instant-segment 0.7.2

Fast English word segmentation
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
134
135
136

use crate::{Search, Segmenter};

/// Run a segmenter against the built-in test cases
pub fn run(segmenter: &Segmenter) {
    let mut search = Search::default();
    for test in TEST_CASES.iter().copied() {
        assert_segments(test, &mut search, segmenter);
    }
    assert_segments(FAIL, &mut search, segmenter);
}

pub fn assert_segments(s: &[&str], search: &mut Search, segmenter: &Segmenter) {
    let words = segmenter.segment(&s.join(""), search).unwrap();
    let cmp = words.collect::<Vec<_>>();
    assert_eq!(cmp, s);
}

pub fn check_segments(s: &[&str], search: &mut Search, segmenter: &Segmenter) -> bool {
    match segmenter.segment(&s.join(""), search) {
        Ok(words) => s == words.collect::<Vec<_>>(),
        Err(_) => false,
    }
}

/// Built-in test cases
///
/// These are exposed so that you can test with different data sources.
pub const TEST_CASES: &[&[&str]] = &[
    &["choose", "spain"],
    &["this", "is", "a", "test"],
    &["who", "represents"],
    &["experts", "exchange"],
    &["speed", "of", "art"],
    &["now", "is", "the", "time", "for", "all", "good"],
    &["it", "is", "a", "truth", "universally", "acknowledged"],
    &[
        "it", "was", "a", "bright", "cold", "day", "in", "april", "and", "the", "clocks", "were",
        "striking", "thirteen",
    ],
    &[
        "when",
        "in",
        "the",
        "course",
        "of",
        "human",
        "events",
        "it",
        "becomes",
        "necessary",
    ],
    &[
        "it",
        "was",
        "the",
        "best",
        "of",
        "times",
        "it",
        "was",
        "the",
        "worst",
        "of",
        "times",
        "it",
        "was",
        "the",
        "age",
        "of",
        "wisdom",
        "it",
        "was",
        "the",
        "age",
        "of",
        "foolishness",
    ],
    &[
        "as",
        "gregor",
        "samsa",
        "awoke",
        "one",
        "morning",
        "from",
        "uneasy",
        "dreams",
        "he",
        "found",
        "himself",
        "transformed",
        "in",
        "his",
        "bed",
        "into",
        "a",
        "gigantic",
        "insect",
    ],
    &[
        "in", "a", "hole", "in", "the", "ground", "there", "lived", "a", "hobbit", "not", "a",
        "nasty", "dirty", "wet", "hole", "filled", "with", "the", "ends", "of", "worms", "and",
        "an", "oozy", "smell", "nor", "yet", "a", "dry", "bare", "sandy", "hole", "with",
        "nothing", "in", "it", "to", "sit", "down", "on", "or", "to", "eat", "it", "was", "a",
        "hobbit", "hole", "and", "that", "means", "comfort",
    ],
];

/// Incorrectly segmented, since the test data doesn't contain "unregarded"
const FAIL: &[&str] = &[
    "far",
    "out",
    "in",
    "the",
    "uncharted",
    "backwaters",
    "of",
    "the",
    "unfashionable",
    "end",
    "of",
    "the",
    "western",
    "spiral",
    "arm",
    "of",
    "the",
    "galaxy",
    "lies",
    "a",
    "small",
    "un",
    "regarded",
    "yellow",
    "sun",
];