C语言
分析strlen源码中遇到的问题
墨衍会员 · AI 创作全网分发 墨衍智能分发 通过墨衍一键同步至各平台 可同步平台 CSDN微信公众号微博知乎掘金百家号博客园抖音小红书 你的文章也可以这样分发 墨衍会员 ¥399起/年，写一次发全网
我也要 关注 + 加入社区贴源码：
glibc 2.7
[/code]
glibc 2.7
#include <string.h>
#include <stdlib.h>
#undef strlen
/* 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 (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. */
/* Do the shift in two steps to avoid a warning if long has 32 bits. */
magic_bits = ((0x7efefefeL << 16) << 16) | 0xfefefeffL;
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 (;;)
{
/* 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;
}
}
}
}
libc_hidden_builtin_def (strlen)
glibc 2.16
[code=C/C++]
#include <string.h>
#include <stdlib.h>
#undef strlen
/* 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 (str)
const char *str;
{
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;
++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;
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)
{
/* 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;
}
}
}
}
libc_hidden_builtin_def (strlen)
请问if (((longword - lomagic) & himagic) != 0) 和 if (((longword - lomagic) & ~longword & himagic) != 0)这两种写法的区别是什么呢？ 真心求教
[/code]
...全文
相关推荐
strlen、strcpy和strcmp源码
strlen、strcpy和strcmp源码
C语言常用函数源码 strcmp strlen atoi atol memcpy strchr strstr printf等等
C语言常用函数源码 strcmp strlen atoi atol memcpy strchr strstr printf等,不可不看.公司面试的时候很容易让写出其中某些函数的源码.这些函数的源码确实简洁,高效
C语言项目案例分析 源码
C语言项目案例分析 源码
C语言指针题目实战解析[可运行源码]
本文深入解析了C语言中指针与数组的常见面试题，涵盖了一维数组、二维数组、字符数组的sizeof和strlen操作，以及指针运算、字符串处理、排序算法等核心知识点。通过20余个典型例题的代码实现和图解分析，详细讲解了指针在不同场景下的应用，包括数组名在不同上下文中的含义、指针加减运算、冒泡排序优化、qsort函数模拟实现等内容。文章还提供了字符串逆序、左旋、查找等实用案例，并针对阿里巴巴等大厂面试题进行解析，最后介绍了如何利用指针高效解决算法问题，为读者系统梳理了指针相关的重点难点。
C语言经典编程282例源码
学习C语言的朋友，如果你把这些 C语言经典编程282例源码搞懂，把这些程序敲一遍，能够灵活运用，那么我可以告诉你，你已经是一个人C语言高手了，不信可以试试。
