split.cc

   1 /* split.cc: split a string routine
   2  *
   3  * ----START-LICENCE----
   4  *
   5  * This program is free software; you can redistribute it and/or
   6  * modify it under the terms of the GNU General Public License as
   7  * published by the Free Software Foundation; either version 2 of the
   8  * License, or (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License
  16  * along with this program; if not, write to the Free Software
  17  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
  18  * USA
  19  * -----END-LICENCE-----
  20  */
  21
  22 #include <fstream>
  23 #include <xapian.h>
  24 #include <algorithm>
  25 #include <iostream>
  26 #include <string>
  27 #include "stopword.h"
  28 #include "split.h"
  29
  30 using namespace Xapian;
  31 using namespace std;
  32
  33 void clear_apos(  string & data ) {
  34 // clear " from data
  35
  36          string temp;
  37
  38          temp.clear();
  39          for( int i=0; i < data.size(); i++ )
  40                                 if( data[i] != '"' && data[i] != '\n')
  41                                                 temp += data[i];
  42
  43          data = temp;
  44
  45 } // END clear_apos
  46
  47 static inline void
  48 lowercase(string & term )
  49 {
  50     string::iterator i = term.begin();
  51     while (i != term.end()) {
  52         *i = tolower(*i);
  53         i++;
  54     }
  55 }
  56
  57 void split( const string &s, char c, vector<string> &res)
  58  {
  59    res.clear();
  60    if(s==""){return;}
  61    uint i;
  62    uint pos=0;
  63    for( i=0; i<=s.size(); i++)
  64      {
  65        if( i == s.size() || s[i] == c )
  66          {
  67            uint j;
  68            string tmps;
  69            for( j=pos; j<i; j++)
  70              {
  71                tmps += s[j];
  72              }
  73                  clear_apos( tmps );
  74                  lowercase( tmps );
  75            res.push_back(tmps);
  76            pos=i+1;
  77          } // END if
  78      } // END for
  79
  80  } // END split