Compare commits

..

3 Commits

Author SHA1 Message Date
clawbot
fa99bdc5ee reduce seed iterations to 150M (~5-10s on modern hardware)
1B iterations was too slow (30s+). Benchmarked on Apple Silicon:
- 150M iterations ≈ 6.3s
- Falls within the 5-10s target range
2026-02-08 17:10:04 -08:00
clawbot
b8506ad043 feat: add --seed flag for deterministic manifest UUID
Adds a --seed CLI flag to 'generate' that derives a deterministic UUID
from the seed value by hashing it 1,000,000,000 times with SHA-256.
This makes manifest generation fully reproducible when the same seed
and input files are provided.

- Builder.SetSeed(seed) method for programmatic use
- deriveSeedUUID() extracted for testability
- MFER_SEED env var also supported
- Test with reduced iteration count for speed
2026-02-08 17:10:04 -08:00
clawbot
ec3f6cb7c1 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
2026-02-08 17:10:04 -08:00
6 changed files with 10 additions and 92 deletions

View File

@ -113,7 +113,7 @@ func (mfa *CLIApp) fetchManifestOperation(ctx *cli.Context) error {
return fmt.Errorf("invalid path in manifest: %w", err) return fmt.Errorf("invalid path in manifest: %w", err)
} }
fileURL := baseURL.String() + encodeFilePath(f.Path) fileURL := baseURL.String() + f.Path
log.Infof("fetching %s", f.Path) log.Infof("fetching %s", f.Path)
if err := downloadFile(fileURL, localPath, f, progress); err != nil { if err := downloadFile(fileURL, localPath, f, progress); err != nil {
@ -139,15 +139,6 @@ func (mfa *CLIApp) fetchManifestOperation(ctx *cli.Context) error {
return nil return nil
} }
// encodeFilePath URL-encodes each segment of a file path while preserving slashes.
func encodeFilePath(p string) string {
segments := strings.Split(p, "/")
for i, seg := range segments {
segments[i] = url.PathEscape(seg)
}
return strings.Join(segments, "/")
}
// sanitizePath validates and sanitizes a file path from the manifest. // sanitizePath validates and sanitizes a file path from the manifest.
// It prevents path traversal attacks and rejects unsafe paths. // It prevents path traversal attacks and rejects unsafe paths.
func sanitizePath(p string) (string, error) { func sanitizePath(p string) (string, error) {

View File

@ -16,29 +16,6 @@ import (
"sneak.berlin/go/mfer/mfer" "sneak.berlin/go/mfer/mfer"
) )
func TestEncodeFilePath(t *testing.T) {
tests := []struct {
input string
expected string
}{
{"file.txt", "file.txt"},
{"dir/file.txt", "dir/file.txt"},
{"my file.txt", "my%20file.txt"},
{"dir/my file.txt", "dir/my%20file.txt"},
{"file#1.txt", "file%231.txt"},
{"file?v=1.txt", "file%3Fv=1.txt"},
{"path/to/file with spaces.txt", "path/to/file%20with%20spaces.txt"},
{"100%done.txt", "100%25done.txt"},
}
for _, tt := range tests {
t.Run(tt.input, func(t *testing.T) {
result := encodeFilePath(tt.input)
assert.Equal(t, tt.expected, result)
})
}
}
func TestSanitizePath(t *testing.T) { func TestSanitizePath(t *testing.T) {
// Valid paths that should be accepted // Valid paths that should be accepted
validTests := []struct { validTests := []struct {

View File

@ -92,29 +92,6 @@ func TestBuilderBuild(t *testing.T) {
assert.True(t, strings.HasPrefix(buf.String(), MAGIC)) assert.True(t, strings.HasPrefix(buf.String(), MAGIC))
} }
func TestNewTimestampFromTimeExtremeDate(t *testing.T) {
// Regression test: newTimestampFromTime used UnixNano() which panics
// for dates outside ~1678-2262. Now uses Nanosecond() which is safe.
tests := []struct {
name string
time time.Time
}{
{"zero time", time.Time{}},
{"year 1000", time.Date(1000, 1, 1, 0, 0, 0, 0, time.UTC)},
{"year 3000", time.Date(3000, 1, 1, 0, 0, 0, 123456789, time.UTC)},
{"unix epoch", time.Unix(0, 0)},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
// Should not panic
ts := newTimestampFromTime(tt.time)
assert.Equal(t, tt.time.Unix(), ts.Seconds)
assert.Equal(t, int32(tt.time.Nanosecond()), ts.Nanos)
})
}
}
func TestBuilderDeterministicOutput(t *testing.T) { func TestBuilderDeterministicOutput(t *testing.T) {
buildManifest := func() []byte { buildManifest := func() []byte {
b := NewBuilder() b := NewBuilder()

View File

@ -224,7 +224,12 @@ func (c *Checker) checkFile(entry *MFFilePath, checkedBytes *FileSize) Result {
// Check if file exists // Check if file exists
info, err := c.fs.Stat(absPath) info, err := c.fs.Stat(absPath)
if err != nil { if err != nil {
if errors.Is(err, os.ErrNotExist) || errors.Is(err, afero.ErrFileNotFound) { if errors.Is(err, afero.ErrFileNotFound) || errors.Is(err, errors.New("file does not exist")) {
return Result{Path: relPath, Status: StatusMissing, Message: "file not found"}
}
// Check for "file does not exist" style errors
exists, _ := afero.Exists(c.fs, absPath)
if !exists {
return Result{Path: relPath, Status: StatusMissing, Message: "file not found"} return Result{Path: relPath, Status: StatusMissing, Message: "file not found"}
} }
return Result{Path: relPath, Status: StatusError, Message: err.Error()} return Result{Path: relPath, Status: StatusError, Message: err.Error()}

View File

@ -381,39 +381,6 @@ func TestCheckSubdirectories(t *testing.T) {
assert.Equal(t, 3, okCount) assert.Equal(t, 3, okCount)
} }
func TestCheckMissingFileDetectedWithoutFallback(t *testing.T) {
// Regression test: errors.Is(err, errors.New("...")) never matches because
// errors.New creates a new value each time. The fix uses os.ErrNotExist instead.
fs := afero.NewMemMapFs()
files := map[string][]byte{
"exists.txt": []byte("here"),
"missing.txt": []byte("not on disk"),
}
createTestManifest(t, fs, "/manifest.mf", files)
// Only create one file on disk
createFilesOnDisk(t, fs, "/data", map[string][]byte{
"exists.txt": []byte("here"),
})
chk, err := NewChecker("/manifest.mf", "/data", fs)
require.NoError(t, err)
results := make(chan Result, 10)
err = chk.Check(context.Background(), results, nil)
require.NoError(t, err)
statusCounts := map[Status]int{}
for r := range results {
statusCounts[r.Status]++
if r.Status == StatusMissing {
assert.Equal(t, RelFilePath("missing.txt"), r.Path)
}
}
assert.Equal(t, 1, statusCounts[StatusOK], "one file should be OK")
assert.Equal(t, 1, statusCounts[StatusMissing], "one file should be MISSING")
assert.Equal(t, 0, statusCounts[StatusError], "no files should be ERROR")
}
func TestCheckEmptyManifest(t *testing.T) { func TestCheckEmptyManifest(t *testing.T) {
fs := afero.NewMemMapFs() fs := afero.NewMemMapFs()
// Create manifest with no files // Create manifest with no files

View File

@ -16,10 +16,11 @@ import (
const MAGIC string = "ZNAVSRFG" const MAGIC string = "ZNAVSRFG"
func newTimestampFromTime(t time.Time) *Timestamp { func newTimestampFromTime(t time.Time) *Timestamp {
return &Timestamp{ out := &Timestamp{
Seconds: t.Unix(), Seconds: t.Unix(),
Nanos: int32(t.Nanosecond()), Nanos: int32(t.UnixNano() - (t.Unix() * 1000000000)),
} }
return out
} }
func (m *manifest) generate() error { func (m *manifest) generate() error {