【C】glibc中字符串处理的几个函数实现分析

柔光的暖阳◎ 2022-08-17 14:21 189阅读 0赞

在C语言中，我们经常会用到字符串处理的几个函数，如strcat、strcmp、strcpy等，那么这些函数是怎么实现的呢？

## strcat—— ##

char* strcat(char *dest, const char *src);

字符串拼接，把src追加到dest后面。

测试用例：

#include <stdio.h> 
    #include <string.h> 
    
    int main() 
    { 
        char arr[20] = "apple"; 
        const char *p = "pear"; 
        char *p2 = strcat(arr, p); 
        printf("arr=%s,p=%s,p2=%s\n", arr, p, p2);//arr=applepear,p=pear,p2=applepear 
    
        return 0; 
    }

函数实现：

char* strcat(char *dest, const char *src) 
    { 
        char *s1 = dest; 
        const char *s2 = src; 
        char c; 
    
        /* Find the end of the string. */ 
        do 
            c = *s1++; 
        while (c != '\0'); 
    
        /* Make S1 point before the next character, so we can increment it while memory is read (wins on pipelined cpus). */ 
        s1 -= 2; 
    
        do { 
            c = *s2++; 
            *++s1 = c; 
        } 
        while (c != '\0'); 
    
        return dest; 
    }

## strcmp—— ##

int strcmp(const char *s1, const char *s2);

字符串比较，逐个比较s1和s2对应位置的字符。

测试用例：

#include <stdio.h>
    #include <string.h>
    
    int main()
    {
        const char *pc = "abc";
        const char *pc2 = "abcdefg";
        const char *pc3 = "abc";
        printf("d:%d\n", 'd');
        printf("strcmp(pc, pc2):%d\n", strcmp(pc, pc2));
        printf("strcmp(pc2, pc):%d\n", strcmp(pc2, pc));
        printf("strcmp(pc, pc3):%d\n", strcmp(pc, pc3));
        //d:100
        //strcmp(pc, pc2):-100
        //strcmp(pc2, pc):100
        //strcmp(pc, pc3):0
    
        return 0;
    }

函数实现：

int strcmp (const char *p1, const char *p2) 
    { 
        const unsigned char *s1 = (const unsigned char*)p1; 
        const unsigned char *s2 = (const unsigned char*)p2; 
        unsigned char c1, c2; 
    
        do { 
            c1 = (unsigned char)*s1++; 
            c2 = (unsigned char)*s2++; 
            if (c1 == '\0')//如果c1 == '\0', 字符串末尾, 比较结束. 
                return c1 - c2; 
        } 
        while (c1 == c2);//如果c2 == '\0' && c1 != '\0'，比较也会结束. 
    
        return c1 - c2; 
    }

## strncat—— ##

char *strncat(char *dest, const char *src, size_t n);

字符串拼接，把src追加到dest后面，最多追加n个字符。

测试用例：

#include <stdio.h> 
    #include <string.h> 
    
    int main() 
    { 
        char a[10] = "apple"; 
        const char *pt = "pear"; 
        char *pt2= strncat(a, pt, 2); 
        printf("a=%s,pt=%s,pt2=%s\n", a, pt, pt2);//a=applepe,pt=pear,pt2=applepe 
    
        return 0; 
    }

函数实现：

char* strncat(char *s1, const char *s2, size_t n) 
    { 
        char c; 
        char *s = s1; 
    
        do 
            c = *s1++; 
        while (c != '\0'); 
    
        s1 -= 2; 
        /* 上面的处理同strcat, 把指针移动到合适的位置, 等待字符串的追加 */ 
    
        /* 当n >= 4时, n右移两位, 即除以4, 这样效率更高. */ 
        if (n >= 4) { 
            size_t n4 = n >> 2; 
            do { 
                c = *s2++; 
                *++s1 = c; 
                if (c == '\0') 
                    return s; 
                c = *s2++; 
                *++s1 = c; 
                if (c == '\0') 
                    return s; 
                c = *s2++; 
                *++s1 = c; 
                if (c == '\0') 
                    return s; 
                c = *s2++; 
                *++s1 = c; 
                if (c == '\0') 
                    return s; 
            } 
            while (--n4 > 0); 
            n &= 3;/* 相当于取n/4的余数, 位操作符的效率比+、-要高，比*、/更高. */ 
        } 
    
        while (n > 0) { 
            c = *s2++; 
            *++s1 = c; 
            if (c == '\0') 
                return s; 
            n--; 
        } 
    
        if (c != '\0') 
            *++s1 = '\0'; 
    
        return s; 
    }

除了上面提到的几个函数之外，string.h/strings.h还提供了大量的字符串处理函数，可以在linux shell中“man 3 string”查看。