gitea

Development moved to Codeberg

  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
  180. 180
  181. 181
  182. 182
  183. 183
  184. 184
  185. 185
  186. 186
  187. 187
  188. 188
  189. 189
  190. 190
  191. 191
  192. 192
  193. 193
  194. 194
  195. 195
  196. 196
  197. 197
  198. 198
  199. 199
  200. 200
  201. 201
  202. 202
  203. 203
  204. 204
  205. 205
  206. 206
  207. 207
  208. 208
  209. 209
  210. 210
  211. 211
  212. 212
  213. 213
  214. 214
  215. 215
  216. 216
  217. 217
  218. 218
  219. 219
  220. 220
  221. 221
  222. 222
  223. 223
  224. 224
  225. 225
  226. 226
  227. 227
  228. 228
  229. 229
  230. 230
  231. 231
  232. 232
  233. 233
  234. 234
  235. 235
  236. 236
  237. 237
  238. 238
  239. 239
  240. 240
  241. 241
  242. 242
  243. 243
  244. 244
  245. 245
  246. 246
  247. 247
  248. 248
  249. 249
  250. 250
  251. 251
  252. 252
  253. 253
  254. 254
  255. 255
  256. 256
  257. 257
  258. 258
  259. 259
  260. 260
  261. 261
  262. 262
  263. 263
  264. 264
  265. 265
  266. 266
  267. 267
  268. 268
  269. 269
  270. 270
  271. 271
  272. 272
  273. 273
  274. 274
  275. 275
  276. 276
  277. 277
  278. 278
  279. 279
  280. 280
  281. 281
  282. 282
  283. 283
  284. 284
  285. 285
  286. 286
  287. 287
  288. 288
  289. 289
  290. 290
  291. 291
  292. 292
  293. 293
  294. 294
  295. 295
  296. 296
  297. 297
  298. 298
  299. 299
  300. 300
  301. 301
  302. 302
  303. 303
  304. 304
  305. 305
  306. 306
  307. 307
  308. 308
  309. 309
  310. 310
  311. 311
  312. 312
package zstd

import (
	"errors"
	"fmt"
	"runtime"
	"strings"
)

// EOption is an option for creating a encoder.
type EOption func(*encoderOptions) error

// options retains accumulated state of multiple options.
type encoderOptions struct {
	concurrent      int
	level           EncoderLevel
	single          *bool
	pad             int
	blockSize       int
	windowSize      int
	crc             bool
	fullZero        bool
	noEntropy       bool
	allLitEntropy   bool
	customWindow    bool
	customALEntropy bool
	lowMem          bool
	dict            *dict
}

func (o *encoderOptions) setDefault() {
	*o = encoderOptions{
		concurrent:    runtime.GOMAXPROCS(0),
		crc:           true,
		single:        nil,
		blockSize:     1 << 16,
		windowSize:    8 << 20,
		level:         SpeedDefault,
		allLitEntropy: true,
		lowMem:        false,
	}
}

// encoder returns an encoder with the selected options.
func (o encoderOptions) encoder() encoder {
	switch o.level {
	case SpeedFastest:
		if o.dict != nil {
			return &fastEncoderDict{fastEncoder: fastEncoder{fastBase: fastBase{maxMatchOff: int32(o.windowSize), lowMem: o.lowMem}}}
		}
		return &fastEncoder{fastBase: fastBase{maxMatchOff: int32(o.windowSize), lowMem: o.lowMem}}

	case SpeedDefault:
		if o.dict != nil {
			return &doubleFastEncoderDict{fastEncoderDict: fastEncoderDict{fastEncoder: fastEncoder{fastBase: fastBase{maxMatchOff: int32(o.windowSize), lowMem: o.lowMem}}}}
		}
		return &doubleFastEncoder{fastEncoder: fastEncoder{fastBase: fastBase{maxMatchOff: int32(o.windowSize), lowMem: o.lowMem}}}
	case SpeedBetterCompression:
		if o.dict != nil {
			return &betterFastEncoderDict{betterFastEncoder: betterFastEncoder{fastBase: fastBase{maxMatchOff: int32(o.windowSize), lowMem: o.lowMem}}}
		}
		return &betterFastEncoder{fastBase: fastBase{maxMatchOff: int32(o.windowSize), lowMem: o.lowMem}}
	case SpeedBestCompression:
		return &bestFastEncoder{fastBase: fastBase{maxMatchOff: int32(o.windowSize), lowMem: o.lowMem}}
	}
	panic("unknown compression level")
}

// WithEncoderCRC will add CRC value to output.
// Output will be 4 bytes larger.
func WithEncoderCRC(b bool) EOption {
	return func(o *encoderOptions) error { o.crc = b; return nil }
}

// WithEncoderConcurrency will set the concurrency,
// meaning the maximum number of encoders to run concurrently.
// The value supplied must be at least 1.
// By default this will be set to GOMAXPROCS.
func WithEncoderConcurrency(n int) EOption {
	return func(o *encoderOptions) error {
		if n <= 0 {
			return fmt.Errorf("concurrency must be at least 1")
		}
		o.concurrent = n
		return nil
	}
}

// WithWindowSize will set the maximum allowed back-reference distance.
// The value must be a power of two between MinWindowSize and MaxWindowSize.
// A larger value will enable better compression but allocate more memory and,
// for above-default values, take considerably longer.
// The default value is determined by the compression level.
func WithWindowSize(n int) EOption {
	return func(o *encoderOptions) error {
		switch {
		case n < MinWindowSize:
			return fmt.Errorf("window size must be at least %d", MinWindowSize)
		case n > MaxWindowSize:
			return fmt.Errorf("window size must be at most %d", MaxWindowSize)
		case (n & (n - 1)) != 0:
			return errors.New("window size must be a power of 2")
		}

		o.windowSize = n
		o.customWindow = true
		if o.blockSize > o.windowSize {
			o.blockSize = o.windowSize
		}
		return nil
	}
}

// WithEncoderPadding will add padding to all output so the size will be a multiple of n.
// This can be used to obfuscate the exact output size or make blocks of a certain size.
// The contents will be a skippable frame, so it will be invisible by the decoder.
// n must be > 0 and <= 1GB, 1<<30 bytes.
// The padded area will be filled with data from crypto/rand.Reader.
// If `EncodeAll` is used with data already in the destination, the total size will be multiple of this.
func WithEncoderPadding(n int) EOption {
	return func(o *encoderOptions) error {
		if n <= 0 {
			return fmt.Errorf("padding must be at least 1")
		}
		// No need to waste our time.
		if n == 1 {
			o.pad = 0
		}
		if n > 1<<30 {
			return fmt.Errorf("padding must less than 1GB (1<<30 bytes) ")
		}
		o.pad = n
		return nil
	}
}

// EncoderLevel predefines encoder compression levels.
// Only use the constants made available, since the actual mapping
// of these values are very likely to change and your compression could change
// unpredictably when upgrading the library.
type EncoderLevel int

const (
	speedNotSet EncoderLevel = iota

	// SpeedFastest will choose the fastest reasonable compression.
	// This is roughly equivalent to the fastest Zstandard mode.
	SpeedFastest

	// SpeedDefault is the default "pretty fast" compression option.
	// This is roughly equivalent to the default Zstandard mode (level 3).
	SpeedDefault

	// SpeedBetterCompression will yield better compression than the default.
	// Currently it is about zstd level 7-8 with ~ 2x-3x the default CPU usage.
	// By using this, notice that CPU usage may go up in the future.
	SpeedBetterCompression

	// SpeedBestCompression will choose the best available compression option.
	// This will offer the best compression no matter the CPU cost.
	SpeedBestCompression

	// speedLast should be kept as the last actual compression option.
	// The is not for external usage, but is used to keep track of the valid options.
	speedLast
)

// EncoderLevelFromString will convert a string representation of an encoding level back
// to a compression level. The compare is not case sensitive.
// If the string wasn't recognized, (false, SpeedDefault) will be returned.
func EncoderLevelFromString(s string) (bool, EncoderLevel) {
	for l := speedNotSet + 1; l < speedLast; l++ {
		if strings.EqualFold(s, l.String()) {
			return true, l
		}
	}
	return false, SpeedDefault
}

// EncoderLevelFromZstd will return an encoder level that closest matches the compression
// ratio of a specific zstd compression level.
// Many input values will provide the same compression level.
func EncoderLevelFromZstd(level int) EncoderLevel {
	switch {
	case level < 3:
		return SpeedFastest
	case level >= 3 && level < 6:
		return SpeedDefault
	case level >= 6 && level < 10:
		return SpeedBetterCompression
	case level >= 10:
		return SpeedBetterCompression
	}
	return SpeedDefault
}

// String provides a string representation of the compression level.
func (e EncoderLevel) String() string {
	switch e {
	case SpeedFastest:
		return "fastest"
	case SpeedDefault:
		return "default"
	case SpeedBetterCompression:
		return "better"
	case SpeedBestCompression:
		return "best"
	default:
		return "invalid"
	}
}

// WithEncoderLevel specifies a predefined compression level.
func WithEncoderLevel(l EncoderLevel) EOption {
	return func(o *encoderOptions) error {
		switch {
		case l <= speedNotSet || l >= speedLast:
			return fmt.Errorf("unknown encoder level")
		}
		o.level = l
		if !o.customWindow {
			switch o.level {
			case SpeedFastest:
				o.windowSize = 4 << 20
			case SpeedDefault:
				o.windowSize = 8 << 20
			case SpeedBetterCompression:
				o.windowSize = 16 << 20
			case SpeedBestCompression:
				o.windowSize = 32 << 20
			}
		}
		if !o.customALEntropy {
			o.allLitEntropy = l > SpeedFastest
		}

		return nil
	}
}

// WithZeroFrames will encode 0 length input as full frames.
// This can be needed for compatibility with zstandard usage,
// but is not needed for this package.
func WithZeroFrames(b bool) EOption {
	return func(o *encoderOptions) error {
		o.fullZero = b
		return nil
	}
}

// WithAllLitEntropyCompression will apply entropy compression if no matches are found.
// Disabling this will skip incompressible data faster, but in cases with no matches but
// skewed character distribution compression is lost.
// Default value depends on the compression level selected.
func WithAllLitEntropyCompression(b bool) EOption {
	return func(o *encoderOptions) error {
		o.customALEntropy = true
		o.allLitEntropy = b
		return nil
	}
}

// WithNoEntropyCompression will always skip entropy compression of literals.
// This can be useful if content has matches, but unlikely to benefit from entropy
// compression. Usually the slight speed improvement is not worth enabling this.
func WithNoEntropyCompression(b bool) EOption {
	return func(o *encoderOptions) error {
		o.noEntropy = b
		return nil
	}
}

// WithSingleSegment will set the "single segment" flag when EncodeAll is used.
// If this flag is set, data must be regenerated within a single continuous memory segment.
// In this case, Window_Descriptor byte is skipped, but Frame_Content_Size is necessarily present.
// As a consequence, the decoder must allocate a memory segment of size equal or larger than size of your content.
// In order to preserve the decoder from unreasonable memory requirements,
// a decoder is allowed to reject a compressed frame which requests a memory size beyond decoder's authorized range.
// For broader compatibility, decoders are recommended to support memory sizes of at least 8 MB.
// This is only a recommendation, each decoder is free to support higher or lower limits, depending on local limitations.
// If this is not specified, block encodes will automatically choose this based on the input size.
// This setting has no effect on streamed encodes.
func WithSingleSegment(b bool) EOption {
	return func(o *encoderOptions) error {
		o.single = &b
		return nil
	}
}

// WithLowerEncoderMem will trade in some memory cases trade less memory usage for
// slower encoding speed.
// This will not change the window size which is the primary function for reducing
// memory usage. See WithWindowSize.
func WithLowerEncoderMem(b bool) EOption {
	return func(o *encoderOptions) error {
		o.lowMem = b
		return nil
	}
}

// WithEncoderDict allows to register a dictionary that will be used for the encode.
// The encoder *may* choose to use no dictionary instead for certain payloads.
func WithEncoderDict(dict []byte) EOption {
	return func(o *encoderOptions) error {
		d, err := loadDict(dict)
		if err != nil {
			return err
		}
		o.dict = d
		return nil
	}
}