smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-09 00:05:21 +01:00
Code Issues Projects Releases Packages Wiki Activity

added checksums for archived documents.

Browse source
This commit is contained in:
jonaswinkler 2020-11-29 12:31:26 +01:00
parent fdaf419a7e
commit 24767f62c7
5 changed files with 57 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

5
src/documents/management/commands/document_archiver.py
View file

@ -1,3 +1,4 @@
import hashlib
import multiprocessing
import ocrmypdf
@ -27,6 +28,8 @@ def handle_document(document):
parser.parse(document.source_path, mime_type)
if parser.get_archive_path():
shutil.copy(parser.get_archive_path(), document.archive_path)
with document.archive_file as f:
document.archive_checksum = hashlib.md5(f.read()).hexdigest()
else:
logging.getLogger(__name__).warning(
f"Parser {parser} did not produce an archived document "
@ -35,7 +38,7 @@ def handle_document(document):
if parser.get_text():
document.content = parser.get_text()
document.save()
document.save()
parser.cleanup()