Be more intelligent about PDFs without OCR layer
This commit is contained in:
parent
0cb21ffae6
commit
f19d9e0877
2 changed files with 9 additions and 1 deletions
|
@ -47,7 +47,9 @@ class OllamaImporter(Importer):
|
|||
|
||||
def identify(self, filepath):
|
||||
mimetype, encoding = mimetypes.guess_type(filepath)
|
||||
return mimetype == "application/pdf"
|
||||
if mimetype != "application/pdf":
|
||||
return False
|
||||
return "".join(pdf_lines(filepath)) != ""
|
||||
|
||||
def account(self, filepath):
|
||||
return self.file_account
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue