AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-12 19:49:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix file encoding detection bug (#653)

Browse Source 
### What problem does this PR solve?

#651 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
KevinHuSh 2024-05-07 10:01:24 +08:00 committed by GitHub
parent ca5acc151a
commit c6b6c748ae
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
api/apps/file_app.py
View File

@ -335,7 +335,7 @@ def get(file_id):
response = flask.make_response(MINIO.get(file.parent_id, file.location)) response = flask.make_response(MINIO.get(file.parent_id, file.location))
ext = re.search(r"\.([^.]+)$", file.name) ext = re.search(r"\.([^.]+)$", file.name)
if ext: if ext:
if doc.type == FileType.VISUAL.value: if file.type == FileType.VISUAL.value:
response.headers.set('Content-Type', 'image/%s' % ext.group(1)) response.headers.set('Content-Type', 'image/%s' % ext.group(1))
else: else:
response.headers.set( response.headers.set(

6
rag/nlp/__init__.py
View File

@ -28,11 +28,17 @@ all_codecs = [
def find_codec(blob): def find_codec(blob):
global all_codecs global all_codecs
for c in all_codecs: for c in all_codecs:
try:
blob[:1024].decode(c)
return c
except Exception as e:
pass
try: try:
blob.decode(c) blob.decode(c)
return c return c
except Exception as e: except Exception as e:
pass pass
return "utf-8" return "utf-8"