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
|
import codecs
import glob
import os
import re
import subprocess
import sys
if sys.version_info[:2] < (2, 7):
import unittest2 as unittest
else:
import unittest
import logging
logging.basicConfig(format='%(levelname)s:%(funcName)s:%(message)s',
level=logging.DEBUG)
import html2text
def test_module(fn, google_doc=False, **kwargs):
h = html2text.HTML2Text()
h.fn = fn
if google_doc:
h.google_doc = True
h.ul_item_mark = '-'
h.body_width = 0
h.hide_strikethrough = True
for k, v in kwargs.items():
setattr(h, k, v)
result = get_baseline(fn)
inf = open(fn)
actual = h.handle(inf.read())
inf.close()
return result, actual
def test_command(fn, *args):
args = list(args)
cmd = [sys.executable, '-m', 'html2text.__init__']
if '--googledoc' in args:
args.remove('--googledoc')
cmd += ['-g', '-d', '-b', '0', '-s']
if args:
cmd.extend(args)
cmd += [fn]
result = get_baseline(fn)
pid = subprocess.Popen(cmd, stdout=subprocess.PIPE)
out, _ = pid.communicate()
actual = out.decode('utf8')
if os.name == 'nt':
# Fix the unwanted CR to CRCRLF replacement
# during text pipelining on Windows/cygwin
actual = re.sub(r'\r+', '\r', actual)
actual = actual.replace('\r\n', '\n')
return result, actual
def get_dump_name(fn, suffix):
return '%s-%s_output.md' % (os.path.splitext(fn)[0], suffix)
def get_baseline_name(fn):
return os.path.splitext(fn)[0] + '.md'
def get_baseline(fn):
name = get_baseline_name(fn)
f = codecs.open(name, mode='r', encoding='utf8')
out = f.read()
f.close()
return out
class TestHTML2Text(unittest.TestCase):
pass
def generate_test(fn):
def test_mod(self):
self.maxDiff = None
result, actual = test_module(fn, **module_args)
self.assertEqual(result, actual)
def test_cmd(self):
# Because there is no command-line option to control unicode_snob
if not 'unicode_snob' in module_args:
self.maxDiff = None
result, actual = test_command(fn, *cmdline_args)
self.assertEqual(result, actual)
module_args = {}
cmdline_args = []
base_fn = os.path.basename(fn).lower()
if base_fn.startswith('google'):
module_args['google_doc'] = True
cmdline_args.append('--googledoc')
if base_fn.find('unicode') >= 0:
module_args['unicode_snob'] = True
if base_fn.find('flip_emphasis') >= 0:
module_args['emphasis_mark'] = '*'
module_args['strong_mark'] = '__'
cmdline_args.append('-e')
if base_fn.find('escape_snob') >= 0:
module_args['escape_snob'] = True
cmdline_args.append('--escape-all')
if base_fn.find('table_bypass') >= 0:
module_args['bypass_tables'] = True
cmdline_args.append('--bypass-tables')
if base_fn.startswith('bodywidth'):
#module_args['unicode_snob'] = True
module_args['body_width'] = 0
cmdline_args.append('--body-width=0')
return test_mod, test_cmd
# Originally from http://stackoverflow.com/questions/32899/\
# how-to-generate-dynamic-parametrized-unit-tests-in-python
test_dir_name = os.path.dirname(os.path.realpath(__file__))
for fn in glob.glob("%s/*.html" % test_dir_name):
test_name = 'test_%s' % os.path.splitext(os.path.basename(fn))[0].lower()
test_m, test_c = generate_test(fn)
setattr(TestHTML2Text, test_name + "_mod", test_m)
if test_c:
setattr(TestHTML2Text, test_name + "_cmd", test_c)
if __name__ == "__main__":
unittest.main()
|
