internal/s3/client.go

@@ -18,6 +18,13 @@ import (
 	"github.com/aws/smithy-go/logging"
 )
 
+// ErrNoContinuationToken is returned by ListObjects and ListObjectsStream
+// when the server marks a page of a listing truncated but sends no
+// continuation token to fetch the rest with, as a server answering V2
+// listings V1-style does.
+var ErrNoContinuationToken = errors.New(
+	"server marked the listing truncated but sent no continuation token")
+
 // Client wraps the AWS S3 client for vaultik operations.
 // It provides a simplified interface for S3 operations with automatic
 // prefix handling and connection management. All operations are performed
@@ -214,7 +221,7 @@ func (c *Client) ListObjects(ctx context.Context, prefix string) ([]string, erro
 	})
 
 	for paginator.HasMorePages() {
-		page, err := paginator.NextPage(ctx)
+		page, err := nextListPage(ctx, paginator)
 		if err != nil {
 			return nil, err
 		}
@@ -235,6 +242,26 @@ func (c *Client) ListObjects(ctx context.Context, prefix string) ([]string, erro
 	return keys, nil
 }
 
+// nextListPage fetches the next page of a listing. The SDK paginator takes
+// a page marked truncated without a continuation token for the last page
+// and stops without an error, so such a page is ErrNoContinuationToken
+// here instead.
+func nextListPage(
+	ctx context.Context, paginator *s3.ListObjectsV2Paginator,
+) (*s3.ListObjectsV2Output, error) {
+	page, err := paginator.NextPage(ctx)
+	if err != nil {
+		return nil, err
+	}
+
+	truncated := aws.ToBool(page.IsTruncated)
+	if truncated && aws.ToString(page.NextContinuationToken) == "" {
+		return nil, ErrNoContinuationToken
+	}
+
+	return page, nil
+}
+
 // HeadObject checks if an object exists in S3.
 // Returns true if the object exists, false otherwise.
 // The key is automatically prefixed with the configured prefix.
@@ -300,7 +327,7 @@ func (c *Client) ListObjectsStream(
 		})
 
 		for paginator.HasMorePages() {
-			page, err := paginator.NextPage(ctx)
+			page, err := nextListPage(ctx, paginator)
 			if err != nil {
 				ch <- ObjectInfo{Err: err}
 

internal/storage/s3_test.go

@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"context"
 	"errors"
+	"io"
 	"net/http"
 	"net/http/httptest"
 	"slices"
@@ -22,13 +23,16 @@ import (
 // s3TestBucket is the bucket created for each in-process S3 server.
 const s3TestBucket = "test-bucket"
 
-// Credentials for the tests that build a storer from a config.Config. The
+// Credentials for the tests' S3 clients. The test servers accept any.
-// in-process S3 server accepts any.
 const (
 	s3TestAccessKeyID     = "key"
 	s3TestSecretAccessKey = "secret"
 )
 
+// s3TestRegion is the region of the S3 clients built here with
+// s3.NewClient. The test servers ignore it.
+const s3TestRegion = "us-east-1"
+
 // newS3Storer builds an s3:// backend backed by a fresh in-process
 // S3 server. It reuses the same in-memory S3 harness (gofakes3 + s3mem
 // over httptest) that internal/s3 and the not-found regression test use,
@@ -55,7 +59,7 @@ func newS3Storer(t *testing.T) storage.Storer {
 		Bucket:          s3TestBucket,
 		AccessKeyID:     "test",
 		SecretAccessKey: "test",
-		Region:          "us-east-1",
+		Region:          s3TestRegion,
 	})
 	if err != nil {
 		t.Fatalf("new client: %v", err)
@@ -93,6 +97,68 @@ func TestS3StorerMissingKeyMapsToErrNotFound(t *testing.T) {
 	}
 }
 
+// TestS3ListingCutShortIsAnError checks that List and ListStream fail on a
+// listing page marked truncated that carries no continuation token, as a
+// server answering V2 listings V1-style sends it. Taken as the last page,
+// it would hide every later key, and prune would treat the blobs of the
+// snapshots listed there as unreferenced.
+func TestS3ListingCutShortIsAnError(t *testing.T) {
+	t.Parallel()
+
+	const (
+		prefix        = "metadata/"
+		truncatedPage = `<?xml version="1.0" encoding="UTF-8"?>
+<ListBucketResult xmlns="http://s3.amazonaws.com/doc/2006-03-01/">
+  <Name>test-bucket</Name>
+  <Prefix>metadata/</Prefix>
+  <KeyCount>1</KeyCount>
+  <MaxKeys>1</MaxKeys>
+  <IsTruncated>true</IsTruncated>
+  <Contents>
+    <Key>metadata/snap/manifest.json.zst</Key>
+    <Size>8</Size>
+  </Contents>
+</ListBucketResult>`
+	)
+
+	srv := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, _ *http.Request) {
+			_, _ = io.WriteString(w, truncatedPage)
+		}))
+	t.Cleanup(srv.Close)
+
+	client, err := s3.NewClient(context.Background(), s3.Config{
+		Endpoint:        srv.URL,
+		Bucket:          s3TestBucket,
+		AccessKeyID:     s3TestAccessKeyID,
+		SecretAccessKey: s3TestSecretAccessKey,
+		Region:          s3TestRegion,
+	})
+	if err != nil {
+		t.Fatalf("new client: %v", err)
+	}
+
+	storer := storage.NewS3Storer(client)
+	ctx := context.Background()
+
+	keys, err := storer.List(ctx, prefix)
+	if !errors.Is(err, s3.ErrNoContinuationToken) {
+		t.Errorf("List = %q, %v; want ErrNoContinuationToken", keys, err)
+	}
+
+	var streamErr error
+
+	for obj := range storer.ListStream(ctx, prefix) {
+		if obj.Err != nil {
+			streamErr = obj.Err
+		}
+	}
+
+	if !errors.Is(streamErr, s3.ErrNoContinuationToken) {
+		t.Errorf("ListStream error = %v, want ErrNoContinuationToken", streamErr)
+	}
+}
+
 // TestS3URLPrefixKeyLayout pins the bucket keys an s3:// URL reads and
 // writes: the README's remote storage layout, with the prefix joined to
 // each key by one "/". s3://b/p and s3://b/p/ must be the same