Files
vaultik/internal/blobgen/reader.go
T
sneak 03f126edc1
check / check (pull_request) Successful in 2m33s
Reject a metadata database truncated to the age header and nonce (closes #152)
An object holding exactly the age header plus its 16-byte nonce decrypts
without error: age.Decrypt succeeds, and on the first read the age stream's
io.ErrUnexpectedEOF is mapped by the zstd decoder to a clean io.EOF at frame
start. blobgen.Reader.Read then reported zero bytes and no error, so a
truncated stream was indistinguishable from a valid empty one. Blobs are
caught by the Close-time hash check, but the metadata database export was not:
restore built a fresh schema on the empty file and exited reporting success.

blobgen.Reader.Read now, on EOF, reads once more from the age reader and
surfaces io.ErrUnexpectedEOF unless that read is (0, io.EOF) — the state a
genuine end leaves behind, so an empty payload still round-trips to empty with
no error. downloadSnapshotDB additionally rejects a zero-length decrypted
database before OpenReadOnly applies a schema.

On next the decrypted-DB identity check already rejects an empty database, so
the restore-level test guards the required end-to-end property; the blobgen
tests are the ones that fail without the reader change.

Model: opus-4-8
2026-09-22 15:12:48 +00:00

97 lines
2.5 KiB
Go

package blobgen
import (
"crypto/sha256"
"errors"
"fmt"
"hash"
"io"
"filippo.io/age"
"github.com/klauspost/compress/zstd"
)
// Reader wraps decompression and decryption with SHA256 verification
type Reader struct {
reader io.Reader
decompressor *zstd.Decoder
decryptor io.Reader
hasher hash.Hash
teeReader io.Reader
bytesRead int64
}
// 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.
func NewReader(r io.Reader, identities ...age.Identity) (*Reader, error) {
// Create decryption reader
decReader, err := age.Decrypt(r, identities...)
if err != nil {
return nil, fmt.Errorf("creating decryption reader: %w", err)
}
// Create decompression reader
decompressor, err := zstd.NewReader(decReader)
if err != nil {
return nil, fmt.Errorf("creating decompression reader: %w", err)
}
// Create SHA256 hasher
hasher := sha256.New()
// Create tee reader that reads from decompressor and writes to hasher
teeReader := io.TeeReader(decompressor, hasher)
return &Reader{
reader: r,
decompressor: decompressor,
decryptor: decReader,
hasher: hasher,
teeReader: teeReader,
}, nil
}
// Read implements io.Reader
func (r *Reader) Read(p []byte) (int, error) {
n, err := r.teeReader.Read(p)
r.bytesRead += int64(n)
// When the ciphertext is cut right after the age header plus its
// 16-byte nonce, the age reader's first read fails with
// io.ErrUnexpectedEOF, and the zstd decoder maps that to a clean
// io.EOF at frame start. That makes a truncated stream look like a
// valid empty one. Distinguish the two: on EOF, read once more from
// the age reader. A genuine end leaves it at (0, io.EOF); a truncated
// stream leaves its stored io.ErrUnexpectedEOF, which we surface.
if errors.Is(err, io.EOF) {
var probe [1]byte
m, ageErr := r.decryptor.Read(probe[:])
if m != 0 || !errors.Is(ageErr, io.EOF) {
return n, io.ErrUnexpectedEOF
}
}
return n, err
}
// Close closes the decompressor
func (r *Reader) Close() error {
r.decompressor.Close()
return nil
}
// Sum256 returns the single SHA-256 of the plaintext read so far. This is the
// first hash only; the stored object name is its double hash, which callers
// obtain by passing this digest to DoubleSHA256.
func (r *Reader) Sum256() []byte {
return r.hasher.Sum(nil)
}
// BytesRead returns the number of uncompressed bytes read
func (r *Reader) BytesRead() int64 {
return r.bytesRead
}