Linux 处理中文字符串 :/区分中文和英文的方法

最近工作中遇到一个问题:要在一大堆 中文字符串中 分割 : 中文冒号:由于中文是unicode 所以用不了 strtok 函数。自己分割的第一步就是要自己找到固定中文字符的位置:

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

int chinese_or_english(char *str,int len)  
{  
 // char *p=NULL;
 

  char chinese[4] = {0};  
  
  for (int i = 0; i < len; i++) {  
    
    if ((str[i] & 0x80) == 0) {   //chinese:the top is 1  
    
	  // printf("alpha:%c\n", str[i]);  
    }  
    
    else {  
      chinese[0] = str[i];  
      chinese[1] = str[i + 1];  
      chinese[2] = str[i + 2];  
      i++;    
      i++;
		
    printf("chinese:%s i is %d\n", chinese,i); 
	if(strcmp(chinese,":")==0 )
	{
		//p=str+i;
			printf("find >>>>>>>>>>>>>> chinese:%s i is %d\n", chinese,i); 
		return i;
	}	
		
	
	  
    }  
  }  
}  













int main()
{
	char buff_s[128]="我算出来了,等于:二";
	printf("buff_s len is [%d]\n",strlen(buff_s));
	//char p=buff_s;
	int i =0;
	
	
	char want_buffer[64]={"\0"};
	
	int n=0;
	char *r=NULL;
	n=chinese_or_english(buff_s,strlen(buff_s));
	
	int j=0;
	printf("n is %d\n",n);
	if(n !=0)
	{
		//r=chinese_or_english+n;
		
		for(i=n+1;i<strlen(buff_s);i++)
		{
			want_buffer[j]=buff_s[i];
			j++;
			printf("i is %d\n",i);
		}
	}
	//want_buffer[i]='\0';
	printf("want_buffer is %s\n",want_buffer);
	
	
	/*
	for(i=0;i<30;i++)
	{
		
		if(i%3==0 && i >0)
		{
			printf("%c%c%c\n",buff_s[i-1],buff_s[i],buff_s[i+1]);
			printf("\n");
		}
			
			
		printf("%x ",buff_s[i]);	
	}
*/
	
	
	/*
	while(p != ":")
	{
		printf("*p is %c\n",*p);
		p++;
	}
	
	
	printf("p====:,ps is %c%c\n",*p,*(p+1));
	
	
	
	char*temp = strtok(buff_s,":");
    while(temp)
    {
        printf("%s \n",temp);
        temp = strtok(NULL,":");
    }
	*/


    return 0;

}

  

 

posted @ 2017-08-01 15:10  慢伴拍的二叉树  阅读(1350)  评论(0编辑  收藏  举报