Add heapsort
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236
diff --git a/ChangeLog b/ChangeLog
index 0408ecc..8195268 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@
+2006-03-29 Robert Millan <rmh@aybabtu.com>
+
+ * src/heapsort.c: New file.
+ * include/bsd/stdlib.h: Add heapsort declaration.
+ * Makefile (LIB_SRCS): Add heapsort.c.
+ * Versions: Add heapsort.
+
2006-03-19 Robert Millan <rmh@aybabtu.com>
* src/vis.c: New file.
diff --git a/Makefile b/Makefile
index 6a6942f..7887263 100644
--- a/Makefile
+++ b/Makefile
@@ -4,7 +4,7 @@
# $Id$
#
-LIB_SRCS := arc4random.c bsd_getopt.c err.c fgetln.c inet_net_pton.c \
+LIB_SRCS := arc4random.c bsd_getopt.c err.c fgetln.c heapsort.c inet_net_pton.c \
strlcat.c strlcpy.c md5c.c fmtcheck.c progname.c vis.c unvis.c
LIB_SRCS := $(patsubst %,src/%,$(LIB_SRCS))
diff --git a/Versions b/Versions
index 0724ffb..f9012f9 100644
--- a/Versions
+++ b/Versions
@@ -6,6 +6,7 @@ LIBBSD_0.0 {
fgetln;
fgetwln;
fmtcheck;
+ heapsort;
inet_net_pton;
getprogname; setprogname;
strlcpy;
diff --git a/include/bsd/stdlib.h b/include/bsd/stdlib.h
index 25c37e2..659d30e 100644
--- a/include/bsd/stdlib.h
+++ b/include/bsd/stdlib.h
@@ -8,4 +8,6 @@ const char *fmtcheck (const char *, const char *);
char *getprogname ();
void setprogname (char *);
+int heapsort (void *, size_t, size_t, int (*)(const void *, const void *));
+
#endif
diff --git a/src/heapsort.c b/src/heapsort.c
new file mode 100644
index 0000000..881e7cf
--- /dev/null
+++ b/src/heapsort.c
@@ -0,0 +1,179 @@
+/*-
+ * Copyright (c) 1991, 1993
+ * The Regents of the University of California. All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Ronnie Kon at Mindcraft Inc., Kevin Lew and Elmer Yglesias.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ * must display the following acknowledgement:
+ * This product includes software developed by the University of
+ * California, Berkeley and its contributors.
+ * 4. Neither the name of the University nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#include <errno.h>
+#include <stddef.h>
+#include <stdlib.h>
+
+/*
+ * Swap two areas of size number of bytes. Although qsort(3) permits random
+ * blocks of memory to be sorted, sorting pointers is almost certainly the
+ * common case (and, were it not, could easily be made so). Regardless, it
+ * isn't worth optimizing; the SWAP's get sped up by the cache, and pointer
+ * arithmetic gets lost in the time required for comparison function calls.
+ */
+#define SWAP(a, b, count, size, tmp) { \
+ count = size; \
+ do { \
+ tmp = *a; \
+ *a++ = *b; \
+ *b++ = tmp; \
+ } while (--count); \
+}
+
+/* Copy one block of size size to another. */
+#define COPY(a, b, count, size, tmp1, tmp2) { \
+ count = size; \
+ tmp1 = a; \
+ tmp2 = b; \
+ do { \
+ *tmp1++ = *tmp2++; \
+ } while (--count); \
+}
+
+/*
+ * Build the list into a heap, where a heap is defined such that for
+ * the records K1 ... KN, Kj/2 >= Kj for 1 <= j/2 <= j <= N.
+ *
+ * There two cases. If j == nmemb, select largest of Ki and Kj. If
+ * j < nmemb, select largest of Ki, Kj and Kj+1.
+ */
+#define CREATE(initval, nmemb, par_i, child_i, par, child, size, count, tmp) { \
+ for (par_i = initval; (child_i = par_i * 2) <= nmemb; \
+ par_i = child_i) { \
+ child = base + child_i * size; \
+ if (child_i < nmemb && compar(child, child + size) < 0) { \
+ child += size; \
+ ++child_i; \
+ } \
+ par = base + par_i * size; \
+ if (compar(child, par) <= 0) \
+ break; \
+ SWAP(par, child, count, size, tmp); \
+ } \
+}
+
+/*
+ * Select the top of the heap and 'heapify'. Since by far the most expensive
+ * action is the call to the compar function, a considerable optimization
+ * in the average case can be achieved due to the fact that k, the displaced
+ * elememt, is ususally quite small, so it would be preferable to first
+ * heapify, always maintaining the invariant that the larger child is copied
+ * over its parent's record.
+ *
+ * Then, starting from the *bottom* of the heap, finding k's correct place,
+ * again maintianing the invariant. As a result of the invariant no element
+ * is 'lost' when k is assigned its correct place in the heap.
+ *
+ * The time savings from this optimization are on the order of 15-20% for the
+ * average case. See Knuth, Vol. 3, page 158, problem 18.
+ *
+ * XXX Don't break the #define SELECT line, below. Reiser cpp gets upset.
+ */
+#define SELECT(par_i, child_i, nmemb, par, child, size, k, count, tmp1, tmp2) { \
+ for (par_i = 1; (child_i = par_i * 2) <= nmemb; par_i = child_i) { \
+ child = base + child_i * size; \
+ if (child_i < nmemb && compar(child, child + size) < 0) { \
+ child += size; \
+ ++child_i; \
+ } \
+ par = base + par_i * size; \
+ COPY(par, child, count, size, tmp1, tmp2); \
+ } \
+ for (;;) { \
+ child_i = par_i; \
+ par_i = child_i / 2; \
+ child = base + child_i * size; \
+ par = base + par_i * size; \
+ if (child_i == 1 || compar(k, par) < 0) { \
+ COPY(child, k, count, size, tmp1, tmp2); \
+ break; \
+ } \
+ COPY(child, par, count, size, tmp1, tmp2); \
+ } \
+}
+
+/*
+ * Heapsort -- Knuth, Vol. 3, page 145. Runs in O (N lg N), both average
+ * and worst. While heapsort is faster than the worst case of quicksort,
+ * the BSD quicksort does median selection so that the chance of finding
+ * a data set that will trigger the worst case is nonexistent. Heapsort's
+ * only advantage over quicksort is that it requires little additional memory.
+ */
+int
+heapsort(vbase, nmemb, size, compar)
+ void *vbase;
+ size_t nmemb, size;
+ int (*compar)(const void *, const void *);
+{
+ int cnt, i, j, l;
+ char tmp, *tmp1, *tmp2;
+ char *base, *k, *p, *t;
+
+ if (nmemb <= 1)
+ return (0);
+
+ if (!size) {
+ errno = EINVAL;
+ return (-1);
+ }
+
+ if ((k = malloc(size)) == NULL)
+ return (-1);
+
+ /*
+ * Items are numbered from 1 to nmemb, so offset from size bytes
+ * below the starting address.
+ */
+ base = (char *)vbase - size;
+
+ for (l = nmemb / 2 + 1; --l;)
+ CREATE(l, nmemb, i, j, t, p, size, cnt, tmp);
+
+ /*
+ * For each element of the heap, save the largest element into its
+ * final slot, save the displaced element (k), then recreate the
+ * heap.
+ */
+ while (nmemb > 1) {
+ COPY(k, base + nmemb * size, cnt, size, tmp1, tmp2);
+ COPY(base + nmemb * size, base + size, cnt, size, tmp1, tmp2);
+ --nmemb;
+ SELECT(i, j, nmemb, t, p, size, k, cnt, tmp1, tmp2);
+ }
+ free(k);
+ return (0);
+}