langchain_community.document_loaders.sharepoint

"""从Sharepoint文档库加载数据的加载程序"""
from __future__ import annotations

from typing import Iterator, List, Optional, Sequence

from langchain_core.documents import Document
from langchain_core.pydantic_v1 import Field

from langchain_community.document_loaders.base_o365 import (
    O365BaseLoader,
    _FileType,
)
from langchain_community.document_loaders.parsers.registry import get_parser


[docs]class SharePointLoader(O365BaseLoader):
    """从`SharePoint`加载。"""

    document_library_id: str = Field(...)
    """要加载数据的SharePoint文档库的ID。"""
    folder_path: Optional[str] = None
    """从中加载数据的文件夹路径。"""
    object_ids: Optional[List[str]] = None
    """要加载数据的对象的ID。"""
    folder_id: Optional[str] = None
    """要加载数据的文件夹的ID。"""

    @property
    def _file_types(self) -> Sequence[_FileType]:
        """返回支持的文件类型。"""
        return _FileType.DOC, _FileType.DOCX, _FileType.PDF

    @property
    def _scopes(self) -> List[str]:
        """返回所需的范围。"""
        return ["sharepoint", "basic"]

[docs]    def lazy_load(self) -> Iterator[Document]:
        """懒加载文档。在大规模工作时使用。"""
        try:
            from O365.drive import Drive, Folder
        except ImportError:
            raise ImportError(
                "O365 package not found, please install it with `pip install o365`"
            )
        drive = self._auth().storage().get_drive(self.document_library_id)
        if not isinstance(drive, Drive):
            raise ValueError(f"There isn't a Drive with id {self.document_library_id}.")
        blob_parser = get_parser("default")
        if self.folder_path:
            target_folder = drive.get_item_by_path(self.folder_path)
            if not isinstance(target_folder, Folder):
                raise ValueError(f"There isn't a folder with path {self.folder_path}.")
            for blob in self._load_from_folder(target_folder):
                yield from blob_parser.lazy_parse(blob)
        if self.folder_id:
            target_folder = drive.get_item(self.folder_id)
            if not isinstance(target_folder, Folder):
                raise ValueError(f"There isn't a folder with path {self.folder_path}.")
            for blob in self._load_from_folder(target_folder):
                yield from blob_parser.lazy_parse(blob)
        if self.object_ids:
            for blob in self._load_from_object_ids(drive, self.object_ids):
                yield from blob_parser.lazy_parse(blob)
        if not (self.folder_path or self.folder_id or self.object_ids):
            target_folder = drive.get_root_folder()
            if not isinstance(target_folder, Folder):
                raise ValueError("Unable to fetch root folder")
            for blob in self._load_from_folder(target_folder):
                yield from blob_parser.lazy_parse(blob)
Source code for langchain_community.document_loaders.sharepoint
