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
|
/*
* 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.index.IndexReader;
import org.apache.lucene.index.Terms;
import org.apache.lucene.util.BytesRef;
import org.elasticsearch.common.ParseField;
import org.elasticsearch.common.io.stream.StreamInput;
import org.elasticsearch.common.io.stream.StreamOutput;
import org.elasticsearch.common.xcontent.XContentBuilder;
import org.elasticsearch.common.xcontent.XContentParser;
import org.elasticsearch.common.xcontent.XContentParser.Token;
import org.elasticsearch.index.query.QueryParseContext;
import org.elasticsearch.search.suggest.phrase.WordScorer.WordScorerFactory;
import java.io.IOException;
import java.util.Objects;
/**
* A "stupid-backoff" smoothing model similar to <a
* href="http://en.wikipedia.org/wiki/Katz's_back-off_model"> Katz's
* Backoff</a>. This model is used as the default if no model is configured.
* <p>
* See <a
* href="http://en.wikipedia.org/wiki/N-gram#Smoothing_techniques">N-Gram
* Smoothing</a> for details.
* </p>
*/
public final class StupidBackoff extends SmoothingModel {
/**
* Default discount parameter for {@link StupidBackoff} smoothing
*/
public static final double DEFAULT_BACKOFF_DISCOUNT = 0.4;
public static final String NAME = "stupid_backoff";
private static final ParseField DISCOUNT_FIELD = new ParseField("discount");
static final ParseField PARSE_FIELD = new ParseField(NAME);
private double discount = DEFAULT_BACKOFF_DISCOUNT;
/**
* Creates a Stupid-Backoff smoothing model.
*
* @param discount
* the discount given to lower order ngrams if the higher order ngram doesn't exits
*/
public StupidBackoff(double discount) {
this.discount = discount;
}
/**
* Read from a stream.
*/
public StupidBackoff(StreamInput in) throws IOException {
discount = in.readDouble();
}
@Override
public void writeTo(StreamOutput out) throws IOException {
out.writeDouble(discount);
}
/**
* @return the discount parameter of the model
*/
public double getDiscount() {
return this.discount;
}
@Override
protected XContentBuilder innerToXContent(XContentBuilder builder, Params params) throws IOException {
builder.field(DISCOUNT_FIELD.getPreferredName(), discount);
return builder;
}
@Override
public String getWriteableName() {
return NAME;
}
@Override
protected boolean doEquals(SmoothingModel other) {
StupidBackoff otherModel = (StupidBackoff) other;
return Objects.equals(discount, otherModel.discount);
}
@Override
protected final int doHashCode() {
return Objects.hash(discount);
}
public static SmoothingModel innerFromXContent(QueryParseContext parseContext) throws IOException {
XContentParser parser = parseContext.parser();
XContentParser.Token token;
String fieldName = null;
double discount = DEFAULT_BACKOFF_DISCOUNT;
while ((token = parser.nextToken()) != Token.END_OBJECT) {
if (token == XContentParser.Token.FIELD_NAME) {
fieldName = parser.currentName();
}
if (token.isValue() && parseContext.parseFieldMatcher().match(fieldName, DISCOUNT_FIELD)) {
discount = parser.doubleValue();
}
}
return new StupidBackoff(discount);
}
@Override
public WordScorerFactory buildWordScorerFactory() {
return (IndexReader reader, Terms terms, String field, double realWordLikelyhood, BytesRef separator)
-> new StupidBackoffScorer(reader, terms, field, realWordLikelyhood, separator, discount);
}
}
|
