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
132. 132
133. 133
134. 134
135. 135
136. 136
137. 137
138. 138
139. 139
140. 140
141. 141
142. 142
143. 143
144. 144
145. 145
146. 146

package rupture

import (
	"fmt"
	"hash/fnv"
	"path/filepath"
	"strconv"

	"github.com/blevesearch/bleve/v2"
	"github.com/blevesearch/bleve/v2/mapping"
	index "github.com/blevesearch/bleve_index_api"
)

// ShardedIndex an index that is built onto of multiple underlying bleve
// indices (i.e. shards). Similar to bleve's index aliases, some methods may
// not be supported.
type ShardedIndex interface {
	bleve.Index
	shards() []bleve.Index
}

// a type alias for bleve.Index, so that the anonymous field of
// shardedIndex does not conflict with the Index(..) method.
type bleveIndex bleve.Index

type shardedIndex struct {
	bleveIndex
	indices []bleve.Index
}

func hash(id string, n int) uint64 {
	fnvHash := fnv.New64()
	fnvHash.Write([]byte(id))
	return fnvHash.Sum64() % uint64(n)
}

func childIndexerPath(rootPath string, i int) string {
	return filepath.Join(rootPath, strconv.Itoa(i))
}

// NewShardedIndex creates a sharded index at the specified path, with the
// specified mapping and number of shards.
func NewShardedIndex(path string, mapping mapping.IndexMapping, numShards int) (ShardedIndex, error) {
	if numShards <= 0 {
		return nil, fmt.Errorf("Invalid number of shards: %d", numShards)
	}
	err := writeJSON(shardedIndexMetadataPath(path), &shardedIndexMetadata{NumShards: numShards})
	if err != nil {
		return nil, err
	}

	s := &shardedIndex{
		indices: make([]bleve.Index, numShards),
	}
	for i := 0; i < numShards; i++ {
		s.indices[i], err = bleve.New(childIndexerPath(path, i), mapping)
		if err != nil {
			return nil, err
		}
	}
	s.bleveIndex = bleve.NewIndexAlias(s.indices...)
	return s, nil
}

// OpenShardedIndex opens a sharded index at the specified path.
func OpenShardedIndex(path string) (ShardedIndex, error) {
	var meta shardedIndexMetadata
	var err error
	if err = readJSON(shardedIndexMetadataPath(path), &meta); err != nil {
		return nil, err
	}

	s := &shardedIndex{
		indices: make([]bleve.Index, meta.NumShards),
	}
	for i := 0; i < meta.NumShards; i++ {
		s.indices[i], err = bleve.Open(childIndexerPath(path, i))
		if err != nil {
			return nil, err
		}
	}
	s.bleveIndex = bleve.NewIndexAlias(s.indices...)
	return s, nil
}

func (s *shardedIndex) Index(id string, data interface{}) error {
	return s.indices[hash(id, len(s.indices))].Index(id, data)
}

func (s *shardedIndex) Delete(id string) error {
	return s.indices[hash(id, len(s.indices))].Delete(id)
}

func (s *shardedIndex) Document(id string) (index.Document, error) {
	return s.indices[hash(id, len(s.indices))].Document(id)
}

func (s *shardedIndex) Close() error {
	if err := s.bleveIndex.Close(); err != nil {
		return err
	}
	for _, index := range s.indices {
		if err := index.Close(); err != nil {
			return err
		}
	}
	return nil
}

func (s *shardedIndex) shards() []bleve.Index {
	return s.indices
}

type shardedIndexFlushingBatch struct {
	batches []*singleIndexFlushingBatch
}

// NewShardedFlushingBatch creates a flushing batch with the specified batch
// size for the specified sharded index.
func NewShardedFlushingBatch(index ShardedIndex, maxBatchSize int) FlushingBatch {
	indices := index.shards()
	b := &shardedIndexFlushingBatch{
		batches: make([]*singleIndexFlushingBatch, len(indices)),
	}
	for i, index := range indices {
		b.batches[i] = newFlushingBatch(index, maxBatchSize)
	}
	return b
}

func (b *shardedIndexFlushingBatch) Index(id string, data interface{}) error {
	return b.batches[hash(id, len(b.batches))].Index(id, data)
}

func (b *shardedIndexFlushingBatch) Delete(id string) error {
	return b.batches[hash(id, len(b.batches))].Delete(id)
}

func (b *shardedIndexFlushingBatch) Flush() error {
	for _, batch := range b.batches {
		if err := batch.Flush(); err != nil {
			return err
		}
	}
	return nil
}