diff --git a/payloads/libpayload/include/string.h b/payloads/libpayload/include/string.h index 952261fa15..ca5d5131e2 100644 --- a/payloads/libpayload/include/string.h +++ b/payloads/libpayload/include/string.h @@ -68,6 +68,13 @@ char *strtok_r(char *str, const char *delim, char **ptr); char *strerror(int errnum); /** @} */ +/** + * @defgroup string Unicode functions + * @{ + */ +char *utf16le_to_ascii(uint16_t *utf16_string, int maxlen); +/** @} */ + /** * @defgroup string OpenBSD based safe string functions * @{ diff --git a/payloads/libpayload/libc/string.c b/payloads/libpayload/libc/string.c index 71dd1a6d1b..99857493c0 100644 --- a/payloads/libpayload/libc/string.c +++ b/payloads/libpayload/libc/string.c @@ -653,3 +653,22 @@ char *strerror(int errnum) snprintf(errstr, sizeof(errstr), "Unknown error %d", errnum); return errstr; } + +/* + * Simple routine to convert UTF-16 to ASCII, giving up with ? if too high. + * A single code point may convert to ?? if not in the BMP. + * @param utf16_string A string encoded in UTF-16LE + * @param maxlen Maximum possible length of the string in code points + * @return Newly allocated ASCII string + */ +char *utf16le_to_ascii(uint16_t *utf16_string, int maxlen) +{ + char *ascii_string = xmalloc(maxlen + 1); /* +1 for trailing \0 */ + ascii_string[maxlen] = '\0'; + int i; + for (i = 0; i < maxlen; i++) { + uint16_t wchar = utf16_string[i]; + ascii_string[i] = wchar > 0x7f ? '?' : (char)wchar; + } + return ascii_string; +}