mirror of
https://github.com/hwchase17/langchain.git
synced 2025-04-30 04:45:23 +00:00
a0c2281540
```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path
import toml
import subprocess
import re
ROOT_DIR = Path(__file__).parents[1]
def main():
for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
print(path)
with open(path, "rb") as f:
pyproject = tomllib.load(f)
try:
pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
"^1.10"
)
pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
"^0.5"
)
except KeyError:
continue
with open(path, "w") as f:
toml.dump(pyproject, f)
cwd = "/".join(path.split("/")[:-1])
completed = subprocess.run(
"poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
logs = completed.stdout.split("\n")
to_ignore = {}
for l in logs:
if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
path, line_no, error_type = re.match(
"^(.*)\:(\d+)\: error:.*\[(.*)\]", l
).groups()
if (path, line_no) in to_ignore:
to_ignore[(path, line_no)].append(error_type)
else:
to_ignore[(path, line_no)] = [error_type]
print(len(to_ignore))
for (error_path, line_no), error_types in to_ignore.items():
all_errors = ", ".join(error_types)
full_path = f"{cwd}/{error_path}"
try:
with open(full_path, "r") as f:
file_lines = f.readlines()
except FileNotFoundError:
continue
file_lines[int(line_no) - 1] = (
file_lines[int(line_no) - 1][:-1] + f" # type: ignore[{all_errors}]\n"
)
with open(full_path, "w") as f:
f.write("".join(file_lines))
subprocess.run(
"poetry run ruff format .; poetry run ruff --select I --fix .",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
if __name__ == "__main__":
main()
```
95 lines
3.2 KiB
Python
95 lines
3.2 KiB
Python
"""Loads data from OneDrive"""
|
|
|
|
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__)
|
|
|
|
|
|
class OneDriveLoader(O365BaseLoader):
|
|
"""Load from `Microsoft OneDrive`."""
|
|
|
|
drive_id: str = Field(...)
|
|
""" The ID of the OneDrive drive to load data from."""
|
|
folder_path: Optional[str] = None
|
|
""" The path to the folder to load data from."""
|
|
object_ids: Optional[List[str]] = None
|
|
""" The IDs of the objects to load data from."""
|
|
|
|
@property
|
|
def _file_types(self) -> Sequence[_FileType]:
|
|
"""Return supported file types."""
|
|
return _FileType.DOC, _FileType.DOCX, _FileType.PDF
|
|
|
|
@property
|
|
def _scopes(self) -> List[str]:
|
|
"""Return required scopes."""
|
|
return ["offline_access", "Files.Read.All"]
|
|
|
|
def _get_folder_from_path(self, drive: Drive) -> Union[Folder, Drive]:
|
|
"""
|
|
Returns the folder or drive object located at the
|
|
specified path relative to the given drive.
|
|
|
|
Args:
|
|
drive (Drive): The root drive from which the folder path is relative.
|
|
|
|
Returns:
|
|
Union[Folder, Drive]: The folder or drive object
|
|
located at the specified path.
|
|
|
|
Raises:
|
|
FileNotFoundError: If the path does not exist.
|
|
"""
|
|
|
|
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
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
"""Load documents lazily. Use this when working at a large scale."""
|
|
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)
|