paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-30 18:27:45 -05:00
Code Issues Packages Projects Releases Wiki Activity

some more tests.

Browse Source
This commit is contained in:
jonaswinkler
2020-12-01 14:15:43 +01:00
parent 24b8c358cc
commit fd3df1ec58
5 changed files with 441 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/paperless_tesseract/parsers.py
View File

@@ -80,6 +80,12 @@ class RasterisedDocumentParser(DocumentParser):
return None
def parse(self, document_path, mime_type):
if settings.OCR_MODE == "skip_noarchive":
text = get_text_from_pdf(document_path)
if text and len(text) > 50:
self.text = text
return
archive_path = os.path.join(self.tempdir, "archive.pdf")
ocr_args = {
@@ -96,7 +102,7 @@ class RasterisedDocumentParser(DocumentParser):
if settings.OCR_PAGES > 0:
ocr_args['pages'] = f"1-{settings.OCR_PAGES}"
if settings.OCR_MODE == 'skip':
if settings.OCR_MODE in ['skip', 'skip_noarchive']:
ocr_args['skip_text'] = True
elif settings.OCR_MODE == 'redo':
ocr_args['redo_ocr'] = True
@@ -184,6 +190,7 @@ def get_text_from_pdf(pdf_file):
try:
pdf = pdftotext.PDF(f)
except pdftotext.Error:
# might not be a PDF file
return None
text = "\n".join(pdf)