~jpakkane/libcolumbus/hud-rework

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
/*
 * Copyright (C) 2012 Canonical, Ltd.
 *
 * Authors:
 *    Jussi Pakkanen <jussi.pakkanen@canonical.com>
 *
 * This library is free software; you can redistribute it and/or modify it under
 * the terms of version 3 of the GNU Lesser General Public License as published
 * by the Free Software Foundation.
 *
 * This library is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
 * FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more
 * details.
 *
 * You should have received a copy of the GNU Lesser General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

/*
 * This file tests the trie portion of the Levenshtein index.
 * That is, exact matches.
 */

#include <cstdio>
#include <cassert>
#include "LevenshteinIndex.hh"
#include "Word.hh"

using namespace Columbus;

void basicTest() {
    LevenshteinIndex ind;
    Word word1("word");
    Word word2("another");
    WordID w1ID = 1;
    WordID w2ID = 2;

    assert(!ind.hasWord(word1));
    assert(!ind.hasWord(word2));

    ind.insertWord(word1, w1ID);
    assert(ind.hasWord(word1));
    assert(!ind.hasWord(word2));

    ind.insertWord(word2, w2ID);
    assert(ind.hasWord(word1));
    assert(ind.hasWord(word2));
}

void shortTest() {
    LevenshteinIndex ind;
    Word word("a");

    assert(!ind.hasWord(word));

    ind.insertWord(word, 1);
    assert(ind.hasWord(word));
}

void prefixTest() {
    LevenshteinIndex ind;
    Word word("ab");
    Word prefix("a");

    assert(!ind.hasWord(word));
    assert(!ind.hasWord(prefix));

    ind.insertWord(word, 1);
    assert(ind.hasWord(word));
    assert(!ind.hasWord(prefix));

    ind.insertWord(prefix, 2);
    assert(ind.hasWord(word));
    assert(ind.hasWord(prefix));
}

void suffixTest() {
    LevenshteinIndex ind;
    Word word("abc");
    Word word2("abcd");

    assert(!ind.hasWord(word));
    assert(!ind.hasWord(word2));

    ind.insertWord(word, 1);
    assert(ind.hasWord(word));
    assert(!ind.hasWord(word2));

    ind.insertWord(word2, 2);
    assert(ind.hasWord(word));
    assert(ind.hasWord(word2));
}

void branchTest() {
    LevenshteinIndex ind;
    Word word("abc");
    Word word2("abcd");
    Word word3("abce");

    assert(!ind.hasWord(word));
    assert(!ind.hasWord(word2));
    assert(!ind.hasWord(word3));

    ind.insertWord(word, 1);
    assert(ind.hasWord(word));
    assert(!ind.hasWord(word2));
    assert(!ind.hasWord(word3));

    ind.insertWord(word2, 2);
    assert(ind.hasWord(word));
    assert(ind.hasWord(word2));
    assert(!ind.hasWord(word3));

    ind.insertWord(word3, 3);
    assert(ind.hasWord(word));
    assert(ind.hasWord(word2));
    assert(ind.hasWord(word3));
}

void countTest() {
    LevenshteinIndex ind;
    Word w1("abc");
    Word w2("def");
    Word w3("abce");
    WordID w1ID = 1;
    WordID w2ID = 2;
    WordID w3ID = 3;

    assert(ind.wordCount(w1ID) == 0);
    assert(ind.wordCount(w2ID) == 0);
    assert(ind.wordCount(w3ID) == 0);
    assert(ind.maxCount() == 0);
    assert(ind.numWords() == 0);

    ind.insertWord(w1, w1ID);
    assert(ind.wordCount(w1ID) == 1);
    assert(ind.wordCount(w2ID) == 0);
    assert(ind.wordCount(w3ID) == 0);
    assert(ind.maxCount() == 1);
    assert(ind.numWords() == 1);

    ind.insertWord(w2, w2ID);
    assert(ind.wordCount(w1ID) == 1);
    assert(ind.wordCount(w2ID) == 1);
    assert(ind.wordCount(w3ID) == 0);
    assert(ind.maxCount() == 1);
    assert(ind.numWords() == 2);

    ind.insertWord(w1, w1ID);
    assert(ind.wordCount(w1ID) == 2);
    assert(ind.wordCount(w2ID) == 1);
    assert(ind.wordCount(w3ID) == 0);
    assert(ind.maxCount() == 2);
    assert(ind.numWords() == 2);
}

int main(int /*argc*/, char **/*argv*/) {
#ifdef NDEBUG
    fprintf(stderr, "NDEBUG is defined, tests will not work!\n");
    return 1;
#else
    try {
        basicTest();
        shortTest();
        prefixTest();
        suffixTest();
        branchTest();
        countTest();
    } catch(const std::exception &e) {
        fprintf(stderr, "Fail: %s\n", e.what());
        return 666;
    }
    return 0;
#endif
}