Show HN: Mojibake – a low-level Unicode library written in C

Mojibake is a low-level Unicode 17 text-processing library written in C11 and compatible with C++17. It is released under the MIT License.

Usage

You don't need to install anything. There are two files ( mojibake.c , mojibake.h ) to add to your C/C++ project. Download it here mojibake-amalgamation-027.zip

Examples of normalization, characters count and NFKC casefold.

void print_string ( const char *input, size_t length) ; int main ( int argc, char * const argv[]) { const char *input = "Cafe\xCC\x81" ; size_t length = strlen (input); mjb_result result; if (mjb_normalize(input, length, MJB_ENC_UTF_8, MJB_NORMALIZATION_NFC, MJB_ENC_UTF_8, &result) != MJB_STATUS_OK) { return 1 ; } print_string(input, length); print_string(result.output, result.output_size); const char *mojibake = "文字化け" ; length = strlen (mojibake); printf ( "\"%s\" encoded in UTF-8 is %zu bytes long, and %zu characters long

" , mojibake, length, mjb_string_length(mojibake, length, MJB_ENC_UTF_8)); mjb_result_free(&result); const char *case_input = "Straße" ; if (mjb_nfkc_casefold(case_input, strlen (case_input), MJB_ENC_UTF_8, MJB_ENC_UTF_8, &result) != MJB_STATUS_OK) { return 1 ; } printf ( "%s -> %.*s

" , case_input, ( int )result.output_size, result.output); mjb_result_free(&result); return 0 ; } void print_string ( const char *input, size_t length) { for ( size_t i = 0 ; i < length; ++i) { unsigned char byte = ( unsigned char )input[i]; if (byte >= 0x21 && byte <= 0x7E ) { printf ( "%c" , byte); } else { printf ( "<%02X>" , byte); } } printf ( "

" ); }

This output:

Cafe<CC><81> Caf<C3><A9> "文字化け" encoded in UTF-8 is 12 bytes long, and 4 characters long Straße -> strasse

... continue reading