File: dict.go

package info (click to toggle)
golang-github-blevesearch-bleve 0.5.0%2Bgit20170912.278.6eea5b78-4
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 3,764 kB
  • sloc: yacc: 311; sh: 51; makefile: 7
file content (141 lines) | stat: -rw-r--r-- 4,001 bytes parent folder | download | duplicates (2)
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
//  Copyright (c) 2014 Couchbase, Inc.
//
// Licensed 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 compound

import (
	"bytes"
	"fmt"
	"unicode/utf8"

	"github.com/blevesearch/bleve/analysis"
	"github.com/blevesearch/bleve/registry"
)

const Name = "dict_compound"

const defaultMinWordSize = 5
const defaultMinSubWordSize = 2
const defaultMaxSubWordSize = 15
const defaultOnlyLongestMatch = false

type DictionaryCompoundFilter struct {
	dict             analysis.TokenMap
	minWordSize      int
	minSubWordSize   int
	maxSubWordSize   int
	onlyLongestMatch bool
}

func NewDictionaryCompoundFilter(dict analysis.TokenMap, minWordSize, minSubWordSize, maxSubWordSize int, onlyLongestMatch bool) *DictionaryCompoundFilter {
	return &DictionaryCompoundFilter{
		dict:             dict,
		minWordSize:      minWordSize,
		minSubWordSize:   minSubWordSize,
		maxSubWordSize:   maxSubWordSize,
		onlyLongestMatch: onlyLongestMatch,
	}
}

func (f *DictionaryCompoundFilter) Filter(input analysis.TokenStream) analysis.TokenStream {
	rv := make(analysis.TokenStream, 0, len(input))

	for _, token := range input {
		rv = append(rv, token)
		tokenLen := utf8.RuneCount(token.Term)
		if tokenLen >= f.minWordSize {
			newtokens := f.decompose(token)
			for _, newtoken := range newtokens {
				rv = append(rv, newtoken)
			}
		}
	}

	return rv
}

func (f *DictionaryCompoundFilter) decompose(token *analysis.Token) []*analysis.Token {
	runes := bytes.Runes(token.Term)
	rv := make([]*analysis.Token, 0)
	rlen := len(runes)
	for i := 0; i <= (rlen - f.minSubWordSize); i++ {
		var longestMatchToken *analysis.Token
		for j := f.minSubWordSize; j <= f.maxSubWordSize; j++ {
			if i+j > rlen {
				break
			}
			_, inDict := f.dict[string(runes[i:i+j])]
			if inDict {
				newtoken := analysis.Token{
					Term:     []byte(string(runes[i : i+j])),
					Position: token.Position,
					Start:    token.Start + i,
					End:      token.Start + i + j,
					Type:     token.Type,
					KeyWord:  token.KeyWord,
				}
				if f.onlyLongestMatch {
					if longestMatchToken == nil || utf8.RuneCount(longestMatchToken.Term) < j {
						longestMatchToken = &newtoken
					}
				} else {
					rv = append(rv, &newtoken)
				}
			}
		}
		if f.onlyLongestMatch && longestMatchToken != nil {
			rv = append(rv, longestMatchToken)
		}
	}
	return rv
}

func DictionaryCompoundFilterConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenFilter, error) {

	minWordSize := defaultMinWordSize
	minSubWordSize := defaultMinSubWordSize
	maxSubWordSize := defaultMaxSubWordSize
	onlyLongestMatch := defaultOnlyLongestMatch

	minVal, ok := config["min_word_size"].(float64)
	if ok {
		minWordSize = int(minVal)
	}
	minSubVal, ok := config["min_subword_size"].(float64)
	if ok {
		minSubWordSize = int(minSubVal)
	}
	maxSubVal, ok := config["max_subword_size"].(float64)
	if ok {
		maxSubWordSize = int(maxSubVal)
	}
	onlyVal, ok := config["only_longest_match"].(bool)
	if ok {
		onlyLongestMatch = onlyVal
	}

	dictTokenMapName, ok := config["dict_token_map"].(string)
	if !ok {
		return nil, fmt.Errorf("must specify dict_token_map")
	}
	dictTokenMap, err := cache.TokenMapNamed(dictTokenMapName)
	if err != nil {
		return nil, fmt.Errorf("error building dict compound words filter: %v", err)
	}
	return NewDictionaryCompoundFilter(dictTokenMap, minWordSize, minSubWordSize, maxSubWordSize, onlyLongestMatch), nil
}

func init() {
	registry.RegisterTokenFilter(Name, DictionaryCompoundFilterConstructor)
}