1 | /**************************************************************************
|
---|
2 | *
|
---|
3 | * FragLevelConvert.cpp -- converting between fragment and document numbers
|
---|
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 "FragLevelConvert.h"
|
---|
23 | #include "bitio_m_stdio.h"
|
---|
24 | #include "bitio_gen.h"
|
---|
25 |
|
---|
26 |
|
---|
27 | FragLevelConvert::FragLevelConvert () {
|
---|
28 | numFrags = 0;
|
---|
29 | numLevelDocs = 0;
|
---|
30 | }
|
---|
31 |
|
---|
32 | bool FragLevelConvert::Read (FILE *invfFile,
|
---|
33 | unsigned long levelPtr,
|
---|
34 | unsigned long _numFrags,
|
---|
35 | unsigned long _numLevelDocs) {
|
---|
36 | levelStarts.erase (levelStarts.begin(), levelStarts.end());
|
---|
37 | numFrags = _numFrags;
|
---|
38 | numLevelDocs = _numLevelDocs;
|
---|
39 |
|
---|
40 | // seek to the appropriate place in the inverted file
|
---|
41 | fseek (invfFile, levelPtr, SEEK_SET);
|
---|
42 |
|
---|
43 | stdio_bitio_buffer buffer(invfFile);
|
---|
44 |
|
---|
45 | unsigned long pTag = numLevelDocs*2;
|
---|
46 | unsigned long B = BIO_Bblock_Init (numFrags+pTag, pTag);
|
---|
47 | unsigned long fragNum = 0;
|
---|
48 | unsigned long i;
|
---|
49 | for (i=0; i<numLevelDocs; ++i) {
|
---|
50 | unsigned long delta = buffer.bblock_decode (B, NULL)-1;
|
---|
51 | fragNum += delta;
|
---|
52 |
|
---|
53 | levelStarts.push_back (fragNum);
|
---|
54 |
|
---|
55 | // ignore end, assume every fragment is in a level
|
---|
56 | delta = buffer.bblock_decode (B, NULL)-1;
|
---|
57 | fragNum += delta;
|
---|
58 | }
|
---|
59 |
|
---|
60 | // fragNum would be the starting fragment of the next document
|
---|
61 | // if there was one
|
---|
62 | levelStarts.push_back (fragNum);
|
---|
63 |
|
---|
64 | if (fragNum != _numFrags) {
|
---|
65 | cerr << "last frag num:"<<fragNum<<" != num frags:"<<_numFrags<<endl;
|
---|
66 | }
|
---|
67 | buffer.done();
|
---|
68 |
|
---|
69 | return true;
|
---|
70 | }
|
---|
71 |
|
---|
72 | bool FragLevelConvert::FragToLevel (unsigned long fragNum,
|
---|
73 | unsigned long &levelDocNum) const {
|
---|
74 | // do binary search for something containing this fragment number
|
---|
75 | unsigned long low = 1, high = numLevelDocs;
|
---|
76 | unsigned long mid;
|
---|
77 |
|
---|
78 | while ((mid = (low+high)/2) >= 1 && low <= high) {
|
---|
79 | if (fragNum > levelStarts[mid]) low = mid+1;
|
---|
80 | else if (fragNum <= levelStarts[mid-1]) high = mid-1;
|
---|
81 | else {
|
---|
82 | levelDocNum = mid;
|
---|
83 | return true;
|
---|
84 | }
|
---|
85 | }
|
---|
86 | return false;
|
---|
87 | }
|
---|
88 |
|
---|
89 |
|
---|
90 | bool FragLevelConvert::LevelToLevel (FragLevelConvert sectionLevelConvert,
|
---|
91 | unsigned long levelNum, unsigned long &DocNum) {
|
---|
92 |
|
---|
93 | if (levelNum==1) {
|
---|
94 | DocNum=1;
|
---|
95 | return true;
|
---|
96 | }
|
---|
97 | unsigned long levelfragnum = sectionLevelConvert.levelStarts[levelNum-1]+1;
|
---|
98 |
|
---|
99 | if (FragToLevel(levelfragnum, DocNum)) {
|
---|
100 | return true;
|
---|
101 | }
|
---|
102 | return false;
|
---|
103 |
|
---|
104 |
|
---|
105 | }
|
---|