paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

Changes the error mode to replace instead of ignore, to better highlight where a problem happened

Browse Source
This commit is contained in:
Trenton Holmes
2023-05-13 07:47:21 -07:00
committed by Trenton H
parent 6722b6e31c
commit 2f12206911
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/documents/parsers.py
View File

@@ -329,7 +329,7 @@ class DocumentParser(LoggingMixin):
text = filepath.read_text(encoding="utf-8")
except UnicodeDecodeError as e:
self.log("warning", f"Unicode error during text reading, continuing: {e}")
text = filepath.read_bytes().decode("utf-8", errors="ignore")
text = filepath.read_bytes().decode("utf-8", errors="replace")
return text
def extract_metadata(self, document_path, mime_type):