Add docstrings, refactor process_query, and move AsyncTimeoutError to gitingest.exceptions

src/gitingest/cli.py

@@ -17,7 +17,32 @@ def main(
     exclude_pattern: tuple[str, ...],
     include_pattern: tuple[str, ...],
 ) -> None:
-    """Analyze a directory and create a text dump of its contents."""
+    """
+    Analyze a directory or repository and create a text dump of its contents.
+
+    This command analyzes the contents of a specified source directory or repository,
+    applies custom include and exclude patterns, and generates a text summary of the analysis
+    which is then written to an output file.
+
+    Parameters
+    ----------
+    source : str
+        The source directory or repository to analyze.
+    output : str | None
+        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.
+    include_pattern : tuple[str, ...]
+        A tuple of patterns to include during the analysis. Only files matching these patterns will be processed.
+
+    Raises
+    ------
+    click.Abort
+        If there is an error during the execution of the command, this exception is raised to abort the process.
+    """
     try:
         # Combine default and custom ignore patterns
         exclude_patterns = list(exclude_pattern)

src/gitingest/clone.py

@@ -1,13 +1,32 @@
 import asyncio
 from dataclasses import dataclass
 
-from gitingest.utils import AsyncTimeoutError, async_timeout
+from gitingest.exceptions import AsyncTimeoutError
+from gitingest.utils import async_timeout
 
 CLONE_TIMEOUT: int = 20
 
 
 @dataclass
 class CloneConfig:
+    """
+    Configuration for cloning a Git repository.
+
+    This class holds the necessary parameters for cloning a repository to a local path, including
+    the repository's URL, the target local path, and optional parameters for a specific commit or branch.
+
+    Attributes
+    ----------
+    url : str
+        The URL of the Git repository to clone.
+    local_path : str
+        The local directory where the repository will be cloned.
+    commit : str | None, optional
+        The specific commit hash to check out after cloning (default is None).
+    branch : str | None, optional
+        The branch to clone (default is None).
+    """
+
     url: str
     local_path: str
     commit: str | None = None
@@ -17,7 +36,11 @@ class CloneConfig:
 @async_timeout(CLONE_TIMEOUT)
 async def clone_repo(config: CloneConfig) -> tuple[bytes, bytes]:
     """
-    Clones a repository to a local path based on the provided query parameters.
+    Clones 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 or commit if provided, and it raises exceptions if
+    any errors occur during the cloning process.
 
     Parameters
     ----------
@@ -30,7 +53,7 @@ async def clone_repo(config: CloneConfig) -> tuple[bytes, bytes]:
 
     Returns
     -------
-    Tuple[bytes, bytes]
+    tuple[bytes, bytes]
         A tuple containing the stdout and stderr of the git commands executed.
 
     Raises
@@ -123,7 +146,7 @@ async def _run_git_command(*args: str) -> tuple[bytes, bytes]:
 
     Returns
     -------
-    Tuple[bytes, bytes]
+    tuple[bytes, bytes]
         A tuple containing the stdout and stderr of the git command.
 
     Raises

src/gitingest/exceptions.py

@@ -0,0 +1,29 @@
+class InvalidPatternError(ValueError):
+    """
+    Exception raised when a pattern contains invalid characters.
+
+    This exception is used to signal that a pattern provided for some operation
+    contains characters that are not allowed. The valid characters for the pattern
+    include alphanumeric characters, dash (-), underscore (_), dot (.), forward slash (/),
+    plus (+), and asterisk (*).
+
+    Parameters
+    ----------
+    pattern : str
+        The invalid pattern that caused the error.
+    """
+
+    def __init__(self, pattern: str) -> None:
+        super().__init__(
+            f"Pattern '{pattern}' contains invalid characters. Only alphanumeric characters, dash (-), "
+            "underscore (_), dot (.), forward slash (/), plus (+), and asterisk (*) are allowed."
+        )
+
+
+class AsyncTimeoutError(Exception):
+    """
+    Raised when an async operation exceeds its timeout limit.
+
+    This exception is used by the `async_timeout` decorator to signal that the wrapped
+    asynchronous function has exceeded the specified time limit for execution.
+    """

src/gitingest/ingest.py

@@ -15,7 +15,39 @@ def ingest(
     exclude_patterns: list[str] | str | None = None,
     output: str | None = None,
 ) -> tuple[str, str, str]:
+    """
+    Main entry point for ingesting a source and processing its contents.
 
+    This function analyzes a source (URL or local path), clones the corresponding repository (if applicable),
+    and processes its files according to the specified query parameters. It returns a summary, a tree-like
+    structure of the files, and the content of the files. The results can optionally be written to an output file.
+
+    Parameters
+    ----------
+    source : str
+        The source to analyze, which can be a URL (for a GitHub repository) or a local directory path.
+    max_file_size : int, optional
+        The maximum allowed file size for file ingestion. Files larger than this size are ignored, by default 10*1024*1024 (10 MB).
+    include_patterns : list[str] | str | None, optional
+        A pattern or list of patterns specifying which files to include in the analysis. If `None`, all files are included.
+    exclude_patterns : list[str] | str | None, optional
+        A pattern or list of patterns specifying which files to exclude from the analysis. If `None`, no files are excluded.
+    output : str | None, optional
+        The file path where the summary and content should be written. If `None`, the results are not written to a file.
+
+    Returns
+    -------
+    tuple[str, str, str]
+        A tuple containing:
+        - A summary string of the analyzed repository or directory.
+        - A tree-like string representation of the file structure.
+        - The content of the files in the repository or directory.
+
+    Raises
+    ------
+    TypeError
+        If `clone_repo` does not return a coroutine, or if the `source` is of an unsupported type.
+    """
     try:
         query = parse_query(
             source=source,
@@ -42,8 +74,8 @@ def ingest(
 
         summary, tree, content = ingest_from_query(query)
 
-        if output:
-            with open(f"{output}", "w") as f:
+        if output is not None:
+            with open(output, "w") as f:
                 f.write(tree + "\n" + content)
 
         return summary, tree, content