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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
extern crate wordcut_engine;
use std::path::Path;
use std::io::Result;
use self::wordcut_engine::Dict;
pub type Wordcut = self::wordcut_engine::Wordcut;
pub fn default_path() -> &'static Path {
Path::new(
concat!(env!("CARGO_MANIFEST_DIR"),
"/data/thai.txt"))
}
pub fn lao_path() -> &'static Path {
Path::new(
concat!(env!("CARGO_MANIFEST_DIR"),
"/data/laowords.txt"))
}
pub fn load_dict(path: &Path) -> Result<Dict> {
self::wordcut_engine::load_dict(path)
}
#[cfg(test)]
mod tests {
use std::path::Path;
use super::wordcut_engine::TextRange;
use super::Wordcut;
#[test]
fn test_default_dict() {
let dict = super::load_dict(super::default_path());
assert!(dict.is_ok());
}
#[test]
fn test_segment_into_ranges() {
let dict = super::load_dict(Path::new("data/thai.txt")).unwrap();
let wordcut = Wordcut::new(dict);
let ranges = wordcut.segment("กากกา");
let expected = vec![TextRange{s:0,e:3}, TextRange{s:3,e:5}];
assert_eq!(ranges, expected)
}
#[test]
fn test_segment_into_strings() {
let dict = super::load_dict(Path::new("data/thai.txt"));
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment_into_strings("กากกา");
let expected = vec!["กาก".to_string(), "กา".to_string()];
assert_eq!(words, expected)
}
#[test]
fn test_segment_with_punc() {
let dict = super::load_dict(Path::new("data/thai.txt"));
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment_into_strings("\"ฆกากา\"");
let expected = &vec!["\"", "ฆ", "กา", "กา", "\"",]
.iter()
.map(|&s| s.to_string()).collect::<Vec<String>>()[..];
assert_eq!(words, expected)
}
#[test]
fn test_segment_with_parentheses() {
let dict = super::load_dict(Path::new("data/thai.txt"));
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment_into_strings(&"(ฆกากา)".to_string());
let expected = &vec!["(", "ฆ", "กา", "กา", ")",]
.iter()
.map(|&s| s.to_string()).collect::<Vec<String>>()[..];
assert_eq!(words, expected)
}
#[test]
fn test_segment_with_unicode_quote() {
let dict = super::load_dict(Path::new("data/thai.txt"));
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment_into_strings("“ฆกากา”");
let expected = &vec!["“", "ฆ", "กา", "กา", "”",]
.iter()
.map(|&s| s.to_string()).collect::<Vec<String>>()[..];
assert_eq!(words, expected)
}
#[test]
fn test_segment_unknown_sandwich() {
let dict = super::load_dict(Path::new("data/thai.txt"));
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment_into_strings("ฮฮกาฮฮ");
let expected = &vec!["ฮฮ", "กา", "ฮฮ"]
.iter()
.map(|&s| s.to_string()).collect::<Vec<String>>()[..];
assert_eq!(words, expected)
}
#[test]
fn test_segment_2spaces() {
let dict = super::load_dict(Path::new("data/thai.txt"));
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment_into_strings("กา มา");
let expected = &vec!["กา", " ", "มา"]
.iter()
.map(|&s| s.to_string()).collect::<Vec<String>>()[..];
assert_eq!(words, expected)
}
#[test]
fn test_segment_2spaces_unk() {
let dict = super::load_dict(Path::new("data/thai.txt"));
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment_into_strings("ฮฮ ญญ");
let expected = &vec!["ฮฮ", " ", "ญญ"]
.iter()
.map(|&s| s.to_string()).collect::<Vec<String>>()[..];
assert_eq!(words, expected)
}
#[test]
fn test_one_word() {
let dict = super::load_dict(Path::new("data/thai.txt"));
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment_into_strings("มาตรา");
let expected = &vec!["มาตรา"]
.iter()
.map(|&s| s.to_string()).collect::<Vec<String>>()[..];
assert_eq!(words, expected)
}
#[test]
fn test_from_law() {
let dict = super::load_dict(Path::new("data/thai.txt"));
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment_into_strings("มาตรา 482 ผู้ขายไม่");
let expected = &vec!["มาตรา", " ", "482", " ", "ผู้", "ขาย", "ไม่"]
.iter()
.map(|&s| s.to_string()).collect::<Vec<String>>()[..];
assert_eq!(words, expected)
}
#[test]
fn test_space() {
let dict = super::load_dict(Path::new("data/thai.txt"));
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment("a cat");
let expected = vec![TextRange{s:0,e:1},TextRange{s:1,e:2},TextRange{s:2,e:5}];
assert_eq!(words, expected)
}
#[test]
fn test_lao() {
let dict = super::load_dict(super::lao_path());
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment(&"ພາສາລາວມີ".to_string());
let expected = vec![TextRange{s:0,e:4},TextRange{s:4,e:7},TextRange{s:7,e:9}];
assert_eq!(words, expected)
}
#[test]
fn test_latin() {
let dict = super::load_dict(super::lao_path());
let wordcut = Wordcut::new(dict.unwrap());
let words = wordcut.segment_into_strings(&"ฑฑACญญ".to_string());
let expected = &vec!["ฑฑ", "AC", "ญญ"]
.iter()
.map(|&s| s.to_string()).collect::<Vec<String>>()[..];
assert_eq!(words, expected)
}
}