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
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
|
"""
A bunch of quick tests that confirm nothing is horribly wrong
"""
import gc
from contextlib import suppress
from shutil import copy
from concurrent.futures import ThreadPoolExecutor, as_completed, TimeoutError
from io import BytesIO
import threading
import os
import time
import signal
import pytest
import pikepdf
from pikepdf import Name, Object, Pdf, Stream
def test_minimum_qpdf_version():
from pikepdf import _qpdf
assert _qpdf.qpdf_version() >= '7.0.0'
def test_open_pdf(resources):
pdf = pikepdf.open(resources / 'graph.pdf')
assert '1.3' <= pdf.pdf_version <= '1.7'
assert pdf.root['/Pages']['/Count'] == 1
def test_open_pdf_password(resources):
pdf = Pdf.open(resources / 'graph-encrypted.pdf', password='owner')
assert pdf.root['/Pages']['/Count'] == 1
def test_attr_access(resources):
pdf = Pdf.open(resources / 'graph.pdf')
assert int(pdf.root.Pages.Count) == 1
def test_create_pdf(outdir):
pdf = Pdf.new()
font = pdf.make_indirect(
Object.parse(
b"""
<<
/Type /Font
/Subtype /Type1
/Name /F1
/BaseFont /Helvetica
/Encoding /WinAnsiEncoding
>>"""
)
)
width, height = 100, 100
image_data = b"\xff\x7f\x00" * (width * height)
image = Stream(pdf, image_data)
image.stream_dict = Object.parse(
b"""
<<
/Type /XObject
/Subtype /Image
/ColorSpace /DeviceRGB
/BitsPerComponent 8
/Width 100
/Height 100
>>"""
)
rfont = {'/F1': font}
xobj = {'/Im1': image}
resources = {'/Font': rfont, '/XObject': xobj}
mediabox = [0, 0, 612, 792]
stream = b"""
BT /F1 24 Tf 72 720 Td (Hi there) Tj ET
q 144 0 0 144 234 324 cm /Im1 Do Q
"""
contents = Stream(pdf, stream)
page_dict = {
'/Type': Name('/Page'),
'/MediaBox': mediabox,
'/Contents': contents,
'/Resources': resources,
}
qpdf_page_dict = page_dict
page = pdf.make_indirect(qpdf_page_dict)
pdf.pages.append(page)
pdf.save(outdir / 'hi.pdf')
def test_copy_semantics(resources):
pdf = Pdf.open(resources / 'graph.pdf')
# Ensure that we can name a reference to a child object and view the
# changes from the parent
page = pdf.pages[0]
mediabox = page['/MediaBox']
assert mediabox[2] != 0
mediabox[2] = 0
assert page['/MediaBox'][2] == mediabox[2]
def test_copy_page_keepalive(resources, outdir):
# str for py<3.6
copy(str(resources / 'sandwich.pdf'), str(outdir / 'sandwich.pdf'))
src = Pdf.open(outdir / 'sandwich.pdf')
pdf = Pdf.open(resources / 'graph.pdf')
pdf.pages.append(src.pages[0])
del src
src = None
gc.collect()
with suppress(PermissionError):
(outdir / 'sandwich.pdf').unlink()
pdf.save(outdir / 'out.pdf')
def test_open_save(resources, outdir):
out = str(outdir / 'graph.pdf')
copy(str(resources / 'graph.pdf'), out)
src = Pdf.open(out)
with pytest.raises(ValueError):
src.save(out)
src.save(outdir / 'graph2.pdf')
def test_readme_example(resources, outdir):
# Elegant, Pythonic API
pdf = pikepdf.open(resources / 'fourpages.pdf')
assert len(pdf.pages) == 4
del pdf.pages[-1]
assert len(pdf.pages) == 3
pdf.save(outdir / 'output.pdf')
|
