forgejo/modules/lfs/pointer.go
Gusted abd94ff5b5
[GITEA] Drop sha256-simd in favor of stdlib
- In Go 1.21 the crypto/sha256 [got a massive
improvement](https://go.dev/doc/go1.21#crypto/sha256) by utilizing the
SHA instructions for AMD64 CPUs, which sha256-simd already was doing.
The performance is now on par and I think it's preferable to use the
standard library rather than a package when possible.

```
cpu: AMD Ryzen 5 3600X 6-Core Processor
                │  simd.txt   │               go.txt                │
                │   sec/op    │    sec/op     vs base               │
Hash/8Bytes-12    63.25n ± 1%    73.38n ± 1%  +16.02% (p=0.002 n=6)
Hash/64Bytes-12   98.73n ± 1%   105.30n ± 1%   +6.65% (p=0.002 n=6)
Hash/1K-12        567.2n ± 1%    572.8n ± 1%   +0.99% (p=0.002 n=6)
Hash/8K-12        4.062µ ± 1%    4.062µ ± 1%        ~ (p=0.396 n=6)
Hash/1M-12        512.1µ ± 0%    510.6µ ± 1%        ~ (p=0.485 n=6)
Hash/5M-12        2.556m ± 1%    2.564m ± 0%        ~ (p=0.093 n=6)
Hash/10M-12       5.112m ± 0%    5.127m ± 0%        ~ (p=0.093 n=6)
geomean           13.82µ         14.27µ        +3.28%

                │   simd.txt   │               go.txt                │
                │     B/s      │     B/s       vs base               │
Hash/8Bytes-12    120.6Mi ± 1%   104.0Mi ± 1%  -13.81% (p=0.002 n=6)
Hash/64Bytes-12   618.2Mi ± 1%   579.8Mi ± 1%   -6.22% (p=0.002 n=6)
Hash/1K-12        1.682Gi ± 1%   1.665Gi ± 1%   -0.98% (p=0.002 n=6)
Hash/8K-12        1.878Gi ± 1%   1.878Gi ± 1%        ~ (p=0.310 n=6)
Hash/1M-12        1.907Gi ± 0%   1.913Gi ± 1%        ~ (p=0.485 n=6)
Hash/5M-12        1.911Gi ± 1%   1.904Gi ± 0%        ~ (p=0.093 n=6)
Hash/10M-12       1.910Gi ± 0%   1.905Gi ± 0%        ~ (p=0.093 n=6)
geomean           1.066Gi        1.032Gi        -3.18%
```
2023-09-30 00:50:25 +02:00

130 lines
3.2 KiB
Go

// Copyright 2021 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package lfs
import (
"crypto/sha256"
"encoding/hex"
"errors"
"fmt"
"io"
"path"
"regexp"
"strconv"
"strings"
)
const (
blobSizeCutoff = 1024
// MetaFileIdentifier is the string appearing at the first line of LFS pointer files.
// https://github.com/git-lfs/git-lfs/blob/master/docs/spec.md
MetaFileIdentifier = "version https://git-lfs.github.com/spec/v1"
// MetaFileOidPrefix appears in LFS pointer files on a line before the sha256 hash.
MetaFileOidPrefix = "oid sha256:"
)
var (
// ErrMissingPrefix occurs if the content lacks the LFS prefix
ErrMissingPrefix = errors.New("content lacks the LFS prefix")
// ErrInvalidStructure occurs if the content has an invalid structure
ErrInvalidStructure = errors.New("content has an invalid structure")
// ErrInvalidOIDFormat occurs if the oid has an invalid format
ErrInvalidOIDFormat = errors.New("OID has an invalid format")
)
// ReadPointer tries to read LFS pointer data from the reader
func ReadPointer(reader io.Reader) (Pointer, error) {
buf := make([]byte, blobSizeCutoff)
n, err := io.ReadFull(reader, buf)
if err != nil && err != io.ErrUnexpectedEOF {
return Pointer{}, err
}
buf = buf[:n]
return ReadPointerFromBuffer(buf)
}
var oidPattern = regexp.MustCompile(`^[a-f\d]{64}$`)
// ReadPointerFromBuffer will return a pointer if the provided byte slice is a pointer file or an error otherwise.
func ReadPointerFromBuffer(buf []byte) (Pointer, error) {
var p Pointer
headString := string(buf)
if !strings.HasPrefix(headString, MetaFileIdentifier) {
return p, ErrMissingPrefix
}
splitLines := strings.Split(headString, "\n")
if len(splitLines) < 3 {
return p, ErrInvalidStructure
}
oid := strings.TrimPrefix(splitLines[1], MetaFileOidPrefix)
if len(oid) != 64 || !oidPattern.MatchString(oid) {
return p, ErrInvalidOIDFormat
}
size, err := strconv.ParseInt(strings.TrimPrefix(splitLines[2], "size "), 10, 64)
if err != nil {
return p, err
}
p.Oid = oid
p.Size = size
return p, nil
}
// IsValid checks if the pointer has a valid structure.
// It doesn't check if the pointed-to-content exists.
func (p Pointer) IsValid() bool {
if len(p.Oid) != 64 {
return false
}
if !oidPattern.MatchString(p.Oid) {
return false
}
if p.Size < 0 {
return false
}
return true
}
// StringContent returns the string representation of the pointer
// https://github.com/git-lfs/git-lfs/blob/main/docs/spec.md#the-pointer
func (p Pointer) StringContent() string {
return fmt.Sprintf("%s\n%s%s\nsize %d\n", MetaFileIdentifier, MetaFileOidPrefix, p.Oid, p.Size)
}
// RelativePath returns the relative storage path of the pointer
func (p Pointer) RelativePath() string {
if len(p.Oid) < 5 {
return p.Oid
}
return path.Join(p.Oid[0:2], p.Oid[2:4], p.Oid[4:])
}
func (p Pointer) LogString() string {
if p.Oid == "" && p.Size == 0 {
return "<LFSPointer empty>"
}
return fmt.Sprintf("<LFSPointer %s:%d>", p.Oid, p.Size)
}
// GeneratePointer generates a pointer for arbitrary content
func GeneratePointer(content io.Reader) (Pointer, error) {
h := sha256.New()
c, err := io.Copy(h, content)
if err != nil {
return Pointer{}, err
}
sum := h.Sum(nil)
return Pointer{Oid: hex.EncodeToString(sum), Size: c}, nil
}