lower() not in ("main", "master"):
+        # Checkout the specific commit
+        checkout_cmd = ["git", "-C", local_path, "checkout", commit]
+        return await _run_git_command(*checkout_cmd)
 
-            # 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)
+    if branch and branch.lower() not in ("main", "master"):
 
-        # Scenario 3: Clone the default branch with shallow depth
-        clone_cmd = ["git", "clone", "--depth=1", "--single-branch", url, local_path]
+        # 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)
 
-    except (RuntimeError, asyncio.TimeoutError, AsyncTimeoutError):
-        raise  # Re-raise the exception
+    # Scenario 3: Clone the default branch with shallow depth
+    clone_cmd = ["git", "clone", "--depth=1", "--single-branch", url, local_path]
+    return await _run_git_command(*clone_cmd)
 
 
 async def _check_repo_exists(url: str) -> bool: