Specify and enforce path invariants in Builder

Add ValidatePath() enforcing: valid UTF-8, forward-slash only,
relative paths, no '..' segments, no empty segments. Called from
both AddFile and AddFileWithHash. Proto comments document the rules.

Closes #26
This commit is contained in:
clawbot 2026-02-08 16:12:06 -08:00
parent 4b80c0067b
commit 6948c65012
2 changed files with 43 additions and 2 deletions

View File

@ -3,13 +3,47 @@ package mfer
import ( import (
"crypto/sha256" "crypto/sha256"
"errors" "errors"
"fmt"
"io" "io"
"strings"
"sync" "sync"
"time" "time"
"unicode/utf8"
"github.com/multiformats/go-multihash" "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. // RelFilePath represents a relative file path within a manifest.
type RelFilePath string type RelFilePath string
@ -74,6 +108,10 @@ func (b *Builder) AddFile(
reader io.Reader, reader io.Reader,
progress chan<- FileHashProgress, progress chan<- FileHashProgress,
) (FileSize, error) { ) (FileSize, error) {
if err := ValidatePath(string(path)); err != nil {
return 0, err
}
// Create hash writer // Create hash writer
h := sha256.New() h := sha256.New()
@ -141,8 +179,8 @@ func (b *Builder) FileCount() int {
// This is useful when the hash is already known (e.g., from an existing manifest). // 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. // 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 { 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 { if size < 0 {
return errors.New("size cannot be negative") return errors.New("size cannot be negative")

View File

@ -46,6 +46,9 @@ message MFFileOuter {
message MFFilePath { message MFFilePath {
// required attributes: // 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; string path = 1;
int64 size = 2; int64 size = 2;