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
|
// 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 unicode
import (
"github.com/blevesearch/segment"
"github.com/blevesearch/bleve/analysis"
"github.com/blevesearch/bleve/registry"
)
const Name = "unicode"
type UnicodeTokenizer struct {
}
func NewUnicodeTokenizer() *UnicodeTokenizer {
return &UnicodeTokenizer{}
}
func (rt *UnicodeTokenizer) Tokenize(input []byte) analysis.TokenStream {
rvx := make([]analysis.TokenStream, 0, 10) // When rv gets full, append to rvx.
rv := make(analysis.TokenStream, 0, 1)
ta := []analysis.Token(nil)
taNext := 0
segmenter := segment.NewWordSegmenterDirect(input)
start := 0
pos := 1
guessRemaining := func(end int) int {
avgSegmentLen := end / (len(rv) + 1)
if avgSegmentLen < 1 {
avgSegmentLen = 1
}
remainingLen := len(input) - end
return remainingLen / avgSegmentLen
}
for segmenter.Segment() {
segmentBytes := segmenter.Bytes()
end := start + len(segmentBytes)
if segmenter.Type() != segment.None {
if taNext >= len(ta) {
remainingSegments := guessRemaining(end)
if remainingSegments > 1000 {
remainingSegments = 1000
}
if remainingSegments < 1 {
remainingSegments = 1
}
ta = make([]analysis.Token, remainingSegments)
taNext = 0
}
token := &ta[taNext]
taNext++
token.Term = segmentBytes
token.Start = start
token.End = end
token.Position = pos
token.Type = convertType(segmenter.Type())
if len(rv) >= cap(rv) { // When rv is full, save it into rvx.
rvx = append(rvx, rv)
rvCap := cap(rv) * 2
if rvCap > 256 {
rvCap = 256
}
rv = make(analysis.TokenStream, 0, rvCap) // Next rv cap is bigger.
}
rv = append(rv, token)
pos++
}
start = end
}
if len(rvx) > 0 {
n := len(rv)
for _, r := range rvx {
n += len(r)
}
rall := make(analysis.TokenStream, 0, n)
for _, r := range rvx {
rall = append(rall, r...)
}
return append(rall, rv...)
}
return rv
}
func UnicodeTokenizerConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.Tokenizer, error) {
return NewUnicodeTokenizer(), nil
}
func init() {
registry.RegisterTokenizer(Name, UnicodeTokenizerConstructor)
}
func convertType(segmentWordType int) analysis.TokenType {
switch segmentWordType {
case segment.Ideo:
return analysis.Ideographic
case segment.Kana:
return analysis.Ideographic
case segment.Number:
return analysis.Numeric
}
return analysis.AlphaNumeric
}
|
