- 论坛徽章:
- 0
|
本帖最后由 fallening 于 2011-11-07 04:27 编辑
我觉得有两个地方可以优化:
1) 查找前边一个空格的时候,可以参照 glibc 的 strlen 实现优化:- 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;
- for (char_ptr = str; ((unsigned long int) char_ptr
- & (sizeof (longword) - 1)) != 0;
- ++char_ptr)
- if (*char_ptr == '\0')
- return char_ptr - str;
- longword_ptr = (unsigned long int *) char_ptr;
- magic_bits = 0x7efefeffL;
- himagic = 0x80808080L;
- lomagic = 0x01010101L;
- if (sizeof (longword) > 4)
- {
- magic_bits = ((0x7efefefeL << 16) << 16) | 0xfefefeffL;
- himagic = ((himagic << 16) << 16) | himagic;
- lomagic = ((lomagic << 16) << 16) | lomagic;
- }
- if (sizeof (longword) > 8)
- abort ();
- for (;;)
- {
- longword = *longword_ptr++;
- if (
- #if 0
- (((longword + magic_bits)
- ^ ~longword)
- & ~magic_bits)
- #else
- ((longword - lomagic) & himagic)
- #endif
- != 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 (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;
- }
- }
- }
- }
复制代码 2) 查找后边一个空格的时候,可以根据字符串的长度,决定 tail 是从前往后找还是从后往前找。当然这个阈值需要统计大量样本找出经验值来,而且可能在不同的机器上存在差别。 |
|