langchain_community.document_loaders.onedrive

"""从OneDrive加载数据"""
from __future__ import annotations

import logging
from typing import TYPE_CHECKING, Iterator, List, Optional, Sequence, Union

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

if TYPE_CHECKING:
    from O365.drive import Drive, Folder

logger = logging.getLogger(__name__)


[docs]class OneDriveLoader(O365BaseLoader):
    """从`Microsoft OneDrive`加载。"""

    drive_id: str = Field(...)
    """要加载数据的OneDrive驱动器的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。"""

    @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 ["offline_access", "Files.Read.All"]

    def _get_folder_from_path(self, drive: Drive) -> Union[Folder, Drive]:
        """返回位于给定驱动器相对于指定路径的文件夹或驱动器对象。

参数：
    drive（Drive）：文件夹路径相对于的根驱动器。

返回：
    Union[Folder, Drive]：位于指定路径的文件夹或驱动器对象。

引发：
    FileNotFoundError：如果路径不存在。
"""

        subfolder_drive = drive
        if self.folder_path is None:
            return subfolder_drive

        subfolders = [f for f in self.folder_path.split("/") if f != ""]
        if len(subfolders) == 0:
            return subfolder_drive

        items = subfolder_drive.get_items()
        for subfolder in subfolders:
            try:
                subfolder_drive = list(filter(lambda x: subfolder in x.name, items))[0]
                items = subfolder_drive.get_items()
            except (IndexError, AttributeError):
                raise FileNotFoundError("Path {} not exist.".format(self.folder_path))
        return subfolder_drive

[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
        except ImportError:
            raise ImportError(
                "O365 package not found, please install it with `pip install o365`"
            )
        drive = self._auth().storage().get_drive(self.drive_id)
        if not isinstance(drive, Drive):
            raise ValueError(f"There isn't a Drive with id {self.drive_id}.")
        blob_parser = get_parser("default")
        if self.folder_path:
            folder = self._get_folder_from_path(drive)
            for blob in self._load_from_folder(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)
Source code for langchain_community.document_loaders.onedrive
