diff options
| author | Přemysl Eric Janouch <p@janouch.name> | 2020-10-21 04:52:24 +0200 |
|---|---|---|
| committer | Přemysl Eric Janouch <p@janouch.name> | 2020-10-21 05:08:59 +0200 |
| commit | b08cf6c29f94373823a910e015c62d437f83dbfd (patch) | |
| tree | 23a5fc7979f05d625b42d921b27accd0f6434094 | |
| parent | 69101eb1554ad2fca6de30cdbaccac076210d7e3 (diff) | |
| download | liberty-b08cf6c29f94373823a910e015c62d437f83dbfd.tar.gz liberty-b08cf6c29f94373823a910e015c62d437f83dbfd.tar.xz liberty-b08cf6c29f94373823a910e015c62d437f83dbfd.zip | |
Reject overlong UTF-8 sequences
| -rw-r--r-- | liberty.c | 5 | ||||
| -rw-r--r-- | tests/liberty.c | 10 |
2 files changed, 11 insertions, 4 deletions
@@ -2753,6 +2753,11 @@ utf8_decode (const char **s, size_t len) // Check the rest of the sequence uint32_t cp = *p++ & ~mask; + + // Overlong sequence (possibly MUTF-8, not supported) + if (!cp && sequence_len) + return -1; + while (sequence_len && --sequence_len) { if (p == end) diff --git a/tests/liberty.c b/tests/liberty.c index b55fe2c..3f0bd3f 100644 --- a/tests/liberty.c +++ b/tests/liberty.c @@ -331,10 +331,12 @@ test_utf8 (void) soft_assert (utf8_decode (&partial, 1) == -2); soft_assert (utf8_decode (&empty, 0) == -1); - const char valid [] = "2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm"; - const char invalid[] = "\xf0\x90\x28\xbc"; - soft_assert ( utf8_validate (valid, sizeof valid)); - soft_assert (!utf8_validate (invalid, sizeof invalid)); + const char valid[] = "2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm"; + const char invalid_1[] = "\xf0\x90\x28\xbc"; + const char invalid_2[] = "\xc0\x80"; + soft_assert ( utf8_validate (valid, sizeof valid)); + soft_assert (!utf8_validate (invalid_1, sizeof invalid_1)); + soft_assert (!utf8_validate (invalid_2, sizeof invalid_2)); struct utf8_iter iter = utf8_iter_make ("fóọ"); size_t ch_len; |