blob: 5b332d63f3f1074c456f674476899832be1af2b7 (
plain) (
blame)
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
|
// Copyright 2016 Yahoo Inc. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
package com.yahoo.language.process;
import com.yahoo.language.Language;
/**
* Language-sensitive tokenization of a text string.
*
* @author Mathias Mølster Lidal
*/
public interface Tokenizer {
/**
* Returns the tokens produced from an input string under the rules of the given Language and additional options
*
* @param input the string to tokenize. May be arbitrarily large.
* @param language the language of the input string.
* @param stemMode the stem mode applied on the returned tokens
* @param removeAccents if true accents and similar are removed from the returned tokens
* @return the tokens of the input String.
* @throws ProcessingException If the underlying library throws an Exception.
*/
Iterable<Token> tokenize(String input, Language language, StemMode stemMode, boolean removeAccents);
/**
* Return a replacement for an input token string.
* This accepts strings returned by Token.getTokenString
* and returns a replacement which will be used as the index token.
* The input token string is returned if there is no replacement.
* <p>
* This default implementation always returns the input token string.
*
* @param tokenString the token string of the term to lookup a replacement for
* @return the replacement, if any, or the argument token string if not
*/
default String getReplacementTerm(String tokenString) { return tokenString; }
}
|