diff options
| author | Rafael G. Martins <rafael@rafaelmartins.eng.br> | 2020-11-05 19:13:47 +0100 |
|---|---|---|
| committer | Rafael G. Martins <rafael@rafaelmartins.eng.br> | 2020-11-05 19:13:49 +0100 |
| commit | de14affe2e316f00663759100d658731fb8fc0ca (patch) | |
| tree | b31937440eedb113f5e936a23c941c7831ee9c23 /tests/common/check_utf8.c | |
| parent | 39986b29f34795d346b8feb10ce4fe9caac8878e (diff) | |
| download | blogc-de14affe2e316f00663759100d658731fb8fc0ca.tar.gz blogc-de14affe2e316f00663759100d658731fb8fc0ca.tar.bz2 blogc-de14affe2e316f00663759100d658731fb8fc0ca.zip | |
common: utf: simplified utf-8 validation
we don't need to evaluate codepoints, just to check if the byte
sequences are valid.
Diffstat (limited to 'tests/common/check_utf8.c')
| -rw-r--r-- | tests/common/check_utf8.c | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/tests/common/check_utf8.c b/tests/common/check_utf8.c index 05bf566..803818b 100644 --- a/tests/common/check_utf8.c +++ b/tests/common/check_utf8.c @@ -39,6 +39,10 @@ test_utf8_invalid(void **state) assert_false(bc_utf8_validate(c, 4)); const uint8_t d[8] = {0xff, 0xfe, 0x00, 0x00, 0xac, 0x20, 0x00, 0x00}; // utf-32 assert_false(bc_utf8_validate(d, 8)); + const uint8_t e[6] = {'a', 0xff, 0xfe, 0xac, 0x20, 'b'}; // utf-16 + assert_false(bc_utf8_validate(e, 6)); + const uint8_t f[10] = {'a', 0xff, 0xfe, 0x00, 0x00, 0xac, 0x20, 0x00, 0x00, 'b'}; // utf-32 + assert_false(bc_utf8_validate(f, 10)); } |