summaryrefslogtreecommitdiff
path: root/core/src/main/java/org/elasticsearch/search/suggest/phrase/PhraseSuggestionContext.java
blob: 99e2e18496b61f9d1adff5197c8b80aad73f8dd9 (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
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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
/*
 * Licensed to Elasticsearch under one or more contributor
 * license agreements. See the NOTICE file distributed with
 * this work for additional information regarding copyright
 * ownership. Elasticsearch licenses this file to you under
 * the Apache License, Version 2.0 (the "License"); you may
 * not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing,
 * software distributed under the License is distributed on an
 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 * KIND, either express or implied.  See the License for the
 * specific language governing permissions and limitations
 * under the License.
 */
package org.elasticsearch.search.suggest.phrase;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Terms;
import org.apache.lucene.util.BytesRef;
import org.elasticsearch.index.query.QueryShardContext;
import org.elasticsearch.script.CompiledScript;
import org.elasticsearch.script.ExecutableScript;
import org.elasticsearch.search.suggest.DirectSpellcheckerSettings;
import org.elasticsearch.search.suggest.SuggestionSearchContext.SuggestionContext;

import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.function.Function;

class PhraseSuggestionContext extends SuggestionContext {
    static final boolean DEFAULT_COLLATE_PRUNE = false;
    static final boolean DEFAULT_REQUIRE_UNIGRAM = true;
    static final float DEFAULT_CONFIDENCE = 1.0f;
    static final int DEFAULT_GRAM_SIZE = 1;
    static final float DEFAULT_RWE_ERRORLIKELIHOOD = 0.95f;
    static final float DEFAULT_MAX_ERRORS = 0.5f;
    static final String DEFAULT_SEPARATOR = " ";
    static final WordScorer.WordScorerFactory DEFAULT_SCORER = (IndexReader reader, Terms terms, String field, double realWordLikelyhood,
            BytesRef separator) -> new StupidBackoffScorer(reader, terms, field, realWordLikelyhood, separator, 0.4f);

    private float maxErrors = DEFAULT_MAX_ERRORS;
    private BytesRef separator = new BytesRef(DEFAULT_SEPARATOR);
    private float realworldErrorLikelihood = DEFAULT_RWE_ERRORLIKELIHOOD;
    private int gramSize = DEFAULT_GRAM_SIZE;
    private float confidence = DEFAULT_CONFIDENCE;
    private int tokenLimit = NoisyChannelSpellChecker.DEFAULT_TOKEN_LIMIT;
    private boolean requireUnigram = DEFAULT_REQUIRE_UNIGRAM;
    private BytesRef preTag;
    private BytesRef postTag;
    private Function<Map<String, Object>, ExecutableScript>  collateQueryScript;
    private boolean prune = DEFAULT_COLLATE_PRUNE;
    private List<DirectCandidateGenerator> generators = new ArrayList<>();
    private Map<String, Object> collateScriptParams = new HashMap<>(1);
    private WordScorer.WordScorerFactory scorer = DEFAULT_SCORER;

    PhraseSuggestionContext(QueryShardContext shardContext) {
        super(PhraseSuggester.INSTANCE, shardContext);
    }

    public float maxErrors() {
        return maxErrors;
    }

    public void setMaxErrors(Float maxErrors) {
        this.maxErrors = maxErrors;
    }

    public BytesRef separator() {
        return separator;
    }

    public void setSeparator(BytesRef separator) {
        this.separator = separator;
    }

    public Float realworldErrorLikelyhood() {
        return realworldErrorLikelihood;
    }

    public void setRealWordErrorLikelihood(Float realworldErrorLikelihood) {
        this.realworldErrorLikelihood = realworldErrorLikelihood;
    }

    public void addGenerator(DirectCandidateGenerator generator) {
        this.generators.add(generator);
    }

    public List<DirectCandidateGenerator> generators() {
        return this.generators ;
    }

    public void setGramSize(int gramSize) {
        this.gramSize = gramSize;
    }

    public int gramSize() {
        return gramSize;
    }

    public float confidence() {
        return confidence;
    }

    public void setConfidence(float confidence) {
        this.confidence = confidence;
    }

    public void setModel(WordScorer.WordScorerFactory scorer) {
        this.scorer = scorer;
    }

    public WordScorer.WordScorerFactory model() {
        return scorer;
    }

    static class DirectCandidateGenerator extends DirectSpellcheckerSettings {
        private Analyzer preFilter;
        private Analyzer postFilter;
        private String field;
        private int size = 5;

        public String field() {
            return field;
        }

        public void setField(String field) {
            this.field = field;
        }

        public int size() {
            return size;
        }

        public void size(int size) {
            if (size <= 0) {
                throw new IllegalArgumentException("Size must be positive");
            }
            this.size = size;
        }

        public Analyzer preFilter() {
            return preFilter;
        }

        public void preFilter(Analyzer preFilter) {
            this.preFilter = preFilter;
        }

        public Analyzer postFilter() {
            return postFilter;
        }

        public void postFilter(Analyzer postFilter) {
            this.postFilter = postFilter;
        }
    }

    public void setRequireUnigram(boolean requireUnigram) {
        this.requireUnigram  = requireUnigram;
    }

    public boolean getRequireUnigram() {
        return requireUnigram;
    }

    public void setTokenLimit(int tokenLimit) {
        this.tokenLimit = tokenLimit;
    }

    public int getTokenLimit() {
        return tokenLimit;
    }

    public void setPreTag(BytesRef preTag) {
        this.preTag = preTag;
    }

    public BytesRef getPreTag() {
        return preTag;
    }

    public void setPostTag(BytesRef postTag) {
        this.postTag = postTag;
    }

    public BytesRef getPostTag() {
        return postTag;
    }

    Function<Map<String, Object>, ExecutableScript> getCollateQueryScript() {
        return collateQueryScript;
    }

    void setCollateQueryScript( Function<Map<String, Object>, ExecutableScript>  collateQueryScript) {
        this.collateQueryScript = collateQueryScript;
    }

    Map<String, Object> getCollateScriptParams() {
        return collateScriptParams;
    }

    void setCollateScriptParams(Map<String, Object> collateScriptParams) {
        this.collateScriptParams = new HashMap<>(collateScriptParams);
    }

    void setCollatePrune(boolean prune) {
        this.prune = prune;
    }

    boolean collatePrune() {
        return prune;
    }
}