| 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 13 1998-11-17 09:36:00Z rjmcnab $
|
|---|
| 21 | *
|
|---|
| 22 | **************************************************************************/
|
|---|
| 23 |
|
|---|
| 24 | /*
|
|---|
| 25 | $Log$
|
|---|
| 26 | Revision 1.1 1998/11/17 09:35:44 rjmcnab
|
|---|
| 27 | *** empty log message ***
|
|---|
| 28 |
|
|---|
| 29 | * Revision 1.1 1994/10/20 03:57:08 tes
|
|---|
| 30 | * I have rewritten the boolean query optimiser and abstracted out the
|
|---|
| 31 | * components of the boolean query.
|
|---|
| 32 | *
|
|---|
| 33 | */
|
|---|
| 34 |
|
|---|
| 35 | #ifndef TERM_LISTS_H
|
|---|
| 36 | #define TERM_LISTS_H
|
|---|
| 37 |
|
|---|
| 38 | #include "sysfuncs.h"
|
|---|
| 39 |
|
|---|
| 40 | #define MAXTERMSTRLEN 1023 /* maximum number of characters in term string */
|
|---|
| 41 |
|
|---|
| 42 | typedef struct WordEntry
|
|---|
| 43 | {
|
|---|
| 44 | int word_num; /* Unique number for each different word */
|
|---|
| 45 | u_long count; /* Number of times the word occurs in the text */
|
|---|
| 46 | u_long doc_count; /* Number of documents that contain the word */
|
|---|
| 47 | u_long max_doc_count; /* [RPAP - Jan 97: Stem Index Change] */
|
|---|
| 48 | u_long invf_ptr; /* This is a byte position of the
|
|---|
| 49 | inverted file entry corresponding to the word */
|
|---|
| 50 | u_long invf_len; /* This is the length of the inverted
|
|---|
| 51 | file entry in bytes */
|
|---|
| 52 | }
|
|---|
| 53 | WordEntry;
|
|---|
| 54 |
|
|---|
| 55 | typedef struct TermEntry
|
|---|
| 56 | {
|
|---|
| 57 | WordEntry WE;
|
|---|
| 58 | int Count; /* The number of times the word occurs in the query */
|
|---|
| 59 | u_char *Word; /* The word. */
|
|---|
| 60 | u_char *Stem; /* [RPAP - Jan 97: Stem Index Change] - The stemmed non-cf version of Word */
|
|---|
| 61 | int require_match; /* [RJM 07/97: Ranked Required Terms] 0=optional match, 1=must match */
|
|---|
| 62 | }
|
|---|
| 63 | TermEntry;
|
|---|
| 64 |
|
|---|
| 65 | typedef struct TermList
|
|---|
| 66 | {
|
|---|
| 67 | int list_size;
|
|---|
| 68 | int num;
|
|---|
| 69 | TermEntry TE[1];
|
|---|
| 70 | }
|
|---|
| 71 | TermList;
|
|---|
| 72 |
|
|---|
| 73 | #define GetNthWE(term_list, n) (&((term_list)->TE[(n)].WE))
|
|---|
| 74 |
|
|---|
| 75 | /* --- prototypes --- */
|
|---|
| 76 | void ConvertTermsToString (TermList * query_term_list, char *str);
|
|---|
| 77 | int AddTermEntry (TermList ** query_term_list, TermEntry * te);
|
|---|
| 78 | int AddTerm (TermList ** query_term_list, u_char * Word, int Count, int word_num,
|
|---|
| 79 | u_long count, u_long doc_count, u_long invf_ptr, u_long invf_len); /* [RPAP - Feb 97: Term Frequency] */
|
|---|
| 80 | void ResetTermList (TermList ** tl);
|
|---|
| 81 | void FreeTermList (TermList ** the_tl);
|
|---|
| 82 | void PrintWordEntry (WordEntry * we, FILE * file);
|
|---|
| 83 | void PrintTermEntry (TermEntry * te, FILE * file);
|
|---|
| 84 | void PrintTermList (TermList * tl, FILE * file);
|
|---|
| 85 | TermList *MakeTermList (int n);
|
|---|
| 86 |
|
|---|
| 87 |
|
|---|
| 88 | #endif
|
|---|
