aboutsummaryrefslogtreecommitdiff
path: root/vendor/github.com/klauspost/compress/zstd/encoder_options.go
blob: 44d8dbd199a61b2dcfe37c2769a0aa644613582d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
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
	customBlockSize bool
	lowMem          bool
	dict            *dict
}

func (o *encoderOptions) setDefault() {
	*o = encoderOptions{
		concurrent:    runtime.GOMAXPROCS(0),
		crc:           true,
		single:        nil,
		blockSize:     maxCompressedBlockSize,
		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.
// For streams, setting a value of 1 will disable async compression.
// 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
			o.customBlockSize = true
		}
		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
	default:
		return SpeedBestCompression
	}
}

// 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
				if !o.customBlockSize {
					o.blockSize = 1 << 16
				}
			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
	}
}