2019-07-23 16:26:39 +00:00
|
|
|
// Package zstd provides decompression of zstandard files.
|
|
|
|
//
|
|
|
|
// For advanced usage and examples, go to the README: https://github.com/klauspost/compress/tree/master/zstd#zstd
|
|
|
|
package zstd
|
|
|
|
|
|
|
|
import (
|
2021-02-01 17:39:00 +00:00
|
|
|
"bytes"
|
2021-04-14 11:20:56 +00:00
|
|
|
"encoding/binary"
|
2019-07-23 16:26:39 +00:00
|
|
|
"errors"
|
|
|
|
"log"
|
2020-02-26 18:45:19 +00:00
|
|
|
"math"
|
2019-07-23 16:26:39 +00:00
|
|
|
"math/bits"
|
|
|
|
)
|
|
|
|
|
2020-02-26 18:45:19 +00:00
|
|
|
// enable debug printing
|
2019-07-23 16:26:39 +00:00
|
|
|
const debug = false
|
2020-02-26 18:45:19 +00:00
|
|
|
|
2021-06-08 12:42:57 +00:00
|
|
|
// enable encoding debug printing
|
|
|
|
const debugEncoder = debug
|
|
|
|
|
|
|
|
// enable decoding debug printing
|
|
|
|
const debugDecoder = debug
|
|
|
|
|
2020-02-26 18:45:19 +00:00
|
|
|
// Enable extra assertions.
|
|
|
|
const debugAsserts = debug || false
|
|
|
|
|
|
|
|
// print sequence details
|
2019-07-23 16:26:39 +00:00
|
|
|
const debugSequences = false
|
2020-02-26 18:45:19 +00:00
|
|
|
|
|
|
|
// print detailed matching information
|
2019-10-28 11:36:35 +00:00
|
|
|
const debugMatches = false
|
2019-07-23 16:26:39 +00:00
|
|
|
|
|
|
|
// force encoder to use predefined tables.
|
|
|
|
const forcePreDef = false
|
|
|
|
|
|
|
|
// zstdMinMatch is the minimum zstd match length.
|
|
|
|
const zstdMinMatch = 3
|
|
|
|
|
2022-03-16 11:55:03 +00:00
|
|
|
// fcsUnknown is used for unknown frame content size.
|
|
|
|
const fcsUnknown = math.MaxUint64
|
|
|
|
|
2019-07-23 16:26:39 +00:00
|
|
|
var (
|
|
|
|
// ErrReservedBlockType is returned when a reserved block type is found.
|
|
|
|
// Typically this indicates wrong or corrupted input.
|
|
|
|
ErrReservedBlockType = errors.New("invalid input: reserved block type encountered")
|
|
|
|
|
|
|
|
// ErrCompressedSizeTooBig is returned when a block is bigger than allowed.
|
|
|
|
// Typically this indicates wrong or corrupted input.
|
|
|
|
ErrCompressedSizeTooBig = errors.New("invalid input: compressed size too big")
|
|
|
|
|
|
|
|
// ErrBlockTooSmall is returned when a block is too small to be decoded.
|
|
|
|
// Typically returned on invalid input.
|
|
|
|
ErrBlockTooSmall = errors.New("block too small")
|
|
|
|
|
2022-03-16 11:55:03 +00:00
|
|
|
// ErrUnexpectedBlockSize is returned when a block has unexpected size.
|
|
|
|
// Typically returned on invalid input.
|
|
|
|
ErrUnexpectedBlockSize = errors.New("unexpected block size")
|
|
|
|
|
2019-07-23 16:26:39 +00:00
|
|
|
// ErrMagicMismatch is returned when a "magic" number isn't what is expected.
|
|
|
|
// Typically this indicates wrong or corrupted input.
|
|
|
|
ErrMagicMismatch = errors.New("invalid input: magic number mismatch")
|
|
|
|
|
|
|
|
// ErrWindowSizeExceeded is returned when a reference exceeds the valid window size.
|
|
|
|
// Typically this indicates wrong or corrupted input.
|
|
|
|
ErrWindowSizeExceeded = errors.New("window size exceeded")
|
|
|
|
|
|
|
|
// ErrWindowSizeTooSmall is returned when no window size is specified.
|
|
|
|
// Typically this indicates wrong or corrupted input.
|
|
|
|
ErrWindowSizeTooSmall = errors.New("invalid input: window size was too small")
|
|
|
|
|
|
|
|
// ErrDecoderSizeExceeded is returned if decompressed size exceeds the configured limit.
|
|
|
|
ErrDecoderSizeExceeded = errors.New("decompressed size exceeds configured limit")
|
|
|
|
|
|
|
|
// ErrUnknownDictionary is returned if the dictionary ID is unknown.
|
|
|
|
ErrUnknownDictionary = errors.New("unknown dictionary")
|
|
|
|
|
|
|
|
// ErrFrameSizeExceeded is returned if the stated frame size is exceeded.
|
|
|
|
// This is only returned if SingleSegment is specified on the frame.
|
|
|
|
ErrFrameSizeExceeded = errors.New("frame size exceeded")
|
|
|
|
|
2022-03-16 11:55:03 +00:00
|
|
|
// ErrFrameSizeMismatch is returned if the stated frame size does not match the expected size.
|
|
|
|
// This is only returned if SingleSegment is specified on the frame.
|
|
|
|
ErrFrameSizeMismatch = errors.New("frame size does not match size on stream")
|
|
|
|
|
2019-07-23 16:26:39 +00:00
|
|
|
// ErrCRCMismatch is returned if CRC mismatches.
|
|
|
|
ErrCRCMismatch = errors.New("CRC check failed")
|
|
|
|
|
|
|
|
// ErrDecoderClosed will be returned if the Decoder was used after
|
|
|
|
// Close has been called.
|
|
|
|
ErrDecoderClosed = errors.New("decoder used after Close")
|
2021-01-07 21:55:02 +00:00
|
|
|
|
|
|
|
// ErrDecoderNilInput is returned when a nil Reader was provided
|
|
|
|
// and an operation other than Reset/DecodeAll/Close was attempted.
|
|
|
|
ErrDecoderNilInput = errors.New("nil input provided as reader")
|
2019-07-23 16:26:39 +00:00
|
|
|
)
|
|
|
|
|
|
|
|
func println(a ...interface{}) {
|
2021-06-08 12:42:57 +00:00
|
|
|
if debug || debugDecoder || debugEncoder {
|
2019-07-23 16:26:39 +00:00
|
|
|
log.Println(a...)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
func printf(format string, a ...interface{}) {
|
2021-06-08 12:42:57 +00:00
|
|
|
if debug || debugDecoder || debugEncoder {
|
2019-07-23 16:26:39 +00:00
|
|
|
log.Printf(format, a...)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2023-01-11 03:57:37 +00:00
|
|
|
// matchLen returns the maximum common prefix length of a and b.
|
2019-07-23 16:26:39 +00:00
|
|
|
// a must be the shortest of the two.
|
2023-01-11 03:57:37 +00:00
|
|
|
func matchLen(a, b []byte) (n int) {
|
|
|
|
for ; len(a) >= 8 && len(b) >= 8; a, b = a[8:], b[8:] {
|
|
|
|
diff := binary.LittleEndian.Uint64(a) ^ binary.LittleEndian.Uint64(b)
|
|
|
|
if diff != 0 {
|
|
|
|
return n + bits.TrailingZeros64(diff)>>3
|
2019-07-23 16:26:39 +00:00
|
|
|
}
|
2023-01-11 03:57:37 +00:00
|
|
|
n += 8
|
2019-07-23 16:26:39 +00:00
|
|
|
}
|
2020-03-12 15:32:07 +00:00
|
|
|
|
2019-07-23 16:26:39 +00:00
|
|
|
for i := range a {
|
|
|
|
if a[i] != b[i] {
|
2023-01-11 03:57:37 +00:00
|
|
|
break
|
2019-07-23 16:26:39 +00:00
|
|
|
}
|
2023-01-11 03:57:37 +00:00
|
|
|
n++
|
2019-07-23 16:26:39 +00:00
|
|
|
}
|
2023-01-11 03:57:37 +00:00
|
|
|
return n
|
|
|
|
|
2019-07-23 16:26:39 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
func load3232(b []byte, i int32) uint32 {
|
2021-04-14 11:20:56 +00:00
|
|
|
return binary.LittleEndian.Uint32(b[i:])
|
2019-07-23 16:26:39 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
func load6432(b []byte, i int32) uint64 {
|
2021-04-14 11:20:56 +00:00
|
|
|
return binary.LittleEndian.Uint64(b[i:])
|
2019-07-23 16:26:39 +00:00
|
|
|
}
|
|
|
|
|
2021-02-01 17:39:00 +00:00
|
|
|
type byter interface {
|
|
|
|
Bytes() []byte
|
|
|
|
Len() int
|
|
|
|
}
|
|
|
|
|
|
|
|
var _ byter = &bytes.Buffer{}
|