diff options
Diffstat (limited to 'vendor/github.com/klauspost/compress')
| -rw-r--r-- | vendor/github.com/klauspost/compress/flate/level5.go | 17 | ||||
| -rw-r--r-- | vendor/github.com/klauspost/compress/flate/level6.go | 25 | ||||
| -rw-r--r-- | vendor/github.com/klauspost/compress/zstd/README.md | 24 | ||||
| -rw-r--r-- | vendor/github.com/klauspost/compress/zstd/enc_best.go | 14 | ||||
| -rw-r--r-- | vendor/github.com/klauspost/compress/zstd/enc_better.go | 73 | ||||
| -rw-r--r-- | vendor/github.com/klauspost/compress/zstd/zip.go | 120 |
6 files changed, 256 insertions, 17 deletions
diff --git a/vendor/github.com/klauspost/compress/flate/level5.go b/vendor/github.com/klauspost/compress/flate/level5.go index d513f1ffd..293a3a320 100644 --- a/vendor/github.com/klauspost/compress/flate/level5.go +++ b/vendor/github.com/klauspost/compress/flate/level5.go @@ -182,12 +182,27 @@ func (e *fastEncL5) Encode(dst *tokens, src []byte) { // match. But, prior to the match, src[nextEmit:s] are unmatched. Emit // them as literal bytes. - // Extend the 4-byte match as long as possible. if l == 0 { + // Extend the 4-byte match as long as possible. l = e.matchlenLong(s+4, t+4, src) + 4 } else if l == maxMatchLength { l += e.matchlenLong(s+l, t+l, src) } + + // Try to locate a better match by checking the end of best match... + if sAt := s + l; l < 30 && sAt < sLimit { + eLong := e.bTable[hash7(load6432(src, sAt), tableBits)].Cur.offset + // Test current + t2 := eLong - e.cur - l + off := s - t2 + if t2 >= 0 && off < maxMatchOffset && off > 0 { + if l2 := e.matchlenLong(s, t2, src); l2 > l { + t = t2 + l = l2 + } + } + } + // Extend backwards for t > 0 && s > nextEmit && src[t-1] == src[s-1] { s-- diff --git a/vendor/github.com/klauspost/compress/flate/level6.go b/vendor/github.com/klauspost/compress/flate/level6.go index a52c80ea4..a709977ec 100644 --- a/vendor/github.com/klauspost/compress/flate/level6.go +++ b/vendor/github.com/klauspost/compress/flate/level6.go @@ -211,6 +211,31 @@ func (e *fastEncL6) Encode(dst *tokens, src []byte) { l += e.matchlenLong(s+l, t+l, src) } + // Try to locate a better match by checking the end-of-match... + if sAt := s + l; sAt < sLimit { + eLong := &e.bTable[hash7(load6432(src, sAt), tableBits)] + // Test current + t2 := eLong.Cur.offset - e.cur - l + off := s - t2 + if off < maxMatchOffset { + if off > 0 && t2 >= 0 { + if l2 := e.matchlenLong(s, t2, src); l2 > l { + t = t2 + l = l2 + } + } + // Test next: + t2 = eLong.Prev.offset - e.cur - l + off := s - t2 + if off > 0 && off < maxMatchOffset && t2 >= 0 { + if l2 := e.matchlenLong(s, t2, src); l2 > l { + t = t2 + l = l2 + } + } + } + } + // Extend backwards for t > 0 && s > nextEmit && src[t-1] == src[s-1] { s-- diff --git a/vendor/github.com/klauspost/compress/zstd/README.md b/vendor/github.com/klauspost/compress/zstd/README.md index 7680bfe1d..e7d7eb0ae 100644 --- a/vendor/github.com/klauspost/compress/zstd/README.md +++ b/vendor/github.com/klauspost/compress/zstd/README.md @@ -152,8 +152,8 @@ This package: file out level insize outsize millis mb/s silesia.tar zskp 1 211947520 73101992 643 313.87 silesia.tar zskp 2 211947520 67504318 969 208.38 -silesia.tar zskp 3 211947520 65177448 1899 106.44 -silesia.tar zskp 4 211947520 61381950 8115 24.91 +silesia.tar zskp 3 211947520 64595893 2007 100.68 +silesia.tar zskp 4 211947520 60995370 7691 26.28 cgo zstd: silesia.tar zstd 1 211947520 73605392 543 371.56 @@ -171,8 +171,8 @@ https://files.klauspost.com/compress/gob-stream.7z file out level insize outsize millis mb/s gob-stream zskp 1 1911399616 235022249 3088 590.30 gob-stream zskp 2 1911399616 205669791 3786 481.34 -gob-stream zskp 3 1911399616 185792019 9324 195.48 -gob-stream zskp 4 1911399616 171537212 32113 56.76 +gob-stream zskp 3 1911399616 175034659 9636 189.17 +gob-stream zskp 4 1911399616 167273881 29337 62.13 gob-stream zstd 1 1911399616 249810424 2637 691.26 gob-stream zstd 3 1911399616 208192146 3490 522.31 gob-stream zstd 6 1911399616 193632038 6687 272.56 @@ -187,8 +187,8 @@ http://mattmahoney.net/dc/textdata.html file out level insize outsize millis mb/s enwik9 zskp 1 1000000000 343848582 3609 264.18 enwik9 zskp 2 1000000000 317276632 5746 165.97 -enwik9 zskp 3 1000000000 294540704 11725 81.34 -enwik9 zskp 4 1000000000 276609671 44029 21.66 +enwik9 zskp 3 1000000000 292243069 12162 78.41 +enwik9 zskp 4 1000000000 275241169 36430 26.18 enwik9 zstd 1 1000000000 358072021 3110 306.65 enwik9 zstd 3 1000000000 313734672 4784 199.35 enwik9 zstd 6 1000000000 295138875 10290 92.68 @@ -202,8 +202,8 @@ https://files.klauspost.com/compress/github-june-2days-2019.json.zst file out level insize outsize millis mb/s github-june-2days-2019.json zskp 1 6273951764 699045015 10620 563.40 github-june-2days-2019.json zskp 2 6273951764 617881763 11687 511.96 -github-june-2days-2019.json zskp 3 6273951764 537511906 29252 204.54 -github-june-2days-2019.json zskp 4 6273951764 512796117 97791 61.18 +github-june-2days-2019.json zskp 3 6273951764 524340691 34043 175.75 +github-june-2days-2019.json zskp 4 6273951764 503314661 93811 63.78 github-june-2days-2019.json zstd 1 6273951764 766284037 8450 708.00 github-june-2days-2019.json zstd 3 6273951764 661889476 10927 547.57 github-june-2days-2019.json zstd 6 6273951764 642756859 22996 260.18 @@ -217,8 +217,8 @@ https://files.klauspost.com/compress/rawstudio-mint14.7z file out level insize outsize millis mb/s rawstudio-mint14.tar zskp 1 8558382592 3667489370 20210 403.84 rawstudio-mint14.tar zskp 2 8558382592 3364592300 31873 256.07 -rawstudio-mint14.tar zskp 3 8558382592 3224594213 71751 113.75 -rawstudio-mint14.tar zskp 4 8558382592 3027332295 486243 16.79 +rawstudio-mint14.tar zskp 3 8558382592 3158085214 77675 105.08 +rawstudio-mint14.tar zskp 4 8558382592 3020370044 404956 20.16 rawstudio-mint14.tar zstd 1 8558382592 3609250104 17136 476.27 rawstudio-mint14.tar zstd 3 8558382592 3341679997 29262 278.92 rawstudio-mint14.tar zstd 6 8558382592 3235846406 77904 104.77 @@ -232,8 +232,8 @@ https://files.klauspost.com/compress/nyc-taxi-data-10M.csv.zst file out level insize outsize millis mb/s nyc-taxi-data-10M.csv zskp 1 3325605752 641339945 8925 355.35 nyc-taxi-data-10M.csv zskp 2 3325605752 591748091 11268 281.44 -nyc-taxi-data-10M.csv zskp 3 3325605752 538490114 19880 159.53 -nyc-taxi-data-10M.csv zskp 4 3325605752 495986829 89368 35.49 +nyc-taxi-data-10M.csv zskp 3 3325605752 530289687 25239 125.66 +nyc-taxi-data-10M.csv zskp 4 3325605752 490907191 65939 48.10 nyc-taxi-data-10M.csv zstd 1 3325605752 687399637 8233 385.18 nyc-taxi-data-10M.csv zstd 3 3325605752 598514411 10065 315.07 nyc-taxi-data-10M.csv zstd 6 3325605752 570522953 20038 158.27 diff --git a/vendor/github.com/klauspost/compress/zstd/enc_best.go b/vendor/github.com/klauspost/compress/zstd/enc_best.go index fe3625c5f..dc1eed5f0 100644 --- a/vendor/github.com/klauspost/compress/zstd/enc_best.go +++ b/vendor/github.com/klauspost/compress/zstd/enc_best.go @@ -220,6 +220,20 @@ encodeLoop: best = bestOf(best, matchAt(candidateL.prev-e.cur, s, uint32(cv), -1)) best = bestOf(best, matchAt(candidateL2.offset-e.cur, s+1, uint32(cv2), -1)) best = bestOf(best, matchAt(candidateL2.prev-e.cur, s+1, uint32(cv2), -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. + if sAt := best.s + best.length; sAt < sLimit { + nextHashL := hash8(load6432(src, sAt), bestLongTableBits) + candidateEnd := e.longTable[nextHashL] + if pos := candidateEnd.offset - e.cur - best.length; pos >= 0 { + bestEnd := bestOf(best, matchAt(pos, best.s, load3232(src, best.s), -1)) + if pos := candidateEnd.prev - e.cur - best.length; pos >= 0 { + bestEnd = bestOf(bestEnd, matchAt(pos, best.s, load3232(src, best.s), -1)) + } + best = bestEnd + } + } } // We have a match, we can store the forward value diff --git a/vendor/github.com/klauspost/compress/zstd/enc_better.go b/vendor/github.com/klauspost/compress/zstd/enc_better.go index c2ce4a2ba..604954290 100644 --- a/vendor/github.com/klauspost/compress/zstd/enc_better.go +++ b/vendor/github.com/klauspost/compress/zstd/enc_better.go @@ -412,8 +412,41 @@ encodeLoop: cv = load6432(src, s) } - // A 4-byte match has been found. Update recent offsets. - // We'll later see if more than 4 bytes. + // Try to find a better match by searching for a long match at the end of the current best match + if true && s+matched < sLimit { + nextHashL := hash8(load6432(src, s+matched), betterLongTableBits) + cv := load3232(src, s) + candidateL := e.longTable[nextHashL] + coffsetL := candidateL.offset - e.cur - matched + if coffsetL >= 0 && coffsetL < s && s-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) { + // Found a long match, at least 4 bytes. + matchedNext := e.matchlen(s+4, coffsetL+4, src) + 4 + if matchedNext > matched { + t = coffsetL + matched = matchedNext + if debugMatches { + println("long match at end-of-match") + } + } + } + + // Check prev long... + if true { + coffsetL = candidateL.prev - e.cur - matched + if coffsetL >= 0 && coffsetL < s && s-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) { + // Found a long match, at least 4 bytes. + matchedNext := e.matchlen(s+4, coffsetL+4, src) + 4 + if matchedNext > matched { + t = coffsetL + matched = matchedNext + if debugMatches { + println("prev long match at end-of-match") + } + } + } + } + } + // A match has been found. Update recent offsets. offset2 = offset1 offset1 = s - t @@ -905,9 +938,41 @@ encodeLoop: } cv = load6432(src, s) } + // Try to find a better match by searching for a long match at the end of the current best match + if s+matched < sLimit { + nextHashL := hash8(load6432(src, s+matched), betterLongTableBits) + cv := load3232(src, s) + candidateL := e.longTable[nextHashL] + coffsetL := candidateL.offset - e.cur - matched + if coffsetL >= 0 && coffsetL < s && s-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) { + // Found a long match, at least 4 bytes. + matchedNext := e.matchlen(s+4, coffsetL+4, src) + 4 + if matchedNext > matched { + t = coffsetL + matched = matchedNext + if debugMatches { + println("long match at end-of-match") + } + } + } - // A 4-byte match has been found. Update recent offsets. - // We'll later see if more than 4 bytes. + // Check prev long... + if true { + coffsetL = candidateL.prev - e.cur - matched + if coffsetL >= 0 && coffsetL < s && s-coffsetL < e.maxMatchOff && cv == load3232(src, coffsetL) { + // Found a long match, at least 4 bytes. + matchedNext := e.matchlen(s+4, coffsetL+4, src) + 4 + if matchedNext > matched { + t = coffsetL + matched = matchedNext + if debugMatches { + println("prev long match at end-of-match") + } + } + } + } + } + // A match has been found. Update recent offsets. offset2 = offset1 offset1 = s - t diff --git a/vendor/github.com/klauspost/compress/zstd/zip.go b/vendor/github.com/klauspost/compress/zstd/zip.go new file mode 100644 index 000000000..e35a0a2f8 --- /dev/null +++ b/vendor/github.com/klauspost/compress/zstd/zip.go @@ -0,0 +1,120 @@ +// Copyright 2019+ Klaus Post. All rights reserved. +// License information can be found in the LICENSE file. + +package zstd + +import ( + "errors" + "io" + "sync" +) + +// ZipMethodWinZip is the method for Zstandard compressed data inside Zip files for WinZip. +// See https://www.winzip.com/win/en/comp_info.html +const ZipMethodWinZip = 93 + +// ZipMethodPKWare is the method number used by PKWARE to indicate Zstandard compression. +// See https://pkware.cachefly.net/webdocs/APPNOTE/APPNOTE-6.3.7.TXT +const ZipMethodPKWare = 20 + +var zipReaderPool sync.Pool + +// newZipReader cannot be used since we would leak goroutines... +func newZipReader(r io.Reader) io.ReadCloser { + dec, ok := zipReaderPool.Get().(*Decoder) + if ok { + dec.Reset(r) + } else { + d, err := NewReader(r, WithDecoderConcurrency(1), WithDecoderLowmem(true)) + if err != nil { + panic(err) + } + dec = d + } + return &pooledZipReader{dec: dec} +} + +type pooledZipReader struct { + mu sync.Mutex // guards Close and Read + dec *Decoder +} + +func (r *pooledZipReader) Read(p []byte) (n int, err error) { + r.mu.Lock() + defer r.mu.Unlock() + if r.dec == nil { + return 0, errors.New("Read after Close") + } + dec, err := r.dec.Read(p) + + return dec, err +} + +func (r *pooledZipReader) Close() error { + r.mu.Lock() + defer r.mu.Unlock() + var err error + if r.dec != nil { + err = r.dec.Reset(nil) + zipReaderPool.Put(r.dec) + r.dec = nil + } + return err +} + +type pooledZipWriter struct { + mu sync.Mutex // guards Close and Read + enc *Encoder +} + +func (w *pooledZipWriter) Write(p []byte) (n int, err error) { + w.mu.Lock() + defer w.mu.Unlock() + if w.enc == nil { + return 0, errors.New("Write after Close") + } + return w.enc.Write(p) +} + +func (w *pooledZipWriter) Close() error { + w.mu.Lock() + defer w.mu.Unlock() + var err error + if w.enc != nil { + err = w.enc.Close() + zipReaderPool.Put(w.enc) + w.enc = nil + } + return err +} + +// ZipCompressor returns a compressor that can be registered with zip libraries. +// The provided encoder options will be used on all encodes. +func ZipCompressor(opts ...EOption) func(w io.Writer) (io.WriteCloser, error) { + var pool sync.Pool + return func(w io.Writer) (io.WriteCloser, error) { + enc, ok := pool.Get().(*Encoder) + if ok { + enc.Reset(w) + } else { + var err error + enc, err = NewWriter(w, opts...) + if err != nil { + return nil, err + } + } + return &pooledZipWriter{enc: enc}, nil + } +} + +// ZipDecompressor returns a decompressor that can be registered with zip libraries. +// See ZipCompressor for example. +func ZipDecompressor() func(r io.Reader) io.ReadCloser { + return func(r io.Reader) io.ReadCloser { + d, err := NewReader(r, WithDecoderConcurrency(1), WithDecoderLowmem(true)) + if err != nil { + panic(err) + } + return d.IOReadCloser() + } +} |