| 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 |
|
| 15 | def test_NextUtf8Char(self):
|
| 16 | CASES = [
|
| 17 | ([1, 3, 6, 10], '\x24\xC2\xA2\xE0\xA4\xB9\xF0\x90\x8D\x88'),
|
| 18 | ([1, 3,
|
| 19 | 'Invalid UTF-8 continuation byte'], '\x24\xC2\xA2\xE0\xE0\xA4'),
|
| 20 | ([1, 3, 6, 'Invalid start of UTF-8 character'],
|
| 21 | '\x24\xC2\xA2\xE0\xA4\xA4\xB9'),
|
| 22 | ([1, 3, 'Invalid start of UTF-8 character'], '\x24\xC2\xA2\xFF'),
|
| 23 | ([1, 'Incomplete UTF-8 character'], '\x24\xF0\x90\x8D'),
|
| 24 | ]
|
| 25 | for expected_indexes, input_str in CASES:
|
| 26 | print()
|
| 27 | print('NextUtf8Char case %r %r' % (expected_indexes, input_str))
|
| 28 | i = 0
|
| 29 | actual_indexes = []
|
| 30 | while True:
|
| 31 | try:
|
| 32 | i = string_ops.NextUtf8Char(input_str, i)
|
| 33 | actual_indexes.append(i)
|
| 34 | if i >= len(input_str):
|
| 35 | break
|
| 36 | except error.Strict as e:
|
| 37 | actual_indexes.append(e.msg)
|
| 38 | break
|
| 39 | self.assertEqual(expected_indexes, actual_indexes)
|
| 40 |
|
| 41 | def test_DecodeNextUtf8Char(self):
|
| 42 | s = '\x61\xC3\x8A\xE1\x82\xA0\xF0\x93\x80\x80'
|
| 43 | codepoints = [0x61, 0xCA, 0x10A0, 0x13000]
|
| 44 | start = 0
|
| 45 | for codepoint in codepoints:
|
| 46 | end = string_ops.NextUtf8Char(s, start)
|
| 47 | codepoint = string_ops.DecodeUtf8Char(s, start)
|
| 48 | self.assertEqual(codepoint, codepoint)
|
| 49 | start = end
|
| 50 |
|
| 51 | def test_DecodePrevUtf8Char(self):
|
| 52 | s = '\x61\xC3\x8A\xE1\x82\xA0\xF0\x93\x80\x80'
|
| 53 | codepoints = [0x61, 0xCA, 0x10A0, 0x13000]
|
| 54 | end = len(s)
|
| 55 | for codepoint in reversed(codepoints):
|
| 56 | start = string_ops.PreviousUtf8Char(s, end)
|
| 57 | codepoint = string_ops.DecodeUtf8Char(s, start)
|
| 58 | self.assertEqual(codepoint, codepoint)
|
| 59 | end = start
|
| 60 |
|
| 61 | def test_DecodeUtf8CharError(self):
|
| 62 | CASES = [
|
| 63 | ('Incomplete UTF-8 character', '\xC0'),
|
| 64 | ('Invalid UTF-8 continuation byte', '\xC0\x01'),
|
| 65 | ('Invalid start of UTF-8 character', '\xff'),
|
| 66 | ]
|
| 67 | for msg, input in CASES:
|
| 68 | with self.assertRaises(error.Expr) as ctx:
|
| 69 | string_ops.DecodeUtf8Char(input, 0)
|
| 70 | self.assertEqual(ctx.exception.msg, msg)
|
| 71 |
|
| 72 | def test_PreviousUtf8Char(self):
|
| 73 | # The error messages could probably be improved for more consistency
|
| 74 | # with NextUtf8Char, at the expense of more complexity.
|
| 75 | CASES = [
|
| 76 | ([6, 3, 1, 0], '\x24\xC2\xA2\xE0\xA4\xB9\xF0\x90\x8D\x88'),
|
| 77 | ([6, 3, 1, 'Invalid start of UTF-8 character'],
|
| 78 | '\xA2\xC2\xA2\xE0\xA4\xB9\xF0\x90\x8D\x88'),
|
| 79 | ([10, 'Invalid start of UTF-8 character'],
|
| 80 | '\xF0\x90\x8D\x88\x90\x8D\x88\x90\x8D\x88\x24'),
|
| 81 | ([3, 'Invalid start of UTF-8 character'], '\xF0\x90\x8D\x24'),
|
| 82 | ]
|
| 83 | for expected_indexes, input_str in CASES:
|
| 84 | print()
|
| 85 | print('PreviousUtf8Char case %r %r' %
|
| 86 | (expected_indexes, input_str))
|
| 87 | i = len(input_str)
|
| 88 | actual_indexes = []
|
| 89 | while True:
|
| 90 | try:
|
| 91 | i = string_ops.PreviousUtf8Char(input_str, i)
|
| 92 | actual_indexes.append(i)
|
| 93 | if i == 0:
|
| 94 | break
|
| 95 | except error.Strict as e:
|
| 96 | actual_indexes.append(e.msg)
|
| 97 | break
|
| 98 | self.assertEqual(expected_indexes, actual_indexes)
|
| 99 |
|
| 100 | # The UTF-8 encoding of all the characters from string_ops.SPACES.
|
| 101 | # See comments there about why that set of characters was chosen.
|
| 102 | #
|
| 103 | # Generated by evaluating this Python3 fragment:
|
| 104 | #
|
| 105 | # ```
|
| 106 | # print('\u0009\u000a\u000b\u000c\u000d\u0020\u00a0\ufeff'.encode('utf-8'))
|
| 107 | # ```
|
| 108 | ALL_WHITESPACES_UTF8 = '\t\n\x0b\x0c\r \xc2\xa0\xef\xbb\xbf'
|
| 109 |
|
| 110 | def test_StartsWithWhitespaceByteRange(self):
|
| 111 | CASES = [
|
| 112 | ((0, 0), ''),
|
| 113 | ((0, 0), 'x'),
|
| 114 | ((0, 1), ' x'),
|
| 115 | ((0, 1), ' x '),
|
| 116 | ((0, 2), '\t x '),
|
| 117 | ((0, 11), LibStrTest.ALL_WHITESPACES_UTF8),
|
| 118 | ]
|
| 119 | for expected, input_str in CASES:
|
| 120 | print()
|
| 121 | print('StartsWithWhitespaceByteRange case %r %r' %
|
| 122 | (expected, input_str))
|
| 123 | self.assertEqual(
|
| 124 | expected, string_ops.StartsWithWhitespaceByteRange(input_str))
|
| 125 |
|
| 126 | def test_EndsWithWhitespaceByteRange(self):
|
| 127 | CASES = [
|
| 128 | ((0, 0), ''),
|
| 129 | ((1, 1), 'x'),
|
| 130 | ((2, 2), ' x'),
|
| 131 | ((2, 3), ' x '),
|
| 132 | ((2, 4), ' x \t'),
|
| 133 | ((0, 11), LibStrTest.ALL_WHITESPACES_UTF8),
|
| 134 | ]
|
| 135 |
|
| 136 | for expected, input_str in CASES:
|
| 137 | print()
|
| 138 | print('EndsWithWhitespaceByteRange case %r %r' %
|
| 139 | (expected, input_str))
|
| 140 | self.assertEqual(expected,
|
| 141 | string_ops.EndsWithWhitespaceByteRange(input_str))
|
| 142 |
|
| 143 | def testUnarySuffixOpDemo(self):
|
| 144 | print(string_ops)
|
| 145 |
|
| 146 | s = 'abcd'
|
| 147 | n = len(s)
|
| 148 |
|
| 149 | # All of these loops test exactly 4.
|
| 150 | # NOTE: These are manually copied into DoUnarySuffixOp
|
| 151 |
|
| 152 | print('## shortest prefix')
|
| 153 | for i in xrange(1, n + 1):
|
| 154 | print('%d test %06r return %06r' % (i, s[:i], s[i:]))
|
| 155 | print()
|
| 156 |
|
| 157 | print('# longest prefix')
|
| 158 | for i in xrange(n, 0, -1):
|
| 159 | print('%d test %06r return %06r' % (i, s[:i], s[i:]))
|
| 160 | print()
|
| 161 |
|
| 162 | print('% shortest suffix')
|
| 163 | for i in xrange(n - 1, -1, -1):
|
| 164 | print('%d test %06r return %06r' % (i, s[i:], s[:i]))
|
| 165 | print()
|
| 166 |
|
| 167 | print('%% longest suffix')
|
| 168 | for i in xrange(0, n):
|
| 169 | print('%d test %06r return %06r' % (i, s[i:], s[:i]))
|
| 170 | print()
|
| 171 |
|
| 172 | def testPatSubAllMatches(self):
|
| 173 | s = 'oXooXoooX'
|
| 174 |
|
| 175 | # Match positions
|
| 176 | self.assertEqual([(1, 3), (4, 6)],
|
| 177 | string_ops._AllMatchPositions(s, '(X.)'))
|
| 178 |
|
| 179 | # No match
|
| 180 | self.assertEqual([], string_ops._AllMatchPositions(s, '(z)'))
|
| 181 |
|
| 182 | # Replacement
|
| 183 | self.assertEqual('o_o_ooX', string_ops._PatSubAll(s, '(X.)', '_'))
|
| 184 |
|
| 185 | # Replacement with no match
|
| 186 | self.assertEqual(s, string_ops._PatSubAll(s, '(z)', '_'))
|
| 187 |
|
| 188 |
|
| 189 | if __name__ == '__main__':
|
| 190 | unittest.main()
|