Merge branch 'next' into fix/issue-26

After reading file content, verify `totalRead == size` and return an error on mismatch.

Co-authored-by: clawbot <clawbot@openclaw>
Reviewed-on: #30
Co-authored-by: clawbot <clawbot@noreply.example.org>
Co-committed-by: clawbot <clawbot@noreply.example.org>

internal/cli/fetch.go

@@ -113,7 +113,7 @@ func (mfa *CLIApp) fetchManifestOperation(ctx *cli.Context) error {
 			return fmt.Errorf("invalid path in manifest: %w", err)
 		}
 
-		fileURL := baseURL.String() + encodeFilePath(f.Path)
+		fileURL := baseURL.String() + f.Path
 		log.Infof("fetching %s", f.Path)
 
 		if err := downloadFile(fileURL, localPath, f, progress); err != nil {
@@ -139,15 +139,6 @@ func (mfa *CLIApp) fetchManifestOperation(ctx *cli.Context) error {
 	return nil
 }
 
-// encodeFilePath URL-encodes each segment of a file path while preserving slashes.
-func encodeFilePath(p string) string {
-	segments := strings.Split(p, "/")
-	for i, seg := range segments {
-		segments[i] = url.PathEscape(seg)
-	}
-	return strings.Join(segments, "/")
-}
-
 // sanitizePath validates and sanitizes a file path from the manifest.
 // It prevents path traversal attacks and rejects unsafe paths.
 func sanitizePath(p string) (string, error) {

internal/cli/fetch_test.go

@@ -16,29 +16,6 @@ import (
 	"sneak.berlin/go/mfer/mfer"
 )
 
-func TestEncodeFilePath(t *testing.T) {
-	tests := []struct {
-		input    string
-		expected string
-	}{
-		{"file.txt", "file.txt"},
-		{"dir/file.txt", "dir/file.txt"},
-		{"my file.txt", "my%20file.txt"},
-		{"dir/my file.txt", "dir/my%20file.txt"},
-		{"file#1.txt", "file%231.txt"},
-		{"file?v=1.txt", "file%3Fv=1.txt"},
-		{"path/to/file with spaces.txt", "path/to/file%20with%20spaces.txt"},
-		{"100%done.txt", "100%25done.txt"},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.input, func(t *testing.T) {
-			result := encodeFilePath(tt.input)
-			assert.Equal(t, tt.expected, result)
-		})
-	}
-}
-
 func TestSanitizePath(t *testing.T) {
 	// Valid paths that should be accepted
 	validTests := []struct {

mfer/builder.go

@@ -3,13 +3,47 @@ package mfer
 import (
 	"crypto/sha256"
 	"errors"
+	"fmt"
 	"io"
+	"strings"
 	"sync"
 	"time"
+	"unicode/utf8"
 
 	"github.com/multiformats/go-multihash"
 )
 
+// ValidatePath checks that a file path conforms to manifest path invariants:
+//   - Must be valid UTF-8
+//   - Must use forward slashes only (no backslashes)
+//   - Must be relative (no leading /)
+//   - Must not contain ".." segments
+//   - Must not contain empty segments (no "//")
+//   - Must not be empty
+func ValidatePath(p string) error {
+	if p == "" {
+		return errors.New("path cannot be empty")
+	}
+	if !utf8.ValidString(p) {
+		return fmt.Errorf("path %q is not valid UTF-8", p)
+	}
+	if strings.ContainsRune(p, '\\') {
+		return fmt.Errorf("path %q contains backslash; use forward slashes only", p)
+	}
+	if strings.HasPrefix(p, "/") {
+		return fmt.Errorf("path %q is absolute; must be relative", p)
+	}
+	for _, seg := range strings.Split(p, "/") {
+		if seg == "" {
+			return fmt.Errorf("path %q contains empty segment", p)
+		}
+		if seg == ".." {
+			return fmt.Errorf("path %q contains '..' segment", p)
+		}
+	}
+	return nil
+}
+
 // RelFilePath represents a relative file path within a manifest.
 type RelFilePath string
 
@@ -74,6 +108,10 @@ func (b *Builder) AddFile(
 	reader io.Reader,
 	progress chan<- FileHashProgress,
 ) (FileSize, error) {
+	if err := ValidatePath(string(path)); err != nil {
+		return 0, err
+	}
+
 	// Create hash writer
 	h := sha256.New()
 
@@ -96,6 +134,11 @@ func (b *Builder) AddFile(
 		}
 	}
 
+	// Verify actual bytes read matches declared size
+	if totalRead != size {
+		return totalRead, fmt.Errorf("size mismatch for %q: declared %d bytes but read %d bytes", path, size, totalRead)
+	}
+
 	// Encode hash as multihash (SHA2-256)
 	mh, err := multihash.Encode(h.Sum(nil), multihash.SHA2_256)
 	if err != nil {
@@ -141,8 +184,8 @@ func (b *Builder) FileCount() int {
 // This is useful when the hash is already known (e.g., from an existing manifest).
 // Returns an error if path is empty, size is negative, or hash is nil/empty.
 func (b *Builder) AddFileWithHash(path RelFilePath, size FileSize, mtime ModTime, hash Multihash) error {
-	if path == "" {
+	if err := ValidatePath(string(path)); err != nil {
-		return errors.New("path cannot be empty")
+		return err
 	}
 	if size < 0 {
 		return errors.New("size cannot be negative")

mfer/mf.proto

@@ -46,6 +46,9 @@ message MFFileOuter {
 
 message MFFilePath {
     // required attributes:
+    // Path invariants: must be valid UTF-8, use forward slashes only,
+    // be relative (no leading /), contain no ".." segments, and no
+    // empty segments (no "//").
     string path = 1;
     int64 size = 2;