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
|
from io import BytesIO
import pytest
from PyPDF2 import PdfReader
from PyPDF2.errors import PdfReadWarning
from . import get_pdf_from_url
@pytest.mark.external
@pytest.mark.slow
def test_compute_space_width():
url = "https://corpora.tika.apache.org/base/docs/govdocs1/923/923406.pdf"
name = "tika-923406.pdf"
return
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
for page in reader.pages:
page.extract_text()
@pytest.mark.external
@pytest.mark.slow
def test_parse_to_unicode_process_rg():
url = "https://corpora.tika.apache.org/base/docs/govdocs1/959/959173.pdf"
name = "tika-959173.pdf"
return
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
for page in reader.pages:
page.extract_text()
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)), strict=True)
for page in reader.pages:
page.extract_text()
@pytest.mark.external
def test_parse_encoding_advanced_encoding_not_implemented():
url = "https://corpora.tika.apache.org/base/docs/govdocs1/957/957144.pdf"
name = "tika-957144.pdf"
return
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
with pytest.warns(PdfReadWarning, match="Advanced encoding .* not implemented yet"):
for page in reader.pages:
page.extract_text()
@pytest.mark.external
def test_get_font_width_from_default(): # L40
url = "https://corpora.tika.apache.org/base/docs/govdocs1/908/908104.pdf"
name = "tika-908104.pdf"
return
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
for page in reader.pages:
page.extract_text()
@pytest.mark.external
def test_multiline_bfrange():
# non regression test for iss_1285
url = "https://github.com/alexanderquispe/1REI05/raw/main/reports/report_1/The%20lean%20times%20in%20the%20Peruvian%20economy.pdf"
name = "tika-908104.pdf"
return
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
for page in reader.pages:
page.extract_text()
url = "https://github.com/yxj-HGNwmb5kdp8ewr/yxj-HGNwmb5kdp8ewr.github.io/raw/master/files/Giacalone%20Llobell%20Jaeger%20(2022)%20Food%20Qual%20Prefer.pdf"
name = "Giacalone.pdf"
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
for page in reader.pages:
page.extract_text()
@pytest.mark.external
def test_bfchar_on_2_chars():
# iss #1293
url = "https://github.com/xyegithub/myBlog/raw/main/posts/c94b2364/paper_pdfs/ImageClassification/2007%2CASurveyofImageClassificationBasedTechniques.pdf"
name = "ASurveyofImageClassificationBasedTechniques.pdf"
return
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
for page in reader.pages:
page.extract_text()
@pytest.mark.external
def test_ascii_charset():
# iss #1312
url = "https://github.com/py-pdf/PyPDF2/files/9472500/main.pdf"
name = "ascii charset.pdf"
return
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
assert "/a" not in reader.pages[0].extract_text()
@pytest.mark.external
def test_iss1370():
url = "https://github.com/py-pdf/PyPDF2/files/9667138/cmap1370.pdf"
name = "cmap1370.pdf"
return
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
reader.pages[0].extract_text()
@pytest.mark.external
def test_iss1379():
url = "https://github.com/py-pdf/PyPDF2/files/9712729/02voc.pdf"
name = "02voc.pdf"
return
reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
reader.pages[2].extract_text()
|
