1 | /**************************************************************************
|
---|
2 | *
|
---|
3 | * weights.c -- Functions for reading the weights file in mgquery
|
---|
4 | * Copyright (C) 1994 Neil Sharman
|
---|
5 | *
|
---|
6 | * This program is free software; you can redistribute it and/or modify
|
---|
7 | * it under the terms of the GNU General Public License as published by
|
---|
8 | * the Free Software Foundation; either version 2 of the License, or
|
---|
9 | * (at your option) any later version.
|
---|
10 | *
|
---|
11 | * This program 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
|
---|
14 | * GNU General Public License for more details.
|
---|
15 | *
|
---|
16 | * You should have received a copy of the GNU General Public License
|
---|
17 | * along with this program; if not, write to the Free Software
|
---|
18 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
19 | *
|
---|
20 | * $Id: weights.c 3745 2003-02-20 21:20:24Z mdewsnip $
|
---|
21 | *
|
---|
22 | **************************************************************************/
|
---|
23 |
|
---|
24 | #include "sysfuncs.h"
|
---|
25 |
|
---|
26 | #include "filestats.h"
|
---|
27 | #include "memlib.h"
|
---|
28 | #include "messages.h"
|
---|
29 | #include "timing.h"
|
---|
30 | #include "netorder.h" /* [RPAP - Jan 97: Endian Ordering] */
|
---|
31 |
|
---|
32 | #include "mg.h"
|
---|
33 | #include "invf.h"
|
---|
34 | #include "text.h"
|
---|
35 | #include "lists.h"
|
---|
36 | #include "backend.h"
|
---|
37 | #include "weights.h"
|
---|
38 | #include "locallib.h"
|
---|
39 | #include "mg_errors.h"
|
---|
40 |
|
---|
41 | #define MAXBITS (sizeof(unsigned long) * 8)
|
---|
42 |
|
---|
43 | /*
|
---|
44 | $Log$
|
---|
45 | Revision 1.1 2003/02/20 21:18:24 mdewsnip
|
---|
46 | Addition of MG package for search and retrieval
|
---|
47 |
|
---|
48 | Revision 1.1 1999/08/10 21:18:27 sjboddie
|
---|
49 | renamed mg-1.3d directory mg
|
---|
50 |
|
---|
51 | Revision 1.1 1998/11/17 09:35:51 rjmcnab
|
---|
52 | *** empty log message ***
|
---|
53 |
|
---|
54 | * Revision 1.2 1994/09/20 04:42:18 tes
|
---|
55 | * For version 1.1
|
---|
56 | *
|
---|
57 | */
|
---|
58 |
|
---|
59 | static char *RCSID = "$Id: weights.c 3745 2003-02-20 21:20:24Z mdewsnip $";
|
---|
60 |
|
---|
61 |
|
---|
62 |
|
---|
63 | approx_weights_data *
|
---|
64 | LoadDocWeights (File * weight_file,
|
---|
65 | unsigned long num_of_docs)
|
---|
66 | {
|
---|
67 | approx_weights_data *awd;
|
---|
68 | int num;
|
---|
69 |
|
---|
70 | if (!(awd = Xmalloc (sizeof (*awd))))
|
---|
71 | {
|
---|
72 | mg_errno = MG_NOMEM;
|
---|
73 | return (NULL);
|
---|
74 | }
|
---|
75 |
|
---|
76 | Fseek (weight_file, sizeof (long), 0);
|
---|
77 | Fread (&awd->bits, sizeof (awd->bits), 1, weight_file);
|
---|
78 | Fread (&awd->L, sizeof (awd->L), 1, weight_file);
|
---|
79 | NTOHD(awd->L); /* [RPAP - Jan 97: Endian Ordering] */
|
---|
80 | Fread (&awd->B, sizeof (awd->B), 1, weight_file);
|
---|
81 | NTOHD(awd->B); /* [RPAP - Jan 97: Endian Ordering] */
|
---|
82 |
|
---|
83 | awd->mask = awd->bits == 32 ? 0xffffffff : (1 << awd->bits) - 1;
|
---|
84 |
|
---|
85 | num = (num_of_docs * awd->bits + 31) / 32;
|
---|
86 | if (!(awd->DocWeights = Xmalloc (sizeof (unsigned long) * num)))
|
---|
87 | {
|
---|
88 | Xfree (awd);
|
---|
89 | mg_errno = MG_NOMEM;
|
---|
90 | return (NULL);
|
---|
91 | }
|
---|
92 |
|
---|
93 | Fread (awd->DocWeights, sizeof (unsigned long), num, weight_file);
|
---|
94 | {
|
---|
95 | /* [RPAP - Jan 97: Endian Ordering] */
|
---|
96 | unsigned long i;
|
---|
97 | for (i = 0; i < num; i++)
|
---|
98 | NTOHUL(awd->DocWeights[i]);
|
---|
99 | }
|
---|
100 |
|
---|
101 | awd->MemForWeights = num * sizeof (unsigned long);
|
---|
102 | awd->num_of_docs = num_of_docs;
|
---|
103 |
|
---|
104 | mg_errno = MG_NOERROR;
|
---|
105 |
|
---|
106 | if (awd->bits <= 12)
|
---|
107 | {
|
---|
108 | int i, size = (1 << awd->bits);
|
---|
109 | if (!(awd->table = (float *) Xmalloc (size * sizeof (float))))
|
---|
110 | return (awd);
|
---|
111 | awd->table[0] = awd->L;
|
---|
112 | for (i = 1; i < size; i++)
|
---|
113 | awd->table[i] = awd->table[i - 1] * awd->B;
|
---|
114 | }
|
---|
115 | else
|
---|
116 | awd->table = NULL;
|
---|
117 | return awd;
|
---|
118 | }
|
---|
119 |
|
---|
120 |
|
---|
121 |
|
---|
122 |
|
---|
123 |
|
---|
124 |
|
---|
125 | /*
|
---|
126 | * the first document in the collection has DocNum = 0
|
---|
127 | */
|
---|
128 | float
|
---|
129 | GetLowerApproxDocWeight (approx_weights_data * awd, register int DocNum)
|
---|
130 | {
|
---|
131 | register unsigned long c, Pos;
|
---|
132 | register unsigned long *dw;
|
---|
133 | if (awd == NULL)
|
---|
134 | return 1.0;
|
---|
135 | #if 0
|
---|
136 | if (DocNum < 0 || DocNum >= awd->num_of_docs)
|
---|
137 | FatalError (1, "Something is wrong in \"GetDocWeight\" DocNum = %d\n",
|
---|
138 | DocNum);
|
---|
139 | #endif
|
---|
140 | Pos = DocNum * awd->bits;
|
---|
141 | dw = &(awd->DocWeights[Pos / MAXBITS]);
|
---|
142 | Pos &= (MAXBITS - 1);
|
---|
143 | c = *dw >> Pos;
|
---|
144 | if (Pos + awd->bits > MAXBITS)
|
---|
145 | c |= *(dw + 1) << (MAXBITS - Pos);
|
---|
146 | c &= awd->mask;
|
---|
147 | if (awd->table)
|
---|
148 | return (awd->table[c]);
|
---|
149 | else
|
---|
150 | return (awd->L * pow (awd->B, (double) c));
|
---|
151 |
|
---|
152 | }
|
---|
153 |
|
---|
154 | void
|
---|
155 | FreeWeights (approx_weights_data * awd)
|
---|
156 | {
|
---|
157 | Xfree (awd->DocWeights);
|
---|
158 | if (awd->table)
|
---|
159 | Xfree (awd->table);
|
---|
160 | Xfree (awd);
|
---|
161 | }
|
---|