File: test_cpp20.cpp

package info (click to toggle)
utfcpp 4.0.8-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 380 kB
  • sloc: cpp: 1,526; ansic: 524; makefile: 13; sh: 4
file content (77 lines) | stat: -rw-r--r-- 2,627 bytes parent folder | download | duplicates (2)
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
#include "ftest.h"
#define UTF_CPP_CPLUSPLUS 202002L
#include "utf8.h"
#include <string>
using namespace utf8;
using namespace std;

TEST(CPP20APITests, test_utf16tou8)
{
    u16string utf16string = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e};
    u16string_view utf16stringview{utf16string};
    u8string u = utf16tou8(utf16string);
    EXPECT_EQ (u.size(), 10);
    u = utf16tou8(utf16stringview);
    EXPECT_EQ (u.size(), 10);
}

TEST(CPP20APITests, tes20t_utf8to16)
{
    u8string utf8_with_surrogates{ reinterpret_cast<const char8_t*>("\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e") };
    u16string utf16result = utf8to16(utf8_with_surrogates);
    EXPECT_EQ (utf16result.size(), 4);
    EXPECT_EQ (utf16result[2], 0xd834);
    EXPECT_EQ (utf16result[3], 0xdd1e);
}

TEST(CPP20APITests, test_utf32tou8)
{
    u32string utf32string = {0x448, 0x65E5, 0x10346};
    u32string_view utf32stringview{utf32string};
    u8string utf8result = utf32tou8(utf32stringview);
    EXPECT_EQ (utf8result.size(), 9);
}

TEST(CPP20APITests, test_utf8to32)
{
    u8string twochars = reinterpret_cast<const char8_t*>("\xe6\x97\xa5\xd1\x88");
    u32string utf32result = utf8to32(twochars);
    EXPECT_EQ (utf32result.size(), 2);
}

TEST(CPP20APITests, test_find_invalid)
{
    u8string utf_invalid = reinterpret_cast<const char8_t*>("\xe6\x97\xa5\xd1\x88\xfa");
    auto invalid = find_invalid(utf_invalid);
    EXPECT_EQ (invalid, 5);
}

TEST(CPP20APITests, test_is_valid)
{
    u8string utf_invalid = reinterpret_cast<const char8_t*>("\xe6\x97\xa5\xd1\x88\xfa");
    bool bvalid = is_valid(utf_invalid);
    EXPECT_FALSE (bvalid);
    u8string utf8_with_surrogates = reinterpret_cast<const char8_t*>("\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e");
    bvalid = is_valid(utf8_with_surrogates);
    EXPECT_TRUE (bvalid);
}

TEST(CPP20APITests, test_replace_invalid)
{
    u8string invalid_sequence = reinterpret_cast<const char8_t*>("a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z");
    u8string replace_invalid_result = replace_invalid(invalid_sequence, u8'?');
    bool bvalid = is_valid(replace_invalid_result);
    EXPECT_TRUE (bvalid);
    const u8string fixed_invalid_sequence = reinterpret_cast<const char8_t*>("a????z");
    EXPECT_EQ(fixed_invalid_sequence, replace_invalid_result);
}

TEST(CPP20APITests, test_starts_with_bom)
{
    u8string byte_order_mark = reinterpret_cast<const char8_t*>("\xef\xbb\xbf");
    bool bbom = starts_with_bom(byte_order_mark);
    EXPECT_TRUE (bbom);
    u8string threechars = reinterpret_cast<const char8_t*>("\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88");
    bool no_bbom = starts_with_bom(threechars);
    EXPECT_FALSE (no_bbom);
}