Function pg_utf_mblen

src/common/wchar.c:567–589

* Return the byte length of a UTF8 character pointed to by s * * Note: in the current implementation we do not support UTF8 sequences * of more than 4 bytes; hence do NOT return a value larger than 4. * We return "1" for any leading byte that is either flat-out illegal or * indicates a length larger than we support. * * pg_utf2wchar_with_len(), utf8_to_unicode(), pg_utf8_islegal(), and perh

 * other places would need to be fixed to change this.
 */
int
pg_utf_mblen(const unsigned char *s)
{
	int			len;

	if ((*s & 0x80) == 0)
		len = 1;
	else if ((*s & 0xe0) == 0xc0)
		len = 2;
	else if ((*s & 0xf0) == 0xe0)
		len = 3;
	else if ((*s & 0xf8) == 0xf0)
		len = 4;
#ifdef NOT_USED
	else if ((*s & 0xfc) == 0xf8)
		len = 5;
	else if ((*s & 0xfe) == 0xfc)
		len = 6;
#endif
	else
		len = 1;
	return len;
}

/*
 * This is an implementation of wcwidth() and wcswidth() as defined in