stopword.cc

   1 /* stopword.cc: stop word manipulation routines
   2  *
   3  * ----START-LICENCE----
   4  * Copyright 2003 Andy MacFarlane, City University
   5  *
   6  * This program is free software; you can redistribute it and/or
   7  * modify it under the terms of the GNU General Public License as
   8  * published by the Free Software Foundation; either version 2 of the
   9  * License, or (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., 59 Temple Place, Suite 330, Boston, MA 02111-1307
  19  * USA
  20  * -----END-LICENCE-----
  21  */
  22
  23
  24 #include <stdio.h>
  25 #include <stdlib.h>
  26 #include <string.h>
  27 #include <ctype.h>
  28
  29 #include "stopword.h"
  30
  31 #define LSTRING 80         /* A Long String of characters */
  32 #define TRUE 1             /* a condition is true */
  33 #define FALSE 0            /* a condition is false */
  34 #define IDENTICAL 0        /* two words are equal in strcmp */
  35 #define LATER 1            /* 1 word is lexico.  later than another */
  36 #define EARLIER -1         /* 1 word is lexico.  ealier than another */
  37 #define NL '\n'            /* newline marker */
  38 #define KW_SIZE 80         /* maximum size of a keyword */
  39
  40 void Init_str( char str[], int size ) {
  41   /* initialise a string */
  42
  43   int i;
  44
  45   for(i = 0; i < size; i++)
  46     str[i] = '\0';
  47
  48 } /* END Init_str */
  49
  50 void Read_Extra_SWord( FILE *f_id, char word[KW_SIZE] ) {
  51   /* read a stop word from the extra stop word file*/
  52
  53   int i;
  54   char c;                         /* character read in */
  55
  56   /*initialize word*/
  57   Init_str( word, KW_SIZE );
  58
  59   /* get character from file until  newline or end of file found */
  60   for( i=0; i < KW_SIZE && (c=fgetc(f_id)) != EOF && c != NL; i++ )
  61     word[i] = c;
  62   /* END for */
  63
  64 } /*END Read_Extra_SWord */
  65
  66
  67 void Read_SW_File( char sw_file[], SW_STORE * sw_store ) {
  68   /* read stop word file into  stop word store
  69      version which goes directly to the file, with need for specifiying dir */
  70
  71   FILE *swf_id; /* file id for stopword file */
  72   int i;
  73   char sw_fname[LSTRING];  /* full path and name of sw file */
  74
  75   sw_store->nstops = 0;  /* init just in case! */
  76
  77   strcpy( sw_fname, sw_file );
  78
  79   swf_id = fopen( sw_fname, "r" );      /*open stop word file*/
  80   if( !swf_id )
  81     {
  82       fprintf(stderr,"ERROR - can't open the extra stop word file [%s]\n",sw_fname );
  83       exit( 0 );
  84     } /* END if */
  85
  86   /*read stop words into stop word store*/
  87   for( i=0; i < MAX_STOPWORDS && !feof(swf_id); i++) {
  88     Read_Extra_SWord( swf_id, sw_store->words[i] );
  89     if(!feof(swf_id))
  90       {
  91         sw_store->nstops++;
  92         //fprintf(stderr,"DEBUG) sw(%d) %s\n", i,
  93           // sw_store->words[i] );
  94       } /* END if */
  95   } /*END for*/
  96   //fprintf(stderr,"STOP_WORDS) read in %d stop words\n", sw_store->nstops );
  97
  98   fclose( swf_id );     /*close down stop word file*/
  99
 100 } /* END Read_SW_File */
 101
 102 int IsStopWord( SW_STORE sw_store, char word[KW_SIZE] ) {
 103   /* see if word is a extra stop word / stop integer during iterative search or
 104      relevance feedback process */
 105
 106   int found = FALSE;            /* word found status */
 107   int low = 0;                  /* min position of search */
 108   int high;                     /* max position of search */
 109   int middle;                   /* middle position of current search */
 110   int result;                   /* result of compare between two words */
 111
 112   high = sw_store.nstops;
 113
 114   if( isdigit(word[0]) )
 115     { /* if its a digit don't index it */
 116       found = TRUE;
 117     }
 118   else /* its a word, so compare it with the full stop word list - using binary chop */
 119     {
 120       while( low <= high && !found )
 121         {
 122           middle = (high + low) / 2;
 123
 124           result = strcmp( word, sw_store.words[middle] );
 125                 //fprintf(stderr,"COMPARE) [%s] with sw[%s], RESULT=%d\n", word, sw_store.words[middle], result );
 126           if (result == IDENTICAL)
 127             found = 1;
 128           else if (result >= LATER)
 129             low = middle + 1;
 130           else
 131             high = middle - 1;
 132           /*END if*/
 133         } /*END while*/
 134     } /* END if */
 135   //fprintf(stderr,"RESULT) %d\n", found );
 136
 137   return found; /* result of search */
 138
 139 } /* END IsStopWord */