[655] | 1 | /**************************************************************************
|
---|
| 2 | *
|
---|
| 3 | * term_lists.h -- description
|
---|
| 4 | * Copyright (C) 1994 Authors
|
---|
| 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: term_lists.h 655 1999-10-11 02:58:42Z cs025 $
|
---|
| 21 | *
|
---|
| 22 | **************************************************************************/
|
---|
| 23 |
|
---|
| 24 | /*
|
---|
| 25 | $Log$
|
---|
| 26 | Revision 1.1 1999/10/11 02:58:36 cs025
|
---|
| 27 | Base install of MG-PP
|
---|
| 28 |
|
---|
| 29 | Revision 1.1 1999/08/10 21:18:24 sjboddie
|
---|
| 30 | renamed mg-1.3d directory mg
|
---|
| 31 |
|
---|
| 32 | Revision 1.2 1998/11/25 07:55:52 rjmcnab
|
---|
| 33 |
|
---|
| 34 | Modified mg to that you can specify the stemmer you want
|
---|
| 35 | to use via a command line option. You specify it to
|
---|
| 36 | mg_passes during the build process. The number of the
|
---|
| 37 | stemmer that you used is stored within the inverted
|
---|
| 38 | dictionary header and the stemmed dictionary header so
|
---|
| 39 | the correct stemmer is used in later stages of building
|
---|
| 40 | and querying.
|
---|
| 41 |
|
---|
| 42 | Revision 1.1 1998/11/17 09:35:44 rjmcnab
|
---|
| 43 | *** empty log message ***
|
---|
| 44 |
|
---|
| 45 | * Revision 1.1 1994/10/20 03:57:08 tes
|
---|
| 46 | * I have rewritten the boolean query optimiser and abstracted out the
|
---|
| 47 | * components of the boolean query.
|
---|
| 48 | *
|
---|
| 49 | */
|
---|
| 50 |
|
---|
| 51 | #ifndef TERM_LISTS_H
|
---|
| 52 | #define TERM_LISTS_H
|
---|
| 53 |
|
---|
| 54 | #include "sysfuncs.h"
|
---|
| 55 |
|
---|
| 56 | #define MAXTERMSTRLEN 1023 /* maximum number of characters in term string */
|
---|
| 57 |
|
---|
| 58 | typedef struct WordEntry
|
---|
| 59 | {
|
---|
| 60 | int word_num; /* Unique number for each different word */
|
---|
| 61 | u_long count; /* Number of times the word occurs in the text */
|
---|
| 62 | u_long doc_count; /* Number of documents that contain the word */
|
---|
| 63 | u_long max_doc_count; /* [RPAP - Jan 97: Stem Index Change] */
|
---|
| 64 | u_long invf_ptr; /* This is a byte position of the
|
---|
| 65 | inverted file entry corresponding to the word */
|
---|
| 66 | u_long invf_len; /* This is the length of the inverted
|
---|
| 67 | file entry in bytes */
|
---|
| 68 | }
|
---|
| 69 | WordEntry;
|
---|
| 70 |
|
---|
| 71 | typedef struct TermEntry
|
---|
| 72 | {
|
---|
| 73 | WordEntry WE;
|
---|
| 74 | int Count; /* The number of times the word occurs in the query */
|
---|
| 75 | u_char *Word; /* The word. */
|
---|
| 76 | u_char *Stem; /* [RPAP - Jan 97: Stem Index Change] - The stemmed non-cf version of Word */
|
---|
| 77 | int require_match; /* [RJM 07/97: Ranked Required Terms] 0=optional match, 1=must match */
|
---|
| 78 |
|
---|
| 79 | inline int wordLength()
|
---|
| 80 | {
|
---|
| 81 | return Word[0];
|
---|
| 82 | }
|
---|
| 83 |
|
---|
| 84 | inline unsigned char *word()
|
---|
| 85 | {
|
---|
| 86 | return Word + 1;
|
---|
| 87 | }
|
---|
| 88 | }
|
---|
| 89 | TermEntry;
|
---|
| 90 |
|
---|
| 91 | typedef struct TermList
|
---|
| 92 | {
|
---|
| 93 | int list_size;
|
---|
| 94 | int num;
|
---|
| 95 | TermEntry *TE;
|
---|
| 96 |
|
---|
| 97 | inline TermEntry *entry(int term)
|
---|
| 98 | { return &TE[term];
|
---|
| 99 | }
|
---|
| 100 |
|
---|
| 101 | inline int size()
|
---|
| 102 | {
|
---|
| 103 | return num;
|
---|
| 104 | }
|
---|
| 105 | }
|
---|
| 106 | TermList;
|
---|
| 107 |
|
---|
| 108 | #define GetNthWE(term_list, n) (&((term_list)->TE[(n)].WE))
|
---|
| 109 |
|
---|
| 110 | /* --- prototypes --- */
|
---|
| 111 | void TermList_toString (TermList * query_term_list, char *str);
|
---|
| 112 | int TermList_AddTermEntry (TermList * query_term_list, TermEntry * te);
|
---|
| 113 | int TermList_AddTerm (TermList * query_term_list, u_char * Word, int Count, int word_num,
|
---|
| 114 | u_long count, u_long doc_count, u_long invf_ptr, u_long invf_len, /* [RPAP - Feb 97: Term Frequency] */
|
---|
| 115 | int stemmer_num);
|
---|
| 116 | #ifdef __cplusplus
|
---|
| 117 | extern "C"
|
---|
| 118 | #endif
|
---|
| 119 | void TermList_reset(TermList **tl);
|
---|
| 120 | void TermList_destroy (TermList ** the_tl);
|
---|
| 121 | void TermList_print (TermList * tl, FILE * file);
|
---|
| 122 | TermList *TermList_create (int n);
|
---|
| 123 |
|
---|
| 124 | #ifdef __cplusplus
|
---|
| 125 | inline int TermList_size(TermList *tl)
|
---|
| 126 | { return tl->num;
|
---|
| 127 | }
|
---|
| 128 | #endif
|
---|
| 129 |
|
---|
| 130 | #endif
|
---|