langchain/libs/community/langchain_community/document_loaders/vsdx.py
Leonid Ganeline 4cb5f4c353
community[patch]: import flattening fix (#20110)
This PR should make it easier for linters to do type checking and for IDEs to jump to definition of code.

See #20050 as a template for this PR.
- As a byproduct: Added 3 missed `test_imports`.
- Added missed `SolarChat` in to __init___.py Added it into test_import
ut.
- Added `# type: ignore` to fix linting. It is not clear, why linting
errors appear after ^ changes.

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2024-04-10 13:01:19 -04:00

55 lines
1.9 KiB
Python

import os
import tempfile
from abc import ABC
from pathlib import Path
from typing import List, Union
from urllib.parse import urlparse
import requests
from langchain_community.docstore.document import Document
from langchain_community.document_loaders.base import BaseLoader
from langchain_community.document_loaders.blob_loaders import Blob
from langchain_community.document_loaders.parsers import VsdxParser
class VsdxLoader(BaseLoader, ABC):
def __init__(self, file_path: Union[str, Path]):
"""Initialize with file path."""
self.file_path = str(file_path)
if "~" in self.file_path:
self.file_path = os.path.expanduser(self.file_path)
# If the file is a web path, download it to a temporary file, and use that
if not os.path.isfile(self.file_path) and self._is_valid_url(self.file_path):
r = requests.get(self.file_path)
if r.status_code != 200:
raise ValueError(
"Check the url of your file; returned status code %s"
% r.status_code
)
self.web_path = self.file_path
self.temp_file = tempfile.NamedTemporaryFile()
self.temp_file.write(r.content)
self.file_path = self.temp_file.name
elif not os.path.isfile(self.file_path):
raise ValueError("File path %s is not a valid file or url" % self.file_path)
self.parser = VsdxParser() # type: ignore[misc]
def __del__(self) -> None:
if hasattr(self, "temp_file"):
self.temp_file.close()
@staticmethod
def _is_valid_url(url: str) -> bool:
"""Check if the url is valid."""
parsed = urlparse(url)
return bool(parsed.netloc) and bool(parsed.scheme)
def load(self) -> List[Document]:
blob = Blob.from_path(self.file_path) # type: ignore[attr-defined]
return list(self.parser.parse(blob))