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
|
/* -*- mode: c; c-basic-offset: 2; indent-tabs-mode: nil; -*-
* vim:expandtab:shiftwidth=2:tabstop=2:smarttab:
*
* Copyright (C) 2010 Monty Taylor
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "config.h"
#include <string>
#include <gtest/gtest.h>
#include <drizzled/utf8/utf8.h>
using namespace drizzled;
TEST(utf8, is_single)
{
ASSERT_TRUE(utf8::is_single('a'));
const char *multi_byte= "ç";
ASSERT_FALSE(utf8::is_single(*multi_byte));
ASSERT_FALSE(utf8::is_single(*(multi_byte + 1)));
}
TEST(utf8, codepoint_length)
{
uint32_t one_byte= 0x0024;
uint32_t two_bytes= 0x00A2;
uint32_t three_bytes= 0x20AC;
uint32_t four_bytes= 0x024B62;
EXPECT_EQ(1, utf8::codepoint_length(one_byte));
EXPECT_EQ(2, utf8::codepoint_length(two_bytes));
EXPECT_EQ(3, utf8::codepoint_length(three_bytes));
EXPECT_EQ(4, utf8::codepoint_length(four_bytes));
}
TEST(utf8, sequence_length)
{
const char *one_byte= "$";
const char *two_bytes= "¢";
const char *three_bytes= "€";
const char *four_bytes= "𤭢";
EXPECT_EQ(1, utf8::sequence_length(*one_byte));
EXPECT_EQ(2, utf8::sequence_length(*two_bytes));
EXPECT_EQ(3, utf8::sequence_length(*three_bytes));
EXPECT_EQ(4, utf8::sequence_length(*four_bytes));
}
TEST(utf8, char_length)
{
const char *one_byte= "$";
const char *two_bytes= "¢";
const char *three_bytes= "€";
const char *four_bytes= "𤭢";
const char *test_string= "__tañgè Ñãmé";
EXPECT_EQ(1, utf8::char_length(one_byte));
EXPECT_EQ(1, utf8::char_length(two_bytes));
EXPECT_EQ(1, utf8::char_length(three_bytes));
EXPECT_EQ(1, utf8::char_length(four_bytes));
EXPECT_EQ(12, utf8::char_length(test_string));
}
TEST(utf8, char_length_string)
{
std::string one_byte= "$";
std::string two_bytes= "¢";
std::string three_bytes= "€";
std::string four_bytes= "𤭢";
std::string test_string= "__tañgè Ñãmé";
EXPECT_EQ(1, utf8::char_length(one_byte));
EXPECT_EQ(1, utf8::char_length(two_bytes));
EXPECT_EQ(1, utf8::char_length(three_bytes));
EXPECT_EQ(1, utf8::char_length(four_bytes));
EXPECT_EQ(12, utf8::char_length(test_string));
}
|