Function clone_repo

src/gitingest/clone.py:31–123

Clone a repository to a local path based on the provided configuration. This function handles the process of cloning a Git repository to the local file system. It can clone a specific branch, tag, or commit if provided, and it raises exceptions if any errors occur during the cloning pro

(config: CloneConfig, *, token: str | None = None)

@async_timeout(DEFAULT_TIMEOUT)
async def clone_repo(config: CloneConfig, *, token: str | None = None) -> None:
    """Clone a repository to a local path based on the provided configuration.

    This function handles the process of cloning a Git repository to the local file system.
    It can clone a specific branch, tag, or commit if provided, and it raises exceptions if
    any errors occur during the cloning process.

    Parameters
    ----------
    config : CloneConfig
        The configuration for cloning the repository.
    token : str | None
        GitHub personal access token (PAT) for accessing private repositories.

    Raises
    ------
    ValueError
        If the repository is not found, if the provided URL is invalid, or if the token format is invalid.

    """
    # Extract and validate query parameters
    url: str = config.url
    local_path: str = config.local_path
    partial_clone: bool = config.subpath != "/"

    logger.info(
        "Starting git clone operation",
        extra={
            "url": url,
            "local_path": local_path,
            "partial_clone": partial_clone,
            "subpath": config.subpath,
            "branch": config.branch,
            "tag": config.tag,
            "commit": config.commit,
            "include_submodules": config.include_submodules,
        },
    )

    logger.debug("Ensuring git is installed")
    await ensure_git_installed()

    logger.debug("Creating local directory", extra={"parent_path": str(Path(local_path).parent)})
    await ensure_directory_exists_or_create(Path(local_path).parent)

    logger.debug("Checking if repository exists", extra={"url": url})
    if not await check_repo_exists(url, token=token):
        logger.error("Repository not found", extra={"url": url})
        msg = "Repository not found. Make sure it is public or that you have provided a valid token."
        raise ValueError(msg)

    logger.debug("Resolving commit reference")
    commit = await resolve_commit(config, token=token)
    logger.debug("Resolved commit", extra={"commit": commit})

    clone_cmd = ["git"]
    if token and is_github_host(url):
        clone_cmd += ["-c", create_git_auth_header(token, url=url)]