Add deterministic file ordering in Builder.Build() (closes #23) #28
@ -25,6 +25,12 @@ func (mfa *CLIApp) generateManifestOperation(ctx *cli.Context) error {
|
||||
Fs: mfa.Fs,
|
||||
}
|
||||
|
||||
// Set seed for deterministic UUID if provided
|
||||
if seed := ctx.String("seed"); seed != "" {
|
||||
opts.Seed = seed
|
||||
log.Infof("using deterministic seed for manifest UUID")
|
||||
}
|
||||
|
||||
// Set up signing options if sign-key is provided
|
||||
if signKey := ctx.String("sign-key"); signKey != "" {
|
||||
opts.SigningOptions = &mfer.SigningOptions{
|
||||
|
||||
@ -154,6 +154,11 @@ func (mfa *CLIApp) run(args []string) {
|
||||
Usage: "GPG key ID to sign the manifest with",
|
||||
EnvVars: []string{"MFER_SIGN_KEY"},
|
||||
},
|
||||
&cli.StringFlag{
|
||||
Name: "seed",
|
||||
Usage: "Seed value for deterministic manifest UUID (hashed 1B times with SHA-256)",
|
||||
EnvVars: []string{"MFER_SEED"},
|
||||
},
|
||||
),
|
||||
},
|
||||
{
|
||||
|
||||
@ -92,6 +92,26 @@ type Builder struct {
|
||||
fixedUUID []byte // if set, use this UUID instead of generating one
|
||||
}
|
||||
|
||||
// seedIterations is the number of SHA-256 rounds used to derive a UUID from a seed.
|
||||
const seedIterations = 1_000_000_000
|
||||
|
||||
// SetSeed derives a deterministic UUID from the given seed string.
|
||||
// The seed is hashed 1,000,000,000 times with SHA-256 to produce
|
||||
// 16 bytes used as a fixed UUID for the manifest.
|
||||
func (b *Builder) SetSeed(seed string) {
|
||||
b.fixedUUID = deriveSeedUUID(seed, seedIterations)
|
||||
}
|
||||
|
||||
// deriveSeedUUID hashes the seed string n times with SHA-256
|
||||
// and returns the first 16 bytes as a UUID.
|
||||
func deriveSeedUUID(seed string, iterations int) []byte {
|
||||
hash := sha256.Sum256([]byte(seed))
|
||||
for i := 1; i < iterations; i++ {
|
||||
hash = sha256.Sum256(hash[:])
|
||||
}
|
||||
return hash[:16]
|
||||
}
|
||||
|
||||
// NewBuilder creates a new Builder.
|
||||
func NewBuilder() *Builder {
|
||||
return &Builder{
|
||||
|
||||
@ -150,6 +150,17 @@ func TestBuilderDeterministicOutput(t *testing.T) {
|
||||
assert.Equal(t, out1, out2, "two builds with same input should produce byte-identical output")
|
||||
}
|
||||
|
||||
func TestDeriveSeedUUID(t *testing.T) {
|
||||
// Use a small iteration count for testing (production uses 1B)
|
||||
uuid1 := deriveSeedUUID("test-seed-value", 1000)
|
||||
uuid2 := deriveSeedUUID("test-seed-value", 1000)
|
||||
assert.Equal(t, uuid1, uuid2, "same seed should produce same UUID")
|
||||
assert.Len(t, uuid1, 16, "UUID should be 16 bytes")
|
||||
|
||||
uuid3 := deriveSeedUUID("different-seed", 1000)
|
||||
assert.NotEqual(t, uuid1, uuid3, "different seeds should produce different UUIDs")
|
||||
}
|
||||
|
||||
func TestBuilderBuildEmpty(t *testing.T) {
|
||||
b := NewBuilder()
|
||||
|
||||
|
||||
@ -47,6 +47,7 @@ type ScannerOptions struct {
|
||||
FollowSymLinks bool // Resolve symlinks instead of skipping them
|
||||
Fs afero.Fs // Filesystem to use, defaults to OsFs if nil
|
||||
SigningOptions *SigningOptions // GPG signing options (nil = no signing)
|
||||
Seed string // If set, derive a deterministic UUID from this seed
|
||||
}
|
||||
|
||||
// FileEntry represents a file that has been enumerated.
|
||||
@ -276,6 +277,9 @@ func (s *Scanner) ToManifest(ctx context.Context, w io.Writer, progress chan<- S
|
||||
if s.options.SigningOptions != nil {
|
||||
builder.SetSigningOptions(s.options.SigningOptions)
|
||||
}
|
||||
if s.options.Seed != "" {
|
||||
builder.SetSeed(s.options.Seed)
|
||||
}
|
||||
|
||||
var scannedFiles FileCount
|
||||
var scannedBytes FileSize
|
||||
|
||||
Loading…
Reference in New Issue
Block a user