strlen源码剖析
来源:互联网 发布:java中的数组声明 编辑:程序博客网 时间:2024/05/20 04:27
网上转载地址:http://www.cppblog.com/ant/archive/2007/10/12/32886.html
谢谢大牛的贡献。
在阅读glic源码库的时候对于strlen函数的时候略有困惑,网上找了下,有详细解析。
大概思路及其亮点:
1.使用4字或8字(取决于运行环境)来加快运行速度,设计对齐。
2.巧妙使用holes及其字符高位为0特性,可迅速找出字中为0 的字节。
3.很多函数使用这种思路,得一可以破百。
以下为源码:
/* 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;
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. */
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:
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
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 ();
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.
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.
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.
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!
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. */
properly. */
longword = *longword_ptr++;
if (
#if 0
/* Add MAGIC_BITS to LONGWORD. */
(((longword + magic_bits)
#if 0
/* Add MAGIC_BITS to LONGWORD. */
(((longword + magic_bits)
/* Set those bits that were unchanged by the addition. */
^ ~longword)
^ ~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. */
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;
}
}
}
}
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;
}
}
}
}
阅读全文
0 0
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- strlen源码剖析
- c/c++:strlen源码剖析
- strlen源码剖析(转自cppblog)
- 【库函数源码剖析系列】(4) strlen
- oracle循环
- linux防火墙操作指令
- 数据结构
- Android 官方兼容库 EmojiCompat Support Library
- 关于Invoke的使用
- strlen源码剖析
- Spring Security——异常信息本地化
- johnson最短路径
- 【c#】控制台程序编写计时器
- (笔记)Android获取相册图片并返回
- DFS简单题 杭电1241 POJ 1154
- 无法启动屏幕键盘
- 图片无缝向下滚动
- Android应用开发工程师技术栈