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
147. 147
148. 148
149. 149
150. 150
151. 151
152. 152
153. 153
154. 154
155. 155
156. 156
157. 157
158. 158
159. 159
160. 160
161. 161
162. 162
163. 163
164. 164
165. 165

package brotli

/* Copyright 2015 Google Inc. All Rights Reserved.

   Distributed under MIT license.
   See file LICENSE for detail or copy at https://opensource.org/licenses/MIT
*/

/* Greedy block splitter for one block category (literal, command or distance).
 */
type blockSplitterLiteral struct {
	alphabet_size_     uint
	min_block_size_    uint
	split_threshold_   float64
	num_blocks_        uint
	split_             *blockSplit
	histograms_        []histogramLiteral
	histograms_size_   *uint
	target_block_size_ uint
	block_size_        uint
	curr_histogram_ix_ uint
	last_histogram_ix_ [2]uint
	last_entropy_      [2]float64
	merge_last_count_  uint
}

func initBlockSplitterLiteral(self *blockSplitterLiteral, alphabet_size uint, min_block_size uint, split_threshold float64, num_symbols uint, split *blockSplit, histograms *[]histogramLiteral, histograms_size *uint) {
	var max_num_blocks uint = num_symbols/min_block_size + 1
	var max_num_types uint = brotli_min_size_t(max_num_blocks, maxNumberOfBlockTypes+1)
	/* We have to allocate one more histogram than the maximum number of block
	   types for the current histogram when the meta-block is too big. */
	self.alphabet_size_ = alphabet_size

	self.min_block_size_ = min_block_size
	self.split_threshold_ = split_threshold
	self.num_blocks_ = 0
	self.split_ = split
	self.histograms_size_ = histograms_size
	self.target_block_size_ = min_block_size
	self.block_size_ = 0
	self.curr_histogram_ix_ = 0
	self.merge_last_count_ = 0
	brotli_ensure_capacity_uint8_t(&split.types, &split.types_alloc_size, max_num_blocks)
	brotli_ensure_capacity_uint32_t(&split.lengths, &split.lengths_alloc_size, max_num_blocks)
	self.split_.num_blocks = max_num_blocks
	*histograms_size = max_num_types
	if histograms == nil || cap(*histograms) < int(*histograms_size) {
		*histograms = make([]histogramLiteral, *histograms_size)
	} else {
		*histograms = (*histograms)[:*histograms_size]
	}
	self.histograms_ = *histograms

	/* Clear only current histogram. */
	histogramClearLiteral(&self.histograms_[0])

	self.last_histogram_ix_[1] = 0
	self.last_histogram_ix_[0] = self.last_histogram_ix_[1]
}

/* Does either of three things:
   (1) emits the current block with a new block type;
   (2) emits the current block with the type of the second last block;
   (3) merges the current block with the last block. */
func blockSplitterFinishBlockLiteral(self *blockSplitterLiteral, is_final bool) {
	var split *blockSplit = self.split_
	var last_entropy []float64 = self.last_entropy_[:]
	var histograms []histogramLiteral = self.histograms_
	self.block_size_ = brotli_max_size_t(self.block_size_, self.min_block_size_)
	if self.num_blocks_ == 0 {
		/* Create first block. */
		split.lengths[0] = uint32(self.block_size_)

		split.types[0] = 0
		last_entropy[0] = bitsEntropy(histograms[0].data_[:], self.alphabet_size_)
		last_entropy[1] = last_entropy[0]
		self.num_blocks_++
		split.num_types++
		self.curr_histogram_ix_++
		if self.curr_histogram_ix_ < *self.histograms_size_ {
			histogramClearLiteral(&histograms[self.curr_histogram_ix_])
		}
		self.block_size_ = 0
	} else if self.block_size_ > 0 {
		var entropy float64 = bitsEntropy(histograms[self.curr_histogram_ix_].data_[:], self.alphabet_size_)
		var combined_histo [2]histogramLiteral
		var combined_entropy [2]float64
		var diff [2]float64
		var j uint
		for j = 0; j < 2; j++ {
			var last_histogram_ix uint = self.last_histogram_ix_[j]
			combined_histo[j] = histograms[self.curr_histogram_ix_]
			histogramAddHistogramLiteral(&combined_histo[j], &histograms[last_histogram_ix])
			combined_entropy[j] = bitsEntropy(combined_histo[j].data_[0:], self.alphabet_size_)
			diff[j] = combined_entropy[j] - entropy - last_entropy[j]
		}

		if split.num_types < maxNumberOfBlockTypes && diff[0] > self.split_threshold_ && diff[1] > self.split_threshold_ {
			/* Create new block. */
			split.lengths[self.num_blocks_] = uint32(self.block_size_)

			split.types[self.num_blocks_] = byte(split.num_types)
			self.last_histogram_ix_[1] = self.last_histogram_ix_[0]
			self.last_histogram_ix_[0] = uint(byte(split.num_types))
			last_entropy[1] = last_entropy[0]
			last_entropy[0] = entropy
			self.num_blocks_++
			split.num_types++
			self.curr_histogram_ix_++
			if self.curr_histogram_ix_ < *self.histograms_size_ {
				histogramClearLiteral(&histograms[self.curr_histogram_ix_])
			}
			self.block_size_ = 0
			self.merge_last_count_ = 0
			self.target_block_size_ = self.min_block_size_
		} else if diff[1] < diff[0]-20.0 {
			split.lengths[self.num_blocks_] = uint32(self.block_size_)
			split.types[self.num_blocks_] = split.types[self.num_blocks_-2]
			/* Combine this block with second last block. */

			var tmp uint = self.last_histogram_ix_[0]
			self.last_histogram_ix_[0] = self.last_histogram_ix_[1]
			self.last_histogram_ix_[1] = tmp
			histograms[self.last_histogram_ix_[0]] = combined_histo[1]
			last_entropy[1] = last_entropy[0]
			last_entropy[0] = combined_entropy[1]
			self.num_blocks_++
			self.block_size_ = 0
			histogramClearLiteral(&histograms[self.curr_histogram_ix_])
			self.merge_last_count_ = 0
			self.target_block_size_ = self.min_block_size_
		} else {
			/* Combine this block with last block. */
			split.lengths[self.num_blocks_-1] += uint32(self.block_size_)

			histograms[self.last_histogram_ix_[0]] = combined_histo[0]
			last_entropy[0] = combined_entropy[0]
			if split.num_types == 1 {
				last_entropy[1] = last_entropy[0]
			}

			self.block_size_ = 0
			histogramClearLiteral(&histograms[self.curr_histogram_ix_])
			self.merge_last_count_++
			if self.merge_last_count_ > 1 {
				self.target_block_size_ += self.min_block_size_
			}
		}
	}

	if is_final {
		*self.histograms_size_ = split.num_types
		split.num_blocks = self.num_blocks_
	}
}

/* Adds the next symbol to the current histogram. When the current histogram
   reaches the target size, decides on merging the block. */
func blockSplitterAddSymbolLiteral(self *blockSplitterLiteral, symbol uint) {
	histogramAddLiteral(&self.histograms_[self.curr_histogram_ix_], symbol)
	self.block_size_++
	if self.block_size_ == self.target_block_size_ {
		blockSplitterFinishBlockLiteral(self, false) /* is_final = */
	}
}