| 1 | /**********************************************************************
|
|---|
| 2 | *
|
|---|
| 3 | * suffix.h -- definitions used in suffix.cpp
|
|---|
| 4 | *
|
|---|
| 5 | * Copyright 2000 Gordon W. Paynter
|
|---|
| 6 | * Copyright 2000 The New Zealand Digital Library Project
|
|---|
| 7 | *
|
|---|
| 8 | * A component of the Greenstone digital library software
|
|---|
| 9 | * from the New Zealand Digital Library Project at the
|
|---|
| 10 | * University of Waikato, New Zealand.
|
|---|
| 11 | *
|
|---|
| 12 | * This program is free software; you can redistribute it and/or modify
|
|---|
| 13 | * it under the terms of the GNU General Public License as published by
|
|---|
| 14 | * the Free Software Foundation; either version 2 of the License, or
|
|---|
| 15 | * (at your option) any later version.
|
|---|
| 16 | *
|
|---|
| 17 | * This program is distributed in the hope that it will be useful,
|
|---|
| 18 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|---|
| 19 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|---|
| 20 | * GNU General Public License for more details.
|
|---|
| 21 | *
|
|---|
| 22 | * You should have received a copy of the GNU General Public License
|
|---|
| 23 | * along with this program; if not, write to the Free Software
|
|---|
| 24 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|---|
| 25 | *
|
|---|
| 26 | *********************************************************************/
|
|---|
| 27 |
|
|---|
| 28 |
|
|---|
| 29 | // Types
|
|---|
| 30 |
|
|---|
| 31 | // The input words stored as an array of type symbol.
|
|---|
| 32 | // Required range: 0 - vocabulary size (typically hundreds of thousands)
|
|---|
| 33 | typedef unsigned int symbol;
|
|---|
| 34 |
|
|---|
| 35 | // The cellindex and cellcount types are used when we store indexes
|
|---|
| 36 | // to and ranges of cells in large arrays.
|
|---|
| 37 | // Required Range: 0 - length of input (typically millions)
|
|---|
| 38 | typedef unsigned int cellindex;
|
|---|
| 39 | typedef unsigned int cellcount;
|
|---|
| 40 |
|
|---|
| 41 | // The frequency type is used when we want to store the frequency with
|
|---|
| 42 | // which a phrase (or some other thing) occurs
|
|---|
| 43 | // Required range: 0 - frequency of most common symbol (often "the")
|
|---|
| 44 | typedef unsigned int frequency;
|
|---|
| 45 |
|
|---|
| 46 | // The check type is used when we want to store low frequency values.
|
|---|
| 47 | // Required range: 0 - 8 (could be recoded to use booleans)
|
|---|
| 48 | typedef unsigned char check;
|
|---|
| 49 |
|
|---|
| 50 |
|
|---|
| 51 | // Global variables
|
|---|
| 52 |
|
|---|
| 53 | // The symbol array holds the input words
|
|---|
| 54 | extern cellcount symbol_array_length;
|
|---|
| 55 | extern symbol *symbols;
|
|---|
| 56 |
|
|---|
| 57 | // The number of words read is storesd in inputLength.
|
|---|
| 58 | extern cellcount inputLength;
|
|---|
| 59 |
|
|---|
| 60 | // Suffix and prefix arrays are used to extract phrases
|
|---|
| 61 | extern symbol **suffixArray;
|
|---|
| 62 | extern check *suffixCheck;
|
|---|
| 63 | extern symbol **prefixArray;
|
|---|
| 64 | extern check *prefixCheck;
|
|---|
| 65 |
|
|---|
| 66 | // Collection-specific information about the first stopword/content symbols
|
|---|
| 67 | extern symbol firstStopSymbol;
|
|---|
| 68 | extern symbol lastStopSymbol;
|
|---|
| 69 | extern symbol firstContentSymbol;
|
|---|
| 70 | extern symbol lastContentSymbol;
|
|---|
| 71 |
|
|---|
| 72 |
|
|---|
| 73 | // Are we allowed to terminate a phrase on a stopword?
|
|---|
| 74 | extern int phraseMode;
|
|---|
| 75 |
|
|---|
| 76 | #define ANYPHRASE 0
|
|---|
| 77 | #define STOPWORDS 1
|
|---|
| 78 |
|
|---|
| 79 |
|
|---|
| 80 | // Direction values
|
|---|
| 81 | #define SUFFIX 0
|
|---|
| 82 | #define PREFIX 1
|
|---|
| 83 |
|
|---|
| 84 |
|
|---|
| 85 | // Special symbol values
|
|---|
| 86 | #define COLLECTIONSTART 1
|
|---|
| 87 | #define COLLECTIONEND 2
|
|---|
| 88 | #define DOCUMENTSTART 3
|
|---|
| 89 | #define PHRASELIMIT 4
|
|---|
| 90 |
|
|---|
| 91 | #define LASTDELIMITER 4
|
|---|
| 92 |
|
|---|
| 93 |
|
|---|
| 94 |
|
|---|
