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
use super::{CharNormalizer, CharOrStr};
use crate::{Script, Token};
pub struct VietnameseNormalizer;
impl CharNormalizer for VietnameseNormalizer {
fn normalize_char(&self, c: char) -> Option<CharOrStr> {
match c {
'Ð' | 'Đ' | 'đ' | 'ð' => Some("d".to_string().into()), // not only Vietnamese, but also many European countries use these letters
_ => Some(c.into()),
}
}
fn should_normalize(&self, token: &Token) -> bool {
token.script == Script::Latin && token.lemma.chars().any(is_should_normalize)
}
}
fn is_should_normalize(c: char) -> bool {
matches!(c, 'Ð' | 'Đ' | 'đ' | 'ð')
}
#[cfg(test)]
mod test {
use std::borrow::Cow::Owned;
use crate::normalizer::test::test_normalizer;
use crate::normalizer::{Normalizer, NormalizerOption};
use crate::token::TokenKind;
// base tokens to normalize.
fn tokens() -> Vec<Token<'static>> {
vec![
Token {
lemma: Owned("Ðại Việt".to_string()),
char_end: 8,
byte_end: 13,
script: Script::Latin,
..Default::default()
},
Token {
lemma: Owned("Đại Việt".to_string()),
char_end: 8,
byte_end: 13,
script: Script::Latin,
..Default::default()
},
Token {
lemma: Owned("đại Việt".to_string()),
char_end: 8,
byte_end: 13,
script: Script::Latin,
..Default::default()
},
]
}
// expected result of the current Normalizer.
fn normalizer_result() -> Vec<Token<'static>> {
vec![
Token {
lemma: Owned("dại Việt".to_string()),
char_end: 8,
byte_end: 13,
char_map: Some(vec![
(2, 1),
(3, 3),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(3, 3),
(1, 1),
]),
script: Script::Latin,
..Default::default()
},
Token {
lemma: Owned("dại Việt".to_string()),
char_end: 8,
byte_end: 13,
char_map: Some(vec![
(2, 1),
(3, 3),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(3, 3),
(1, 1),
]),
script: Script::Latin,
..Default::default()
},
Token {
lemma: Owned("dại Việt".to_string()),
char_end: 8,
byte_end: 13,
char_map: Some(vec![
(2, 1),
(3, 3),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(3, 3),
(1, 1),
]),
script: Script::Latin,
..Default::default()
},
]
}
// expected result of the complete Normalizer pieline.
fn normalized_tokens() -> Vec<Token<'static>> {
vec![
Token {
kind: TokenKind::Word,
lemma: Owned("dai viet".to_string()),
char_end: 8,
byte_end: 13,
char_map: Some(vec![
(2, 1),
(3, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(3, 1),
(1, 1),
]),
script: Script::Latin,
..Default::default()
},
Token {
kind: TokenKind::Word,
lemma: Owned("dai viet".to_string()),
char_end: 8,
byte_end: 13,
char_map: Some(vec![
(2, 1),
(3, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(3, 1),
(1, 1),
]),
script: Script::Latin,
..Default::default()
},
Token {
kind: TokenKind::Word,
lemma: Owned("dai viet".to_string()),
char_end: 8,
byte_end: 13,
char_map: Some(vec![
(2, 1),
(3, 1),
(1, 1),
(1, 1),
(1, 1),
(1, 1),
(3, 1),
(1, 1),
]),
script: Script::Latin,
..Default::default()
},
]
}
test_normalizer!(VietnameseNormalizer, tokens(), normalizer_result(), normalized_tokens());
}