Update vendoring

This commit is contained in:
Jeff Mitchell
2016-06-01 10:24:48 -04:00
parent ed0897330b
commit 7fd919f908
229 changed files with 13493 additions and 9865 deletions

View File

@@ -1,16 +0,0 @@
cmd/snappytool/snappytool
testdata/bench
# These explicitly listed benchmark data files are for an obsolete version of
# snappy_test.go.
testdata/alice29.txt
testdata/asyoulik.txt
testdata/fireworks.jpeg
testdata/geo.protodata
testdata/html
testdata/html_x_4
testdata/kppkn.gtb
testdata/lcet10.txt
testdata/paper-100k.pdf
testdata/plrabn12.txt
testdata/urls.10K

View File

@@ -13,65 +13,65 @@ Benchmarks.
The golang/snappy benchmarks include compressing (Z) and decompressing (U) ten
or so files, the same set used by the C++ Snappy code (github.com/google/snappy
and note the "google", not "golang"). On an "Intel(R) Core(TM) i7-3770 CPU @
3.40GHz", Go's GOARCH=amd64 numbers as of 2016-04-29:
3.40GHz", Go's GOARCH=amd64 numbers as of 2016-05-29:
"go test -test.bench=."
_UFlat0-8 2.23GB/s ± 1% html
_UFlat1-8 1.43GB/s ± 0% urls
_UFlat2-8 23.7GB/s ± 1% jpg
_UFlat3-8 1.93GB/s ± 0% jpg_200
_UFlat4-8 13.9GB/s ± 2% pdf
_UFlat5-8 2.00GB/s ± 0% html4
_UFlat6-8 829MB/s ± 0% txt1
_UFlat7-8 799MB/s ± 0% txt2
_UFlat8-8 871MB/s ± 0% txt3
_UFlat9-8 730MB/s ± 0% txt4
_UFlat10-8 2.87GB/s ± 0% pb
_UFlat11-8 1.07GB/s ± 0% gaviota
_UFlat0-8 2.19GB/s ± 0% html
_UFlat1-8 1.41GB/s ± 0% urls
_UFlat2-8 23.5GB/s ± 2% jpg
_UFlat3-8 1.91GB/s ± 0% jpg_200
_UFlat4-8 14.0GB/s ± 1% pdf
_UFlat5-8 1.97GB/s ± 0% html4
_UFlat6-8 814MB/s ± 0% txt1
_UFlat7-8 785MB/s ± 0% txt2
_UFlat8-8 857MB/s ± 0% txt3
_UFlat9-8 719MB/s ± 1% txt4
_UFlat10-8 2.84GB/s ± 0% pb
_UFlat11-8 1.05GB/s ± 0% gaviota
_ZFlat0-8 1.04GB/s ± 0% html
_ZFlat1-8 536MB/s ± 0% urls
_ZFlat2-8 16.3GB/s ± 2% jpg
_ZFlat3-8 762MB/s ± 0% jpg_200
_ZFlat4-8 9.48GB/s ± 1% pdf
_ZFlat5-8 990MB/s ± 0% html4
_ZFlat6-8 381MB/s ± 0% txt1
_ZFlat7-8 353MB/s ± 0% txt2
_ZFlat8-8 398MB/s ± 0% txt3
_ZFlat9-8 329MB/s ± 0% txt4
_ZFlat10-8 1.35GB/s ± 1% pb
_ZFlat11-8 608MB/s ± 0% gaviota
_ZFlat1-8 534MB/s ± 0% urls
_ZFlat2-8 15.7GB/s ± 1% jpg
_ZFlat3-8 740MB/s ± 3% jpg_200
_ZFlat4-8 9.20GB/s ± 1% pdf
_ZFlat5-8 991MB/s ± 0% html4
_ZFlat6-8 379MB/s ± 0% txt1
_ZFlat7-8 352MB/s ± 0% txt2
_ZFlat8-8 396MB/s ± 1% txt3
_ZFlat9-8 327MB/s ± 1% txt4
_ZFlat10-8 1.33GB/s ± 1% pb
_ZFlat11-8 605MB/s ± 1% gaviota
"go test -test.bench=. -tags=noasm"
_UFlat0-8 637MB/s ± 0% html
_UFlat1-8 506MB/s ± 0% urls
_UFlat2-8 23.0GB/s ± 5% jpg
_UFlat3-8 1.17GB/s ± 0% jpg_200
_UFlat4-8 4.44GB/s ± 1% pdf
_UFlat5-8 623MB/s ± 0% html4
_UFlat6-8 300MB/s ± 1% txt1
_UFlat7-8 293MB/s ± 0% txt2
_UFlat8-8 316MB/s ± 0% txt3
_UFlat9-8 285MB/s ± 0% txt4
_UFlat10-8 768MB/s ± 0% pb
_UFlat11-8 406MB/s ± 1% gaviota
_UFlat0-8 621MB/s ± 2% html
_UFlat1-8 494MB/s ± 1% urls
_UFlat2-8 23.2GB/s ± 1% jpg
_UFlat3-8 1.12GB/s ± 1% jpg_200
_UFlat4-8 4.35GB/s ± 1% pdf
_UFlat5-8 609MB/s ± 0% html4
_UFlat6-8 296MB/s ± 0% txt1
_UFlat7-8 288MB/s ± 0% txt2
_UFlat8-8 309MB/s ± 1% txt3
_UFlat9-8 280MB/s ± 1% txt4
_UFlat10-8 753MB/s ± 0% pb
_UFlat11-8 400MB/s ± 0% gaviota
_ZFlat0-8 411MB/s ± 1% html
_ZFlat0-8 409MB/s ± 1% html
_ZFlat1-8 250MB/s ± 1% urls
_ZFlat2-8 12.7GB/s ± 1% jpg
_ZFlat3-8 157MB/s ± 0% jpg_200
_ZFlat4-8 2.95GB/s ± 0% pdf
_ZFlat5-8 406MB/s ± 0% html4
_ZFlat6-8 182MB/s ± 0% txt1
_ZFlat7-8 173MB/s ± 1% txt2
_ZFlat8-8 191MB/s ± 0% txt3
_ZFlat9-8 166MB/s ± 0% txt4
_ZFlat10-8 480MB/s ± 0% pb
_ZFlat11-8 272MB/s ± 0% gaviota
_ZFlat2-8 12.3GB/s ± 1% jpg
_ZFlat3-8 132MB/s ± 0% jpg_200
_ZFlat4-8 2.92GB/s ± 0% pdf
_ZFlat5-8 405MB/s ± 1% html4
_ZFlat6-8 179MB/s ± 1% txt1
_ZFlat7-8 170MB/s ± 1% txt2
_ZFlat8-8 189MB/s ± 1% txt3
_ZFlat9-8 164MB/s ± 1% txt4
_ZFlat10-8 479MB/s ± 1% pb
_ZFlat11-8 270MB/s ± 1% gaviota

View File

@@ -18,7 +18,6 @@ var (
// ErrUnsupported reports that the input isn't supported.
ErrUnsupported = errors.New("snappy: unsupported input")
errUnsupportedCopy4Tag = errors.New("snappy: unsupported COPY_4 tag")
errUnsupportedLiteralLength = errors.New("snappy: unsupported literal length")
)
@@ -46,7 +45,6 @@ func decodedLen(src []byte) (blockLen, headerLen int, err error) {
const (
decodeErrCodeCorrupt = 1
decodeErrCodeUnsupportedLiteralLength = 2
decodeErrCodeUnsupportedCopy4Tag = 3
)
// Decode returns the decoded form of src. The returned slice may be a sub-
@@ -69,8 +67,6 @@ func Decode(dst, src []byte) ([]byte, error) {
return dst, nil
case decodeErrCodeUnsupportedLiteralLength:
return nil, errUnsupportedLiteralLength
case decodeErrCodeUnsupportedCopy4Tag:
return nil, errUnsupportedCopy4Tag
}
return nil, ErrCorrupt
}

View File

@@ -226,6 +226,25 @@ tagLit63:
// ----------------------------------------
// The code below handles copy tags.
tagCopy4:
// case tagCopy4:
// s += 5
ADDQ $5, SI
// if uint(s) > uint(len(src)) { etc }
MOVQ SI, BX
SUBQ R11, BX
CMPQ BX, R12
JA errCorrupt
// length = 1 + int(src[s-5])>>2
SHRQ $2, CX
INCQ CX
// offset = int(uint32(src[s-4]) | uint32(src[s-3])<<8 | uint32(src[s-2])<<16 | uint32(src[s-1])<<24)
MOVLQZX -4(SI), DX
JMP doCopy
tagCopy2:
// case tagCopy2:
// s += 3
@@ -241,7 +260,7 @@ tagCopy2:
SHRQ $2, CX
INCQ CX
// offset = int(src[s-2]) | int(src[s-1])<<8
// offset = int(uint32(src[s-2]) | uint32(src[s-1])<<8)
MOVWQZX -2(SI), DX
JMP doCopy
@@ -251,7 +270,7 @@ tagCopy:
// - CX == src[s]
CMPQ BX, $2
JEQ tagCopy2
JA errUC4T
JA tagCopy4
// case tagCopy1:
// s += 2
@@ -263,7 +282,7 @@ tagCopy:
CMPQ BX, R12
JA errCorrupt
// offset = int(src[s-2])&0xe0<<3 | int(src[s-1])
// offset = int(uint32(src[s-2])&0xe0<<3 | uint32(src[s-1]))
MOVQ CX, DX
ANDQ $0xe0, DX
SHLQ $3, DX
@@ -469,8 +488,3 @@ errCorrupt:
// return decodeErrCodeCorrupt
MOVQ $1, ret+48(FP)
RET
errUC4T:
// return decodeErrCodeUnsupportedCopy4Tag
MOVQ $3, ret+48(FP)
RET

View File

@@ -1,96 +0,0 @@
// 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.
// +build !amd64 appengine !gc noasm
package snappy
// 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(src[s-2])&0xe0<<3 | int(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(src[s-2]) | int(src[s-1])<<8
case tagCopy4:
return decodeErrCodeUnsupportedCopy4Tag
}
if offset <= 0 || d < offset || length > len(dst)-d {
return decodeErrCodeCorrupt
}
// Copy from an earlier sub-slice of dst to a later sub-slice. 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:])
for end := d + length; d != end; d++ {
dst[d] = dst[d-offset]
}
}
if d != len(dst) {
return decodeErrCodeCorrupt
}
return 0
}

View File

@@ -26,4 +26,4 @@ func extendMatch(src []byte, i, j int) int
// encodeBlock has the same semantics as in encode_other.go.
//
//go:noescape
func encodeBlock(dst, src []byte) (d int)
func encodeBlock(dst, src []byte) (d int)

View File

@@ -1,238 +0,0 @@
// 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.
// +build !amd64 appengine !gc noasm
package snappy
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
}

View File

@@ -6,7 +6,7 @@
// It aims for very high speeds and reasonable compression.
//
// The C++ snappy implementation is at https://github.com/google/snappy
package snappy
package snappy // import "github.com/golang/snappy"
import (
"hash/crc32"
@@ -32,7 +32,10 @@ Lempel-Ziv compression algorithms. In particular:
- 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 supported.
- 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