vtext 0.2.0

NLP with Rust
Documentation 
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

// Copyright 2019 vtext developers
//
// Licensed under the Apache License, Version 2.0,
// <http://apache.org/licenses/LICENSE-2.0>. This file may not be copied,
// modified, or distributed except according to those terms.

use crate::tokenize::*;

#[test]
fn test_regexp_tokenizer() {
    let s = "fox can't jump 32.3 feet, right?";

    let tokenizer = RegexpTokenizer::default();
    let tokens: Vec<&str> = tokenizer.tokenize(s).collect();
    let b: &[_] = &["fox", "can", "jump", "32", "feet", "right"];
    assert_eq!(tokens, b);
}

#[test]
fn test_regexp_tokenizer_error() {
    let tokenizer = RegexpTokenizerParams::default().pattern("(").build();

    assert!(tokenizer.is_err());
}

#[test]
fn test_unicode_tokenizer() {
    let s = "The quick (\"brown\") fox can't jump 32.3 feet, right?";

    let tokenizer = UnicodeWordTokenizerParams::default()
        .word_bounds(false)
        .build()
        .unwrap();
    let tokens: Vec<&str> = tokenizer.tokenize(s).collect();
    let b: &[_] = &[
        "The", "quick", "brown", "fox", "can't", "jump", "32.3", "feet", "right",
    ];
    assert_eq!(tokens, b);

    let tokenizer = UnicodeWordTokenizer::default();
    let tokens: Vec<&str> = tokenizer.tokenize(s).collect();
    let b: &[_] = &[
        "The", "quick", "(", "\"", "brown", "\"", ")", "fox", "can't", "jump", "32.3", "feet", ",",
        "right", "?",
    ];
    assert_eq!(tokens, b);
}

#[test]
fn test_vtext_tokenizer_all_lang() {
    let tokenizer = VTextTokenizer::default();

    for (s, tokens_ref) in [
        // float numbers
        ("23.2 meters", vec!["23.2", "meters"]),
        ("11,2 m", vec!["11,2", "m"]),
        // repeated punctuation
        ("1 ..", vec!["1", ".."]),
        ("I ...", vec!["I", "..."]),
        (", o ! o", vec![",", "o", "!", "o"]),
        ("... ok.", vec!["...", "ok", "."]),
        // dash separated words
        ("porte-manteau", vec!["porte-manteau"]),
        // emails
        ("name@domain.com", vec!["name@domain.com"]),
        // fractions
        ("1/2", vec!["1/2"]),
        ("and/or", vec!["and", "/", "or"]),
        // time
        ("8:30", vec!["8:30"]),
        ("B&B", vec!["B&B"]),
        // TODO ("Hello :)", vec!["Hello", ":)"])
        // TODO ("http://www.youtube.com/watch?v=q2lDF0XU3NI",
        // vec!["http://www.youtube.com/watch?v=q2lDF0XU3NI"])
    ]
    .iter()
    {
        let tokens: Vec<&str> = tokenizer.tokenize(s).collect();
        assert_eq!(&tokens, tokens_ref);
    }
}

#[test]
fn test_vtext_tokenizer_en() {
    let tokenizer = VTextTokenizer::default();

    for (s, tokens_ref) in [
        ("We can't", vec!["We", "ca", "n't"]),
        ("it's", vec!["it", "'s"]),
        ("it’s", vec!["it", "’s"]),
        // TODO ("N.Y.", vec!["N.Y."])
    ]
    .iter()
    {
        let tokens: Vec<&str> = tokenizer.tokenize(s).collect();
        assert_eq!(&tokens, tokens_ref);
    }
}

#[test]
fn test_vtext_tokenizer_fr() {
    let tokenizer = VTextTokenizerParams::default().lang("fr").build().unwrap();

    for (s, tokens_ref) in [("l'image", vec!["l'", "image"])].iter() {
        let tokens: Vec<&str> = tokenizer.tokenize(s).collect();
        assert_eq!(&tokens, tokens_ref);
    }
}

#[test]
fn test_vtext_tokenizer_invalid_lang() {
    let tokenizer = VTextTokenizerParams::default()
        .lang("unknown")
        .build()
        .unwrap();
    assert_eq!(tokenizer.params.lang, "any");
}

#[test]
fn test_character_tokenizer() {
    let s = "fox can't";

    let tokenizer = CharacterTokenizer::default();
    let tokens: Vec<&str> = tokenizer.tokenize(s).collect();
    let b: &[_] = &["fox ", "ox c", "x ca", " can", "can'", "an't"];
    assert_eq!(tokens, b);
}

#[test]
fn test_tokenizer_defaults() {
    let tokenizer = UnicodeWordTokenizer::default();
    assert_eq!(tokenizer.params.word_bounds, true);
}