C标准库string.h源码一strlen

头文件<string.h>中定义了2组字符串函数。第一组函数的名字以str开头;第二组函数的名字以mem开头。除函数memmove外,其他函数都没有定义重叠对象间的复制行为。比较函数将参数作为unsigned char类型的数组看待。

glibc库函数没有对指针的合法性进行检查,用户在调用函数之前,需要先检查指针的合法性。用户应该写类似如下的代码:

if(src == NULL || dest == NULL)
        return;//错误处理或返回
strcpy(dest,src);

对于string.h中的库函数,为了方便理解,我们先给出一般实现,说明其功能,然后再看看linux开源glibc的实现或windows CRT库Intel模块的实现。本节内容主要介绍strlen函数:

/*
strlen - return the length of a null-terminated string

Purpose:
       Finds the length in bytes of the given string, not including
       the final null character.
*/
int strlen (const char * str)
{
    int length = 0;
    while( *str++ )
        ++length;
    return( length );
}

 或者:

​
int strlen(const char *str)
{
    const char *p = str;
    while(*p != '\0')
        ++p;
    return p - str;
}

​

下面给出CRT的实现,先附上代码:

size_t strlen(const char *str)
{
        const char *char_ptr = NULL;
        const unsigned long int *longword_ptr = NULL;
        register unsigned long int longword, magic_bits;
 
        for (char_ptr = str; ((unsigned long int)(char_ptr) 
                        & (sizeof(unsigned long int) - 1)) != 0; ++char_ptr)
        {   
                if (*char_ptr == '\0')
                        return char_ptr - str;
        }    
 
        longword_ptr = (const unsigned long int *)char_ptr;
        magic_bits = 0x7efefeffL;
 
        for ( ;; )
        {   
                longword = *longword_ptr++;
                if ((((longword + magic_bits) ^ ~longword) & ~magic_bits) != 0)
                {   
                        const char *cp = (const char *)(longword_ptr - 1); 
                        if (cp[0] == '\0')
                                return cp - str;
                        if (cp[1] == '\0')
                                return cp - str + 1;
                        if (cp[2] == '\0')
                                return cp - str + 2;
                        if (cp[3] == '\0')
                                return cp - str + 3;
                }   
        }   
}

算法大致步骤:

1、首先把指针移到地址是机器字的整数倍的位置,假如已经遇到为0的字节,则直接返回长度

2、从此位置开始,每次比较一个机器字,直至遇到第一个为0的字节

3、找出这个字节在这个机器字的位置,然后返回长度

//下面代码将char_ptr从起始位置str移动到操作系统内存对齐位置,如果操作系统为32位,
//该操作就是将char_ptr从起始位置str移动到(内存为0,4,8,12....),如果移动过程中已
//到str尾部,则返回,否则循环结束后,char_ptr的位置,一定是4的整数倍,它为接下来
//程序一次性操作4个字节做准备。这样做的原因是32位系统一次性操作32位数据时速度最快。
for (char_ptr = str; ((unsigned long int)(char_ptr) 
        & (sizeof(unsigned long int) - 1)) != 0; ++char_ptr)
{   
    if (*char_ptr == '\0')
        return char_ptr - str;
} 

 

//for循环中,指针每次步进4个字节,以遍历整个str,当遇到'\0'则返回长度
//if ((((longword + magic_bits) ^ ~longword) & ~magic_bits) != 0)
//这条if语句表示整数longword这4个字节中是否存在某个字节为0,如果存在某
//个字节为0,则找到它,返回字符串长度,如果longword4个字节都非0,则指针
//继续向前,每次步进4个字节长度,直到找到str中某一位为0
for ( ;; )
{   
    longword = *longword_ptr++;
    if ((((longword + magic_bits) ^ ~longword) & ~magic_bits) != 0)
    {   
        const char *cp = (const char *)(longword_ptr - 1); 
        if (cp[0] == '\0')
            return cp - str;
        if (cp[1] == '\0')
            return cp - str + 1;
        if (cp[2] == '\0')
            return cp - str + 2;
        if (cp[3] == '\0')
            return cp - str + 3;
    }   
}

 if ((((longword + magic_bits) ^ ~longword) & ~magic_bits) != 0)来查找长整型longword4(或8)字节中是否存在某一个字节为0的具体算法可参考https://blog.csdn.net/astrotycoon/article/details/8124359,这里不多做介绍了。

本文最后给出glibc的strlen实现:
 

/* Return the length of the null-terminated string STR.  Scan for
   the null terminator quickly by testing four bytes at a time.  */

size_t strlen(const char *str), CONST char *str)
{
  const char *char_ptr;
  const unsigned long int *longword_ptr;
  unsigned long int longword, magic_bits, himagic, lomagic;

  /* Handle the first few characters by reading one character at a time.
     Do this until CHAR_PTR is aligned on a longword boundary.  */
  for (char_ptr = str; ((unsigned long int) char_ptr
			& (sizeof (longword) - 1)) != 0; ++char_ptr)
    if (*char_ptr == '\0')
      return char_ptr - str;

  /* All these elucidatory comments refer to 4-byte longwords,
     but the theory applies equally well to 8-byte longwords.  */

  longword_ptr = (unsigned long int *) char_ptr;

  /* Bits 31, 24, 16, and 8 of this number are zero.  Call these bits
     the "holes."  Note that there is a hole just to the left of
     each byte, with an extra at the end:
     
     bits:  01111110 11111110 11111110 11111111
     bytes: AAAAAAAA BBBBBBBB CCCCCCCC DDDDDDDD 

     The 1-bits make sure that carries propagate to the next 0-bit.
     The 0-bits provide holes for carries to fall into.  */
  magic_bits = 0x7efefeffL;
  himagic = 0x80808080L;
  lomagic = 0x01010101L;
  if (sizeof (longword) > 4)
    {
      /* 64-bit version of the magic.  */
      magic_bits = (0x7efefefeL << 32) | 0xfefefeffL;
      himagic = (himagic << 32) | himagic;
      lomagic = (lomagic << 32) | lomagic;
    }
  if (sizeof (longword) > 8)
    abort ();

  /* Instead of the traditional loop which tests each character,
     we will test a longword at a time.  The tricky part is testing
     if *any of the four* bytes in the longword in question are zero.  */
  for (;;)
    {
      /* We tentatively exit the loop if adding MAGIC_BITS to
	 LONGWORD fails to change any of the hole bits of LONGWORD.

	 1) Is this safe?  Will it catch all the zero bytes?
	 Suppose there is a byte with all zeros.  Any carry bits
	 propagating from its left will fall into the hole at its
	 least significant bit and stop.  Since there will be no
	 carry from its most significant bit, the LSB of the
	 byte to the left will be unchanged, and the zero will be
	 detected.

	 2) Is this worthwhile?  Will it ignore everything except
	 zero bytes?  Suppose every byte of LONGWORD has a bit set
	 somewhere.  There will be a carry into bit 8.  If bit 8
	 is set, this will carry into bit 16.  If bit 8 is clear,
	 one of bits 9-15 must be set, so there will be a carry
	 into bit 16.  Similarly, there will be a carry into bit
	 24.  If one of bits 24-30 is set, there will be a carry
	 into bit 31, so all of the hole bits will be changed.

	 The one misfire occurs when bits 24-30 are clear and bit
	 31 is set; in this case, the hole at bit 31 is not
	 changed.  If we had access to the processor carry flag,
	 we could close this loophole by putting the fourth hole
	 at bit 32!

	 So it ignores everything except 128's, when they're aligned
	 properly.  */

      longword = *longword_ptr++;

      if (
#if 0
	  /* Add MAGIC_BITS to LONGWORD.  */
	  (((longword + magic_bits)

	    /* Set those bits that were unchanged by the addition.  */
	    ^ ~longword)

	   /* Look at only the hole bits.  If any of the hole bits
	      are unchanged, most likely one of the bytes was a
	      zero.  */
	   & ~magic_bits)
#else
	  ((longword - lomagic) & himagic)
#endif
	  != 0)
	{
	  /* Which of the bytes was the zero?  If none of them were, it was
	     a misfire; continue the search.  */

	  CONST char *cp = (CONST char *) (longword_ptr - 1);

	  if (cp[0] == 0)
	    return cp - str;
	  if (cp[1] == 0)
	    return cp - str + 1;
	  if (cp[2] == 0)
	    return cp - str + 2;
	  if (cp[3] == 0)
	    return cp - str + 3;
	  if (sizeof (longword) > 4)
	    {
	      if (cp[4] == 0)
		return cp - str + 4;
	      if (cp[5] == 0)
		return cp - str + 5;
	      if (cp[6] == 0)
		return cp - str + 6;
	      if (cp[7] == 0)
		return cp - str + 7;
	    }
	}
    }
}

 


 

 

 

 


 

 

 

 

展开阅读全文

没有更多推荐了,返回首页