Files
0dd474baab Delta sync: large files move as content-defined chunks (#161)
* feat(sync): delta sync — large files move as content-defined chunks

Files over 4 MiB push as chunks/<sha256> pieces plus a manifests/<sha256>
chunk list keyed by the whole file's hash, so Op.Blob alone locates it and
the journal format is byte-identical. A 1-byte edit to a 20 MiB file now
transfers ~2 MB instead of ~21 MB, both directions; chunk boundaries come
from a rolling hash (restic/chunker), so front insertions stay cheap.

The hub reassembles whole blobs on demand (spool, verify, backfill, serve),
which is the entire backward-compatibility story: old clients ask for
blobs/<sha> and never learn anything changed. Proven by e2e tests that build
the real pre-change binary from the pinned merge-base commit.

The push skip-proof is one Exists per chunk — three cheaper proxies (local
basis, manifest existence, stored manifest content) each proved false or
forgeable across four CTO review rounds and are recorded in the code
comment. Hub-side, manifests are write-once and must name only chunks the
store holds; reassembly is bounded at 256 MiB against amplified manifests.

Also: per-file sync ceiling 32 -> 100 MiB; import refuses archives whose
journals reference content they do not hold (--allow-incomplete overrides).

Deploy hubs before clients: old hubs refuse chunk keys (push degrades to
offline-retry), and old clients cap reads at 32 MiB so 32-100 MiB files
report "blob corrupt on remote" until the client upgrades.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R6nqxi5a9qcENmJvrgBJF7

* fix(test): fetch the pinned pre-delta commit on shallow CI clones

buildOldBinary archives the pinned merge-base sha, which a fetch-depth-1
actions/checkout does not have — all three old-binary e2e tests failed in
CI with exit 128 while passing on any full local clone. On archive failure,
fetch just that commit (--depth=1, one object; actions/checkout persists
credentials so the in-job fetch works) and retry. Verified against a real
GitHub shallow clone: archive fails, the single-sha fetch succeeds, archive
then yields the pre-delta tree.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R6nqxi5a9qcENmJvrgBJF7

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-08-13 07:18:37 -07:00

167 lines
4.4 KiB
Go

package main
import (
"archive/tar"
"bytes"
"compress/gzip"
"context"
"crypto/sha256"
"encoding/hex"
"io"
"strings"
"testing"
"time"
"github.com/runbear-io/beardrive/internal/remote"
)
func openFileBackend(t *testing.T) remote.Backend {
t.Helper()
be, err := remote.Open(context.Background(), "file://"+t.TempDir())
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { be.Close() })
return be
}
func put(t *testing.T, be remote.Backend, key, content string) {
t.Helper()
if err := be.Put(context.Background(), key, strings.NewReader(content), int64(len(content))); err != nil {
t.Fatalf("put %s: %v", key, err)
}
}
func blobKey(content string) string {
sum := sha256.Sum256([]byte(content))
return "blobs/" + hex.EncodeToString(sum[:])
}
func TestExportImportRoundTrip(t *testing.T) {
ctx := context.Background()
src := openFileBackend(t)
// A project as two devices left it: two journals, two blobs.
blobA, blobB := "hello from device one", "and from device two"
put(t, src, blobKey(blobA), blobA)
put(t, src, blobKey(blobB), blobB)
put(t, src, "journal/dev-1.jsonl", `{"path":"a.md"}`+"\n")
put(t, src, "journal/dev-2.jsonl", `{"path":"b.md"}`+"\n")
var buf bytes.Buffer
man := exportManifest{Project: "wiki", Remote: "https://old.example/p/p-00000000", ExportedAt: time.Now().UTC()}
blobs, journals, _, err := exportStore(ctx, src, &buf, man)
if err != nil {
t.Fatal(err)
}
if blobs != 2 || journals != 2 {
t.Fatalf("export counted %d blobs, %d journals; want 2, 2", blobs, journals)
}
// The manifest comes first and names the project.
gz, err := gzip.NewReader(bytes.NewReader(buf.Bytes()))
if err != nil {
t.Fatal(err)
}
tr := tar.NewReader(gz)
gotMan, first, err := readManifest(tr)
if err != nil {
t.Fatal(err)
}
if first != nil || gotMan.Project != "wiki" {
t.Fatalf("manifest = %+v (first=%v), want project wiki consumed first", gotMan, first)
}
dst := openFileBackend(t)
blobs, journals, _, err = importStore(ctx, dst, tr, first, false)
if err != nil {
t.Fatal(err)
}
if blobs != 2 || journals != 2 {
t.Fatalf("import counted %d blobs, %d journals; want 2, 2", blobs, journals)
}
// Every key round-trips byte-identical.
for _, prefix := range []string{"journal/", "blobs/"} {
objs, err := src.List(ctx, prefix)
if err != nil {
t.Fatal(err)
}
for _, o := range objs {
want := read(t, src, o.Key)
got := read(t, dst, o.Key)
if want != got {
t.Errorf("%s: imported %q, want %q", o.Key, got, want)
}
}
}
}
func TestImportRejectsCorruptBlob(t *testing.T) {
var buf bytes.Buffer
gz := gzip.NewWriter(&buf)
tw := tar.NewWriter(gz)
// Content that does not hash to its key.
writeTarFile(tw, blobKey("original"), []byte("tampered"))
writeTarFile(tw, "journal/dev-1.jsonl", []byte("{}\n"))
tw.Close()
gz.Close()
dst := openFileBackend(t)
if _, _, _, err := importStore(context.Background(), dst, openTar(t, buf.Bytes()), nil, false); err == nil || !strings.Contains(err.Error(), "corrupt") {
t.Fatalf("err = %v, want corrupt-archive error", err)
}
}
func TestImportRejectsForeignEntries(t *testing.T) {
var buf bytes.Buffer
gz := gzip.NewWriter(&buf)
tw := tar.NewWriter(gz)
writeTarFile(tw, "../../etc/passwd", []byte("nope"))
tw.Close()
gz.Close()
dst := openFileBackend(t)
if _, _, _, err := importStore(context.Background(), dst, openTar(t, buf.Bytes()), nil, false); err == nil || !strings.Contains(err.Error(), "unexpected entry") {
t.Fatalf("err = %v, want unexpected-entry error", err)
}
}
func TestImportRequiresJournals(t *testing.T) {
content := "just a blob"
var buf bytes.Buffer
gz := gzip.NewWriter(&buf)
tw := tar.NewWriter(gz)
writeTarFile(tw, blobKey(content), []byte(content))
tw.Close()
gz.Close()
dst := openFileBackend(t)
if _, _, _, err := importStore(context.Background(), dst, openTar(t, buf.Bytes()), nil, false); err == nil || !strings.Contains(err.Error(), "no journals") {
t.Fatalf("err = %v, want no-journals error", err)
}
}
func openTar(t *testing.T, b []byte) *tar.Reader {
t.Helper()
gz, err := gzip.NewReader(bytes.NewReader(b))
if err != nil {
t.Fatal(err)
}
return tar.NewReader(gz)
}
func read(t *testing.T, be remote.Backend, key string) string {
t.Helper()
rc, err := be.Get(context.Background(), key)
if err != nil {
t.Fatalf("get %s: %v", key, err)
}
defer rc.Close()
b, err := io.ReadAll(rc)
if err != nil {
t.Fatal(err)
}
return string(b)
}