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

#![cfg_attr(feature = "cargo-clippy", allow(clippy::new_without_default))]

use super::{Token, TokenFilter, TokenStream};
use rust_stemmers::{self, Algorithm};

/// Available stemmer languages.
#[derive(Debug, Serialize, Deserialize, Eq, PartialEq, Copy, Clone)]
#[allow(missing_docs)]
pub enum Language {
    Arabic,
    Danish,
    Dutch,
    English,
    Finnish,
    French,
    German,
    Greek,
    Hungarian,
    Italian,
    Portuguese,
    Romanian,
    Russian,
    Spanish,
    Swedish,
    Tamil,
    Turkish,
}

impl Language {
    fn algorithm(self) -> Algorithm {
        use self::Language::*;
        match self {
            Arabic => Algorithm::Arabic,
            Danish => Algorithm::Danish,
            Dutch => Algorithm::Dutch,
            English => Algorithm::English,
            Finnish => Algorithm::Finnish,
            French => Algorithm::French,
            German => Algorithm::German,
            Greek => Algorithm::Greek,
            Hungarian => Algorithm::Hungarian,
            Italian => Algorithm::Italian,
            Portuguese => Algorithm::Portuguese,
            Romanian => Algorithm::Romanian,
            Russian => Algorithm::Russian,
            Spanish => Algorithm::Spanish,
            Swedish => Algorithm::Swedish,
            Tamil => Algorithm::Tamil,
            Turkish => Algorithm::Turkish,
        }
    }
}

/// `Stemmer` token filter. Several languages are supported, see `Language` for the available
/// languages.
/// Tokens are expected to be lowercased beforehand.
#[derive(Clone)]
pub struct Stemmer {
    stemmer_algorithm: Algorithm,
}

impl Stemmer {
    /// Creates a new Stemmer `TokenFilter` for a given language algorithm.
    pub fn new(language: Language) -> Stemmer {
        Stemmer {
            stemmer_algorithm: language.algorithm(),
        }
    }
}

impl Default for Stemmer {
    /// Creates a new Stemmer `TokenFilter` for English.
    fn default() -> Self {
        Stemmer::new(Language::English)
    }
}

impl<TailTokenStream> TokenFilter<TailTokenStream> for Stemmer
where
    TailTokenStream: TokenStream,
{
    type ResultTokenStream = StemmerTokenStream<TailTokenStream>;

    fn transform(&self, token_stream: TailTokenStream) -> Self::ResultTokenStream {
        let inner_stemmer = rust_stemmers::Stemmer::create(self.stemmer_algorithm);
        StemmerTokenStream::wrap(inner_stemmer, token_stream)
    }
}

pub struct StemmerTokenStream<TailTokenStream>
where
    TailTokenStream: TokenStream,
{
    tail: TailTokenStream,
    stemmer: rust_stemmers::Stemmer,
}

impl<TailTokenStream> TokenStream for StemmerTokenStream<TailTokenStream>
where
    TailTokenStream: TokenStream,
{
    fn token(&self) -> &Token {
        self.tail.token()
    }

    fn token_mut(&mut self) -> &mut Token {
        self.tail.token_mut()
    }

    fn advance(&mut self) -> bool {
        if !self.tail.advance() {
            return false;
        }
        // TODO remove allocation
        let stemmed_str: String = self.stemmer.stem(&self.token().text).into_owned();
        self.token_mut().text.clear();
        self.token_mut().text.push_str(&stemmed_str);
        true
    }
}

impl<TailTokenStream> StemmerTokenStream<TailTokenStream>
where
    TailTokenStream: TokenStream,
{
    fn wrap(
        stemmer: rust_stemmers::Stemmer,
        tail: TailTokenStream,
    ) -> StemmerTokenStream<TailTokenStream> {
        StemmerTokenStream { tail, stemmer }
    }
}