Require a SHA-256 hash in every manifest entry (closes #224)

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

docs/FORMAT.md

@@ -80,15 +80,15 @@ After decompressing `innerMessage`, the result is a serialized `MFFile`
 
 Each file entry contains:
 
-| Field      | Number | Type                      | Description                                                   |
-| ---------- | ------ | ------------------------- | ------------------------------------------------------------- |
-| `path`     | 1      | string                    | Relative file path (see Path Rules)                           |
-| `size`     | 2      | int64                     | File size in bytes                                            |
-| `hashes`   | 3      | repeated `MFFileChecksum` | At least one hash required; readers reject an entry with none |
-| `mimeType` | 301    | string (optional)         | MIME type                                                     |
-| `mtime`    | 302    | Timestamp (optional)      | Modification time                                             |
-| `ctime`    | 303    | Timestamp (optional)      | Change time (inode metadata change)                           |
-| `mode`     | 304    | uint32                    | Permission bits (see File Mode)                               |
+| Field      | Number | Type                      | Description                                                  |
+| ---------- | ------ | ------------------------- | ------------------------------------------------------------ |
+| `path`     | 1      | string                    | Relative file path (see Path Rules)                          |
+| `size`     | 2      | int64                     | File size in bytes                                           |
+| `hashes`   | 3      | repeated `MFFileChecksum` | Must include exactly one SHA-256 multihash (see Hash Format) |
+| `mimeType` | 301    | string (optional)         | MIME type                                                    |
+| `mtime`    | 302    | Timestamp (optional)      | Modification time                                            |
+| `ctime`    | 303    | Timestamp (optional)      | Change time (inode metadata change)                          |
+| `mode`     | 304    | uint32                    | Permission bits (see File Mode)                              |
 
 ## File Mode
 
@@ -133,8 +133,16 @@ Each checksum is a single `bytes multiHash` field containing a
 self-describing: the encoded bytes include a varint algorithm identifier
 followed by a varint digest length followed by the digest itself.
 
-The 1.0 implementation writes SHA-256 multihashes (`0x12` algorithm code).
-Implementations must be able to verify SHA-256 multihashes at minimum.
+A writer must give every file entry exactly one SHA-256 multihash of the file's
+content: the algorithm code `0x12`, the digest length `0x20` and the 32 bytes of
+the digest. It may list multihashes of other algorithms beside it. A reader must
+refuse a manifest with an entry that has no SHA-256 multihash or more than one,
+whatever other hashes the entry lists. A verifier then needs only SHA-256,
+checking each file against its entry's SHA-256 multihash; it may ignore the
+other hashes.
+
+The reference implementation writes one hash for each entry, the SHA-256
+multihash, and its `check` and `fetch` compute only SHA-256.
 
 ## Signature Scheme
 
@@ -212,10 +220,11 @@ compresses the same inner message to the same bytes:
 - Each entry holds only `path`, `size`, `hashes` with exactly one hash, `mtime`
   and `mode`. The hash is the SHA-256 multihash of the file's content, except
   that `freshen` reads only the files that are new or whose size, `mtime` or
-  `mode` changed, and for every other file carries the first hash of its
-  existing entry over unchanged. `mtime` is the file's modification time as the
-  file system gives it, to the nanosecond, and `mode` is `0000` unless `gen` or
-  `freshen` is given `--include-permissions`.
+  `mode` changed, and for every other file carries the SHA-256 multihash of its
+  existing entry over unchanged, leaving out any other hash the entry lists.
+  `mtime` is the file's modification time as the file system gives it, to the
+  nanosecond, and `mode` is `0000` unless `gen` or `freshen` is given
+  `--include-permissions`.
 - `createdAt` is left out unless `gen` or `freshen` is given
   `--include-timestamps`. Then it holds the time the run started building the
   manifest, to the nanosecond, so it differs on every run.

internal/cli/freshen.go

@@ -33,9 +33,9 @@ var (
 	// modification time where one is required to carry it forward unchanged.
 	errEntryMissingMtime = errors.New("manifest entry has no mtime")
 
-	// errEntryMissingHash indicates a manifest entry that carries no hash
-	// to carry forward.
-	errEntryMissingHash = errors.New("manifest entry has no hash")
+	// errEntryMissingHash indicates a manifest entry that carries no
+	// SHA-256 hash to carry forward.
+	errEntryMissingHash = errors.New("manifest entry has no SHA-256 hash")
 )
 
 // errSignKeyNeeded indicates a signed manifest given to freshen with no
@@ -699,26 +699,26 @@ func addFileToBuilder(
 // Entries reach this path only when recordEntry classified them as
 // unchanged, which requires a recorded mtime, so an absent mtime here is
 // an error rather than something to paper over with the Unix epoch.
-// Loading refuses an entry with no hash; one that got here anyway is an
-// error too, not a file to leave out of the manifest.
+// Only the entry's SHA-256 hash is carried over, wherever the entry lists
+// it, since check and fetch compare with no other. Loading refuses an
+// entry with no SHA-256 hash; one that got here anyway is an error too,
+// not a file to leave out of the manifest.
 func addExistingToBuilder(b *mfer.Builder, entry *mfer.MFFilePath) error {
 	mtime, ok := entryMtime(entry)
 	if !ok {
 		return fmt.Errorf("%w: %s", errEntryMissingMtime, entry.GetPath())
 	}
 
-	if len(entry.GetHashes()) == 0 {
+	hash := mfer.SHA256Multihash(entry)
+	if hash == nil {
 		return fmt.Errorf("%w: %s", errEntryMissingHash, entry.GetPath())
 	}
 
 	err := b.AddFileWithHash(mfer.RelFilePath(entry.GetPath()),
 		mfer.FileSize(entry.GetSize()), mfer.ModTime(mtime),
-		fs.FileMode(entry.GetMode()), entry.GetHashes()[0].GetMultiHash())
+		fs.FileMode(entry.GetMode()), hash)
 	if err != nil {
-		return fmt.Errorf(
-			"manifest entry %s: %w (regenerate the manifest with mfer generate)",
-			entry.GetPath(), err,
-		)
+		return fmt.Errorf("manifest entry %s: %w", entry.GetPath(), err)
 	}
 
 	return nil

internal/cli/freshen_test.go

@@ -2,7 +2,10 @@
 package cli
 
 import (
+	"bytes"
+	"context"
 	"crypto/sha256"
+	"crypto/sha512"
 	"maps"
 	"os"
 	"path/filepath"
@@ -584,48 +587,76 @@ func TestFreshenAddExistingRejectsMissingMtime(t *testing.T) {
 	assert.Contains(t, err.Error(), "file1.txt")
 }
 
-// TestFreshenAddExistingRejectsMissingHash pins that an entry with no hash
-// is an error rather than a file left out of the rebuilt manifest.
+// TestFreshenAddExistingRejectsMissingHash pins that an entry with no
+// SHA-256 hash, whether it lists no hash or only a SHA-1 one, is an error
+// rather than a file left out of the rebuilt manifest.
 func TestFreshenAddExistingRejectsMissingHash(t *testing.T) {
 	t.Parallel()
 
-	b := mfer.NewBuilder()
-	entry := &mfer.MFFilePath{
-		Path:  "data.bin",
-		Size:  8,
-		Mtime: &mfer.Timestamp{Seconds: 1_700_000_000},
-	}
-
-	err := addExistingToBuilder(b, entry)
-	require.ErrorIs(t, err, errEntryMissingHash)
-	assert.Contains(t, err.Error(), "data.bin")
-	assert.Zero(t, b.FileCount())
-}
-
-// TestFreshenAddExistingRejectsShortHash pins that an existing manifest
-// entry whose hash the builder refuses is reported as a problem with the
-// manifest, with the command that fixes it.
-func TestFreshenAddExistingRejectsShortHash(t *testing.T) {
-	t.Parallel()
-
 	sha1Hash, err := multihash.Encode(make([]byte, 20), multihash.SHA1)
 	require.NoError(t, err)
 
+	tests := []struct {
+		name   string
+		hashes []*mfer.MFFileChecksum
+	}{
+		{"no hash", nil},
+		{"SHA-1 hash only", []*mfer.MFFileChecksum{{MultiHash: sha1Hash}}},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			b := mfer.NewBuilder()
+			entry := &mfer.MFFilePath{
+				Path:   "data.bin",
+				Size:   8,
+				Mtime:  &mfer.Timestamp{Seconds: 1_700_000_000},
+				Hashes: tt.hashes,
+			}
+
+			err := addExistingToBuilder(b, entry)
+			require.ErrorIs(t, err, errEntryMissingHash)
+			assert.Contains(t, err.Error(), "data.bin")
+			assert.Zero(t, b.FileCount())
+		})
+	}
+}
+
+// TestFreshenAddExistingKeepsSHA256Hash pins that an unchanged entry that
+// lists another hash before its SHA-256 hash is carried over with the
+// SHA-256 hash, the one check and fetch compare with, and nothing else.
+func TestFreshenAddExistingKeepsSHA256Hash(t *testing.T) {
+	t.Parallel()
+
+	sha512Hash, err := multihash.Encode(make([]byte, sha512.Size), multihash.SHA2_512)
+	require.NoError(t, err)
+
+	sha256Hash, err := multihash.Encode(make([]byte, sha256.Size), multihash.SHA2_256)
+	require.NoError(t, err)
+
 	b := mfer.NewBuilder()
 	entry := &mfer.MFFilePath{
-		Path:  "old.txt",
-		Size:  8,
+		Path:  "kept.txt",
+		Size:  6,
 		Mtime: &mfer.Timestamp{Seconds: 1_700_000_000},
 		Hashes: []*mfer.MFFileChecksum{
-			{MultiHash: sha1Hash},
+			{MultiHash: sha512Hash},
+			{MultiHash: sha256Hash},
 		},
 	}
 
-	err = addExistingToBuilder(b, entry)
-	require.Error(t, err)
-	assert.Contains(t, err.Error(), "manifest entry old.txt")
-	assert.Contains(t, err.Error(), "mfer generate")
-	assert.Zero(t, b.FileCount())
+	require.NoError(t, addExistingToBuilder(b, entry))
+
+	var buf bytes.Buffer
+	require.NoError(t, b.Build(context.Background(), &buf))
+
+	m, err := mfer.NewManifestFromReader(&buf)
+	require.NoError(t, err)
+	require.Len(t, m.Files(), 1)
+	require.Len(t, m.Files()[0].GetHashes(), 1)
+	assert.Equal(t, sha256Hash, m.Files()[0].GetHashes()[0].GetMultiHash())
 }
 
 // TestEntryMtime pins the presence semantics the callers depend on.

mfer/builder.go

@@ -37,8 +37,7 @@ var (
 	errPathDot          = errors.New("contains '.' segment")
 	errSizeMismatch     = errors.New("size mismatch")
 	errNegativeSize     = errors.New("size cannot be negative")
-	errHashNotMultihash = errors.New("hash is not a valid multihash")
-	errHashTooShort     = errors.New("hash digest is too short")
+	errHashNotSHA256    = errors.New("hash is not a SHA-256 multihash")
 	errDuplicatePath    = errors.New("duplicate path")
 )
 
@@ -113,6 +112,28 @@ func (m ModTime) Timestamp() *Timestamp {
 // Multihash represents a multihash-encoded file hash (typically SHA2-256).
 type Multihash []byte
 
+// SHA256Multihash returns the first of entry's hashes that is a SHA-256
+// multihash, or nil if none is. Loading a manifest refuses an entry that
+// does not list exactly one, so for a loaded entry it is the only one.
+func SHA256Multihash(entry *MFFilePath) Multihash {
+	for _, h := range entry.GetHashes() {
+		if isSHA256Multihash(h.GetMultiHash()) {
+			return h.GetMultiHash()
+		}
+	}
+
+	return nil
+}
+
+// isSHA256Multihash reports whether hash is a SHA-256 multihash: the
+// multihash code for SHA-256, then a 32-byte digest.
+func isSHA256Multihash(hash []byte) bool {
+	decoded, err := multihash.Decode(hash)
+
+	return err == nil && decoded.Code == multihash.SHA2_256 &&
+		len(decoded.Digest) == sha256.Size
+}
+
 // FileHashProgress reports progress during file hashing.
 type FileHashProgress struct {
 	BytesRead FileSize // Total bytes read so far for the current file
@@ -241,8 +262,7 @@ func (b *Builder) FileCount() int {
 // This is useful when the hash is already known (e.g., from an existing manifest).
 // Only mode's permission bits (mode.Perm()) are recorded; 0 records none.
 // Returns an error if path is invalid or already added, size is negative,
-// or hash is not a multihash with a digest of at least 32 bytes, as long
-// as SHA-256's.
+// or hash is not a SHA-256 multihash, the hash every entry must carry.
 func (b *Builder) AddFileWithHash(
 	path RelFilePath,
 	size FileSize,
@@ -259,19 +279,8 @@ func (b *Builder) AddFileWithHash(
 		return errNegativeSize
 	}
 
-	decoded, err := multihash.Decode(hash)
-	if err != nil {
-		return fmt.Errorf("%w: %w", errHashNotMultihash, err)
-	}
-
-	// The reader's limit on decoding cost (maxDecodedGrowth) assumes every
-	// hash is at least as long as a SHA-256 multihash, so a manifest of
-	// shorter ones could fail to load.
-	if len(decoded.Digest) < sha256.Size {
-		return fmt.Errorf(
-			"%w: %d bytes, at least %d needed",
-			errHashTooShort, len(decoded.Digest), sha256.Size,
-		)
+	if !isSHA256Multihash(hash) {
+		return errHashNotSHA256
 	}
 
 	entry := &MFFilePath{

mfer/builder_test.go

@@ -5,6 +5,7 @@ import (
 	"bytes"
 	"context"
 	"crypto/sha256"
+	"crypto/sha512"
 	"fmt"
 	"path/filepath"
 	"strings"
@@ -94,23 +95,25 @@ func TestBuilderAddFileWithHashRejectsBadHashes(t *testing.T) {
 	sha1Hash, err := multihash.Encode(make([]byte, 20), multihash.SHA1)
 	require.NoError(t, err)
 
+	sha512Hash, err := multihash.Encode(make([]byte, sha512.Size), multihash.SHA2_512)
+	require.NoError(t, err)
+
 	truncatedHash, err := multihash.Encode(make([]byte, sha256.Size-1), multihash.SHA2_256)
 	require.NoError(t, err)
 
 	tests := []struct {
 		name string
 		hash Multihash
-		want error
 	}{
-		{"nil hash", nil, errHashNotMultihash},
-		{"empty hash", []byte{}, errHashNotMultihash},
-		{"one-byte hash", []byte{0x12}, errHashNotMultihash},
+		{"nil hash", nil},
+		{"empty hash", []byte{}},
+		{"one-byte hash", []byte{0x12}},
 		// A SHA-256 code and 32-byte length, then only two bytes of digest.
-		{"malformed multihash", []byte{0x12, 0x20, 0x01, 0x02}, errHashNotMultihash},
-		// A valid multihash, but its 20-byte SHA-1 digest is too short.
-		{"SHA-1 multihash", sha1Hash, errHashTooShort},
-		// A valid multihash whose 31-byte digest is one byte short.
-		{"31-byte digest", truncatedHash, errHashTooShort},
+		{"malformed multihash", []byte{0x12, 0x20, 0x01, 0x02}},
+		{"SHA-1 multihash", sha1Hash},
+		{"SHA-512 multihash", sha512Hash},
+		// A SHA-256 code with a 31-byte digest.
+		{"31-byte digest", truncatedHash},
 	}
 
 	for _, tt := range tests {
@@ -119,7 +122,7 @@ func TestBuilderAddFileWithHashRejectsBadHashes(t *testing.T) {
 
 			b := NewBuilder()
 			err := b.AddFileWithHash("test.txt", 100, ModTime(time.Now()), 0, tt.hash)
-			require.ErrorIs(t, err, tt.want)
+			require.ErrorIs(t, err, errHashNotSHA256)
 			assert.Equal(t, 0, b.FileCount())
 		})
 	}

mfer/deserialize.go

@@ -27,7 +27,8 @@ var (
 	errUUIDMismatch         = errors.New("outer and inner UUID mismatch")
 	errInvalidFileFormat    = errors.New("invalid file format")
 	errInvalidManifestPath  = errors.New("invalid file entry")
-	errEntryMissingHash     = errors.New("file entry has no hash")
+	errEntryMissingHash     = errors.New("file entry has no SHA-256 hash")
+	errEntryExtraSHA256Hash = errors.New("file entry has more than one SHA-256 hash")
 	errDecodedTooLarge      = errors.New("too much memory needed")
 	errSignerNotSigningKey  = errors.New(
 		"signer is not the fingerprint of the key that made the signature")
@@ -236,6 +237,30 @@ func forEachBytesField(
 	return nil
 }
 
+// validateEntryHashes refuses, naming its path, an entry that does not list
+// exactly one SHA-256 multihash; hashes of other algorithms beside it are
+// allowed. check and fetch compute only SHA-256, so with none they would
+// have nothing to check the file against, and with two check would pass a
+// file that matches either.
+func validateEntryHashes(entry *MFFilePath) error {
+	sha256Hashes := 0
+
+	for _, h := range entry.GetHashes() {
+		if isSHA256Multihash(h.GetMultiHash()) {
+			sha256Hashes++
+		}
+	}
+
+	switch {
+	case sha256Hashes == 0:
+		return fmt.Errorf("%w: %q", errEntryMissingHash, entry.GetPath())
+	case sha256Hashes > 1:
+		return fmt.Errorf("%w: %q", errEntryExtraSHA256Hash, entry.GetPath())
+	default:
+		return nil
+	}
+}
+
 func (m *manifest) deserializeInner() error {
 	err := m.validateOuterHeader()
 	if err != nil {
@@ -294,8 +319,8 @@ func (m *manifest) deserializeInner() error {
 	// untrusted .mf. Reject loudly on the first offender rather than
 	// dropping entries, which would let a hostile manifest hide files from a
 	// check. A path listed twice is refused too: check would check the one
-	// file against both entries. So is an entry with no hash: there is
-	// nothing to check the file against.
+	// file against both entries. So is an entry that does not list exactly
+	// one SHA-256 hash.
 	seen := make(map[string]bool, len(m.pbInner.GetFiles()))
 
 	for _, f := range m.pbInner.GetFiles() {
@@ -304,8 +329,9 @@ func (m *manifest) deserializeInner() error {
 			return fmt.Errorf("%w: %w", errInvalidManifestPath, err)
 		}
 
-		if len(f.GetHashes()) == 0 {
-			return fmt.Errorf("%w: %q", errEntryMissingHash, f.GetPath())
+		err = validateEntryHashes(f)
+		if err != nil {
+			return err
 		}
 
 		if seen[f.GetPath()] {

mfer/deserialize_path_test.go

@@ -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()