From 878fef8ebf6cf513842de14284ee58f4d92fcef3 Mon Sep 17 00:00:00 2001 From: Jiang Xin Date: Sat, 15 Nov 2025 08:36:10 -0500 Subject: [PATCH 1/2] 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 Signed-off-by: Junio C Hamano --- Makefile | 1 + t/meson.build | 1 + t/unit-tests/u-utf8-width.c | 97 +++++++++++++++++++++++++++++++++++++ 3 files changed, 99 insertions(+) create mode 100644 t/unit-tests/u-utf8-width.c diff --git a/Makefile b/Makefile index 7e0f77e298..2a67546154 100644 --- a/Makefile +++ b/Makefile @@ -1525,6 +1525,7 @@ CLAR_TEST_SUITES += u-string-list CLAR_TEST_SUITES += u-strvec CLAR_TEST_SUITES += u-trailer CLAR_TEST_SUITES += u-urlmatch-normalization +CLAR_TEST_SUITES += u-utf8-width CLAR_TEST_PROG = $(UNIT_TEST_BIN)/unit-tests$(X) CLAR_TEST_OBJS = $(patsubst %,$(UNIT_TEST_DIR)/%.o,$(CLAR_TEST_SUITES)) CLAR_TEST_OBJS += $(UNIT_TEST_DIR)/clar/clar.o diff --git a/t/meson.build b/t/meson.build index a5531df415..dc43d69636 100644 --- a/t/meson.build +++ b/t/meson.build @@ -24,6 +24,7 @@ clar_test_suites = [ 'unit-tests/u-strvec.c', 'unit-tests/u-trailer.c', 'unit-tests/u-urlmatch-normalization.c', + 'unit-tests/u-utf8-width.c', ] clar_sources = [ diff --git a/t/unit-tests/u-utf8-width.c b/t/unit-tests/u-utf8-width.c new file mode 100644 index 0000000000..3766f19726 --- /dev/null +++ b/t/unit-tests/u-utf8-width.c @@ -0,0 +1,97 @@ +#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); +} From 7a03a10a3a746dd8565a3a0e6126f60523b41738 Mon Sep 17 00:00:00 2001 From: Jiang Xin Date: Sat, 15 Nov 2025 08:36:11 -0500 Subject: [PATCH 2/2] builtin/repo: fix table alignment for UTF-8 characters MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The output table from "git repo structure" is misaligned when displaying UTF-8 characters (e.g., non-ASCII glyphs). E.g.: | 仓库结构 | 值 | | -------------- | ---- | | * 引用 | | | * 计数 | 67 | The previous implementation used simple width formatting with printf() which didn't properly handle multi-byte UTF-8 characters, causing misaligned table columns when displaying repository structure information. This change modifies the stats_table_print_structure function to use strbuf_utf8_align() instead of basic printf width specifiers. This ensures proper column alignment regardless of the character encoding of the content being displayed. Also add test cases for strbuf_utf8_align(), a function newly introduced in "builtin/repo.c". Signed-off-by: Jiang Xin Signed-off-by: Junio C Hamano --- builtin/repo.c | 21 +++++++++++++++++---- t/unit-tests/u-utf8-width.c | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 54 insertions(+), 4 deletions(-) diff --git a/builtin/repo.c b/builtin/repo.c index 9d4749f79b..e3adb353a2 100644 --- a/builtin/repo.c +++ b/builtin/repo.c @@ -292,14 +292,20 @@ static void stats_table_print_structure(const struct stats_table *table) int name_col_width = utf8_strwidth(name_col_title); int value_col_width = utf8_strwidth(value_col_title); struct string_list_item *item; + struct strbuf buf = STRBUF_INIT; if (table->name_col_width > name_col_width) name_col_width = table->name_col_width; if (table->value_col_width > value_col_width) value_col_width = table->value_col_width; - printf("| %-*s | %-*s |\n", name_col_width, name_col_title, - value_col_width, value_col_title); + strbuf_addstr(&buf, "| "); + strbuf_utf8_align(&buf, ALIGN_LEFT, name_col_width, name_col_title); + strbuf_addstr(&buf, " | "); + strbuf_utf8_align(&buf, ALIGN_LEFT, value_col_width, value_col_title); + strbuf_addstr(&buf, " |"); + printf("%s\n", buf.buf); + printf("| "); for (int i = 0; i < name_col_width; i++) putchar('-'); @@ -317,9 +323,16 @@ static void stats_table_print_structure(const struct stats_table *table) value = entry->value; } - printf("| %-*s | %*s |\n", name_col_width, item->string, - value_col_width, value); + strbuf_reset(&buf); + strbuf_addstr(&buf, "| "); + strbuf_utf8_align(&buf, ALIGN_LEFT, name_col_width, item->string); + strbuf_addstr(&buf, " | "); + strbuf_utf8_align(&buf, ALIGN_RIGHT, value_col_width, value); + strbuf_addstr(&buf, " |"); + printf("%s\n", buf.buf); } + + strbuf_release(&buf); } static void stats_table_clear(struct stats_table *table) diff --git a/t/unit-tests/u-utf8-width.c b/t/unit-tests/u-utf8-width.c index 3766f19726..86e09c3574 100644 --- a/t/unit-tests/u-utf8-width.c +++ b/t/unit-tests/u-utf8-width.c @@ -95,3 +95,40 @@ void test_utf8_width__strnwidth_cjk_with_ansi(void) /* "Hello"(5) + "世界"(4) + "!"(1) = 10 */ cl_assert_equal_i(10, width); } + +/* + * Test the strbuf_utf8_align function with CJK characters + */ +void test_utf8_width__strbuf_utf8_align(void) +{ + struct strbuf buf = STRBUF_INIT; + + /* Test left alignment with CJK */ + strbuf_utf8_align(&buf, ALIGN_LEFT, 10, "你好"); + /* Since "你好" is 4 display columns, we need 6 more spaces to reach 10 */ + cl_assert_equal_s("你好 ", buf.buf); + strbuf_reset(&buf); + + /* Test right alignment with CJK */ + strbuf_utf8_align(&buf, ALIGN_RIGHT, 8, "世界"); + /* "世界" is 4 display columns, so we need 4 leading spaces */ + cl_assert_equal_s(" 世界", buf.buf); + strbuf_reset(&buf); + + /* Test center alignment with CJK */ + strbuf_utf8_align(&buf, ALIGN_MIDDLE, 10, "中"); + /* "中" is 2 display columns, so (10-2)/2 = 4 spaces on left, 4 on right */ + cl_assert_equal_s(" 中 ", buf.buf); + strbuf_reset(&buf); + + strbuf_utf8_align(&buf, ALIGN_MIDDLE, 5, "中"); + /* "中" is 2 display columns, so (5-2)/2 = 1 spaces on left, 2 on right */ + cl_assert_equal_s(" 中 ", buf.buf); + strbuf_reset(&buf); + + /* Test alignment that is smaller than string width */ + strbuf_utf8_align(&buf, ALIGN_LEFT, 2, "你好"); + /* Since "你好" is 4 display columns, it should not be truncated */ + cl_assert_equal_s("你好", buf.buf); + strbuf_release(&buf); +}