jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

Correctly Handle Text File Encoding to Avoid 'GBK' Codec Errors (#2072)

Browse source
This commit is contained in:
Jackie Moo 2024-06-05 19:47:40 +08:00 • committed by GitHub
commit d8643d1384
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 7 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

9
src/backend/base/langflow/base/data/utils.py
View file

@ -3,7 +3,7 @@ import xml.etree.ElementTree as ET
from concurrent import futures from concurrent import futures
from pathlib import Path from pathlib import Path
from typing import Callable, List, Optional, Text from typing import Callable, List, Optional, Text
import chardet
import yaml import yaml
from langflow.schema.schema import Record from langflow.schema.schema import Record
@ -89,7 +89,12 @@ def retrieve_file_paths(
def read_text_file(file_path: str) -> str: def read_text_file(file_path: str) -> str:
with open(file_path, "r") as f: with open(file_path, "rb") as f:
raw_data = f.read()
result = chardet.detect(raw_data)
encoding = result['encoding']
with open(file_path, "r", encoding=encoding) as f:
return f.read() return f.read()