glibc系列之strlen()函数学习。
首先奉上的是strlen的源代码:
size_t
STRLEN (const char *str) 可以看到返回值是个size_t,输入参数是char型数组。
{
const char *char_ptr;
const unsigned long int *longword_ptr;
unsigned long int longword, 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; 这里在做的是字节对齐。
++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. */
himagic = 0x80808080L; 这两个魔数很重要。
lomagic = 0x01010101L;
if (sizeof (longword) > 4)
{
/* 64-bit version of the magic. */
/* Do the shift in two steps to avoid a warning if long has 32 bits. */
himagic = ((himagic << 16) << 16) | himagic;
lomagic = ((lomagic << 16) << 16) | 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 (;;)
{
longword = *longword_ptr++;
if (((longword - lomagic) & ~longword & himagic) != 0) 主要是判断这连续的四个字节有没有0x0,如果有0,那么进入到if语句中,
{
/* 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;
}
}
}
}
下面是代码解析
首先给出俩例子来形象的说明这个问题。
1
himagic = 0x80808080L; 1000-0000 1000-0000 1000-0000 1000-0000
lomagic = 0x01010101L; 0000-0001 0000-0001 0000-0001 0000-0001
((longword - lomagic) & ~longword & himagic) != 0
举个例子来说明这个问题:
longword = 000000ff
a =(longword - lomagic) =fefefffe
b = ~longword = ffffff00
a&b = fefeff00
himagic = 80808080
a&b&himagic 80808000
2
另一个例子: longword =00000000
a =(longword - lomagic) =fefefeff
b = ~longword =ffffffff
a&b = fefefeff
himagic = 80808080
a&b&himagic = 80808080
其实最主要的是if (((longword - lomagic) & ~longword & himagic) != 0)
怎么理解的。
首先考虑到的是ASCII码最高位是是0,
~longword & himagic
运算的结果就是看看哪个字节的最高位不是0.如果都是0 ,则运算结果是0x80808080.
longword - lomagic 运算结果是一旦longword 有一个字节为0,那么久会是0xfe。也就是找到了‘\0’,进入了if体里。
下面是我自己写的strlen()函数。
#define ulint unsigned long int //宏定义ulint
unsigned int
mglStrLen(const char * str)
{
//allign
const char *tempStr ;
for (tempStr = str; (ulint)tempStr &(sizeof(ulint) - 1) != 0; tempStr++)
{
if (*tempStr == '\0')
return tempStr - str;
}
//caculate the length
ulint himagic = 0x80808080;
ulint lomagic = 0x01010101;
const ulint* longwordPtr = ( const ulint *)tempStr; //这里也要注意对const char* 强制类型转化成const ulint*时也需要( const ulint *) 。这里的const修饰很有意思。
while (1)
{
longwordPtr++;
if (((*longwordPtr - lomagic)&~(*longwordPtr)&himagic) != 0) //跟glibc一样的处理方法。
{
if (*(char *)longwordPtr == 0) //这里要注意的是longwordPtr 指向的int型,对于单个的字节比对,需要(char*)强制类型转换。
return (char *)longwordPtr - str; //这里的强制类型转化是因为str是const char* ,他们要一样。
if (*((char *)longwordPtr+1) == 0)
return (char *)longwordPtr - str+1;
if (*((char *)longwordPtr + 2) == 0)
return (char *)longwordPtr - str + 2;
if (*((char *)longwordPtr + 3) == 0)
return (char *)longwordPtr - str + 3;
}
}
}
void main()
{
char str[] = "mglhahaahhahah"; ---->14个字节
int len = mglStrLen(str);
cout << "mgl " <<len<< endl;
}
程序运行结果:
mgl 14
请按任意键继续. . .
一个属于mgl的完美unsigned int strlen(const char * str){}函数。
哈哈!!