yann/ScoDoc
1
0
Fork 0
forked from ScoDoc/ScoDoc
Code Issues Pull Requests Projects Releases Wiki Activity

Fix: read non-utf8 archives index

Browse Source
This commit is contained in:
Emmanuel Viennet 2021-12-12 16:53:52 +01:00
parent 848a168f02
commit 3eda56e89c
1 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
app/scodoc/sco_archives.py
View File

@ -47,6 +47,7 @@
qui est une description (humaine, format libre) de l'archive. qui est une description (humaine, format libre) de l'archive.
""" """
import chardet
import datetime import datetime
import glob import glob
import mimetypes import mimetypes
@ -203,8 +204,16 @@ class BaseArchiver(object):
def get_archive_description(self, archive_id): def get_archive_description(self, archive_id):
"""Return description of archive""" """Return description of archive"""
self.initialize() self.initialize()
with open(os.path.join(archive_id, "_description.txt")) as f: filename = os.path.join(archive_id, "_description.txt")
descr = f.read() try:
with open(filename) as f:
descr = f.read()
except UnicodeDecodeError:
# some (old) files may have saved under exotic encodings
with open(filename, "rb") as f:
data = f.read()
descr = data.decode(chardet.detect(data)["encoding"])
return descr return descr
def create_obj_archive(self, oid: int, description: str): def create_obj_archive(self, oid: int, description: str):