2024-01-23 06:07:03 +00:00
|
|
|
import os
|
|
|
|
import tempfile
|
|
|
|
from abc import ABC
|
2024-03-26 15:51:52 +00:00
|
|
|
from pathlib import Path
|
|
|
|
from typing import List, Union
|
2024-01-23 06:07:03 +00:00
|
|
|
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):
|
2024-03-26 15:51:52 +00:00
|
|
|
def __init__(self, file_path: Union[str, Path]):
|
2024-01-23 06:07:03 +00:00
|
|
|
"""Initialize with file path."""
|
2024-03-26 15:51:52 +00:00
|
|
|
self.file_path = str(file_path)
|
2024-01-23 06:07:03 +00:00
|
|
|
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)
|
|
|
|
|
2024-04-10 17:01:19 +00:00
|
|
|
self.parser = VsdxParser() # type: ignore[misc]
|
2024-01-23 06:07:03 +00:00
|
|
|
|
|
|
|
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]:
|
2024-04-10 17:01:19 +00:00
|
|
|
blob = Blob.from_path(self.file_path) # type: ignore[attr-defined]
|
2024-01-23 06:07:03 +00:00
|
|
|
return list(self.parser.parse(blob))
|