bool is_utf8(const char *source)
{
const unsigned char* cur = (const unsigned char*)source;
while (*cur)
{
unsigned short next_n = g_trailing_bytes_for_utf8[*cur] + 1;
if (!is_legal_utf8(cur, next_n))
{
return false;
}
cur += next_n;
}
return true;
}
bool is_utf8(const char *source, size_t length)
{
const unsigned char* begin = (const unsigned char*)source;
const unsigned char* end = begin + length;
const unsigned char* cur = begin;
while (cur < end)
{
unsigned short next_n = g_trailing_bytes_for_utf8[*cur] + 1;
if (0 == *cur || cur + next_n > end)
{
return false;
}
if (!is_legal_utf8(cur, next_n))
{
return false;
}
cur += next_n;
}
return true;
}
bool is_utf8(const char *source)
{
while (*source)
{
const unsigned char *srcptr = (const unsigned char*)source;
unsigned short extra_bytes_to_read = g_trailing_bytes_for_utf8[*srcptr];
switch (extra_bytes_to_read)
{
case 5: if (0 == *source++) return false;
case 4: if (0 == *source++) return false;
case 3: if (0 == *source++) return false;
case 2: if (0 == *source++) return false;
case 1: if (0 == *source++) return false;
case 0: if (0 == *source++) return false;
}
if (!is_legal_utf8(srcptr, extra_bytes_to_read+1))
{
return false;
}
}
return true;
}
