File: convert_utf16be_to_utf32_tests.cpp

package info (click to toggle)
simdutf 8.0.0-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 7,524 kB
  • sloc: cpp: 64,498; ansic: 15,347; python: 3,592; sh: 366; makefile: 12
file content (193 lines) | stat: -rw-r--r-- 6,796 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
#include "simdutf.h"

#include <array>
#include <vector>

#include <tests/helpers/fixed_string.h>
#include <tests/helpers/random_int.h>
#include <tests/helpers/test.h>
#include <tests/helpers/transcode_test_base.h>
#include <tests/reference/validate_utf16.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_utf32_test_base;

} // namespace

TEST_LOOP(convert_2_UTF16_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,
                                     char32_t *utf32) -> size_t {
    return implementation.convert_utf16be_to_utf32(utf16, size, utf32);
  };
  auto size_procedure = [&implementation](const char16_t *utf16,
                                          size_t size) -> size_t {
    return implementation.utf32_length_from_utf16be(utf16, size);
  };
  for (size_t size : input_size) {
    transcode_utf16_to_utf32_test_base test(BE, random, size);
    ASSERT_TRUE(test(procedure));
    ASSERT_TRUE(test.check_size(size_procedure));
  }
}

TEST_LOOP(convert_with_surrogates) {
  // 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,
                                     char32_t *utf32) -> size_t {
    return implementation.convert_utf16be_to_utf32(utf16, size, utf32);
  };
  auto size_procedure = [&implementation](const char16_t *utf16,
                                          size_t size) -> size_t {
    return implementation.utf32_length_from_utf16be(utf16, size);
  };
  for (size_t size : input_size) {
    transcode_utf16_to_utf32_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) {
  auto procedure = [&implementation](const char16_t *utf16, size_t size,
                                     char32_t *utf32) -> size_t {
    return implementation.convert_utf16be_to_utf32(utf16, size, utf32);
  };
  const size_t size = 64;
  transcode_utf16_to_utf32_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++) {
      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) {
  auto procedure = [&implementation](const char16_t *utf16, size_t size,
                                     char32_t *utf32) -> size_t {
    return implementation.convert_utf16be_to_utf32(utf16, size, utf32);
  };

  const size_t size = 64;
  transcode_utf16_to_utf32_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++) {
      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) {
  auto procedure = [&implementation](const char16_t *utf16, size_t size,
                                     char32_t *utf32) -> size_t {
    return implementation.convert_utf16be_to_utf32(utf16, size, utf32);
  };

  const size_t size = 64;
  transcode_utf16_to_utf32_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++) {
      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) {
  auto procedure = [&implementation](const char16_t *utf16, size_t size,
                                     char32_t *utf32) -> size_t {
    return implementation.convert_utf16be_to_utf32(utf16, size, utf32);
  };

  const size_t size = 64;
  transcode_utf16_to_utf32_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++) {
    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(all_possible_8_codepoint_combinations) {
  auto procedure = [&implementation](const char16_t *utf16, size_t size,
                                     char32_t *utf32) -> size_t {
    return implementation.convert_utf16be_to_utf32(utf16, size, utf32);
  };

  std::vector<char32_t> output_utf32(256, ' ');
  const auto &combinations = all_utf16_combinations(BE);
  for (const auto &input_utf16 : combinations) {
    if (simdutf::tests::reference::validate_utf16(BE, input_utf16.data(),
                                                  input_utf16.size())) {
      transcode_utf16_to_utf32_test_base test(BE, input_utf16);
      ASSERT_TRUE(test(procedure));
    } else {
      ASSERT_FALSE(procedure(input_utf16.data(), input_utf16.size(),
                             output_utf32.data()));
    }
  }
}

#if SIMDUTF_CPLUSPLUS23

namespace {
template <auto input> constexpr auto size_be() {
  return simdutf::utf32_length_from_utf16be(input);
}
template <auto input> constexpr auto convert_be() {
  using namespace simdutf::tests::helpers;
  CTString<char32_t, size_be<input>()> tmp;
  const auto ret = simdutf::convert_utf16be_to_utf32(input, tmp);
  if (ret != tmp.size()) {
    throw "unexpected write size";
  }
  return tmp;
}
} // namespace

TEST(compile_time_convert_utf16be_to_utf32) {
  using namespace simdutf::tests::helpers;
  static_assert(convert_be<u"köttbulle"_utf16be>() == U"köttbulle"_utf32);
}

#endif

TEST_MAIN