about summary refs log tree commit diff
path: root/string/strchr.c
diff options
context:
space:
mode:
Diffstat (limited to 'string/strchr.c')
-rw-r--r--string/strchr.c191
1 files changed, 191 insertions, 0 deletions
diff --git a/string/strchr.c b/string/strchr.c
new file mode 100644
index 0000000000..5afd364533
--- /dev/null
+++ b/string/strchr.c
@@ -0,0 +1,191 @@
+/* Copyright (C) 1991,1993-1997,1999,2000,2003,2006
+   Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+   Based on strlen implementation by Torbjorn Granlund (tege@sics.se),
+   with help from Dan Sahlin (dan@sics.se) and
+   bug fix and commentary by Jim Blandy (jimb@ai.mit.edu);
+   adaptation to strchr suggested by Dick Karpinski (dick@cca.ucsf.edu),
+   and implemented by Roland McGrath (roland@ai.mit.edu).
+
+   The GNU C Library is free software; you can redistribute it and/or
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, write to the Free
+   Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+   02111-1307 USA.  */
+
+#include <string.h>
+#include <memcopy.h>
+#include <stdlib.h>
+
+#undef strchr
+
+/* Find the first occurrence of C in S.  */
+char *
+strchr (s, c_in)
+     const char *s;
+     int c_in;
+{
+  const unsigned char *char_ptr;
+  const unsigned long int *longword_ptr;
+  unsigned long int longword, magic_bits, charmask;
+  unsigned reg_char c;
+
+  c = (unsigned char) c_in;
+
+  /* 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 = (const unsigned char *) s;
+       ((unsigned long int) char_ptr & (sizeof (longword) - 1)) != 0;
+       ++char_ptr)
+    if (*char_ptr == c)
+      return (void *) char_ptr;
+    else if (*char_ptr == '\0')
+      return NULL;
+
+  /* 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.  */
+  switch (sizeof (longword))
+    {
+    case 4: magic_bits = 0x7efefeffL; break;
+    case 8: magic_bits = ((0x7efefefeL << 16) << 16) | 0xfefefeffL; break;
+    default:
+      abort ();
+    }
+
+  /* Set up a longword, each of whose bytes is C.  */
+  charmask = c | (c << 8);
+  charmask |= charmask << 16;
+  if (sizeof (longword) > 4)
+    /* Do the shift in two steps to avoid a warning if long has 32 bits.  */
+    charmask |= (charmask << 16) << 16;
+  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.
+
+	 3) But wait!  Aren't we looking for C as well as zero?
+	 Good point.  So what we do is XOR LONGWORD with a longword,
+	 each of whose bytes is C.  This turns each byte that is C
+	 into a zero.  */
+
+      longword = *longword_ptr++;
+
+      /* Add MAGIC_BITS to LONGWORD.  */
+      if ((((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) != 0 ||
+
+	  /* That caught zeroes.  Now test for C.  */
+	  ((((longword ^ charmask) + magic_bits) ^ ~(longword ^ charmask))
+	   & ~magic_bits) != 0)
+	{
+	  /* Which of the bytes was C or zero?
+	     If none of them were, it was a misfire; continue the search.  */
+
+	  const unsigned char *cp = (const unsigned char *) (longword_ptr - 1);
+
+	  if (*cp == c)
+	    return (char *) cp;
+	  else if (*cp == '\0')
+	    return NULL;
+	  if (*++cp == c)
+	    return (char *) cp;
+	  else if (*cp == '\0')
+	    return NULL;
+	  if (*++cp == c)
+	    return (char *) cp;
+	  else if (*cp == '\0')
+	    return NULL;
+	  if (*++cp == c)
+	    return (char *) cp;
+	  else if (*cp == '\0')
+	    return NULL;
+	  if (sizeof (longword) > 4)
+	    {
+	      if (*++cp == c)
+		return (char *) cp;
+	      else if (*cp == '\0')
+		return NULL;
+	      if (*++cp == c)
+		return (char *) cp;
+	      else if (*cp == '\0')
+		return NULL;
+	      if (*++cp == c)
+		return (char *) cp;
+	      else if (*cp == '\0')
+		return NULL;
+	      if (*++cp == c)
+		return (char *) cp;
+	      else if (*cp == '\0')
+		return NULL;
+	    }
+	}
+    }
+
+  return NULL;
+}
+
+#ifdef weak_alias
+#undef index
+weak_alias (strchr, index)
+#endif
+libc_hidden_builtin_def (strchr)