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

use kvariants::KVARIANTS;
use pinyin::ToPinyin;

use super::CharNormalizer;
use crate::detection::{Language, Script};
use crate::normalizer::CharOrStr;
use crate::Token;

mod kvariants;

/// Normalize Chinese characters by:
/// 1. convert Z, Simplified, Semantic, Old, and Wrong variants
/// 2. converting them into Pinyin characters
///
/// This Normalizer uses [`pinyin`] internally to normalize the provided token.
pub struct ChineseNormalizer;

impl CharNormalizer for ChineseNormalizer {
    fn normalize_char(&self, c: char) -> Option<CharOrStr> {
        // Normalize Z, Simplified, Semantic, Old, and Wrong variants
        let kvariant = match KVARIANTS.get(&c) {
            Some(kvariant) => kvariant.destination_ideograph,
            None => c,
        };

        // Normalize to Pinyin
        // If we don't manage to convert the kvariant, we try to convert the original character.
        // If none of them are converted, we return the kvariant.
        match kvariant.to_pinyin().or_else(|| c.to_pinyin()) {
            Some(converted) => {
                let with_tone = converted.with_tone();

                Some(with_tone.to_string().into())
            }
            None => Some(kvariant.into()), // e.g. 杤
        }
    }

    fn should_normalize(&self, token: &Token) -> bool {
        token.script == Script::Cj && matches!(token.language, None | Some(Language::Cmn))
    }
}

#[cfg(test)]
mod test {
    use std::borrow::Cow::Owned;

    use crate::normalizer::test::test_normalizer;
    use crate::normalizer::{Normalizer, NormalizerOption};

    // base tokens to normalize.
    fn tokens() -> Vec<Token<'static>> {
        vec![
            Token {
                lemma: Owned("尊嚴".to_string()),
                char_end: 2,
                byte_end: 6,
                script: Script::Cj,
                language: Some(Language::Cmn),
                ..Default::default()
            },
            Token {
                lemma: Owned("生而自由".to_string()),
                char_end: 4,
                byte_end: 12,
                script: Script::Cj,
                language: Some(Language::Cmn),
                ..Default::default()
            },
            Token {
                lemma: Owned("澚䀾亚㮺刄杤".to_string()),
                char_end: 5,
                byte_end: 15,
                script: Script::Cj,
                language: Some(Language::Cmn),
                ..Default::default()
            },
        ]
    }

    // expected result of the current Normalizer.
    fn normalizer_result() -> Vec<Token<'static>> {
        vec![
            Token {
                // lowercased
                lemma: Owned("zūnyán".to_string()),
                char_end: 2,
                byte_end: 6,
                char_map: Some(vec![(3, 4), (3, 4)]),
                script: Script::Cj,
                language: Some(Language::Cmn),
                ..Default::default()
            },
            Token {
                // lowercased
                lemma: Owned("shēngérzìyóu".to_string()),
                char_end: 4,
                byte_end: 12,
                char_map: Some(vec![(3, 6), (3, 3), (3, 3), (3, 4)]),
                script: Script::Cj,
                language: Some(Language::Cmn),
                ..Default::default()
            },
            Token {
                // It would be "yudǔyàběnrèn" without the kvariant normalization.
                lemma: Owned("àoqìyàběnrènwàn".to_string()),
                char_end: 5,
                byte_end: 15,
                char_map: Some(vec![(3, 3), (3, 3), (3, 3), (3, 4), (3, 4), (3, 4)]),
                script: Script::Cj,
                language: Some(Language::Cmn),
                ..Default::default()
            },
        ]
    }

    // expected result of the complete Normalizer pieline.
    fn normalized_tokens() -> Vec<Token<'static>> {
        vec![
            Token {
                lemma: Owned("zūnyán".to_string()),
                char_end: 2,
                byte_end: 6,
                char_map: Some(vec![(3, 4), (3, 4)]),
                script: Script::Cj,
                language: Some(Language::Cmn),
                ..Default::default()
            },
            Token {
                lemma: Owned("shēngérzìyóu".to_string()),
                char_end: 4,
                byte_end: 12,
                char_map: Some(vec![(3, 6), (3, 3), (3, 3), (3, 4)]),
                script: Script::Cj,
                language: Some(Language::Cmn),
                ..Default::default()
            },
            Token {
                lemma: Owned("àoqìyàběnrènwàn".to_string()),
                char_end: 5,
                byte_end: 15,
                char_map: Some(vec![(3, 3), (3, 3), (3, 3), (3, 4), (3, 4), (3, 4)]),
                script: Script::Cj,
                language: Some(Language::Cmn),
                ..Default::default()
            },
        ]
    }

    test_normalizer!(ChineseNormalizer, tokens(), normalizer_result(), normalized_tokens());
}