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
166. 166
167. 167
168. 168
169. 169
170. 170
171. 171
172. 172
173. 173
174. 174
175. 175
176. 176
177. 177
178. 178

package zstd

import (
	"fmt"
	"math/bits"

	"github.com/klauspost/compress/zstd/internal/xxhash"
)

const (
	dictShardBits = 6
)

type fastBase struct {
	// cur is the offset at the start of hist
	cur int32
	// maximum offset. Should be at least 2x block size.
	maxMatchOff int32
	hist        []byte
	crc         *xxhash.Digest
	tmp         [8]byte
	blk         *blockEnc
	lastDictID  uint32
	lowMem      bool
}

// CRC returns the underlying CRC writer.
func (e *fastBase) CRC() *xxhash.Digest {
	return e.crc
}

// AppendCRC will append the CRC to the destination slice and return it.
func (e *fastBase) AppendCRC(dst []byte) []byte {
	crc := e.crc.Sum(e.tmp[:0])
	dst = append(dst, crc[7], crc[6], crc[5], crc[4])
	return dst
}

// WindowSize returns the window size of the encoder,
// or a window size small enough to contain the input size, if > 0.
func (e *fastBase) WindowSize(size int) int32 {
	if size > 0 && size < int(e.maxMatchOff) {
		b := int32(1) << uint(bits.Len(uint(size)))
		// Keep minimum window.
		if b < 1024 {
			b = 1024
		}
		return b
	}
	return e.maxMatchOff
}

// Block returns the current block.
func (e *fastBase) Block() *blockEnc {
	return e.blk
}

func (e *fastBase) addBlock(src []byte) int32 {
	if debugAsserts && e.cur > bufferReset {
		panic(fmt.Sprintf("ecur (%d) > buffer reset (%d)", e.cur, bufferReset))
	}
	// check if we have space already
	if len(e.hist)+len(src) > cap(e.hist) {
		if cap(e.hist) == 0 {
			e.ensureHist(len(src))
		} else {
			if cap(e.hist) < int(e.maxMatchOff+maxCompressedBlockSize) {
				panic(fmt.Errorf("unexpected buffer cap %d, want at least %d with window %d", cap(e.hist), e.maxMatchOff+maxCompressedBlockSize, e.maxMatchOff))
			}
			// Move down
			offset := int32(len(e.hist)) - e.maxMatchOff
			copy(e.hist[0:e.maxMatchOff], e.hist[offset:])
			e.cur += offset
			e.hist = e.hist[:e.maxMatchOff]
		}
	}
	s := int32(len(e.hist))
	e.hist = append(e.hist, src...)
	return s
}

// ensureHist will ensure that history can keep at least this many bytes.
func (e *fastBase) ensureHist(n int) {
	if cap(e.hist) >= n {
		return
	}
	l := e.maxMatchOff
	if (e.lowMem && e.maxMatchOff > maxCompressedBlockSize) || e.maxMatchOff <= maxCompressedBlockSize {
		l += maxCompressedBlockSize
	} else {
		l += e.maxMatchOff
	}
	// Make it at least 1MB.
	if l < 1<<20 && !e.lowMem {
		l = 1 << 20
	}
	// Make it at least the requested size.
	if l < int32(n) {
		l = int32(n)
	}
	e.hist = make([]byte, 0, l)
}

// useBlock will replace the block with the provided one,
// but transfer recent offsets from the previous.
func (e *fastBase) UseBlock(enc *blockEnc) {
	enc.reset(e.blk)
	e.blk = enc
}

func (e *fastBase) matchlenNoHist(s, t int32, src []byte) int32 {
	// Extend the match to be as long as possible.
	return int32(matchLen(src[s:], src[t:]))
}

func (e *fastBase) matchlen(s, t int32, src []byte) int32 {
	if debugAsserts {
		if s < 0 {
			err := fmt.Sprintf("s (%d) < 0", s)
			panic(err)
		}
		if t < 0 {
			err := fmt.Sprintf("s (%d) < 0", s)
			panic(err)
		}
		if s-t > e.maxMatchOff {
			err := fmt.Sprintf("s (%d) - t (%d) > maxMatchOff (%d)", s, t, e.maxMatchOff)
			panic(err)
		}
		if len(src)-int(s) > maxCompressedBlockSize {
			panic(fmt.Sprintf("len(src)-s (%d) > maxCompressedBlockSize (%d)", len(src)-int(s), maxCompressedBlockSize))
		}
	}

	// Extend the match to be as long as possible.
	return int32(matchLen(src[s:], src[t:]))
}

// Reset the encoding table.
func (e *fastBase) resetBase(d *dict, singleBlock bool) {
	if e.blk == nil {
		e.blk = &blockEnc{lowMem: e.lowMem}
		e.blk.init()
	} else {
		e.blk.reset(nil)
	}
	e.blk.initNewEncode()
	if e.crc == nil {
		e.crc = xxhash.New()
	} else {
		e.crc.Reset()
	}
	if d != nil {
		low := e.lowMem
		if singleBlock {
			e.lowMem = true
		}
		e.ensureHist(d.DictContentSize() + maxCompressedBlockSize)
		e.lowMem = low
	}

	// We offset current position so everything will be out of reach.
	// If above reset line, history will be purged.
	if e.cur < bufferReset {
		e.cur += e.maxMatchOff + int32(len(e.hist))
	}
	e.hist = e.hist[:0]
	if d != nil {
		// Set offsets (currently not used)
		for i, off := range d.offsets {
			e.blk.recentOffsets[i] = uint32(off)
			e.blk.prevRecentOffsets[i] = e.blk.recentOffsets[i]
		}
		// Transfer litenc.
		e.blk.dictLitEnc = d.litEnc
		e.hist = append(e.hist, d.content...)
	}
}