diff options
author | Heinrich Schuchardt | 2021-02-27 14:08:38 +0100 |
---|---|---|
committer | Heinrich Schuchardt | 2021-03-07 17:37:13 +0100 |
commit | e91789e2f6611c0d7f3510691c154e524e7cfa43 (patch) | |
tree | 98e84ebbc76d03a249e8db3794b54ef834ba7a26 /test | |
parent | ddbaff53da5b99563fa371db0b09544e139fdabb (diff) |
lib/charset: UTF-8 stream conversion
Provide functions to convert an UTF-8 stream to code page 437 or UTF-32.
Add unit tests.
Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
Diffstat (limited to 'test')
-rw-r--r-- | test/unicode_ut.c | 78 |
1 files changed, 78 insertions, 0 deletions
diff --git a/test/unicode_ut.c b/test/unicode_ut.c index 154361aea7d..6f6aea5f602 100644 --- a/test/unicode_ut.c +++ b/test/unicode_ut.c @@ -47,6 +47,9 @@ static const char d3[] = {0xe6, 0xbd, 0x9c, 0xe6, 0xb0, 0xb4, 0xe8, 0x89, /* Three letters translating to two utf-16 word each */ static const char d4[] = {0xf0, 0x90, 0x92, 0x8d, 0xf0, 0x90, 0x92, 0x96, 0xf0, 0x90, 0x92, 0x87, 0x00}; +/* Letter not in code page 437 */ +static const char d5[] = {0xCE, 0x92, 0x20, 0x69, 0x73, 0x20, 0x6E, 0x6F, + 0x74, 0x20, 0x42, 0x00}; /* Illegal utf-8 strings */ static const char j1[] = {0x6a, 0x31, 0xa1, 0x6c, 0x00}; @@ -631,6 +634,81 @@ static int unicode_test_utf_to_cp(struct unit_test_state *uts) } UNICODE_TEST(unicode_test_utf_to_cp); +static void utf8_to_cp437_stream_helper(const char *in, char *out) +{ + char buffer[5]; + int ret; + + *buffer = 0; + for (; *in; ++in) { + ret = utf8_to_cp437_stream(*in, buffer); + if (ret) + *out++ = ret; + } + *out = 0; +} + +static int unicode_test_utf8_to_cp437_stream(struct unit_test_state *uts) +{ + char buf[16]; + + utf8_to_cp437_stream_helper(d1, buf); + ut_asserteq_str("U-Boot", buf); + utf8_to_cp437_stream_helper(d2, buf); + ut_asserteq_str("kafb\xa0tur", buf); + utf8_to_cp437_stream_helper(d5, buf); + ut_asserteq_str("? is not B", buf); + utf8_to_cp437_stream_helper(j2, buf); + ut_asserteq_str("j2l", buf); + + return 0; +} +UNICODE_TEST(unicode_test_utf8_to_cp437_stream); + +static void utf8_to_utf32_stream_helper(const char *in, s32 *out) +{ + char buffer[5]; + int ret; + + *buffer = 0; + for (; *in; ++in) { + ret = utf8_to_utf32_stream(*in, buffer); + if (ret) + *out++ = ret; + } + *out = 0; +} + +static int unicode_test_utf8_to_utf32_stream(struct unit_test_state *uts) +{ + s32 buf[16]; + + const u32 u1[] = {0x55, 0x2D, 0x42, 0x6F, 0x6F, 0x74, 0x0000}; + const u32 u2[] = {0x6B, 0x61, 0x66, 0x62, 0xE1, 0x74, 0x75, 0x72, 0x00}; + const u32 u3[] = {0x0392, 0x20, 0x69, 0x73, 0x20, 0x6E, 0x6F, 0x74, + 0x20, 0x42, 0x00}; + const u32 u4[] = {0x6A, 0x32, 0x6C, 0x00}; + + memset(buf, 0, sizeof(buf)); + utf8_to_utf32_stream_helper(d1, buf); + ut_asserteq_mem(u1, buf, sizeof(u1)); + + memset(buf, 0, sizeof(buf)); + utf8_to_utf32_stream_helper(d2, buf); + ut_asserteq_mem(u2, buf, sizeof(u2)); + + memset(buf, 0, sizeof(buf)); + utf8_to_utf32_stream_helper(d5, buf); + ut_asserteq_mem(u3, buf, sizeof(u3)); + + memset(buf, 0, sizeof(buf)); + utf8_to_utf32_stream_helper(j2, buf); + ut_asserteq_mem(u4, buf, sizeof(u4)); + + return 0; +} +UNICODE_TEST(unicode_test_utf8_to_utf32_stream); + #ifdef CONFIG_EFI_LOADER static int unicode_test_efi_create_indexed_name(struct unit_test_state *uts) { |