C Language Study-Three large character processing function implementation

Three large character processing function implementation | | | |

==--==--==--==--==--==--

Strlen, strcpy, strcmp.

GLIBC:

The first appearances are strcmp:

/* Compare S1 and S2, returning less than, equal to or   greater than zero if S1 are lexicographically less than,   equ Al to or greater than S2.  */INTSTRCMP (const char *P1, const char *P2) {  const unsigned char *s1 = (const unsigned char *) p1;  Const unsigned char *s2 = (const unsigned char *) P2;  unsigned char c1, C2;  Do    {      C1 = (unsigned char) *s1++;      C2 = (unsigned char) *s2++;      if (c1 = = ') ' Return c1-c2;    }  while (c1 = = C2);  return C1-C2;}

strcpy:

/* Copy SRC to DEST.  */char *strcpy (char *dest, const char *src) {  return memcpy (dest, SRC, strlen (src) + 1);}

strlen:

/* Return The length of the null-terminated string STR.  Scan for the null terminator quickly by testing four bytes at a time.  */size_tstrlen (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 are aligned on a longword boundary. */for (char_ptr = str;       ((unsigned long int) char_ptr& (sizeof (Longword)-1))! = 0;  ++CHAR_PTR) if (*char_ptr = = ' + ') 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, and 8 of this number is zero.  Call these bits the "holes." Note that there was a hole just to the left of each of the bytes, with an extra at the end:bits:01111110 11111110 111111 Ten 11111111 bytes:aaaaaaaa bbbbbbbb CCCCCCCC dddddddd The 1-bits make sure this carries propagate to the next 0-bit.  The 0-bits provide holes for carries and fall into.  */himagic = 0x80808080l;  Lomagic = 0x01010101l;  if (sizeof (Longword) > 4) {/* 64-bit version of the magic.  */*/* Do the shift in and steps to avoid a warning if long has a. */Himagic = ((himagic << +) << 16) |      Himagic; Lomagic = ((lomagic <<) << 16) |    Lomagic;  } if (sizeof (Longword) > 8) abort ();  /* Instead of the traditional loop which tests each character, we'll test a longword at a time.  The tricky part was testing if *any of the four* bytes in the Longword in question is 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; }}    }}

XNUSLIBC:

C Language Study-Three large character processing function implementation