xapian-core/tests/stemtest.cc

   1 /* stemtest.cc
   2  *
   3  * ----START-LICENCE----
   4  * Copyright 1999,2000,2001 BrightStation PLC
   5  * Copyright 2002 Ananova Ltd
   6  *
   7  * This program is free software; you can redistribute it and/or
   8  * modify it under the terms of the GNU General Public License as
   9  * published by the Free Software Foundation; either version 2 of the
  10  * License, or (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License
  18  * along with this program; if not, write to the Free Software
  19  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
  20  * USA
  21  * -----END-LICENCE-----
  22  */
  23
  24 #include <stdio.h>
  25 #include <ctype.h>
  26 #include <getopt.h>
  27
  28 #include <string>
  29 #include <iostream>
  30
  31 using std::string;
  32 using std::cout;
  33 using std::cerr;
  34 using std::endl;
  35
  36 #include "om/omstem.h"
  37
  38 static void
  39 stemfile(const OmStem &stemmer, FILE * f)
  40 {
  41     while (true) {
  42         int ch = getc(f);
  43         if (ch == EOF) return;
  44         if (isspace(ch)) {
  45             putchar(ch);
  46             continue;
  47         }
  48
  49         std::string word;
  50         while (true) {
  51             word += tolower(ch);
  52
  53             ch = getc(f);
  54             if (ch == EOF) break;
  55             if (isspace(ch)) {
  56                 ungetc(ch, f);
  57                 break;
  58             }
  59         }
  60
  61         cout << stemmer.stem_word(word);
  62     }
  63 }
  64
  65 int main(int argc, char **argv)
  66 {
  67     std::string lang = "english";
  68
  69     struct option opts[] = {
  70         {"language",    required_argument, 0, 'l'},
  71         {NULL,          0, 0, 0}
  72     };
  73
  74     bool syntax_error = false;
  75
  76     int c;
  77     while ((c = getopt_long(argc, argv, "l", opts, NULL)) != EOF) {
  78         if (c == 'l') {
  79             lang = argv[optind];
  80         } else {
  81             syntax_error = true;
  82         }
  83     }
  84
  85     try {
  86         OmStem stemmer(lang);
  87         while (argv[optind]) {
  88             FILE * f = fopen(argv[optind], "r");
  89             if (f == NULL) {
  90                 cerr << "File " << argv[optind] << " not found\n";
  91                 exit(1);
  92             }
  93             stemfile(stemmer, f);
  94             ++optind;
  95         }
  96     } catch (const OmError &e) {
  97         cout << e.get_msg() << endl;
  98         return 1;
  99     }
 100
 101     return 0;
 102 }