Add deterministic file ordering in Builder.Build()
Sort file entries by path (lexicographic, byte-order) before serialization to ensure deterministic output. Add fixedUUID support for testing reproducibility, and a test asserting byte-identical output from two runs with the same input. Closes #23
This commit is contained in:
parent
1f12d10cb7
commit
410dd20032
@ -5,6 +5,7 @@ import (
|
|||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"io"
|
"io"
|
||||||
|
"sort"
|
||||||
"strings"
|
"strings"
|
||||||
"sync"
|
"sync"
|
||||||
"time"
|
"time"
|
||||||
@ -88,6 +89,7 @@ type Builder struct {
|
|||||||
files []*MFFilePath
|
files []*MFFilePath
|
||||||
createdAt time.Time
|
createdAt time.Time
|
||||||
signingOptions *SigningOptions
|
signingOptions *SigningOptions
|
||||||
|
fixedUUID []byte // if set, use this UUID instead of generating one
|
||||||
}
|
}
|
||||||
|
|
||||||
// NewBuilder creates a new Builder.
|
// NewBuilder creates a new Builder.
|
||||||
@ -222,6 +224,11 @@ func (b *Builder) Build(w io.Writer) error {
|
|||||||
b.mu.Lock()
|
b.mu.Lock()
|
||||||
defer b.mu.Unlock()
|
defer b.mu.Unlock()
|
||||||
|
|
||||||
|
// Sort files by path for deterministic output
|
||||||
|
sort.Slice(b.files, func(i, j int) bool {
|
||||||
|
return b.files[i].Path < b.files[j].Path
|
||||||
|
})
|
||||||
|
|
||||||
// Create inner manifest
|
// Create inner manifest
|
||||||
inner := &MFFile{
|
inner := &MFFile{
|
||||||
Version: MFFile_VERSION_ONE,
|
Version: MFFile_VERSION_ONE,
|
||||||
@ -233,6 +240,7 @@ func (b *Builder) Build(w io.Writer) error {
|
|||||||
m := &manifest{
|
m := &manifest{
|
||||||
pbInner: inner,
|
pbInner: inner,
|
||||||
signingOptions: b.signingOptions,
|
signingOptions: b.signingOptions,
|
||||||
|
fixedUUID: b.fixedUUID,
|
||||||
}
|
}
|
||||||
|
|
||||||
// Generate outer wrapper
|
// Generate outer wrapper
|
||||||
|
|||||||
@ -115,6 +115,41 @@ func TestNewTimestampFromTimeExtremeDate(t *testing.T) {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func TestBuilderDeterministicOutput(t *testing.T) {
|
||||||
|
buildManifest := func() []byte {
|
||||||
|
b := NewBuilder()
|
||||||
|
// Use a fixed createdAt and UUID so output is reproducible
|
||||||
|
b.createdAt = time.Date(2025, 1, 1, 0, 0, 0, 0, time.UTC)
|
||||||
|
b.fixedUUID = make([]byte, 16) // all zeros
|
||||||
|
|
||||||
|
mtime := ModTime(time.Date(2025, 6, 1, 0, 0, 0, 0, time.UTC))
|
||||||
|
|
||||||
|
// Add files in reverse order to test sorting
|
||||||
|
files := []struct {
|
||||||
|
path string
|
||||||
|
content string
|
||||||
|
}{
|
||||||
|
{"c/file.txt", "content c"},
|
||||||
|
{"a/file.txt", "content a"},
|
||||||
|
{"b/file.txt", "content b"},
|
||||||
|
}
|
||||||
|
for _, f := range files {
|
||||||
|
r := bytes.NewReader([]byte(f.content))
|
||||||
|
_, err := b.AddFile(RelFilePath(f.path), FileSize(len(f.content)), mtime, r, nil)
|
||||||
|
require.NoError(t, err)
|
||||||
|
}
|
||||||
|
|
||||||
|
var buf bytes.Buffer
|
||||||
|
err := b.Build(&buf)
|
||||||
|
require.NoError(t, err)
|
||||||
|
return buf.Bytes()
|
||||||
|
}
|
||||||
|
|
||||||
|
out1 := buildManifest()
|
||||||
|
out2 := buildManifest()
|
||||||
|
assert.Equal(t, out1, out2, "two builds with same input should produce byte-identical output")
|
||||||
|
}
|
||||||
|
|
||||||
func TestBuilderBuildEmpty(t *testing.T) {
|
func TestBuilderBuildEmpty(t *testing.T) {
|
||||||
b := NewBuilder()
|
b := NewBuilder()
|
||||||
|
|
||||||
|
|||||||
@ -17,6 +17,7 @@ type manifest struct {
|
|||||||
pbOuter *MFFileOuter
|
pbOuter *MFFileOuter
|
||||||
output *bytes.Buffer
|
output *bytes.Buffer
|
||||||
signingOptions *SigningOptions
|
signingOptions *SigningOptions
|
||||||
|
fixedUUID []byte // if set, use this UUID instead of generating one
|
||||||
}
|
}
|
||||||
|
|
||||||
func (m *manifest) String() string {
|
func (m *manifest) String() string {
|
||||||
|
|||||||
@ -49,8 +49,13 @@ func (m *manifest) generateOuter() error {
|
|||||||
return errors.New("internal error")
|
return errors.New("internal error")
|
||||||
}
|
}
|
||||||
|
|
||||||
// Generate UUID and set on inner message
|
// Use fixed UUID if provided, otherwise generate a new one
|
||||||
manifestUUID := uuid.New()
|
var manifestUUID uuid.UUID
|
||||||
|
if len(m.fixedUUID) == 16 {
|
||||||
|
copy(manifestUUID[:], m.fixedUUID)
|
||||||
|
} else {
|
||||||
|
manifestUUID = uuid.New()
|
||||||
|
}
|
||||||
m.pbInner.Uuid = manifestUUID[:]
|
m.pbInner.Uuid = manifestUUID[:]
|
||||||
|
|
||||||
innerData, err := proto.MarshalOptions{Deterministic: true}.Marshal(m.pbInner)
|
innerData, err := proto.MarshalOptions{Deterministic: true}.Marshal(m.pbInner)
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user