admin/kubesphere
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: kubesphere 4.0 (#6115)

Browse Source 
* feat: kubesphere 4.0

Signed-off-by: ci-bot <ci-bot@kubesphere.io>

* feat: kubesphere 4.0

Signed-off-by: ci-bot <ci-bot@kubesphere.io>

---------

Signed-off-by: ci-bot <ci-bot@kubesphere.io>
Co-authored-by: ks-ci-bot <ks-ci-bot@example.com>
Co-authored-by: joyceliu <joyceliu@yunify.com>
This commit is contained in:
KubeSphere CI Bot
2024-09-06 11:05:52 +08:00
committed by GitHub
parent b5015ec7b9
commit 447a51f08b
8557 changed files with 546695 additions and 1146174 deletions
Download Patch File Download Diff File Expand all files Collapse all files

130
vendor/github.com/klauspost/compress/huff0/bitreader.go generated vendored
View File

@@ -8,115 +8,10 @@ package huff0
import (
"encoding/binary"
"errors"
"fmt"
"io"
)
// bitReader reads a bitstream in reverse.
// The last set bit indicates the start of the stream and is used
// for aligning the input.
type bitReader struct {
in []byte
off uint // next byte to read is at in[off - 1]
value uint64
bitsRead uint8
}
// init initializes and resets the bit reader.
func (b *bitReader) init(in []byte) error {
if len(in) < 1 {
return errors.New("corrupt stream: too short")
}
b.in = in
b.off = uint(len(in))
// The highest bit of the last byte indicates where to start
v := in[len(in)-1]
if v == 0 {
return errors.New("corrupt stream, did not find end of stream")
}
b.bitsRead = 64
b.value = 0
if len(in) >= 8 {
b.fillFastStart()
} else {
b.fill()
b.fill()
}
b.bitsRead += 8 - uint8(highBit32(uint32(v)))
return nil
}
// peekBitsFast requires that at least one bit is requested every time.
// There are no checks if the buffer is filled.
func (b *bitReader) peekBitsFast(n uint8) uint16 {
const regMask = 64 - 1
v := uint16((b.value << (b.bitsRead & regMask)) >> ((regMask + 1 - n) & regMask))
return v
}
// fillFast() will make sure at least 32 bits are available.
// There must be at least 4 bytes available.
func (b *bitReader) fillFast() {
if b.bitsRead < 32 {
return
}
// 2 bounds checks.
v := b.in[b.off-4 : b.off]
v = v[:4]
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
b.value = (b.value << 32) | uint64(low)
b.bitsRead -= 32
b.off -= 4
}
func (b *bitReader) advance(n uint8) {
b.bitsRead += n
}
// fillFastStart() assumes the bitreader is empty and there is at least 8 bytes to read.
func (b *bitReader) fillFastStart() {
// Do single re-slice to avoid bounds checks.
b.value = binary.LittleEndian.Uint64(b.in[b.off-8:])
b.bitsRead = 0
b.off -= 8
}
// fill() will make sure at least 32 bits are available.
func (b *bitReader) fill() {
if b.bitsRead < 32 {
return
}
if b.off > 4 {
v := b.in[b.off-4:]
v = v[:4]
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
b.value = (b.value << 32) | uint64(low)
b.bitsRead -= 32
b.off -= 4
return
}
for b.off > 0 {
b.value = (b.value << 8) | uint64(b.in[b.off-1])
b.bitsRead -= 8
b.off--
}
}
// finished returns true if all bits have been read from the bit stream.
func (b *bitReader) finished() bool {
return b.off == 0 && b.bitsRead >= 64
}
// close the bitstream and returns an error if out-of-buffer reads occurred.
func (b *bitReader) close() error {
// Release reference.
b.in = nil
if b.bitsRead > 64 {
return io.ErrUnexpectedEOF
}
return nil
}
// bitReader reads a bitstream in reverse.
// The last set bit indicates the start of the stream and is used
// for aligning the input.
@@ -172,7 +67,6 @@ func (b *bitReaderBytes) fillFast() {
// 2 bounds checks.
v := b.in[b.off-4 : b.off]
v = v[:4]
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
b.value |= uint64(low) << (b.bitsRead - 32)
b.bitsRead -= 32
@@ -193,8 +87,7 @@ func (b *bitReaderBytes) fill() {
return
}
if b.off > 4 {
v := b.in[b.off-4:]
v = v[:4]
v := b.in[b.off-4 : b.off]
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
b.value |= uint64(low) << (b.bitsRead - 32)
b.bitsRead -= 32
@@ -213,10 +106,17 @@ func (b *bitReaderBytes) finished() bool {
return b.off == 0 && b.bitsRead >= 64
}
func (b *bitReaderBytes) remaining() uint {
return b.off*8 + uint(64-b.bitsRead)
}
// close the bitstream and returns an error if out-of-buffer reads occurred.
func (b *bitReaderBytes) close() error {
// Release reference.
b.in = nil
if b.remaining() > 0 {
return fmt.Errorf("corrupt input: %d bits remain on stream", b.remaining())
}
if b.bitsRead > 64 {
return io.ErrUnexpectedEOF
}
@@ -277,7 +177,6 @@ func (b *bitReaderShifted) fillFast() {
// 2 bounds checks.
v := b.in[b.off-4 : b.off]
v = v[:4]
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
b.value |= uint64(low) << ((b.bitsRead - 32) & 63)
b.bitsRead -= 32
@@ -298,8 +197,7 @@ func (b *bitReaderShifted) fill() {
return
}
if b.off > 4 {
v := b.in[b.off-4:]
v = v[:4]
v := b.in[b.off-4 : b.off]
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
b.value |= uint64(low) << ((b.bitsRead - 32) & 63)
b.bitsRead -= 32
@@ -313,15 +211,17 @@ func (b *bitReaderShifted) fill() {
}
}
// finished returns true if all bits have been read from the bit stream.
func (b *bitReaderShifted) finished() bool {
return b.off == 0 && b.bitsRead >= 64
func (b *bitReaderShifted) remaining() uint {
return b.off*8 + uint(64-b.bitsRead)
}
// close the bitstream and returns an error if out-of-buffer reads occurred.
func (b *bitReaderShifted) close() error {
// Release reference.
b.in = nil
if b.remaining() > 0 {
return fmt.Errorf("corrupt input: %d bits remain on stream", b.remaining())
}
if b.bitsRead > 64 {
return io.ErrUnexpectedEOF
}

136
vendor/github.com/klauspost/compress/huff0/bitwriter.go generated vendored
View File

@@ -5,8 +5,6 @@
package huff0
import "fmt"
// bitWriter will write bits.
// First bit will be LSB of the first byte of output.
type bitWriter struct {
@@ -15,22 +13,6 @@ type bitWriter struct {
out []byte
}
// bitMask16 is bitmasks. Has extra to avoid bounds check.
var bitMask16 = [32]uint16{
0, 1, 3, 7, 0xF, 0x1F,
0x3F, 0x7F, 0xFF, 0x1FF, 0x3FF, 0x7FF,
0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0xFFFF,
0xFFFF, 0xFFFF, 0xFFFF, 0xFFFF, 0xFFFF, 0xFFFF,
0xFFFF, 0xFFFF} /* up to 16 bits */
// addBits16NC will add up to 16 bits.
// It will not check if there is space for them,
// so the caller must ensure that it has flushed recently.
func (b *bitWriter) addBits16NC(value uint16, bits uint8) {
b.bitContainer |= uint64(value&bitMask16[bits&31]) << (b.nBits & 63)
b.nBits += bits
}
// addBits16Clean will add up to 16 bits. value may not contain more set bits than indicated.
// It will not check if there is space for them, so the caller must ensure that it has flushed recently.
func (b *bitWriter) addBits16Clean(value uint16, bits uint8) {
@@ -70,102 +52,20 @@ func (b *bitWriter) encTwoSymbols(ct cTable, av, bv byte) {
b.nBits += encA.nBits + encB.nBits
}
// addBits16ZeroNC will add up to 16 bits.
// encFourSymbols adds up to 32 bits from four symbols.
// It will not check if there is space for them,
// so the caller must ensure that it has flushed recently.
// This is fastest if bits can be zero.
func (b *bitWriter) addBits16ZeroNC(value uint16, bits uint8) {
if bits == 0 {
return
}
value <<= (16 - bits) & 15
value >>= (16 - bits) & 15
b.bitContainer |= uint64(value) << (b.nBits & 63)
b.nBits += bits
}
// flush will flush all pending full bytes.
// There will be at least 56 bits available for writing when this has been called.
// Using flush32 is faster, but leaves less space for writing.
func (b *bitWriter) flush() {
v := b.nBits >> 3
switch v {
case 0:
return
case 1:
b.out = append(b.out,
byte(b.bitContainer),
)
b.bitContainer >>= 1 << 3
case 2:
b.out = append(b.out,
byte(b.bitContainer),
byte(b.bitContainer>>8),
)
b.bitContainer >>= 2 << 3
case 3:
b.out = append(b.out,
byte(b.bitContainer),
byte(b.bitContainer>>8),
byte(b.bitContainer>>16),
)
b.bitContainer >>= 3 << 3
case 4:
b.out = append(b.out,
byte(b.bitContainer),
byte(b.bitContainer>>8),
byte(b.bitContainer>>16),
byte(b.bitContainer>>24),
)
b.bitContainer >>= 4 << 3
case 5:
b.out = append(b.out,
byte(b.bitContainer),
byte(b.bitContainer>>8),
byte(b.bitContainer>>16),
byte(b.bitContainer>>24),
byte(b.bitContainer>>32),
)
b.bitContainer >>= 5 << 3
case 6:
b.out = append(b.out,
byte(b.bitContainer),
byte(b.bitContainer>>8),
byte(b.bitContainer>>16),
byte(b.bitContainer>>24),
byte(b.bitContainer>>32),
byte(b.bitContainer>>40),
)
b.bitContainer >>= 6 << 3
case 7:
b.out = append(b.out,
byte(b.bitContainer),
byte(b.bitContainer>>8),
byte(b.bitContainer>>16),
byte(b.bitContainer>>24),
byte(b.bitContainer>>32),
byte(b.bitContainer>>40),
byte(b.bitContainer>>48),
)
b.bitContainer >>= 7 << 3
case 8:
b.out = append(b.out,
byte(b.bitContainer),
byte(b.bitContainer>>8),
byte(b.bitContainer>>16),
byte(b.bitContainer>>24),
byte(b.bitContainer>>32),
byte(b.bitContainer>>40),
byte(b.bitContainer>>48),
byte(b.bitContainer>>56),
)
b.bitContainer = 0
b.nBits = 0
return
default:
panic(fmt.Errorf("bits (%d) > 64", b.nBits))
}
b.nBits &= 7
// so the caller must ensure that b has been flushed recently.
func (b *bitWriter) encFourSymbols(encA, encB, encC, encD cTableEntry) {
bitsA := encA.nBits
bitsB := bitsA + encB.nBits
bitsC := bitsB + encC.nBits
bitsD := bitsC + encD.nBits
combined := uint64(encA.val) |
(uint64(encB.val) << (bitsA & 63)) |
(uint64(encC.val) << (bitsB & 63)) |
(uint64(encD.val) << (bitsC & 63))
b.bitContainer |= combined << (b.nBits & 63)
b.nBits += bitsD
}
// flush32 will flush out, so there are at least 32 bits available for writing.
@@ -194,17 +94,9 @@ func (b *bitWriter) flushAlign() {
// close will write the alignment bit and write the final byte(s)
// to the output.
func (b *bitWriter) close() error {
func (b *bitWriter) close() {
// End mark
b.addBits16Clean(1, 1)
// flush until next byte.
b.flushAlign()
return nil
}
// reset and continue writing by appending to out.
func (b *bitWriter) reset(out []byte) {
b.bitContainer = 0
b.nBits = 0
b.out = out
}

10
vendor/github.com/klauspost/compress/huff0/bytereader.go generated vendored
View File

@@ -20,11 +20,6 @@ func (b *byteReader) init(in []byte) {
b.off = 0
}
// advance the stream b n bytes.
func (b *byteReader) advance(n uint) {
b.off += int(n)
}
// Int32 returns a little endian int32 starting at current offset.
func (b byteReader) Int32() int32 {
v3 := int32(b.b[b.off+3])
@@ -43,11 +38,6 @@ func (b byteReader) Uint32() uint32 {
return (v3 << 24) | (v2 << 16) | (v1 << 8) | v0
}
// unread returns the unread portion of the input.
func (b byteReader) unread() []byte {
return b.b[b.off:]
}
// remain will return the number of bytes remaining.
func (b byteReader) remain() int {
return len(b.b) - b.off

145
vendor/github.com/klauspost/compress/huff0/compress.go generated vendored
View File

@@ -2,6 +2,7 @@ package huff0
import (
"fmt"
"math"
"runtime"
"sync"
)
@@ -226,10 +227,10 @@ func EstimateSizes(in []byte, s *Scratch) (tableSz, dataSz, reuseSz int, err err
}
func (s *Scratch) compress1X(src []byte) ([]byte, error) {
return s.compress1xDo(s.Out, src)
return s.compress1xDo(s.Out, src), nil
}
func (s *Scratch) compress1xDo(dst, src []byte) ([]byte, error) {
func (s *Scratch) compress1xDo(dst, src []byte) []byte {
var bw = bitWriter{out: dst}
// N is length divisible by 4.
@@ -247,8 +248,7 @@ func (s *Scratch) compress1xDo(dst, src []byte) ([]byte, error) {
tmp := src[n : n+4]
// tmp should be len 4
bw.flush32()
bw.encTwoSymbols(cTable, tmp[3], tmp[2])
bw.encTwoSymbols(cTable, tmp[1], tmp[0])
bw.encFourSymbols(cTable[tmp[3]], cTable[tmp[2]], cTable[tmp[1]], cTable[tmp[0]])
}
} else {
for ; n >= 0; n -= 4 {
@@ -260,8 +260,8 @@ func (s *Scratch) compress1xDo(dst, src []byte) ([]byte, error) {
bw.encTwoSymbols(cTable, tmp[1], tmp[0])
}
}
err := bw.close()
return bw.out, err
bw.close()
return bw.out
}
var sixZeros [6]byte
@@ -283,11 +283,11 @@ func (s *Scratch) compress4X(src []byte) ([]byte, error) {
}
src = src[len(toDo):]
var err error
idx := len(s.Out)
s.Out, err = s.compress1xDo(s.Out, toDo)
if err != nil {
return nil, err
s.Out = s.compress1xDo(s.Out, toDo)
if len(s.Out)-idx > math.MaxUint16 {
// We cannot store the size in the jump table
return nil, ErrIncompressible
}
// Write compressed length as little endian before block.
if i < 3 {
@@ -311,7 +311,6 @@ func (s *Scratch) compress4Xp(src []byte) ([]byte, error) {
segmentSize := (len(src) + 3) / 4
var wg sync.WaitGroup
var errs [4]error
wg.Add(4)
for i := 0; i < 4; i++ {
toDo := src
@@ -322,16 +321,17 @@ func (s *Scratch) compress4Xp(src []byte) ([]byte, error) {
// Separate goroutine for each block.
go func(i int) {
s.tmpOut[i], errs[i] = s.compress1xDo(s.tmpOut[i][:0], toDo)
s.tmpOut[i] = s.compress1xDo(s.tmpOut[i][:0], toDo)
wg.Done()
}(i)
}
wg.Wait()
for i := 0; i < 4; i++ {
if errs[i] != nil {
return nil, errs[i]
}
o := s.tmpOut[i]
if len(o) > math.MaxUint16 {
// We cannot store the size in the jump table
return nil, ErrIncompressible
}
// Write compressed length as little endian before block.
if i < 3 {
// Last length is not written.
@@ -356,29 +356,29 @@ func (s *Scratch) countSimple(in []byte) (max int, reuse bool) {
m := uint32(0)
if len(s.prevTable) > 0 {
for i, v := range s.count[:] {
if v == 0 {
continue
}
if v > m {
m = v
}
if v > 0 {
s.symbolLen = uint16(i) + 1
if i >= len(s.prevTable) {
reuse = false
} else {
if s.prevTable[i].nBits == 0 {
reuse = false
}
}
s.symbolLen = uint16(i) + 1
if i >= len(s.prevTable) {
reuse = false
} else if s.prevTable[i].nBits == 0 {
reuse = false
}
}
return int(m), reuse
}
for i, v := range s.count[:] {
if v == 0 {
continue
}
if v > m {
m = v
}
if v > 0 {
s.symbolLen = uint16(i) + 1
}
s.symbolLen = uint16(i) + 1
}
return int(m), false
}
@@ -395,6 +395,7 @@ func (s *Scratch) canUseTable(c cTable) bool {
return true
}
//lint:ignore U1000 used for debugging
func (s *Scratch) validateTable(c cTable) bool {
if len(c) < int(s.symbolLen) {
return false
@@ -474,34 +475,35 @@ func (s *Scratch) buildCTable() error {
// Different from reference implementation.
huffNode0 := s.nodes[0 : huffNodesLen+1]
for huffNode[nonNullRank].count == 0 {
for huffNode[nonNullRank].count() == 0 {
nonNullRank--
}
lowS := int16(nonNullRank)
nodeRoot := nodeNb + lowS - 1
lowN := nodeNb
huffNode[nodeNb].count = huffNode[lowS].count + huffNode[lowS-1].count
huffNode[lowS].parent, huffNode[lowS-1].parent = uint16(nodeNb), uint16(nodeNb)
huffNode[nodeNb].setCount(huffNode[lowS].count() + huffNode[lowS-1].count())
huffNode[lowS].setParent(nodeNb)
huffNode[lowS-1].setParent(nodeNb)
nodeNb++
lowS -= 2
for n := nodeNb; n <= nodeRoot; n++ {
huffNode[n].count = 1 << 30
huffNode[n].setCount(1 << 30)
}
// fake entry, strong barrier
huffNode0[0].count = 1 << 31
huffNode0[0].setCount(1 << 31)
// create parents
for nodeNb <= nodeRoot {
var n1, n2 int16
if huffNode0[lowS+1].count < huffNode0[lowN+1].count {
if huffNode0[lowS+1].count() < huffNode0[lowN+1].count() {
n1 = lowS
lowS--
} else {
n1 = lowN
lowN++
}
if huffNode0[lowS+1].count < huffNode0[lowN+1].count {
if huffNode0[lowS+1].count() < huffNode0[lowN+1].count() {
n2 = lowS
lowS--
} else {
@@ -509,18 +511,19 @@ func (s *Scratch) buildCTable() error {
lowN++
}
huffNode[nodeNb].count = huffNode0[n1+1].count + huffNode0[n2+1].count
huffNode0[n1+1].parent, huffNode0[n2+1].parent = uint16(nodeNb), uint16(nodeNb)
huffNode[nodeNb].setCount(huffNode0[n1+1].count() + huffNode0[n2+1].count())
huffNode0[n1+1].setParent(nodeNb)
huffNode0[n2+1].setParent(nodeNb)
nodeNb++
}
// distribute weights (unlimited tree height)
huffNode[nodeRoot].nbBits = 0
huffNode[nodeRoot].setNbBits(0)
for n := nodeRoot - 1; n >= startNode; n-- {
huffNode[n].nbBits = huffNode[huffNode[n].parent].nbBits + 1
huffNode[n].setNbBits(huffNode[huffNode[n].parent()].nbBits() + 1)
}
for n := uint16(0); n <= nonNullRank; n++ {
huffNode[n].nbBits = huffNode[huffNode[n].parent].nbBits + 1
huffNode[n].setNbBits(huffNode[huffNode[n].parent()].nbBits() + 1)
}
s.actualTableLog = s.setMaxHeight(int(nonNullRank))
maxNbBits := s.actualTableLog
@@ -532,7 +535,7 @@ func (s *Scratch) buildCTable() error {
var nbPerRank [tableLogMax + 1]uint16
var valPerRank [16]uint16
for _, v := range huffNode[:nonNullRank+1] {
nbPerRank[v.nbBits]++
nbPerRank[v.nbBits()]++
}
// determine stating value per rank
{
@@ -547,7 +550,7 @@ func (s *Scratch) buildCTable() error {
// push nbBits per symbol, symbol order
for _, v := range huffNode[:nonNullRank+1] {
s.cTable[v.symbol].nBits = v.nbBits
s.cTable[v.symbol()].nBits = v.nbBits()
}
// assign value within rank, symbol order
@@ -593,12 +596,12 @@ func (s *Scratch) huffSort() {
pos := rank[r].current
rank[r].current++
prev := nodes[(pos-1)&huffNodesMask]
for pos > rank[r].base && c > prev.count {
for pos > rank[r].base && c > prev.count() {
nodes[pos&huffNodesMask] = prev
pos--
prev = nodes[(pos-1)&huffNodesMask]
}
nodes[pos&huffNodesMask] = nodeElt{count: c, symbol: byte(n)}
nodes[pos&huffNodesMask] = makeNodeElt(c, byte(n))
}
}
@@ -607,7 +610,7 @@ func (s *Scratch) setMaxHeight(lastNonNull int) uint8 {
huffNode := s.nodes[1 : huffNodesLen+1]
//huffNode = huffNode[: huffNodesLen]
largestBits := huffNode[lastNonNull].nbBits
largestBits := huffNode[lastNonNull].nbBits()
// early exit : no elt > maxNbBits
if largestBits <= maxNbBits {
@@ -617,14 +620,14 @@ func (s *Scratch) setMaxHeight(lastNonNull int) uint8 {
baseCost := int(1) << (largestBits - maxNbBits)
n := uint32(lastNonNull)
for huffNode[n].nbBits > maxNbBits {
totalCost += baseCost - (1 << (largestBits - huffNode[n].nbBits))
huffNode[n].nbBits = maxNbBits
for huffNode[n].nbBits() > maxNbBits {
totalCost += baseCost - (1 << (largestBits - huffNode[n].nbBits()))
huffNode[n].setNbBits(maxNbBits)
n--
}
// n stops at huffNode[n].nbBits <= maxNbBits
for huffNode[n].nbBits == maxNbBits {
for huffNode[n].nbBits() == maxNbBits {
n--
}
// n end at index of smallest symbol using < maxNbBits
@@ -645,10 +648,10 @@ func (s *Scratch) setMaxHeight(lastNonNull int) uint8 {
{
currentNbBits := maxNbBits
for pos := int(n); pos >= 0; pos-- {
if huffNode[pos].nbBits >= currentNbBits {
if huffNode[pos].nbBits() >= currentNbBits {
continue
}
currentNbBits = huffNode[pos].nbBits // < maxNbBits
currentNbBits = huffNode[pos].nbBits() // < maxNbBits
rankLast[maxNbBits-currentNbBits] = uint32(pos)
}
}
@@ -665,8 +668,8 @@ func (s *Scratch) setMaxHeight(lastNonNull int) uint8 {
if lowPos == noSymbol {
break
}
highTotal := huffNode[highPos].count
lowTotal := 2 * huffNode[lowPos].count
highTotal := huffNode[highPos].count()
lowTotal := 2 * huffNode[lowPos].count()
if highTotal <= lowTotal {
break
}
@@ -682,13 +685,14 @@ func (s *Scratch) setMaxHeight(lastNonNull int) uint8 {
// this rank is no longer empty
rankLast[nBitsToDecrease-1] = rankLast[nBitsToDecrease]
}
huffNode[rankLast[nBitsToDecrease]].nbBits++
huffNode[rankLast[nBitsToDecrease]].setNbBits(1 +
huffNode[rankLast[nBitsToDecrease]].nbBits())
if rankLast[nBitsToDecrease] == 0 {
/* special case, reached largest symbol */
rankLast[nBitsToDecrease] = noSymbol
} else {
rankLast[nBitsToDecrease]--
if huffNode[rankLast[nBitsToDecrease]].nbBits != maxNbBits-nBitsToDecrease {
if huffNode[rankLast[nBitsToDecrease]].nbBits() != maxNbBits-nBitsToDecrease {
rankLast[nBitsToDecrease] = noSymbol /* this rank is now empty */
}
}
@@ -696,15 +700,15 @@ func (s *Scratch) setMaxHeight(lastNonNull int) uint8 {
for totalCost < 0 { /* Sometimes, cost correction overshoot */
if rankLast[1] == noSymbol { /* special case : no rank 1 symbol (using maxNbBits-1); let's create one from largest rank 0 (using maxNbBits) */
for huffNode[n].nbBits == maxNbBits {
for huffNode[n].nbBits() == maxNbBits {
n--
}
huffNode[n+1].nbBits--
huffNode[n+1].setNbBits(huffNode[n+1].nbBits() - 1)
rankLast[1] = n + 1
totalCost++
continue
}
huffNode[rankLast[1]+1].nbBits--
huffNode[rankLast[1]+1].setNbBits(huffNode[rankLast[1]+1].nbBits() - 1)
rankLast[1]++
totalCost++
}
@@ -712,9 +716,26 @@ func (s *Scratch) setMaxHeight(lastNonNull int) uint8 {
return maxNbBits
}
type nodeElt struct {
count uint32
parent uint16
symbol byte
nbBits uint8
// A nodeElt is the fields
//
// count uint32
// parent uint16
// symbol byte
// nbBits uint8
//
// in some order, all squashed into an integer so that the compiler
// always loads and stores entire nodeElts instead of separate fields.
type nodeElt uint64
func makeNodeElt(count uint32, symbol byte) nodeElt {
return nodeElt(count) | nodeElt(symbol)<<48
}
func (e *nodeElt) count() uint32 { return uint32(*e) }
func (e *nodeElt) parent() uint16 { return uint16(*e >> 32) }
func (e *nodeElt) symbol() byte { return byte(*e >> 48) }
func (e *nodeElt) nbBits() uint8 { return uint8(*e >> 56) }
func (e *nodeElt) setCount(c uint32) { *e = (*e)&0xffffffff00000000 | nodeElt(c) }
func (e *nodeElt) setParent(p int16) { *e = (*e)&0xffff0000ffffffff | nodeElt(uint16(p))<<32 }
func (e *nodeElt) setNbBits(n uint8) { *e = (*e)&0x00ffffffffffffff | nodeElt(n)<<56 }

712
vendor/github.com/klauspost/compress/huff0/decompress.go generated vendored
View File

File diff suppressed because it is too large Load Diff

226
vendor/github.com/klauspost/compress/huff0/decompress_amd64.go generated vendored Normal file
View File

@@ -0,0 +1,226 @@
//go:build amd64 && !appengine && !noasm && gc
// +build amd64,!appengine,!noasm,gc
// This file contains the specialisation of Decoder.Decompress4X
// and Decoder.Decompress1X that use an asm implementation of thir main loops.
package huff0
import (
"errors"
"fmt"
"github.com/klauspost/compress/internal/cpuinfo"
)
// decompress4x_main_loop_x86 is an x86 assembler implementation
// of Decompress4X when tablelog > 8.
//
//go:noescape
func decompress4x_main_loop_amd64(ctx *decompress4xContext)
// decompress4x_8b_loop_x86 is an x86 assembler implementation
// of Decompress4X when tablelog <= 8 which decodes 4 entries
// per loop.
//
//go:noescape
func decompress4x_8b_main_loop_amd64(ctx *decompress4xContext)
// fallback8BitSize is the size where using Go version is faster.
const fallback8BitSize = 800
type decompress4xContext struct {
pbr *[4]bitReaderShifted
peekBits uint8
out *byte
dstEvery int
tbl *dEntrySingle
decoded int
limit *byte
}
// Decompress4X will decompress a 4X encoded stream.
// The length of the supplied input must match the end of a block exactly.
// The *capacity* of the dst slice must match the destination size of
// the uncompressed data exactly.
func (d *Decoder) Decompress4X(dst, src []byte) ([]byte, error) {
if len(d.dt.single) == 0 {
return nil, errors.New("no table loaded")
}
if len(src) < 6+(4*1) {
return nil, errors.New("input too small")
}
use8BitTables := d.actualTableLog <= 8
if cap(dst) < fallback8BitSize && use8BitTables {
return d.decompress4X8bit(dst, src)
}
var br [4]bitReaderShifted
// Decode "jump table"
start := 6
for i := 0; i < 3; i++ {
length := int(src[i*2]) | (int(src[i*2+1]) << 8)
if start+length >= len(src) {
return nil, errors.New("truncated input (or invalid offset)")
}
err := br[i].init(src[start : start+length])
if err != nil {
return nil, err
}
start += length
}
err := br[3].init(src[start:])
if err != nil {
return nil, err
}
// destination, offset to match first output
dstSize := cap(dst)
dst = dst[:dstSize]
out := dst
dstEvery := (dstSize + 3) / 4
const tlSize = 1 << tableLogMax
const tlMask = tlSize - 1
single := d.dt.single[:tlSize]
var decoded int
if len(out) > 4*4 && !(br[0].off < 4 || br[1].off < 4 || br[2].off < 4 || br[3].off < 4) {
ctx := decompress4xContext{
pbr: &br,
peekBits: uint8((64 - d.actualTableLog) & 63), // see: bitReaderShifted.peekBitsFast()
out: &out[0],
dstEvery: dstEvery,
tbl: &single[0],
limit: &out[dstEvery-4], // Always stop decoding when first buffer gets here to avoid writing OOB on last.
}
if use8BitTables {
decompress4x_8b_main_loop_amd64(&ctx)
} else {
decompress4x_main_loop_amd64(&ctx)
}
decoded = ctx.decoded
out = out[decoded/4:]
}
// Decode remaining.
remainBytes := dstEvery - (decoded / 4)
for i := range br {
offset := dstEvery * i
endsAt := offset + remainBytes
if endsAt > len(out) {
endsAt = len(out)
}
br := &br[i]
bitsLeft := br.remaining()
for bitsLeft > 0 {
br.fill()
if offset >= endsAt {
return nil, errors.New("corruption detected: stream overrun 4")
}
// Read value and increment offset.
val := br.peekBitsFast(d.actualTableLog)
v := single[val&tlMask].entry
nBits := uint8(v)
br.advance(nBits)
bitsLeft -= uint(nBits)
out[offset] = uint8(v >> 8)
offset++
}
if offset != endsAt {
return nil, fmt.Errorf("corruption detected: short output block %d, end %d != %d", i, offset, endsAt)
}
decoded += offset - dstEvery*i
err = br.close()
if err != nil {
return nil, err
}
}
if dstSize != decoded {
return nil, errors.New("corruption detected: short output block")
}
return dst, nil
}
// decompress4x_main_loop_x86 is an x86 assembler implementation
// of Decompress1X when tablelog > 8.
//
//go:noescape
func decompress1x_main_loop_amd64(ctx *decompress1xContext)
// decompress4x_main_loop_x86 is an x86 with BMI2 assembler implementation
// of Decompress1X when tablelog > 8.
//
//go:noescape
func decompress1x_main_loop_bmi2(ctx *decompress1xContext)
type decompress1xContext struct {
pbr *bitReaderShifted
peekBits uint8
out *byte
outCap int
tbl *dEntrySingle
decoded int
}
// Error reported by asm implementations
const error_max_decoded_size_exeeded = -1
// Decompress1X will decompress a 1X encoded stream.
// The cap of the output buffer will be the maximum decompressed size.
// The length of the supplied input must match the end of a block exactly.
func (d *Decoder) Decompress1X(dst, src []byte) ([]byte, error) {
if len(d.dt.single) == 0 {
return nil, errors.New("no table loaded")
}
var br bitReaderShifted
err := br.init(src)
if err != nil {
return dst, err
}
maxDecodedSize := cap(dst)
dst = dst[:maxDecodedSize]
const tlSize = 1 << tableLogMax
const tlMask = tlSize - 1
if maxDecodedSize >= 4 {
ctx := decompress1xContext{
pbr: &br,
out: &dst[0],
outCap: maxDecodedSize,
peekBits: uint8((64 - d.actualTableLog) & 63), // see: bitReaderShifted.peekBitsFast()
tbl: &d.dt.single[0],
}
if cpuinfo.HasBMI2() {
decompress1x_main_loop_bmi2(&ctx)
} else {
decompress1x_main_loop_amd64(&ctx)
}
if ctx.decoded == error_max_decoded_size_exeeded {
return nil, ErrMaxDecodedSizeExceeded
}
dst = dst[:ctx.decoded]
}
// br < 8, so uint8 is fine
bitsLeft := uint8(br.off)*8 + 64 - br.bitsRead
for bitsLeft > 0 {
br.fill()
if len(dst) >= maxDecodedSize {
br.close()
return nil, ErrMaxDecodedSizeExceeded
}
v := d.dt.single[br.peekBitsFast(d.actualTableLog)&tlMask]
nBits := uint8(v.entry)
br.advance(nBits)
bitsLeft -= nBits
dst = append(dst, uint8(v.entry>>8))
}
return dst, br.close()
}

830
vendor/github.com/klauspost/compress/huff0/decompress_amd64.s generated vendored Normal file
View File

@@ -0,0 +1,830 @@
// Code generated by command: go run gen.go -out ../decompress_amd64.s -pkg=huff0. DO NOT EDIT.
//go:build amd64 && !appengine && !noasm && gc
// func decompress4x_main_loop_amd64(ctx *decompress4xContext)
TEXT ·decompress4x_main_loop_amd64(SB), $0-8
// Preload values
MOVQ ctx+0(FP), AX
MOVBQZX 8(AX), DI
MOVQ 16(AX), BX
MOVQ 48(AX), SI
MOVQ 24(AX), R8
MOVQ 32(AX), R9
MOVQ (AX), R10
// Main loop
main_loop:
XORL DX, DX
CMPQ BX, SI
SETGE DL
// br0.fillFast32()
MOVQ 32(R10), R11
MOVBQZX 40(R10), R12
CMPQ R12, $0x20
JBE skip_fill0
MOVQ 24(R10), AX
SUBQ $0x20, R12
SUBQ $0x04, AX
MOVQ (R10), R13
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (AX)(R13*1), R13
MOVQ R12, CX
SHLQ CL, R13
MOVQ AX, 24(R10)
ORQ R13, R11
// exhausted += (br0.off < 4)
CMPQ AX, $0x04
ADCB $+0, DL
skip_fill0:
// val0 := br0.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br0.peekTopBits(peekBits)
MOVQ DI, CX
MOVQ R11, R13
SHRQ CL, R13
// v1 := table[val1&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v1.entry))
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// these two writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
MOVW AX, (BX)
// update the bitreader structure
MOVQ R11, 32(R10)
MOVB R12, 40(R10)
// br1.fillFast32()
MOVQ 80(R10), R11
MOVBQZX 88(R10), R12
CMPQ R12, $0x20
JBE skip_fill1
MOVQ 72(R10), AX
SUBQ $0x20, R12
SUBQ $0x04, AX
MOVQ 48(R10), R13
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (AX)(R13*1), R13
MOVQ R12, CX
SHLQ CL, R13
MOVQ AX, 72(R10)
ORQ R13, R11
// exhausted += (br1.off < 4)
CMPQ AX, $0x04
ADCB $+0, DL
skip_fill1:
// val0 := br1.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br1.peekTopBits(peekBits)
MOVQ DI, CX
MOVQ R11, R13
SHRQ CL, R13
// v1 := table[val1&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v1.entry))
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// these two writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
MOVW AX, (BX)(R8*1)
// update the bitreader structure
MOVQ R11, 80(R10)
MOVB R12, 88(R10)
// br2.fillFast32()
MOVQ 128(R10), R11
MOVBQZX 136(R10), R12
CMPQ R12, $0x20
JBE skip_fill2
MOVQ 120(R10), AX
SUBQ $0x20, R12
SUBQ $0x04, AX
MOVQ 96(R10), R13
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (AX)(R13*1), R13
MOVQ R12, CX
SHLQ CL, R13
MOVQ AX, 120(R10)
ORQ R13, R11
// exhausted += (br2.off < 4)
CMPQ AX, $0x04
ADCB $+0, DL
skip_fill2:
// val0 := br2.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br2.peekTopBits(peekBits)
MOVQ DI, CX
MOVQ R11, R13
SHRQ CL, R13
// v1 := table[val1&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v1.entry))
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// these two writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
MOVW AX, (BX)(R8*2)
// update the bitreader structure
MOVQ R11, 128(R10)
MOVB R12, 136(R10)
// br3.fillFast32()
MOVQ 176(R10), R11
MOVBQZX 184(R10), R12
CMPQ R12, $0x20
JBE skip_fill3
MOVQ 168(R10), AX
SUBQ $0x20, R12
SUBQ $0x04, AX
MOVQ 144(R10), R13
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (AX)(R13*1), R13
MOVQ R12, CX
SHLQ CL, R13
MOVQ AX, 168(R10)
ORQ R13, R11
// exhausted += (br3.off < 4)
CMPQ AX, $0x04
ADCB $+0, DL
skip_fill3:
// val0 := br3.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br3.peekTopBits(peekBits)
MOVQ DI, CX
MOVQ R11, R13
SHRQ CL, R13
// v1 := table[val1&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v1.entry))
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// these two writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
LEAQ (R8)(R8*2), CX
MOVW AX, (BX)(CX*1)
// update the bitreader structure
MOVQ R11, 176(R10)
MOVB R12, 184(R10)
ADDQ $0x02, BX
TESTB DL, DL
JZ main_loop
MOVQ ctx+0(FP), AX
SUBQ 16(AX), BX
SHLQ $0x02, BX
MOVQ BX, 40(AX)
RET
// func decompress4x_8b_main_loop_amd64(ctx *decompress4xContext)
TEXT ·decompress4x_8b_main_loop_amd64(SB), $0-8
// Preload values
MOVQ ctx+0(FP), CX
MOVBQZX 8(CX), DI
MOVQ 16(CX), BX
MOVQ 48(CX), SI
MOVQ 24(CX), R8
MOVQ 32(CX), R9
MOVQ (CX), R10
// Main loop
main_loop:
XORL DX, DX
CMPQ BX, SI
SETGE DL
// br0.fillFast32()
MOVQ 32(R10), R11
MOVBQZX 40(R10), R12
CMPQ R12, $0x20
JBE skip_fill0
MOVQ 24(R10), R13
SUBQ $0x20, R12
SUBQ $0x04, R13
MOVQ (R10), R14
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (R13)(R14*1), R14
MOVQ R12, CX
SHLQ CL, R14
MOVQ R13, 24(R10)
ORQ R14, R11
// exhausted += (br0.off < 4)
CMPQ R13, $0x04
ADCB $+0, DL
skip_fill0:
// val0 := br0.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br0.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v1 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v1.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// val2 := br0.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v2 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v2.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// val3 := br0.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v3 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br0.advance(uint8(v3.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// these four writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
MOVL AX, (BX)
// update the bitreader structure
MOVQ R11, 32(R10)
MOVB R12, 40(R10)
// br1.fillFast32()
MOVQ 80(R10), R11
MOVBQZX 88(R10), R12
CMPQ R12, $0x20
JBE skip_fill1
MOVQ 72(R10), R13
SUBQ $0x20, R12
SUBQ $0x04, R13
MOVQ 48(R10), R14
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (R13)(R14*1), R14
MOVQ R12, CX
SHLQ CL, R14
MOVQ R13, 72(R10)
ORQ R14, R11
// exhausted += (br1.off < 4)
CMPQ R13, $0x04
ADCB $+0, DL
skip_fill1:
// val0 := br1.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br1.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v1 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v1.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// val2 := br1.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v2 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v2.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// val3 := br1.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v3 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br1.advance(uint8(v3.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// these four writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
MOVL AX, (BX)(R8*1)
// update the bitreader structure
MOVQ R11, 80(R10)
MOVB R12, 88(R10)
// br2.fillFast32()
MOVQ 128(R10), R11
MOVBQZX 136(R10), R12
CMPQ R12, $0x20
JBE skip_fill2
MOVQ 120(R10), R13
SUBQ $0x20, R12
SUBQ $0x04, R13
MOVQ 96(R10), R14
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (R13)(R14*1), R14
MOVQ R12, CX
SHLQ CL, R14
MOVQ R13, 120(R10)
ORQ R14, R11
// exhausted += (br2.off < 4)
CMPQ R13, $0x04
ADCB $+0, DL
skip_fill2:
// val0 := br2.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br2.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v1 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v1.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// val2 := br2.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v2 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v2.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// val3 := br2.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v3 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br2.advance(uint8(v3.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// these four writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
MOVL AX, (BX)(R8*2)
// update the bitreader structure
MOVQ R11, 128(R10)
MOVB R12, 136(R10)
// br3.fillFast32()
MOVQ 176(R10), R11
MOVBQZX 184(R10), R12
CMPQ R12, $0x20
JBE skip_fill3
MOVQ 168(R10), R13
SUBQ $0x20, R12
SUBQ $0x04, R13
MOVQ 144(R10), R14
// b.value |= uint64(low) << (b.bitsRead & 63)
MOVL (R13)(R14*1), R14
MOVQ R12, CX
SHLQ CL, R14
MOVQ R13, 168(R10)
ORQ R14, R11
// exhausted += (br3.off < 4)
CMPQ R13, $0x04
ADCB $+0, DL
skip_fill3:
// val0 := br3.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v0 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v0.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
// val1 := br3.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v1 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v1.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// val2 := br3.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v2 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v2.entry)
MOVB CH, AH
SHLQ CL, R11
ADDB CL, R12
// val3 := br3.peekTopBits(peekBits)
MOVQ R11, R13
MOVQ DI, CX
SHRQ CL, R13
// v3 := table[val0&mask]
MOVW (R9)(R13*2), CX
// br3.advance(uint8(v3.entry)
MOVB CH, AL
SHLQ CL, R11
ADDB CL, R12
BSWAPL AX
// these four writes get coalesced
// out[id * dstEvery + 0] = uint8(v0.entry >> 8)
// out[id * dstEvery + 1] = uint8(v1.entry >> 8)
// out[id * dstEvery + 3] = uint8(v2.entry >> 8)
// out[id * dstEvery + 4] = uint8(v3.entry >> 8)
LEAQ (R8)(R8*2), CX
MOVL AX, (BX)(CX*1)
// update the bitreader structure
MOVQ R11, 176(R10)
MOVB R12, 184(R10)
ADDQ $0x04, BX
TESTB DL, DL
JZ main_loop
MOVQ ctx+0(FP), AX
SUBQ 16(AX), BX
SHLQ $0x02, BX
MOVQ BX, 40(AX)
RET
// func decompress1x_main_loop_amd64(ctx *decompress1xContext)
TEXT ·decompress1x_main_loop_amd64(SB), $0-8
MOVQ ctx+0(FP), CX
MOVQ 16(CX), DX
MOVQ 24(CX), BX
CMPQ BX, $0x04
JB error_max_decoded_size_exceeded
LEAQ (DX)(BX*1), BX
MOVQ (CX), SI
MOVQ (SI), R8
MOVQ 24(SI), R9
MOVQ 32(SI), R10
MOVBQZX 40(SI), R11
MOVQ 32(CX), SI
MOVBQZX 8(CX), DI
JMP loop_condition
main_loop:
// Check if we have room for 4 bytes in the output buffer
LEAQ 4(DX), CX
CMPQ CX, BX
JGE error_max_decoded_size_exceeded
// Decode 4 values
CMPQ R11, $0x20
JL bitReader_fillFast_1_end
SUBQ $0x20, R11
SUBQ $0x04, R9
MOVL (R8)(R9*1), R12
MOVQ R11, CX
SHLQ CL, R12
ORQ R12, R10
bitReader_fillFast_1_end:
MOVQ DI, CX
MOVQ R10, R12
SHRQ CL, R12
MOVW (SI)(R12*2), CX
MOVB CH, AL
MOVBQZX CL, CX
ADDQ CX, R11
SHLQ CL, R10
MOVQ DI, CX
MOVQ R10, R12
SHRQ CL, R12
MOVW (SI)(R12*2), CX
MOVB CH, AH
MOVBQZX CL, CX
ADDQ CX, R11
SHLQ CL, R10
BSWAPL AX
CMPQ R11, $0x20
JL bitReader_fillFast_2_end
SUBQ $0x20, R11
SUBQ $0x04, R9
MOVL (R8)(R9*1), R12
MOVQ R11, CX
SHLQ CL, R12
ORQ R12, R10
bitReader_fillFast_2_end:
MOVQ DI, CX
MOVQ R10, R12
SHRQ CL, R12
MOVW (SI)(R12*2), CX
MOVB CH, AH
MOVBQZX CL, CX
ADDQ CX, R11
SHLQ CL, R10
MOVQ DI, CX
MOVQ R10, R12
SHRQ CL, R12
MOVW (SI)(R12*2), CX
MOVB CH, AL
MOVBQZX CL, CX
ADDQ CX, R11
SHLQ CL, R10
BSWAPL AX
// Store the decoded values
MOVL AX, (DX)
ADDQ $0x04, DX
loop_condition:
CMPQ R9, $0x08
JGE main_loop
// Update ctx structure
MOVQ ctx+0(FP), AX
SUBQ 16(AX), DX
MOVQ DX, 40(AX)
MOVQ (AX), AX
MOVQ R9, 24(AX)
MOVQ R10, 32(AX)
MOVB R11, 40(AX)
RET
// Report error
error_max_decoded_size_exceeded:
MOVQ ctx+0(FP), AX
MOVQ $-1, CX
MOVQ CX, 40(AX)
RET
// func decompress1x_main_loop_bmi2(ctx *decompress1xContext)
// Requires: BMI2
TEXT ·decompress1x_main_loop_bmi2(SB), $0-8
MOVQ ctx+0(FP), CX
MOVQ 16(CX), DX
MOVQ 24(CX), BX
CMPQ BX, $0x04
JB error_max_decoded_size_exceeded
LEAQ (DX)(BX*1), BX
MOVQ (CX), SI
MOVQ (SI), R8
MOVQ 24(SI), R9
MOVQ 32(SI), R10
MOVBQZX 40(SI), R11
MOVQ 32(CX), SI
MOVBQZX 8(CX), DI
JMP loop_condition
main_loop:
// Check if we have room for 4 bytes in the output buffer
LEAQ 4(DX), CX
CMPQ CX, BX
JGE error_max_decoded_size_exceeded
// Decode 4 values
CMPQ R11, $0x20
JL bitReader_fillFast_1_end
SUBQ $0x20, R11
SUBQ $0x04, R9
MOVL (R8)(R9*1), CX
SHLXQ R11, CX, CX
ORQ CX, R10
bitReader_fillFast_1_end:
SHRXQ DI, R10, CX
MOVW (SI)(CX*2), CX
MOVB CH, AL
MOVBQZX CL, CX
ADDQ CX, R11
SHLXQ CX, R10, R10
SHRXQ DI, R10, CX
MOVW (SI)(CX*2), CX
MOVB CH, AH
MOVBQZX CL, CX
ADDQ CX, R11
SHLXQ CX, R10, R10
BSWAPL AX
CMPQ R11, $0x20
JL bitReader_fillFast_2_end
SUBQ $0x20, R11
SUBQ $0x04, R9
MOVL (R8)(R9*1), CX
SHLXQ R11, CX, CX
ORQ CX, R10
bitReader_fillFast_2_end:
SHRXQ DI, R10, CX
MOVW (SI)(CX*2), CX
MOVB CH, AH
MOVBQZX CL, CX
ADDQ CX, R11
SHLXQ CX, R10, R10
SHRXQ DI, R10, CX
MOVW (SI)(CX*2), CX
MOVB CH, AL
MOVBQZX CL, CX
ADDQ CX, R11
SHLXQ CX, R10, R10
BSWAPL AX
// Store the decoded values
MOVL AX, (DX)
ADDQ $0x04, DX
loop_condition:
CMPQ R9, $0x08
JGE main_loop
// Update ctx structure
MOVQ ctx+0(FP), AX
SUBQ 16(AX), DX
MOVQ DX, 40(AX)
MOVQ (AX), AX
MOVQ R9, 24(AX)
MOVQ R10, 32(AX)
MOVB R11, 40(AX)
RET
// Report error
error_max_decoded_size_exceeded:
MOVQ ctx+0(FP), AX
MOVQ $-1, CX
MOVQ CX, 40(AX)
RET

299
vendor/github.com/klauspost/compress/huff0/decompress_generic.go generated vendored Normal file
View File

@@ -0,0 +1,299 @@
//go:build !amd64 || appengine || !gc || noasm
// +build !amd64 appengine !gc noasm
// This file contains a generic implementation of Decoder.Decompress4X.
package huff0
import (
"errors"
"fmt"
)
// Decompress4X will decompress a 4X encoded stream.
// The length of the supplied input must match the end of a block exactly.
// The *capacity* of the dst slice must match the destination size of
// the uncompressed data exactly.
func (d *Decoder) Decompress4X(dst, src []byte) ([]byte, error) {
if len(d.dt.single) == 0 {
return nil, errors.New("no table loaded")
}
if len(src) < 6+(4*1) {
return nil, errors.New("input too small")
}
if use8BitTables && d.actualTableLog <= 8 {
return d.decompress4X8bit(dst, src)
}
var br [4]bitReaderShifted
// Decode "jump table"
start := 6
for i := 0; i < 3; i++ {
length := int(src[i*2]) | (int(src[i*2+1]) << 8)
if start+length >= len(src) {
return nil, errors.New("truncated input (or invalid offset)")
}
err := br[i].init(src[start : start+length])
if err != nil {
return nil, err
}
start += length
}
err := br[3].init(src[start:])
if err != nil {
return nil, err
}
// destination, offset to match first output
dstSize := cap(dst)
dst = dst[:dstSize]
out := dst
dstEvery := (dstSize + 3) / 4
const tlSize = 1 << tableLogMax
const tlMask = tlSize - 1
single := d.dt.single[:tlSize]
// Use temp table to avoid bound checks/append penalty.
buf := d.buffer()
var off uint8
var decoded int
// Decode 2 values from each decoder/loop.
const bufoff = 256
for {
if br[0].off < 4 || br[1].off < 4 || br[2].off < 4 || br[3].off < 4 {
break
}
{
const stream = 0
const stream2 = 1
br[stream].fillFast()
br[stream2].fillFast()
val := br[stream].peekBitsFast(d.actualTableLog)
val2 := br[stream2].peekBitsFast(d.actualTableLog)
v := single[val&tlMask]
v2 := single[val2&tlMask]
br[stream].advance(uint8(v.entry))
br[stream2].advance(uint8(v2.entry))
buf[stream][off] = uint8(v.entry >> 8)
buf[stream2][off] = uint8(v2.entry >> 8)
val = br[stream].peekBitsFast(d.actualTableLog)
val2 = br[stream2].peekBitsFast(d.actualTableLog)
v = single[val&tlMask]
v2 = single[val2&tlMask]
br[stream].advance(uint8(v.entry))
br[stream2].advance(uint8(v2.entry))
buf[stream][off+1] = uint8(v.entry >> 8)
buf[stream2][off+1] = uint8(v2.entry >> 8)
}
{
const stream = 2
const stream2 = 3
br[stream].fillFast()
br[stream2].fillFast()
val := br[stream].peekBitsFast(d.actualTableLog)
val2 := br[stream2].peekBitsFast(d.actualTableLog)
v := single[val&tlMask]
v2 := single[val2&tlMask]
br[stream].advance(uint8(v.entry))
br[stream2].advance(uint8(v2.entry))
buf[stream][off] = uint8(v.entry >> 8)
buf[stream2][off] = uint8(v2.entry >> 8)
val = br[stream].peekBitsFast(d.actualTableLog)
val2 = br[stream2].peekBitsFast(d.actualTableLog)
v = single[val&tlMask]
v2 = single[val2&tlMask]
br[stream].advance(uint8(v.entry))
br[stream2].advance(uint8(v2.entry))
buf[stream][off+1] = uint8(v.entry >> 8)
buf[stream2][off+1] = uint8(v2.entry >> 8)
}
off += 2
if off == 0 {
if bufoff > dstEvery {
d.bufs.Put(buf)
return nil, errors.New("corruption detected: stream overrun 1")
}
// There must at least be 3 buffers left.
if len(out)-bufoff < dstEvery*3 {
d.bufs.Put(buf)
return nil, errors.New("corruption detected: stream overrun 2")
}
//copy(out, buf[0][:])
//copy(out[dstEvery:], buf[1][:])
//copy(out[dstEvery*2:], buf[2][:])
//copy(out[dstEvery*3:], buf[3][:])
*(*[bufoff]byte)(out) = buf[0]
*(*[bufoff]byte)(out[dstEvery:]) = buf[1]
*(*[bufoff]byte)(out[dstEvery*2:]) = buf[2]
*(*[bufoff]byte)(out[dstEvery*3:]) = buf[3]
out = out[bufoff:]
decoded += bufoff * 4
}
}
if off > 0 {
ioff := int(off)
if len(out) < dstEvery*3+ioff {
d.bufs.Put(buf)
return nil, errors.New("corruption detected: stream overrun 3")
}
copy(out, buf[0][:off])
copy(out[dstEvery:], buf[1][:off])
copy(out[dstEvery*2:], buf[2][:off])
copy(out[dstEvery*3:], buf[3][:off])
decoded += int(off) * 4
out = out[off:]
}
// Decode remaining.
remainBytes := dstEvery - (decoded / 4)
for i := range br {
offset := dstEvery * i
endsAt := offset + remainBytes
if endsAt > len(out) {
endsAt = len(out)
}
br := &br[i]
bitsLeft := br.remaining()
for bitsLeft > 0 {
br.fill()
if offset >= endsAt {
d.bufs.Put(buf)
return nil, errors.New("corruption detected: stream overrun 4")
}
// Read value and increment offset.
val := br.peekBitsFast(d.actualTableLog)
v := single[val&tlMask].entry
nBits := uint8(v)
br.advance(nBits)
bitsLeft -= uint(nBits)
out[offset] = uint8(v >> 8)
offset++
}
if offset != endsAt {
d.bufs.Put(buf)
return nil, fmt.Errorf("corruption detected: short output block %d, end %d != %d", i, offset, endsAt)
}
decoded += offset - dstEvery*i
err = br.close()
if err != nil {
return nil, err
}
}
d.bufs.Put(buf)
if dstSize != decoded {
return nil, errors.New("corruption detected: short output block")
}
return dst, nil
}
// Decompress1X will decompress a 1X encoded stream.
// The cap of the output buffer will be the maximum decompressed size.
// The length of the supplied input must match the end of a block exactly.
func (d *Decoder) Decompress1X(dst, src []byte) ([]byte, error) {
if len(d.dt.single) == 0 {
return nil, errors.New("no table loaded")
}
if use8BitTables && d.actualTableLog <= 8 {
return d.decompress1X8Bit(dst, src)
}
var br bitReaderShifted
err := br.init(src)
if err != nil {
return dst, err
}
maxDecodedSize := cap(dst)
dst = dst[:0]
// Avoid bounds check by always having full sized table.
const tlSize = 1 << tableLogMax
const tlMask = tlSize - 1
dt := d.dt.single[:tlSize]
// Use temp table to avoid bound checks/append penalty.
bufs := d.buffer()
buf := &bufs[0]
var off uint8
for br.off >= 8 {
br.fillFast()
v := dt[br.peekBitsFast(d.actualTableLog)&tlMask]
br.advance(uint8(v.entry))
buf[off+0] = uint8(v.entry >> 8)
v = dt[br.peekBitsFast(d.actualTableLog)&tlMask]
br.advance(uint8(v.entry))
buf[off+1] = uint8(v.entry >> 8)
// Refill
br.fillFast()
v = dt[br.peekBitsFast(d.actualTableLog)&tlMask]
br.advance(uint8(v.entry))
buf[off+2] = uint8(v.entry >> 8)
v = dt[br.peekBitsFast(d.actualTableLog)&tlMask]
br.advance(uint8(v.entry))
buf[off+3] = uint8(v.entry >> 8)
off += 4
if off == 0 {
if len(dst)+256 > maxDecodedSize {
br.close()
d.bufs.Put(bufs)
return nil, ErrMaxDecodedSizeExceeded
}
dst = append(dst, buf[:]...)
}
}
if len(dst)+int(off) > maxDecodedSize {
d.bufs.Put(bufs)
br.close()
return nil, ErrMaxDecodedSizeExceeded
}
dst = append(dst, buf[:off]...)
// br < 8, so uint8 is fine
bitsLeft := uint8(br.off)*8 + 64 - br.bitsRead
for bitsLeft > 0 {
br.fill()
if false && br.bitsRead >= 32 {
if br.off >= 4 {
v := br.in[br.off-4:]
v = v[:4]
low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
br.value = (br.value << 32) | uint64(low)
br.bitsRead -= 32
br.off -= 4
} else {
for br.off > 0 {
br.value = (br.value << 8) | uint64(br.in[br.off-1])
br.bitsRead -= 8
br.off--
}
}
}
if len(dst) >= maxDecodedSize {
d.bufs.Put(bufs)
br.close()
return nil, ErrMaxDecodedSizeExceeded
}
v := d.dt.single[br.peekBitsFast(d.actualTableLog)&tlMask]
nBits := uint8(v.entry)
br.advance(nBits)
bitsLeft -= nBits
dst = append(dst, uint8(v.entry>>8))
}
d.bufs.Put(bufs)
return dst, br.close()
}

2
vendor/github.com/klauspost/compress/huff0/huff0.go generated vendored
View File

@@ -8,6 +8,7 @@ import (
"fmt"
"math"
"math/bits"
"sync"
"github.com/klauspost/compress/fse"
)
@@ -116,6 +117,7 @@ type Scratch struct {
nodes []nodeElt
tmpOut [4][]byte
fse *fse.Scratch
decPool sync.Pool // *[4][256]byte buffers.
huffWeight [maxSymbolValue + 1]byte
}