1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
|
import shutil
from subprocess import PIPE, run
import sys
import pytest
import pikepdf
@pytest.fixture
def pal(resources):
return pikepdf.open(resources / 'pal-1bit-rgb.pdf')
class FilterThru(pikepdf.TokenFilter):
def handle_token(self, token):
return token
class FilterDrop(pikepdf.TokenFilter):
def handle_token(self, token):
return None
class FilterNumbers(pikepdf.TokenFilter):
def __init__(self):
super().__init__()
def handle_token(self, token):
if token.type_ in (pikepdf.TokenType.real, pikepdf.TokenType.integer):
return [token, pikepdf.Token(pikepdf.TokenType.space, b" ")]
class FilterCollectNames(pikepdf.TokenFilter):
def __init__(self):
super().__init__()
self.names = []
def handle_token(self, token):
if token.type_ == pikepdf.TokenType.name:
self.names.append(token.value)
return None
@pytest.mark.parametrize(
'filter, expected',
[
(FilterThru, b'q\n144.0000 0 0 144.0000 0.0000 0.0000 cm\n/Im0 Do\nQ'),
(FilterDrop, b''),
(FilterNumbers, b'144.0000 0 0 144.0000 0.0000 0.0000 '),
],
)
def test_filter_thru(pal, filter, expected):
page = pikepdf.Page(pal.pages[0])
page.add_content_token_filter(filter())
after = page.obj.Contents.read_bytes()
assert after == expected
def test_filter_names(pal):
page = pikepdf.Page(pal.pages[0])
filter = FilterCollectNames()
result = page.get_filtered_contents(filter)
assert result == b''
assert filter.names == ['/Im0']
after = page.obj.Contents.read_bytes()
assert after != b''
class FilterInvalid(pikepdf.TokenFilter):
def handle_token(self, token):
return 42
def test_invalid_handle_token(pal):
page = pikepdf.Page(pal.pages[0])
with pytest.raises((TypeError, pikepdf.PdfError)):
page.get_filtered_contents(FilterInvalid())
def test_invalid_tokenfilter(pal):
page = pikepdf.Page(pal.pages[0])
with pytest.raises(TypeError):
page.get_filtered_contents(list())
def test_tokenfilter_is_abstract(pal):
page = pikepdf.Page(pal.pages[0])
with pytest.raises((RuntimeError, pikepdf.PdfError)):
page.get_filtered_contents(pikepdf.TokenFilter())
|
