xapian-core/tests/api_stem.cc

   1 /** @file api_stem.cc
   2  * @brief Test the stemming API
   3  */
   4 /* Copyright (C) 2010,2012 Olly Betts
   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., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA
  19  */
  20
  21 #include <config.h>
  22
  23 #include "api_stem.h"
  24
  25 #include <xapian.h>
  26
  27 #include "apitest.h"
  28 #include "testsuite.h"
  29 #include "testutils.h"
  30
  31 using namespace std;
  32
  33 class MyStemImpl : public Xapian::StemImplementation {
  34     string operator()(const string & word) {
  35         if (word == "vanish")
  36             return string();
  37         return word.substr(0, 3);
  38     }
  39
  40     string get_description() const {
  41         return "MyStem()";
  42     }
  43 };
  44
  45 /// Test user stemming algorithms.
  46 DEFINE_TESTCASE(stem1, !backend) {
  47     Xapian::Stem st(new MyStemImpl);
  48
  49     TEST_EQUAL(st.get_description(), "Xapian::Stem(MyStem())");
  50     TEST_EQUAL(st("a"), "a");
  51     TEST_EQUAL(st("foo"), "foo");
  52     TEST_EQUAL(st("food"), "foo");
  53
  54     return true;
  55 }
  56
  57 /// New feature in 1.0.21/1.2.1 - "nb" and "nn" select the Norwegian stemmer.
  58 DEFINE_TESTCASE(stem2, !backend) {
  59     Xapian::Stem st_norwegian("norwegian");
  60     TEST_EQUAL(st_norwegian.get_description(),
  61                Xapian::Stem("nb").get_description());
  62     TEST_EQUAL(st_norwegian.get_description(),
  63                Xapian::Stem("nn").get_description());
  64     TEST_EQUAL(st_norwegian.get_description(),
  65                Xapian::Stem("no").get_description());
  66     TEST_NOT_EQUAL(st_norwegian.get_description(),
  67                    Xapian::Stem("en").get_description());
  68     TEST_NOT_EQUAL(st_norwegian.get_description(),
  69                    Xapian::Stem("none").get_description());
  70     return true;
  71 }
  72
  73 /// Test add a stemmer test
  74 DEFINE_TESTCASE(stem3, !backend) {
  75     Xapian::Stem earlyenglish("earlyenglish");
  76     TEST_EQUAL(earlyenglish("loved"), "love");
  77     TEST_EQUAL(earlyenglish("loving"), "love");
  78     TEST_EQUAL(earlyenglish("loveth"), "love");
  79     TEST_EQUAL(earlyenglish("givest"), "give");
  80     return true;
  81 }
  82
  83 /// Test handling of a stemmer returning an empty string.
  84 // Regression test for https://trac.xapian.org/ticket/741 fixed in 1.4.2.
  85 DEFINE_TESTCASE(stemempty1, !backend) {
  86     Xapian::Stem st(new MyStemImpl);
  87
  88     Xapian::TermGenerator tg;
  89     Xapian::Document doc;
  90     tg.set_document(doc);
  91     tg.set_stemmer(st);
  92     tg.set_stemming_strategy(tg.STEM_ALL);
  93
  94     tg.index_text("watch me vanish now");
  95     auto i = doc.termlist_begin();
  96     TEST(i != doc.termlist_end());
  97     TEST_EQUAL(*i, "me");
  98     TEST(++i != doc.termlist_end());
  99     TEST_EQUAL(*i, "now");
 100     TEST(++i != doc.termlist_end());
 101     TEST_EQUAL(*i, "wat");
 102     TEST(++i == doc.termlist_end());
 103
 104     return true;
 105 }
 106
 107 /// Test invalid language names with various characters in.
 108 DEFINE_TESTCASE(stemlangs2, !backend) {
 109     string lang("xdummy");
 110     for (unsigned ch = 0; ch <= 255; ++ch) {
 111         lang[0] = ch;
 112         TEST_EXCEPTION(Xapian::InvalidArgumentError, Xapian::Stem stem(lang));
 113     }
 114     return true;
 115 }