blob: d0a640edf2ba7dc750d7cb4835e382a81c58d20c (
plain)
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
|
use super::Language;
use crate::pipeline::{Pipeline, PipelineFn};
use regex::Regex;
/// Arabic Language
///
/// Designed to be compatibile with the included Javascript implementation. See `js/lunr.ar.js`.
pub struct Arabic {}
impl Arabic {
pub fn new() -> Self {
Self {}
}
}
impl Language for Arabic {
fn name(&self) -> String {
"Arabic".into()
}
fn code(&self) -> String {
"ar".into()
}
fn tokenize(&self, text: &str) -> Vec<String> {
super::tokenize_whitespace(text)
}
fn make_pipeline(&self) -> Pipeline {
Pipeline {
queue: vec![Box::new(Stemmer::new())],
}
}
}
struct Stemmer {
diacritics: Regex,
alefs: Regex,
}
impl Stemmer {
pub fn new() -> Self {
let diacritics = Regex::new("[\u{0640}\u{064b}-\u{065b}]").unwrap();
let alefs = Regex::new("[\u{0622}\u{0623}\u{0625}\u{0671}\u{0649}]").unwrap();
Self { diacritics, alefs }
}
}
impl PipelineFn for Stemmer {
fn name(&self) -> String {
"stemmer-ar".into()
}
fn filter(&self, token: String) -> Option<String> {
// remove diacritics and elongating character
let result = self.diacritics.replace(&token, "");
// replace all variations of alef (آأإٱى) to a plain alef (ا)
let result = self.alefs.replace(&result, "\u{0627}");
if result.is_empty() {
None
} else if result == token {
Some(token)
} else {
Some(result.into())
}
}
}
|
