[3365] | 1 | /**************************************************************************
|
---|
| 2 | *
|
---|
| 3 | * Weights.cpp -- Dealing with document weights
|
---|
| 4 | * Copyright (C) 1999 Rodger McNab
|
---|
| 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 | **************************************************************************/
|
---|
| 21 |
|
---|
| 22 | #include "UCArray.h"
|
---|
| 23 | #include "Weights.h"
|
---|
| 24 | #include "sysfuncs.h"
|
---|
| 25 |
|
---|
| 26 | #define MAXBITS (sizeof(unsigned long) * 8)
|
---|
| 27 |
|
---|
| 28 |
|
---|
| 29 | ApproxWeightsData::ApproxWeightsData () {
|
---|
| 30 | weightBuf = NULL;
|
---|
| 31 | table = NULL;
|
---|
| 32 | Free();
|
---|
| 33 | }
|
---|
| 34 |
|
---|
| 35 | ApproxWeightsData::~ApproxWeightsData () {
|
---|
| 36 | Free ();
|
---|
| 37 | }
|
---|
| 38 |
|
---|
| 39 | void ApproxWeightsData::Free () {
|
---|
| 40 | bits = 0;
|
---|
| 41 | mask = 0;
|
---|
| 42 | L = 0.0;
|
---|
| 43 | B = 0.0;
|
---|
| 44 | numLevelDocs = 0;
|
---|
| 45 | if (weightBuf != NULL) {
|
---|
| 46 | delete [] weightBuf;
|
---|
| 47 | weightBuf = NULL;
|
---|
| 48 | }
|
---|
| 49 | if (table != NULL) {
|
---|
| 50 | delete [] table;
|
---|
| 51 | table = NULL;
|
---|
| 52 | }
|
---|
| 53 | }
|
---|
| 54 |
|
---|
| 55 | bool ApproxWeightsData::Read (FILE *approxWeightsFile, unsigned long diskPtr,
|
---|
| 56 | unsigned long _numLevelDocs) {
|
---|
| 57 | Free ();
|
---|
| 58 |
|
---|
| 59 | // go to the appropriate place in the weights file
|
---|
| 60 | fseek (approxWeightsFile, diskPtr, SEEK_SET);
|
---|
| 61 |
|
---|
| 62 | // read in approx weights parameters
|
---|
| 63 | ReadUC (approxWeightsFile, bits);
|
---|
| 64 | ReadD (approxWeightsFile, L);
|
---|
| 65 | ReadD (approxWeightsFile, B);
|
---|
| 66 |
|
---|
| 67 | mask = (bits == 32) ? 0xffffffff : (1 << bits) - 1;
|
---|
| 68 | numLevelDocs = _numLevelDocs;
|
---|
| 69 |
|
---|
| 70 | // allocate buffer for the weights
|
---|
| 71 | unsigned long arrSize = (bits*numLevelDocs+sizeof(unsigned long)-1) / 32;
|
---|
| 72 | weightBuf = new unsigned long[arrSize];
|
---|
| 73 |
|
---|
| 74 | // read in the weights
|
---|
| 75 | unsigned long i;
|
---|
[9613] | 76 | for (i=0; i<arrSize; ++i) {
|
---|
[3365] | 77 | ReadUL (approxWeightsFile, weightBuf[i]);
|
---|
| 78 | }
|
---|
| 79 |
|
---|
| 80 | // create precomputed table of values if it will be small enough
|
---|
| 81 | // (if not small enough table == NULL
|
---|
| 82 | if (bits <= 12) {
|
---|
| 83 | unsigned long i, tableSize = (1 << bits);
|
---|
| 84 | table = new float[tableSize];
|
---|
| 85 | table[0] = L;
|
---|
[9613] | 86 | for (i = 1; i < tableSize; ++i)
|
---|
[3365] | 87 | table[i] = table[i - 1] * B;
|
---|
| 88 | }
|
---|
| 89 |
|
---|
| 90 | return true;
|
---|
| 91 | }
|
---|
| 92 |
|
---|
| 93 | float ApproxWeightsData::GetLowerApproxDocWeight (unsigned long levelDocNum) {
|
---|
| 94 | // sanity check
|
---|
| 95 | if (bits == 0 || weightBuf == NULL) return 1.0;
|
---|
| 96 |
|
---|
| 97 | register unsigned long c, pos;
|
---|
| 98 | register unsigned long *dw;
|
---|
| 99 |
|
---|
| 100 | // get the compressed version of the weight
|
---|
| 101 | pos = levelDocNum * bits;
|
---|
| 102 | dw = &weightBuf[pos / MAXBITS];
|
---|
| 103 | pos &= (MAXBITS - 1);
|
---|
| 104 | c = *dw >> pos;
|
---|
| 105 | if (pos + bits > MAXBITS)
|
---|
| 106 | c |= *(dw + 1) << (MAXBITS - pos);
|
---|
| 107 | c &= mask;
|
---|
| 108 |
|
---|
| 109 | // decompress the weight
|
---|
| 110 | if (table != NULL) return table[c];
|
---|
| 111 | return (L * pow (B, (double) c));
|
---|
| 112 | }
|
---|
| 113 |
|
---|
| 114 |
|
---|
| 115 |
|
---|
| 116 | float GetExactDocWeight (FILE *exactWeightsFile, unsigned long diskPtr,
|
---|
| 117 | unsigned long levelDocNum) {
|
---|
| 118 | // go to the appropriate place in the weights file
|
---|
| 119 | fseek (exactWeightsFile, diskPtr+sizeof(float)*levelDocNum, SEEK_SET);
|
---|
| 120 |
|
---|
| 121 | // read in the exact weight
|
---|
| 122 | float weight;
|
---|
| 123 | ReadF (exactWeightsFile, weight);
|
---|
| 124 |
|
---|
| 125 | return weight;
|
---|
| 126 | }
|
---|