smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-19 21:16:56 +01:00
Code Issues Projects Releases Packages Wiki Activity

Adds better handling for files with invalid utf8 content

Browse source
This commit is contained in:
Trenton H 2023-05-12 14:21:32 -07:00
parent 350c20d6ab
commit 111960c530
6 changed files with 47 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

5
src/paperless_tesseract/parsers.py
View file

@ -122,8 +122,7 @@ class RasterisedDocumentParser(DocumentParser):
and os.path.isfile(sidecar_file)
and settings.OCR_MODE != "redo"
):
with open(sidecar_file) as f:
text = f.read()
text = self.read_file_handle_unicode_errors(sidecar_file)
if "[OCR skipped on page" not in text:
# This happens when there's already text in the input file.
@ -155,7 +154,7 @@ class RasterisedDocumentParser(DocumentParser):
tmp.name,
],
)
text = tmp.read()
text = self.read_file_handle_unicode_errors(Path(tmp.name))
return post_process_text(text)