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
|
#include "unit-test.h"
#include "utf8.h"
#include "strbuf.h"
/*
* Test utf8_strnwidth with various Chinese strings
* Chinese characters typically have a width of 2 columns when displayed
*/
void test_utf8_width__strnwidth_chinese(void)
{
const char *str;
/* Test basic ASCII - each character should have width 1 */
cl_assert_equal_i(5, utf8_strnwidth("Hello", 5, 0));
/* skip_ansi = 1 */
cl_assert_equal_i(5, utf8_strnwidth("Hello", 5, 1));
/* Test simple Chinese characters - each should have width 2 */
/* "你好" is 6 bytes (3 bytes per char in UTF-8), 4 display columns */
cl_assert_equal_i(4, utf8_strnwidth("你好", 6, 0));
/* Test mixed ASCII and Chinese - ASCII = 1 column, Chinese = 2 columns */
/* "h"(1) + "i"(1) + "你"(2) + "好"(2) = 6 */
cl_assert_equal_i(6, utf8_strnwidth("Hi你好", 8, 0));
/* Test longer Chinese string */
/* 5 Chinese chars = 10 display columns */
cl_assert_equal_i(10, utf8_strnwidth("你好世界！", 15, 0));
/* Test individual Chinese character width */
cl_assert_equal_i(2, utf8_strnwidth("中", 3, 0));
/* Test empty string */
cl_assert_equal_i(0, utf8_strnwidth("", 0, 0));
/* Test length limiting */
str = "你好世界";
/* Only first char "你"(2 columns) within 3 bytes */
cl_assert_equal_i(2, utf8_strnwidth(str, 3, 0));
/* First two chars "你好"(4 columns) in 6 bytes */
cl_assert_equal_i(4, utf8_strnwidth(str, 6, 0));
}
/*
* Tests for utf8_strwidth (simpler version without length limit)
*/
void test_utf8_width__strwidth_chinese(void)
{
/* Test basic ASCII */
cl_assert_equal_i(5, utf8_strwidth("Hello"));
/* Test Chinese characters */
/* 2 Chinese chars = 4 display columns */
cl_assert_equal_i(4, utf8_strwidth("你好"));
/* Test longer Chinese string */
/* 5 Chinese chars = 10 display columns */
cl_assert_equal_i(10, utf8_strwidth("你好世界！"));
/* Test mixed ASCII and Chinese */
/* 5 ASCII (5 cols) + 2 Chinese (4 cols) = 9 */
cl_assert_equal_i(9, utf8_strwidth("Hello世界"));
/* 2 ASCII (2 cols) + 2 Chinese (4 cols) + 1 ASCII (1 col) = 7 */
cl_assert_equal_i(7, utf8_strwidth("Hi世界!"));
}
/*
* Additional tests with other East Asian characters
*/
void test_utf8_width__strnwidth_japanese_korean(void)
{
/* Japanese characters (should also be 2 columns each) */
/* 5 Japanese chars x 2 cols each = 10 display columns */
cl_assert_equal_i(10, utf8_strnwidth("こんにちは", 15, 0));
/* Korean characters (should also be 2 columns each) */
/* 5 Korean chars x 2 cols each = 10 display columns */
cl_assert_equal_i(10, utf8_strnwidth("안녕하세요", 15, 0));
}
/*
* Test utf8_strnwidth with CJK strings and ANSI sequences
*/
void test_utf8_width__strnwidth_cjk_with_ansi(void)
{
/* Test CJK with ANSI sequences */
const char *ansi_test = "\033[1m你好\033[0m";
int width = utf8_strnwidth(ansi_test, strlen(ansi_test), 1);
/* Should skip ANSI sequences and count "你好" as 4 columns */
cl_assert_equal_i(4, width);
/* Test mixed ASCII, CJK, and ANSI */
ansi_test = "Hello\033[32m世界\033[0m!";
width = utf8_strnwidth(ansi_test, strlen(ansi_test), 1);
/* "Hello"(5) + "世界"(4) + "!"(1) = 10 */
cl_assert_equal_i(10, width);
}
|
