xapian-core/languages/stem.cc

   1 /** @file
   2  *  @brief Implementation of Xapian::Stem API class.
   3  */
   4 /* Copyright (C) 2007,2008,2010,2011,2012,2015,2018,2019,2024 Olly Betts
   5  * Copyright (C) 2010 Evgeny Sizikov
   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., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA
  20  */
  21
  22 #include <config.h>
  23
  24 #include <xapian/stem.h>
  25
  26 #include <xapian/error.h>
  27
  28 #include "steminternal.h"
  29
  30 #include "allsnowballheaders.h"
  31 #include "keyword.h"
  32 #include "sbl-dispatch.h"
  33
  34 #include <string>
  35 #include <string_view>
  36
  37 using namespace std;
  38
  39 namespace Xapian {
  40
  41 Stem::Stem(std::string_view language, bool fallback)
  42 {
  43     int l = keyword2(tab, language.data(), language.size());
  44     if (l >= 0) {
  45         switch (static_cast<sbl_code>(l)) {
  46             case ARABIC:
  47                 internal = new InternalStemArabic;
  48                 return;
  49             case ARMENIAN:
  50                 internal = new InternalStemArmenian;
  51                 return;
  52             case BASQUE:
  53                 internal = new InternalStemBasque;
  54                 return;
  55             case CATALAN:
  56                 internal = new InternalStemCatalan;
  57                 return;
  58             case DANISH:
  59                 internal = new InternalStemDanish;
  60                 return;
  61             case DUTCH:
  62                 internal = new InternalStemDutch;
  63                 return;
  64             case EARLYENGLISH:
  65                 internal = new InternalStemEarlyenglish;
  66                 return;
  67             case ENGLISH:
  68                 internal = new InternalStemEnglish;
  69                 return;
  70             case FINNISH:
  71                 internal = new InternalStemFinnish;
  72                 return;
  73             case FRENCH:
  74                 internal = new InternalStemFrench;
  75                 return;
  76             case GERMAN:
  77                 internal = new InternalStemGerman;
  78                 return;
  79             case GERMAN2:
  80                 internal = new InternalStemGerman2;
  81                 return;
  82             case HUNGARIAN:
  83                 internal = new InternalStemHungarian;
  84                 return;
  85             case INDONESIAN:
  86                 internal = new InternalStemIndonesian;
  87                 return;
  88             case IRISH:
  89                 internal = new InternalStemIrish;
  90                 return;
  91             case ITALIAN:
  92                 internal = new InternalStemItalian;
  93                 return;
  94             case KRAAIJ_POHLMANN:
  95                 internal = new InternalStemKraaij_pohlmann;
  96                 return;
  97             case LITHUANIAN:
  98                 internal = new InternalStemLithuanian;
  99                 return;
 100             case LOVINS:
 101                 internal = new InternalStemLovins;
 102                 return;
 103             case NEPALI:
 104                 internal = new InternalStemNepali;
 105                 return;
 106             case NORWEGIAN:
 107                 internal = new InternalStemNorwegian;
 108                 return;
 109             case NONE:
 110                 return;
 111             case PORTUGUESE:
 112                 internal = new InternalStemPortuguese;
 113                 return;
 114             case PORTER:
 115                 internal = new InternalStemPorter;
 116                 return;
 117             case RUSSIAN:
 118                 internal = new InternalStemRussian;
 119                 return;
 120             case ROMANIAN:
 121                 internal = new InternalStemRomanian;
 122                 return;
 123             case SPANISH:
 124                 internal = new InternalStemSpanish;
 125                 return;
 126             case SWEDISH:
 127                 internal = new InternalStemSwedish;
 128                 return;
 129             case TAMIL:
 130                 internal = new InternalStemTamil;
 131                 return;
 132             case TURKISH:
 133                 internal = new InternalStemTurkish;
 134                 return;
 135         }
 136     }
 137     if (fallback || language.empty())
 138         return;
 139
 140     string m{"Language code "};
 141     m += language;
 142     m += " unknown";
 143     throw Xapian::InvalidArgumentError(m);
 144 }
 145
 146 string
 147 Stem::operator()(const std::string &word) const
 148 {
 149     if (!internal || word.empty()) return word;
 150     return internal->operator()(word);
 151 }
 152
 153 string
 154 Stem::get_description() const
 155 {
 156     string desc = "Xapian::Stem(";
 157     if (internal) {
 158         desc += internal->get_description();
 159         desc += ')';
 160     } else {
 161         desc += "none)";
 162     }
 163     return desc;
 164 }
 165
 166 }