Report an unreadable blob once, without its bytes (closes #424)

blobgen.NewReader returns ErrNotAgeStream when age cannot open the
data, in place of age's error, which quotes the data's first bytes. A
failed read of the header is still returned as the read error, and a
wrong key as age.NoIdentityMatchError.

Under --skip-errors, restore reports a blob that could not be
downloaded once, with the number of files that need it. Those files
are counted in the final warning, not listed; each is logged at debug
level.

Model: opus-5-5

internal/blobgen/negative_test.go

@@ -2,8 +2,10 @@ package blobgen_test
 
 import (
 	"bytes"
+	"errors"
 	"fmt"
 	"testing"
+	"testing/iotest"
 
 	"filippo.io/age"
 	"github.com/stretchr/testify/assert"
@@ -120,6 +122,37 @@ func TestNewReaderTrailingAndGarbage(t *testing.T) {
 	})
 }
 
+// TestNewReaderGarbageErrorQuotesNoBytes checks that random bytes in
+// place of a blob fail with ErrNotAgeStream, and that the error carries
+// none of those bytes.
+func TestNewReaderGarbageErrorQuotesNoBytes(t *testing.T) {
+	t.Parallel()
+
+	id, _ := makeIdentity(t)
+	garbage := bytes.Repeat([]byte("garbage-bytes-"), 100)
+
+	_, err := blobgen.NewReader(bytes.NewReader(garbage), id)
+
+	require.ErrorIs(t, err, blobgen.ErrNotAgeStream)
+	assert.NotContains(t, err.Error(), "garbage-bytes-")
+}
+
+// errConnectionReset stands for a storage read that fails.
+var errConnectionReset = errors.New("connection reset")
+
+// TestNewReaderReadFailure checks that a failed read of the age header is
+// returned as that read error, not as ErrNotAgeStream.
+func TestNewReaderReadFailure(t *testing.T) {
+	t.Parallel()
+
+	id, _ := makeIdentity(t)
+
+	_, err := blobgen.NewReader(iotest.ErrReader(errConnectionReset), id)
+
+	require.ErrorIs(t, err, errConnectionReset)
+	assert.NotErrorIs(t, err, blobgen.ErrNotAgeStream)
+}
+
 // TestNewWriterInvalidLevel covers the rejected end of issue case 9: an
 // out-of-range compression level errors and writes nothing to the destination.
 func TestNewWriterInvalidLevel(t *testing.T) {

internal/blobgen/reader.go

@@ -11,6 +11,11 @@ import (
 	"github.com/klauspost/compress/zstd"
 )
 
+// ErrNotAgeStream is returned by NewReader when the data cannot be opened
+// as an age stream, for example because its header is malformed. It
+// replaces age's own error, which can quote the data's first bytes.
+var ErrNotAgeStream = errors.New("not a valid age stream")
+
 // Reader wraps decompression and decryption with SHA256 verification
 type Reader struct {
 	reader       io.Reader
@@ -24,11 +29,25 @@ type Reader struct {
 // NewReader creates a new Reader that decrypts, decompresses, and verifies
 // data. Every supplied identity is offered to age.Decrypt, so a blob
 // encrypted to any one of them can be read.
+//
+// A failure to read r is returned as that error, and a blob encrypted to
+// none of the identities as age.NoIdentityMatchError. Any other failure
+// to open the age stream is ErrNotAgeStream.
 func NewReader(r io.Reader, identities ...age.Identity) (*Reader, error) {
-	// Create decryption reader
-	decReader, err := age.Decrypt(r, identities...)
+	src := &readErrorRecorder{reader: r}
+
+	decReader, err := age.Decrypt(src, identities...)
 	if err != nil {
-		return nil, fmt.Errorf("creating decryption reader: %w", err)
+		var noMatch *age.NoIdentityMatchError
+
+		switch {
+		case src.err != nil:
+			return nil, fmt.Errorf("reading age header: %w", src.err)
+		case errors.As(err, &noMatch):
+			return nil, fmt.Errorf("creating decryption reader: %w", err)
+		default:
+			return nil, ErrNotAgeStream
+		}
 	}
 
 	// Create decompression reader
@@ -52,6 +71,23 @@ func NewReader(r io.Reader, identities ...age.Identity) (*Reader, error) {
 	}, nil
 }
 
+// readErrorRecorder passes reads through to reader and keeps the first
+// error other than io.EOF, so NewReader can tell a failed read from bad
+// data.
+type readErrorRecorder struct {
+	reader io.Reader
+	err    error
+}
+
+func (r *readErrorRecorder) Read(p []byte) (int, error) {
+	n, err := r.reader.Read(p)
+	if err != nil && !errors.Is(err, io.EOF) && r.err == nil {
+		r.err = err
+	}
+
+	return n, err
+}
+
 // Read implements io.Reader
 func (r *Reader) Read(p []byte) (int, error) {
 	n, err := r.teeReader.Read(p)