UTF-8字符串分段选取（转）

原创

woodcol 2022-09-14 12:44:10 博主文章分类：C/C++ ©著作权

©著作权归作者所有：来自51CTO博客作者woodcol的原创作品，请联系作者获取转载授权，否则将追究法律责任

最近项目中要处理utf-8字符串，需要计算字符串长度以及对其裁剪，例子代码如下：

#include <stdio.h>
#include <string.h>
#include <stdlib.h>


//utf8字符长度1-6，可以根据每个字符第一个字节判断整个字符长度
//0xxxxxxx
//110xxxxx 10xxxxxx
//1110xxxx 10xxxxxx 10xxxxxx
//11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
//111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
//1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
//
//定义查找表，长度256，表中的数值表示以此为起始字节的utf8字符长度
unsigned char utf8_look_for_table[] = 
{
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 6, 6, 1, 1
};

#define UTFLEN(x) 

//计算str字符数目
int getUtf8Length(char *str)
{
int clen = strlen(str);
int len = 0;
for(char *ptr = str; 
*ptr!=0&&len<clen; 
len++, ptr+=UTFLEN((unsigned char)*ptr));
return len;
}

//get子串
char* subUtfString(char *str, unsigned int start, unsigned int end)
{
int len = getUtf8Length(str);
if(start >= len) return NULL;
if(end > len) end = len;
char *sptr = str;
for(int i = 0; i < start; ++i,sptr+=UTFLEN((unsigned char)*sptr));
char *eptr = sptr;
for(int i = start; i < end; ++i,eptr += UTFLEN((unsigned char)*eptr));
int retLen = eptr - sptr;
char *retStr = (char*)malloc(retLen+1);
memcpy(retStr, sptr, retLen);
retStr[retLen] = 0;
return retStr;
}

int main()
{
char*str = "我的a测试工具阿斯顿aaab123阿斯顿个流氓了卡斯！";
printf("%s\n", str);
for(char *ptr=str; *ptr!=0;) {
unsignedcharc = (unsignedchar)*ptr;
printf("str[%d] is a word character with %d bytes\n", c, UTFLEN(c));
ptr += UTFLEN(c);
}
printf("%d\n", getUtf8Length(str));
char *sub = subUtfString(str, 2, 100);
if(sub) {
printf("%s\n", sub);
free(sub);
sub = NULL;
}
return0;
}