about summary refs log tree commit diff
path: root/REORG.TODO/string/strlen.c
diff options
context:
space:
mode:
Diffstat (limited to 'REORG.TODO/string/strlen.c')
-rw-r--r--REORG.TODO/string/strlen.c109
1 files changed, 109 insertions, 0 deletions
diff --git a/REORG.TODO/string/strlen.c b/REORG.TODO/string/strlen.c
new file mode 100644
index 0000000000..b368ccf58f
--- /dev/null
+++ b/REORG.TODO/string/strlen.c
@@ -0,0 +1,109 @@
+/* Copyright (C) 1991-2017 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+   Written by Torbjorn Granlund (tege@sics.se),
+   with help from Dan Sahlin (dan@sics.se);
+   commentary by Jim Blandy (jimb@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, see
+   <http://www.gnu.org/licenses/>.  */
+
+#include <string.h>
+#include <stdlib.h>
+
+#undef strlen
+
+#ifndef STRLEN
+# define STRLEN strlen
+#endif
+
+/* 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 (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)