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
|
# -*- coding: utf-8 -*-
import sys
import unittest
from os.path import abspath, dirname
rootDir = dirname(dirname(abspath(__file__)))
sys.path.insert(0, rootDir)
from pyglossary.html_utils import unescape_unicode
class UnescapeUnicodeTest(unittest.TestCase):
def case(self, text, expected):
actual = unescape_unicode(text)
self.assertEqual(actual, expected)
def test(self):
self.case("<", "<")
self.case(">", ">")
self.case("&", "&")
self.case(""", """)
self.case("'", "'")
self.case(" ", " ")
self.case(" ", " ")
self.case("<á>", "<á>")
self.case("/wəːkiŋtiːm/", "/wəːkiŋtiːm/")
# Babylon dictionaries contain a lot of non-standard entity,
# references for example, csdot, fllig, nsm, cancer, thlig,
# tsdot, upslur...
self.case("<&etilde;", "<ẽ")
self.case("<⅓", "<⅓")
self.case("<⅔", "<⅔")
self.case("<ĩ", "<ĩ")
self.case("<&ldash;", "<–")
self.case("<ů", "<ů")
self.case("<ũ", "<ũ")
self.case("<&wring;", "<ẘ")
self.case("<&xfrac13;", "<⅓")
self.case("<ŷ", "<ŷ")
self.case("<&ygrave;", "<ỳ")
self.case("<&yring;", "<ẙ")
self.case("<&ytilde;", "<ỹ")
def benchmark_main():
import timeit
from random import choice
from english_words import english_words_set
english_words_list = list(english_words_set)
textList = []
for _ in range(20):
text = ""
for _ in range(10):
text += choice(english_words_list) + " "
textList.append(text)
print("avg length:", sum(len(text) for text in textList) / len(textList))
def run_benchmark1():
for text in textList:
unescape_unicode(text)
print("benchmark 1:", timeit.timeit("run_benchmark1()", globals=locals()))
if __name__ == "__main__":
if "-b" in sys.argv:
benchmark_main()
else:
unittest.main()
|
