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
62 lines
2.0 KiB
Python
62 lines
2.0 KiB
Python
import logging
|
|
from pathlib import Path
|
|
from typing import Iterator, Optional, Union
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
from langchain_community.document_loaders.helpers import detect_file_encodings
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class TextLoader(BaseLoader):
|
|
"""Load text file.
|
|
|
|
|
|
Args:
|
|
file_path: Path to the file to load.
|
|
|
|
encoding: File encoding to use. If `None`, the file will be loaded
|
|
with the default system encoding.
|
|
|
|
autodetect_encoding: Whether to try to autodetect the file encoding
|
|
if the specified encoding fails.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
file_path: Union[str, Path],
|
|
encoding: Optional[str] = None,
|
|
autodetect_encoding: bool = False,
|
|
):
|
|
"""Initialize with file path."""
|
|
self.file_path = file_path
|
|
self.encoding = encoding
|
|
self.autodetect_encoding = autodetect_encoding
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
"""Load from file path."""
|
|
text = ""
|
|
try:
|
|
with open(self.file_path, encoding=self.encoding) as f:
|
|
text = f.read()
|
|
except UnicodeDecodeError as e:
|
|
if self.autodetect_encoding:
|
|
detected_encodings = detect_file_encodings(self.file_path)
|
|
for encoding in detected_encodings:
|
|
logger.debug(f"Trying encoding: {encoding.encoding}")
|
|
try:
|
|
with open(self.file_path, encoding=encoding.encoding) as f:
|
|
text = f.read()
|
|
break
|
|
except UnicodeDecodeError:
|
|
continue
|
|
else:
|
|
raise RuntimeError(f"Error loading {self.file_path}") from e
|
|
except Exception as e:
|
|
raise RuntimeError(f"Error loading {self.file_path}") from e
|
|
|
|
metadata = {"source": str(self.file_path)}
|
|
yield Document(page_content=text, metadata=metadata)
|