File: convert_utf16be_to_utf8_with_errors_tests.cpp

package info (click to toggle)
simdutf 7.7.1-3
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 7,244 kB
  • sloc: cpp: 60,074; ansic: 14,226; python: 3,364; sh: 321; makefile: 12
file content (236 lines) | stat: -rw-r--r-- 8,795 bytes parent folder | download
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
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
#include "simdutf.h"

#include <array>
#include <vector>

#include <tests/helpers/transcode_test_base.h>
#include <tests/helpers/random_int.h>
#include <tests/helpers/test.h>

namespace {
constexpr std::array<size_t, 7> input_size{7, 16, 12, 64, 67, 128, 256};
constexpr simdutf::endianness BE = simdutf::endianness::BIG;

using simdutf::tests::helpers::transcode_utf16_to_utf8_test_base;

} // namespace

TEST(allow_empty_input) {
  std::vector<char16_t> emptydata;
  std::vector<char32_t> output(10);

  auto ret = implementation.convert_utf16be_to_utf32_with_errors(
      emptydata.data(), emptydata.size(), output.data());
  ASSERT_EQUAL(ret.error, simdutf::error_code::SUCCESS);
}

TEST(convert_pure_ASCII) {
  size_t counter = 0;
  auto generator = [&counter]() -> uint32_t { return counter++ & 0x7f; };

  auto procedure = [&implementation](const char16_t *utf16, size_t size,
                                     char *utf8) -> size_t {
    simdutf::result res =
        implementation.convert_utf16be_to_utf8_with_errors(utf16, size, utf8);
    ASSERT_EQUAL(res.error, simdutf::error_code::SUCCESS);
    return res.count;
  };

  auto size_procedure = [&implementation](const char16_t *utf16,
                                          size_t size) -> size_t {
    return implementation.utf8_length_from_utf16be(utf16, size);
  };

  for (size_t size : input_size) {
    transcode_utf16_to_utf8_test_base test(BE, generator, size);
    ASSERT_TRUE(test(procedure));
    ASSERT_TRUE(test.check_size(size_procedure));
  }
}

TEST_LOOP(convert_into_1_or_2_UTF8_bytes) {
  simdutf::tests::helpers::RandomInt random(
      0x0000, 0x07ff, seed); // range for 1 or 2 UTF-8 bytes

  auto procedure = [&implementation](const char16_t *utf16, size_t size,
                                     char *utf8) -> size_t {
    simdutf::result res =
        implementation.convert_utf16be_to_utf8_with_errors(utf16, size, utf8);
    ASSERT_EQUAL(res.error, simdutf::error_code::SUCCESS);
    return res.count;
  };

  auto size_procedure = [&implementation](const char16_t *utf16,
                                          size_t size) -> size_t {
    return implementation.utf8_length_from_utf16be(utf16, size);
  };

  for (size_t size : input_size) {
    transcode_utf16_to_utf8_test_base test(BE, random, size);
    ASSERT_TRUE(test(procedure));
    ASSERT_TRUE(test.check_size(size_procedure));
  }
}

TEST_LOOP(convert_into_1_or_2_or_3_UTF8_bytes) {
  // range for 1, 2 or 3 UTF-8 bytes
  simdutf::tests::helpers::RandomIntRanges random(
      {{0x0000, 0x007f}, {0x0080, 0x07ff}, {0x0800, 0xd7ff}, {0xe000, 0xffff}},
      seed);

  auto procedure = [&implementation](const char16_t *utf16, size_t size,
                                     char *utf8) -> size_t {
    simdutf::result res =
        implementation.convert_utf16be_to_utf8_with_errors(utf16, size, utf8);
    ASSERT_EQUAL(res.error, simdutf::error_code::SUCCESS);
    return res.count;
  };
  auto size_procedure = [&implementation](const char16_t *utf16,
                                          size_t size) -> size_t {
    return implementation.utf8_length_from_utf16be(utf16, size);
  };
  for (size_t size : input_size) {
    transcode_utf16_to_utf8_test_base test(BE, random, size);
    ASSERT_TRUE(test(procedure));
    ASSERT_TRUE(test.check_size(size_procedure));
  }
}

TEST_LOOP(convert_into_3_or_4_UTF8_bytes) {
  // range for 3 or 4 UTF-8 bytes
  simdutf::tests::helpers::RandomIntRanges random(
      {{0x0800, 0xd800 - 1}, {0xe000, 0x10ffff}}, seed);

  auto procedure = [&implementation](const char16_t *utf16, size_t size,
                                     char *utf8) -> size_t {
    const simdutf::result res =
        implementation.convert_utf16be_to_utf8_with_errors(utf16, size, utf8);
    ASSERT_EQUAL(res.error, simdutf::error_code::SUCCESS);
    return res.count;
  };
  auto size_procedure = [&implementation](const char16_t *utf16,
                                          size_t size) -> size_t {
    return implementation.utf8_length_from_utf16be(utf16, size);
  };
  for (size_t size : input_size) {
    transcode_utf16_to_utf8_test_base test(BE, random, size);
    ASSERT_TRUE(test(procedure));
    ASSERT_TRUE(test.check_size(size_procedure));
  }
}

TEST(convert_fails_if_there_is_sole_low_surrogate) {
  const size_t size = 64;
  transcode_utf16_to_utf8_test_base test(BE, []() { return '*'; }, size + 32);

  for (char16_t low_surrogate = 0xdc00; low_surrogate <= 0xdfff;
       low_surrogate++) {
    for (size_t i = 0; i < size; i++) {
      auto procedure = [&implementation, i](const char16_t *utf16, size_t size,
                                            char *utf8) -> size_t {
        simdutf::result res =
            implementation.convert_utf16be_to_utf8_with_errors(utf16, size,
                                                               utf8);
        ASSERT_EQUAL(res.error, simdutf::error_code::SURROGATE);
        ASSERT_EQUAL(res.count, i);
        return 0;
      };
      const auto old = test.input_utf16[i];
      test.input_utf16[i] = to_utf16be(low_surrogate);
      ASSERT_TRUE(test(procedure));
      test.input_utf16[i] = old;
    }
  }
}

TEST(convert_fails_if_there_is_sole_high_surrogate) {
  const size_t size = 64;
  transcode_utf16_to_utf8_test_base test(BE, []() { return '*'; }, size + 32);

  for (char16_t high_surrogate = 0xdc00; high_surrogate <= 0xdfff;
       high_surrogate++) {
    for (size_t i = 0; i < size; i++) {
      auto procedure = [&implementation, &i](const char16_t *utf16, size_t size,
                                             char *utf8) -> size_t {
        simdutf::result res =
            implementation.convert_utf16be_to_utf8_with_errors(utf16, size,
                                                               utf8);
        ASSERT_EQUAL(res.error, simdutf::error_code::SURROGATE);
        ASSERT_EQUAL(res.count, i);
        return 0;
      };
      const auto old = test.input_utf16[i];
      test.input_utf16[i] = to_utf16be(high_surrogate);
      ASSERT_TRUE(test(procedure));
      test.input_utf16[i] = old;
    }
  }
}

TEST(
    convert_fails_if_there_is_low_surrogate_is_followed_by_another_low_surrogate) {
  const size_t size = 64;
  transcode_utf16_to_utf8_test_base test(BE, []() { return '*'; }, size + 32);

  for (char16_t low_surrogate = 0xdc00; low_surrogate <= 0xdfff;
       low_surrogate++) {
    for (size_t i = 0; i < size - 1; i++) {
      auto procedure = [&implementation, &i](const char16_t *utf16, size_t size,
                                             char *utf8) -> size_t {
        const simdutf::result res =
            implementation.convert_utf16be_to_utf8_with_errors(utf16, size,
                                                               utf8);
        ASSERT_EQUAL(res.error, simdutf::error_code::SURROGATE);
        ASSERT_EQUAL(res.count, i);
        return 0;
      };
      const auto old0 = test.input_utf16[i + 0];
      const auto old1 = test.input_utf16[i + 1];
      test.input_utf16[i + 0] = to_utf16be(low_surrogate);
      test.input_utf16[i + 1] = to_utf16be(low_surrogate);
      ASSERT_TRUE(test(procedure));
      test.input_utf16[i + 0] = old0;
      test.input_utf16[i + 1] = old1;
    }
  }
}

TEST(convert_fails_if_there_is_surrogate_pair_is_followed_by_high_surrogate) {
  const size_t size = 64;
  transcode_utf16_to_utf8_test_base test(BE, []() { return '*'; }, size + 32);

  const char16_t low_surrogate = to_utf16be(0xd801);
  const char16_t high_surrogate = to_utf16be(0xdc02);
  for (size_t i = 0; i < size - 2; i++) {
    auto procedure = [&implementation, &i](const char16_t *utf16, size_t size,
                                           char *utf8) -> size_t {
      const simdutf::result res =
          implementation.convert_utf16be_to_utf8_with_errors(utf16, size, utf8);
      ASSERT_EQUAL(res.error, simdutf::error_code::SURROGATE);
      ASSERT_EQUAL(res.count, i + 2);
      return 0;
    };
    const auto old0 = test.input_utf16[i + 0];
    const auto old1 = test.input_utf16[i + 1];
    const auto old2 = test.input_utf16[i + 2];
    test.input_utf16[i + 0] = low_surrogate;
    test.input_utf16[i + 1] = high_surrogate;
    test.input_utf16[i + 2] = high_surrogate;
    ASSERT_TRUE(test(procedure));
    test.input_utf16[i + 0] = old0;
    test.input_utf16[i + 1] = old1;
    test.input_utf16[i + 2] = old2;
  }
}

TEST(issue_445) {
  alignas(2) const unsigned char crash[] = {0x20, 0x20, 0xdd, 0x20};
  const unsigned int crash_len = 4;
  std::vector<char> output(4 * crash_len);
  const auto r = implementation.convert_utf16be_to_utf8_with_errors(
      (const char16_t *)crash, crash_len / sizeof(char16_t), output.data());
  ASSERT_EQUAL(r.count, 1);
  ASSERT_EQUAL(r.error, simdutf::error_code::SURROGATE);
}

TEST_MAIN