1. 1
2. 2
3. 3
4. 4
5. 5
6. 6
7. 7
8. 8
9. 9
10. 10
11. 11
12. 12
13. 13
14. 14
15. 15
16. 16
17. 17
18. 18
19. 19
20. 20
21. 21
22. 22
23. 23
24. 24
25. 25
26. 26
27. 27
28. 28
29. 29
30. 30
31. 31
32. 32
33. 33
34. 34
35. 35
36. 36
37. 37
38. 38
39. 39
40. 40
41. 41
42. 42
43. 43
44. 44
45. 45
46. 46
47. 47
48. 48
49. 49
50. 50
51. 51
52. 52
53. 53
54. 54
55. 55
56. 56
57. 57
58. 58
59. 59
60. 60
61. 61
62. 62
63. 63
64. 64
65. 65
66. 66
67. 67
68. 68
69. 69
70. 70
71. 71
72. 72
73. 73
74. 74
75. 75
76. 76
77. 77
78. 78
79. 79
80. 80
81. 81
82. 82
83. 83
84. 84
85. 85
86. 86
87. 87
88. 88
89. 89
90. 90
91. 91
92. 92
93. 93
94. 94
95. 95
96. 96
97. 97
98. 98
99. 99
100. 100
101. 101
102. 102
103. 103
104. 104
105. 105
106. 106
107. 107
108. 108
109. 109
110. 110
111. 111
112. 112
113. 113
114. 114
115. 115
116. 116
117. 117
118. 118
119. 119
120. 120
121. 121
122. 122
123. 123
124. 124
125. 125
126. 126
127. 127
128. 128
129. 129
130. 130
131. 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/v2/analysis"
	"github.com/blevesearch/bleve/v2/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
}