ik-rs 0.1.0

chinese segment, ik-analyzer for 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

use crate::core::char_util::char_type_of;
use crate::core::char_util::CharType;
use crate::core::char_util::utf8_len;
use crate::core::lexeme::{Lexeme, LexemeType};
use crate::core::segmentor::Segmenter;
use crate::dict::dictionary::GLOBAL_DICT;

const SEGMENTER_NAME: &str = "CJK_SEGMENTER";

// 中文-日韩文子分词器
#[derive(Debug)]
pub struct CJKSegmenter {}

impl Segmenter for CJKSegmenter {
    fn analyze(&mut self, input: &str) -> Vec<Lexeme> {
        let mut new_lexemes: Vec<Lexeme> = Vec::new();
        let char_count = utf8_len(input);
        for cursor in 0..char_count {
            let curr_char = input.chars().nth(cursor).unwrap();
            let curr_char_type = char_type_of(curr_char);
            if CharType::USELESS != curr_char_type {
                let hit_options = GLOBAL_DICT.lock().unwrap().match_in_main_dict_with_offset(
                    input,
                    cursor,
                    char_count - cursor,
                );
                for hit in hit_options.iter() {
                    if hit.is_match() {
                        //输出当前的词
                        let new_lexeme =
                            Lexeme::new(0, hit.begin, hit.end - hit.begin + 1, LexemeType::CNWORD);
                        new_lexemes.push(new_lexeme);
                    }
                }
            }
        }
        new_lexemes
    }

    fn name(&self) -> &str {
        return SEGMENTER_NAME;
    }
}

impl CJKSegmenter {
    pub fn new() -> Self {
        CJKSegmenter {}
    }
}