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
179. 179

package flate

import "fmt"

// fastGen maintains the table for matches,
// and the previous byte block for level 2.
// This is the generic implementation.
type fastEncL1 struct {
	fastGen
	table [tableSize]tableEntry
}

// EncodeL1 uses a similar algorithm to level 1
func (e *fastEncL1) Encode(dst *tokens, src []byte) {
	const (
		inputMargin            = 12 - 1
		minNonLiteralBlockSize = 1 + 1 + inputMargin
	)
	if debugDeflate && e.cur < 0 {
		panic(fmt.Sprint("e.cur < 0: ", e.cur))
	}

	// Protect against e.cur wraparound.
	for e.cur >= bufferReset {
		if len(e.hist) == 0 {
			for i := range e.table[:] {
				e.table[i] = tableEntry{}
			}
			e.cur = maxMatchOffset
			break
		}
		// Shift down everything in the table that isn't already too far away.
		minOff := e.cur + int32(len(e.hist)) - maxMatchOffset
		for i := range e.table[:] {
			v := e.table[i].offset
			if v <= minOff {
				v = 0
			} else {
				v = v - e.cur + maxMatchOffset
			}
			e.table[i].offset = v
		}
		e.cur = maxMatchOffset
	}

	s := e.addBlock(src)

	// This check isn't in the Snappy implementation, but there, the caller
	// instead of the callee handles this case.
	if len(src) < minNonLiteralBlockSize {
		// We do not fill the token table.
		// This will be picked up by caller.
		dst.n = uint16(len(src))
		return
	}

	// Override src
	src = e.hist
	nextEmit := s

	// sLimit is when to stop looking for offset/length copies. The inputMargin
	// lets us use a fast path for emitLiteral in the main loop, while we are
	// looking for copies.
	sLimit := int32(len(src) - inputMargin)

	// nextEmit is where in src the next emitLiteral should start from.
	cv := load3232(src, s)

	for {
		const skipLog = 5
		const doEvery = 2

		nextS := s
		var candidate tableEntry
		for {
			nextHash := hash(cv)
			candidate = e.table[nextHash]
			nextS = s + doEvery + (s-nextEmit)>>skipLog
			if nextS > sLimit {
				goto emitRemainder
			}

			now := load6432(src, nextS)
			e.table[nextHash] = tableEntry{offset: s + e.cur}
			nextHash = hash(uint32(now))

			offset := s - (candidate.offset - e.cur)
			if offset < maxMatchOffset && cv == load3232(src, candidate.offset-e.cur) {
				e.table[nextHash] = tableEntry{offset: nextS + e.cur}
				break
			}

			// Do one right away...
			cv = uint32(now)
			s = nextS
			nextS++
			candidate = e.table[nextHash]
			now >>= 8
			e.table[nextHash] = tableEntry{offset: s + e.cur}

			offset = s - (candidate.offset - e.cur)
			if offset < maxMatchOffset && cv == load3232(src, candidate.offset-e.cur) {
				e.table[nextHash] = tableEntry{offset: nextS + e.cur}
				break
			}
			cv = uint32(now)
			s = nextS
		}

		// A 4-byte match has been found. We'll later see if more than 4 bytes
		// match. But, prior to the match, src[nextEmit:s] are unmatched. Emit
		// them as literal bytes.
		for {
			// Invariant: we have a 4-byte match at s, and no need to emit any
			// literal bytes prior to s.

			// Extend the 4-byte match as long as possible.
			t := candidate.offset - e.cur
			l := e.matchlenLong(s+4, t+4, src) + 4

			// Extend backwards
			for t > 0 && s > nextEmit && src[t-1] == src[s-1] {
				s--
				t--
				l++
			}
			if nextEmit < s {
				emitLiteral(dst, src[nextEmit:s])
			}

			// Save the match found
			dst.AddMatchLong(l, uint32(s-t-baseMatchOffset))
			s += l
			nextEmit = s
			if nextS >= s {
				s = nextS + 1
			}
			if s >= sLimit {
				// Index first pair after match end.
				if int(s+l+4) < len(src) {
					cv := load3232(src, s)
					e.table[hash(cv)] = tableEntry{offset: s + e.cur}
				}
				goto emitRemainder
			}

			// We could immediately start working at s now, but to improve
			// compression we first update the hash table at s-2 and at s. If
			// another emitCopy is not our next move, also calculate nextHash
			// at s+1. At least on GOARCH=amd64, these three hash calculations
			// are faster as one load64 call (with some shifts) instead of
			// three load32 calls.
			x := load6432(src, s-2)
			o := e.cur + s - 2
			prevHash := hash(uint32(x))
			e.table[prevHash] = tableEntry{offset: o}
			x >>= 16
			currHash := hash(uint32(x))
			candidate = e.table[currHash]
			e.table[currHash] = tableEntry{offset: o + 2}

			offset := s - (candidate.offset - e.cur)
			if offset > maxMatchOffset || uint32(x) != load3232(src, candidate.offset-e.cur) {
				cv = uint32(x >> 8)
				s++
				break
			}
		}
	}

emitRemainder:
	if int(nextEmit) < len(src) {
		// If nothing was added, don't encode literals.
		if dst.n == 0 {
			return
		}
		emitLiteral(dst, src[nextEmit:])
	}
}