Improve hashing quality when configured --with-wide-int.

* fns.c (hash_string): New function, taken from sxhash_string.
Do not discard information about ASCII character case; this
discarding is no longer needed.
(sxhash-string): Use it.  Change sig to match it.  Caller changed.
* lisp.h: Declare it.
* lread.c (hash_string): Remove, since we now use fns.c's version.
The fns.c version returns a wider integer if --with-wide-int is
specified, so this should help the quality of the hashing a bit.

diff --git a/src/ChangeLog b/src/ChangeLog
index 0265828c60e7fb3cbf8b0ca35bcb1ee02cf1eb44..aaf87deb9a547be44a7e634a01d137292a2072d3 100644 (file)
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,3 +1,15 @@
+2011-07-08  Paul Eggert  <eggert@cs.ucla.edu>
+
+       Improve hashing quality when configured --with-wide-int.
+       * fns.c (hash_string): New function, taken from sxhash_string.
+       Do not discard information about ASCII character case; this
+       discarding is no longer needed.
+       (sxhash-string): Use it.  Change sig to match it.  Caller changed.
+       * lisp.h: Declare it.
+       * lread.c (hash_string): Remove, since we now use fns.c's version.
+       The fns.c version returns a wider integer if --with-wide-int is
+       specified, so this should help the quality of the hashing a bit.
+
 2011-07-07  Paul Eggert  <eggert@cs.ucla.edu>
 
        * emacs.c: Integer overflow minor fix.

diff --git a/src/fns.c b/src/fns.c
index 0ca731ed331a7882d2c566ed6882df3d4c9b552d..9c9d19fe26a4419467d2cf32e9f52cd85d5aaac3 100644 (file)
--- a/src/fns.c
+++ b/src/fns.c
@@ -4098,25 +4098,33 @@ sweep_weak_hash_tables (void)
 #define SXHASH_REDUCE(X) \
   ((((X) ^ (X) >> (BITS_PER_EMACS_INT - FIXNUM_BITS))) & INTMASK)
 
-/* Return a hash for string PTR which has length LEN.  The hash
-   code returned is guaranteed to fit in a Lisp integer.  */
+/* Return a hash for string PTR which has length LEN.  The hash value
+   can be any EMACS_UINT value.  */
 
-static EMACS_UINT
-sxhash_string (unsigned char *ptr, EMACS_INT len)
+EMACS_UINT
+hash_string (char const *ptr, ptrdiff_t len)
 {
-  unsigned char *p = ptr;
-  unsigned char *end = p + len;
+  char const *p = ptr;
+  char const *end = p + len;
   unsigned char c;
   EMACS_UINT hash = 0;
 
   while (p != end)
     {
       c = *p++;
-      if (c >= 0140)
-       c -= 40;
       hash = SXHASH_COMBINE (hash, c);
     }
 
+  return hash;
+}
+
+/* Return a hash for string PTR which has length LEN.  The hash
+   code returned is guaranteed to fit in a Lisp integer.  */
+
+static EMACS_UINT
+sxhash_string (char const *ptr, ptrdiff_t len)
+{
+  EMACS_UINT hash = hash_string (ptr, len);
   return SXHASH_REDUCE (hash);
 }
 
@@ -4231,7 +4239,7 @@ sxhash (Lisp_Object obj, int depth)
       /* Fall through.  */
 
     case Lisp_String:
-      hash = sxhash_string (SDATA (obj), SCHARS (obj));
+      hash = sxhash_string (SSDATA (obj), SBYTES (obj));
       break;
 
       /* This can be everything from a vector to an overlay.  */

diff --git a/src/lisp.h b/src/lisp.h
index 257c204e3b0a932823d149fa2819958b54ebf95a..1e141dbb5d09eb54e96bbe70b819c420f9c6b0d2 100644 (file)
--- a/src/lisp.h
+++ b/src/lisp.h
@@ -2557,6 +2557,7 @@ extern void sweep_weak_hash_tables (void);
 extern Lisp_Object Qcursor_in_echo_area;
 extern Lisp_Object Qstring_lessp;
 extern Lisp_Object QCsize, QCtest, QCweakness, Qequal, Qeq, Qeql;
+EMACS_UINT hash_string (char const *, ptrdiff_t);
 EMACS_UINT sxhash (Lisp_Object, int);
 Lisp_Object make_hash_table (Lisp_Object, Lisp_Object, Lisp_Object,
                              Lisp_Object, Lisp_Object, Lisp_Object,

diff --git a/src/lread.c b/src/lread.c
index a9b69a1977b0d79b11354fdf919168e02c44bfac..6a97be2be420a7d6c526b5c51609d333b48be5d0 100644 (file)
--- a/src/lread.c
+++ b/src/lread.c
@@ -3647,8 +3647,6 @@ static Lisp_Object initial_obarray;
 
 static size_t oblookup_last_bucket_number;
 
-static size_t hash_string (const char *ptr, size_t len);
-
 /* Get an error if OBARRAY is not an obarray.
    If it is one, return it.  */
 
@@ -3891,23 +3889,6 @@ oblookup (Lisp_Object obarray, register const char *ptr, EMACS_INT size, EMACS_I
   XSETINT (tem, hash);
   return tem;
 }
-
-static size_t
-hash_string (const char *ptr, size_t len)
-{
-  register const char *p = ptr;
-  register const char *end = p + len;
-  register unsigned char c;
-  register size_t hash = 0;
-
-  while (p != end)
-    {
-      c = *p++;
-      if (c >= 0140) c -= 40;
-      hash = (hash << 3) + (hash >> (CHAR_BIT * sizeof hash - 4)) + c;
-    }
-  return hash;
-}
 \f
 void
 map_obarray (Lisp_Object obarray, void (*fn) (Lisp_Object, Lisp_Object), Lisp_Object arg)