Add Python 3.9 support by using ParamSpec from typing_extensions and …

…removing match statements

.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: ["3.9", "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 3.9+
+
 ## 📦 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 +3,20 @@ 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 = ">= 3.9"
 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 = "romain@coderamp.io"}]
 classifiers=[
  "Development Status :: 3 - Alpha",
  "Intended Audience :: Developers",
  "License :: OSI Approved :: MIT License",
+ "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=">=3.9",
  author="Romain Courtois",
  author_email="romain@coderamp.io",
  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
 
 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,
+ 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 : Optional[str]
  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, ...]
- A tuple of patterns to exclude during the analysis. Files matching these patterns will be ignored.
+  A tuple of patterns to exclude during the analysis. Files matching these patterns will be ignored.
  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 : Optional[str]
  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,
+ branch: Optional[str],
 ) -> None:
  """
  Analyze a directory or repository and create a text dump of its contents.
@@ -68,7 +69,7 @@ async def _async_main(
  ----------
  source : str
  The source directory or repository to analyze.
- output : str | None
+ output : Optional[str]
  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
@@ -77,7 +78,7 @@ async def _async_main(
  A tuple of patterns to exclude during the analysis. Files matching these patterns will be ignored.
  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 : Optional[str]
  The branch to clone (optional).
 
  Raises

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, Optional
 
 from gitingest.exceptions import InvalidNotebookError
 
@@ -63,7 +63,7 @@ def process_notebook(file: Path, include_output: bool = True) -> 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.
 
@@ -76,7 +76,7 @@ def _process_cell(cell: dict[str, Any], include_output: bool) -> str | None:
 
  Returns
  -------
- str | None
+ Optional[str]
  The cell content as a string, or None if the cell is empty.
 
  Raises
@@ -139,15 +139,13 @@ 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}")

src/gitingest/query_ingestion.py

@@ -5,7 +5,7 @@
 import platform
 from fnmatch import fnmatch
 from pathlib import Path
-from typing import Any
+from typing import Any, Optional, Union
 
 import tiktoken
 
@@ -42,7 +42,7 @@ def _normalize_path(path: Path) -> Path:
  return Path(os.path.normpath(str(path)))
 
 
-def _normalize_path_str(path: str | Path) -> str:
+def _normalize_path_str(path: Union[Path, str]) -> str:
  """
  Convert path to string with forward slashes for consistent output.
 
@@ -293,10 +293,10 @@ def _sort_children(children: list[dict[str, Any]]) -> list[dict[str, Any]]:
 def _scan_directory(
  path: Path,
  query: ParsedQuery,
- seen_paths: set[Path] | None = None,
+ seen_paths: Optional[set[Path]] = None,
  depth: int = 0,
- stats: dict[str, int] | None = None,
-) -> dict[str, Any] | None:
+ stats: Optional[dict[str, int]] = None,
+) -> Optional[dict[str, Any]]:
  """
  Recursively analyze a directory and its contents with safety limits.
 
@@ -573,7 +573,7 @@ def _process_item(
 def _extract_files_content(
  query: ParsedQuery,
  node: dict[str, Any],
- files: list[dict[str, Any]] | None = None,
+ files: Optional[list[dict[str, Any]]] = None,
 ) -> list[dict[str, Any]]:
  """
  Recursively collect all text files with their contents.
@@ -733,7 +733,7 @@ def _create_tree_structure(query: ParsedQuery, node: dict[str, Any], prefix: str
  return tree
 
 
-def _generate_token_string(context_string: str) -> str | None:
+def _generate_token_string(context_string: str) -> Optional[str]:
  """
  Return the number of tokens in a text string.
 
@@ -747,7 +747,7 @@ def _generate_token_string(context_string: str) -> str | None:
 
  Returns
  -------
- str | None
+ Optional[str]
  The formatted number of tokens as a string (e.g., '1.2k', '1.2M'), or `None` if an error occurs.
  """
  try:

src/gitingest/query_parser.py

@@ -7,6 +7,7 @@
 import warnings
 from dataclasses import dataclass
 from pathlib import Path
+from typing import Optional, Union
 from urllib.parse import unquote, urlparse
 
 from gitingest.config import MAX_FILE_SIZE, TMP_BASE_PATH
@@ -32,28 +33,28 @@ class ParsedQuery: # pylint: disable=too-many-instance-attributes
  Dataclass to store the parsed details of the repository or file path.
  """
 
- user_name: str | None
- repo_name: str | None
+ user_name: Optional[str]
+ repo_name: Optional[str]
  subpath: str
  local_path: Path
- url: str | None
+ url: Optional[str]
  slug: str
  id: str
- type: str | None = None
- branch: str | None = None
- commit: str | None = None
+ type: Optional[str] = None
+ branch: Optional[str] = None
+ commit: Optional[str] = None
  max_file_size: int = MAX_FILE_SIZE
- ignore_patterns: set[str] | None = None
- include_patterns: set[str] | None = None
- pattern_type: str | None = None
+ ignore_patterns: Optional[set[str]] = None
+ include_patterns: Optional[set[str]] = None
+ pattern_type: Optional[str] = None
 
 
 async def parse_query(
  source: str,
  max_file_size: int,
  from_web: bool,
- include_patterns: set[str] | str | None = None,
- ignore_patterns: set[str] | str | None = None,
+ include_patterns: Optional[Union[str, set[str]]] = None,
+ ignore_patterns: Optional[Union[str, set[str]]] = None,
 ) -> ParsedQuery:
  """
  Parse the input source (URL or path) to extract relevant details for the query.
@@ -70,9 +71,9 @@ async def parse_query(
  The maximum file size in bytes to include.
  from_web : bool
  Flag indicating whether the source is a web URL.
- include_patterns : set[str] | str | None, optional
+ include_patterns : Union[str, set[str]], optional
  Patterns to include, by default None. Can be a set of strings or a single string.
- ignore_patterns : set[str] | str | None, optional
+ ignore_patterns : Union[str, set[str]], optional
  Patterns to ignore, by default None. Can be a set of strings or a single string.
 
  Returns
@@ -208,7 +209,7 @@ async def _parse_repo_source(source: str) -> ParsedQuery:
  return parsed
 
 
-async def _configure_branch_and_subpath(remaining_parts: list[str], url: str) -> str | None:
+async def _configure_branch_and_subpath(remaining_parts: list[str], url: str) -> Optional[str]:
  """
  Configure the branch and subpath based on the remaining parts of the URL.
  Parameters
@@ -219,7 +220,7 @@ async def _configure_branch_and_subpath(remaining_parts: list[str], url: str) ->
  The URL of the repository.
  Returns
  -------
- str | None
+ str, optional
  The branch name if found, otherwise None.
 
  """
@@ -283,7 +284,7 @@ def _normalize_pattern(pattern: str) -> str:
  return pattern
 
 
-def _parse_patterns(pattern: set[str] | str) -> set[str]:
+def _parse_patterns(pattern: Union[str, set[str]]) -> set[str]:
  """
  Parse and validate file/directory patterns for inclusion or exclusion.