Update

vendor/github.com/klauspost/compress/zstd/README.md

@@ -6,7 +6,7 @@ A high performance compression algorithm is implemented. For now focused on spee
 
 This package provides [compression](#Compressor) to and [decompression](#Decompressor) of Zstandard content. 
 
-This package is pure Go and without use of "unsafe". 
+This package is pure Go. Use `noasm` and `nounsafe` to disable relevant features.
 
 The `zstd` package is provided as open source software using a Go standard license.
 

vendor/github.com/klauspost/compress/zstd/bitreader.go

@@ -5,11 +5,12 @@
 package zstd
 
 import (
-	"encoding/binary"
 	"errors"
 	"fmt"
 	"io"
 	"math/bits"
+
+	"github.com/klauspost/compress/internal/le"
 )
 
 // bitReader reads a bitstream in reverse.
@@ -18,6 +19,7 @@ import (
 type bitReader struct {
 	in       []byte
 	value    uint64 // Maybe use [16]byte, but shifting is awkward.
+	cursor   int    // offset where next read should end
 	bitsRead uint8
 }
 
@@ -32,6 +34,7 @@ func (b *bitReader) init(in []byte) error {
 	if v == 0 {
 		return errors.New("corrupt stream, did not find end of stream")
 	}
+	b.cursor = len(in)
 	b.bitsRead = 64
 	b.value = 0
 	if len(in) >= 8 {
@@ -67,18 +70,15 @@ func (b *bitReader) fillFast() {
 	if b.bitsRead < 32 {
 		return
 	}
-	v := b.in[len(b.in)-4:]
-	b.in = b.in[:len(b.in)-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.cursor -= 4
+	b.value = (b.value << 32) | uint64(le.Load32(b.in, b.cursor))
 	b.bitsRead -= 32
 }
 
 // fillFastStart() assumes the bitreader is empty and there is at least 8 bytes to read.
 func (b *bitReader) fillFastStart() {
-	v := b.in[len(b.in)-8:]
-	b.in = b.in[:len(b.in)-8]
-	b.value = binary.LittleEndian.Uint64(v)
+	b.cursor -= 8
+	b.value = le.Load64(b.in, b.cursor)
 	b.bitsRead = 0
 }
 
@@ -87,25 +87,23 @@ func (b *bitReader) fill() {
 	if b.bitsRead < 32 {
 		return
 	}
-	if len(b.in) >= 4 {
-		v := b.in[len(b.in)-4:]
-		b.in = b.in[:len(b.in)-4]
-		low := (uint32(v[0])) | (uint32(v[1]) << 8) | (uint32(v[2]) << 16) | (uint32(v[3]) << 24)
-		b.value = (b.value << 32) | uint64(low)
+	if b.cursor >= 4 {
+		b.cursor -= 4
+		b.value = (b.value << 32) | uint64(le.Load32(b.in, b.cursor))
 		b.bitsRead -= 32
 		return
 	}
 
-	b.bitsRead -= uint8(8 * len(b.in))
-	for len(b.in) > 0 {
-		b.value = (b.value << 8) | uint64(b.in[len(b.in)-1])
-		b.in = b.in[:len(b.in)-1]
+	b.bitsRead -= uint8(8 * b.cursor)
+	for b.cursor > 0 {
+		b.cursor -= 1
+		b.value = (b.value << 8) | uint64(b.in[b.cursor])
 	}
 }
 
 // finished returns true if all bits have been read from the bit stream.
 func (b *bitReader) finished() bool {
-	return len(b.in) == 0 && b.bitsRead >= 64
+	return b.cursor == 0 && b.bitsRead >= 64
 }
 
 // overread returns true if more bits have been requested than is on the stream.
@@ -115,13 +113,14 @@ func (b *bitReader) overread() bool {
 
 // remain returns the number of bits remaining.
 func (b *bitReader) remain() uint {
-	return 8*uint(len(b.in)) + 64 - uint(b.bitsRead)
+	return 8*uint(b.cursor) + 64 - uint(b.bitsRead)
 }
 
 // close the bitstream and returns an error if out-of-buffer reads occurred.
 func (b *bitReader) close() error {
 	// Release reference.
 	b.in = nil
+	b.cursor = 0
 	if !b.finished() {
 		return fmt.Errorf("%d extra bits on block, should be 0", b.remain())
 	}

vendor/github.com/klauspost/compress/zstd/bitwriter.go

@@ -88,7 +88,7 @@ func (b *bitWriter) flush32() {
 // flushAlign will flush remaining full bytes and align to next byte boundary.
 func (b *bitWriter) flushAlign() {
 	nbBytes := (b.nBits + 7) >> 3
-	for i := uint8(0); i < nbBytes; i++ {
+	for i := range nbBytes {
 		b.out = append(b.out, byte(b.bitContainer>>(i*8)))
 	}
 	b.nBits = 0

vendor/github.com/klauspost/compress/zstd/blockdec.go

@@ -5,14 +5,10 @@
 package zstd
 
 import (
-	"bytes"
-	"encoding/binary"
 	"errors"
 	"fmt"
 	"hash/crc32"
 	"io"
-	"os"
-	"path/filepath"
 	"sync"
 
 	"github.com/klauspost/compress/huff0"
@@ -58,11 +54,11 @@ const (
 )
 
 var (
-	huffDecoderPool = sync.Pool{New: func() interface{} {
+	huffDecoderPool = sync.Pool{New: func() any {
 		return &huff0.Scratch{}
 	}}
 
-	fseDecoderPool = sync.Pool{New: func() interface{} {
+	fseDecoderPool = sync.Pool{New: func() any {
 		return &fseDecoder{}
 	}}
 )
@@ -557,7 +553,7 @@ func (b *blockDec) prepareSequences(in []byte, hist *history) (err error) {
 		if compMode&3 != 0 {
 			return errors.New("corrupt block: reserved bits not zero")
 		}
-		for i := uint(0); i < 3; i++ {
+		for i := range uint(3) {
 			mode := seqCompMode((compMode >> (6 - i*2)) & 3)
 			if debugDecoder {
 				println("Table", tableIndex(i), "is", mode)
@@ -648,21 +644,6 @@ func (b *blockDec) prepareSequences(in []byte, hist *history) (err error) {
 		println("initializing sequences:", err)
 		return err
 	}
-	// Extract blocks...
-	if false && hist.dict == nil {
-		fatalErr := func(err error) {
-			if err != nil {
-				panic(err)
-			}
-		}
-		fn := fmt.Sprintf("n-%d-lits-%d-prev-%d-%d-%d-win-%d.blk", hist.decoders.nSeqs, len(hist.decoders.literals), hist.recentOffsets[0], hist.recentOffsets[1], hist.recentOffsets[2], hist.windowSize)
-		var buf bytes.Buffer
-		fatalErr(binary.Write(&buf, binary.LittleEndian, hist.decoders.litLengths.fse))
-		fatalErr(binary.Write(&buf, binary.LittleEndian, hist.decoders.matchLengths.fse))
-		fatalErr(binary.Write(&buf, binary.LittleEndian, hist.decoders.offsets.fse))
-		buf.Write(in)
-		os.WriteFile(filepath.Join("testdata", "seqs", fn), buf.Bytes(), os.ModePerm)
-	}
 
 	return nil
 }

vendor/github.com/klauspost/compress/zstd/blockenc.go

@@ -9,6 +9,7 @@ import (
 	"fmt"
 	"math"
 	"math/bits"
+	"slices"
 
 	"github.com/klauspost/compress/huff0"
 )
@@ -457,16 +458,7 @@ func fuzzFseEncoder(data []byte) int {
 		// All 0
 		return 0
 	}
-	maxCount := func(a []uint32) int {
-		var max uint32
-		for _, v := range a {
-			if v > max {
-				max = v
-			}
-		}
-		return int(max)
-	}
-	cnt := maxCount(hist[:maxSym])
+	cnt := int(slices.Max(hist[:maxSym]))
 	if cnt == len(data) {
 		// RLE
 		return 0
@@ -884,15 +876,6 @@ func (b *blockEnc) genCodes() {
 			}
 		}
 	}
-	maxCount := func(a []uint32) int {
-		var max uint32
-		for _, v := range a {
-			if v > max {
-				max = v
-			}
-		}
-		return int(max)
-	}
 	if debugAsserts && mlMax > maxMatchLengthSymbol {
 		panic(fmt.Errorf("mlMax > maxMatchLengthSymbol (%d)", mlMax))
 	}
@@ -903,7 +886,7 @@ func (b *blockEnc) genCodes() {
 		panic(fmt.Errorf("llMax > maxLiteralLengthSymbol (%d)", llMax))
 	}
 
-	b.coders.mlEnc.HistogramFinished(mlMax, maxCount(mlH[:mlMax+1]))
-	b.coders.ofEnc.HistogramFinished(ofMax, maxCount(ofH[:ofMax+1]))
-	b.coders.llEnc.HistogramFinished(llMax, maxCount(llH[:llMax+1]))
+	b.coders.mlEnc.HistogramFinished(mlMax, int(slices.Max(mlH[:mlMax+1])))
+	b.coders.ofEnc.HistogramFinished(ofMax, int(slices.Max(ofH[:ofMax+1])))
+	b.coders.llEnc.HistogramFinished(llMax, int(slices.Max(llH[:llMax+1])))
 }

vendor/github.com/klauspost/compress/zstd/decoder.go

@@ -123,7 +123,7 @@ func NewReader(r io.Reader, opts ...DOption) (*Decoder, error) {
 }
 
 // Read bytes from the decompressed stream into p.
-// Returns the number of bytes written and any error that occurred.
+// Returns the number of bytes read and any error that occurred.
 // When the stream is done, io.EOF will be returned.
 func (d *Decoder) Read(p []byte) (int, error) {
 	var n int
@@ -323,6 +323,7 @@ func (d *Decoder) DecodeAll(input, dst []byte) ([]byte, error) {
 		frame.bBuf = nil
 		if frame.history.decoders.br != nil {
 			frame.history.decoders.br.in = nil
+			frame.history.decoders.br.cursor = 0
 		}
 		d.decoders <- block
 	}()
@@ -372,11 +373,9 @@ func (d *Decoder) DecodeAll(input, dst []byte) ([]byte, error) {
 		if cap(dst) == 0 && !d.o.limitToCap {
 			// Allocate len(input) * 2 by default if nothing is provided
 			// and we didn't get frame content size.
-			size := len(input) * 2
-			// Cap to 1 MB.
-			if size > 1<<20 {
-				size = 1 << 20
-			}
+			size := min(
+				// Cap to 1 MB.
+				len(input)*2, 1<<20)
 			if uint64(size) > d.o.maxDecodedSize {
 				size = int(d.o.maxDecodedSize)
 			}

vendor/github.com/klauspost/compress/zstd/dict.go

@@ -194,17 +194,17 @@ func BuildDict(o BuildDictOptions) ([]byte, error) {
 	hist := o.History
 	contents := o.Contents
 	debug := o.DebugOut != nil
-	println := func(args ...interface{}) {
+	println := func(args ...any) {
 		if o.DebugOut != nil {
 			fmt.Fprintln(o.DebugOut, args...)
 		}
 	}
-	printf := func(s string, args ...interface{}) {
+	printf := func(s string, args ...any) {
 		if o.DebugOut != nil {
 			fmt.Fprintf(o.DebugOut, s, args...)
 		}
 	}
-	print := func(args ...interface{}) {
+	print := func(args ...any) {
 		if o.DebugOut != nil {
 			fmt.Fprint(o.DebugOut, args...)
 		}
@@ -424,16 +424,10 @@ func BuildDict(o BuildDictOptions) ([]byte, error) {
 	}
 
 	// Literal table
-	avgSize := litTotal
-	if avgSize > huff0.BlockSizeMax/2 {
-		avgSize = huff0.BlockSizeMax / 2
-	}
+	avgSize := min(litTotal, huff0.BlockSizeMax/2)
 	huffBuff := make([]byte, 0, avgSize)
 	// Target size
-	div := litTotal / avgSize
-	if div < 1 {
-		div = 1
-	}
+	div := max(litTotal/avgSize, 1)
 	if debug {
 		println("Huffman weights:")
 	}
@@ -454,7 +448,7 @@ func BuildDict(o BuildDictOptions) ([]byte, error) {
 		huffBuff = append(huffBuff, 255)
 	}
 	scratch := &huff0.Scratch{TableLog: 11}
-	for tries := 0; tries < 255; tries++ {
+	for tries := range 255 {
 		scratch = &huff0.Scratch{TableLog: 11}
 		_, _, err = huff0.Compress1X(huffBuff, scratch)
 		if err == nil {
@@ -471,7 +465,7 @@ func BuildDict(o BuildDictOptions) ([]byte, error) {
 
 			// Bail out.... Just generate something
 			huffBuff = append(huffBuff, bytes.Repeat([]byte{255}, 10000)...)
-			for i := 0; i < 128; i++ {
+			for i := range 128 {
 				huffBuff = append(huffBuff, byte(i))
 			}
 			continue

vendor/github.com/klauspost/compress/zstd/enc_base.go

@@ -8,7 +8,7 @@ import (
 )
 
 const (
-	dictShardBits = 6
+	dictShardBits = 7
 )
 
 type fastBase struct {
@@ -41,11 +41,9 @@ func (e *fastBase) AppendCRC(dst []byte) []byte {
 // or a window size small enough to contain the input size, if > 0.
 func (e *fastBase) WindowSize(size int64) int32 {
 	if size > 0 && size < int64(e.maxMatchOff) {
-		b := int32(1) << uint(bits.Len(uint(size)))
-		// Keep minimum window.
-		if b < 1024 {
-			b = 1024
-		}
+		b := max(
+			// Keep minimum window.
+			int32(1)<<uint(bits.Len(uint(size))), 1024)
 		return b
 	}
 	return e.maxMatchOff
@@ -116,7 +114,7 @@ func (e *fastBase) matchlen(s, t int32, src []byte) int32 {
 			panic(err)
 		}
 		if t < 0 {
-			err := fmt.Sprintf("s (%d) < 0", s)
+			err := fmt.Sprintf("t (%d) < 0", t)
 			panic(err)
 		}
 		if s-t > e.maxMatchOff {

vendor/github.com/klauspost/compress/zstd/enc_best.go

@@ -158,11 +158,9 @@ func (e *bestFastEncoder) Encode(blk *blockEnc, src []byte) {
 
 	// Use this to estimate literal cost.
 	// Scaled by 10 bits.
-	bitsPerByte := int32((compress.ShannonEntropyBits(src) * 1024) / len(src))
-	// Huffman can never go < 1 bit/byte
-	if bitsPerByte < 1024 {
-		bitsPerByte = 1024
-	}
+	bitsPerByte := max(
+		// Huffman can never go < 1 bit/byte
+		int32((compress.ShannonEntropyBits(src)*1024)/len(src)), 1024)
 
 	// Override src
 	src = e.hist
@@ -235,10 +233,7 @@ encodeLoop:
 				// Extend candidate match backwards as far as possible.
 				// Do not extend repeats as we can assume they are optimal
 				// and offsets change if s == nextEmit.
-				tMin := s - e.maxMatchOff
-				if tMin < 0 {
-					tMin = 0
-				}
+				tMin := max(s-e.maxMatchOff, 0)
 				for offset > tMin && s > nextEmit && src[offset-1] == src[s-1] && l < maxMatchLength {
 					s--
 					offset--
@@ -382,10 +377,7 @@ encodeLoop:
 			nextEmit = s
 
 			// Index skipped...
-			end := s
-			if s > sLimit+4 {
-				end = sLimit + 4
-			}
+			end := min(s, sLimit+4)
 			off := index0 + e.cur
 			for index0 < end {
 				cv0 := load6432(src, index0)
@@ -444,10 +436,7 @@ encodeLoop:
 		nextEmit = s
 
 		// Index old s + 1 -> s - 1 or sLimit
-		end := s
-		if s > sLimit-4 {
-			end = sLimit - 4
-		}
+		end := min(s, sLimit-4)
 
 		off := index0 + e.cur
 		for index0 < end {

vendor/github.com/klauspost/compress/zstd/enc_better.go

@@ -190,10 +190,7 @@ encodeLoop:
 					// and have to do special offset treatment.
 					startLimit := nextEmit + 1
 
-					tMin := s - e.maxMatchOff
-					if tMin < 0 {
-						tMin = 0
-					}
+					tMin := max(s-e.maxMatchOff, 0)
 					for repIndex > tMin && start > startLimit && src[repIndex-1] == src[start-1] && seq.matchLen < maxMatchLength-zstdMinMatch-1 {
 						repIndex--
 						start--
@@ -252,10 +249,7 @@ encodeLoop:
 					// and have to do special offset treatment.
 					startLimit := nextEmit + 1
 
-					tMin := s - e.maxMatchOff
-					if tMin < 0 {
-						tMin = 0
-					}
+					tMin := max(s-e.maxMatchOff, 0)
 					for repIndex > tMin && start > startLimit && src[repIndex-1] == src[start-1] && seq.matchLen < maxMatchLength-zstdMinMatch-1 {
 						repIndex--
 						start--
@@ -480,10 +474,7 @@ encodeLoop:
 		l := matched
 
 		// Extend backwards
-		tMin := s - e.maxMatchOff
-		if tMin < 0 {
-			tMin = 0
-		}
+		tMin := max(s-e.maxMatchOff, 0)
 		for t > tMin && s > nextEmit && src[t-1] == src[s-1] && l < maxMatchLength {
 			s--
 			t--
@@ -719,10 +710,7 @@ encodeLoop:
 					// and have to do special offset treatment.
 					startLimit := nextEmit + 1
 
-					tMin := s - e.maxMatchOff
-					if tMin < 0 {
-						tMin = 0
-					}
+					tMin := max(s-e.maxMatchOff, 0)
 					for repIndex > tMin && start > startLimit && src[repIndex-1] == src[start-1] && seq.matchLen < maxMatchLength-zstdMinMatch-1 {
 						repIndex--
 						start--
@@ -783,10 +771,7 @@ encodeLoop:
 					// and have to do special offset treatment.
 					startLimit := nextEmit + 1
 
-					tMin := s - e.maxMatchOff
-					if tMin < 0 {
-						tMin = 0
-					}
+					tMin := max(s-e.maxMatchOff, 0)
 					for repIndex > tMin && start > startLimit && src[repIndex-1] == src[start-1] && seq.matchLen < maxMatchLength-zstdMinMatch-1 {
 						repIndex--
 						start--
@@ -1005,10 +990,7 @@ encodeLoop:
 		l := matched
 
 		// Extend backwards
-		tMin := s - e.maxMatchOff
-		if tMin < 0 {
-			tMin = 0
-		}
+		tMin := max(s-e.maxMatchOff, 0)
 		for t > tMin && s > nextEmit && src[t-1] == src[s-1] && l < maxMatchLength {
 			s--
 			t--

vendor/github.com/klauspost/compress/zstd/enc_dfast.go

@@ -13,7 +13,7 @@ const (
 	dFastLongLen       = 8                       // Bytes used for table hash
 
 	dLongTableShardCnt  = 1 << (dFastLongTableBits - dictShardBits) // Number of shards in the table
-	dLongTableShardSize = dFastLongTableSize / tableShardCnt        // Size of an individual shard
+	dLongTableShardSize = dFastLongTableSize / dLongTableShardCnt   // Size of an individual shard
 
 	dFastShortTableBits = tableBits                // Bits used in the short match table
 	dFastShortTableSize = 1 << dFastShortTableBits // Size of the table
@@ -149,10 +149,7 @@ encodeLoop:
 					// and have to do special offset treatment.
 					startLimit := nextEmit + 1
 
-					tMin := s - e.maxMatchOff
-					if tMin < 0 {
-						tMin = 0
-					}
+					tMin := max(s-e.maxMatchOff, 0)
 					for repIndex > tMin && start > startLimit && src[repIndex-1] == src[start-1] && seq.matchLen < maxMatchLength-zstdMinMatch-1 {
 						repIndex--
 						start--
@@ -266,10 +263,7 @@ encodeLoop:
 		l := e.matchlen(s+4, t+4, src) + 4
 
 		// Extend backwards
-		tMin := s - e.maxMatchOff
-		if tMin < 0 {
-			tMin = 0
-		}
+		tMin := max(s-e.maxMatchOff, 0)
 		for t > tMin && s > nextEmit && src[t-1] == src[s-1] && l < maxMatchLength {
 			s--
 			t--
@@ -462,10 +456,7 @@ encodeLoop:
 					// and have to do special offset treatment.
 					startLimit := nextEmit + 1
 
-					tMin := s - e.maxMatchOff
-					if tMin < 0 {
-						tMin = 0
-					}
+					tMin := max(s-e.maxMatchOff, 0)
 					for repIndex > tMin && start > startLimit && src[repIndex-1] == src[start-1] {
 						repIndex--
 						start--
@@ -576,10 +567,7 @@ encodeLoop:
 		l := int32(matchLen(src[s+4:], src[t+4:])) + 4
 
 		// Extend backwards
-		tMin := s - e.maxMatchOff
-		if tMin < 0 {
-			tMin = 0
-		}
+		tMin := max(s-e.maxMatchOff, 0)
 		for t > tMin && s > nextEmit && src[t-1] == src[s-1] {
 			s--
 			t--
@@ -809,10 +797,7 @@ encodeLoop:
 					// and have to do special offset treatment.
 					startLimit := nextEmit + 1
 
-					tMin := s - e.maxMatchOff
-					if tMin < 0 {
-						tMin = 0
-					}
+					tMin := max(s-e.maxMatchOff, 0)
 					for repIndex > tMin && start > startLimit && src[repIndex-1] == src[start-1] && seq.matchLen < maxMatchLength-zstdMinMatch-1 {
 						repIndex--
 						start--
@@ -927,10 +912,7 @@ encodeLoop:
 		l := e.matchlen(s+4, t+4, src) + 4
 
 		// Extend backwards
-		tMin := s - e.maxMatchOff
-		if tMin < 0 {
-			tMin = 0
-		}
+		tMin := max(s-e.maxMatchOff, 0)
 		for t > tMin && s > nextEmit && src[t-1] == src[s-1] && l < maxMatchLength {
 			s--
 			t--

vendor/github.com/klauspost/compress/zstd/enc_fast.go

@@ -143,10 +143,7 @@ encodeLoop:
 				// and have to do special offset treatment.
 				startLimit := nextEmit + 1
 
-				sMin := s - e.maxMatchOff
-				if sMin < 0 {
-					sMin = 0
-				}
+				sMin := max(s-e.maxMatchOff, 0)
 				for repIndex > sMin && start > startLimit && src[repIndex-1] == src[start-1] && seq.matchLen < maxMatchLength-zstdMinMatch {
 					repIndex--
 					start--
@@ -223,10 +220,7 @@ encodeLoop:
 		l := e.matchlen(s+4, t+4, src) + 4
 
 		// Extend backwards
-		tMin := s - e.maxMatchOff
-		if tMin < 0 {
-			tMin = 0
-		}
+		tMin := max(s-e.maxMatchOff, 0)
 		for t > tMin && s > nextEmit && src[t-1] == src[s-1] && l < maxMatchLength {
 			s--
 			t--
@@ -387,10 +381,7 @@ encodeLoop:
 				// and have to do special offset treatment.
 				startLimit := nextEmit + 1
 
-				sMin := s - e.maxMatchOff
-				if sMin < 0 {
-					sMin = 0
-				}
+				sMin := max(s-e.maxMatchOff, 0)
 				for repIndex > sMin && start > startLimit && src[repIndex-1] == src[start-1] {
 					repIndex--
 					start--
@@ -469,10 +460,7 @@ encodeLoop:
 		l := e.matchlen(s+4, t+4, src) + 4
 
 		// Extend backwards
-		tMin := s - e.maxMatchOff
-		if tMin < 0 {
-			tMin = 0
-		}
+		tMin := max(s-e.maxMatchOff, 0)
 		for t > tMin && s > nextEmit && src[t-1] == src[s-1] {
 			s--
 			t--
@@ -655,10 +643,7 @@ encodeLoop:
 				// and have to do special offset treatment.
 				startLimit := nextEmit + 1
 
-				sMin := s - e.maxMatchOff
-				if sMin < 0 {
-					sMin = 0
-				}
+				sMin := max(s-e.maxMatchOff, 0)
 				for repIndex > sMin && start > startLimit && src[repIndex-1] == src[start-1] && seq.matchLen < maxMatchLength-zstdMinMatch {
 					repIndex--
 					start--
@@ -735,10 +720,7 @@ encodeLoop:
 		l := e.matchlen(s+4, t+4, src) + 4
 
 		// Extend backwards
-		tMin := s - e.maxMatchOff
-		if tMin < 0 {
-			tMin = 0
-		}
+		tMin := max(s-e.maxMatchOff, 0)
 		for t > tMin && s > nextEmit && src[t-1] == src[s-1] && l < maxMatchLength {
 			s--
 			t--

vendor/github.com/klauspost/compress/zstd/framedec.go

@@ -238,10 +238,7 @@ func (d *frameDec) reset(br byteBuffer) error {
 
 	if d.WindowSize == 0 && d.SingleSegment {
 		// We may not need window in this case.
-		d.WindowSize = d.FrameContentSize
-		if d.WindowSize < MinWindowSize {
-			d.WindowSize = MinWindowSize
-		}
+		d.WindowSize = max(d.FrameContentSize, MinWindowSize)
 		if d.WindowSize > d.o.maxDecodedSize {
 			if debugDecoder {
 				printf("window size %d > max %d\n", d.WindowSize, d.o.maxWindowSize)

vendor/github.com/klauspost/compress/zstd/fse_encoder.go

@@ -149,7 +149,7 @@ func (s *fseEncoder) buildCTable() error {
 			if v > largeLimit {
 				s.zeroBits = true
 			}
-			for nbOccurrences := int16(0); nbOccurrences < v; nbOccurrences++ {
+			for range v {
 				tableSymbol[position] = symbol
 				position = (position + step) & tableMask
 				for position > highThreshold {

vendor/github.com/klauspost/compress/zstd/matchlen_generic.go

@@ -7,20 +7,25 @@
 package zstd
 
 import (
-	"encoding/binary"
 	"math/bits"
+
+	"github.com/klauspost/compress/internal/le"
 )
 
 // matchLen returns the maximum common prefix length of a and b.
 // a must be the shortest of the two.
 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)
+	left := len(a)
+	for left >= 8 {
+		diff := le.Load64(a, n) ^ le.Load64(b, n)
 		if diff != 0 {
 			return n + bits.TrailingZeros64(diff)>>3
 		}
 		n += 8
+		left -= 8
 	}
+	a = a[n:]
+	b = b[n:]
 
 	for i := range a {
 		if a[i] != b[i] {

vendor/github.com/klauspost/compress/zstd/seqdec.go

@@ -231,10 +231,7 @@ func (s *sequenceDecs) decodeSync(hist []byte) error {
 	llTable, mlTable, ofTable := s.litLengths.fse.dt[:maxTablesize], s.matchLengths.fse.dt[:maxTablesize], s.offsets.fse.dt[:maxTablesize]
 	llState, mlState, ofState := s.litLengths.state.state, s.matchLengths.state.state, s.offsets.state.state
 	out := s.out
-	maxBlockSize := maxCompressedBlockSize
-	if s.windowSize < maxBlockSize {
-		maxBlockSize = s.windowSize
-	}
+	maxBlockSize := min(s.windowSize, maxCompressedBlockSize)
 
 	if debugDecoder {
 		println("decodeSync: decoding", seqs, "sequences", br.remain(), "bits remain on stream")
@@ -245,7 +242,7 @@ func (s *sequenceDecs) decodeSync(hist []byte) error {
 			return io.ErrUnexpectedEOF
 		}
 		var ll, mo, ml int
-		if len(br.in) > 4+((maxOffsetBits+16+16)>>3) {
+		if br.cursor > 4+((maxOffsetBits+16+16)>>3) {
 			// inlined function:
 			// ll, mo, ml = s.nextFast(br, llState, mlState, ofState)
 

vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go

@@ -79,10 +79,7 @@ func (s *sequenceDecs) decodeSyncSimple(hist []byte) (bool, error) {
 
 	br := s.br
 
-	maxBlockSize := maxCompressedBlockSize
-	if s.windowSize < maxBlockSize {
-		maxBlockSize = s.windowSize
-	}
+	maxBlockSize := min(s.windowSize, maxCompressedBlockSize)
 
 	ctx := decodeSyncAsmContext{
 		llTable:     s.litLengths.fse.dt[:maxTablesize],
@@ -237,10 +234,7 @@ func sequenceDecs_decode_56_bmi2(s *sequenceDecs, br *bitReader, ctx *decodeAsmC
 func (s *sequenceDecs) decode(seqs []seqVals) error {
 	br := s.br
 
-	maxBlockSize := maxCompressedBlockSize
-	if s.windowSize < maxBlockSize {
-		maxBlockSize = s.windowSize
-	}
+	maxBlockSize := min(s.windowSize, maxCompressedBlockSize)
 
 	ctx := decodeAsmContext{
 		llTable:   s.litLengths.fse.dt[:maxTablesize],

vendor/github.com/klauspost/compress/zstd/seqdec_amd64.s

@@ -7,9 +7,9 @@
 TEXT ·sequenceDecs_decode_amd64(SB), $8-32
 	MOVQ    br+8(FP), CX
 	MOVQ    24(CX), DX
-	MOVBQZX 32(CX), BX
+	MOVBQZX 40(CX), BX
 	MOVQ    (CX), AX
-	MOVQ    8(CX), SI
+	MOVQ    32(CX), SI
 	ADDQ    SI, AX
 	MOVQ    AX, (SP)
 	MOVQ    ctx+16(FP), AX
@@ -299,8 +299,8 @@ sequenceDecs_decode_amd64_match_len_ofs_ok:
 	MOVQ R13, 160(AX)
 	MOVQ br+8(FP), AX
 	MOVQ DX, 24(AX)
-	MOVB BL, 32(AX)
-	MOVQ SI, 8(AX)
+	MOVB BL, 40(AX)
+	MOVQ SI, 32(AX)
 
 	// Return success
 	MOVQ $0x00000000, ret+24(FP)
@@ -335,9 +335,9 @@ error_overread:
 TEXT ·sequenceDecs_decode_56_amd64(SB), $8-32
 	MOVQ    br+8(FP), CX
 	MOVQ    24(CX), DX
-	MOVBQZX 32(CX), BX
+	MOVBQZX 40(CX), BX
 	MOVQ    (CX), AX
-	MOVQ    8(CX), SI
+	MOVQ    32(CX), SI
 	ADDQ    SI, AX
 	MOVQ    AX, (SP)
 	MOVQ    ctx+16(FP), AX
@@ -598,8 +598,8 @@ sequenceDecs_decode_56_amd64_match_len_ofs_ok:
 	MOVQ R13, 160(AX)
 	MOVQ br+8(FP), AX
 	MOVQ DX, 24(AX)
-	MOVB BL, 32(AX)
-	MOVQ SI, 8(AX)
+	MOVB BL, 40(AX)
+	MOVQ SI, 32(AX)
 
 	// Return success
 	MOVQ $0x00000000, ret+24(FP)
@@ -634,9 +634,9 @@ error_overread:
 TEXT ·sequenceDecs_decode_bmi2(SB), $8-32
 	MOVQ    br+8(FP), BX
 	MOVQ    24(BX), AX
-	MOVBQZX 32(BX), DX
+	MOVBQZX 40(BX), DX
 	MOVQ    (BX), CX
-	MOVQ    8(BX), BX
+	MOVQ    32(BX), BX
 	ADDQ    BX, CX
 	MOVQ    CX, (SP)
 	MOVQ    ctx+16(FP), CX
@@ -884,8 +884,8 @@ sequenceDecs_decode_bmi2_match_len_ofs_ok:
 	MOVQ R12, 160(CX)
 	MOVQ br+8(FP), CX
 	MOVQ AX, 24(CX)
-	MOVB DL, 32(CX)
-	MOVQ BX, 8(CX)
+	MOVB DL, 40(CX)
+	MOVQ BX, 32(CX)
 
 	// Return success
 	MOVQ $0x00000000, ret+24(FP)
@@ -920,9 +920,9 @@ error_overread:
 TEXT ·sequenceDecs_decode_56_bmi2(SB), $8-32
 	MOVQ    br+8(FP), BX
 	MOVQ    24(BX), AX
-	MOVBQZX 32(BX), DX
+	MOVBQZX 40(BX), DX
 	MOVQ    (BX), CX
-	MOVQ    8(BX), BX
+	MOVQ    32(BX), BX
 	ADDQ    BX, CX
 	MOVQ    CX, (SP)
 	MOVQ    ctx+16(FP), CX
@@ -1141,8 +1141,8 @@ sequenceDecs_decode_56_bmi2_match_len_ofs_ok:
 	MOVQ R12, 160(CX)
 	MOVQ br+8(FP), CX
 	MOVQ AX, 24(CX)
-	MOVB DL, 32(CX)
-	MOVQ BX, 8(CX)
+	MOVB DL, 40(CX)
+	MOVQ BX, 32(CX)
 
 	// Return success
 	MOVQ $0x00000000, ret+24(FP)
@@ -1787,9 +1787,9 @@ empty_seqs:
 TEXT ·sequenceDecs_decodeSync_amd64(SB), $64-32
 	MOVQ    br+8(FP), CX
 	MOVQ    24(CX), DX
-	MOVBQZX 32(CX), BX
+	MOVBQZX 40(CX), BX
 	MOVQ    (CX), AX
-	MOVQ    8(CX), SI
+	MOVQ    32(CX), SI
 	ADDQ    SI, AX
 	MOVQ    AX, (SP)
 	MOVQ    ctx+16(FP), AX
@@ -2281,8 +2281,8 @@ handle_loop:
 loop_finished:
 	MOVQ br+8(FP), AX
 	MOVQ DX, 24(AX)
-	MOVB BL, 32(AX)
-	MOVQ SI, 8(AX)
+	MOVB BL, 40(AX)
+	MOVQ SI, 32(AX)
 
 	// Update the context
 	MOVQ ctx+16(FP), AX
@@ -2349,9 +2349,9 @@ error_not_enough_space:
 TEXT ·sequenceDecs_decodeSync_bmi2(SB), $64-32
 	MOVQ    br+8(FP), BX
 	MOVQ    24(BX), AX
-	MOVBQZX 32(BX), DX
+	MOVBQZX 40(BX), DX
 	MOVQ    (BX), CX
-	MOVQ    8(BX), BX
+	MOVQ    32(BX), BX
 	ADDQ    BX, CX
 	MOVQ    CX, (SP)
 	MOVQ    ctx+16(FP), CX
@@ -2801,8 +2801,8 @@ handle_loop:
 loop_finished:
 	MOVQ br+8(FP), CX
 	MOVQ AX, 24(CX)
-	MOVB DL, 32(CX)
-	MOVQ BX, 8(CX)
+	MOVB DL, 40(CX)
+	MOVQ BX, 32(CX)
 
 	// Update the context
 	MOVQ ctx+16(FP), AX
@@ -2869,9 +2869,9 @@ error_not_enough_space:
 TEXT ·sequenceDecs_decodeSync_safe_amd64(SB), $64-32
 	MOVQ    br+8(FP), CX
 	MOVQ    24(CX), DX
-	MOVBQZX 32(CX), BX
+	MOVBQZX 40(CX), BX
 	MOVQ    (CX), AX
-	MOVQ    8(CX), SI
+	MOVQ    32(CX), SI
 	ADDQ    SI, AX
 	MOVQ    AX, (SP)
 	MOVQ    ctx+16(FP), AX
@@ -3465,8 +3465,8 @@ handle_loop:
 loop_finished:
 	MOVQ br+8(FP), AX
 	MOVQ DX, 24(AX)
-	MOVB BL, 32(AX)
-	MOVQ SI, 8(AX)
+	MOVB BL, 40(AX)
+	MOVQ SI, 32(AX)
 
 	// Update the context
 	MOVQ ctx+16(FP), AX
@@ -3533,9 +3533,9 @@ error_not_enough_space:
 TEXT ·sequenceDecs_decodeSync_safe_bmi2(SB), $64-32
 	MOVQ    br+8(FP), BX
 	MOVQ    24(BX), AX
-	MOVBQZX 32(BX), DX
+	MOVBQZX 40(BX), DX
 	MOVQ    (BX), CX
-	MOVQ    8(BX), BX
+	MOVQ    32(BX), BX
 	ADDQ    BX, CX
 	MOVQ    CX, (SP)
 	MOVQ    ctx+16(FP), CX
@@ -4087,8 +4087,8 @@ handle_loop:
 loop_finished:
 	MOVQ br+8(FP), CX
 	MOVQ AX, 24(CX)
-	MOVB DL, 32(CX)
-	MOVQ BX, 8(CX)
+	MOVB DL, 40(CX)
+	MOVQ BX, 32(CX)
 
 	// Update the context
 	MOVQ ctx+16(FP), AX

vendor/github.com/klauspost/compress/zstd/seqdec_generic.go

@@ -29,7 +29,7 @@ func (s *sequenceDecs) decode(seqs []seqVals) error {
 	}
 	for i := range seqs {
 		var ll, mo, ml int
-		if len(br.in) > 4+((maxOffsetBits+16+16)>>3) {
+		if br.cursor > 4+((maxOffsetBits+16+16)>>3) {
 			// inlined function:
 			// ll, mo, ml = s.nextFast(br, llState, mlState, ofState)
 

vendor/github.com/klauspost/compress/zstd/seqenc.go

@@ -69,7 +69,6 @@ var llBitsTable = [maxLLCode + 1]byte{
 func llCode(litLength uint32) uint8 {
 	const llDeltaCode = 19
 	if litLength <= 63 {
-		// Compiler insists on bounds check (Go 1.12)
 		return llCodeTable[litLength&63]
 	}
 	return uint8(highBit(litLength)) + llDeltaCode
@@ -102,7 +101,6 @@ var mlBitsTable = [maxMLCode + 1]byte{
 func mlCode(mlBase uint32) uint8 {
 	const mlDeltaCode = 36
 	if mlBase <= 127 {
-		// Compiler insists on bounds check (Go 1.12)
 		return mlCodeTable[mlBase&127]
 	}
 	return uint8(highBit(mlBase)) + mlDeltaCode

vendor/github.com/klauspost/compress/zstd/simple_go124.go

@@ -0,0 +1,56 @@
+// Copyright 2025+ Klaus Post. All rights reserved.
+// License information can be found in the LICENSE file.
+
+//go:build go1.24
+
+package zstd
+
+import (
+	"errors"
+	"runtime"
+	"sync"
+	"weak"
+)
+
+var weakMu sync.Mutex
+var simpleEnc weak.Pointer[Encoder]
+var simpleDec weak.Pointer[Decoder]
+
+// EncodeTo appends the encoded data from src to dst.
+func EncodeTo(dst []byte, src []byte) []byte {
+	weakMu.Lock()
+	enc := simpleEnc.Value()
+	if enc == nil {
+		var err error
+		enc, err = NewWriter(nil, WithEncoderConcurrency(runtime.NumCPU()), WithWindowSize(1<<20), WithLowerEncoderMem(true), WithZeroFrames(true))
+		if err != nil {
+			panic("failed to create simple encoder: " + err.Error())
+		}
+		simpleEnc = weak.Make(enc)
+	}
+	weakMu.Unlock()
+
+	return enc.EncodeAll(src, dst)
+}
+
+// DecodeTo appends the decoded data from src to dst.
+// The maximum decoded size is 1GiB,
+// not including what may already be in dst.
+func DecodeTo(dst []byte, src []byte) ([]byte, error) {
+	weakMu.Lock()
+	dec := simpleDec.Value()
+	if dec == nil {
+		var err error
+		dec, err = NewReader(nil, WithDecoderConcurrency(runtime.NumCPU()), WithDecoderLowmem(true), WithDecoderMaxMemory(1<<30))
+		if err != nil {
+			weakMu.Unlock()
+			return nil, errors.New("failed to create simple decoder: " + err.Error())
+		}
+		runtime.SetFinalizer(dec, func(d *Decoder) {
+			d.Close()
+		})
+		simpleDec = weak.Make(dec)
+	}
+	weakMu.Unlock()
+	return dec.DecodeAll(src, dst)
+}

vendor/github.com/klauspost/compress/zstd/snappy.go

@@ -197,7 +197,7 @@ func (r *SnappyConverter) Convert(in io.Reader, w io.Writer) (int64, error) {
 
 			n, r.err = w.Write(r.block.output)
 			if r.err != nil {
-				return written, err
+				return written, r.err
 			}
 			written += int64(n)
 			continue
@@ -239,7 +239,7 @@ func (r *SnappyConverter) Convert(in io.Reader, w io.Writer) (int64, error) {
 			}
 			n, r.err = w.Write(r.block.output)
 			if r.err != nil {
-				return written, err
+				return written, r.err
 			}
 			written += int64(n)
 			continue
@@ -257,7 +257,7 @@ func (r *SnappyConverter) Convert(in io.Reader, w io.Writer) (int64, error) {
 			if !r.readFull(r.buf[:len(snappyMagicBody)], false) {
 				return written, r.err
 			}
-			for i := 0; i < len(snappyMagicBody); i++ {
+			for i := range len(snappyMagicBody) {
 				if r.buf[i] != snappyMagicBody[i] {
 					println("r.buf[i] != snappyMagicBody[i]", r.buf[i], snappyMagicBody[i], i)
 					r.err = ErrSnappyCorrupt

vendor/github.com/klauspost/compress/zstd/zip.go

@@ -19,7 +19,7 @@ const ZipMethodWinZip = 93
 const ZipMethodPKWare = 20
 
 // zipReaderPool is the default reader pool.
-var zipReaderPool = sync.Pool{New: func() interface{} {
+var zipReaderPool = sync.Pool{New: func() any {
 	z, err := NewReader(nil, WithDecoderLowmem(true), WithDecoderMaxWindow(128<<20), WithDecoderConcurrency(1))
 	if err != nil {
 		panic(err)

vendor/github.com/klauspost/compress/zstd/zstd.go

@@ -5,10 +5,11 @@ package zstd
 
 import (
 	"bytes"
-	"encoding/binary"
 	"errors"
 	"log"
 	"math"
+
+	"github.com/klauspost/compress/internal/le"
 )
 
 // enable debug printing
@@ -97,24 +98,24 @@ var (
 	ErrDecoderNilInput = errors.New("nil input provided as reader")
 )
 
-func println(a ...interface{}) {
+func println(a ...any) {
 	if debug || debugDecoder || debugEncoder {
 		log.Println(a...)
 	}
 }
 
-func printf(format string, a ...interface{}) {
+func printf(format string, a ...any) {
 	if debug || debugDecoder || debugEncoder {
 		log.Printf(format, a...)
 	}
 }
 
 func load3232(b []byte, i int32) uint32 {
-	return binary.LittleEndian.Uint32(b[:len(b):len(b)][i:])
+	return le.Load32(b, i)
 }
 
 func load6432(b []byte, i int32) uint64 {
-	return binary.LittleEndian.Uint64(b[:len(b):len(b)][i:])
+	return le.Load64(b, i)
 }
 
 type byter interface {