diff options
| author | Eugene Triguba <hello@eugenetriguba.com> | 2025-10-11 14:19:39 -0400 |
|---|---|---|
| committer | Eugene Triguba <hello@eugenetriguba.com> | 2025-10-11 14:31:37 -0400 |
| commit | d3ec525b7d6ecd8de064d3f3a54d112769d1d3b3 (patch) | |
| tree | 935b51f95afb513604c82c9e1efca223af60c109 /tests | |
| parent | Fix git clone link in readme (diff) | |
| download | cli-d3ec525b7d6ecd8de064d3f3a54d112769d1d3b3.zip | |
Add unicode support to justify
Diffstat (limited to 'tests')
| -rw-r--r-- | tests/CMakeLists.txt | 9 | ||||
| -rw-r--r-- | tests/justify.bats | 39 | ||||
| -rw-r--r-- | tests/test_linebuffer.c | 10 | ||||
| -rw-r--r-- | tests/test_utf8.c | 118 |
4 files changed, 170 insertions, 6 deletions
diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt index a0a8afa..fb75bc6 100644 --- a/tests/CMakeLists.txt +++ b/tests/CMakeLists.txt @@ -1,14 +1,19 @@ -set(TEST_LINEBUFFER_SOURCES test_linebuffer.c ../src/linebuffer.c) +set(TEST_LINEBUFFER_SOURCES test_linebuffer.c ../src/linebuffer.c ../src/utf8.c) set(TEST_WORD_SOURCES test_word.c ../src/word.c) +set(TEST_UTF8_SOURCES test_utf8.c ../src/utf8.c) add_executable(test_linebuffer ${TEST_LINEBUFFER_SOURCES}) add_executable(test_word ${TEST_WORD_SOURCES}) +add_executable(test_utf8 ${TEST_UTF8_SOURCES}) add_test(NAME test_linebuffer COMMAND test_linebuffer) add_test(NAME test_word COMMAND test_word) +add_test(NAME test_utf8 COMMAND test_utf8) find_package(PkgConfig REQUIRED) pkg_check_modules(CMOCKA REQUIRED cmocka) +pkg_check_modules(ICU REQUIRED IMPORTED_TARGET icu-uc icu-i18n) include_directories(${CMOCKA_INCLUDE_DIRS}) -target_link_libraries(test_linebuffer ${CMOCKA_LIBRARIES}) +target_link_libraries(test_linebuffer ${CMOCKA_LIBRARIES} PkgConfig::ICU) target_link_libraries(test_word ${CMOCKA_LIBRARIES}) +target_link_libraries(test_utf8 ${CMOCKA_LIBRARIES} PkgConfig::ICU) diff --git a/tests/justify.bats b/tests/justify.bats index 806ea81..525c5d8 100644 --- a/tests/justify.bats +++ b/tests/justify.bats @@ -94,3 +94,42 @@ EOF assert_success assert_output "" } + +@test "unicode text with accented characters is justified correctly" { + run "${JUSTIFY_BIN}" -w 30 <<EOF +café résumé naïve Zürich another word +EOF + assert_success + expected_output="café résumé naïve Zürich +another word" + assert_output "$expected_output" +} + +@test "unicode text with CJK characters is justified correctly" { + run "${JUSTIFY_BIN}" -w 20 <<EOF +Hello 世界 test this is a longer line +EOF + assert_success + expected_output="Hello 世界 test this +is a longer line" + assert_output "$expected_output" +} + +@test "mixed ASCII and unicode text wraps correctly" { + run "${JUSTIFY_BIN}" -w 25 <<EOF +This is café and résumé text that should wrap properly +EOF + assert_success + expected_output="This is café and résumé +text that should wrap +properly" + assert_output "$expected_output" +} + +@test "unicode text on last line is left-aligned" { + run "${JUSTIFY_BIN}" <<EOF +café résumé +EOF + assert_success + assert_output "café résumé" +} diff --git a/tests/test_linebuffer.c b/tests/test_linebuffer.c index ae233cc..6d84780 100644 --- a/tests/test_linebuffer.c +++ b/tests/test_linebuffer.c @@ -10,17 +10,19 @@ #include <string.h> /** - * GIVEN a specific buffer capacity + * GIVEN a specific line width * WHEN we attempt to create a LineBuffer * THEN we expect it to be created successfully * with the expected internal state */ void test_linebuffer_create(void **state) { - const int buffer_capacity = 50; - LineBuffer *lb = linebuffer_create(buffer_capacity); + const int line_width = 50; + LineBuffer *lb = linebuffer_create(line_width); assert_non_null(lb); - assert_int_equal(lb->_buffer_capacity, buffer_capacity); + assert_int_equal(lb->_line_width, line_width); + assert_int_equal(lb->_buffer_capacity, line_width * 4); assert_int_equal(lb->_buffer_length, 0); + assert_int_equal(lb->_display_width, 0); assert_int_equal(lb->_num_words, 0); linebuffer_destroy(lb); } diff --git a/tests/test_utf8.c b/tests/test_utf8.c new file mode 100644 index 0000000..623b607 --- /dev/null +++ b/tests/test_utf8.c @@ -0,0 +1,118 @@ +#include "utf8.h" +// clang-format off +#include <stdarg.h> +#include <stddef.h> +#include <setjmp.h> +#include <cmocka.h> +// clang-format on + +/** + * GIVEN an ASCII string + * WHEN we calculate the display width + * THEN we expect the width to equal the byte length + */ +void test_utf8_display_width_ascii(void **state) { + const char *input = "hello"; + size_t expected = 5; + + size_t result = utf8_display_width(input); + + assert_int_equal(result, expected); +} + +/** + * GIVEN a string with accented characters (combining marks) + * WHEN we calculate the display width + * THEN we expect the width to be less than the byte length + */ +void test_utf8_display_width_accented(void **state) { + const char *input = "café"; // é is 2 bytes in UTF-8 + size_t expected = 4; // 4 visible characters + + size_t result = utf8_display_width(input); + + assert_int_equal(result, expected); +} + +/** + * GIVEN a string with East Asian wide characters + * WHEN we calculate the display width + * THEN we expect the width to be double the character count + */ +void test_utf8_display_width_cjk(void **state) { + const char *input = "日本語"; // 3 Japanese characters + size_t expected = 6; // Each CJK character is 2 columns wide + + size_t result = utf8_display_width(input); + + assert_int_equal(result, expected); +} + +/** + * GIVEN a string with mixed ASCII and UTF-8 characters + * WHEN we calculate the display width + * THEN we expect the correct combined width + */ +void test_utf8_display_width_mixed(void **state) { + const char *input = "Hello 世界"; // "Hello " (6) + "世界" (4) + size_t expected = 10; // 6 ASCII + 2 CJK (2 columns each) + + size_t result = utf8_display_width(input); + + assert_int_equal(result, expected); +} + +/** + * GIVEN an empty string + * WHEN we calculate the display width + * THEN we expect width of 0 + */ +void test_utf8_display_width_empty(void **state) { + const char *input = ""; + size_t expected = 0; + + size_t result = utf8_display_width(input); + + assert_int_equal(result, expected); +} + +/** + * GIVEN a NULL pointer + * WHEN we calculate the display width + * THEN we expect width of 0 + */ +void test_utf8_display_width_null(void **state) { + size_t expected = 0; + + size_t result = utf8_display_width(NULL); + + assert_int_equal(result, expected); +} + +/** + * GIVEN a string with various Unicode characters + * WHEN we calculate the display width + * THEN we expect the correct width + */ +void test_utf8_display_width_various_unicode(void **state) { + const char *input = "Zürich"; // ü is 2 bytes in UTF-8 + size_t expected = 6; // 6 visible characters + + size_t result = utf8_display_width(input); + + assert_int_equal(result, expected); +} + +int main(void) { + const struct CMUnitTest tests[] = { + cmocka_unit_test(test_utf8_display_width_ascii), + cmocka_unit_test(test_utf8_display_width_accented), + cmocka_unit_test(test_utf8_display_width_cjk), + cmocka_unit_test(test_utf8_display_width_mixed), + cmocka_unit_test(test_utf8_display_width_empty), + cmocka_unit_test(test_utf8_display_width_null), + cmocka_unit_test(test_utf8_display_width_various_unicode), + }; + + return cmocka_run_group_tests(tests, NULL, NULL); +} |