feat: Add Python 3.7 Support and Restore Compatibility with Older Syntax

.github/workflows/ci.yml

@@ -13,7 +13,7 @@ jobs:
       fail-fast: true
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ["3.10", "3.11", "3.12", "3.13"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12", "3.13"]
 
     steps:
     - uses: actions/checkout@v4

.pre-commit-config.yaml

@@ -48,7 +48,7 @@ repos:
     hooks:
       - id: pyupgrade
         description: "Automatically upgrade syntax for newer versions."
-        args: [--py3-plus, --py36-plus, --py38-plus, --py39-plus, --py310-plus]
+        args: [--py3-plus, --py36-plus]
 
   - repo: https://github.com/pre-commit/pygrep-hooks
     rev: v1.10.0

README.md

@@ -26,6 +26,10 @@ You can also replace `hub` with `ingest` in any GitHub URL to access the corespo
 - **CLI tool**: Run it as a shell command
 - **Python package**: Import it in your code
 
+## 📚 Requirements
+
+- Python 3.7+
+
 ## 📦 Installation
 
 ``` bash
@@ -61,7 +65,7 @@ gitingest --help
 
 This will write the digest in a text file (default `digest.txt`) in your current working directory.
 
-## 🐛 Python package usage
+## 🐍 Python package usage
 
 ```python
 # Synchronous usage
@@ -81,7 +85,7 @@ result = asyncio.run(ingest_async("path/to/directory"))
 
 By default, this won't write a file but can be enabled with the `output` argument.
 
-## 🌐 Self-host
+## 🐳 Self-host
 
 1. Build the image:
 
@@ -104,7 +108,7 @@ If you are hosting it on a domain, you can specify the allowed hostnames via env
    ALLOWED_HOSTS="example.com, localhost, 127.0.0.1"
    ```
 
-## ✔️ Contributing to Gitingest
+## 🤝 Contributing
 
 ### Non-technical ways to contribute
 
@@ -128,6 +132,6 @@ Gitingest aims to be friendly for first time contributors, with a simple python
 
 Check out the NPM alternative 📦 Repomix: <https://github.com/yamadashy/repomix>
 
-## Project Growth
+## 🚀 Project Growth
 
 [![Star History Chart](https://api.star-history.com/svg?repos=cyclotruc/gitingest&type=Date)](https://star-history.com/#cyclotruc/gitingest&Date)

pyproject.toml

@@ -3,22 +3,21 @@ name = "gitingest"
 version = "0.1.3"
 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"
+requires-python = ">= 3.7"
 dependencies = [
     "click>=8.0.0",
-    "fastapi[standard]",
-    "python-dotenv",
-    "slowapi",
-    "starlette",
     "tiktoken",
-    "uvicorn",
+    "typing_extensions; python_version < '3.10'",
 ]
+
 license = {file = "LICENSE"}
 authors = [{name = "Romain Courtois", email = "[email protected]"}]
 classifiers=[
     "Development Status :: 3 - Alpha",
     "Intended Audience :: Developers",
     "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",

setup.py

@@ -14,13 +14,14 @@
     install_requires=[
         "click>=8.0.0",
         "tiktoken",
+        "typing_extensions; python_version < '3.10'",
     ],
     entry_points={
         "console_scripts": [
             "gitingest=gitingest.cli:main",
         ],
     },
-    python_requires=">=3.6",
+    python_requires=">=3.7",
     author="Romain Courtois",
     author_email="[email protected]",
     description="CLI tool to analyze and create text dumps of codebases for LLMs",

src/gitingest/cli.py

@@ -3,6 +3,7 @@
 # pylint: disable=no-value-for-parameter
 
 import asyncio
+from typing import Optional, Tuple
 
 import click
 
@@ -19,31 +20,31 @@
 @click.option("--branch", "-b", default=None, help="Branch to clone and ingest")
 def main(
     source: str,
-    output: str | None,
+    output: Optional[str],
     max_size: int,
-    exclude_pattern: tuple[str, ...],
-    include_pattern: tuple[str, ...],
-    branch: str | None,
+    exclude_pattern: Tuple[str, ...],
+    include_pattern: Tuple[str, ...],
+    branch: Optional[str],
 ):
     """
-    Main entry point for the CLI. This function is called when the CLI is run as a script.
+     Main entry point for the CLI. This function is called when the CLI is run as a script.
 
     It calls the async main function to run the command.
 
     Parameters
     ----------
     source : str
         The source directory or repository to analyze.
-    output : str | None
+    output : str, optional
         The path where the output file will be written. If not specified, the output will be written
         to a file named `<repo_name>.txt` in the current directory.
     max_size : int
         The maximum file size to process, in bytes. Files larger than this size will be ignored.
-    exclude_pattern : tuple[str, ...]
+    exclude_pattern : Tuple[str, ...]
         A tuple of patterns to exclude during the analysis. Files matching these patterns will be ignored.
-    include_pattern : tuple[str, ...]
+    include_pattern : Tuple[str, ...]
         A tuple of patterns to include during the analysis. Only files matching these patterns will be processed.
-    branch : str | None
+    branch : str, optional
         The branch to clone (optional).
     """
     # Main entry point for the CLI. This function is called when the CLI is run as a script.
@@ -52,11 +53,11 @@ def main(
 
 async def _async_main(
     source: str,
-    output: str | None,
+    output: Optional[str],
     max_size: int,
-    exclude_pattern: tuple[str, ...],
-    include_pattern: tuple[str, ...],
-    branch: str | None,
+    exclude_pattern: Tuple[str, ...],
+    include_pattern: Tuple[str, ...],
+    branch: Optional[str],
 ) -> None:
     """
     Analyze a directory or repository and create a text dump of its contents.
@@ -68,16 +69,16 @@ async def _async_main(
     ----------
     source : str
         The source directory or repository to analyze.
-    output : str | None
+    output : str, optional
         The path where the output file will be written. If not specified, the output will be written
         to a file named `<repo_name>.txt` in the current directory.
     max_size : int
         The maximum file size to process, in bytes. Files larger than this size will be ignored.
-    exclude_pattern : tuple[str, ...]
+    exclude_pattern : Tuple[str, ...]
         A tuple of patterns to exclude during the analysis. Files matching these patterns will be ignored.
-    include_pattern : tuple[str, ...]
+    include_pattern : Tuple[str, ...]
         A tuple of patterns to include during the analysis. Only files matching these patterns will be processed.
-    branch : str | None
+    branch : str, optional
         The branch to clone (optional).
 
     Raises

src/gitingest/ignore_patterns.py

@@ -1,6 +1,8 @@
 """ Default ignore patterns for Gitingest. """
 
-DEFAULT_IGNORE_PATTERNS: set[str] = {
+from typing import Set
+
+DEFAULT_IGNORE_PATTERNS: Set[str] = {
     # Python
     "*.pyc",
     "*.pyo",

src/gitingest/notebook_utils.py

@@ -4,7 +4,7 @@
 import warnings
 from itertools import chain
 from pathlib import Path
-from typing import Any
+from typing import Any, Dict, List, Optional
 
 from gitingest.exceptions import InvalidNotebookError
 
@@ -32,12 +32,13 @@ def process_notebook(file: Path, include_output: bool = True) -> str:
     """
     try:
         with file.open(encoding="utf-8") as f:
-            notebook: dict[str, Any] = json.load(f)
+            notebook: Dict[str, Any] = json.load(f)
     except json.JSONDecodeError as e:
         raise InvalidNotebookError(f"Invalid JSON in notebook: {file}") from e
 
     # Check if the notebook contains worksheets
-    if worksheets := notebook.get("worksheets"):
+    worksheets = notebook.get("worksheets")
+    if worksheets:
         warnings.warn(
             "Worksheets are deprecated as of IPEP-17. Consider updating the notebook. "
             "(See: https://github.com/jupyter/nbformat and "
@@ -57,26 +58,27 @@ def process_notebook(file: Path, include_output: bool = True) -> str:
     result = ["# Jupyter notebook converted to Python script."]
 
     for cell in cells:
-        if cell_str := _process_cell(cell, include_output=include_output):
+        cell_str = _process_cell(cell, include_output=include_output)
+        if cell_str:
             result.append(cell_str)
 
     return "\n\n".join(result) + "\n"
 
 
-def _process_cell(cell: dict[str, Any], include_output: bool) -> str | None:
+def _process_cell(cell: Dict[str, Any], include_output: bool) -> Optional[str]:
     """
     Process a Jupyter notebook cell and return the cell content as a string.
 
     Parameters
     ----------
-    cell : dict[str, Any]
+    cell : Dict[str, Any]
         The cell dictionary from a Jupyter notebook.
     include_output : bool
         Whether to include cell outputs in the generated script
 
     Returns
     -------
-    str | None
+    str, optional
         The cell content as a string, or None if the cell is empty.
 
     Raises
@@ -101,7 +103,8 @@ def _process_cell(cell: dict[str, Any], include_output: bool) -> str | None:
         return f'"""\n{cell_str}\n"""'
 
     # Add cell output as comments
-    if include_output and (outputs := cell.get("outputs")):
+    outputs = cell.get("outputs")
+    if include_output and outputs:
 
         # Include cell outputs as comments
         output_lines = []
@@ -118,18 +121,18 @@ def _process_cell(cell: dict[str, Any], include_output: bool) -> str | None:
     return cell_str
 
 
-def _extract_output(output: dict[str, Any]) -> list[str]:
+def _extract_output(output: Dict[str, Any]) -> List[str]:
     """
     Extract the output from a Jupyter notebook cell.
 
     Parameters
     ----------
-    output : dict[str, Any]
+    output : Dict[str, Any]
         The output dictionary from a Jupyter notebook cell.
 
     Returns
     -------
-    list[str]
+    List[str]
         The output as a list of strings.
 
     Raises
@@ -139,15 +142,13 @@ def _extract_output(output: dict[str, Any]) -> list[str]:
     """
     output_type = output["output_type"]
 
-    match output_type:
-        case "stream":
-            return output["text"]
+    if output_type == "stream":
+        return output["text"]
 
-        case "execute_result" | "display_data":
-            return output["data"]["text/plain"]
+    if output_type in ("execute_result", "display_data"):
+        return output["data"]["text/plain"]
 
-        case "error":
-            return [f"Error: {output['ename']}: {output['evalue']}"]
+    if output_type == "error":
+        return [f"Error: {output['ename']}: {output['evalue']}"]
 
-        case _:
-            raise ValueError(f"Unknown output type: {output_type}")
+    raise ValueError(f"Unknown output type: {output_type}")