Refuse a path listed twice in a manifest (closes #170)

gen given arguments whose files share a path, such as gen a b with a.txt
in both, or gen . ., now fails while listing the files, before hashing
any, naming the path and both files. Builder.AddFile and
Builder.AddFileWithHash refuse a path already added. Loading refuses a
manifest that lists a path twice, compared byte for byte; fetch keeps
its own letter-case check. The Path Rules in docs/FORMAT.md say each
path appears at most once. The decode-size test listed one path 1000
times; each entry now has its own path of the same length.

Model: opus-5-5

mfer/deserialize_path_test.go

@@ -7,7 +7,6 @@ import (
 	"crypto/sha256"
 	"fmt"
 	"strconv"
-	"strings"
 	"testing"
 	"time"
 	"uuid"
@@ -118,12 +117,61 @@ func TestDeserializeRejectsInvalidEntryPaths(t *testing.T) {
 	}
 }
 
+// A manifest that lists a path twice is refused as it is loaded, naming the
+// path. Paths are compared byte for byte: two that differ only in letter case
+// load, and fetch refuses those itself. Each entry has a hash, as entries mfer
+// writes do; entries of a path alone would take too much memory to decode.
+func TestDeserializeRefusesPathListedTwice(t *testing.T) {
+	t.Parallel()
+
+	hash, err := multihash.Encode(make([]byte, sha256.Size), multihash.SHA2_256)
+	require.NoError(t, err)
+
+	tests := []struct {
+		name    string
+		paths   []string
+		refused bool
+	}{
+		{"same path twice", []string{"dir/a.txt", "other.txt", "dir/a.txt"}, true},
+		{"paths differing in letter case", []string{"dir/b.txt", "dir/B.txt"}, false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			id := uuid.NewV4()
+			inner := &MFFile{Version: MFFile_VERSION_ONE, Uuid: id[:]}
+
+			for _, p := range tt.paths {
+				inner.Files = append(inner.Files, &MFFilePath{
+					Path:   p,
+					Hashes: []*MFFileChecksum{{MultiHash: hash}},
+				})
+			}
+
+			innerData, err := proto.Marshal(inner)
+			require.NoError(t, err)
+
+			m, err := NewManifestFromReader(bytes.NewReader(wrapInner(t, id, innerData)))
+			if tt.refused {
+				require.ErrorIs(t, err, errDuplicatePath)
+				require.EqualError(t, err, `duplicate path "dir/a.txt"`)
+			} else {
+				require.NoError(t, err)
+				assert.Len(t, m.Files(), len(tt.paths))
+			}
+		})
+	}
+}
+
 // 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.
+// 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.
 func TestDeserializeRefusesEntriesThatDecodeTooLarge(t *testing.T) {
 	t.Parallel()
 
@@ -139,24 +187,24 @@ func TestDeserializeRefusesEntriesThatDecodeTooLarge(t *testing.T) {
 		t.Run(strconv.Itoa(tt.pathLen), func(t *testing.T) {
 			t.Parallel()
 
-			entry := protowire.AppendTag(nil, 1, protowire.BytesType) // MFFilePath.path
-			entry = protowire.AppendString(entry, strings.Repeat("a", tt.pathLen))
-			entry = protowire.AppendTag(entry, 3, protowire.BytesType) // MFFilePath.hashes
-			entry = protowire.AppendBytes(entry, nil)
-			entry = protowire.AppendTag(entry, 301, protowire.BytesType) // MFFilePath.mimeType
-			entry = protowire.AppendBytes(entry, nil)
-			entry = protowire.AppendTag(entry, 302, protowire.BytesType) // MFFilePath.mtime
-			entry = protowire.AppendBytes(entry, nil)
-			entry = protowire.AppendTag(entry, 303, protowire.BytesType) // MFFilePath.ctime
-			entry = protowire.AppendBytes(entry, nil)
-
 			id := uuid.NewV4()
 			inner := protowire.AppendTag(nil, 100, protowire.VarintType) // MFFile.version
 			inner = protowire.AppendVarint(inner, uint64(MFFile_VERSION_ONE))
 			inner = protowire.AppendTag(inner, 102, protowire.BytesType) // MFFile.uuid
 			inner = protowire.AppendBytes(inner, id[:])
 
-			for range 1000 {
+			for i := range 1000 {
+				entry := protowire.AppendTag(nil, 1, protowire.BytesType) // MFFilePath.path
+				entry = protowire.AppendString(entry, fmt.Sprintf("%0*d", tt.pathLen, i))
+				entry = protowire.AppendTag(entry, 3, protowire.BytesType) // MFFilePath.hashes
+				entry = protowire.AppendBytes(entry, nil)
+				entry = protowire.AppendTag(entry, 301, protowire.BytesType) // MFFilePath.mimeType
+				entry = protowire.AppendBytes(entry, nil)
+				entry = protowire.AppendTag(entry, 302, protowire.BytesType) // MFFilePath.mtime
+				entry = protowire.AppendBytes(entry, nil)
+				entry = protowire.AppendTag(entry, 303, protowire.BytesType) // MFFilePath.ctime
+				entry = protowire.AppendBytes(entry, nil)
+
 				inner = protowire.AppendTag(inner, 101, protowire.BytesType) // MFFile.files
 				inner = protowire.AppendBytes(inner, entry)
 			}