mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-07-21 00:35:23 -04:00
Eugene Yurtsev
e46202829f
# TextLoader auto detect encoding and enhanced exception handling - Add an option to enable encoding detection on `TextLoader`. - The detection is done using `chardet` - The loading is done by trying all detected encodings by order of confidence or raise an exception otherwise. ### New Dependencies: - `chardet` Fixes #4479 ## Before submitting <!-- If you're adding a new integration, include an integration test and an example notebook showing its use! --> ## Who can review? Community members can review the PR once tests pass. Tag maintainers/contributors who might be interested: - @eyurtsev --------- Co-authored-by: blob42 <spike@w530>
60 lines
1.9 KiB
Python
60 lines
1.9 KiB
Python
import logging
|
|
from typing import List, Optional
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.document_loaders.base import BaseLoader
|
|
from langchain.document_loaders.helpers import detect_file_encodings
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class TextLoader(BaseLoader):
|
|
"""Load text files.
|
|
|
|
|
|
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: str,
|
|
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 load(self) -> List[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("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": self.file_path}
|
|
return [Document(page_content=text, metadata=metadata)]
|