mirror of
https://github.com/hwchase17/langchain
synced 2024-11-18 09:25:54 +00:00
f7a1fd91b8
So this arose from the https://github.com/langchain-ai/langchain/pull/18397 problem of document loaders not supporting `pathlib.Path`. This pull request provides more uniform support for Path as an argument. The core ideas for this upgrade: - if there is a local file path used as an argument, it should be supported as `pathlib.Path` - if there are some external calls that may or may not support Pathlib, the argument is immidiately converted to `str` - if there `self.file_path` is used in a way that it allows for it to stay pathlib without conversion, is is only converted for the metadata. Twitter handle: https://twitter.com/mwmajewsk
20 lines
590 B
Python
20 lines
590 B
Python
import tokenize
|
|
from pathlib import Path
|
|
from typing import Union
|
|
|
|
from langchain_community.document_loaders.text import TextLoader
|
|
|
|
|
|
class PythonLoader(TextLoader):
|
|
"""Load `Python` files, respecting any non-default encoding if specified."""
|
|
|
|
def __init__(self, file_path: Union[str, Path]):
|
|
"""Initialize with a file path.
|
|
|
|
Args:
|
|
file_path: The path to the file to load.
|
|
"""
|
|
with open(file_path, "rb") as f:
|
|
encoding, _ = tokenize.detect_encoding(f.readline)
|
|
super().__init__(file_path=file_path, encoding=encoding)
|