diff --git a/go.mod b/go.mod index e3ce1c1..6d328c8 100644 --- a/go.mod +++ b/go.mod @@ -4,7 +4,7 @@ go 1.20 require ( github.com/h2non/filetype v1.1.3 - github.com/klauspost/compress v1.16.0 + github.com/klauspost/compress v1.16.3 github.com/spf13/cobra v1.6.1 github.com/yosssi/gohtml v0.0.0-20201013000340-ee4748c638f4 golang.org/x/image v0.6.0 diff --git a/go.sum b/go.sum index 8998f11..fad6402 100644 --- a/go.sum +++ b/go.sum @@ -4,8 +4,8 @@ github.com/h2non/filetype v1.1.3/go.mod h1:319b3zT68BvV+WRj7cwy856M2ehB3HqNOt6sy github.com/inconshreveable/mousetrap v1.0.1/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw= github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8= github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw= -github.com/klauspost/compress v1.16.0 h1:iULayQNOReoYUe+1qtKOqw9CwJv3aNQu8ivo7lw1HU4= -github.com/klauspost/compress v1.16.0/go.mod h1:ntbaceVETuRiXiv4DpjP66DpAtAGkEQskQzEyD//IeE= +github.com/klauspost/compress v1.16.3 h1:XuJt9zzcnaz6a16/OU53ZjWp/v7/42WcR5t2a0PcNQY= +github.com/klauspost/compress v1.16.3/go.mod h1:ntbaceVETuRiXiv4DpjP66DpAtAGkEQskQzEyD//IeE= github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM= github.com/spf13/cobra v1.6.1 h1:o94oiPyS4KD1mPy2fmcYYHHfCxLqYjJOhGsCHFZtEzA= github.com/spf13/cobra v1.6.1/go.mod h1:IOw/AERYS7UzyrGinqmz6HLUo219MORXGxhbaJUqzrY= diff --git a/vendor/github.com/klauspost/compress/README.md b/vendor/github.com/klauspost/compress/README.md index 958666e..c2c7252 100644 --- a/vendor/github.com/klauspost/compress/README.md +++ b/vendor/github.com/klauspost/compress/README.md @@ -16,6 +16,21 @@ This package provides various compression algorithms. # changelog +* Mar 13, 2023 - [v1.16.1](https://github.com/klauspost/compress/releases/tag/v1.16.1) + * zstd: Speed up + improve best encoder by @greatroar in https://github.com/klauspost/compress/pull/776 + * gzhttp: Add optional [BREACH mitigation](https://github.com/klauspost/compress/tree/master/gzhttp#breach-mitigation). https://github.com/klauspost/compress/pull/762 https://github.com/klauspost/compress/pull/768 https://github.com/klauspost/compress/pull/769 https://github.com/klauspost/compress/pull/770 https://github.com/klauspost/compress/pull/767 + * s2: Add Intel LZ4s converter https://github.com/klauspost/compress/pull/766 + * zstd: Minor bug fixes https://github.com/klauspost/compress/pull/771 https://github.com/klauspost/compress/pull/772 https://github.com/klauspost/compress/pull/773 + * huff0: Speed up compress1xDo by @greatroar in https://github.com/klauspost/compress/pull/774 + +* Feb 26, 2023 - [v1.16.0](https://github.com/klauspost/compress/releases/tag/v1.16.0) + * s2: Add [Dictionary](https://github.com/klauspost/compress/tree/master/s2#dictionaries) support. https://github.com/klauspost/compress/pull/685 + * s2: Add Compression Size Estimate. https://github.com/klauspost/compress/pull/752 + * s2: Add support for custom stream encoder. https://github.com/klauspost/compress/pull/755 + * s2: Add LZ4 block converter. https://github.com/klauspost/compress/pull/748 + * s2: Support io.ReaderAt in ReadSeeker. https://github.com/klauspost/compress/pull/747 + * s2c/s2sx: Use concurrent decoding. https://github.com/klauspost/compress/pull/746 + * Jan 21st, 2023 (v1.15.15) * deflate: Improve level 7-9 by @klauspost in https://github.com/klauspost/compress/pull/739 * zstd: Add delta encoding support by @greatroar in https://github.com/klauspost/compress/pull/728 diff --git a/vendor/github.com/klauspost/compress/fse/decompress.go b/vendor/github.com/klauspost/compress/fse/decompress.go index 926f5f1..cc05d0f 100644 --- a/vendor/github.com/klauspost/compress/fse/decompress.go +++ b/vendor/github.com/klauspost/compress/fse/decompress.go @@ -260,7 +260,9 @@ func (s *Scratch) buildDtable() error { // If the buffer is over-read an error is returned. func (s *Scratch) decompress() error { br := &s.bits - br.init(s.br.unread()) + if err := br.init(s.br.unread()); err != nil { + return err + } var s1, s2 decoder // Initialize and decode first state and symbol. diff --git a/vendor/github.com/klauspost/compress/huff0/bitwriter.go b/vendor/github.com/klauspost/compress/huff0/bitwriter.go index ec71f7a..aed2347 100644 --- a/vendor/github.com/klauspost/compress/huff0/bitwriter.go +++ b/vendor/github.com/klauspost/compress/huff0/bitwriter.go @@ -60,6 +60,22 @@ func (b *bitWriter) encTwoSymbols(ct cTable, av, bv byte) { b.nBits += encA.nBits + encB.nBits } +// 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 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. func (b *bitWriter) flush32() { if b.nBits < 32 { diff --git a/vendor/github.com/klauspost/compress/huff0/compress.go b/vendor/github.com/klauspost/compress/huff0/compress.go index cdc9485..4ee4fa1 100644 --- a/vendor/github.com/klauspost/compress/huff0/compress.go +++ b/vendor/github.com/klauspost/compress/huff0/compress.go @@ -248,8 +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 { diff --git a/vendor/github.com/klauspost/compress/zstd/blockdec.go b/vendor/github.com/klauspost/compress/zstd/blockdec.go index 2445bb4..5f272d8 100644 --- a/vendor/github.com/klauspost/compress/zstd/blockdec.go +++ b/vendor/github.com/klauspost/compress/zstd/blockdec.go @@ -9,6 +9,7 @@ import ( "encoding/binary" "errors" "fmt" + "hash/crc32" "io" "os" "path/filepath" @@ -442,6 +443,9 @@ func (b *blockDec) decodeLiterals(in []byte, hist *history) (remain []byte, err } } var err error + if debugDecoder { + println("huff table input:", len(literals), "CRC:", crc32.ChecksumIEEE(literals)) + } huff, literals, err = huff0.ReadTable(literals, huff) if err != nil { println("reading huffman table:", err) diff --git a/vendor/github.com/klauspost/compress/zstd/bytebuf.go b/vendor/github.com/klauspost/compress/zstd/bytebuf.go index 176788f..512ffe5 100644 --- a/vendor/github.com/klauspost/compress/zstd/bytebuf.go +++ b/vendor/github.com/klauspost/compress/zstd/bytebuf.go @@ -54,7 +54,7 @@ func (b *byteBuf) readBig(n int, dst []byte) ([]byte, error) { func (b *byteBuf) readByte() (byte, error) { bb := *b if len(bb) < 1 { - return 0, nil + return 0, io.ErrUnexpectedEOF } r := bb[0] *b = bb[1:] diff --git a/vendor/github.com/klauspost/compress/zstd/enc_best.go b/vendor/github.com/klauspost/compress/zstd/enc_best.go index 830f5ba..07f657d 100644 --- a/vendor/github.com/klauspost/compress/zstd/enc_best.go +++ b/vendor/github.com/klauspost/compress/zstd/enc_best.go @@ -32,7 +32,6 @@ type match struct { length int32 rep int32 est int32 - _ [12]byte // Aligned size to cache line: 4+4+4+4+4 bytes + 12 bytes padding = 32 bytes } const highScore = 25000 @@ -189,12 +188,6 @@ encodeLoop: panic("offset0 was 0") } - bestOf := func(a, b *match) *match { - if a.est-b.est+(a.s-b.s)*bitsPerByte>>10 < 0 { - return a - } - return b - } const goodEnough = 100 nextHashL := hashLen(cv, bestLongTableBits, bestLongLen) @@ -202,40 +195,41 @@ encodeLoop: candidateL := e.longTable[nextHashL] candidateS := e.table[nextHashS] - matchAt := func(offset int32, s int32, first uint32, rep int32) match { + // Set m to a match at offset if it looks like that will improve compression. + improve := func(m *match, offset int32, s int32, first uint32, rep int32) { if s-offset >= e.maxMatchOff || load3232(src, offset) != first { - return match{s: s, est: highScore} + return } if debugAsserts { if !bytes.Equal(src[s:s+4], src[offset:offset+4]) { panic(fmt.Sprintf("first match mismatch: %v != %v, first: %08x", src[s:s+4], src[offset:offset+4], first)) } } - m := match{offset: offset, s: s, length: 4 + e.matchlen(s+4, offset+4, src), rep: rep} - m.estBits(bitsPerByte) - return m + cand := match{offset: offset, s: s, length: 4 + e.matchlen(s+4, offset+4, src), rep: rep} + cand.estBits(bitsPerByte) + if m.est >= highScore || cand.est-m.est+(cand.s-m.s)*bitsPerByte>>10 < 0 { + *m = cand + } } - m1 := matchAt(candidateL.offset-e.cur, s, uint32(cv), -1) - m2 := matchAt(candidateL.prev-e.cur, s, uint32(cv), -1) - m3 := matchAt(candidateS.offset-e.cur, s, uint32(cv), -1) - m4 := matchAt(candidateS.prev-e.cur, s, uint32(cv), -1) - best := bestOf(bestOf(&m1, &m2), bestOf(&m3, &m4)) + best := match{s: s, est: highScore} + improve(&best, candidateL.offset-e.cur, s, uint32(cv), -1) + improve(&best, candidateL.prev-e.cur, s, uint32(cv), -1) + improve(&best, candidateS.offset-e.cur, s, uint32(cv), -1) + improve(&best, candidateS.prev-e.cur, s, uint32(cv), -1) if canRepeat && best.length < goodEnough { cv32 := uint32(cv >> 8) spp := s + 1 - m1 := matchAt(spp-offset1, spp, cv32, 1) - m2 := matchAt(spp-offset2, spp, cv32, 2) - m3 := matchAt(spp-offset3, spp, cv32, 3) - best = bestOf(bestOf(best, &m1), bestOf(&m2, &m3)) + improve(&best, spp-offset1, spp, cv32, 1) + improve(&best, spp-offset2, spp, cv32, 2) + improve(&best, spp-offset3, spp, cv32, 3) if best.length > 0 { cv32 = uint32(cv >> 24) spp += 2 - m1 := matchAt(spp-offset1, spp, cv32, 1) - m2 := matchAt(spp-offset2, spp, cv32, 2) - m3 := matchAt(spp-offset3, spp, cv32, 3) - best = bestOf(bestOf(best, &m1), bestOf(&m2, &m3)) + improve(&best, spp-offset1, spp, cv32, 1) + improve(&best, spp-offset2, spp, cv32, 2) + improve(&best, spp-offset3, spp, cv32, 3) } } // Load next and check... @@ -262,18 +256,16 @@ encodeLoop: candidateL2 := e.longTable[hashLen(cv2, bestLongTableBits, bestLongLen)] // Short at s+1 - m1 := matchAt(candidateS.offset-e.cur, s, uint32(cv), -1) + improve(&best, candidateS.offset-e.cur, s, uint32(cv), -1) // Long at s+1, s+2 - m2 := matchAt(candidateL.offset-e.cur, s, uint32(cv), -1) - m3 := matchAt(candidateL.prev-e.cur, s, uint32(cv), -1) - m4 := matchAt(candidateL2.offset-e.cur, s+1, uint32(cv2), -1) - m5 := matchAt(candidateL2.prev-e.cur, s+1, uint32(cv2), -1) - best = bestOf(bestOf(bestOf(best, &m1), &m2), bestOf(bestOf(&m3, &m4), &m5)) + improve(&best, candidateL.offset-e.cur, s, uint32(cv), -1) + improve(&best, candidateL.prev-e.cur, s, uint32(cv), -1) + improve(&best, candidateL2.offset-e.cur, s+1, uint32(cv2), -1) + improve(&best, candidateL2.prev-e.cur, s+1, uint32(cv2), -1) if false { // Short at s+3. // Too often worse... - m := matchAt(e.table[hashLen(cv2>>8, bestShortTableBits, bestShortLen)].offset-e.cur, s+2, uint32(cv2>>8), -1) - best = bestOf(best, &m) + improve(&best, e.table[hashLen(cv2>>8, bestShortTableBits, bestShortLen)].offset-e.cur, s+2, uint32(cv2>>8), -1) } // See if we can find a better match by checking where the current best ends. // Use that offset to see if we can find a better full match. @@ -284,13 +276,10 @@ encodeLoop: // For this compression level 2 yields the best results. const skipBeginning = 2 if pos := candidateEnd.offset - e.cur - best.length + skipBeginning; pos >= 0 { - m := matchAt(pos, best.s+skipBeginning, load3232(src, best.s+skipBeginning), -1) - bestEnd := bestOf(best, &m) + improve(&best, pos, best.s+skipBeginning, load3232(src, best.s+skipBeginning), -1) if pos := candidateEnd.prev - e.cur - best.length + skipBeginning; pos >= 0 { - m := matchAt(pos, best.s+skipBeginning, load3232(src, best.s+skipBeginning), -1) - bestEnd = bestOf(bestEnd, &m) + improve(&best, pos, best.s+skipBeginning, load3232(src, best.s+skipBeginning), -1) } - best = bestEnd } } } diff --git a/vendor/github.com/klauspost/compress/zstd/seqdec.go b/vendor/github.com/klauspost/compress/zstd/seqdec.go index f833d15..27fdf90 100644 --- a/vendor/github.com/klauspost/compress/zstd/seqdec.go +++ b/vendor/github.com/klauspost/compress/zstd/seqdec.go @@ -314,9 +314,6 @@ func (s *sequenceDecs) decodeSync(hist []byte) error { } size := ll + ml + len(out) if size-startSize > maxBlockSize { - if size-startSize == 424242 { - panic("here") - } return fmt.Errorf("output bigger than max block size (%d)", maxBlockSize) } if size > cap(out) { @@ -427,8 +424,7 @@ func (s *sequenceDecs) decodeSync(hist []byte) error { } } - // Check if space for literals - if size := len(s.literals) + len(s.out) - startSize; size > maxBlockSize { + if size := len(s.literals) + len(out) - startSize; size > maxBlockSize { return fmt.Errorf("output bigger than max block size (%d)", maxBlockSize) } diff --git a/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go b/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go index 191384a..387a30e 100644 --- a/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go +++ b/vendor/github.com/klauspost/compress/zstd/seqdec_amd64.go @@ -148,7 +148,6 @@ func (s *sequenceDecs) decodeSyncSimple(hist []byte) (bool, error) { s.seqSize += ctx.litRemain if s.seqSize > maxBlockSize { return true, fmt.Errorf("output bigger than max block size (%d)", maxBlockSize) - } err := br.close() if err != nil { diff --git a/vendor/modules.txt b/vendor/modules.txt index 4b84519..c79b7d2 100644 --- a/vendor/modules.txt +++ b/vendor/modules.txt @@ -7,7 +7,7 @@ github.com/h2non/filetype/types # github.com/inconshreveable/mousetrap v1.1.0 ## explicit; go 1.18 github.com/inconshreveable/mousetrap -# github.com/klauspost/compress v1.16.0 +# github.com/klauspost/compress v1.16.3 ## explicit; go 1.18 github.com/klauspost/compress github.com/klauspost/compress/fse