From b08cf6c29f94373823a910e015c62d437f83dbfd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?P=C5=99emysl=20Eric=20Janouch?= Date: Wed, 21 Oct 2020 04:52:24 +0200 Subject: [PATCH] Reject overlong UTF-8 sequences --- liberty.c | 5 +++++ tests/liberty.c | 10 ++++++---- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/liberty.c b/liberty.c index 3aadc29..c0b6bb4 100644 --- a/liberty.c +++ b/liberty.c @@ -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;