t/unit-tests: add UTF-8 width tests for CJK chars
The file "builtin/repo.c" uses utf8_strwidth() to calculate the display width of UTF-8 characters in a table, but the resulting output is still misaligned. Add test cases for both utf8_strwidth and utf8_strnwidth to verify that they correctly compute the display width for UTF-8 characters. Also updated the build configuration in Makefile and meson.build to include the new test suite in the build process. Signed-off-by: Jiang Xin <worldhello.net@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Jiang Xin committed
Nov 15, 2025 at 08:36 UTC
878fef8ebf6cf513842de14284ee58f4d92fcef3
3 files changed
+99
Makefile
+1
@@ -1525,6 +1525,7 @@ CLAR_TEST_SUITES += u-string-list
1525
CLAR_TEST_SUITES += u-strvec
1526
CLAR_TEST_SUITES += u-trailer
1527
CLAR_TEST_SUITES += u-urlmatch-normalization
1528
+CLAR_TEST_SUITES += u-utf8-width
1529
CLAR_TEST_PROG = $(UNIT_TEST_BIN)/unit-tests$(X)
1530
CLAR_TEST_OBJS = $(patsubst %,$(UNIT_TEST_DIR)/%.o,$(CLAR_TEST_SUITES))
1531
CLAR_TEST_OBJS += $(UNIT_TEST_DIR)/clar/clar.o
t/meson.build
+1
@@ -24,6 +24,7 @@ clar_test_suites = [
24
'unit-tests/u-strvec.c',
25
'unit-tests/u-trailer.c',
26
'unit-tests/u-urlmatch-normalization.c',
27
+ 'unit-tests/u-utf8-width.c',
28
]
29
30
clar_sources = [
t/unit-tests/u-utf8-width.c
new
+97
@@ -0,0 +1,97 @@
1
+#include "unit-test.h"
2
+#include "utf8.h"
3
+#include "strbuf.h"
4
+
5
+/*
6
+ * Test utf8_strnwidth with various Chinese strings
7
+ * Chinese characters typically have a width of 2 columns when displayed
8
+ */
9
+void test_utf8_width__strnwidth_chinese(void)
10
+{
11
+ const char *str;
12
+
13
+ /* Test basic ASCII - each character should have width 1 */
14
+ cl_assert_equal_i(5, utf8_strnwidth("Hello", 5, 0));
15
+ /* skip_ansi = 1 */
16
+ cl_assert_equal_i(5, utf8_strnwidth("Hello", 5, 1));
17
+
18
+ /* Test simple Chinese characters - each should have width 2 */
19
+ /* "你好" is 6 bytes (3 bytes per char in UTF-8), 4 display columns */
20
+ cl_assert_equal_i(4, utf8_strnwidth("你好", 6, 0));
21
+
22
+ /* Test mixed ASCII and Chinese - ASCII = 1 column, Chinese = 2 columns */
23
+ /* "h"(1) + "i"(1) + "你"(2) + "好"(2) = 6 */
24
+ cl_assert_equal_i(6, utf8_strnwidth("Hi你好", 8, 0));
25
+
26
+ /* Test longer Chinese string */
27
+ /* 5 Chinese chars = 10 display columns */
28
+ cl_assert_equal_i(10, utf8_strnwidth("你好世界！", 15, 0));
29
+
30
+ /* Test individual Chinese character width */
31
+ cl_assert_equal_i(2, utf8_strnwidth("中", 3, 0));
32
+
33
+ /* Test empty string */
34
+ cl_assert_equal_i(0, utf8_strnwidth("", 0, 0));
35
+
36
+ /* Test length limiting */
37
+ str = "你好世界";
38
+ /* Only first char "你"(2 columns) within 3 bytes */
39
+ cl_assert_equal_i(2, utf8_strnwidth(str, 3, 0));
40
+ /* First two chars "你好"(4 columns) in 6 bytes */
41
+ cl_assert_equal_i(4, utf8_strnwidth(str, 6, 0));
42
+}
43
+
44
+/*
45
+ * Tests for utf8_strwidth (simpler version without length limit)
46
+ */
47
+void test_utf8_width__strwidth_chinese(void)
48
+{
49
+ /* Test basic ASCII */
50
+ cl_assert_equal_i(5, utf8_strwidth("Hello"));
51
+
52
+ /* Test Chinese characters */
53
+ /* 2 Chinese chars = 4 display columns */
54
+ cl_assert_equal_i(4, utf8_strwidth("你好"));
55
+
56
+ /* Test longer Chinese string */
57
+ /* 5 Chinese chars = 10 display columns */
58
+ cl_assert_equal_i(10, utf8_strwidth("你好世界！"));
59
+
60
+ /* Test mixed ASCII and Chinese */
61
+ /* 5 ASCII (5 cols) + 2 Chinese (4 cols) = 9 */
62
+ cl_assert_equal_i(9, utf8_strwidth("Hello世界"));
63
+ /* 2 ASCII (2 cols) + 2 Chinese (4 cols) + 1 ASCII (1 col) = 7 */
64
+ cl_assert_equal_i(7, utf8_strwidth("Hi世界!"));
65
+}
66
+
67
+/*
68
+ * Additional tests with other East Asian characters
69
+ */
70
+void test_utf8_width__strnwidth_japanese_korean(void)
71
+{
72
+ /* Japanese characters (should also be 2 columns each) */
73
+ /* 5 Japanese chars x 2 cols each = 10 display columns */
74
+ cl_assert_equal_i(10, utf8_strnwidth("こんにちは", 15, 0));
75
+
76
+ /* Korean characters (should also be 2 columns each) */
77
+ /* 5 Korean chars x 2 cols each = 10 display columns */
78
+ cl_assert_equal_i(10, utf8_strnwidth("안녕하세요", 15, 0));
79
+}
80
+
81
+/*
82
+ * Test utf8_strnwidth with CJK strings and ANSI sequences
83
+ */
84
+void test_utf8_width__strnwidth_cjk_with_ansi(void)
85
+{
86
+ /* Test CJK with ANSI sequences */
87
+ const char *ansi_test = "\033[1m你好\033[0m";
88
+ int width = utf8_strnwidth(ansi_test, strlen(ansi_test), 1);
89
+ /* Should skip ANSI sequences and count "你好" as 4 columns */
90
+ cl_assert_equal_i(4, width);
91
+
92
+ /* Test mixed ASCII, CJK, and ANSI */
93
+ ansi_test = "Hello\033[32m世界\033[0m!";
94
+ width = utf8_strnwidth(ansi_test, strlen(ansi_test), 1);
95
+ /* "Hello"(5) + "世界"(4) + "!"(1) = 10 */
96
+ cl_assert_equal_i(10, width);
97
+}