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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437
|
// Copyright 2011 The Snappy-Go Authors. All rights reserved.
// Copyright (c) 2019 Klaus Post. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package s2
import (
"encoding/binary"
"errors"
"fmt"
"strconv"
)
var (
// ErrCorrupt reports that the input is invalid.
ErrCorrupt = errors.New("s2: corrupt input")
// ErrCRC reports that the input failed CRC validation (streams only)
ErrCRC = errors.New("s2: corrupt input, crc mismatch")
// ErrTooLarge reports that the uncompressed length is too large.
ErrTooLarge = errors.New("s2: decoded block is too large")
// ErrUnsupported reports that the input isn't supported.
ErrUnsupported = errors.New("s2: unsupported input")
)
// DecodedLen returns the length of the decoded block.
func DecodedLen(src []byte) (int, error) {
v, _, err := decodedLen(src)
return v, err
}
// decodedLen returns the length of the decoded block and the number of bytes
// that the length header occupied.
func decodedLen(src []byte) (blockLen, headerLen int, err error) {
v, n := binary.Uvarint(src)
if n <= 0 || v > 0xffffffff {
return 0, 0, ErrCorrupt
}
const wordSize = 32 << (^uint(0) >> 32 & 1)
if wordSize == 32 && v > 0x7fffffff {
return 0, 0, ErrTooLarge
}
return int(v), n, nil
}
const (
decodeErrCodeCorrupt = 1
)
// Decode returns the decoded form of src. The returned slice may be a sub-
// slice of dst if dst was large enough to hold the entire decoded block.
// Otherwise, a newly allocated slice will be returned.
//
// The dst and src must not overlap. It is valid to pass a nil dst.
func Decode(dst, src []byte) ([]byte, error) {
dLen, s, err := decodedLen(src)
if err != nil {
return nil, err
}
if dLen <= cap(dst) {
dst = dst[:dLen]
} else {
dst = make([]byte, dLen)
}
if s2Decode(dst, src[s:]) != 0 {
return nil, ErrCorrupt
}
return dst, nil
}
// s2DecodeDict writes the decoding of src to dst. It assumes that the varint-encoded
// length of the decompressed bytes has already been read, and that len(dst)
// equals that length.
//
// It returns 0 on success or a decodeErrCodeXxx error code on failure.
func s2DecodeDict(dst, src []byte, dict *Dict) int {
if dict == nil {
return s2Decode(dst, src)
}
const debug = false
const debugErrs = debug
if debug {
fmt.Println("Starting decode, dst len:", len(dst))
}
var d, s, length int
offset := len(dict.dict) - dict.repeat
// As long as we can read at least 5 bytes...
for s < len(src)-5 {
// Removing bounds checks is SLOWER, when if doing
// in := src[s:s+5]
// Checked on Go 1.18
switch src[s] & 0x03 {
case tagLiteral:
x := uint32(src[s] >> 2)
switch {
case x < 60:
s++
case x == 60:
s += 2
x = uint32(src[s-1])
case x == 61:
in := src[s : s+3]
x = uint32(in[1]) | uint32(in[2])<<8
s += 3
case x == 62:
in := src[s : s+4]
// Load as 32 bit and shift down.
x = uint32(in[0]) | uint32(in[1])<<8 | uint32(in[2])<<16 | uint32(in[3])<<24
x >>= 8
s += 4
case x == 63:
in := src[s : s+5]
x = uint32(in[1]) | uint32(in[2])<<8 | uint32(in[3])<<16 | uint32(in[4])<<24
s += 5
}
length = int(x) + 1
if debug {
fmt.Println("literals, length:", length, "d-after:", d+length)
}
if length > len(dst)-d || length > len(src)-s || (strconv.IntSize == 32 && length <= 0) {
if debugErrs {
fmt.Println("corrupt literal: length:", length, "d-left:", len(dst)-d, "src-left:", len(src)-s)
}
return decodeErrCodeCorrupt
}
copy(dst[d:], src[s:s+length])
d += length
s += length
continue
case tagCopy1:
s += 2
toffset := int(uint32(src[s-2])&0xe0<<3 | uint32(src[s-1]))
length = int(src[s-2]) >> 2 & 0x7
if toffset == 0 {
if debug {
fmt.Print("(repeat) ")
}
// keep last offset
switch length {
case 5:
length = int(src[s]) + 4
s += 1
case 6:
in := src[s : s+2]
length = int(uint32(in[0])|(uint32(in[1])<<8)) + (1 << 8)
s += 2
case 7:
in := src[s : s+3]
length = int((uint32(in[2])<<16)|(uint32(in[1])<<8)|uint32(in[0])) + (1 << 16)
s += 3
default: // 0-> 4
}
} else {
offset = toffset
}
length += 4
case tagCopy2:
in := src[s : s+3]
offset = int(uint32(in[1]) | uint32(in[2])<<8)
length = 1 + int(in[0])>>2
s += 3
case tagCopy4:
in := src[s : s+5]
offset = int(uint32(in[1]) | uint32(in[2])<<8 | uint32(in[3])<<16 | uint32(in[4])<<24)
length = 1 + int(in[0])>>2
s += 5
}
if offset <= 0 || length > len(dst)-d {
if debugErrs {
fmt.Println("match error; offset:", offset, "length:", length, "dst-left:", len(dst)-d)
}
return decodeErrCodeCorrupt
}
// copy from dict
if d < offset {
if d > MaxDictSrcOffset {
if debugErrs {
fmt.Println("dict after", MaxDictSrcOffset, "d:", d, "offset:", offset, "length:", length)
}
return decodeErrCodeCorrupt
}
startOff := len(dict.dict) - offset + d
if startOff < 0 || startOff+length > len(dict.dict) {
if debugErrs {
fmt.Printf("offset (%d) + length (%d) bigger than dict (%d)\n", offset, length, len(dict.dict))
}
return decodeErrCodeCorrupt
}
if debug {
fmt.Println("dict copy, length:", length, "offset:", offset, "d-after:", d+length, "dict start offset:", startOff)
}
copy(dst[d:d+length], dict.dict[startOff:])
d += length
continue
}
if debug {
fmt.Println("copy, length:", length, "offset:", offset, "d-after:", d+length)
}
// Copy from an earlier sub-slice of dst to a later sub-slice.
// If no overlap, use the built-in copy:
if offset > length {
copy(dst[d:d+length], dst[d-offset:])
d += length
continue
}
// Unlike the built-in copy function, this byte-by-byte copy always runs
// forwards, even if the slices overlap. Conceptually, this is:
//
// d += forwardCopy(dst[d:d+length], dst[d-offset:])
//
// We align the slices into a and b and show the compiler they are the same size.
// This allows the loop to run without bounds checks.
a := dst[d : d+length]
b := dst[d-offset:]
b = b[:len(a)]
for i := range a {
a[i] = b[i]
}
d += length
}
// Remaining with extra checks...
for s < len(src) {
switch src[s] & 0x03 {
case tagLiteral:
x := uint32(src[s] >> 2)
switch {
case x < 60:
s++
case x == 60:
s += 2
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
if debugErrs {
fmt.Println("src went oob")
}
return decodeErrCodeCorrupt
}
x = uint32(src[s-1])
case x == 61:
s += 3
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
if debugErrs {
fmt.Println("src went oob")
}
return decodeErrCodeCorrupt
}
x = uint32(src[s-2]) | uint32(src[s-1])<<8
case x == 62:
s += 4
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
if debugErrs {
fmt.Println("src went oob")
}
return decodeErrCodeCorrupt
}
x = uint32(src[s-3]) | uint32(src[s-2])<<8 | uint32(src[s-1])<<16
case x == 63:
s += 5
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
if debugErrs {
fmt.Println("src went oob")
}
return decodeErrCodeCorrupt
}
x = uint32(src[s-4]) | uint32(src[s-3])<<8 | uint32(src[s-2])<<16 | uint32(src[s-1])<<24
}
length = int(x) + 1
if length > len(dst)-d || length > len(src)-s || (strconv.IntSize == 32 && length <= 0) {
if debugErrs {
fmt.Println("corrupt literal: length:", length, "d-left:", len(dst)-d, "src-left:", len(src)-s)
}
return decodeErrCodeCorrupt
}
if debug {
fmt.Println("literals, length:", length, "d-after:", d+length)
}
copy(dst[d:], src[s:s+length])
d += length
s += length
continue
case tagCopy1:
s += 2
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
if debugErrs {
fmt.Println("src went oob")
}
return decodeErrCodeCorrupt
}
length = int(src[s-2]) >> 2 & 0x7
toffset := int(uint32(src[s-2])&0xe0<<3 | uint32(src[s-1]))
if toffset == 0 {
if debug {
fmt.Print("(repeat) ")
}
// keep last offset
switch length {
case 5:
s += 1
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
if debugErrs {
fmt.Println("src went oob")
}
return decodeErrCodeCorrupt
}
length = int(uint32(src[s-1])) + 4
case 6:
s += 2
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
if debugErrs {
fmt.Println("src went oob")
}
return decodeErrCodeCorrupt
}
length = int(uint32(src[s-2])|(uint32(src[s-1])<<8)) + (1 << 8)
case 7:
s += 3
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
if debugErrs {
fmt.Println("src went oob")
}
return decodeErrCodeCorrupt
}
length = int(uint32(src[s-3])|(uint32(src[s-2])<<8)|(uint32(src[s-1])<<16)) + (1 << 16)
default: // 0-> 4
}
} else {
offset = toffset
}
length += 4
case tagCopy2:
s += 3
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
if debugErrs {
fmt.Println("src went oob")
}
return decodeErrCodeCorrupt
}
length = 1 + int(src[s-3])>>2
offset = int(uint32(src[s-2]) | uint32(src[s-1])<<8)
case tagCopy4:
s += 5
if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
if debugErrs {
fmt.Println("src went oob")
}
return decodeErrCodeCorrupt
}
length = 1 + int(src[s-5])>>2
offset = int(uint32(src[s-4]) | uint32(src[s-3])<<8 | uint32(src[s-2])<<16 | uint32(src[s-1])<<24)
}
if offset <= 0 || length > len(dst)-d {
if debugErrs {
fmt.Println("match error; offset:", offset, "length:", length, "dst-left:", len(dst)-d)
}
return decodeErrCodeCorrupt
}
// copy from dict
if d < offset {
if d > MaxDictSrcOffset {
if debugErrs {
fmt.Println("dict after", MaxDictSrcOffset, "d:", d, "offset:", offset, "length:", length)
}
return decodeErrCodeCorrupt
}
rOff := len(dict.dict) - (offset - d)
if debug {
fmt.Println("starting dict entry from dict offset", len(dict.dict)-rOff)
}
if rOff+length > len(dict.dict) {
if debugErrs {
fmt.Println("err: END offset", rOff+length, "bigger than dict", len(dict.dict), "dict offset:", rOff, "length:", length)
}
return decodeErrCodeCorrupt
}
if rOff < 0 {
if debugErrs {
fmt.Println("err: START offset", rOff, "less than 0", len(dict.dict), "dict offset:", rOff, "length:", length)
}
return decodeErrCodeCorrupt
}
copy(dst[d:d+length], dict.dict[rOff:])
d += length
continue
}
if debug {
fmt.Println("copy, length:", length, "offset:", offset, "d-after:", d+length)
}
// Copy from an earlier sub-slice of dst to a later sub-slice.
// If no overlap, use the built-in copy:
if offset > length {
copy(dst[d:d+length], dst[d-offset:])
d += length
continue
}
// Unlike the built-in copy function, this byte-by-byte copy always runs
// forwards, even if the slices overlap. Conceptually, this is:
//
// d += forwardCopy(dst[d:d+length], dst[d-offset:])
//
// We align the slices into a and b and show the compiler they are the same size.
// This allows the loop to run without bounds checks.
a := dst[d : d+length]
b := dst[d-offset:]
b = b[:len(a)]
for i := range a {
a[i] = b[i]
}
d += length
}
if d != len(dst) {
if debugErrs {
fmt.Println("wanted length", len(dst), "got", d)
}
return decodeErrCodeCorrupt
}
return 0
}
|