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
|
// Copyright 2017 Yahoo Holdings. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
package com.yahoo.language.process;
import com.yahoo.language.simple.SimpleLinguistics;
import org.junit.Test;
import java.util.Iterator;
import static org.hamcrest.CoreMatchers.is;
import static org.junit.Assert.*;
/**
* @author bratseth
*/
public class GramSplitterTestCase {
private static final GramSplitter gramSplitter = new SimpleLinguistics().getGramSplitter();
@Test
public void testNoSpaces() {
// no spaces
assertGramSplit("engulbillesang", 1, "[e, n, g, u, l, b, i, l, l, e, s, a, n, g]");
assertGramSplit("engulbillesang", 2, "[en, ng, gu, ul, lb, bi, il, ll, le, es, sa, an, ng]");
assertGramSplit("engulbillesang", 3, "[eng, ngu, gul, ulb, lbi, bil, ill, lle, les, esa, san, ang]");
}
@Test
public void testWithSpaces() {
// with spaces
assertGramSplit("en gul bille sang", 1, "[e, n, g, u, l, b, i, l, l, e, s, a, n, g]");
assertGramSplit("en gul bille sang", 2, "[en, gu, ul, bi, il, ll, le, sa, an, ng]");
assertGramSplit("en gul bille sang", 3, "[en, gul, bil, ill, lle, san, ang]");
}
@Test
public void testCornerCases() {
// corner cases
assertGramSplit("", 1, "[]");
assertGramSplit("", 2, "[]");
assertGramSplit("e", 1, "[e]");
assertGramSplit("e", 2, "[e]");
assertGramSplit("en", 1, "[e, n]");
assertGramSplit("en", 2, "[en]");
assertGramSplit("en", 3, "[en]");
}
@Test
public void testSpaceCornerCases() {
// space corner cases
assertGramSplit("e en e", 1, "[e, e, n, e]");
assertGramSplit("e en e", 2, "[e, en, e]");
assertGramSplit("e en e", 3, "[e, en, e]");
assertGramSplit(" e en e ", 1, "[e, e, n, e]");
assertGramSplit(" e en e ", 2, "[e, en, e]");
assertGramSplit(" e en e ", 3, "[e, en, e]");
assertGramSplit(" e en e ", 1, "[e, e, n, e]");
assertGramSplit(" e en e ", 2, "[e, en, e]");
assertGramSplit(" e en e ", 3, "[e, en, e]");
assertGramSplit("a b c", 4, "[a, b, c]");
}
@Test
public void testWithCasing() {
assertGramSplit("This is the Black Eyed Peas", 2,
"[Th, hi, is, is, th, he, Bl, la, ac, ck, Ey, ye, ed, Pe, ea, as]");
assertGramSplit("This is the Black Eyed Peas", 3,
"[Thi, his, is, the, Bla, lac, ack, Eye, yed, Pea, eas]");
assertGramSplit("This is the Black Eyed Peas", 4,
"[This, is, the, Blac, lack, Eyed, Peas]");
assertGramSplit("This is the Black Eyed Peas", 5,
"[This, is, the, Black, Eyed, Peas]");
assertGramSplit("This is the Black Eyed Peas", 6,
"[This, is, the, Black, Eyed, Peas]");
}
@Test
public void testWithPunctuation() {
assertGramSplit("this is, in a sense, more than the sum of parts!", 2,
"[th, hi, is, is, in, a, se, en, ns, se, mo, or, re, th, ha, an, th, he, su, um, of, pa, ar, rt, ts]");
assertGramSplit("this is, in a sense, more than the sum of parts!", 3,
"[thi, his, is, in, a, sen, ens, nse, mor, ore, tha, han, the, sum, of, par, art, rts]");
assertGramSplit("this is, in a sense, more than the sum of parts!", 4,
"[this, is, in, a, sens, ense, more, than, the, sum, of, part, arts]");
assertGramSplit("this is, in a sense, more than the sum of parts!", 5,
"[this, is, in, a, sense, more, than, the, sum, of, parts]");
assertGramSplit("this is, in a sense, more than the sum of parts!", 6,
"[this, is, in, a, sense, more, than, the, sum, of, parts]");
}
@Test
public void testAccents() {
assertGramSplit("caf\u00e9 de l'h\u00f4tel", 2, "[ca, af, f\u00e9, de, l, h\u00f4, \u00f4t, te, el]");
assertGramSplit("caf\u00e9 de l'h\u00f4tel", 3, "[caf, af\u00e9, de, l, h\u00f4t, \u00f4te, tel]");
assertGramSplit("caf\u00e9 de l'h\u00f4tel", 4, "[caf\u00e9, de, l, h\u00f4te, \u00f4tel]");
assertGramSplit("caf\u00e9 de l'h\u00f4tel", 5, "[caf\u00e9, de, l, h\u00f4tel]");
assertGramSplit("caf\u00e9 de l'h\u00f4tel", 6, "[caf\u00e9, de, l, h\u00f4tel]");
}
@Test
public void testChinese() {
String input = "\u77f3\u5ba4\u8a69\u58eb\u65bd\u6c0f\uff0c\u55dc\u7345\uff0c\u8a93\u98df\u5341\u7345\u3002" +
"\u65bd\u6c0f\u6642\u6642\u9069\u5e02\u8996\u7345\uff0c\u5341\u6642\uff0c\u9069\u5341\u7345" +
"\u9069\u5e02\u3002";
assertGramSplit(input, 2, "[\u77f3\u5ba4, \u5ba4\u8a69, \u8a69\u58eb, \u58eb\u65bd, \u65bd\u6c0f, " +
"\u55dc\u7345, \u8a93\u98df, \u98df\u5341, \u5341\u7345, \u65bd\u6c0f, " +
"\u6c0f\u6642, \u6642\u6642, \u6642\u9069, \u9069\u5e02, \u5e02\u8996, " +
"\u8996\u7345, \u5341\u6642, \u9069\u5341, \u5341\u7345, \u7345\u9069, " +
"\u9069\u5e02]");
assertGramSplit(input, 3, "[\u77f3\u5ba4\u8a69, \u5ba4\u8a69\u58eb, \u8a69\u58eb\u65bd, \u58eb\u65bd\u6c0f, " +
"\u55dc\u7345, \u8a93\u98df\u5341, \u98df\u5341\u7345, \u65bd\u6c0f\u6642, " +
"\u6c0f\u6642\u6642, \u6642\u6642\u9069, \u6642\u9069\u5e02, \u9069\u5e02\u8996, " +
"\u5e02\u8996\u7345, \u5341\u6642, \u9069\u5341\u7345, \u5341\u7345\u9069, " +
"\u7345\u9069\u5e02]");
}
@Test(expected = IllegalArgumentException.class)
public void testInvalidSplitSize() {
gramSplitter.split("en", 0);
}
@Test(expected = NullPointerException.class)
public void testInvalidSplitNull() {
gramSplitter.split(null, 1);
}
@Test
public void testUnusualIteratorUse() {
String text = "en gul bille sang";
Iterator<GramSplitter.Gram> grams = gramSplitter.split(text, 3);
assertThat(grams.next().extractFrom(text), is("en"));
assertTrue(grams.hasNext());
assertTrue(grams.hasNext());
assertThat(grams.next().extractFrom(text), is("gul"));
assertThat(grams.next().extractFrom(text), is("bil"));
assertThat(grams.next().extractFrom(text), is("ill"));
assertThat(grams.next().extractFrom(text), is("lle"));
assertTrue(grams.hasNext());
assertTrue(grams.hasNext());
assertThat(grams.next().extractFrom(text), is("san"));
assertThat(grams.next().extractFrom(text), is("ang"));
assertFalse(grams.hasNext());
assertFalse(grams.hasNext());
}
private void assertGramSplit(String input, int gramSize, String expected) {
assertThat(gramSplitter.split(input, gramSize).toExtractedList().toString(), is(expected));
}
}
|
