summaryrefslogtreecommitdiff
path: root/vendor/github.com/klauspost/compress/internal/snapref
diff options
context:
space:
mode:
Diffstat (limited to 'vendor/github.com/klauspost/compress/internal/snapref')
-rw-r--r--vendor/github.com/klauspost/compress/internal/snapref/LICENSE27
-rw-r--r--vendor/github.com/klauspost/compress/internal/snapref/decode.go264
-rw-r--r--vendor/github.com/klauspost/compress/internal/snapref/decode_other.go113
-rw-r--r--vendor/github.com/klauspost/compress/internal/snapref/encode.go289
-rw-r--r--vendor/github.com/klauspost/compress/internal/snapref/encode_other.go236
-rw-r--r--vendor/github.com/klauspost/compress/internal/snapref/snappy.go98
6 files changed, 1027 insertions, 0 deletions
diff --git a/vendor/github.com/klauspost/compress/internal/snapref/LICENSE b/vendor/github.com/klauspost/compress/internal/snapref/LICENSE
new file mode 100644
index 000000000..6050c10f4
--- /dev/null
+++ b/vendor/github.com/klauspost/compress/internal/snapref/LICENSE
@@ -0,0 +1,27 @@
+Copyright (c) 2011 The Snappy-Go Authors. All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+ * Redistributions of source code must retain the above copyright
+notice, this list of conditions and the following disclaimer.
+ * Redistributions in binary form must reproduce the above
+copyright notice, this list of conditions and the following disclaimer
+in the documentation and/or other materials provided with the
+distribution.
+ * Neither the name of Google Inc. nor the names of its
+contributors may be used to endorse or promote products derived from
+this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
diff --git a/vendor/github.com/klauspost/compress/internal/snapref/decode.go b/vendor/github.com/klauspost/compress/internal/snapref/decode.go
new file mode 100644
index 000000000..40796a49d
--- /dev/null
+++ b/vendor/github.com/klauspost/compress/internal/snapref/decode.go
@@ -0,0 +1,264 @@
+// Copyright 2011 The Snappy-Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package snapref
+
+import (
+ "encoding/binary"
+ "errors"
+ "io"
+)
+
+var (
+ // ErrCorrupt reports that the input is invalid.
+ ErrCorrupt = errors.New("snappy: corrupt input")
+ // ErrTooLarge reports that the uncompressed length is too large.
+ ErrTooLarge = errors.New("snappy: decoded block is too large")
+ // ErrUnsupported reports that the input isn't supported.
+ ErrUnsupported = errors.New("snappy: unsupported input")
+
+ errUnsupportedLiteralLength = errors.New("snappy: unsupported literal length")
+)
+
+// DecodedLen returns the length of the decoded block.
+func DecodedLen(src []byte) (int, error) {
+ v, _, err := decodedLen(src)
+ return v, err
+}
+
+// decodedLen returns the length of the decoded block and the number of bytes
+// that the length header occupied.
+func decodedLen(src []byte) (blockLen, headerLen int, err error) {
+ v, n := binary.Uvarint(src)
+ if n <= 0 || v > 0xffffffff {
+ return 0, 0, ErrCorrupt
+ }
+
+ const wordSize = 32 << (^uint(0) >> 32 & 1)
+ if wordSize == 32 && v > 0x7fffffff {
+ return 0, 0, ErrTooLarge
+ }
+ return int(v), n, nil
+}
+
+const (
+ decodeErrCodeCorrupt = 1
+ decodeErrCodeUnsupportedLiteralLength = 2
+)
+
+// Decode returns the decoded form of src. The returned slice may be a sub-
+// slice of dst if dst was large enough to hold the entire decoded block.
+// Otherwise, a newly allocated slice will be returned.
+//
+// The dst and src must not overlap. It is valid to pass a nil dst.
+//
+// Decode handles the Snappy block format, not the Snappy stream format.
+func Decode(dst, src []byte) ([]byte, error) {
+ dLen, s, err := decodedLen(src)
+ if err != nil {
+ return nil, err
+ }
+ if dLen <= len(dst) {
+ dst = dst[:dLen]
+ } else {
+ dst = make([]byte, dLen)
+ }
+ switch decode(dst, src[s:]) {
+ case 0:
+ return dst, nil
+ case decodeErrCodeUnsupportedLiteralLength:
+ return nil, errUnsupportedLiteralLength
+ }
+ return nil, ErrCorrupt
+}
+
+// NewReader returns a new Reader that decompresses from r, using the framing
+// format described at
+// https://github.com/google/snappy/blob/master/framing_format.txt
+func NewReader(r io.Reader) *Reader {
+ return &Reader{
+ r: r,
+ decoded: make([]byte, maxBlockSize),
+ buf: make([]byte, maxEncodedLenOfMaxBlockSize+checksumSize),
+ }
+}
+
+// Reader is an io.Reader that can read Snappy-compressed bytes.
+//
+// Reader handles the Snappy stream format, not the Snappy block format.
+type Reader struct {
+ r io.Reader
+ err error
+ decoded []byte
+ buf []byte
+ // decoded[i:j] contains decoded bytes that have not yet been passed on.
+ i, j int
+ readHeader bool
+}
+
+// Reset discards any buffered data, resets all state, and switches the Snappy
+// reader to read from r. This permits reusing a Reader rather than allocating
+// a new one.
+func (r *Reader) Reset(reader io.Reader) {
+ r.r = reader
+ r.err = nil
+ r.i = 0
+ r.j = 0
+ r.readHeader = false
+}
+
+func (r *Reader) readFull(p []byte, allowEOF bool) (ok bool) {
+ if _, r.err = io.ReadFull(r.r, p); r.err != nil {
+ if r.err == io.ErrUnexpectedEOF || (r.err == io.EOF && !allowEOF) {
+ r.err = ErrCorrupt
+ }
+ return false
+ }
+ return true
+}
+
+func (r *Reader) fill() error {
+ for r.i >= r.j {
+ if !r.readFull(r.buf[:4], true) {
+ return r.err
+ }
+ chunkType := r.buf[0]
+ if !r.readHeader {
+ if chunkType != chunkTypeStreamIdentifier {
+ r.err = ErrCorrupt
+ return r.err
+ }
+ r.readHeader = true
+ }
+ chunkLen := int(r.buf[1]) | int(r.buf[2])<<8 | int(r.buf[3])<<16
+ if chunkLen > len(r.buf) {
+ r.err = ErrUnsupported
+ return r.err
+ }
+
+ // The chunk types are specified at
+ // https://github.com/google/snappy/blob/master/framing_format.txt
+ switch chunkType {
+ case chunkTypeCompressedData:
+ // Section 4.2. Compressed data (chunk type 0x00).
+ if chunkLen < checksumSize {
+ r.err = ErrCorrupt
+ return r.err
+ }
+ buf := r.buf[:chunkLen]
+ if !r.readFull(buf, false) {
+ return r.err
+ }
+ checksum := uint32(buf[0]) | uint32(buf[1])<<8 | uint32(buf[2])<<16 | uint32(buf[3])<<24
+ buf = buf[checksumSize:]
+
+ n, err := DecodedLen(buf)
+ if err != nil {
+ r.err = err
+ return r.err
+ }
+ if n > len(r.decoded) {
+ r.err = ErrCorrupt
+ return r.err
+ }
+ if _, err := Decode(r.decoded, buf); err != nil {
+ r.err = err
+ return r.err
+ }
+ if crc(r.decoded[:n]) != checksum {
+ r.err = ErrCorrupt
+ return r.err
+ }
+ r.i, r.j = 0, n
+ continue
+
+ case chunkTypeUncompressedData:
+ // Section 4.3. Uncompressed data (chunk type 0x01).
+ if chunkLen < checksumSize {
+ r.err = ErrCorrupt
+ return r.err
+ }
+ buf := r.buf[:checksumSize]
+ if !r.readFull(buf, false) {
+ return r.err
+ }
+ checksum := uint32(buf[0]) | uint32(buf[1])<<8 | uint32(buf[2])<<16 | uint32(buf[3])<<24
+ // Read directly into r.decoded instead of via r.buf.
+ n := chunkLen - checksumSize
+ if n > len(r.decoded) {
+ r.err = ErrCorrupt
+ return r.err
+ }
+ if !r.readFull(r.decoded[:n], false) {
+ return r.err
+ }
+ if crc(r.decoded[:n]) != checksum {
+ r.err = ErrCorrupt
+ return r.err
+ }
+ r.i, r.j = 0, n
+ continue
+
+ case chunkTypeStreamIdentifier:
+ // Section 4.1. Stream identifier (chunk type 0xff).
+ if chunkLen != len(magicBody) {
+ r.err = ErrCorrupt
+ return r.err
+ }
+ if !r.readFull(r.buf[:len(magicBody)], false) {
+ return r.err
+ }
+ for i := 0; i < len(magicBody); i++ {
+ if r.buf[i] != magicBody[i] {
+ r.err = ErrCorrupt
+ return r.err
+ }
+ }
+ continue
+ }
+
+ if chunkType <= 0x7f {
+ // Section 4.5. Reserved unskippable chunks (chunk types 0x02-0x7f).
+ r.err = ErrUnsupported
+ return r.err
+ }
+ // Section 4.4 Padding (chunk type 0xfe).
+ // Section 4.6. Reserved skippable chunks (chunk types 0x80-0xfd).
+ if !r.readFull(r.buf[:chunkLen], false) {
+ return r.err
+ }
+ }
+
+ return nil
+}
+
+// Read satisfies the io.Reader interface.
+func (r *Reader) Read(p []byte) (int, error) {
+ if r.err != nil {
+ return 0, r.err
+ }
+
+ if err := r.fill(); err != nil {
+ return 0, err
+ }
+
+ n := copy(p, r.decoded[r.i:r.j])
+ r.i += n
+ return n, nil
+}
+
+// ReadByte satisfies the io.ByteReader interface.
+func (r *Reader) ReadByte() (byte, error) {
+ if r.err != nil {
+ return 0, r.err
+ }
+
+ if err := r.fill(); err != nil {
+ return 0, err
+ }
+
+ c := r.decoded[r.i]
+ r.i++
+ return c, nil
+}
diff --git a/vendor/github.com/klauspost/compress/internal/snapref/decode_other.go b/vendor/github.com/klauspost/compress/internal/snapref/decode_other.go
new file mode 100644
index 000000000..77395a6b8
--- /dev/null
+++ b/vendor/github.com/klauspost/compress/internal/snapref/decode_other.go
@@ -0,0 +1,113 @@
+// Copyright 2016 The Snappy-Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package snapref
+
+// decode writes the decoding of src to dst. It assumes that the varint-encoded
+// length of the decompressed bytes has already been read, and that len(dst)
+// equals that length.
+//
+// It returns 0 on success or a decodeErrCodeXxx error code on failure.
+func decode(dst, src []byte) int {
+ var d, s, offset, length int
+ for s < len(src) {
+ switch src[s] & 0x03 {
+ case tagLiteral:
+ x := uint32(src[s] >> 2)
+ switch {
+ case x < 60:
+ s++
+ case x == 60:
+ s += 2
+ if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
+ return decodeErrCodeCorrupt
+ }
+ x = uint32(src[s-1])
+ case x == 61:
+ s += 3
+ if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
+ return decodeErrCodeCorrupt
+ }
+ x = uint32(src[s-2]) | uint32(src[s-1])<<8
+ case x == 62:
+ s += 4
+ if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
+ return decodeErrCodeCorrupt
+ }
+ x = uint32(src[s-3]) | uint32(src[s-2])<<8 | uint32(src[s-1])<<16
+ case x == 63:
+ s += 5
+ if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
+ return decodeErrCodeCorrupt
+ }
+ x = uint32(src[s-4]) | uint32(src[s-3])<<8 | uint32(src[s-2])<<16 | uint32(src[s-1])<<24
+ }
+ length = int(x) + 1
+ if length <= 0 {
+ return decodeErrCodeUnsupportedLiteralLength
+ }
+ if length > len(dst)-d || length > len(src)-s {
+ return decodeErrCodeCorrupt
+ }
+ copy(dst[d:], src[s:s+length])
+ d += length
+ s += length
+ continue
+
+ case tagCopy1:
+ s += 2
+ if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
+ return decodeErrCodeCorrupt
+ }
+ length = 4 + int(src[s-2])>>2&0x7
+ offset = int(uint32(src[s-2])&0xe0<<3 | uint32(src[s-1]))
+
+ case tagCopy2:
+ s += 3
+ if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
+ return decodeErrCodeCorrupt
+ }
+ length = 1 + int(src[s-3])>>2
+ offset = int(uint32(src[s-2]) | uint32(src[s-1])<<8)
+
+ case tagCopy4:
+ s += 5
+ if uint(s) > uint(len(src)) { // The uint conversions catch overflow from the previous line.
+ return decodeErrCodeCorrupt
+ }
+ length = 1 + int(src[s-5])>>2
+ offset = int(uint32(src[s-4]) | uint32(src[s-3])<<8 | uint32(src[s-2])<<16 | uint32(src[s-1])<<24)
+ }
+
+ if offset <= 0 || d < offset || length > len(dst)-d {
+ return decodeErrCodeCorrupt
+ }
+ // Copy from an earlier sub-slice of dst to a later sub-slice.
+ // If no overlap, use the built-in copy:
+ if offset >= length {
+ copy(dst[d:d+length], dst[d-offset:])
+ d += length
+ continue
+ }
+
+ // Unlike the built-in copy function, this byte-by-byte copy always runs
+ // forwards, even if the slices overlap. Conceptually, this is:
+ //
+ // d += forwardCopy(dst[d:d+length], dst[d-offset:])
+ //
+ // We align the slices into a and b and show the compiler they are the same size.
+ // This allows the loop to run without bounds checks.
+ a := dst[d : d+length]
+ b := dst[d-offset:]
+ b = b[:len(a)]
+ for i := range a {
+ a[i] = b[i]
+ }
+ d += length
+ }
+ if d != len(dst) {
+ return decodeErrCodeCorrupt
+ }
+ return 0
+}
diff --git a/vendor/github.com/klauspost/compress/internal/snapref/encode.go b/vendor/github.com/klauspost/compress/internal/snapref/encode.go
new file mode 100644
index 000000000..13c6040a5
--- /dev/null
+++ b/vendor/github.com/klauspost/compress/internal/snapref/encode.go
@@ -0,0 +1,289 @@
+// Copyright 2011 The Snappy-Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package snapref
+
+import (
+ "encoding/binary"
+ "errors"
+ "io"
+)
+
+// Encode returns the encoded form of src. The returned slice may be a sub-
+// slice of dst if dst was large enough to hold the entire encoded block.
+// Otherwise, a newly allocated slice will be returned.
+//
+// The dst and src must not overlap. It is valid to pass a nil dst.
+//
+// Encode handles the Snappy block format, not the Snappy stream format.
+func Encode(dst, src []byte) []byte {
+ if n := MaxEncodedLen(len(src)); n < 0 {
+ panic(ErrTooLarge)
+ } else if len(dst) < n {
+ dst = make([]byte, n)
+ }
+
+ // The block starts with the varint-encoded length of the decompressed bytes.
+ d := binary.PutUvarint(dst, uint64(len(src)))
+
+ for len(src) > 0 {
+ p := src
+ src = nil
+ if len(p) > maxBlockSize {
+ p, src = p[:maxBlockSize], p[maxBlockSize:]
+ }
+ if len(p) < minNonLiteralBlockSize {
+ d += emitLiteral(dst[d:], p)
+ } else {
+ d += encodeBlock(dst[d:], p)
+ }
+ }
+ return dst[:d]
+}
+
+// inputMargin is the minimum number of extra input bytes to keep, inside
+// encodeBlock's inner loop. On some architectures, this margin lets us
+// implement a fast path for emitLiteral, where the copy of short (<= 16 byte)
+// literals can be implemented as a single load to and store from a 16-byte
+// register. That literal's actual length can be as short as 1 byte, so this
+// can copy up to 15 bytes too much, but that's OK as subsequent iterations of
+// the encoding loop will fix up the copy overrun, and this inputMargin ensures
+// that we don't overrun the dst and src buffers.
+const inputMargin = 16 - 1
+
+// minNonLiteralBlockSize is the minimum size of the input to encodeBlock that
+// could be encoded with a copy tag. This is the minimum with respect to the
+// algorithm used by encodeBlock, not a minimum enforced by the file format.
+//
+// The encoded output must start with at least a 1 byte literal, as there are
+// no previous bytes to copy. A minimal (1 byte) copy after that, generated
+// from an emitCopy call in encodeBlock's main loop, would require at least
+// another inputMargin bytes, for the reason above: we want any emitLiteral
+// calls inside encodeBlock's main loop to use the fast path if possible, which
+// requires being able to overrun by inputMargin bytes. Thus,
+// minNonLiteralBlockSize equals 1 + 1 + inputMargin.
+//
+// The C++ code doesn't use this exact threshold, but it could, as discussed at
+// https://groups.google.com/d/topic/snappy-compression/oGbhsdIJSJ8/discussion
+// The difference between Go (2+inputMargin) and C++ (inputMargin) is purely an
+// optimization. It should not affect the encoded form. This is tested by
+// TestSameEncodingAsCppShortCopies.
+const minNonLiteralBlockSize = 1 + 1 + inputMargin
+
+// MaxEncodedLen returns the maximum length of a snappy block, given its
+// uncompressed length.
+//
+// It will return a negative value if srcLen is too large to encode.
+func MaxEncodedLen(srcLen int) int {
+ n := uint64(srcLen)
+ if n > 0xffffffff {
+ return -1
+ }
+ // Compressed data can be defined as:
+ // compressed := item* literal*
+ // item := literal* copy
+ //
+ // The trailing literal sequence has a space blowup of at most 62/60
+ // since a literal of length 60 needs one tag byte + one extra byte
+ // for length information.
+ //
+ // Item blowup is trickier to measure. Suppose the "copy" op copies
+ // 4 bytes of data. Because of a special check in the encoding code,
+ // we produce a 4-byte copy only if the offset is < 65536. Therefore
+ // the copy op takes 3 bytes to encode, and this type of item leads
+ // to at most the 62/60 blowup for representing literals.
+ //
+ // Suppose the "copy" op copies 5 bytes of data. If the offset is big
+ // enough, it will take 5 bytes to encode the copy op. Therefore the
+ // worst case here is a one-byte literal followed by a five-byte copy.
+ // That is, 6 bytes of input turn into 7 bytes of "compressed" data.
+ //
+ // This last factor dominates the blowup, so the final estimate is:
+ n = 32 + n + n/6
+ if n > 0xffffffff {
+ return -1
+ }
+ return int(n)
+}
+
+var errClosed = errors.New("snappy: Writer is closed")
+
+// NewWriter returns a new Writer that compresses to w.
+//
+// The Writer returned does not buffer writes. There is no need to Flush or
+// Close such a Writer.
+//
+// Deprecated: the Writer returned is not suitable for many small writes, only
+// for few large writes. Use NewBufferedWriter instead, which is efficient
+// regardless of the frequency and shape of the writes, and remember to Close
+// that Writer when done.
+func NewWriter(w io.Writer) *Writer {
+ return &Writer{
+ w: w,
+ obuf: make([]byte, obufLen),
+ }
+}
+
+// NewBufferedWriter returns a new Writer that compresses to w, using the
+// framing format described at
+// https://github.com/google/snappy/blob/master/framing_format.txt
+//
+// The Writer returned buffers writes. Users must call Close to guarantee all
+// data has been forwarded to the underlying io.Writer. They may also call
+// Flush zero or more times before calling Close.
+func NewBufferedWriter(w io.Writer) *Writer {
+ return &Writer{
+ w: w,
+ ibuf: make([]byte, 0, maxBlockSize),
+ obuf: make([]byte, obufLen),
+ }
+}
+
+// Writer is an io.Writer that can write Snappy-compressed bytes.
+//
+// Writer handles the Snappy stream format, not the Snappy block format.
+type Writer struct {
+ w io.Writer
+ err error
+
+ // ibuf is a buffer for the incoming (uncompressed) bytes.
+ //
+ // Its use is optional. For backwards compatibility, Writers created by the
+ // NewWriter function have ibuf == nil, do not buffer incoming bytes, and
+ // therefore do not need to be Flush'ed or Close'd.
+ ibuf []byte
+
+ // obuf is a buffer for the outgoing (compressed) bytes.
+ obuf []byte
+
+ // wroteStreamHeader is whether we have written the stream header.
+ wroteStreamHeader bool
+}
+
+// Reset discards the writer's state and switches the Snappy writer to write to
+// w. This permits reusing a Writer rather than allocating a new one.
+func (w *Writer) Reset(writer io.Writer) {
+ w.w = writer
+ w.err = nil
+ if w.ibuf != nil {
+ w.ibuf = w.ibuf[:0]
+ }
+ w.wroteStreamHeader = false
+}
+
+// Write satisfies the io.Writer interface.
+func (w *Writer) Write(p []byte) (nRet int, errRet error) {
+ if w.ibuf == nil {
+ // Do not buffer incoming bytes. This does not perform or compress well
+ // if the caller of Writer.Write writes many small slices. This
+ // behavior is therefore deprecated, but still supported for backwards
+ // compatibility with code that doesn't explicitly Flush or Close.
+ return w.write(p)
+ }
+
+ // The remainder of this method is based on bufio.Writer.Write from the
+ // standard library.
+
+ for len(p) > (cap(w.ibuf)-len(w.ibuf)) && w.err == nil {
+ var n int
+ if len(w.ibuf) == 0 {
+ // Large write, empty buffer.
+ // Write directly from p to avoid copy.
+ n, _ = w.write(p)
+ } else {
+ n = copy(w.ibuf[len(w.ibuf):cap(w.ibuf)], p)
+ w.ibuf = w.ibuf[:len(w.ibuf)+n]
+ w.Flush()
+ }
+ nRet += n
+ p = p[n:]
+ }
+ if w.err != nil {
+ return nRet, w.err
+ }
+ n := copy(w.ibuf[len(w.ibuf):cap(w.ibuf)], p)
+ w.ibuf = w.ibuf[:len(w.ibuf)+n]
+ nRet += n
+ return nRet, nil
+}
+
+func (w *Writer) write(p []byte) (nRet int, errRet error) {
+ if w.err != nil {
+ return 0, w.err
+ }
+ for len(p) > 0 {
+ obufStart := len(magicChunk)
+ if !w.wroteStreamHeader {
+ w.wroteStreamHeader = true
+ copy(w.obuf, magicChunk)
+ obufStart = 0
+ }
+
+ var uncompressed []byte
+ if len(p) > maxBlockSize {
+ uncompressed, p = p[:maxBlockSize], p[maxBlockSize:]
+ } else {
+ uncompressed, p = p, nil
+ }
+ checksum := crc(uncompressed)
+
+ // Compress the buffer, discarding the result if the improvement
+ // isn't at least 12.5%.
+ compressed := Encode(w.obuf[obufHeaderLen:], uncompressed)
+ chunkType := uint8(chunkTypeCompressedData)
+ chunkLen := 4 + len(compressed)
+ obufEnd := obufHeaderLen + len(compressed)
+ if len(compressed) >= len(uncompressed)-len(uncompressed)/8 {
+ chunkType = chunkTypeUncompressedData
+ chunkLen = 4 + len(uncompressed)
+ obufEnd = obufHeaderLen
+ }
+
+ // Fill in the per-chunk header that comes before the body.
+ w.obuf[len(magicChunk)+0] = chunkType
+ w.obuf[len(magicChunk)+1] = uint8(chunkLen >> 0)
+ w.obuf[len(magicChunk)+2] = uint8(chunkLen >> 8)
+ w.obuf[len(magicChunk)+3] = uint8(chunkLen >> 16)
+ w.obuf[len(magicChunk)+4] = uint8(checksum >> 0)
+ w.obuf[len(magicChunk)+5] = uint8(checksum >> 8)
+ w.obuf[len(magicChunk)+6] = uint8(checksum >> 16)
+ w.obuf[len(magicChunk)+7] = uint8(checksum >> 24)
+
+ if _, err := w.w.Write(w.obuf[obufStart:obufEnd]); err != nil {
+ w.err = err
+ return nRet, err
+ }
+ if chunkType == chunkTypeUncompressedData {
+ if _, err := w.w.Write(uncompressed); err != nil {
+ w.err = err
+ return nRet, err
+ }
+ }
+ nRet += len(uncompressed)
+ }
+ return nRet, nil
+}
+
+// Flush flushes the Writer to its underlying io.Writer.
+func (w *Writer) Flush() error {
+ if w.err != nil {
+ return w.err
+ }
+ if len(w.ibuf) == 0 {
+ return nil
+ }
+ w.write(w.ibuf)
+ w.ibuf = w.ibuf[:0]
+ return w.err
+}
+
+// Close calls Flush and then closes the Writer.
+func (w *Writer) Close() error {
+ w.Flush()
+ ret := w.err
+ if w.err == nil {
+ w.err = errClosed
+ }
+ return ret
+}
diff --git a/vendor/github.com/klauspost/compress/internal/snapref/encode_other.go b/vendor/github.com/klauspost/compress/internal/snapref/encode_other.go
new file mode 100644
index 000000000..511bba65d
--- /dev/null
+++ b/vendor/github.com/klauspost/compress/internal/snapref/encode_other.go
@@ -0,0 +1,236 @@
+// Copyright 2016 The Snappy-Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package snapref
+
+func load32(b []byte, i int) uint32 {
+ b = b[i : i+4 : len(b)] // Help the compiler eliminate bounds checks on the next line.
+ return uint32(b[0]) | uint32(b[1])<<8 | uint32(b[2])<<16 | uint32(b[3])<<24
+}
+
+func load64(b []byte, i int) uint64 {
+ b = b[i : i+8 : len(b)] // Help the compiler eliminate bounds checks on the next line.
+ return uint64(b[0]) | uint64(b[1])<<8 | uint64(b[2])<<16 | uint64(b[3])<<24 |
+ uint64(b[4])<<32 | uint64(b[5])<<40 | uint64(b[6])<<48 | uint64(b[7])<<56
+}
+
+// emitLiteral writes a literal chunk and returns the number of bytes written.
+//
+// It assumes that:
+// dst is long enough to hold the encoded bytes
+// 1 <= len(lit) && len(lit) <= 65536
+func emitLiteral(dst, lit []byte) int {
+ i, n := 0, uint(len(lit)-1)
+ switch {
+ case n < 60:
+ dst[0] = uint8(n)<<2 | tagLiteral
+ i = 1
+ case n < 1<<8:
+ dst[0] = 60<<2 | tagLiteral
+ dst[1] = uint8(n)
+ i = 2
+ default:
+ dst[0] = 61<<2 | tagLiteral
+ dst[1] = uint8(n)
+ dst[2] = uint8(n >> 8)
+ i = 3
+ }
+ return i + copy(dst[i:], lit)
+}
+
+// emitCopy writes a copy chunk and returns the number of bytes written.
+//
+// It assumes that:
+// dst is long enough to hold the encoded bytes
+// 1 <= offset && offset <= 65535
+// 4 <= length && length <= 65535
+func emitCopy(dst []byte, offset, length int) int {
+ i := 0
+ // The maximum length for a single tagCopy1 or tagCopy2 op is 64 bytes. The
+ // threshold for this loop is a little higher (at 68 = 64 + 4), and the
+ // length emitted down below is is a little lower (at 60 = 64 - 4), because
+ // it's shorter to encode a length 67 copy as a length 60 tagCopy2 followed
+ // by a length 7 tagCopy1 (which encodes as 3+2 bytes) than to encode it as
+ // a length 64 tagCopy2 followed by a length 3 tagCopy2 (which encodes as
+ // 3+3 bytes). The magic 4 in the 64±4 is because the minimum length for a
+ // tagCopy1 op is 4 bytes, which is why a length 3 copy has to be an
+ // encodes-as-3-bytes tagCopy2 instead of an encodes-as-2-bytes tagCopy1.
+ for length >= 68 {
+ // Emit a length 64 copy, encoded as 3 bytes.
+ dst[i+0] = 63<<2 | tagCopy2
+ dst[i+1] = uint8(offset)
+ dst[i+2] = uint8(offset >> 8)
+ i += 3
+ length -= 64
+ }
+ if length > 64 {
+ // Emit a length 60 copy, encoded as 3 bytes.
+ dst[i+0] = 59<<2 | tagCopy2
+ dst[i+1] = uint8(offset)
+ dst[i+2] = uint8(offset >> 8)
+ i += 3
+ length -= 60
+ }
+ if length >= 12 || offset >= 2048 {
+ // Emit the remaining copy, encoded as 3 bytes.
+ dst[i+0] = uint8(length-1)<<2 | tagCopy2
+ dst[i+1] = uint8(offset)
+ dst[i+2] = uint8(offset >> 8)
+ return i + 3
+ }
+ // Emit the remaining copy, encoded as 2 bytes.
+ dst[i+0] = uint8(offset>>8)<<5 | uint8(length-4)<<2 | tagCopy1
+ dst[i+1] = uint8(offset)
+ return i + 2
+}
+
+// extendMatch returns the largest k such that k <= len(src) and that
+// src[i:i+k-j] and src[j:k] have the same contents.
+//
+// It assumes that:
+// 0 <= i && i < j && j <= len(src)
+func extendMatch(src []byte, i, j int) int {
+ for ; j < len(src) && src[i] == src[j]; i, j = i+1, j+1 {
+ }
+ return j
+}
+
+func hash(u, shift uint32) uint32 {
+ return (u * 0x1e35a7bd) >> shift
+}
+
+// encodeBlock encodes a non-empty src to a guaranteed-large-enough dst. It
+// assumes that the varint-encoded length of the decompressed bytes has already
+// been written.
+//
+// It also assumes that:
+// len(dst) >= MaxEncodedLen(len(src)) &&
+// minNonLiteralBlockSize <= len(src) && len(src) <= maxBlockSize
+func encodeBlock(dst, src []byte) (d int) {
+ // Initialize the hash table. Its size ranges from 1<<8 to 1<<14 inclusive.
+ // The table element type is uint16, as s < sLimit and sLimit < len(src)
+ // and len(src) <= maxBlockSize and maxBlockSize == 65536.
+ const (
+ maxTableSize = 1 << 14
+ // tableMask is redundant, but helps the compiler eliminate bounds
+ // checks.
+ tableMask = maxTableSize - 1
+ )
+ shift := uint32(32 - 8)
+ for tableSize := 1 << 8; tableSize < maxTableSize && tableSize < len(src); tableSize *= 2 {
+ shift--
+ }
+ // In Go, all array elements are zero-initialized, so there is no advantage
+ // to a smaller tableSize per se. However, it matches the C++ algorithm,
+ // and in the asm versions of this code, we can get away with zeroing only
+ // the first tableSize elements.
+ var table [maxTableSize]uint16
+
+ // sLimit is when to stop looking for offset/length copies. The inputMargin
+ // lets us use a fast path for emitLiteral in the main loop, while we are
+ // looking for copies.
+ sLimit := len(src) - inputMargin
+
+ // nextEmit is where in src the next emitLiteral should start from.
+ nextEmit := 0
+
+ // The encoded form must start with a literal, as there are no previous
+ // bytes to copy, so we start looking for hash matches at s == 1.
+ s := 1
+ nextHash := hash(load32(src, s), shift)
+
+ for {
+ // Copied from the C++ snappy implementation:
+ //
+ // Heuristic match skipping: If 32 bytes are scanned with no matches
+ // found, start looking only at every other byte. If 32 more bytes are
+ // scanned (or skipped), look at every third byte, etc.. When a match
+ // is found, immediately go back to looking at every byte. This is a
+ // small loss (~5% performance, ~0.1% density) for compressible data
+ // due to more bookkeeping, but for non-compressible data (such as
+ // JPEG) it's a huge win since the compressor quickly "realizes" the
+ // data is incompressible and doesn't bother looking for matches
+ // everywhere.
+ //
+ // The "skip" variable keeps track of how many bytes there are since
+ // the last match; dividing it by 32 (ie. right-shifting by five) gives
+ // the number of bytes to move ahead for each iteration.
+ skip := 32
+
+ nextS := s
+ candidate := 0
+ for {
+ s = nextS
+ bytesBetweenHashLookups := skip >> 5
+ nextS = s + bytesBetweenHashLookups
+ skip += bytesBetweenHashLookups
+ if nextS > sLimit {
+ goto emitRemainder
+ }
+ candidate = int(table[nextHash&tableMask])
+ table[nextHash&tableMask] = uint16(s)
+ nextHash = hash(load32(src, nextS), shift)
+ if load32(src, s) == load32(src, candidate) {
+ break
+ }
+ }
+
+ // A 4-byte match has been found. We'll later see if more than 4 bytes
+ // match. But, prior to the match, src[nextEmit:s] are unmatched. Emit
+ // them as literal bytes.
+ d += emitLiteral(dst[d:], src[nextEmit:s])
+
+ // Call emitCopy, and then see if another emitCopy could be our next
+ // move. Repeat until we find no match for the input immediately after
+ // what was consumed by the last emitCopy call.
+ //
+ // If we exit this loop normally then we need to call emitLiteral next,
+ // though we don't yet know how big the literal will be. We handle that
+ // by proceeding to the next iteration of the main loop. We also can
+ // exit this loop via goto if we get close to exhausting the input.
+ for {
+ // Invariant: we have a 4-byte match at s, and no need to emit any
+ // literal bytes prior to s.
+ base := s
+
+ // Extend the 4-byte match as long as possible.
+ //
+ // This is an inlined version of:
+ // s = extendMatch(src, candidate+4, s+4)
+ s += 4
+ for i := candidate + 4; s < len(src) && src[i] == src[s]; i, s = i+1, s+1 {
+ }
+
+ d += emitCopy(dst[d:], base-candidate, s-base)
+ nextEmit = s
+ if s >= sLimit {
+ goto emitRemainder
+ }
+
+ // We could immediately start working at s now, but to improve
+ // compression we first update the hash table at s-1 and at s. If
+ // another emitCopy is not our next move, also calculate nextHash
+ // at s+1. At least on GOARCH=amd64, these three hash calculations
+ // are faster as one load64 call (with some shifts) instead of
+ // three load32 calls.
+ x := load64(src, s-1)
+ prevHash := hash(uint32(x>>0), shift)
+ table[prevHash&tableMask] = uint16(s - 1)
+ currHash := hash(uint32(x>>8), shift)
+ candidate = int(table[currHash&tableMask])
+ table[currHash&tableMask] = uint16(s)
+ if uint32(x>>8) != load32(src, candidate) {
+ nextHash = hash(uint32(x>>16), shift)
+ s++
+ break
+ }
+ }
+ }
+
+emitRemainder:
+ if nextEmit < len(src) {
+ d += emitLiteral(dst[d:], src[nextEmit:])
+ }
+ return d
+}
diff --git a/vendor/github.com/klauspost/compress/internal/snapref/snappy.go b/vendor/github.com/klauspost/compress/internal/snapref/snappy.go
new file mode 100644
index 000000000..34d01f4aa
--- /dev/null
+++ b/vendor/github.com/klauspost/compress/internal/snapref/snappy.go
@@ -0,0 +1,98 @@
+// Copyright 2011 The Snappy-Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+// Package snapref implements the Snappy compression format. It aims for very
+// high speeds and reasonable compression.
+//
+// There are actually two Snappy formats: block and stream. They are related,
+// but different: trying to decompress block-compressed data as a Snappy stream
+// will fail, and vice versa. The block format is the Decode and Encode
+// functions and the stream format is the Reader and Writer types.
+//
+// The block format, the more common case, is used when the complete size (the
+// number of bytes) of the original data is known upfront, at the time
+// compression starts. The stream format, also known as the framing format, is
+// for when that isn't always true.
+//
+// The canonical, C++ implementation is at https://github.com/google/snappy and
+// it only implements the block format.
+package snapref
+
+import (
+ "hash/crc32"
+)
+
+/*
+Each encoded block begins with the varint-encoded length of the decoded data,
+followed by a sequence of chunks. Chunks begin and end on byte boundaries. The
+first byte of each chunk is broken into its 2 least and 6 most significant bits
+called l and m: l ranges in [0, 4) and m ranges in [0, 64). l is the chunk tag.
+Zero means a literal tag. All other values mean a copy tag.
+
+For literal tags:
+ - If m < 60, the next 1 + m bytes are literal bytes.
+ - Otherwise, let n be the little-endian unsigned integer denoted by the next
+ m - 59 bytes. The next 1 + n bytes after that are literal bytes.
+
+For copy tags, length bytes are copied from offset bytes ago, in the style of
+Lempel-Ziv compression algorithms. In particular:
+ - For l == 1, the offset ranges in [0, 1<<11) and the length in [4, 12).
+ The length is 4 + the low 3 bits of m. The high 3 bits of m form bits 8-10
+ of the offset. The next byte is bits 0-7 of the offset.
+ - For l == 2, the offset ranges in [0, 1<<16) and the length in [1, 65).
+ The length is 1 + m. The offset is the little-endian unsigned integer
+ denoted by the next 2 bytes.
+ - For l == 3, this tag is a legacy format that is no longer issued by most
+ encoders. Nonetheless, the offset ranges in [0, 1<<32) and the length in
+ [1, 65). The length is 1 + m. The offset is the little-endian unsigned
+ integer denoted by the next 4 bytes.
+*/
+const (
+ tagLiteral = 0x00
+ tagCopy1 = 0x01
+ tagCopy2 = 0x02
+ tagCopy4 = 0x03
+)
+
+const (
+ checksumSize = 4
+ chunkHeaderSize = 4
+ magicChunk = "\xff\x06\x00\x00" + magicBody
+ magicBody = "sNaPpY"
+
+ // maxBlockSize is the maximum size of the input to encodeBlock. It is not
+ // part of the wire format per se, but some parts of the encoder assume
+ // that an offset fits into a uint16.
+ //
+ // Also, for the framing format (Writer type instead of Encode function),
+ // https://github.com/google/snappy/blob/master/framing_format.txt says
+ // that "the uncompressed data in a chunk must be no longer than 65536
+ // bytes".
+ maxBlockSize = 65536
+
+ // maxEncodedLenOfMaxBlockSize equals MaxEncodedLen(maxBlockSize), but is
+ // hard coded to be a const instead of a variable, so that obufLen can also
+ // be a const. Their equivalence is confirmed by
+ // TestMaxEncodedLenOfMaxBlockSize.
+ maxEncodedLenOfMaxBlockSize = 76490
+
+ obufHeaderLen = len(magicChunk) + checksumSize + chunkHeaderSize
+ obufLen = obufHeaderLen + maxEncodedLenOfMaxBlockSize
+)
+
+const (
+ chunkTypeCompressedData = 0x00
+ chunkTypeUncompressedData = 0x01
+ chunkTypePadding = 0xfe
+ chunkTypeStreamIdentifier = 0xff
+)
+
+var crcTable = crc32.MakeTable(crc32.Castagnoli)
+
+// crc implements the checksum specified in section 3 of
+// https://github.com/google/snappy/blob/master/framing_format.txt
+func crc(b []byte) uint32 {
+ c := crc32.Update(0, crcTable, b)
+ return uint32(c>>15|c<<17) + 0xa282ead8
+}