Files
vaultik/internal/blobgen/writer_test.go
T
sneak 9ec1c005df
check / check (pull_request) Successful in 1m22s
Remove the unused crypto path and write the blob-ID hash step once (closes #151)
Production encryption and decryption already run through blobgen; the
crypto package (Encryptor, Decryptor, UpdateRecipients, the fx Module)
and Vaultik.GetEncryptor/GetDecryptor had no production caller. Delete
crypto and route verify --deep through the same blobgen reader restore
uses: it parses the age key once and reads both the database (still
streamed to a temp file) and every blob through blobgen.NewReader.

The second, blob-ID hash step is now one exported function,
blobgen.DoubleSHA256, called by the three former copies. Writer.Sum256
(the double hash) becomes Writer.ContentID so it no longer shares the
name Sum256 with Reader.Sum256 (the single plaintext hash). CompressData
and CompressStream, unused outside tests, are deleted.

Delete the unused, never-adopted secret/config newtypes in internal/types
(the redacting AgeSecretKey and AWSSecretAccessKey plus AgeRecipient,
S3Endpoint, BucketName, S3Prefix, AWSRegion, AWSAccessKeyID). Delete the
uncalled CleanupIncompleteSnapshots (and deleteSnapshot, its only caller,
now dead) and correct ARCHITECTURE.md. The only multi-recipient test
moves to blobgen; the pre-#131 encrypted-bytes hash test is removed.

Model: opus-4-8
2026-09-22 11:17:33 +00:00

128 lines
4.1 KiB
Go

package blobgen_test
import (
"bytes"
"crypto/rand"
"crypto/sha256"
"encoding/hex"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/vaultik/internal/blobgen"
)
// TestWriterHashIsDoubleHash verifies that Writer.ContentID() returns
// the double hash SHA256(SHA256(plaintext)) for security.
// Double hashing prevents attackers from confirming existence of known content.
func TestWriterHashIsDoubleHash(t *testing.T) {
t.Parallel()
// Test data - random data that doesn't compress well
testData := make([]byte, 1024*1024) // 1MB
_, err := rand.Read(testData)
require.NoError(t, err)
// Test recipient (generated with age-keygen)
testRecipient := "age1cplgrwj77ta54dnmydvvmzn64ltk83ankxl5sww04mrtmu62kv3s89gmvv"
// Create a buffer to capture the encrypted output
var encryptedBuf bytes.Buffer
// Create blobgen writer
writer, err := blobgen.NewWriter(&encryptedBuf, 3, []string{testRecipient})
require.NoError(t, err)
// Write test data
n, err := writer.Write(testData)
require.NoError(t, err)
assert.Equal(t, len(testData), n)
// Close to flush all data
err = writer.Close()
require.NoError(t, err)
// Get the hash from the writer
writerHash := hex.EncodeToString(writer.ContentID())
// Calculate the expected double hash: SHA256(SHA256(plaintext))
firstHash := sha256.Sum256(testData)
secondHash := sha256.Sum256(firstHash[:])
expectedDoubleHash := hex.EncodeToString(secondHash[:])
// Also compute single hash to verify it's different
singleHashStr := hex.EncodeToString(firstHash[:])
t.Logf("Input size: %d bytes", len(testData))
t.Logf("Single hash (SHA256(data)): %s", singleHashStr)
t.Logf("Double hash (SHA256(SHA256(data))): %s", expectedDoubleHash)
t.Logf("Writer hash: %s", writerHash)
// The writer hash should match the double hash
assert.Equal(t, expectedDoubleHash, writerHash,
"Writer.ContentID() should return SHA256(SHA256(plaintext)) for security")
// Verify it's NOT the single hash (would leak information)
assert.NotEqual(t, singleHashStr, writerHash,
"Writer hash should not be single hash (would allow content confirmation attacks)")
}
// TestWriterDeterministicHash verifies that the same input always produces
// the same hash, even with non-deterministic encryption.
func TestWriterDeterministicHash(t *testing.T) {
t.Parallel()
// Test data
testData := []byte("Hello, World! This is test data for deterministic hashing.")
// Test recipient
testRecipient := "age1cplgrwj77ta54dnmydvvmzn64ltk83ankxl5sww04mrtmu62kv3s89gmvv"
// Create two writers and verify they produce the same hash
var buf1, buf2 bytes.Buffer
writer1, err := blobgen.NewWriter(&buf1, 3, []string{testRecipient})
require.NoError(t, err)
_, err = writer1.Write(testData)
require.NoError(t, err)
require.NoError(t, writer1.Close())
writer2, err := blobgen.NewWriter(&buf2, 3, []string{testRecipient})
require.NoError(t, err)
_, err = writer2.Write(testData)
require.NoError(t, err)
require.NoError(t, writer2.Close())
hash1 := hex.EncodeToString(writer1.ContentID())
hash2 := hex.EncodeToString(writer2.ContentID())
// Hashes should be identical (deterministic)
assert.Equal(t, hash1, hash2, "Same input should produce same hash")
// Encrypted outputs should be different (non-deterministic encryption)
assert.NotEqual(t, buf1.Bytes(), buf2.Bytes(),
"Encrypted outputs should differ due to non-deterministic encryption")
t.Logf("Hash 1: %s", hash1)
t.Logf("Hash 2: %s", hash2)
t.Logf("Encrypted size 1: %d bytes", buf1.Len())
t.Logf("Encrypted size 2: %d bytes", buf2.Len())
}
// TestNewWriterSecretKeyNotEchoed verifies that a secret key mistakenly passed
// as a recipient does not appear in the returned error. A recipient string can
// be sensitive, so the error must name only the position, not the value.
func TestNewWriterSecretKeyNotEchoed(t *testing.T) {
t.Parallel()
secretKey := "AGE-SECRET-KEY-19CR5YSFW59HM4TLD6GX" +
"VEDMZFTVVF7PPHKUT68TXSFPK7APHXA2QS2NJA5"
var buf bytes.Buffer
_, err := blobgen.NewWriter(&buf, 3, []string{secretKey})
require.Error(t, err)
assert.NotContains(t, err.Error(), secretKey,
"error must not echo the recipient value")
}