indexinglanguage/src/main/java/com/yahoo/vespa/indexinglanguage/expressions/TokenizeExpression.java


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

// Copyright Vespa.ai. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
package com.yahoo.vespa.indexinglanguage.expressions;

import com.yahoo.document.DataType;
import com.yahoo.document.datatypes.StringFieldValue;
import com.yahoo.language.Language;
import com.yahoo.language.Linguistics;
import com.yahoo.language.process.StemMode;
import com.yahoo.vespa.indexinglanguage.linguistics.AnnotatorConfig;
import com.yahoo.vespa.indexinglanguage.linguistics.LinguisticsAnnotator;

/**
 * @author Simon Thoresen Hult
 */
public final class TokenizeExpression extends Expression {

    private final Linguistics linguistics;
    private final AnnotatorConfig config;

    public TokenizeExpression(Linguistics linguistics, AnnotatorConfig config) {
        super(DataType.STRING);
        this.linguistics = linguistics;
        this.config = config;
    }

    public Linguistics getLinguistics() {
        return linguistics;
    }

    public AnnotatorConfig getConfig() {
        return config;
    }

    @Override
    protected void doExecute(ExecutionContext context) {
        StringFieldValue input = (StringFieldValue)context.getValue();
        StringFieldValue output = input.clone();
        context.setValue(output);

        AnnotatorConfig cfg = new AnnotatorConfig(config);
        Language lang = context.resolveLanguage(linguistics);
        if (lang != null) {
            cfg.setLanguage(lang);
        }
        LinguisticsAnnotator annotator = new LinguisticsAnnotator(linguistics, cfg);
        annotator.annotate(output);
    }

    @Override
    protected void doVerify(VerificationContext context) {
        // empty
    }

    @Override
    public DataType createdOutputType() {
        return null;
    }

    @Override
    public String toString() {
        StringBuilder ret = new StringBuilder();
        ret.append("tokenize");
        if (config.getRemoveAccents()) {
            ret.append(" normalize");
        }
        if (config.getStemMode() != StemMode.NONE) {
            ret.append(" stem:\""+config.getStemMode()+"\"");
        }
        if (config.hasNonDefaultMaxTokenizeLength()) {
            ret.append(" max-length:" + config.getMaxTokenizeLength());
        }
        if (config.hasNonDefaultMaxTokenLength()) {
            ret.append(" max-token-length:" + config.getMaxTokenLength());
        }
        if (config.hasNonDefaultMaxTermOccurrences()) {
            ret.append(" max-occurrences:" + config.getMaxTermOccurrences());
        }
        return ret.toString();
    }

    @Override
    public boolean equals(Object obj) {
        if (!(obj instanceof TokenizeExpression rhs)) return false;
        if (!config.equals(rhs.config)) return false;
        return true;
    }

    @Override
    public int hashCode() {
        return getClass().hashCode() + config.hashCode();
    }

}