OILS
/
osh
/
string_ops_test.py
1 |
#!/usr/bin/env python2
|
2 |
"""
|
3 |
string_ops_test.py: Tests for string_ops.py
|
4 |
"""
|
5 |
from __future__ import print_function
|
6 |
|
7 |
import unittest
|
8 |
|
9 |
from core import error
|
10 |
from osh import string_ops # module under test
|
11 |
|
12 |
|
13 |
class LibStrTest(unittest.TestCase):
|
14 |
def testUtf8Encode(self):
|
15 |
CASES = [
|
16 |
(u'\u0065'.encode('utf-8'), 0x0065),
|
17 |
(u'\u0100'.encode('utf-8'), 0x0100),
|
18 |
(u'\u1234'.encode('utf-8'), 0x1234),
|
19 |
(u'\U00020000'.encode('utf-8'), 0x00020000),
|
20 |
# Out of range gives Unicode replacement character.
|
21 |
('\xef\xbf\xbd', 0x10020000),
|
22 |
]
|
23 |
|
24 |
for expected, code_point in CASES:
|
25 |
print('')
|
26 |
print('Utf8Encode case %r %r' % (expected, code_point))
|
27 |
self.assertEqual(expected, string_ops.Utf8Encode(code_point))
|
28 |
|
29 |
def test_NextUtf8Char(self):
|
30 |
CASES = [
|
31 |
([1, 3, 6, 10], '\x24\xC2\xA2\xE0\xA4\xB9\xF0\x90\x8D\x88'),
|
32 |
([1, 3,
|
33 |
'Invalid UTF-8 continuation byte'], '\x24\xC2\xA2\xE0\xE0\xA4'),
|
34 |
([1, 3, 6, 'Invalid start of UTF-8 character'],
|
35 |
'\x24\xC2\xA2\xE0\xA4\xA4\xB9'),
|
36 |
([1, 3, 'Invalid start of UTF-8 character'], '\x24\xC2\xA2\xFF'),
|
37 |
([1, 'Incomplete UTF-8 character'], '\x24\xF0\x90\x8D'),
|
38 |
]
|
39 |
for expected_indexes, input_str in CASES:
|
40 |
print()
|
41 |
print('_NextUtf8Char case %r %r' % (expected_indexes, input_str))
|
42 |
i = 0
|
43 |
actual_indexes = []
|
44 |
while True:
|
45 |
try:
|
46 |
i = string_ops._NextUtf8Char(input_str, i)
|
47 |
actual_indexes.append(i)
|
48 |
if i >= len(input_str):
|
49 |
break
|
50 |
except error.Strict as e:
|
51 |
actual_indexes.append(e.msg)
|
52 |
break
|
53 |
self.assertEqual(expected_indexes, actual_indexes)
|
54 |
|
55 |
def test_PreviousUtf8Char(self):
|
56 |
# The error messages could probably be improved for more consistency
|
57 |
# with NextUtf8Char, at the expense of more complexity.
|
58 |
CASES = [
|
59 |
([6, 3, 1, 0], '\x24\xC2\xA2\xE0\xA4\xB9\xF0\x90\x8D\x88'),
|
60 |
([6, 3, 1, 'Invalid start of UTF-8 character'],
|
61 |
'\xA2\xC2\xA2\xE0\xA4\xB9\xF0\x90\x8D\x88'),
|
62 |
([10, 'Invalid start of UTF-8 character'],
|
63 |
'\xF0\x90\x8D\x88\x90\x8D\x88\x90\x8D\x88\x24'),
|
64 |
([3, 'Invalid start of UTF-8 character'], '\xF0\x90\x8D\x24'),
|
65 |
]
|
66 |
for expected_indexes, input_str in CASES:
|
67 |
print()
|
68 |
print('PreviousUtf8Char case %r %r' % (expected_indexes, input_str))
|
69 |
i = len(input_str)
|
70 |
actual_indexes = []
|
71 |
while True:
|
72 |
try:
|
73 |
i = string_ops.PreviousUtf8Char(input_str, i)
|
74 |
actual_indexes.append(i)
|
75 |
if i == 0:
|
76 |
break
|
77 |
except error.Strict as e:
|
78 |
actual_indexes.append(e.msg)
|
79 |
break
|
80 |
self.assertEqual(expected_indexes, actual_indexes)
|
81 |
|
82 |
def testUnarySuffixOpDemo(self):
|
83 |
print(string_ops)
|
84 |
|
85 |
s = 'abcd'
|
86 |
n = len(s)
|
87 |
|
88 |
# All of these loops test exactly 4.
|
89 |
# NOTE: These are manually copied into DoUnarySuffixOp
|
90 |
|
91 |
print('## shortest prefix')
|
92 |
for i in xrange(1, n + 1):
|
93 |
print('%d test %06r return %06r' % (i, s[:i], s[i:]))
|
94 |
print()
|
95 |
|
96 |
print('# longest prefix')
|
97 |
for i in xrange(n, 0, -1):
|
98 |
print('%d test %06r return %06r' % (i, s[:i], s[i:]))
|
99 |
print()
|
100 |
|
101 |
print('% shortest suffix')
|
102 |
for i in xrange(n - 1, -1, -1):
|
103 |
print('%d test %06r return %06r' % (i, s[i:], s[:i]))
|
104 |
print()
|
105 |
|
106 |
print('%% longest suffix')
|
107 |
for i in xrange(0, n):
|
108 |
print('%d test %06r return %06r' % (i, s[i:], s[:i]))
|
109 |
print()
|
110 |
|
111 |
def testPatSubAllMatches(self):
|
112 |
s = 'oXooXoooX'
|
113 |
|
114 |
# Match positions
|
115 |
self.assertEqual([(1, 3), (4, 6)],
|
116 |
string_ops._AllMatchPositions(s, '(X.)'))
|
117 |
|
118 |
# No match
|
119 |
self.assertEqual([], string_ops._AllMatchPositions(s, '(z)'))
|
120 |
|
121 |
# Replacement
|
122 |
self.assertEqual('o_o_ooX', string_ops._PatSubAll(s, '(X.)', '_'))
|
123 |
|
124 |
# Replacement with no match
|
125 |
self.assertEqual(s, string_ops._PatSubAll(s, '(z)', '_'))
|
126 |
|
127 |
|
128 |
if __name__ == '__main__':
|
129 |
unittest.main()
|