Require a SHA-256 hash in every manifest entry (closes #224)
check / check (push) Canceled after 0s

Loading accepted an entry whose hashes held no SHA-256 multihash, and
check and fetch, which compute only SHA-256, then reported the intact
file as a hash mismatch. Loading now refuses, naming the path, an entry
that does not list exactly one SHA-256 multihash; other hashes beside
it are allowed. AddFileWithHash accepts only a SHA-256 multihash, and
freshen carries an unchanged entry's SHA-256 hash over instead of its
first hash, found with SHA256Multihash, new in package mfer.
docs/FORMAT.md states the rule for writers and readers. Two loading
tests whose entries held an empty hash now give each entry a SHA-256
hash; the decoding-size test's path lengths change with it.

Model: opus-5-5
This commit was merged in pull request #228.
This commit is contained in:
2026-10-15 21:25:27 +02:00
parent 6a3f532c8d
commit 7d601a5902
7 changed files with 255 additions and 112 deletions
+90 -25
View File
@@ -5,8 +5,10 @@ import (
"bytes"
"context"
"crypto/sha256"
"crypto/sha512"
"fmt"
"strconv"
"strings"
"testing"
"time"
"uuid"
@@ -167,40 +169,94 @@ func TestDeserializeRefusesPathListedTwice(t *testing.T) {
}
}
// A manifest holding a file entry with no hash is refused as it is loaded,
// naming the path: there is nothing to check the file against.
func TestDeserializeRefusesEntryWithNoHash(t *testing.T) {
// A file entry must list exactly one SHA-256 hash, and may list hashes of
// other algorithms beside it. An entry with none, even one that lists a
// SHA-512 hash, is refused as it is loaded, and so is an entry with two;
// each refusal names the path. An entry listing a SHA-512 hash and then a
// SHA-256 one loads with both.
func TestDeserializeRequiresExactlyOneSHA256Hash(t *testing.T) {
t.Parallel()
id := uuid.NewV4()
inner, err := proto.Marshal(&MFFile{
Version: MFFile_VERSION_ONE,
Files: []*MFFilePath{{Path: "x", Size: 1}},
Uuid: id[:],
})
sha256Hash, err := multihash.Encode(make([]byte, sha256.Size), multihash.SHA2_256)
require.NoError(t, err)
_, err = NewManifestFromReader(bytes.NewReader(wrapInner(t, id, inner)))
require.ErrorIs(t, err, errEntryMissingHash)
require.EqualError(t, err, `file entry has no hash: "x"`)
otherSHA256Hash, err := multihash.Encode(
bytes.Repeat([]byte{1}, sha256.Size), multihash.SHA2_256)
require.NoError(t, err)
sha512Hash, err := multihash.Encode(make([]byte, sha512.Size), multihash.SHA2_512)
require.NoError(t, err)
tests := []struct {
name string
hashes [][]byte
want error // nil for an entry that loads
}{
{"no hash", nil, errEntryMissingHash},
{"SHA-512 hash only", [][]byte{sha512Hash}, errEntryMissingHash},
{
"two SHA-256 hashes",
[][]byte{sha256Hash, otherSHA256Hash},
errEntryExtraSHA256Hash,
},
{"SHA-512 hash then SHA-256 hash", [][]byte{sha512Hash, sha256Hash}, nil},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
entry := &MFFilePath{Path: "x", Size: 1}
for _, h := range tt.hashes {
entry.Hashes = append(entry.Hashes, &MFFileChecksum{MultiHash: h})
}
id := uuid.NewV4()
inner, err := proto.Marshal(&MFFile{
Version: MFFile_VERSION_ONE,
Files: []*MFFilePath{entry},
Uuid: id[:],
})
require.NoError(t, err)
m, err := NewManifestFromReader(bytes.NewReader(wrapInner(t, id, inner)))
if tt.want == nil {
require.NoError(t, err)
require.Len(t, m.Files(), 1)
assert.Len(t, m.Files()[0].GetHashes(), len(tt.hashes))
return
}
require.ErrorIs(t, err, tt.want)
assert.Contains(t, err.Error(), `"x"`)
})
}
}
// Entries of a path, an empty hash, an empty MIME type and empty modification
// and change times are counted at 432 bytes each (176 + 112 + 16 + 64 + 64)
// and take 16 bytes plus the path to encode. A 37-character path makes that
// 53 bytes, about 8.2 times: refused, and leaving any one of the five
// uncounted, even the MIME type, brings it under 8. A 39-character path makes
// it 55 bytes, about 7.9 times: loaded. Each entry's path is its number,
// padded with zeros to that length, since a manifest lists a path only once.
// Entries of a path, a SHA-256 hash, an empty MIME type and empty
// modification and change times are counted at 432 bytes each (176 + 112 +
// 16 + 64 + 64) and take 52 bytes plus the path to encode. A one-character
// path makes that 53 bytes, about 8.2 times: refused, and leaving any one of
// the five uncounted, even the MIME type, brings it under 8. A two-character
// path makes it 54 bytes, 8 times exactly: loaded. There is one entry for
// each base-36 digit, and each entry's path is its number in base 36, padded
// with zeros to that length, since a manifest lists a path only once.
func TestDeserializeRefusesEntriesThatDecodeTooLarge(t *testing.T) {
t.Parallel()
hash, err := multihash.Encode(make([]byte, sha256.Size), multihash.SHA2_256)
require.NoError(t, err)
checksum, err := proto.Marshal(&MFFileChecksum{MultiHash: hash})
require.NoError(t, err)
tests := []struct {
pathLen int
refused bool
}{
{37, true},
{39, false},
{1, true},
{2, false},
}
for _, tt := range tests {
@@ -213,11 +269,14 @@ func TestDeserializeRefusesEntriesThatDecodeTooLarge(t *testing.T) {
inner = protowire.AppendTag(inner, 102, protowire.BytesType) // MFFile.uuid
inner = protowire.AppendBytes(inner, id[:])
for i := range 1000 {
for i := range 36 {
path := strconv.FormatInt(int64(i), 36)
path = strings.Repeat("0", tt.pathLen-len(path)) + path
entry := protowire.AppendTag(nil, 1, protowire.BytesType) // MFFilePath.path
entry = protowire.AppendString(entry, fmt.Sprintf("%0*d", tt.pathLen, i))
entry = protowire.AppendString(entry, path)
entry = protowire.AppendTag(entry, 3, protowire.BytesType) // MFFilePath.hashes
entry = protowire.AppendBytes(entry, nil)
entry = protowire.AppendBytes(entry, checksum)
entry = protowire.AppendTag(entry, 301, protowire.BytesType) // MFFilePath.mimeType
entry = protowire.AppendBytes(entry, nil)
entry = protowire.AppendTag(entry, 302, protowire.BytesType) // MFFilePath.mtime
@@ -247,10 +306,16 @@ func TestDeserializeDropsUnknownFields(t *testing.T) {
unknown := protowire.AppendTag(nil, 99, protowire.BytesType) // in no message
unknown = protowire.AppendBytes(unknown, []byte("not known"))
hash, err := multihash.Encode(make([]byte, sha256.Size), multihash.SHA2_256)
require.NoError(t, err)
checksum, err := proto.Marshal(&MFFileChecksum{MultiHash: hash})
require.NoError(t, err)
entry := protowire.AppendTag(nil, 1, protowire.BytesType) // MFFilePath.path
entry = protowire.AppendString(entry, "a")
entry = protowire.AppendTag(entry, 3, protowire.BytesType) // MFFilePath.hashes
entry = protowire.AppendBytes(entry, nil)
entry = protowire.AppendBytes(entry, checksum)
entry = append(entry, unknown...)
id := uuid.NewV4()