backend/devops
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

modify scripts

Browse Source
This commit is contained in:
sophon
2025-11-07 09:03:35 +08:00
parent 808dbaa985
commit 17356c79f9
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docker/paperless/plugins/parsers.py
View File

@ -335,6 +335,11 @@ class RasterisedDocumentParser(DocumentParser):
os.environ["OMP_THREAD_LIMIT"] = "1" os.environ["OMP_THREAD_LIMIT"] = "1"
VALID_TEXT_LENGTH = 50 VALID_TEXT_LENGTH = 50
# skip ocr process entirely to save time.
self.text = "defautl text"
self.log.debug("skipping reading file entirely.")
return
if mime_type == "application/pdf": if mime_type == "application/pdf":
text_original = self.extract_text(None, document_path) text_original = self.extract_text(None, document_path)
original_has_text = ( original_has_text = (