Name each prefix once in restore, verify and purge errors (closes #327)

A missing blob during restore, a failed shallow verify and an invalid
purge duration each printed their prefix twice. FetchBlob now returns
the storage error as is, since restore and deep verify name the blob
themselves; purge returns the duration parser's error unchanged; and a
failed shallow verify wraps "problems found in storage" instead of
"verification failed", which the command already prints. Deep verify
words a storage error other than not found as a blob it could not
check, and its log line no longer says S3.

Already fixed for #314: the
deep verify size message naming S3 and other errors called missing;
tests now check both.
Not tested: the log line.

Model: opus-5-5

internal/storage/url.go

@@ -30,6 +30,12 @@ var (
 		"storage URL must not carry credentials; " +
 			"set s3.access_key_id and s3.secret_access_key in the config instead")
 	ErrURLUnknownParam = errors.New("unknown query parameter in storage URL")
+	ErrURLBadQuery     = errors.New(
+		"storage URL query cannot be decoded; " +
+			"check it for a ; or a % not followed by two hex digits")
+	ErrRcloneRemoteParams = errors.New(
+		"rclone URL must not carry parameters in the remote name; " +
+			"set them on the remote with rclone config instead")
 )
 
 // URL represents a parsed storage URL.
@@ -90,8 +96,9 @@ func parseFileURL(rawPath string) (*URL, error) {
 }
 
 // parseS3URL parses an s3://bucket/prefix URL. It rejects credentials in
-// the userinfo and any query parameter other than endpoint, region and
-// ssl, so a credential-bearing URL is never stored or echoed.
+// the userinfo or in the endpoint parameter's userinfo, a query that
+// cannot be decoded, and any query parameter other than endpoint, region
+// and ssl, so a credential-bearing URL is never stored or echoed.
 func parseS3URL(rawURL string) (*URL, error) {
 	u, err := url.Parse(rawURL)
 	if err != nil {
@@ -107,13 +114,26 @@ func parseS3URL(rawURL string) (*URL, error) {
 		return nil, ErrMissingBucket
 	}
 
-	query := u.Query()
+	// u.Query() would silently drop a part it cannot decode, endpoint
+	// included. The decode error is not wrapped: it can quote the value.
+	query, err := url.ParseQuery(u.RawQuery)
+	if err != nil {
+		return nil, ErrURLBadQuery
+	}
 
 	err = rejectUnknownParams(query, "endpoint", "region", "ssl")
 	if err != nil {
 		return nil, err
 	}
 
+	// A host name never contains "@", so one in an endpoint, with or
+	// without a scheme, can only introduce userinfo.
+	for _, endpoint := range query["endpoint"] {
+		if strings.Contains(endpoint, "@") {
+			return nil, ErrURLCredentials
+		}
+	}
+
 	return &URL{
 		Scheme:   schemeS3,
 		Bucket:   bucket,
@@ -125,9 +145,23 @@ func parseS3URL(rawURL string) (*URL, error) {
 }
 
 // parseRcloneURL parses an rclone://remote/path URL. rclone:// takes no
-// query parameters, so credentials in the userinfo and any parameter at
+// query parameters, so credentials in the userinfo, parameters in the
+// remote name, a query that cannot be decoded and any query parameter at
 // all are rejected rather than silently ignored.
 func parseRcloneURL(rawURL string) (*URL, error) {
+	// The remote name runs up to the first "/", "?" or "#". It never
+	// contains a comma; one starts rclone's remote,param=value form,
+	// whose values can be credentials. This is checked before url.Parse,
+	// whose error for such a name can print part of it.
+	remote := strings.TrimPrefix(rawURL, "rclone://")
+	if end := strings.IndexAny(remote, "/?#"); end >= 0 {
+		remote = remote[:end]
+	}
+
+	if strings.Contains(remote, ",") {
+		return nil, ErrRcloneRemoteParams
+	}
+
 	u, err := url.Parse(rawURL)
 	if err != nil {
 		return nil, wrapParseError(err)
@@ -137,12 +171,19 @@ func parseRcloneURL(rawURL string) (*URL, error) {
 		return nil, ErrURLCredentials
 	}
 
-	remote := u.Host
+	remote = u.Host
 	if remote == "" {
 		return nil, ErrMissingRemote
 	}
 
-	err = rejectUnknownParams(u.Query())
+	// As in parseS3URL: u.Query() would drop a part it cannot decode, and
+	// the decode error can quote the value.
+	query, err := url.ParseQuery(u.RawQuery)
+	if err != nil {
+		return nil, ErrURLBadQuery
+	}
+
+	err = rejectUnknownParams(query)
 	if err != nil {
 		return nil, err
 	}

internal/storage/url_parse_test.go

@@ -150,6 +150,19 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
 			wantErr: storage.ErrURLCredentials,
 			secrets: []string{key, secret, "mybucket"},
 		},
+		{
+			name: "s3 userinfo in endpoint",
+			raw: "s3://mybucket?endpoint=https://" +
+				key + ":" + secret + "@minio.example.com",
+			wantErr: storage.ErrURLCredentials,
+			secrets: []string{key, secret},
+		},
+		{
+			name:    "s3 userinfo in endpoint without scheme",
+			raw:     "s3://mybucket?endpoint=" + key + ":" + secret + "@minio.example.com",
+			wantErr: storage.ErrURLCredentials,
+			secrets: []string{key, secret},
+		},
 		{
 			name:    "s3 unknown query param",
 			raw:     "s3://mybucket?access_key=" + key + "&secret=" + secret,
@@ -203,6 +216,112 @@ func TestParseStorageURLRejectsCredentials(t *testing.T) {
 	}
 }
 
+// TestParseStorageURLRejectsRcloneRemoteParams checks that an rclone
+// remote name carrying parameters (rclone's "remote,param=value" form,
+// which can hold a credential) is rejected without echoing the value,
+// including the URLs that url.Parse itself refuses.
+func TestParseStorageURLRejectsRcloneRemoteParams(t *testing.T) {
+	t.Parallel()
+
+	cases := []struct {
+		name    string
+		raw     string
+		secrets []string // must not appear in the error message
+	}{
+		{
+			name:    "configured remote",
+			raw:     "rclone://gdrive,client_secret=topsecret/backups",
+			secrets: []string{"topsecret"},
+		},
+		{
+			name:    "remote defined inline",
+			raw:     "rclone://:s3,access_key_id=KEY,secret_access_key=SECRET/bucket",
+			secrets: []string{"KEY", "SECRET"},
+		},
+		{
+			name:    "colon in a parameter value",
+			raw:     "rclone://gdrive,client_secret=ab:cd/backups",
+			secrets: []string{"cd"},
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := storage.ParseStorageURL(tc.raw)
+			if !errors.Is(err, storage.ErrRcloneRemoteParams) {
+				t.Fatalf("ParseStorageURL(%q) error = %v, want %v",
+					tc.raw, err, storage.ErrRcloneRemoteParams)
+			}
+
+			for _, secret := range tc.secrets {
+				if strings.Contains(err.Error(), secret) {
+					t.Errorf("error message leaked %q: %v", secret, err.Error())
+				}
+			}
+		})
+	}
+}
+
+// TestParseStorageURLRejectsUndecodableQuery checks that an s3 or rclone
+// URL whose query cannot be decoded is rejected, not read with that part
+// of the query left out, and that the error does not echo it.
+func TestParseStorageURLRejectsUndecodableQuery(t *testing.T) {
+	t.Parallel()
+
+	const (
+		key    = "AKIAKEY"
+		secret = "topsecret"
+	)
+
+	cases := []struct {
+		name string
+		raw  string
+	}{
+		{
+			name: "semicolon",
+			raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
+				"@minio.example.com:9000;region=us-east-1",
+		},
+		{
+			name: "bad percent escape",
+			raw: "s3://mybucket/prefix?endpoint=https://" + key + ":" + secret +
+				"%zz@minio.example.com:9000",
+		},
+		{
+			name: "rclone semicolon",
+			raw:  "rclone://gdrive/backups?token=" + secret + ";x=1",
+		},
+		{
+			name: "rclone bad percent escape",
+			raw:  "rclone://gdrive/backups?token=" + secret + "%zz",
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := storage.ParseStorageURL(tc.raw)
+			if err == nil {
+				t.Fatalf("ParseStorageURL(%q) returned no error", tc.raw)
+			}
+
+			if !errors.Is(err, storage.ErrURLBadQuery) {
+				t.Errorf("ParseStorageURL(%q) error = %v, want %v",
+					tc.raw, err, storage.ErrURLBadQuery)
+			}
+
+			for _, s := range []string{key, secret, "minio.example.com"} {
+				if strings.Contains(err.Error(), s) {
+					t.Errorf("error message leaked %q: %v", s, err.Error())
+				}
+			}
+		})
+	}
+}
+
 // TestParseStorageURLParseFailureHidesURL checks that when url.Parse
 // itself fails, the wrapped error carries only the inner cause, not the
 // *url.Error whose text embeds the raw (possibly credential-bearing) URL.

internal/vaultik/blob_fetch.go

@@ -104,7 +104,8 @@ func (v *Vaultik) FetchAndDecryptBlob(
 
 // FetchBlob downloads a blob and returns a reader for the encrypted data.
 // The reader is closed as soon as ctx is cancelled, which ends a read
-// blocked inside it.
+// blocked inside it. A storage error is returned as is: restore and deep
+// verify name the blob in their own errors.
 func (v *Vaultik) FetchBlob(
 	ctx context.Context, blobHash string,
 ) (io.ReadCloser, error) {
@@ -119,7 +120,7 @@ func (v *Vaultik) FetchBlob(
 
 	rc, err := v.Storage.Get(ctx, blobPath)
 	if err != nil {
-		return nil, fmt.Errorf("downloading blob %s: %w", shortHash(blobHash), err)
+		return nil, err
 	}
 
 	return newCloseOnCancelReader(ctx, rc), nil

internal/vaultik/deep_verify_test.go

@@ -6,6 +6,7 @@ import (
 	"crypto/rand"
 	"io"
 	"os"
+	"path"
 	"path/filepath"
 	"testing"
 
@@ -142,7 +143,8 @@ func TestDeepVerifyJSONCountsBlobs(t *testing.T) {
 
 // TestDeepVerifyJSONCountsWrongSizeBlob checks that under --deep --json a
 // blob of the wrong size is counted in mismatched and fails the run, and
-// that the check goes on past it to count a missing blob after it.
+// that the check goes on past it to count a missing blob after it. The
+// store is on disk, so the message must not call it S3.
 func TestDeepVerifyJSONCountsWrongSizeBlob(t *testing.T) {
 	log.Initialize(log.Config{})
 	t.Parallel()
@@ -168,11 +170,14 @@ func TestDeepVerifyJSONCountsWrongSizeBlob(t *testing.T) {
 	require.Equal(t, 1, got.Mismatched)
 	require.Equal(t, 1, got.Missing)
 	require.Zero(t, got.Verified)
+	require.Contains(t, got.ErrorMessage, "with the wrong size")
+	require.NotContains(t, got.ErrorMessage, "S3")
 }
 
 // TestDeepVerifyStopsOnBlobThatCannotBeChecked checks that a blob that is
 // present in storage but cannot be checked is not counted as missing:
-// deep verify stops and fails with the storage error.
+// deep verify stops and fails, saying it could not check the blob, with
+// the storage error.
 func TestDeepVerifyStopsOnBlobThatCannotBeChecked(t *testing.T) {
 	log.Initialize(log.Config{})
 	t.Parallel()
@@ -187,6 +192,8 @@ func TestDeepVerifyStopsOnBlobThatCannotBeChecked(t *testing.T) {
 	require.Error(t, err)
 	require.Equal(t, "failed", got.Status)
 	require.Zero(t, got.Missing)
+	require.Contains(t, got.ErrorMessage,
+		"could not check blob "+path.Base(keys[0]))
 	require.Contains(t, got.ErrorMessage, errStatDenied.Error())
 }
 

internal/vaultik/purge_per_name_test.go

@@ -281,7 +281,8 @@ func TestPurgeOlderThan_TooLargeDeletesNothing(t *testing.T) {
 		OlderThan: "1000y",
 		Force:     true,
 	})
-	require.Error(t, err)
+	require.EqualError(t, err,
+		`invalid duration: "1000y" is longer than about 292 years`)
 
 	err = v.PurgeSnapshotsWithOptions(&vaultik.SnapshotPurgeOptions{
 		OlderThan: "292y",

internal/vaultik/restore_skip_errors_test.go

@@ -231,7 +231,8 @@ func (f trailingByteFile) Close() error {
 }
 
 // TestRestoreMissingBlobAbortsWithoutSkipErrors checks that a deleted blob
-// still ends the restore with an error when SkipErrors is not set.
+// still ends the restore with an error when SkipErrors is not set, and
+// that the error names the blob once.
 func TestRestoreMissingBlobAbortsWithoutSkipErrors(t *testing.T) {
 	log.Initialize(log.Config{})
 	t.Parallel()
@@ -247,6 +248,8 @@ func TestRestoreMissingBlobAbortsWithoutSkipErrors(t *testing.T) {
 	})
 
 	require.ErrorIs(t, err, storage.ErrNotFound)
+	assert.Equal(t, 1, strings.Count(err.Error(), "downloading blob"),
+		err.Error())
 }
 
 // TestRestoreChunkInNoBlobAbortsWithoutSkipErrors checks that a chunk held

internal/vaultik/shallow_verify_test.go

@@ -27,7 +27,7 @@ import (
 // then grows one stored blob so its size no longer matches the manifest.
 // Shallow verify must then fail, count the grown blob as a size mismatch,
 // and drop it from the verified count rather than continuing to report it
-// as checked.
+// as checked, and its error must not repeat the cli layer's prefix.
 func TestShallowVerifyDetectsWrongBlobSize(t *testing.T) {
 	log.Initialize(log.Config{})
 	t.Parallel()
@@ -96,6 +96,12 @@ func TestShallowVerifyDetectsWrongBlobSize(t *testing.T) {
 	require.Equal(t, 1, bad.Mismatched)
 	require.Equal(t, healthy.BlobCount-1, bad.Verified,
 		"the wrong-sized blob must not be counted as verified")
+
+	// The cli layer prints this error after its own "Verification failed:".
+	err = newVerifier(io.Discard).VerifySnapshotWithOptions(
+		snapshotID, &vaultik.VerifyOptions{})
+	require.EqualError(t, err,
+		"problems found in storage: 1 blobs have the wrong size")
 }
 
 // TestShallowVerifyDetectsMissingDatabase backs up a real snapshot,

internal/vaultik/snapshot.go

@@ -23,6 +23,7 @@ var (
 	errSnapshotNotInConfig  = errors.New("snapshot not found in config")
 	errNoSnapshotsInConfig  = errors.New("no snapshots configured")
 	errSnapshotVerifyFailed = errors.New("verification failed")
+	errProblemsInStorage    = errors.New("problems found in storage")
 	errRemoveAllNeedsForce  = errors.New("--all requires --force")
 	errSnapshotNotFound     = errors.New("snapshot not found")
 	errSnapshotRemoveFailed = errors.New("snapshot(s) could not be removed")
@@ -612,7 +613,7 @@ func selectSnapshotsToPurge(
 	case opts.OlderThan != "":
 		duration, err := parseDuration(opts.OlderThan)
 		if err != nil {
-			return nil, fmt.Errorf("invalid duration: %w", err)
+			return nil, err
 		}
 
 		cutoff := time.Now().UTC().Add(-duration)
@@ -941,8 +942,10 @@ func (v *Vaultik) formatVerifyResult(
 		v.printVerifySummary(result, failure)
 	}
 
+	// Not errSnapshotVerifyFailed: the cli layer prints this after its own
+	// "Verification failed:".
 	if failure != "" {
-		return fmt.Errorf("%w: %s", errSnapshotVerifyFailed, failure)
+		return fmt.Errorf("%w: %s", errProblemsInStorage, failure)
 	}
 
 	return nil

internal/vaultik/verify.go

@@ -680,7 +680,7 @@ func (v *Vaultik) verifyManifestAgainstDatabase(
 func (v *Vaultik) verifyBlobExistenceFromDB(
 	blobs []snapshot.BlobInfo, result *VerifyResult,
 ) error {
-	log.Info("Verifying blob existence in S3", "blob_count", len(blobs))
+	log.Info("Verifying blob existence in storage", "blob_count", len(blobs))
 
 	for i, blob := range blobs {
 		// The hash is read from the snapshot database, which is not
@@ -700,7 +700,7 @@ func (v *Vaultik) verifyBlobExistenceFromDB(
 			result.Missing++
 			result.MissingSize += blob.CompressedSize
 		case err != nil:
-			return fmt.Errorf("checking blob %s in storage: %w",
+			return fmt.Errorf("could not check blob %s in storage: %w",
 				blob.Hash, err)
 		case stat.Size != blob.CompressedSize:
 			log.Warn("Blob has the wrong size in storage",