Skip to content

C: Use uint32_t in utf8.c #777

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
marcoroth merged 1 commit into from
Nov 4, 2025
Merged

C: Use uint32_t in utf8.c #777

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
5 changes: 3 additions & 2 deletions src/include/utf8.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,11 @@
#define HERB_UTF8_H

#include <stdbool.h>
#include <stdint.h>
#include <stdlib.h>

int utf8_char_byte_length(unsigned char first_byte);
int utf8_sequence_length(const char* str, size_t position, size_t max_length);
uint32_t utf8_char_byte_length(unsigned char first_byte);
uint32_t utf8_sequence_length(const char* str, size_t position, size_t max_length);
bool utf8_is_valid_continuation_byte(unsigned char byte);

#endif
8 changes: 4 additions & 4 deletions src/utf8.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
// 110xxxxx = 2 bytes
// 1110xxxx = 3 bytes
// 11110xxx = 4 bytes
int utf8_char_byte_length(unsigned char first_byte) {
uint32_t utf8_char_byte_length(unsigned char first_byte) {
if ((first_byte & 0x80) == 0) {
return 1;
} else if ((first_byte & 0xE0) == 0xC0) {
Expand All @@ -24,18 +24,18 @@ bool utf8_is_valid_continuation_byte(unsigned char byte) {
return (byte & 0xC0) == 0x80;
}

int utf8_sequence_length(const char* str, size_t position, size_t max_length) {
uint32_t utf8_sequence_length(const char* str, size_t position, size_t max_length) {
if (position >= max_length) { return 0; }

unsigned char first_byte = (unsigned char) str[position];
int expected_length = utf8_char_byte_length(first_byte);
uint32_t expected_length = utf8_char_byte_length(first_byte);

if (position + expected_length > max_length) {
return 1; // Not enough bytes, treat as single byte
}

if (expected_length > 1) {
for (int i = 1; i < expected_length; i++) {
for (uint32_t i = 1; i < expected_length; i++) {
if (!utf8_is_valid_continuation_byte((unsigned char) str[position + i])) {
return 1; // Invalid continuation byte, treat first byte as single byte
}
Expand Down
Loading