如何通过指针读取 UTF-8 字符? [英] How do I read UTF-8 characters via a pointer?
问题描述
假设我在内存中存储了 UTF-8 内容，如何使用指针读取字符?我想我需要注意指示多字节字符的第 8 位，但是我究竟如何将序列转换为有效的 Unicode 字符?另外，wchar_t 是存储单个 Unicode 字符的正确类型吗?
这是我的想法:
<前><代码>wchar_t readNextChar (char*& p){wchar_t unicodeChar;字符 ch = *p++;如果 ((ch & 128) != 0){//这是一个多字节字符，我现在该怎么办?//字符 chNext = *p++;//...但是我如何组合Unicode字符?...}...返回 unicodeChar;}您必须将 UTF-8 位模式解码为其未编码的 UTF-32 表示.如果您想要实际的 Unicode 代码点，则必须使用 32 位数据类型.
在 Windows 上，wchar_t 不够大，因为它只有 16 位.您必须使用 unsigned int 或 unsigned long 代替.仅在处理 UTF-16 代码单元时使用 wchar_t.
在其他平台上，wchar_t 通常是 32 位.但是在编写可移植代码时，除了绝对需要的地方(例如 std::wstring)外，您应该远离 wchar_t.
尝试更像这样的事情:
#define IS_IN_RANGE(c, f, l) (((c) >= (f)) && ((c) <= (l)))u_long readNextChar (char* &p){//TODO: 因为 UTF-8 是可变长度的//编码，你应该传入输入//缓冲区的实际字节长度，以便您//可以判断是否是格式错误的 UTF-8//序列将超过缓冲区的末尾...u_char c1, c2, *ptr = (u_char*) p;u_long uc = 0;整数序列；//int datalen = ... p 的可用长度 ...;/*如果(数据len <1 ){//格式错误的数据，做点什么！！！返回(u_long)-1；}*/c1 = ptr[0];if( (c1 & 0x80) == 0 ){uc = (u_long) (c1 & 0x7F);序列= 1;}否则如果((c1& 0xE0)== 0xC0){uc = (u_long) (c1 & 0x1F);序列= 2;}否则如果((c1& 0xF0)== 0xE0){uc = (u_long) (c1 & 0x0F);序列= 3;}否则如果((c1& 0xF8)== 0xF0){uc = (u_long) (c1 & 0x07);序列= 4;}别的{//格式错误的数据，做点什么！！！返回(u_long)-1；}/*if( seqlen > datalen ){//格式错误的数据，做点什么！！！返回(u_long)-1；}*/for(int i = 1; i < seqlen; ++i){c1 = ptr[i];如果( (c1 & 0xC0) != 0x80 ){//格式错误的数据，做点什么！！！返回(u_long)-1；}}开关(序列){案例2:{c1 = ptr[0];如果(！IS_IN_RANGE(c1，0xC2，0xDF)){//格式错误的数据，做点什么！！！返回(u_long)-1；}休息;}案例3:{c1 = ptr[0];c2 = ptr[1];开关 (c1){案例 0xE0:如果(！IS_IN_RANGE(c2，0xA0，0xBF)){//格式错误的数据，做点什么！！！返回(u_long)-1；}休息;案例 0xED:如果 (!IS_IN_RANGE(c2, 0x80, 0x9F)){//格式错误的数据，做点什么！！！返回(u_long)-1；}休息;默认:如果 (!IS_IN_RANGE(c1, 0xE1, 0xEC) && !IS_IN_RANGE(c1, 0xEE, 0xEF)){//格式错误的数据，做点什么！！！返回(u_long)-1；}休息;}休息;}案例4:{c1 = ptr[0];c2 = ptr[1];开关 (c1){案例 0xF0:如果(！IS_IN_RANGE(c2，0x90，0xBF)){//格式错误的数据，做点什么！！！返回(u_long)-1；}休息;案例0xF4:如果 (!IS_IN_RANGE(c2, 0x80, 0x8F)){//格式错误的数据，做点什么！！！返回(u_long)-1；}休息;默认:如果 (!IS_IN_RANGE(c1, 0xF1, 0xF3)){//格式错误的数据，做点什么！！！返回(u_long)-1；}休息;}休息;}}for(int i = 1; i < seqlen; ++i){uc = ((uc <<6) | (u_long)(ptr[i] & 0x3F));}p += 序列；返回 uc;}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;
}
这篇关于如何通过指针读取 UTF-8 字符?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
