gqsort.c

   1 /* GLIB - Library of useful routines for C programming
   2  * Copyright (C) 1991, 1992, 1996, 1997 Free Software Foundation, Inc.
   3  * Copyright (C) 2000 Eazel, Inc.
   4  * Copyright (C) 1995-1997  Peter Mattis, Spencer Kimball and Josh MacDonald
   5  *
   6  * This library is free software; you can redistribute it and/or
   7  * modify it under the terms of the GNU Lesser General Public
   8  * License as published by the Free Software Foundation; either
   9  * version 2 of the License, or (at your option) any later version.
  10  *
  11  * This library is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14  * Lesser General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU Lesser General Public
  17  * License along with this library; if not, write to the
  18  * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  19  * Boston, MA 02111-1307, USA.
  20  */
  21
  22 /*
  23  * This file was originally part of the GNU C Library, and was modified to allow
  24  * user data to be passed in to the sorting function.
  25  *
  26  * Written by Douglas C. Schmidt (schmidt@ics.uci.edu).
  27  * Modified by Maciej Stachowiak (mjs@eazel.com)
  28  *
  29  * Modified by the GLib Team and others 1997-2000.  See the AUTHORS
  30  * file for a list of people on the GLib Team.  See the ChangeLog
  31  * files for a list of changes.  These files are distributed with
  32  * GLib at ftp://ftp.gtk.org/pub/gtk/.  */
  33
  34 #include <string.h>
  35
  36 #include "glib.h"
  37
  38 /* Byte-wise swap two items of size SIZE. */
  39 #define SWAP(a, b, size)                                                      \
  40   do                                                                          \
  41     {                                                                         \
  42       register size_t __size = (size);                                        \
  43       register char *__a = (a), *__b = (b);                                   \
  44       do                                                                      \
  45         {                                                                     \
  46           char __tmp = *__a;                                                  \
  47           *__a++ = *__b;                                                      \
  48           *__b++ = __tmp;                                                     \
  49         } while (--__size > 0);                                               \
  50     } while (0)
  51
  52 /* Discontinue quicksort algorithm when partition gets below this size.
  53    This particular magic number was chosen to work best on a Sun 4/260. */
  54 #define MAX_THRESH 4
  55
  56 /* Stack node declarations used to store unfulfilled partition obligations. */
  57 typedef struct
  58 {
  59   char *lo;
  60   char *hi;
  61 }
  62 stack_node;
  63
  64 /* The next 4 #defines implement a very fast in-line stack abstraction. */
  65 #define STACK_SIZE      (8 * sizeof(unsigned long int))
  66 #define PUSH(low, high) ((void) ((top->lo = (low)), (top->hi = (high)), ++top))
  67 #define POP(low, high)  ((void) (--top, (low = top->lo), (high = top->hi)))
  68 #define STACK_NOT_EMPTY (stack < top)
  69
  70
  71 /* Order size using quicksort.  This implementation incorporates
  72  * four optimizations discussed in Sedgewick:
  73  *
  74  * 1. Non-recursive, using an explicit stack of pointer that store the next
  75  *    array partition to sort.  To save time, this maximum amount of space
  76  *    required to store an array of MAX_INT is allocated on the stack.  Assuming
  77  *    a 32-bit integer, this needs only 32 * sizeof(stack_node) == 136 bits.
  78  *    Pretty cheap, actually.
  79  *
  80  * 2. Chose the pivot element using a median-of-three decision tree.  This
  81  *    reduces the probability of selecting a bad pivot value and eliminates
  82  *    certain * extraneous comparisons.
  83  *
  84  * 3. Only quicksorts TOTAL_ELEMS / MAX_THRESH partitions, leaving insertion
  85  *    sort to order the MAX_THRESH items within each partition.  This is a big
  86  *    win, since insertion sort is faster for small, mostly sorted array
  87  *    segments.
  88  *
  89  * 4. The larger of the two sub-partitions is always pushed onto the stack
  90  *    first, with the algorithm then concentrating on the smaller partition.
  91  *    This *guarantees* no more than log (n) stack size is needed (actually O(1)
  92  *    in this case)!
  93  */
  94
  95 void
  96 g_qsort_with_data (gconstpointer    pbase,
  97                    gint             total_elems,
  98                    size_t           size,
  99                    GCompareDataFunc compare_func,
 100                    gpointer         user_data)
 101 {
 102   register char *base_ptr = (char *) pbase;
 103
 104   /* Allocating SIZE bytes for a pivot buffer facilitates a better
 105    * algorithm below since we can do comparisons directly on the pivot.
 106    */
 107   char *pivot_buffer = (char *) alloca (size);
 108   const size_t max_thresh = MAX_THRESH * size;
 109
 110   g_return_if_fail (total_elems > 0);
 111   g_return_if_fail (pbase != NULL);
 112   g_return_if_fail (compare_func != NULL);
 113
 114   if (total_elems > MAX_THRESH)
 115     {
 116       char *lo = base_ptr;
 117       char *hi = &lo[size * (total_elems - 1)];
 118       /* Largest size needed for 32-bit int!!! */
 119       stack_node stack[STACK_SIZE];
 120       stack_node *top = stack + 1;
 121
 122       while (STACK_NOT_EMPTY)
 123         {
 124           char *left_ptr;
 125           char *right_ptr;
 126
 127           char *pivot = pivot_buffer;
 128
 129           /* Select median value from among LO, MID, and HI. Rearrange
 130            * LO and HI so the three values are sorted. This lowers the
 131            * probability of picking a pathological pivot value and
 132            * skips a comparison for both the LEFT_PTR and RIGHT_PTR. */
 133
 134           char *mid = lo + size * ((hi - lo) / size >> 1);
 135
 136           if ((*compare_func) ((void *) mid, (void *) lo, user_data) < 0)
 137             SWAP (mid, lo, size);
 138           if ((*compare_func) ((void *) hi, (void *) mid, user_data) < 0)
 139             SWAP (mid, hi, size);
 140           else
 141             goto jump_over;
 142           if ((*compare_func) ((void *) mid, (void *) lo, user_data) < 0)
 143             SWAP (mid, lo, size);
 144         jump_over:;
 145           memcpy (pivot, mid, size);
 146           pivot = pivot_buffer;
 147
 148           left_ptr = lo + size;
 149           right_ptr = hi - size;
 150
 151           /* Here's the famous ``collapse the walls'' section of quicksort.
 152            * Gotta like those tight inner loops!  They are the main reason
 153            * that this algorithm runs much faster than others. */
 154           do
 155             {
 156               while ((*compare_func)
 157                      ((void *) left_ptr, (void *) pivot,
 158                       user_data) < 0)
 159                 left_ptr += size;
 160
 161               while ((*compare_func)
 162                      ((void *) pivot, (void *) right_ptr,
 163                       user_data) < 0)
 164                 right_ptr -= size;
 165
 166               if (left_ptr < right_ptr)
 167                 {
 168                   SWAP (left_ptr, right_ptr, size);
 169                   left_ptr += size;
 170                   right_ptr -= size;
 171                 }
 172               else if (left_ptr == right_ptr)
 173                 {
 174                   left_ptr += size;
 175                   right_ptr -= size;
 176                   break;
 177                 }
 178             }
 179           while (left_ptr <= right_ptr);
 180
 181           /* Set up pointers for next iteration.  First determine whether
 182            * left and right partitions are below the threshold size.  If so,
 183            * ignore one or both.  Otherwise, push the larger partition's
 184            * bounds on the stack and continue sorting the smaller one. */
 185
 186           if ((size_t) (right_ptr - lo) <= max_thresh)
 187             {
 188               if ((size_t) (hi - left_ptr) <= max_thresh)
 189                 /* Ignore both small partitions. */
 190                 POP (lo, hi);
 191               else
 192                 /* Ignore small left partition. */
 193                 lo = left_ptr;
 194             }
 195           else if ((size_t) (hi - left_ptr) <= max_thresh)
 196                                 /* Ignore small right partition. */
 197             hi = right_ptr;
 198           else if ((right_ptr - lo) > (hi - left_ptr))
 199             {
 200                                 /* Push larger left partition indices. */
 201               PUSH (lo, right_ptr);
 202               lo = left_ptr;
 203
 204             }
 205           else
 206             {
 207                                 /* Push larger right partition indices. */
 208               PUSH (left_ptr, hi);
 209               hi = right_ptr;
 210             }
 211         }
 212     }
 213
 214   /* Once the BASE_PTR array is partially sorted by quicksort the rest
 215    * is completely sorted using insertion sort, since this is efficient
 216    * for partitions below MAX_THRESH size. BASE_PTR points to the beginning
 217    * of the array to sort, and END_PTR points at the very last element in
 218    * the array (*not* one beyond it!). */
 219
 220   {
 221     char *const end_ptr = &base_ptr[size * (total_elems - 1)];
 222     char *tmp_ptr = base_ptr;
 223     char *thresh = MIN (end_ptr, base_ptr + max_thresh);
 224     register char *run_ptr;
 225
 226     /* Find smallest element in first threshold and place it at the
 227      * array's beginning.  This is the smallest array element,
 228      * and the operation speeds up insertion sort's inner loop. */
 229
 230     for (run_ptr = tmp_ptr + size; run_ptr <= thresh;
 231          run_ptr +=
 232            size) if ((*compare_func) ((void *) run_ptr, (void *) tmp_ptr,
 233                                       user_data) < 0)
 234              tmp_ptr = run_ptr;
 235
 236     if (tmp_ptr != base_ptr)
 237       SWAP (tmp_ptr, base_ptr, size);
 238
 239     /* Insertion sort, running from left-hand-side up to right-hand-side.  */
 240
 241     run_ptr = base_ptr + size;
 242     while ((run_ptr += size) <= end_ptr)
 243       {
 244         tmp_ptr = run_ptr - size;
 245         while ((*compare_func)
 246                ((void *) run_ptr, (void *) tmp_ptr,
 247                 user_data) < 0)
 248           tmp_ptr -= size;
 249
 250         tmp_ptr += size;
 251         if (tmp_ptr != run_ptr)
 252           {
 253             char *trav;
 254
 255             trav = run_ptr + size;
 256             while (--trav >= run_ptr)
 257               {
 258                 char c = *trav;
 259                 char *hi, *lo;
 260
 261                 for (hi = lo = trav;
 262                      (lo -= size) >= tmp_ptr; hi = lo)
 263                   *hi = *lo;
 264                 *hi = c;
 265               }
 266           }
 267       }
 268   }
 269 }