indexinglanguage/src/main/java/com/yahoo/vespa/indexinglanguage/linguistics/AnnotatorConfig.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
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

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

import com.yahoo.language.Language;
import com.yahoo.language.process.StemMode;
import com.yahoo.vespa.configdefinition.IlscriptsConfig;

/**
 * @author Simon Thoresen Hult
 */
public class AnnotatorConfig implements Cloneable {

    private Language language;
    private StemMode stemMode;
    private boolean removeAccents;
    private int maxTermOccurrences;
    private int maxTokenizeLength;

    public static final int DEFAULT_MAX_TERM_OCCURRENCES;
    private static final int DEFAULT_MAX_TOKENIZE_LENGTH;

    static {
        IlscriptsConfig defaults = new IlscriptsConfig(new IlscriptsConfig.Builder());
        DEFAULT_MAX_TERM_OCCURRENCES = defaults.maxtermoccurrences();
        DEFAULT_MAX_TOKENIZE_LENGTH = defaults.fieldmatchmaxlength();
    }

    public AnnotatorConfig() {
        language = Language.ENGLISH;
        stemMode = StemMode.NONE;
        removeAccents = false;
        maxTermOccurrences = DEFAULT_MAX_TERM_OCCURRENCES;
        maxTokenizeLength = DEFAULT_MAX_TOKENIZE_LENGTH;
    }

    public AnnotatorConfig(AnnotatorConfig rhs) {
        language = rhs.language;
        stemMode = rhs.stemMode;
        removeAccents = rhs.removeAccents;
        maxTermOccurrences = rhs.maxTermOccurrences;
        maxTokenizeLength = rhs.maxTokenizeLength;
    }

    public Language getLanguage() {
        return language;
    }

    public AnnotatorConfig setLanguage(Language language) {
        this.language = language;
        return this;
    }

    public StemMode getStemMode() {
        return stemMode;
    }

    public AnnotatorConfig setStemMode(StemMode stemMode) {
        this.stemMode = stemMode;
        return this;
    }

    public AnnotatorConfig setStemMode(String name) {
        this.stemMode = StemMode.valueOf(name);
        return this;
    }

    public boolean getRemoveAccents() {
        return removeAccents;
    }

    public AnnotatorConfig setRemoveAccents(boolean removeAccents) {
        this.removeAccents = removeAccents;
        return this;
    }

    public int getMaxTermOccurrences() {
        return maxTermOccurrences;
    }

    public AnnotatorConfig setMaxTermOccurrences(int maxTermCount) {
        this.maxTermOccurrences = maxTermCount;
        return this;
    }

    public AnnotatorConfig setMaxTokenLength(int maxTokenizeLength) {
        this.maxTokenizeLength = maxTokenizeLength;
        return this;
    }

    public int getMaxTokenizeLength() {
        return maxTokenizeLength;
    }

    public boolean hasNonDefaultMaxTokenLength() {
        return maxTokenizeLength != DEFAULT_MAX_TOKENIZE_LENGTH;
    }

    @Override
    public boolean equals(Object obj) {
        if (!(obj instanceof AnnotatorConfig)) {
            return false;
        }
        AnnotatorConfig rhs = (AnnotatorConfig)obj;
        if (!language.equals(rhs.language)) {
            return false;
        }
        if (!stemMode.equals(rhs.stemMode)) {
            return false;
        }
        if (removeAccents != rhs.removeAccents) {
            return false;
        }
        if (maxTermOccurrences != rhs.maxTermOccurrences) {
            return false;
        }
        if (maxTokenizeLength != rhs.maxTokenizeLength) {
            return false;
        }
        return true;
    }

    @Override
    public int hashCode() {
        return getClass().hashCode() + language.hashCode() + stemMode.hashCode() +
               Boolean.valueOf(removeAccents).hashCode() + maxTermOccurrences + maxTokenizeLength;
    }
}