charabia 0.9.9

A simple library to detect the language, tokenize the text and normalize the tokens
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
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

use std::sync::LazyLock;

use fst::raw::Fst;

use crate::segmenter::utils::{BufferingStrategy, FstSegmenter};
use crate::segmenter::Segmenter;

/// German specialized [`Segmenter`].
///
/// This Segmenter uses a dictionary encoded as an FST to segment the provided text.
pub struct GermanSegmenter;

static WORDS_FST: LazyLock<Fst<&[u8]>> = LazyLock::new(|| {
    Fst::new(&include_bytes!("../../dictionaries/fst/german/words.fst")[..]).unwrap()
});

static FST_SEGMENTER: LazyLock<FstSegmenter> = LazyLock::new(|| {
    // no max char count, so the segmenter will buffer the sequence until the next match is found
    FstSegmenter::new(&WORDS_FST, BufferingStrategy::UntilNextMatch { max_char_count: None })
});

impl Segmenter for GermanSegmenter {
    fn segment_str<'o>(&self, to_segment: &'o str) -> Box<dyn Iterator<Item = &'o str> + 'o> {
        FST_SEGMENTER.segment_str(to_segment)
    }
}

// Test the segmenter:
#[cfg(test)]
mod test {
    use crate::segmenter::test::test_segmenter;

    const TEXT: &str =
        "Der Dampfschifffahrtskapitän fährt über den Mittellandkanal zur Strombrücke Magdeburg 123 456. Feuchteschutz insgesamt";

    const SEGMENTED: &[&str] = &[
        "Der",
        " ",
        "Dampf",
        "schifffahrts",
        "kapitän",
        " ",
        "fähr",
        "t",
        " ",
        "über",
        " ",
        "den",
        " ",
        "Mittel",
        "land",
        "kanal",
        " ",
        "zur",
        " ",
        "Strom",
        "brücke",
        " ",
        "Magdeburg",
        " ",
        "123",
        " ",
        "456",
        ". ",
        "Feuchte",
        "schutz",
        " ",
        "ins",
        "gesamt",
    ];

    const TOKENIZED: &[&str] = &[
        "der",
        " ",
        "dampf",
        "schifffahrts",
        "kapitan",
        " ",
        "fahr",
        "t",
        " ",
        "uber",
        " ",
        "den",
        " ",
        "mittel",
        "land",
        "kanal",
        " ",
        "zur",
        " ",
        "strom",
        "brucke",
        " ",
        "magdeburg",
        " ",
        "123",
        " ",
        "456",
        ". ",
        "feuchte",
        "schutz",
        " ",
        "ins",
        "gesamt",
    ];

    // Macro that runs several tests on the Segmenter.
    test_segmenter!(GermanSegmenter, TEXT, SEGMENTED, TOKENIZED, Script::Latin, Language::Deu);

    macro_rules! test_segmentation {
        ($text:expr, $segmented:expr, $name:ident) => {
            #[test]
            fn $name() {
                let segmented_text: Vec<_> = FST_SEGMENTER.segment_str($text).collect::<Vec<_>>();
                assert_eq!(segmented_text, $segmented);
            }
        };
    }

    test_segmentation!(
        "Literaturverwaltungsprogramm",
        &["Literatur", "verwaltungs", "programm"],
        word1
    );
    test_segmentation!("Schreibprozess", &["Schreib", "prozess"], word2);
    test_segmentation!("Interkulturalität", &["Inter", "kulturalität"], word3);
    test_segmentation!("Wissensorganisation", &["Wissens", "organisation"], word4);
    test_segmentation!("Aufgabenplanung", &["Aufgaben", "planung"], word5);
    test_segmentation!("Eisbrecher", &["Eis", "brecher"], word6);
    test_segmentation!("Zuckerei", &["Zucker", "ei"], word7);
    test_segmentation!("Glatteis", &["Glatt", "eis"], word8);
    test_segmentation!("Sinnfindung", &["Sinn", "findung"], word9);
    test_segmentation!(
        "Donaudampfschifffahrtsgesellschaftskapitän",
        &["Donau", "dampf", "schifffahrts", "gesellschafts", "kapitän"],
        word10
    );
    test_segmentation!(
        "Rindfleischetikettierungsüberwachungsaufgabenübertragungsgesetz",
        &[
            "Rind",
            "fleisch",
            "etikettierungs",
            "überwachungs",
            "aufgaben",
            "übertragungs",
            "gesetz"
        ],
        word11
    );
    test_segmentation!(
        "Nahrungsmittelunverträglichkeitsdiagnoseverfahren",
        &["Nahrungs", "mittel", "un", "verträglichkeits", "diagnose", "verfahren"],
        word12
    );
    test_segmentation!("Volleyball", &["Volley", "ball"], word13);
    test_segmentation!("Fußball", &["Fuß", "ball"], word14);
    test_segmentation!("Beachvolleyball", &["Beach", "volley", "ball"], word15);
    test_segmentation!("Basketball", &["Basket", "ball"], word16);
    test_segmentation!("Handball", &["Hand", "ball"], word17);
    test_segmentation!("Spikeball", &["Spike", "ball"], word18);
}