mirror of
https://github.com/kanzure/pdfparanoia.git
synced 2025-07-04 20:37:38 +02:00
SPIE watermark removal
This is slightly broken because the SPIE plugin removes more than just watermarks. For some reason it seems to also remove images and large blocks of text from the paper. However, the object that is being removed is tiny. In the unit testing sample, the removed object is pdf stream 55. For now, SPIE is partially disabled until this is fixed. The problem does not originate from the other plugins. fixes #20
This commit is contained in:
parent
9d7fd1dbb6
commit
caed396870
7 changed files with 74 additions and 2 deletions
14
tests/test_spie.py
Normal file
14
tests/test_spie.py
Normal file
|
@ -0,0 +1,14 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
import unittest
|
||||
import pdfparanoia
|
||||
|
||||
class SPIETestCase(unittest.TestCase):
|
||||
def test_spie(self):
|
||||
file_handler = open("tests/samples/spie/266c86e6f47e39415584450f5a3af4d0.pdf", "rb")
|
||||
content = file_handler.read()
|
||||
self.assertIn("\n46 0 obj", content)
|
||||
|
||||
output = pdfparanoia.plugins.SPIE.scrub(content)
|
||||
self.assertNotIn("\n55 0 obj", output)
|
||||
|
Loading…
Add table
Add a link
Reference in a new issue