Skip to content

[libc] Added isValidState to CharacterConverter class to ensure a provided mbstate is valid #145564

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
merged 4 commits into from
Jun 25, 2025
Merged

[libc] Added isValidState to CharacterConverter class to ensure a provided mbstate is valid #145564

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f370bf7
added isValidState
uzairnawaz Jun 24, 2025
f665228
fixed isValidState edge case
uzairnawaz Jun 24, 2025
1b5d23b
replaced magic number
uzairnawaz Jun 24, 2025
6c7705c
redundant check
uzairnawaz Jun 25, 2025
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
18 changes: 15 additions & 3 deletions libc/src/__support/wchar/character_converter.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,9 @@ constexpr size_t ENCODED_BITS_PER_UTF8 = 6;
// Information not metadata (# of bits excluding the byte headers)
constexpr uint32_t MASK_ENCODED_BITS =
mask_trailing_ones<uint32_t, ENCODED_BITS_PER_UTF8>();
// Maximum value for utf-32 for a utf-8 sequence of a given length
constexpr char32_t MAX_VALUE_PER_UTF8_LEN[] = {0x7f, 0x7ff, 0xffff, 0x10ffff};
constexpr int MAX_UTF8_LENGTH = 4;

CharacterConverter::CharacterConverter(mbstate *mbstate) { state = mbstate; }

Expand All @@ -40,6 +43,17 @@ bool CharacterConverter::isFull() {

bool CharacterConverter::isEmpty() { return state->bytes_stored == 0; }

bool CharacterConverter::isValidState() {
Copy link
Contributor

@michaelrj-google michaelrj-google Jun 24, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this seems useful, can you use this in any of the other functions to simplify their logic?

Copy link
Contributor Author

@uzairnawaz uzairnawaz Jun 24, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't see an obvious place to use this in any of the other functions, especially since the single character conversion functions (mbrtowc and wcrtomb) don't require checking this.

if (state->total_bytes > 4)
return false;

const char32_t max_utf32_value =
state->total_bytes == 0 ? 0
: MAX_VALUE_PER_UTF8_LEN[state->total_bytes - 1];
return state->bytes_stored <= state->total_bytes &&
state->bytes_stored >= 0 && state->partial <= max_utf32_value;
}

int CharacterConverter::push(char8_t utf8_byte) {
uint8_t num_ones = static_cast<uint8_t>(cpp::countl_one(utf8_byte));
// Checking the first byte if first push
Expand Down Expand Up @@ -90,9 +104,7 @@ int CharacterConverter::push(char32_t utf32) {
state->partial = utf32;

// determine number of utf-8 bytes needed to represent this utf32 value
constexpr char32_t MAX_VALUE_PER_UTF8_LEN[] = {0x7f, 0x7ff, 0xffff, 0x10ffff};
constexpr int NUM_RANGES = 4;
for (uint8_t i = 0; i < NUM_RANGES; i++) {
for (uint8_t i = 0; i < MAX_UTF8_LENGTH; i++) {
if (state->partial <= MAX_VALUE_PER_UTF8_LEN[i]) {
state->total_bytes = i + 1;
state->bytes_stored = i + 1;
Expand Down
1 change: 1 addition & 0 deletions libc/src/__support/wchar/character_converter.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ class CharacterConverter {
void clear();
bool isFull();
bool isEmpty();
bool isValidState();

int push(char8_t utf8_byte);
int push(char32_t utf32);
Expand Down
42 changes: 42 additions & 0 deletions libc/test/src/__support/wchar/utf32_to_8_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,3 +186,45 @@ TEST(LlvmLibcCharacterConverterUTF32To8Test, CantPushMidConversion) {
int err = cr.push(utf32);
ASSERT_EQ(err, -1);
}

TEST(LlvmLibcCharacterConverterUTF32To8Test, InvalidState) {
LIBC_NAMESPACE::internal::mbstate s1;
LIBC_NAMESPACE::internal::CharacterConverter c1(&s1);
ASSERT_TRUE(c1.isValidState());

LIBC_NAMESPACE::internal::mbstate s2{0, 2, 0};
LIBC_NAMESPACE::internal::CharacterConverter c2(&s2);
ASSERT_FALSE(c2.isValidState());

LIBC_NAMESPACE::internal::mbstate s3{0x7f, 1, 1};
LIBC_NAMESPACE::internal::CharacterConverter c3(&s3);
ASSERT_TRUE(c3.isValidState());
LIBC_NAMESPACE::internal::mbstate s4{0x80, 1, 1};
LIBC_NAMESPACE::internal::CharacterConverter c4(&s4);
ASSERT_FALSE(c4.isValidState());

LIBC_NAMESPACE::internal::mbstate s5{0x7ff, 1, 2};
LIBC_NAMESPACE::internal::CharacterConverter c5(&s5);
ASSERT_TRUE(c5.isValidState());
LIBC_NAMESPACE::internal::mbstate s6{0x800, 1, 2};
LIBC_NAMESPACE::internal::CharacterConverter c6(&s6);
ASSERT_FALSE(c6.isValidState());

LIBC_NAMESPACE::internal::mbstate s7{0xffff, 1, 3};
LIBC_NAMESPACE::internal::CharacterConverter c7(&s7);
ASSERT_TRUE(c7.isValidState());
LIBC_NAMESPACE::internal::mbstate s8{0x10000, 1, 3};
LIBC_NAMESPACE::internal::CharacterConverter c8(&s8);
ASSERT_FALSE(c8.isValidState());

LIBC_NAMESPACE::internal::mbstate s9{0x10ffff, 1, 4};
LIBC_NAMESPACE::internal::CharacterConverter c9(&s9);
ASSERT_TRUE(c9.isValidState());
LIBC_NAMESPACE::internal::mbstate s10{0x110000, 1, 2};
LIBC_NAMESPACE::internal::CharacterConverter c10(&s10);
ASSERT_FALSE(c10.isValidState());

LIBC_NAMESPACE::internal::mbstate s11{0, 0, 5};
LIBC_NAMESPACE::internal::CharacterConverter c11(&s11);
ASSERT_FALSE(c11.isValidState());
}
Loading