Suppose I have UTF-8 content stored in memory, how do I read the characters using a pointer? I presume I need to watch for the 8th bit indicating a multi-byte character, but how exactly do I turn the sequence into a valid Unicode character? Also, is wchar_t
the proper type to store a single Unicode character?
This is what I have in mind:
wchar_t readNextChar (char*& p)
{
wchar_t unicodeChar;
char ch = *p++;
if ((ch & 128) != 0)
{
// This is a multi-byte character, what do I do now?
// char chNext = *p++;
// ... but how do I assemble the Unicode character?
...
}
...
return unicodeChar;
}
You have to decode the UTF-8 bit pattern to its unencoded UTF-32 representation. If you want the actual Unicode codepoint, you have to use a 32-bit data type.
On Windows, wchar_t
is NOT large enough, as it is only 16-bit. You have to use an unsigned int
or unsigned long
instead. Use wchar_t
only when dealing with UTF-16 codeunits instead.
On other platforms, wchar_t
is usually 32bit. But when writing portable code, you should stay away from wchar_t
except where absolutely needed (like std::wstring
).
Try something more like this:
#define IS_IN_RANGE(c, f, l) (((c) >= (f)) && ((c) <= (l)))
u_long readNextChar (char* &p)
{
// TODO: since UTF-8 is a variable-length
// encoding, you should pass in the input
// buffer's actual byte length so that you
// can determine if a malformed UTF-8
// sequence would exceed the end of the buffer...
u_char c1, c2, *ptr = (u_char*) p;
u_long uc = 0;
int seqlen;
// int datalen = ... available length of p ...;
/*
if( datalen < 1 )
{
// malformed data, do something !!!
return (u_long) -1;
}
*/
c1 = ptr[0];
if( (c1 & 0x80) == 0 )
{
uc = (u_long) (c1 & 0x7F);
seqlen = 1;
}
else if( (c1 & 0xE0) == 0xC0 )
{
uc = (u_long) (c1 & 0x1F);
seqlen = 2;
}
else if( (c1 & 0xF0) == 0xE0 )
{
uc = (u_long) (c1 & 0x0F);
seqlen = 3;
}
else if( (c1 & 0xF8) == 0xF0 )
{
uc = (u_long) (c1 & 0x07);
seqlen = 4;
}
else
{
// malformed data, do something !!!
return (u_long) -1;
}
/*
if( seqlen > datalen )
{
// malformed data, do something !!!
return (u_long) -1;
}
*/
for(int i = 1; i < seqlen; ++i)
{
c1 = ptr[i];
if( (c1 & 0xC0) != 0x80 )
{
// malformed data, do something !!!
return (u_long) -1;
}
}
switch( seqlen )
{
case 2:
{
c1 = ptr[0];
if( !IS_IN_RANGE(c1, 0xC2, 0xDF) )
{
// malformed data, do something !!!
return (u_long) -1;
}
break;
}
case 3:
{
c1 = ptr[0];
c2 = ptr[1];
switch (c1)
{
case 0xE0:
if (!IS_IN_RANGE(c2, 0xA0, 0xBF))
{
// malformed data, do something !!!
return (u_long) -1;
}
break;
case 0xED:
if (!IS_IN_RANGE(c2, 0x80, 0x9F))
{
// malformed data, do something !!!
return (u_long) -1;
}
break;
default:
if (!IS_IN_RANGE(c1, 0xE1, 0xEC) && !IS_IN_RANGE(c1, 0xEE, 0xEF))
{
// malformed data, do something !!!
return (u_long) -1;
}
break;
}
break;
}
case 4:
{
c1 = ptr[0];
c2 = ptr[1];
switch (c1)
{
case 0xF0:
if (!IS_IN_RANGE(c2, 0x90, 0xBF))
{
// malformed data, do something !!!
return (u_long) -1;
}
break;
case 0xF4:
if (!IS_IN_RANGE(c2, 0x80, 0x8F))
{
// malformed data, do something !!!
return (u_long) -1;
}
break;
default:
if (!IS_IN_RANGE(c1, 0xF1, 0xF3))
{
// malformed data, do something !!!
return (u_long) -1;
}
break;
}
break;
}
}
for(int i = 1; i < seqlen; ++i)
{
uc = ((uc << 6) | (u_long)(ptr[i] & 0x3F));
}
p += seqlen;
return uc;
}
Here is a quick macro that will count UTF-8 bytes
#define UTF8_CHAR_LEN( byte ) (( 0xE5000000 >> (( byte >> 3 ) & 0x1e )) & 3 ) + 1
This will help you detect the size of the UTF-8 character for easier parsing.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With