Skip to content

test(display): cover malformed UTF-8 and fix boundary read #596

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
gg582 merged 1 commit into from
Nov 2, 2026
Merged

test(display): cover malformed UTF-8 and fix boundary read #596

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 13 additions & 13 deletions src/display_model.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,10 +123,20 @@ static unsigned int utf8_char_width(const char **p)

if ((s[0] & 0xE0) == 0xC0) {
byte_len = 2U;
display_cols = 1U;
} else if ((s[0] & 0xF0) == 0xE0) {
byte_len = 3U;
/* Decode code point to determine width */
} else if ((s[0] & 0xF8) == 0xF0) {
byte_len = 4U;
}

for (unsigned int i = 1U; i < byte_len; ++i) {
if (s[i] == '\0' || (s[i] & 0xC0) != 0x80) {
byte_len = i;
break;
}
}

if (byte_len == 3U) {
unsigned int cp = ((unsigned int)(s[0] & 0x0F) << 12) |
((unsigned int)(s[1] & 0x3F) << 6) |
(unsigned int)(s[2] & 0x3F);
Expand All @@ -142,9 +152,7 @@ static unsigned int utf8_char_width(const char **p)
(cp >= 0xFFE0 && cp <= 0xFFE6)) {
display_cols = 2U;
}
} else if ((s[0] & 0xF8) == 0xF0) {
byte_len = 4U;
/* Most 4-byte characters (supplementary planes) including CJK ext. */
} else if (byte_len == 4U) {
unsigned int cp = ((unsigned int)(s[0] & 0x07) << 18) |
((unsigned int)(s[1] & 0x3F) << 12) |
((unsigned int)(s[2] & 0x3F) << 6) |
Expand All @@ -154,14 +162,6 @@ static unsigned int utf8_char_width(const char **p)
}
}

/* Validate continuation bytes */
for (unsigned int i = 1U; i < byte_len && s[i] != '\0'; ++i) {
if ((s[i] & 0xC0) != 0x80) {
byte_len = i;
break;
}
}

*p = (const char *)(s + byte_len);
return display_cols;
}
Expand Down
29 changes: 29 additions & 0 deletions tests/display_model_test.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -550,6 +550,33 @@ static void test_burst_replay(void)
++g_tests_passed;
}

static void test_wrap_truncated_utf8_stays_in_bounds(void)
{
const unsigned char prefix[] = {0xF0U, 0x9FU, 0x92U};
for (size_t length = 1U; length <= sizeof(prefix); ++length) {
char *text = malloc(length + 1U);
TEST_ASSERT(text != NULL, "allocate exact truncated UTF-8 buffer");
memcpy(text, prefix, length);
text[length] = '\0';

display_line_t out[4];
size_t produced = display_model_wrap_line(text, 80, 77, out, 4);
free(text);
TEST_ASSERT_EQ(produced, 1U, "truncated UTF-8 should produce one line");
}
++g_tests_passed;
}

static void test_wrap_invalid_utf8_continuation(void)
{
const char text[] = "\xE2" "A\xA2";
display_line_t out[4];
size_t produced = display_model_wrap_line(text, 80, 78, out, 4);
TEST_ASSERT_EQ(produced, 1U, "invalid continuation should not loop");
TEST_ASSERT_EQ(out[0].message_id, 78U, "message id should survive invalid input");
++g_tests_passed;
}

/* ---- Main ---- */

int main(void)
Expand All @@ -573,6 +600,8 @@ int main(void)
test_empty_model();
test_long_wrap_content_preserved();
test_burst_replay();
test_wrap_truncated_utf8_stays_in_bounds();
test_wrap_invalid_utf8_continuation();

printf("\n%d passed, %d failed\n", g_tests_passed, g_tests_failed);

Expand Down
Loading